| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #ifndef _NET_IPV6_H #define _NET_IPV6_H #include <linux/ipv6.h> #include <linux/hardirq.h> #include <linux/jhash.h> #include <linux/refcount.h> #include <linux/jump_label_ratelimit.h> #include <net/if_inet6.h> #include <net/flow.h> #include <net/flow_dissector.h> #include <net/inet_dscp.h> #include <net/snmp.h> #include <net/netns/hash.h> struct ip_tunnel_info; #define SIN6_LEN_RFC2133 24 #define IPV6_MAXPLEN 65535 /* * NextHeader field of IPv6 header */ #define NEXTHDR_HOP 0 /* Hop-by-hop option header. */ #define NEXTHDR_IPV4 4 /* IPv4 in IPv6 */ #define NEXTHDR_TCP 6 /* TCP segment. */ #define NEXTHDR_UDP 17 /* UDP message. */ #define NEXTHDR_IPV6 41 /* IPv6 in IPv6 */ #define NEXTHDR_ROUTING 43 /* Routing header. */ #define NEXTHDR_FRAGMENT 44 /* Fragmentation/reassembly header. */ #define NEXTHDR_GRE 47 /* GRE header. */ #define NEXTHDR_ESP 50 /* Encapsulating security payload. */ #define NEXTHDR_AUTH 51 /* Authentication header. */ #define NEXTHDR_ICMP 58 /* ICMP for IPv6. */ #define NEXTHDR_NONE 59 /* No next header */ #define NEXTHDR_DEST 60 /* Destination options header. */ #define NEXTHDR_SCTP 132 /* SCTP message. */ #define NEXTHDR_MOBILITY 135 /* Mobility header. */ #define NEXTHDR_MAX 255 #define IPV6_DEFAULT_HOPLIMIT 64 #define IPV6_DEFAULT_MCASTHOPS 1 /* Limits on Hop-by-Hop and Destination options. * * Per RFC8200 there is no limit on the maximum number or lengths of options in * Hop-by-Hop or Destination options other then the packet must fit in an MTU. * We allow configurable limits in order to mitigate potential denial of * service attacks. * * There are three limits that may be set: * - Limit the number of options in a Hop-by-Hop or Destination options * extension header * - Limit the byte length of a Hop-by-Hop or Destination options extension * header * - Disallow unknown options * * The limits are expressed in corresponding sysctls: * * ipv6.sysctl.max_dst_opts_cnt * ipv6.sysctl.max_hbh_opts_cnt * ipv6.sysctl.max_dst_opts_len * ipv6.sysctl.max_hbh_opts_len * * max_*_opts_cnt is the number of TLVs that are allowed for Destination * options or Hop-by-Hop options. If the number is less than zero then unknown * TLVs are disallowed and the number of known options that are allowed is the * absolute value. Setting the value to INT_MAX indicates no limit. * * max_*_opts_len is the length limit in bytes of a Destination or * Hop-by-Hop options extension header. Setting the value to INT_MAX * indicates no length limit. * * If a limit is exceeded when processing an extension header the packet is * silently discarded. */ /* Default limits for Hop-by-Hop and Destination options */ #define IP6_DEFAULT_MAX_DST_OPTS_CNT 8 #define IP6_DEFAULT_MAX_HBH_OPTS_CNT 8 #define IP6_DEFAULT_MAX_DST_OPTS_LEN INT_MAX /* No limit */ #define IP6_DEFAULT_MAX_HBH_OPTS_LEN INT_MAX /* No limit */ /* * Addr type * * type - unicast | multicast * scope - local | site | global * v4 - compat * v4mapped * any * loopback */ #define IPV6_ADDR_ANY 0x0000U #define IPV6_ADDR_UNICAST 0x0001U #define IPV6_ADDR_MULTICAST 0x0002U #define IPV6_ADDR_LOOPBACK 0x0010U #define IPV6_ADDR_LINKLOCAL 0x0020U #define IPV6_ADDR_SITELOCAL 0x0040U #define IPV6_ADDR_COMPATv4 0x0080U #define IPV6_ADDR_SCOPE_MASK 0x00f0U #define IPV6_ADDR_MAPPED 0x1000U /* * Addr scopes */ #define IPV6_ADDR_MC_SCOPE(a) \ ((a)->s6_addr[1] & 0x0f) /* nonstandard */ #define __IPV6_ADDR_SCOPE_INVALID -1 #define IPV6_ADDR_SCOPE_NODELOCAL 0x01 #define IPV6_ADDR_SCOPE_LINKLOCAL 0x02 #define IPV6_ADDR_SCOPE_SITELOCAL 0x05 #define IPV6_ADDR_SCOPE_ORGLOCAL 0x08 #define IPV6_ADDR_SCOPE_GLOBAL 0x0e /* * Addr flags */ #define IPV6_ADDR_MC_FLAG_TRANSIENT(a) \ ((a)->s6_addr[1] & 0x10) #define IPV6_ADDR_MC_FLAG_PREFIX(a) \ ((a)->s6_addr[1] & 0x20) #define IPV6_ADDR_MC_FLAG_RENDEZVOUS(a) \ ((a)->s6_addr[1] & 0x40) /* * fragmentation header */ struct frag_hdr { __u8 nexthdr; __u8 reserved; __be16 frag_off; __be32 identification; }; /* * Jumbo payload option, as described in RFC 2675 2. */ struct hop_jumbo_hdr { u8 nexthdr; u8 hdrlen; u8 tlv_type; /* IPV6_TLV_JUMBO, 0xC2 */ u8 tlv_len; /* 4 */ __be32 jumbo_payload_len; }; #define IP6_MF 0x0001 #define IP6_OFFSET 0xFFF8 struct ip6_fraglist_iter { struct ipv6hdr *tmp_hdr; struct sk_buff *frag; int offset; unsigned int hlen; __be32 frag_id; u8 nexthdr; }; int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_fraglist_iter *iter); void ip6_fraglist_prepare(struct sk_buff *skb, struct ip6_fraglist_iter *iter); static inline struct sk_buff *ip6_fraglist_next(struct ip6_fraglist_iter *iter) { struct sk_buff *skb = iter->frag; iter->frag = skb->next; skb_mark_not_on_list(skb); return skb; } struct ip6_frag_state { u8 *prevhdr; unsigned int hlen; unsigned int mtu; unsigned int left; int offset; int ptr; int hroom; int troom; __be32 frag_id; u8 nexthdr; }; void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu, unsigned short needed_tailroom, int hdr_room, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state); struct sk_buff *ip6_frag_next(struct sk_buff *skb, struct ip6_frag_state *state); #define IP6_REPLY_MARK(net, mark) \ ((net)->ipv6.sysctl.fwmark_reflect ? (mark) : 0) #include <net/sock.h> /* sysctls */ extern int sysctl_mld_max_msf; extern int sysctl_mld_qrv; #define _DEVINC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ mod##SNMP_INC_STATS64((_idev)->stats.statname, (field));\ mod##SNMP_INC_STATS64((net)->mib.statname##_statistics, (field));\ }) /* per device counters are atomic_long_t */ #define _DEVINCATOMIC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ mod##SNMP_INC_STATS((net)->mib.statname##_statistics, (field));\ }) /* per device and per net counters are atomic_long_t */ #define _DEVINC_ATOMIC_ATOMIC(net, statname, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ SNMP_INC_STATS_ATOMIC_LONG((net)->mib.statname##_statistics, (field));\ }) #define _DEVADD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ mod##SNMP_ADD_STATS((_idev)->stats.statname, (field), (val)); \ mod##SNMP_ADD_STATS((net)->mib.statname##_statistics, (field), (val));\ }) #define _DEVUPD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ mod##SNMP_UPD_PO_STATS((_idev)->stats.statname, field, (val)); \ mod##SNMP_UPD_PO_STATS((net)->mib.statname##_statistics, field, (val));\ }) /* MIBs */ #define IP6_INC_STATS(net, idev,field) \ _DEVINC(net, ipv6, , idev, field) #define __IP6_INC_STATS(net, idev,field) \ _DEVINC(net, ipv6, __, idev, field) #define IP6_ADD_STATS(net, idev,field,val) \ _DEVADD(net, ipv6, , idev, field, val) #define __IP6_ADD_STATS(net, idev,field,val) \ _DEVADD(net, ipv6, __, idev, field, val) #define IP6_UPD_PO_STATS(net, idev,field,val) \ _DEVUPD(net, ipv6, , idev, field, val) #define __IP6_UPD_PO_STATS(net, idev,field,val) \ _DEVUPD(net, ipv6, __, idev, field, val) #define ICMP6_INC_STATS(net, idev, field) \ _DEVINCATOMIC(net, icmpv6, , idev, field) #define __ICMP6_INC_STATS(net, idev, field) \ _DEVINCATOMIC(net, icmpv6, __, idev, field) #define ICMP6MSGOUT_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256) #define ICMP6MSGIN_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field) struct ip6_ra_chain { struct ip6_ra_chain *next; struct sock *sk; int sel; void (*destructor)(struct sock *); }; extern struct ip6_ra_chain *ip6_ra_chain; extern rwlock_t ip6_ra_lock; /* This structure is prepared by protocol, when parsing ancillary data and passed to IPv6. */ struct ipv6_txoptions { refcount_t refcnt; /* Length of this structure */ int tot_len; /* length of extension headers */ __u16 opt_flen; /* after fragment hdr */ __u16 opt_nflen; /* before fragment hdr */ struct ipv6_opt_hdr *hopopt; struct ipv6_opt_hdr *dst0opt; struct ipv6_rt_hdr *srcrt; /* Routing Header */ struct ipv6_opt_hdr *dst1opt; struct rcu_head rcu; /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */ }; /* flowlabel_reflect sysctl values */ enum flowlabel_reflect { FLOWLABEL_REFLECT_ESTABLISHED = 1, FLOWLABEL_REFLECT_TCP_RESET = 2, FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES = 4, }; struct ip6_flowlabel { struct ip6_flowlabel __rcu *next; __be32 label; atomic_t users; struct in6_addr dst; struct ipv6_txoptions *opt; unsigned long linger; struct rcu_head rcu; u8 share; union { struct pid *pid; kuid_t uid; } owner; unsigned long lastuse; unsigned long expires; struct net *fl_net; }; #define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF) #define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF) #define IPV6_FLOWLABEL_STATELESS_FLAG cpu_to_be32(0x00080000) #define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) #define IPV6_TCLASS_SHIFT 20 struct ipv6_fl_socklist { struct ipv6_fl_socklist __rcu *next; struct ip6_flowlabel *fl; struct rcu_head rcu; }; struct ipcm6_cookie { struct sockcm_cookie sockc; __s16 hlimit; __s16 tclass; __u16 gso_size; __s8 dontfrag; struct ipv6_txoptions *opt; }; static inline void ipcm6_init(struct ipcm6_cookie *ipc6) { *ipc6 = (struct ipcm6_cookie) { .hlimit = -1, .tclass = -1, .dontfrag = -1, }; } static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6, const struct sock *sk) { *ipc6 = (struct ipcm6_cookie) { .hlimit = -1, .tclass = inet6_sk(sk)->tclass, .dontfrag = inet6_test_bit(DONTFRAG, sk), }; } static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) { struct ipv6_txoptions *opt; rcu_read_lock(); opt = rcu_dereference(np->opt); if (opt) { if (!refcount_inc_not_zero(&opt->refcnt)) opt = NULL; else opt = rcu_pointer_handoff(opt); } rcu_read_unlock(); return opt; } static inline void txopt_put(struct ipv6_txoptions *opt) { if (opt && refcount_dec_and_test(&opt->refcnt)) kfree_rcu(opt, rcu); } #if IS_ENABLED(CONFIG_IPV6) struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label); extern struct static_key_false_deferred ipv6_flowlabel_exclusive; static inline struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label) { if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key) && READ_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl)) return __fl6_sock_lookup(sk, label) ? : ERR_PTR(-ENOENT); return NULL; } #endif struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, struct ipv6_txoptions *fopt); void fl6_free_socklist(struct sock *sk); int ipv6_flowlabel_opt(struct sock *sk, sockptr_t optval, int optlen); int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, int flags); int ip6_flowlabel_init(void); void ip6_flowlabel_cleanup(void); bool ip6_autoflowlabel(struct net *net, const struct sock *sk); static inline void fl6_sock_release(struct ip6_flowlabel *fl) { if (fl) atomic_dec(&fl->users); } enum skb_drop_reason icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info); void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len); int ip6_ra_control(struct sock *sk, int sel); int ipv6_parse_hopopts(struct sk_buff *skb); struct ipv6_txoptions *ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt); struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, struct ipv6_opt_hdr *newopt); struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt); static inline struct ipv6_txoptions * ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt) { if (!opt) return NULL; return __ipv6_fixup_options(opt_space, opt); } bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct inet6_skb_parm *opt); struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt); /* This helper is specialized for BIG TCP needs. * It assumes the hop_jumbo_hdr will immediately follow the IPV6 header. * It assumes headers are already in skb->head. * Returns 0, or IPPROTO_TCP if a BIG TCP packet is there. */ static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) { const struct hop_jumbo_hdr *jhdr; const struct ipv6hdr *nhdr; if (likely(skb->len <= GRO_LEGACY_MAX_SIZE)) return 0; if (skb->protocol != htons(ETH_P_IPV6)) return 0; if (skb_network_offset(skb) + sizeof(struct ipv6hdr) + sizeof(struct hop_jumbo_hdr) > skb_headlen(skb)) return 0; nhdr = ipv6_hdr(skb); if (nhdr->nexthdr != NEXTHDR_HOP) return 0; jhdr = (const struct hop_jumbo_hdr *) (nhdr + 1); if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 || jhdr->nexthdr != IPPROTO_TCP) return 0; return jhdr->nexthdr; } /* Return 0 if HBH header is successfully removed * Or if HBH removal is unnecessary (packet is not big TCP) * Return error to indicate dropping the packet */ static inline int ipv6_hopopt_jumbo_remove(struct sk_buff *skb) { const int hophdr_len = sizeof(struct hop_jumbo_hdr); int nexthdr = ipv6_has_hopopt_jumbo(skb); struct ipv6hdr *h6; if (!nexthdr) return 0; if (skb_cow_head(skb, 0)) return -1; /* Remove the HBH header. * Layout: [Ethernet header][IPv6 header][HBH][L4 Header] */ memmove(skb_mac_header(skb) + hophdr_len, skb_mac_header(skb), skb_network_header(skb) - skb_mac_header(skb) + sizeof(struct ipv6hdr)); __skb_pull(skb, hophdr_len); skb->network_header += hophdr_len; skb->mac_header += hophdr_len; h6 = ipv6_hdr(skb); h6->nexthdr = nexthdr; return 0; } static inline bool ipv6_accept_ra(const struct inet6_dev *idev) { s32 accept_ra = READ_ONCE(idev->cnf.accept_ra); /* If forwarding is enabled, RA are not accepted unless the special * hybrid mode (accept_ra=2) is enabled. */ return READ_ONCE(idev->cnf.forwarding) ? accept_ra == 2 : accept_ra; } #define IPV6_FRAG_HIGH_THRESH (4 * 1024*1024) /* 4194304 */ #define IPV6_FRAG_LOW_THRESH (3 * 1024*1024) /* 3145728 */ #define IPV6_FRAG_TIMEOUT (60 * HZ) /* 60 seconds */ int __ipv6_addr_type(const struct in6_addr *addr); static inline int ipv6_addr_type(const struct in6_addr *addr) { return __ipv6_addr_type(addr) & 0xffff; } static inline int ipv6_addr_scope(const struct in6_addr *addr) { return __ipv6_addr_type(addr) & IPV6_ADDR_SCOPE_MASK; } static inline int __ipv6_addr_src_scope(int type) { return (type == IPV6_ADDR_ANY) ? __IPV6_ADDR_SCOPE_INVALID : (type >> 16); } static inline int ipv6_addr_src_scope(const struct in6_addr *addr) { return __ipv6_addr_src_scope(__ipv6_addr_type(addr)); } static inline bool __ipv6_addr_needs_scope_id(int type) { return type & IPV6_ADDR_LINKLOCAL || (type & IPV6_ADDR_MULTICAST && (type & (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL))); } static inline __u32 ipv6_iface_scope_id(const struct in6_addr *addr, int iface) { return __ipv6_addr_needs_scope_id(__ipv6_addr_type(addr)) ? iface : 0; } static inline int ipv6_addr_cmp(const struct in6_addr *a1, const struct in6_addr *a2) { return memcmp(a1, a2, sizeof(struct in6_addr)); } static inline bool ipv6_masked_addr_cmp(const struct in6_addr *a1, const struct in6_addr *m, const struct in6_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ulm = (const unsigned long *)m; const unsigned long *ul2 = (const unsigned long *)a2; return !!(((ul1[0] ^ ul2[0]) & ulm[0]) | ((ul1[1] ^ ul2[1]) & ulm[1])); #else return !!(((a1->s6_addr32[0] ^ a2->s6_addr32[0]) & m->s6_addr32[0]) | ((a1->s6_addr32[1] ^ a2->s6_addr32[1]) & m->s6_addr32[1]) | ((a1->s6_addr32[2] ^ a2->s6_addr32[2]) & m->s6_addr32[2]) | ((a1->s6_addr32[3] ^ a2->s6_addr32[3]) & m->s6_addr32[3])); #endif } static inline void ipv6_addr_prefix(struct in6_addr *pfx, const struct in6_addr *addr, int plen) { /* caller must guarantee 0 <= plen <= 128 */ int o = plen >> 3, b = plen & 0x7; memset(pfx->s6_addr, 0, sizeof(pfx->s6_addr)); memcpy(pfx->s6_addr, addr, o); if (b != 0) pfx->s6_addr[o] = addr->s6_addr[o] & (0xff00 >> b); } static inline void ipv6_addr_prefix_copy(struct in6_addr *addr, const struct in6_addr *pfx, int plen) { /* caller must guarantee 0 <= plen <= 128 */ int o = plen >> 3, b = plen & 0x7; memcpy(addr->s6_addr, pfx, o); if (b != 0) { addr->s6_addr[o] &= ~(0xff00 >> b); addr->s6_addr[o] |= (pfx->s6_addr[o] & (0xff00 >> b)); } } static inline void __ipv6_addr_set_half(__be32 *addr, __be32 wh, __be32 wl) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #if defined(__BIG_ENDIAN) if (__builtin_constant_p(wh) && __builtin_constant_p(wl)) { *(__force u64 *)addr = ((__force u64)(wh) << 32 | (__force u64)(wl)); return; } #elif defined(__LITTLE_ENDIAN) if (__builtin_constant_p(wl) && __builtin_constant_p(wh)) { *(__force u64 *)addr = ((__force u64)(wl) << 32 | (__force u64)(wh)); return; } #endif #endif addr[0] = wh; addr[1] = wl; } static inline void ipv6_addr_set(struct in6_addr *addr, __be32 w1, __be32 w2, __be32 w3, __be32 w4) { __ipv6_addr_set_half(&addr->s6_addr32[0], w1, w2); __ipv6_addr_set_half(&addr->s6_addr32[2], w3, w4); } static inline bool ipv6_addr_equal(const struct in6_addr *a1, const struct in6_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ul2 = (const unsigned long *)a2; return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL; #else return ((a1->s6_addr32[0] ^ a2->s6_addr32[0]) | (a1->s6_addr32[1] ^ a2->s6_addr32[1]) | (a1->s6_addr32[2] ^ a2->s6_addr32[2]) | (a1->s6_addr32[3] ^ a2->s6_addr32[3])) == 0; #endif } #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 static inline bool __ipv6_prefix_equal64_half(const __be64 *a1, const __be64 *a2, unsigned int len) { if (len && ((*a1 ^ *a2) & cpu_to_be64((~0UL) << (64 - len)))) return false; return true; } static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, const struct in6_addr *addr2, unsigned int prefixlen) { const __be64 *a1 = (const __be64 *)addr1; const __be64 *a2 = (const __be64 *)addr2; if (prefixlen >= 64) { if (a1[0] ^ a2[0]) return false; return __ipv6_prefix_equal64_half(a1 + 1, a2 + 1, prefixlen - 64); } return __ipv6_prefix_equal64_half(a1, a2, prefixlen); } #else static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, const struct in6_addr *addr2, unsigned int prefixlen) { const __be32 *a1 = addr1->s6_addr32; const __be32 *a2 = addr2->s6_addr32; unsigned int pdw, pbi; /* check complete u32 in prefix */ pdw = prefixlen >> 5; if (pdw && memcmp(a1, a2, pdw << 2)) return false; /* check incomplete u32 in prefix */ pbi = prefixlen & 0x1f; if (pbi && ((a1[pdw] ^ a2[pdw]) & htonl((0xffffffff) << (32 - pbi)))) return false; return true; } #endif static inline bool ipv6_addr_any(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul = (const unsigned long *)a; return (ul[0] | ul[1]) == 0UL; #else return (a->s6_addr32[0] | a->s6_addr32[1] | a->s6_addr32[2] | a->s6_addr32[3]) == 0; #endif } static inline u32 ipv6_addr_hash(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul = (const unsigned long *)a; unsigned long x = ul[0] ^ ul[1]; return (u32)(x ^ (x >> 32)); #else return (__force u32)(a->s6_addr32[0] ^ a->s6_addr32[1] ^ a->s6_addr32[2] ^ a->s6_addr32[3]); #endif } /* more secured version of ipv6_addr_hash() */ static inline u32 __ipv6_addr_jhash(const struct in6_addr *a, const u32 initval) { return jhash2((__force const u32 *)a->s6_addr32, ARRAY_SIZE(a->s6_addr32), initval); } static inline bool ipv6_addr_loopback(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const __be64 *be = (const __be64 *)a; return (be[0] | (be[1] ^ cpu_to_be64(1))) == 0UL; #else return (a->s6_addr32[0] | a->s6_addr32[1] | a->s6_addr32[2] | (a->s6_addr32[3] ^ cpu_to_be32(1))) == 0; #endif } /* * Note that we must __force cast these to unsigned long to make sparse happy, * since all of the endian-annotated types are fixed size regardless of arch. */ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) { return ( #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 *(unsigned long *)a | #else (__force unsigned long)(a->s6_addr32[0] | a->s6_addr32[1]) | #endif (__force unsigned long)(a->s6_addr32[2] ^ cpu_to_be32(0x0000ffff))) == 0UL; } static inline bool ipv6_addr_v4mapped_loopback(const struct in6_addr *a) { return ipv6_addr_v4mapped(a) && ipv4_is_loopback(a->s6_addr32[3]); } static inline u32 ipv6_portaddr_hash(const struct net *net, const struct in6_addr *addr6, unsigned int port) { unsigned int hash, mix = net_hash_mix(net); if (ipv6_addr_any(addr6)) hash = jhash_1word(0, mix); else if (ipv6_addr_v4mapped(addr6)) hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix); else hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix); return hash ^ port; } /* * Check for a RFC 4843 ORCHID address * (Overlay Routable Cryptographic Hash Identifiers) */ static inline bool ipv6_addr_orchid(const struct in6_addr *a) { return (a->s6_addr32[0] & htonl(0xfffffff0)) == htonl(0x20010010); } static inline bool ipv6_addr_is_multicast(const struct in6_addr *addr) { return (addr->s6_addr32[0] & htonl(0xFF000000)) == htonl(0xFF000000); } static inline void ipv6_addr_set_v4mapped(const __be32 addr, struct in6_addr *v4mapped) { ipv6_addr_set(v4mapped, 0, 0, htonl(0x0000FFFF), addr); } /* * find the first different bit between two addresses * length of address must be a multiple of 32bits */ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int addrlen) { const __be32 *a1 = token1, *a2 = token2; int i; addrlen >>= 2; for (i = 0; i < addrlen; i++) { __be32 xb = a1[i] ^ a2[i]; if (xb) return i * 32 + 31 - __fls(ntohl(xb)); } /* * we should *never* get to this point since that * would mean the addrs are equal * * However, we do get to it 8) And exactly, when * addresses are equal 8) * * ip route add 1111::/128 via ... * ip route add 1111::/64 via ... * and we are here. * * Ideally, this function should stop comparison * at prefix length. It does not, but it is still OK, * if returned value is greater than prefix length. * --ANK (980803) */ return addrlen << 5; } #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 static inline int __ipv6_addr_diff64(const void *token1, const void *token2, int addrlen) { const __be64 *a1 = token1, *a2 = token2; int i; addrlen >>= 3; for (i = 0; i < addrlen; i++) { __be64 xb = a1[i] ^ a2[i]; if (xb) return i * 64 + 63 - __fls(be64_to_cpu(xb)); } return addrlen << 6; } #endif static inline int __ipv6_addr_diff(const void *token1, const void *token2, int addrlen) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 if (__builtin_constant_p(addrlen) && !(addrlen & 7)) return __ipv6_addr_diff64(token1, token2, addrlen); #endif return __ipv6_addr_diff32(token1, token2, addrlen); } static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_addr *a2) { return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr); __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6, struct dst_entry *dst) { int hlimit; if (ipv6_addr_is_multicast(&fl6->daddr)) hlimit = READ_ONCE(np->mcast_hops); else hlimit = READ_ONCE(np->hop_limit); if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); return hlimit; } /* copy IPv6 saddr & daddr to flow_keys, possibly using 64bit load/store * Equivalent to : flow->v6addrs.src = iph->saddr; * flow->v6addrs.dst = iph->daddr; */ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, const struct ipv6hdr *iph) { BUILD_BUG_ON(offsetof(typeof(flow->addrs), v6addrs.dst) != offsetof(typeof(flow->addrs), v6addrs.src) + sizeof(flow->addrs.v6addrs.src)); memcpy(&flow->addrs.v6addrs, &iph->addrs, sizeof(flow->addrs.v6addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } #if IS_ENABLED(CONFIG_IPV6) static inline bool ipv6_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { return net->ipv6.sysctl.ip_nonlocal_bind || test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) || test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags); } /* Sysctl settings for net ipv6.auto_flowlabels */ #define IP6_AUTO_FLOW_LABEL_OFF 0 #define IP6_AUTO_FLOW_LABEL_OPTOUT 1 #define IP6_AUTO_FLOW_LABEL_OPTIN 2 #define IP6_AUTO_FLOW_LABEL_FORCED 3 #define IP6_AUTO_FLOW_LABEL_MAX IP6_AUTO_FLOW_LABEL_FORCED #define IP6_DEFAULT_AUTO_FLOW_LABELS IP6_AUTO_FLOW_LABEL_OPTOUT static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { u32 hash; /* @flowlabel may include more than a flow label, eg, the traffic class. * Here we want only the flow label value. */ flowlabel &= IPV6_FLOWLABEL_MASK; if (flowlabel || net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF || (!autolabel && net->ipv6.sysctl.auto_flowlabels != IP6_AUTO_FLOW_LABEL_FORCED)) return flowlabel; hash = skb_get_hash_flowi6(skb, fl6); /* Since this is being sent on the wire obfuscate hash a bit * to minimize possibility that any useful information to an * attacker is leaked. Only lower 20 bits are relevant. */ hash = rol32(hash, 16); flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; if (net->ipv6.sysctl.flowlabel_state_ranges) flowlabel |= IPV6_FLOWLABEL_STATELESS_FLAG; return flowlabel; } static inline int ip6_default_np_autolabel(struct net *net) { switch (net->ipv6.sysctl.auto_flowlabels) { case IP6_AUTO_FLOW_LABEL_OFF: case IP6_AUTO_FLOW_LABEL_OPTIN: default: return 0; case IP6_AUTO_FLOW_LABEL_OPTOUT: case IP6_AUTO_FLOW_LABEL_FORCED: return 1; } } #else static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { return flowlabel; } static inline int ip6_default_np_autolabel(struct net *net) { return 0; } #endif #if IS_ENABLED(CONFIG_IPV6) static inline int ip6_multipath_hash_policy(const struct net *net) { return net->ipv6.sysctl.multipath_hash_policy; } static inline u32 ip6_multipath_hash_fields(const struct net *net) { return net->ipv6.sysctl.multipath_hash_fields; } #else static inline int ip6_multipath_hash_policy(const struct net *net) { return 0; } static inline u32 ip6_multipath_hash_fields(const struct net *net) { return 0; } #endif /* * Header manipulation */ static inline void ip6_flow_hdr(struct ipv6hdr *hdr, unsigned int tclass, __be32 flowlabel) { *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | flowlabel; } static inline __be32 ip6_flowinfo(const struct ipv6hdr *hdr) { return *(__be32 *)hdr & IPV6_FLOWINFO_MASK; } static inline __be32 ip6_flowlabel(const struct ipv6hdr *hdr) { return *(__be32 *)hdr & IPV6_FLOWLABEL_MASK; } static inline u8 ip6_tclass(__be32 flowinfo) { return ntohl(flowinfo & IPV6_TCLASS_MASK) >> IPV6_TCLASS_SHIFT; } static inline dscp_t ip6_dscp(__be32 flowinfo) { return inet_dsfield_to_dscp(ip6_tclass(flowinfo)); } static inline __be32 ip6_make_flowinfo(unsigned int tclass, __be32 flowlabel) { return htonl(tclass << IPV6_TCLASS_SHIFT) | flowlabel; } static inline __be32 flowi6_get_flowlabel(const struct flowi6 *fl6) { return fl6->flowlabel & IPV6_FLOWLABEL_MASK; } /* * Prototypes exported by ipv6 */ /* * rcv function (called from netdevice level) */ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); void ipv6_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *orig_dev); int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); /* * upper-layer output functions */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags); int ip6_push_pending_frames(struct sock *sk); void ip6_flush_pending_frames(struct sock *sk); int ip6_send_skb(struct sk_buff *skb); struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork, struct inet6_cork *v6_cork); struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork); static inline struct sk_buff *ip6_finish_skb(struct sock *sk) { return __ip6_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork, &inet6_sk(sk)->cork); } int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, bool connected); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *orig_dst); /* * skb processing functions */ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr, bool have_final); int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); /* * Extension header (options) processing */ void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto, struct in6_addr **daddr_p, struct in6_addr *saddr); void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto); int ipv6_skip_exthdr(const struct sk_buff *, int start, u8 *nexthdrp, __be16 *frag_offp); bool ipv6_ext_hdr(u8 nexthdr); enum { IP6_FH_F_FRAG = (1 << 0), IP6_FH_F_AUTH = (1 << 1), IP6_FH_F_SKIP_RH = (1 << 2), }; /* find specified header and get offset to it */ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, int target, unsigned short *fragoff, int *fragflg); int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type); struct in6_addr *fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, struct in6_addr *orig); /* * socket options (ipv6_sockglue.c) */ DECLARE_STATIC_KEY_FALSE(ip6_min_hopcount); int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int do_ipv6_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); int ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int __ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr); void ip6_datagram_release_cb(struct sock *sk); int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, int *addr_len); void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); void inet6_cleanup_sock(struct sock *sk); void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet6_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk); int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); /* * reassembly.c */ extern const struct proto_ops inet6_stream_ops; extern const struct proto_ops inet6_dgram_ops; extern const struct proto_ops inet6_sockraw_ops; struct group_source_req; struct group_filter; int ip6_mc_source(int add, int omode, struct sock *sk, struct group_source_req *pgsr); int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, struct sockaddr_storage *list); int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset); #ifdef CONFIG_PROC_FS int ac6_proc_init(struct net *net); void ac6_proc_exit(struct net *net); int raw6_proc_init(void); void raw6_proc_exit(void); int tcp6_proc_init(struct net *net); void tcp6_proc_exit(struct net *net); int udp6_proc_init(struct net *net); void udp6_proc_exit(struct net *net); int udplite6_proc_init(void); void udplite6_proc_exit(void); int ipv6_misc_proc_init(void); void ipv6_misc_proc_exit(void); int snmp6_register_dev(struct inet6_dev *idev); int snmp6_unregister_dev(struct inet6_dev *idev); #else static inline int ac6_proc_init(struct net *net) { return 0; } static inline void ac6_proc_exit(struct net *net) { } static inline int snmp6_register_dev(struct inet6_dev *idev) { return 0; } static inline int snmp6_unregister_dev(struct inet6_dev *idev) { return 0; } #endif #ifdef CONFIG_SYSCTL struct ctl_table *ipv6_icmp_sysctl_init(struct net *net); size_t ipv6_icmp_sysctl_table_size(void); struct ctl_table *ipv6_route_sysctl_init(struct net *net); size_t ipv6_route_sysctl_table_size(struct net *net); int ipv6_sysctl_register(void); void ipv6_sysctl_unregister(void); #endif int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); static inline int ip6_sock_set_v6only(struct sock *sk) { if (inet_sk(sk)->inet_num) return -EINVAL; lock_sock(sk); sk->sk_ipv6only = true; release_sock(sk); return 0; } static inline void ip6_sock_set_recverr(struct sock *sk) { inet6_set_bit(RECVERR6, sk); } #define IPV6_PREFER_SRC_MASK (IPV6_PREFER_SRC_TMP | IPV6_PREFER_SRC_PUBLIC | \ IPV6_PREFER_SRC_COA) static inline int ip6_sock_set_addr_preferences(struct sock *sk, int val) { unsigned int prefmask = ~IPV6_PREFER_SRC_MASK; unsigned int pref = 0; /* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */ switch (val & (IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP | IPV6_PREFER_SRC_PUBTMP_DEFAULT)) { case IPV6_PREFER_SRC_PUBLIC: pref |= IPV6_PREFER_SRC_PUBLIC; prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP); break; case IPV6_PREFER_SRC_TMP: pref |= IPV6_PREFER_SRC_TMP; prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP); break; case IPV6_PREFER_SRC_PUBTMP_DEFAULT: prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP); break; case 0: break; default: return -EINVAL; } /* check HOME/COA conflicts */ switch (val & (IPV6_PREFER_SRC_HOME | IPV6_PREFER_SRC_COA)) { case IPV6_PREFER_SRC_HOME: prefmask &= ~IPV6_PREFER_SRC_COA; break; case IPV6_PREFER_SRC_COA: pref |= IPV6_PREFER_SRC_COA; break; case 0: break; default: return -EINVAL; } /* check CGA/NONCGA conflicts */ switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) { case IPV6_PREFER_SRC_CGA: case IPV6_PREFER_SRC_NONCGA: case 0: break; default: return -EINVAL; } WRITE_ONCE(inet6_sk(sk)->srcprefs, (READ_ONCE(inet6_sk(sk)->srcprefs) & prefmask) | pref); return 0; } static inline void ip6_sock_set_recvpktinfo(struct sock *sk) { lock_sock(sk); inet6_sk(sk)->rxopt.bits.rxinfo = true; release_sock(sk); } #define IPV6_ADDR_WORDS 4 static inline void ipv6_addr_cpu_to_be32(__be32 *dst, const u32 *src) { cpu_to_be32_array(dst, src, IPV6_ADDR_WORDS); } static inline void ipv6_addr_be32_to_cpu(u32 *dst, const __be32 *src) { be32_to_cpu_array(dst, src, IPV6_ADDR_WORDS); } #endif /* _NET_IPV6_H */ |
| 2 222 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Hash: Hash algorithms under the crypto API * * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_HASH_H #define _CRYPTO_HASH_H #include <linux/atomic.h> #include <linux/crypto.h> #include <linux/string.h> struct crypto_ahash; /** * DOC: Message Digest Algorithm Definitions * * These data structures define modular message digest algorithm * implementations, managed via crypto_register_ahash(), * crypto_register_shash(), crypto_unregister_ahash() and * crypto_unregister_shash(). */ /* * struct hash_alg_common - define properties of message digest * @digestsize: Size of the result of the transformation. A buffer of this size * must be available to the @final and @finup calls, so they can * store the resulting hash into it. For various predefined sizes, * search include/crypto/ using * git grep _DIGEST_SIZE include/crypto. * @statesize: Size of the block for partial state of the transformation. A * buffer of this size must be passed to the @export function as it * will save the partial state of the transformation into it. On the * other side, the @import function will load the state from a * buffer of this size as well. * @base: Start of data structure of cipher algorithm. The common data * structure of crypto_alg contains information common to all ciphers. * The hash_alg_common data structure now adds the hash-specific * information. */ #define HASH_ALG_COMMON { \ unsigned int digestsize; \ unsigned int statesize; \ \ struct crypto_alg base; \ } struct hash_alg_common HASH_ALG_COMMON; struct ahash_request { struct crypto_async_request base; unsigned int nbytes; struct scatterlist *src; u8 *result; /* This field may only be used by the ahash API code. */ void *priv; void *__ctx[] CRYPTO_MINALIGN_ATTR; }; /** * struct ahash_alg - asynchronous message digest definition * @init: **[mandatory]** Initialize the transformation context. Intended only to initialize the * state of the HASH transformation at the beginning. This shall fill in * the internal structures used during the entire duration of the whole * transformation. No data processing happens at this point. Driver code * implementation must not use req->result. * @update: **[mandatory]** Push a chunk of data into the driver for transformation. This * function actually pushes blocks of data from upper layers into the * driver, which then passes those to the hardware as seen fit. This * function must not finalize the HASH transformation by calculating the * final message digest as this only adds more data into the * transformation. This function shall not modify the transformation * context, as this function may be called in parallel with the same * transformation object. Data processing can happen synchronously * [SHASH] or asynchronously [AHASH] at this point. Driver must not use * req->result. * @final: **[mandatory]** Retrieve result from the driver. This function finalizes the * transformation and retrieves the resulting hash from the driver and * pushes it back to upper layers. No data processing happens at this * point unless hardware requires it to finish the transformation * (then the data buffered by the device driver is processed). * @finup: **[optional]** Combination of @update and @final. This function is effectively a * combination of @update and @final calls issued in sequence. As some * hardware cannot do @update and @final separately, this callback was * added to allow such hardware to be used at least by IPsec. Data * processing can happen synchronously [SHASH] or asynchronously [AHASH] * at this point. * @digest: Combination of @init and @update and @final. This function * effectively behaves as the entire chain of operations, @init, * @update and @final issued in sequence. Just like @finup, this was * added for hardware which cannot do even the @finup, but can only do * the whole transformation in one run. Data processing can happen * synchronously [SHASH] or asynchronously [AHASH] at this point. * @setkey: Set optional key used by the hashing algorithm. Intended to push * optional key used by the hashing algorithm from upper layers into * the driver. This function can store the key in the transformation * context or can outright program it into the hardware. In the former * case, one must be careful to program the key into the hardware at * appropriate time and one must be careful that .setkey() can be * called multiple times during the existence of the transformation * object. Not all hashing algorithms do implement this function as it * is only needed for keyed message digests. SHAx/MDx/CRCx do NOT * implement this function. HMAC(MDx)/HMAC(SHAx)/CMAC(AES) do implement * this function. This function must be called before any other of the * @init, @update, @final, @finup, @digest is called. No data * processing happens at this point. * @export: Export partial state of the transformation. This function dumps the * entire state of the ongoing transformation into a provided block of * data so it can be @import 'ed back later on. This is useful in case * you want to save partial result of the transformation after * processing certain amount of data and reload this partial result * multiple times later on for multiple re-use. No data processing * happens at this point. Driver must not use req->result. * @import: Import partial state of the transformation. This function loads the * entire state of the ongoing transformation from a provided block of * data so the transformation can continue from this point onward. No * data processing happens at this point. Driver must not use * req->result. * @init_tfm: Initialize the cryptographic transformation object. * This function is called only once at the instantiation * time, right after the transformation context was * allocated. In case the cryptographic hardware has * some special requirements which need to be handled * by software, this function shall check for the precise * requirement of the transformation and put any software * fallbacks in place. * @exit_tfm: Deinitialize the cryptographic transformation object. * This is a counterpart to @init_tfm, used to remove * various changes set in @init_tfm. * @clone_tfm: Copy transform into new object, may allocate memory. * @halg: see struct hash_alg_common */ struct ahash_alg { int (*init)(struct ahash_request *req); int (*update)(struct ahash_request *req); int (*final)(struct ahash_request *req); int (*finup)(struct ahash_request *req); int (*digest)(struct ahash_request *req); int (*export)(struct ahash_request *req, void *out); int (*import)(struct ahash_request *req, const void *in); int (*setkey)(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen); int (*init_tfm)(struct crypto_ahash *tfm); void (*exit_tfm)(struct crypto_ahash *tfm); int (*clone_tfm)(struct crypto_ahash *dst, struct crypto_ahash *src); struct hash_alg_common halg; }; struct shash_desc { struct crypto_shash *tfm; void *__ctx[] __aligned(ARCH_SLAB_MINALIGN); }; #define HASH_MAX_DIGESTSIZE 64 /* * Worst case is hmac(sha3-224-generic). Its context is a nested 'shash_desc' * containing a 'struct sha3_state'. */ #define HASH_MAX_DESCSIZE (sizeof(struct shash_desc) + 360) #define SHASH_DESC_ON_STACK(shash, ctx) \ char __##shash##_desc[sizeof(struct shash_desc) + HASH_MAX_DESCSIZE] \ __aligned(__alignof__(struct shash_desc)); \ struct shash_desc *shash = (struct shash_desc *)__##shash##_desc /** * struct shash_alg - synchronous message digest definition * @init: see struct ahash_alg * @update: see struct ahash_alg * @final: see struct ahash_alg * @finup: see struct ahash_alg * @digest: see struct ahash_alg * @export: see struct ahash_alg * @import: see struct ahash_alg * @setkey: see struct ahash_alg * @init_tfm: Initialize the cryptographic transformation object. * This function is called only once at the instantiation * time, right after the transformation context was * allocated. In case the cryptographic hardware has * some special requirements which need to be handled * by software, this function shall check for the precise * requirement of the transformation and put any software * fallbacks in place. * @exit_tfm: Deinitialize the cryptographic transformation object. * This is a counterpart to @init_tfm, used to remove * various changes set in @init_tfm. * @clone_tfm: Copy transform into new object, may allocate memory. * @descsize: Size of the operational state for the message digest. This state * size is the memory size that needs to be allocated for * shash_desc.__ctx * @halg: see struct hash_alg_common * @HASH_ALG_COMMON: see struct hash_alg_common */ struct shash_alg { int (*init)(struct shash_desc *desc); int (*update)(struct shash_desc *desc, const u8 *data, unsigned int len); int (*final)(struct shash_desc *desc, u8 *out); int (*finup)(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); int (*digest)(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); int (*export)(struct shash_desc *desc, void *out); int (*import)(struct shash_desc *desc, const void *in); int (*setkey)(struct crypto_shash *tfm, const u8 *key, unsigned int keylen); int (*init_tfm)(struct crypto_shash *tfm); void (*exit_tfm)(struct crypto_shash *tfm); int (*clone_tfm)(struct crypto_shash *dst, struct crypto_shash *src); unsigned int descsize; union { struct HASH_ALG_COMMON; struct hash_alg_common halg; }; }; #undef HASH_ALG_COMMON struct crypto_ahash { bool using_shash; /* Underlying algorithm is shash, not ahash */ unsigned int statesize; unsigned int reqsize; struct crypto_tfm base; }; struct crypto_shash { unsigned int descsize; struct crypto_tfm base; }; /** * DOC: Asynchronous Message Digest API * * The asynchronous message digest API is used with the ciphers of type * CRYPTO_ALG_TYPE_AHASH (listed as type "ahash" in /proc/crypto) * * The asynchronous cipher operation discussion provided for the * CRYPTO_ALG_TYPE_SKCIPHER API applies here as well. */ static inline struct crypto_ahash *__crypto_ahash_cast(struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_ahash, base); } /** * crypto_alloc_ahash() - allocate ahash cipher handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * ahash cipher * @type: specifies the type of the cipher * @mask: specifies the mask for the cipher * * Allocate a cipher handle for an ahash. The returned struct * crypto_ahash is the cipher handle that is required for any subsequent * API invocation for that ahash. * * Return: allocated cipher handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_ahash *crypto_alloc_ahash(const char *alg_name, u32 type, u32 mask); struct crypto_ahash *crypto_clone_ahash(struct crypto_ahash *tfm); static inline struct crypto_tfm *crypto_ahash_tfm(struct crypto_ahash *tfm) { return &tfm->base; } /** * crypto_free_ahash() - zeroize and free the ahash handle * @tfm: cipher handle to be freed * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_ahash(struct crypto_ahash *tfm) { crypto_destroy_tfm(tfm, crypto_ahash_tfm(tfm)); } /** * crypto_has_ahash() - Search for the availability of an ahash. * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * ahash * @type: specifies the type of the ahash * @mask: specifies the mask for the ahash * * Return: true when the ahash is known to the kernel crypto API; false * otherwise */ int crypto_has_ahash(const char *alg_name, u32 type, u32 mask); static inline const char *crypto_ahash_alg_name(struct crypto_ahash *tfm) { return crypto_tfm_alg_name(crypto_ahash_tfm(tfm)); } static inline const char *crypto_ahash_driver_name(struct crypto_ahash *tfm) { return crypto_tfm_alg_driver_name(crypto_ahash_tfm(tfm)); } /** * crypto_ahash_blocksize() - obtain block size for cipher * @tfm: cipher handle * * The block size for the message digest cipher referenced with the cipher * handle is returned. * * Return: block size of cipher */ static inline unsigned int crypto_ahash_blocksize(struct crypto_ahash *tfm) { return crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm)); } static inline struct hash_alg_common *__crypto_hash_alg_common( struct crypto_alg *alg) { return container_of(alg, struct hash_alg_common, base); } static inline struct hash_alg_common *crypto_hash_alg_common( struct crypto_ahash *tfm) { return __crypto_hash_alg_common(crypto_ahash_tfm(tfm)->__crt_alg); } /** * crypto_ahash_digestsize() - obtain message digest size * @tfm: cipher handle * * The size for the message digest created by the message digest cipher * referenced with the cipher handle is returned. * * * Return: message digest size of cipher */ static inline unsigned int crypto_ahash_digestsize(struct crypto_ahash *tfm) { return crypto_hash_alg_common(tfm)->digestsize; } /** * crypto_ahash_statesize() - obtain size of the ahash state * @tfm: cipher handle * * Return the size of the ahash state. With the crypto_ahash_export() * function, the caller can export the state into a buffer whose size is * defined with this function. * * Return: size of the ahash state */ static inline unsigned int crypto_ahash_statesize(struct crypto_ahash *tfm) { return tfm->statesize; } static inline u32 crypto_ahash_get_flags(struct crypto_ahash *tfm) { return crypto_tfm_get_flags(crypto_ahash_tfm(tfm)); } static inline void crypto_ahash_set_flags(struct crypto_ahash *tfm, u32 flags) { crypto_tfm_set_flags(crypto_ahash_tfm(tfm), flags); } static inline void crypto_ahash_clear_flags(struct crypto_ahash *tfm, u32 flags) { crypto_tfm_clear_flags(crypto_ahash_tfm(tfm), flags); } /** * crypto_ahash_reqtfm() - obtain cipher handle from request * @req: asynchronous request handle that contains the reference to the ahash * cipher handle * * Return the ahash cipher handle that is registered with the asynchronous * request handle ahash_request. * * Return: ahash cipher handle */ static inline struct crypto_ahash *crypto_ahash_reqtfm( struct ahash_request *req) { return __crypto_ahash_cast(req->base.tfm); } /** * crypto_ahash_reqsize() - obtain size of the request data structure * @tfm: cipher handle * * Return: size of the request data */ static inline unsigned int crypto_ahash_reqsize(struct crypto_ahash *tfm) { return tfm->reqsize; } static inline void *ahash_request_ctx(struct ahash_request *req) { return req->__ctx; } /** * crypto_ahash_setkey - set key for cipher handle * @tfm: cipher handle * @key: buffer holding the key * @keylen: length of the key in bytes * * The caller provided key is set for the ahash cipher. The cipher * handle must point to a keyed hash in order for this function to succeed. * * Return: 0 if the setting of the key was successful; < 0 if an error occurred */ int crypto_ahash_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen); /** * crypto_ahash_finup() - update and finalize message digest * @req: reference to the ahash_request handle that holds all information * needed to perform the cipher operation * * This function is a "short-hand" for the function calls of * crypto_ahash_update and crypto_ahash_final. The parameters have the same * meaning as discussed for those separate functions. * * Return: see crypto_ahash_final() */ int crypto_ahash_finup(struct ahash_request *req); /** * crypto_ahash_final() - calculate message digest * @req: reference to the ahash_request handle that holds all information * needed to perform the cipher operation * * Finalize the message digest operation and create the message digest * based on all data added to the cipher handle. The message digest is placed * into the output buffer registered with the ahash_request handle. * * Return: * 0 if the message digest was successfully calculated; * -EINPROGRESS if data is fed into hardware (DMA) or queued for later; * -EBUSY if queue is full and request should be resubmitted later; * other < 0 if an error occurred */ int crypto_ahash_final(struct ahash_request *req); /** * crypto_ahash_digest() - calculate message digest for a buffer * @req: reference to the ahash_request handle that holds all information * needed to perform the cipher operation * * This function is a "short-hand" for the function calls of crypto_ahash_init, * crypto_ahash_update and crypto_ahash_final. The parameters have the same * meaning as discussed for those separate three functions. * * Return: see crypto_ahash_final() */ int crypto_ahash_digest(struct ahash_request *req); /** * crypto_ahash_export() - extract current message digest state * @req: reference to the ahash_request handle whose state is exported * @out: output buffer of sufficient size that can hold the hash state * * This function exports the hash state of the ahash_request handle into the * caller-allocated output buffer out which must have sufficient size (e.g. by * calling crypto_ahash_statesize()). * * Return: 0 if the export was successful; < 0 if an error occurred */ int crypto_ahash_export(struct ahash_request *req, void *out); /** * crypto_ahash_import() - import message digest state * @req: reference to ahash_request handle the state is imported into * @in: buffer holding the state * * This function imports the hash state into the ahash_request handle from the * input buffer. That buffer should have been generated with the * crypto_ahash_export function. * * Return: 0 if the import was successful; < 0 if an error occurred */ int crypto_ahash_import(struct ahash_request *req, const void *in); /** * crypto_ahash_init() - (re)initialize message digest handle * @req: ahash_request handle that already is initialized with all necessary * data using the ahash_request_* API functions * * The call (re-)initializes the message digest referenced by the ahash_request * handle. Any potentially existing state created by previous operations is * discarded. * * Return: see crypto_ahash_final() */ int crypto_ahash_init(struct ahash_request *req); /** * crypto_ahash_update() - add data to message digest for processing * @req: ahash_request handle that was previously initialized with the * crypto_ahash_init call. * * Updates the message digest state of the &ahash_request handle. The input data * is pointed to by the scatter/gather list registered in the &ahash_request * handle * * Return: see crypto_ahash_final() */ int crypto_ahash_update(struct ahash_request *req); /** * DOC: Asynchronous Hash Request Handle * * The &ahash_request data structure contains all pointers to data * required for the asynchronous cipher operation. This includes the cipher * handle (which can be used by multiple &ahash_request instances), pointer * to plaintext and the message digest output buffer, asynchronous callback * function, etc. It acts as a handle to the ahash_request_* API calls in a * similar way as ahash handle to the crypto_ahash_* API calls. */ /** * ahash_request_set_tfm() - update cipher handle reference in request * @req: request handle to be modified * @tfm: cipher handle that shall be added to the request handle * * Allow the caller to replace the existing ahash handle in the request * data structure with a different one. */ static inline void ahash_request_set_tfm(struct ahash_request *req, struct crypto_ahash *tfm) { req->base.tfm = crypto_ahash_tfm(tfm); } /** * ahash_request_alloc() - allocate request data structure * @tfm: cipher handle to be registered with the request * @gfp: memory allocation flag that is handed to kmalloc by the API call. * * Allocate the request data structure that must be used with the ahash * message digest API calls. During * the allocation, the provided ahash handle * is registered in the request data structure. * * Return: allocated request handle in case of success, or NULL if out of memory */ static inline struct ahash_request *ahash_request_alloc_noprof( struct crypto_ahash *tfm, gfp_t gfp) { struct ahash_request *req; req = kmalloc_noprof(sizeof(struct ahash_request) + crypto_ahash_reqsize(tfm), gfp); if (likely(req)) ahash_request_set_tfm(req, tfm); return req; } #define ahash_request_alloc(...) alloc_hooks(ahash_request_alloc_noprof(__VA_ARGS__)) /** * ahash_request_free() - zeroize and free the request data structure * @req: request data structure cipher handle to be freed */ static inline void ahash_request_free(struct ahash_request *req) { kfree_sensitive(req); } static inline void ahash_request_zero(struct ahash_request *req) { memzero_explicit(req, sizeof(*req) + crypto_ahash_reqsize(crypto_ahash_reqtfm(req))); } static inline struct ahash_request *ahash_request_cast( struct crypto_async_request *req) { return container_of(req, struct ahash_request, base); } /** * ahash_request_set_callback() - set asynchronous callback function * @req: request handle * @flags: specify zero or an ORing of the flags * CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and * increase the wait queue beyond the initial maximum size; * CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep * @compl: callback function pointer to be registered with the request handle * @data: The data pointer refers to memory that is not used by the kernel * crypto API, but provided to the callback function for it to use. Here, * the caller can provide a reference to memory the callback function can * operate on. As the callback function is invoked asynchronously to the * related functionality, it may need to access data structures of the * related functionality which can be referenced using this pointer. The * callback function can access the memory via the "data" field in the * &crypto_async_request data structure provided to the callback function. * * This function allows setting the callback function that is triggered once * the cipher operation completes. * * The callback function is registered with the &ahash_request handle and * must comply with the following template:: * * void callback_function(struct crypto_async_request *req, int error) */ static inline void ahash_request_set_callback(struct ahash_request *req, u32 flags, crypto_completion_t compl, void *data) { req->base.complete = compl; req->base.data = data; req->base.flags = flags; } /** * ahash_request_set_crypt() - set data buffers * @req: ahash_request handle to be updated * @src: source scatter/gather list * @result: buffer that is filled with the message digest -- the caller must * ensure that the buffer has sufficient space by, for example, calling * crypto_ahash_digestsize() * @nbytes: number of bytes to process from the source scatter/gather list * * By using this call, the caller references the source scatter/gather list. * The source scatter/gather list points to the data the message digest is to * be calculated for. */ static inline void ahash_request_set_crypt(struct ahash_request *req, struct scatterlist *src, u8 *result, unsigned int nbytes) { req->src = src; req->nbytes = nbytes; req->result = result; } /** * DOC: Synchronous Message Digest API * * The synchronous message digest API is used with the ciphers of type * CRYPTO_ALG_TYPE_SHASH (listed as type "shash" in /proc/crypto) * * The message digest API is able to maintain state information for the * caller. * * The synchronous message digest API can store user-related context in its * shash_desc request data structure. */ /** * crypto_alloc_shash() - allocate message digest handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * message digest cipher * @type: specifies the type of the cipher * @mask: specifies the mask for the cipher * * Allocate a cipher handle for a message digest. The returned &struct * crypto_shash is the cipher handle that is required for any subsequent * API invocation for that message digest. * * Return: allocated cipher handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_shash *crypto_alloc_shash(const char *alg_name, u32 type, u32 mask); struct crypto_shash *crypto_clone_shash(struct crypto_shash *tfm); int crypto_has_shash(const char *alg_name, u32 type, u32 mask); static inline struct crypto_tfm *crypto_shash_tfm(struct crypto_shash *tfm) { return &tfm->base; } /** * crypto_free_shash() - zeroize and free the message digest handle * @tfm: cipher handle to be freed * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_shash(struct crypto_shash *tfm) { crypto_destroy_tfm(tfm, crypto_shash_tfm(tfm)); } static inline const char *crypto_shash_alg_name(struct crypto_shash *tfm) { return crypto_tfm_alg_name(crypto_shash_tfm(tfm)); } static inline const char *crypto_shash_driver_name(struct crypto_shash *tfm) { return crypto_tfm_alg_driver_name(crypto_shash_tfm(tfm)); } /** * crypto_shash_blocksize() - obtain block size for cipher * @tfm: cipher handle * * The block size for the message digest cipher referenced with the cipher * handle is returned. * * Return: block size of cipher */ static inline unsigned int crypto_shash_blocksize(struct crypto_shash *tfm) { return crypto_tfm_alg_blocksize(crypto_shash_tfm(tfm)); } static inline struct shash_alg *__crypto_shash_alg(struct crypto_alg *alg) { return container_of(alg, struct shash_alg, base); } static inline struct shash_alg *crypto_shash_alg(struct crypto_shash *tfm) { return __crypto_shash_alg(crypto_shash_tfm(tfm)->__crt_alg); } /** * crypto_shash_digestsize() - obtain message digest size * @tfm: cipher handle * * The size for the message digest created by the message digest cipher * referenced with the cipher handle is returned. * * Return: digest size of cipher */ static inline unsigned int crypto_shash_digestsize(struct crypto_shash *tfm) { return crypto_shash_alg(tfm)->digestsize; } static inline unsigned int crypto_shash_statesize(struct crypto_shash *tfm) { return crypto_shash_alg(tfm)->statesize; } static inline u32 crypto_shash_get_flags(struct crypto_shash *tfm) { return crypto_tfm_get_flags(crypto_shash_tfm(tfm)); } static inline void crypto_shash_set_flags(struct crypto_shash *tfm, u32 flags) { crypto_tfm_set_flags(crypto_shash_tfm(tfm), flags); } static inline void crypto_shash_clear_flags(struct crypto_shash *tfm, u32 flags) { crypto_tfm_clear_flags(crypto_shash_tfm(tfm), flags); } /** * crypto_shash_descsize() - obtain the operational state size * @tfm: cipher handle * * The size of the operational state the cipher needs during operation is * returned for the hash referenced with the cipher handle. This size is * required to calculate the memory requirements to allow the caller allocating * sufficient memory for operational state. * * The operational state is defined with struct shash_desc where the size of * that data structure is to be calculated as * sizeof(struct shash_desc) + crypto_shash_descsize(alg) * * Return: size of the operational state */ static inline unsigned int crypto_shash_descsize(struct crypto_shash *tfm) { return tfm->descsize; } static inline void *shash_desc_ctx(struct shash_desc *desc) { return desc->__ctx; } /** * crypto_shash_setkey() - set key for message digest * @tfm: cipher handle * @key: buffer holding the key * @keylen: length of the key in bytes * * The caller provided key is set for the keyed message digest cipher. The * cipher handle must point to a keyed message digest cipher in order for this * function to succeed. * * Context: Any context. * Return: 0 if the setting of the key was successful; < 0 if an error occurred */ int crypto_shash_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen); /** * crypto_shash_digest() - calculate message digest for buffer * @desc: see crypto_shash_final() * @data: see crypto_shash_update() * @len: see crypto_shash_update() * @out: see crypto_shash_final() * * This function is a "short-hand" for the function calls of crypto_shash_init, * crypto_shash_update and crypto_shash_final. The parameters have the same * meaning as discussed for those separate three functions. * * Context: Any context. * Return: 0 if the message digest creation was successful; < 0 if an error * occurred */ int crypto_shash_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); /** * crypto_shash_tfm_digest() - calculate message digest for buffer * @tfm: hash transformation object * @data: see crypto_shash_update() * @len: see crypto_shash_update() * @out: see crypto_shash_final() * * This is a simplified version of crypto_shash_digest() for users who don't * want to allocate their own hash descriptor (shash_desc). Instead, * crypto_shash_tfm_digest() takes a hash transformation object (crypto_shash) * directly, and it allocates a hash descriptor on the stack internally. * Note that this stack allocation may be fairly large. * * Context: Any context. * Return: 0 on success; < 0 if an error occurred. */ int crypto_shash_tfm_digest(struct crypto_shash *tfm, const u8 *data, unsigned int len, u8 *out); /** * crypto_shash_export() - extract operational state for message digest * @desc: reference to the operational state handle whose state is exported * @out: output buffer of sufficient size that can hold the hash state * * This function exports the hash state of the operational state handle into the * caller-allocated output buffer out which must have sufficient size (e.g. by * calling crypto_shash_descsize). * * Context: Any context. * Return: 0 if the export creation was successful; < 0 if an error occurred */ int crypto_shash_export(struct shash_desc *desc, void *out); /** * crypto_shash_import() - import operational state * @desc: reference to the operational state handle the state imported into * @in: buffer holding the state * * This function imports the hash state into the operational state handle from * the input buffer. That buffer should have been generated with the * crypto_ahash_export function. * * Context: Any context. * Return: 0 if the import was successful; < 0 if an error occurred */ int crypto_shash_import(struct shash_desc *desc, const void *in); /** * crypto_shash_init() - (re)initialize message digest * @desc: operational state handle that is already filled * * The call (re-)initializes the message digest referenced by the * operational state handle. Any potentially existing state created by * previous operations is discarded. * * Context: Any context. * Return: 0 if the message digest initialization was successful; < 0 if an * error occurred */ static inline int crypto_shash_init(struct shash_desc *desc) { struct crypto_shash *tfm = desc->tfm; if (crypto_shash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return crypto_shash_alg(tfm)->init(desc); } /** * crypto_shash_update() - add data to message digest for processing * @desc: operational state handle that is already initialized * @data: input data to be added to the message digest * @len: length of the input data * * Updates the message digest state of the operational state handle. * * Context: Any context. * Return: 0 if the message digest update was successful; < 0 if an error * occurred */ int crypto_shash_update(struct shash_desc *desc, const u8 *data, unsigned int len); /** * crypto_shash_final() - calculate message digest * @desc: operational state handle that is already filled with data * @out: output buffer filled with the message digest * * Finalize the message digest operation and create the message digest * based on all data added to the cipher handle. The message digest is placed * into the output buffer. The caller must ensure that the output buffer is * large enough by using crypto_shash_digestsize. * * Context: Any context. * Return: 0 if the message digest creation was successful; < 0 if an error * occurred */ int crypto_shash_final(struct shash_desc *desc, u8 *out); /** * crypto_shash_finup() - calculate message digest of buffer * @desc: see crypto_shash_final() * @data: see crypto_shash_update() * @len: see crypto_shash_update() * @out: see crypto_shash_final() * * This function is a "short-hand" for the function calls of * crypto_shash_update and crypto_shash_final. The parameters have the same * meaning as discussed for those separate functions. * * Context: Any context. * Return: 0 if the message digest creation was successful; < 0 if an error * occurred */ int crypto_shash_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); static inline void shash_desc_zero(struct shash_desc *desc) { memzero_explicit(desc, sizeof(*desc) + crypto_shash_descsize(desc->tfm)); } #endif /* _CRYPTO_HASH_H */ |
| 2986 1183 1693 1697 6 138 610 391 391 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMSTAT_H #define _LINUX_VMSTAT_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/mmzone.h> #include <linux/vm_event_item.h> #include <linux/atomic.h> #include <linux/static_key.h> #include <linux/mmdebug.h> extern int sysctl_stat_interval; #ifdef CONFIG_NUMA #define ENABLE_NUMA_STAT 1 #define DISABLE_NUMA_STAT 0 extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); int sysctl_vm_numa_stat_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); #endif struct reclaim_stat { unsigned nr_dirty; unsigned nr_unqueued_dirty; unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; unsigned nr_pageout; unsigned nr_activate[ANON_AND_FILE]; unsigned nr_ref_keep; unsigned nr_unmap_fail; unsigned nr_lazyfree_fail; unsigned nr_demoted; }; /* Stat data for system wide items */ enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, NR_MEMMAP_PAGES, /* page metadata allocated through buddy allocator */ NR_MEMMAP_BOOT_PAGES, /* page metadata allocated through boot allocator */ NR_VM_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. * * Counters should only be incremented and no critical kernel component * should rely on the counter values. * * Counters are handled completely inline. On many platforms the code * generated will simply be the increment of a global address. */ struct vm_event_state { unsigned long event[NR_VM_EVENT_ITEMS]; }; DECLARE_PER_CPU(struct vm_event_state, vm_event_states); /* * vm counters are allowed to be racy. Use raw_cpu_ops to avoid the * local_irq_disable overhead. */ static inline void __count_vm_event(enum vm_event_item item) { raw_cpu_inc(vm_event_states.event[item]); } static inline void count_vm_event(enum vm_event_item item) { this_cpu_inc(vm_event_states.event[item]); } static inline void __count_vm_events(enum vm_event_item item, long delta) { raw_cpu_add(vm_event_states.event[item], delta); } static inline void count_vm_events(enum vm_event_item item, long delta) { this_cpu_add(vm_event_states.event[item], delta); } extern void all_vm_events(unsigned long *); extern void vm_events_fold_cpu(int cpu); #else /* Disable counters */ static inline void count_vm_event(enum vm_event_item item) { } static inline void count_vm_events(enum vm_event_item item, long delta) { } static inline void __count_vm_event(enum vm_event_item item) { } static inline void __count_vm_events(enum vm_event_item item, long delta) { } static inline void all_vm_events(unsigned long *ret) { } static inline void vm_events_fold_cpu(int cpu) { } #endif /* CONFIG_VM_EVENT_COUNTERS */ #ifdef CONFIG_NUMA_BALANCING #define count_vm_numa_event(x) count_vm_event(x) #define count_vm_numa_events(x, y) count_vm_events(x, y) #else #define count_vm_numa_event(x) do {} while (0) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_DEBUG_TLBFLUSH #define count_vm_tlb_event(x) count_vm_event(x) #define count_vm_tlb_events(x, y) count_vm_events(x, y) #else #define count_vm_tlb_event(x) do {} while (0) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif #ifdef CONFIG_PER_VMA_LOCK_STATS #define count_vm_vma_lock_event(x) count_vm_event(x) #else #define count_vm_vma_lock_event(x) do {} while (0) #endif #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) /* * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; extern atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #ifdef CONFIG_NUMA static inline void zone_numa_event_add(long x, struct zone *zone, enum numa_stat_item item) { atomic_long_add(x, &zone->vm_numa_event[item]); atomic_long_add(x, &vm_numa_event[item]); } static inline unsigned long zone_numa_event_state(struct zone *zone, enum numa_stat_item item) { return atomic_long_read(&zone->vm_numa_event[item]); } static inline unsigned long global_numa_event_state(enum numa_stat_item item) { return atomic_long_read(&vm_numa_event[item]); } #endif /* CONFIG_NUMA */ static inline void zone_page_state_add(long x, struct zone *zone, enum zone_stat_item item) { atomic_long_add(x, &zone->vm_stat[item]); atomic_long_add(x, &vm_zone_stat[item]); } static inline void node_page_state_add(long x, struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_add(x, &pgdat->vm_stat[item]); atomic_long_add(x, &vm_node_stat[item]); } static inline unsigned long global_zone_page_state(enum zone_stat_item item) { long x = atomic_long_read(&vm_zone_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state_pages(enum node_stat_item item) { long x = atomic_long_read(&vm_node_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state(enum node_stat_item item) { VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); return global_node_page_state_pages(item); } static inline unsigned long zone_page_state(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * More accurate version that also considers the currently pending * deltas. For that we need to loop over all cpus to find the current * deltas. There is no synchronization so the result cannot be * exactly accurate either. */ static inline unsigned long zone_page_state_snapshot(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_stat_diff[item]; if (x < 0) x = 0; #endif return x; } #ifdef CONFIG_NUMA /* See __count_vm_event comment on why raw_cpu_inc is used. */ static inline void __count_numa_event(struct zone *zone, enum numa_stat_item item) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; raw_cpu_inc(pzstats->vm_numa_event[item]); } static inline void __count_numa_events(struct zone *zone, enum numa_stat_item item, long delta) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; raw_cpu_add(pzstats->vm_numa_event[item], delta); } extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); extern unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); extern void fold_vm_numa_events(void); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #define node_page_state_pages(node, item) global_node_page_state_pages(item) static inline void fold_vm_numa_events(void) { } #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long); void __inc_node_page_state(struct page *, enum node_stat_item); void __dec_node_page_state(struct page *, enum node_stat_item); void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); void mod_node_page_state(struct pglist_data *, enum node_stat_item, long); void inc_node_page_state(struct page *, enum node_stat_item); void dec_node_page_state(struct page *, enum node_stat_item); extern void inc_node_state(struct pglist_data *, enum node_stat_item); extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void __inc_node_state(struct pglist_data *, enum node_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_node_state(struct pglist_data *, enum node_stat_item); void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); struct ctl_table; int vmstat_refresh(const struct ctl_table *, int write, void *buffer, size_t *lenp, loff_t *ppos); void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *); int calculate_pressure_threshold(struct zone *zone); int calculate_normal_threshold(struct zone *zone); void set_pgdat_percpu_threshold(pg_data_t *pgdat, int (*calculate_pressure)(struct zone *)); #else /* CONFIG_SMP */ /* * We do not maintain differentials in a single processor configuration. * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { if (vmstat_item_in_bytes(item)) { /* * Only cgroups use subpage accounting right now; at * the global level, these items still change in * multiples of whole pages. Store them as pages * internally to keep the per-cpu counters compact. */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } node_page_state_add(delta, pgdat, item); } static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_inc(&zone->vm_stat[item]); atomic_long_inc(&vm_zone_stat[item]); } static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_inc(&pgdat->vm_stat[item]); atomic_long_inc(&vm_node_stat[item]); } static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_dec(&zone->vm_stat[item]); atomic_long_dec(&vm_zone_stat[item]); } static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_dec(&pgdat->vm_stat[item]); atomic_long_dec(&vm_node_stat[item]); } static inline void __inc_zone_page_state(struct page *page, enum zone_stat_item item) { __inc_zone_state(page_zone(page), item); } static inline void __inc_node_page_state(struct page *page, enum node_stat_item item) { __inc_node_state(page_pgdat(page), item); } static inline void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } static inline void __dec_node_page_state(struct page *page, enum node_stat_item item) { __dec_node_state(page_pgdat(page), item); } /* * We only use atomic operations to update counters. So there is no need to * disable interrupts. */ #define inc_zone_page_state __inc_zone_page_state #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state #define inc_node_page_state __inc_node_page_state #define dec_node_page_state __dec_node_page_state #define mod_node_page_state __mod_node_page_state #define inc_zone_state __inc_zone_state #define inc_node_state __inc_node_state #define dec_zone_state __dec_zone_state #define set_pgdat_percpu_threshold(pgdat, callback) { } static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *pzstats) { } #endif /* CONFIG_SMP */ static inline void __zone_stat_mod_folio(struct folio *folio, enum zone_stat_item item, long nr) { __mod_zone_page_state(folio_zone(folio), item, nr); } static inline void __zone_stat_add_folio(struct folio *folio, enum zone_stat_item item) { __mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); } static inline void __zone_stat_sub_folio(struct folio *folio, enum zone_stat_item item) { __mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); } static inline void zone_stat_mod_folio(struct folio *folio, enum zone_stat_item item, long nr) { mod_zone_page_state(folio_zone(folio), item, nr); } static inline void zone_stat_add_folio(struct folio *folio, enum zone_stat_item item) { mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); } static inline void zone_stat_sub_folio(struct folio *folio, enum zone_stat_item item) { mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); } static inline void __node_stat_mod_folio(struct folio *folio, enum node_stat_item item, long nr) { __mod_node_page_state(folio_pgdat(folio), item, nr); } static inline void __node_stat_add_folio(struct folio *folio, enum node_stat_item item) { __mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); } static inline void __node_stat_sub_folio(struct folio *folio, enum node_stat_item item) { __mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); } static inline void node_stat_mod_folio(struct folio *folio, enum node_stat_item item, long nr) { mod_node_page_state(folio_pgdat(folio), item, nr); } static inline void node_stat_add_folio(struct folio *folio, enum node_stat_item item) { mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); } static inline void node_stat_sub_folio(struct folio *folio, enum node_stat_item item) { mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); } extern const char * const vmstat_text[]; static inline const char *zone_stat_name(enum zone_stat_item item) { return vmstat_text[item]; } #ifdef CONFIG_NUMA static inline const char *numa_stat_name(enum numa_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + item]; } #endif /* CONFIG_NUMA */ static inline const char *node_stat_name(enum node_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + item]; } static inline const char *lru_list_name(enum lru_list lru) { return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" } #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + NR_VM_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ #ifdef CONFIG_MEMCG void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_state(lruvec, idx, val); local_irq_restore(flags); } void __lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val); static inline void lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __lruvec_stat_mod_folio(folio, idx, val); local_irq_restore(flags); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { lruvec_stat_mod_folio(page_folio(page), idx, val); } #else static inline void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void __lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val) { __mod_node_page_state(folio_pgdat(folio), idx, val); } static inline void lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val) { mod_node_page_state(folio_pgdat(folio), idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { mod_node_page_state(page_pgdat(page), idx, val); } #endif /* CONFIG_MEMCG */ static inline void __lruvec_stat_add_folio(struct folio *folio, enum node_stat_item idx) { __lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio)); } static inline void __lruvec_stat_sub_folio(struct folio *folio, enum node_stat_item idx) { __lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } static inline void lruvec_stat_add_folio(struct folio *folio, enum node_stat_item idx) { lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio)); } static inline void lruvec_stat_sub_folio(struct folio *folio, enum node_stat_item idx) { lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } void memmap_boot_pages_add(long delta); void memmap_pages_add(long delta); #endif /* _LINUX_VMSTAT_H */ |
| 6 2 1 1 2 2 2 6 2 2 2 1 1 6 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2000-2001 Christoph Hellwig. * Copyright (c) 2016 Krzysztof Blaszkowski */ /* * Veritas filesystem driver - superblock related routines. */ #include <linux/init.h> #include <linux/module.h> #include <linux/blkdev.h> #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/stat.h> #include <linux/vfs.h> #include <linux/fs_context.h> #include "vxfs.h" #include "vxfs_extern.h" #include "vxfs_dir.h" #include "vxfs_inode.h" MODULE_AUTHOR("Christoph Hellwig, Krzysztof Blaszkowski"); MODULE_DESCRIPTION("Veritas Filesystem (VxFS) driver"); MODULE_LICENSE("Dual BSD/GPL"); static struct kmem_cache *vxfs_inode_cachep; /** * vxfs_put_super - free superblock resources * @sbp: VFS superblock. * * Description: * vxfs_put_super frees all resources allocated for @sbp * after the last instance of the filesystem is unmounted. */ static void vxfs_put_super(struct super_block *sbp) { struct vxfs_sb_info *infp = VXFS_SBI(sbp); iput(infp->vsi_fship); iput(infp->vsi_ilist); iput(infp->vsi_stilist); brelse(infp->vsi_bp); kfree(infp); } /** * vxfs_statfs - get filesystem information * @dentry: VFS dentry to locate superblock * @bufp: output buffer * * Description: * vxfs_statfs fills the statfs buffer @bufp with information * about the filesystem described by @dentry. * * Returns: * Zero. * * Locking: * No locks held. * * Notes: * This is everything but complete... */ static int vxfs_statfs(struct dentry *dentry, struct kstatfs *bufp) { struct vxfs_sb_info *infp = VXFS_SBI(dentry->d_sb); struct vxfs_sb *raw_sb = infp->vsi_raw; u64 id = huge_encode_dev(dentry->d_sb->s_bdev->bd_dev); bufp->f_type = VXFS_SUPER_MAGIC; bufp->f_bsize = dentry->d_sb->s_blocksize; bufp->f_blocks = fs32_to_cpu(infp, raw_sb->vs_dsize); bufp->f_bfree = fs32_to_cpu(infp, raw_sb->vs_free); bufp->f_bavail = 0; bufp->f_files = 0; bufp->f_ffree = fs32_to_cpu(infp, raw_sb->vs_ifree); bufp->f_fsid = u64_to_fsid(id); bufp->f_namelen = VXFS_NAMELEN; return 0; } static int vxfs_reconfigure(struct fs_context *fc) { sync_filesystem(fc->root->d_sb); fc->sb_flags |= SB_RDONLY; return 0; } static struct inode *vxfs_alloc_inode(struct super_block *sb) { struct vxfs_inode_info *vi; vi = alloc_inode_sb(sb, vxfs_inode_cachep, GFP_KERNEL); if (!vi) return NULL; inode_init_once(&vi->vfs_inode); return &vi->vfs_inode; } static void vxfs_free_inode(struct inode *inode) { kmem_cache_free(vxfs_inode_cachep, VXFS_INO(inode)); } static const struct super_operations vxfs_super_ops = { .alloc_inode = vxfs_alloc_inode, .free_inode = vxfs_free_inode, .evict_inode = vxfs_evict_inode, .put_super = vxfs_put_super, .statfs = vxfs_statfs, }; static int vxfs_try_sb_magic(struct super_block *sbp, struct fs_context *fc, unsigned blk, __fs32 magic) { struct buffer_head *bp; struct vxfs_sb *rsbp; struct vxfs_sb_info *infp = VXFS_SBI(sbp); int silent = fc->sb_flags & SB_SILENT; int rc = -ENOMEM; bp = sb_bread(sbp, blk); do { if (!bp || !buffer_mapped(bp)) { if (!silent) { warnf(fc, "vxfs: unable to read disk superblock at %u", blk); } break; } rc = -EINVAL; rsbp = (struct vxfs_sb *)bp->b_data; if (rsbp->vs_magic != magic) { if (!silent) infof(fc, "vxfs: WRONG superblock magic %08x at %u", rsbp->vs_magic, blk); break; } rc = 0; infp->vsi_raw = rsbp; infp->vsi_bp = bp; } while (0); if (rc) { infp->vsi_raw = NULL; infp->vsi_bp = NULL; brelse(bp); } return rc; } /** * vxfs_fill_super - read superblock into memory and initialize filesystem * @sbp: VFS superblock (to fill) * @fc: filesytem context * * Description: * We are called on the first mount of a filesystem to read the * superblock into memory and do some basic setup. * * Returns: * The superblock on success, else %NULL. * * Locking: * We are under @sbp->s_lock. */ static int vxfs_fill_super(struct super_block *sbp, struct fs_context *fc) { struct vxfs_sb_info *infp; struct vxfs_sb *rsbp; u_long bsize; struct inode *root; int ret = -EINVAL; int silent = fc->sb_flags & SB_SILENT; u32 j; sbp->s_flags |= SB_RDONLY; infp = kzalloc(sizeof(*infp), GFP_KERNEL); if (!infp) { warnf(fc, "vxfs: unable to allocate incore superblock"); return -ENOMEM; } bsize = sb_min_blocksize(sbp, BLOCK_SIZE); if (!bsize) { warnf(fc, "vxfs: unable to set blocksize"); goto out; } sbp->s_op = &vxfs_super_ops; sbp->s_fs_info = infp; sbp->s_time_min = 0; sbp->s_time_max = U32_MAX; if (!vxfs_try_sb_magic(sbp, fc, 1, (__force __fs32)cpu_to_le32(VXFS_SUPER_MAGIC))) { /* Unixware, x86 */ infp->byte_order = VXFS_BO_LE; } else if (!vxfs_try_sb_magic(sbp, fc, 8, (__force __fs32)cpu_to_be32(VXFS_SUPER_MAGIC))) { /* HP-UX, parisc */ infp->byte_order = VXFS_BO_BE; } else { if (!silent) infof(fc, "vxfs: can't find superblock."); goto out; } rsbp = infp->vsi_raw; j = fs32_to_cpu(infp, rsbp->vs_version); if ((j < 2 || j > 4) && !silent) { infof(fc, "vxfs: unsupported VxFS version (%d)", j); goto out; } #ifdef DIAGNOSTIC printk(KERN_DEBUG "vxfs: supported VxFS version (%d)\n", j); printk(KERN_DEBUG "vxfs: blocksize: %d\n", fs32_to_cpu(infp, rsbp->vs_bsize)); #endif sbp->s_magic = fs32_to_cpu(infp, rsbp->vs_magic); infp->vsi_oltext = fs32_to_cpu(infp, rsbp->vs_oltext[0]); infp->vsi_oltsize = fs32_to_cpu(infp, rsbp->vs_oltsize); j = fs32_to_cpu(infp, rsbp->vs_bsize); if (!sb_set_blocksize(sbp, j)) { warnf(fc, "vxfs: unable to set final block size"); goto out; } if (vxfs_read_olt(sbp, bsize)) { warnf(fc, "vxfs: unable to read olt"); goto out; } if (vxfs_read_fshead(sbp)) { warnf(fc, "vxfs: unable to read fshead"); goto out; } root = vxfs_iget(sbp, VXFS_ROOT_INO); if (IS_ERR(root)) { ret = PTR_ERR(root); goto out; } sbp->s_root = d_make_root(root); if (!sbp->s_root) { warnf(fc, "vxfs: unable to get root dentry."); goto out_free_ilist; } return 0; out_free_ilist: iput(infp->vsi_fship); iput(infp->vsi_ilist); iput(infp->vsi_stilist); out: brelse(infp->vsi_bp); kfree(infp); return ret; } /* * The usual module blurb. */ static int vxfs_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, vxfs_fill_super); } static const struct fs_context_operations vxfs_context_ops = { .get_tree = vxfs_get_tree, .reconfigure = vxfs_reconfigure, }; static int vxfs_init_fs_context(struct fs_context *fc) { fc->ops = &vxfs_context_ops; return 0; } static struct file_system_type vxfs_fs_type = { .owner = THIS_MODULE, .name = "vxfs", .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = vxfs_init_fs_context, }; MODULE_ALIAS_FS("vxfs"); /* makes mount -t vxfs autoload the module */ MODULE_ALIAS("vxfs"); static int __init vxfs_init(void) { int rv; vxfs_inode_cachep = kmem_cache_create_usercopy("vxfs_inode", sizeof(struct vxfs_inode_info), 0, SLAB_RECLAIM_ACCOUNT, offsetof(struct vxfs_inode_info, vii_immed.vi_immed), sizeof_field(struct vxfs_inode_info, vii_immed.vi_immed), NULL); if (!vxfs_inode_cachep) return -ENOMEM; rv = register_filesystem(&vxfs_fs_type); if (rv < 0) kmem_cache_destroy(vxfs_inode_cachep); return rv; } static void __exit vxfs_cleanup(void) { unregister_filesystem(&vxfs_fs_type); /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(vxfs_inode_cachep); } module_init(vxfs_init); module_exit(vxfs_cleanup); |
| 143 132 18 268 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 | /* * Copyright (c) 1982, 1986 Regents of the University of California. * All rights reserved. * * This code is derived from software contributed to Berkeley by * Robert Elz at The University of Melbourne. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ #ifndef _LINUX_QUOTA_ #define _LINUX_QUOTA_ #include <linux/list.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/spinlock.h> #include <linux/wait.h> #include <linux/percpu_counter.h> #include <linux/dqblk_xfs.h> #include <linux/dqblk_v1.h> #include <linux/dqblk_v2.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/projid.h> #include <uapi/linux/quota.h> #undef USRQUOTA #undef GRPQUOTA #undef PRJQUOTA enum quota_type { USRQUOTA = 0, /* element used for user quotas */ GRPQUOTA = 1, /* element used for group quotas */ PRJQUOTA = 2, /* element used for project quotas */ }; /* Masks for quota types when used as a bitmask */ #define QTYPE_MASK_USR (1 << USRQUOTA) #define QTYPE_MASK_GRP (1 << GRPQUOTA) #define QTYPE_MASK_PRJ (1 << PRJQUOTA) typedef __kernel_uid32_t qid_t; /* Type in which we store ids in memory */ typedef long long qsize_t; /* Type in which we store sizes */ struct kqid { /* Type in which we store the quota identifier */ union { kuid_t uid; kgid_t gid; kprojid_t projid; }; enum quota_type type; /* USRQUOTA (uid) or GRPQUOTA (gid) or PRJQUOTA (projid) */ }; extern bool qid_eq(struct kqid left, struct kqid right); extern bool qid_lt(struct kqid left, struct kqid right); extern qid_t from_kqid(struct user_namespace *to, struct kqid qid); extern qid_t from_kqid_munged(struct user_namespace *to, struct kqid qid); extern bool qid_valid(struct kqid qid); /** * make_kqid - Map a user-namespace, type, qid tuple into a kqid. * @from: User namespace that the qid is in * @type: The type of quota * @qid: Quota identifier * * Maps a user-namespace, type qid tuple into a kernel internal * kqid, and returns that kqid. * * When there is no mapping defined for the user-namespace, type, * qid tuple an invalid kqid is returned. Callers are expected to * test for and handle invalid kqids being returned. * Invalid kqids may be tested for using qid_valid(). */ static inline struct kqid make_kqid(struct user_namespace *from, enum quota_type type, qid_t qid) { struct kqid kqid; kqid.type = type; switch (type) { case USRQUOTA: kqid.uid = make_kuid(from, qid); break; case GRPQUOTA: kqid.gid = make_kgid(from, qid); break; case PRJQUOTA: kqid.projid = make_kprojid(from, qid); break; default: BUG(); } return kqid; } /** * make_kqid_invalid - Explicitly make an invalid kqid * @type: The type of quota identifier * * Returns an invalid kqid with the specified type. */ static inline struct kqid make_kqid_invalid(enum quota_type type) { struct kqid kqid; kqid.type = type; switch (type) { case USRQUOTA: kqid.uid = INVALID_UID; break; case GRPQUOTA: kqid.gid = INVALID_GID; break; case PRJQUOTA: kqid.projid = INVALID_PROJID; break; default: BUG(); } return kqid; } /** * make_kqid_uid - Make a kqid from a kuid * @uid: The kuid to make the quota identifier from */ static inline struct kqid make_kqid_uid(kuid_t uid) { struct kqid kqid; kqid.type = USRQUOTA; kqid.uid = uid; return kqid; } /** * make_kqid_gid - Make a kqid from a kgid * @gid: The kgid to make the quota identifier from */ static inline struct kqid make_kqid_gid(kgid_t gid) { struct kqid kqid; kqid.type = GRPQUOTA; kqid.gid = gid; return kqid; } /** * make_kqid_projid - Make a kqid from a projid * @projid: The kprojid to make the quota identifier from */ static inline struct kqid make_kqid_projid(kprojid_t projid) { struct kqid kqid; kqid.type = PRJQUOTA; kqid.projid = projid; return kqid; } /** * qid_has_mapping - Report if a qid maps into a user namespace. * @ns: The user namespace to see if a value maps into. * @qid: The kernel internal quota identifier to test. */ static inline bool qid_has_mapping(struct user_namespace *ns, struct kqid qid) { return from_kqid(ns, qid) != (qid_t) -1; } extern spinlock_t dq_data_lock; /* Maximal numbers of writes for quota operation (insert/delete/update) * (over VFS all formats) */ #define DQUOT_INIT_ALLOC max(V1_INIT_ALLOC, V2_INIT_ALLOC) #define DQUOT_INIT_REWRITE max(V1_INIT_REWRITE, V2_INIT_REWRITE) #define DQUOT_DEL_ALLOC max(V1_DEL_ALLOC, V2_DEL_ALLOC) #define DQUOT_DEL_REWRITE max(V1_DEL_REWRITE, V2_DEL_REWRITE) /* * Data for one user/group kept in memory */ struct mem_dqblk { qsize_t dqb_bhardlimit; /* absolute limit on disk blks alloc */ qsize_t dqb_bsoftlimit; /* preferred limit on disk blks */ qsize_t dqb_curspace; /* current used space */ qsize_t dqb_rsvspace; /* current reserved space for delalloc*/ qsize_t dqb_ihardlimit; /* absolute limit on allocated inodes */ qsize_t dqb_isoftlimit; /* preferred inode limit */ qsize_t dqb_curinodes; /* current # allocated inodes */ time64_t dqb_btime; /* time limit for excessive disk use */ time64_t dqb_itime; /* time limit for excessive inode use */ }; /* * Data for one quotafile kept in memory */ struct quota_format_type; struct mem_dqinfo { struct quota_format_type *dqi_format; int dqi_fmt_id; /* Id of the dqi_format - used when turning * quotas on after remount RW */ struct list_head dqi_dirty_list; /* List of dirty dquots [dq_list_lock] */ unsigned long dqi_flags; /* DFQ_ flags [dq_data_lock] */ unsigned int dqi_bgrace; /* Space grace time [dq_data_lock] */ unsigned int dqi_igrace; /* Inode grace time [dq_data_lock] */ qsize_t dqi_max_spc_limit; /* Maximum space limit [static] */ qsize_t dqi_max_ino_limit; /* Maximum inode limit [static] */ void *dqi_priv; }; struct super_block; /* Mask for flags passed to userspace */ #define DQF_GETINFO_MASK (DQF_ROOT_SQUASH | DQF_SYS_FILE) /* Mask for flags modifiable from userspace */ #define DQF_SETINFO_MASK DQF_ROOT_SQUASH enum { DQF_INFO_DIRTY_B = DQF_PRIVATE, }; #define DQF_INFO_DIRTY (1 << DQF_INFO_DIRTY_B) /* Is info dirty? */ extern void mark_info_dirty(struct super_block *sb, int type); static inline int info_dirty(struct mem_dqinfo *info) { return test_bit(DQF_INFO_DIRTY_B, &info->dqi_flags); } enum { DQST_LOOKUPS, DQST_DROPS, DQST_READS, DQST_WRITES, DQST_CACHE_HITS, DQST_ALLOC_DQUOTS, DQST_FREE_DQUOTS, DQST_SYNCS, _DQST_DQSTAT_LAST }; struct dqstats { unsigned long stat[_DQST_DQSTAT_LAST]; struct percpu_counter counter[_DQST_DQSTAT_LAST]; }; extern struct dqstats dqstats; static inline void dqstats_inc(unsigned int type) { percpu_counter_inc(&dqstats.counter[type]); } static inline void dqstats_dec(unsigned int type) { percpu_counter_dec(&dqstats.counter[type]); } #define DQ_MOD_B 0 /* dquot modified since read */ #define DQ_BLKS_B 1 /* uid/gid has been warned about blk limit */ #define DQ_INODES_B 2 /* uid/gid has been warned about inode limit */ #define DQ_FAKE_B 3 /* no limits only usage */ #define DQ_READ_B 4 /* dquot was read into memory */ #define DQ_ACTIVE_B 5 /* dquot is active (dquot_release not called) */ #define DQ_RELEASING_B 6 /* dquot is in releasing_dquots list waiting * to be cleaned up */ #define DQ_LASTSET_B 7 /* Following 6 bits (see QIF_) are reserved\ * for the mask of entries set via SETQUOTA\ * quotactl. They are set under dq_data_lock\ * and the quota format handling dquot can\ * clear them when it sees fit. */ struct dquot { struct hlist_node dq_hash; /* Hash list in memory [dq_list_lock] */ struct list_head dq_inuse; /* List of all quotas [dq_list_lock] */ struct list_head dq_free; /* Free list element [dq_list_lock] */ struct list_head dq_dirty; /* List of dirty dquots [dq_list_lock] */ struct mutex dq_lock; /* dquot IO lock */ spinlock_t dq_dqb_lock; /* Lock protecting dq_dqb changes */ atomic_t dq_count; /* Use count */ struct super_block *dq_sb; /* superblock this applies to */ struct kqid dq_id; /* ID this applies to (uid, gid, projid) */ loff_t dq_off; /* Offset of dquot on disk [dq_lock, stable once set] */ unsigned long dq_flags; /* See DQ_* */ struct mem_dqblk dq_dqb; /* Diskquota usage [dq_dqb_lock] */ }; /* Operations which must be implemented by each quota format */ struct quota_format_ops { int (*check_quota_file)(struct super_block *sb, int type); /* Detect whether file is in our format */ int (*read_file_info)(struct super_block *sb, int type); /* Read main info about file - called on quotaon() */ int (*write_file_info)(struct super_block *sb, int type); /* Write main info about file */ int (*free_file_info)(struct super_block *sb, int type); /* Called on quotaoff() */ int (*read_dqblk)(struct dquot *dquot); /* Read structure for one user */ int (*commit_dqblk)(struct dquot *dquot); /* Write structure for one user */ int (*release_dqblk)(struct dquot *dquot); /* Called when last reference to dquot is being dropped */ int (*get_next_id)(struct super_block *sb, struct kqid *qid); /* Get next ID with existing structure in the quota file */ }; /* Operations working with dquots */ struct dquot_operations { int (*write_dquot) (struct dquot *); /* Ordinary dquot write */ struct dquot *(*alloc_dquot)(struct super_block *, int); /* Allocate memory for new dquot */ void (*destroy_dquot)(struct dquot *); /* Free memory for dquot */ int (*acquire_dquot) (struct dquot *); /* Quota is going to be created on disk */ int (*release_dquot) (struct dquot *); /* Quota is going to be deleted from disk */ int (*mark_dirty) (struct dquot *); /* Dquot is marked dirty */ int (*write_info) (struct super_block *, int); /* Write of quota "superblock" */ /* get reserved quota for delayed alloc, value returned is managed by * quota code only */ qsize_t *(*get_reserved_space) (struct inode *); int (*get_projid) (struct inode *, kprojid_t *);/* Get project ID */ /* Get number of inodes that were charged for a given inode */ int (*get_inode_usage) (struct inode *, qsize_t *); /* Get next ID with active quota structure */ int (*get_next_id) (struct super_block *sb, struct kqid *qid); }; struct path; /* Structure for communicating via ->get_dqblk() & ->set_dqblk() */ struct qc_dqblk { int d_fieldmask; /* mask of fields to change in ->set_dqblk() */ u64 d_spc_hardlimit; /* absolute limit on used space */ u64 d_spc_softlimit; /* preferred limit on used space */ u64 d_ino_hardlimit; /* maximum # allocated inodes */ u64 d_ino_softlimit; /* preferred inode limit */ u64 d_space; /* Space owned by the user */ u64 d_ino_count; /* # inodes owned by the user */ s64 d_ino_timer; /* zero if within inode limits */ /* if not, we refuse service */ s64 d_spc_timer; /* similar to above; for space */ int d_ino_warns; /* # warnings issued wrt num inodes */ int d_spc_warns; /* # warnings issued wrt used space */ u64 d_rt_spc_hardlimit; /* absolute limit on realtime space */ u64 d_rt_spc_softlimit; /* preferred limit on RT space */ u64 d_rt_space; /* realtime space owned */ s64 d_rt_spc_timer; /* similar to above; for RT space */ int d_rt_spc_warns; /* # warnings issued wrt RT space */ }; /* * Field specifiers for ->set_dqblk() in struct qc_dqblk and also for * ->set_info() in struct qc_info */ #define QC_INO_SOFT (1<<0) #define QC_INO_HARD (1<<1) #define QC_SPC_SOFT (1<<2) #define QC_SPC_HARD (1<<3) #define QC_RT_SPC_SOFT (1<<4) #define QC_RT_SPC_HARD (1<<5) #define QC_LIMIT_MASK (QC_INO_SOFT | QC_INO_HARD | QC_SPC_SOFT | QC_SPC_HARD | \ QC_RT_SPC_SOFT | QC_RT_SPC_HARD) #define QC_SPC_TIMER (1<<6) #define QC_INO_TIMER (1<<7) #define QC_RT_SPC_TIMER (1<<8) #define QC_TIMER_MASK (QC_SPC_TIMER | QC_INO_TIMER | QC_RT_SPC_TIMER) #define QC_SPC_WARNS (1<<9) #define QC_INO_WARNS (1<<10) #define QC_RT_SPC_WARNS (1<<11) #define QC_WARNS_MASK (QC_SPC_WARNS | QC_INO_WARNS | QC_RT_SPC_WARNS) #define QC_SPACE (1<<12) #define QC_INO_COUNT (1<<13) #define QC_RT_SPACE (1<<14) #define QC_ACCT_MASK (QC_SPACE | QC_INO_COUNT | QC_RT_SPACE) #define QC_FLAGS (1<<15) #define QCI_SYSFILE (1 << 0) /* Quota file is hidden from userspace */ #define QCI_ROOT_SQUASH (1 << 1) /* Root squash turned on */ #define QCI_ACCT_ENABLED (1 << 2) /* Quota accounting enabled */ #define QCI_LIMITS_ENFORCED (1 << 3) /* Quota limits enforced */ /* Structures for communicating via ->get_state */ struct qc_type_state { unsigned int flags; /* Flags QCI_* */ unsigned int spc_timelimit; /* Time after which space softlimit is * enforced */ unsigned int ino_timelimit; /* Ditto for inode softlimit */ unsigned int rt_spc_timelimit; /* Ditto for real-time space */ unsigned int spc_warnlimit; /* Limit for number of space warnings */ unsigned int ino_warnlimit; /* Ditto for inodes */ unsigned int rt_spc_warnlimit; /* Ditto for real-time space */ unsigned long long ino; /* Inode number of quota file */ blkcnt_t blocks; /* Number of 512-byte blocks in the file */ blkcnt_t nextents; /* Number of extents in the file */ }; struct qc_state { unsigned int s_incoredqs; /* Number of dquots in core */ struct qc_type_state s_state[MAXQUOTAS]; /* Per quota type information */ }; /* Structure for communicating via ->set_info */ struct qc_info { int i_fieldmask; /* mask of fields to change in ->set_info() */ unsigned int i_flags; /* Flags QCI_* */ unsigned int i_spc_timelimit; /* Time after which space softlimit is * enforced */ unsigned int i_ino_timelimit; /* Ditto for inode softlimit */ unsigned int i_rt_spc_timelimit;/* Ditto for real-time space */ unsigned int i_spc_warnlimit; /* Limit for number of space warnings */ unsigned int i_ino_warnlimit; /* Limit for number of inode warnings */ unsigned int i_rt_spc_warnlimit; /* Ditto for real-time space */ }; /* Operations handling requests from userspace */ struct quotactl_ops { int (*quota_on)(struct super_block *, int, int, const struct path *); int (*quota_off)(struct super_block *, int); int (*quota_enable)(struct super_block *, unsigned int); int (*quota_disable)(struct super_block *, unsigned int); int (*quota_sync)(struct super_block *, int); int (*set_info)(struct super_block *, int, struct qc_info *); int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*get_nextdqblk)(struct super_block *, struct kqid *, struct qc_dqblk *); int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*get_state)(struct super_block *, struct qc_state *); int (*rm_xquota)(struct super_block *, unsigned int); }; struct quota_format_type { int qf_fmt_id; /* Quota format id */ const struct quota_format_ops *qf_ops; /* Operations of format */ struct module *qf_owner; /* Module implementing quota format */ struct quota_format_type *qf_next; }; /** * Quota state flags - they come in three flavors - for users, groups and projects. * * Actual typed flags layout: * USRQUOTA GRPQUOTA PRJQUOTA * DQUOT_USAGE_ENABLED 0x0001 0x0002 0x0004 * DQUOT_LIMITS_ENABLED 0x0008 0x0010 0x0020 * DQUOT_SUSPENDED 0x0040 0x0080 0x0100 * * Following bits are used for non-typed flags: * DQUOT_QUOTA_SYS_FILE 0x0200 * DQUOT_NEGATIVE_USAGE 0x0400 * DQUOT_NOLIST_DIRTY 0x0800 */ enum { _DQUOT_USAGE_ENABLED = 0, /* Track disk usage for users */ _DQUOT_LIMITS_ENABLED, /* Enforce quota limits for users */ _DQUOT_SUSPENDED, /* User diskquotas are off, but * we have necessary info in * memory to turn them on */ _DQUOT_STATE_FLAGS }; #define DQUOT_USAGE_ENABLED (1 << _DQUOT_USAGE_ENABLED * MAXQUOTAS) #define DQUOT_LIMITS_ENABLED (1 << _DQUOT_LIMITS_ENABLED * MAXQUOTAS) #define DQUOT_SUSPENDED (1 << _DQUOT_SUSPENDED * MAXQUOTAS) #define DQUOT_STATE_FLAGS (DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED | \ DQUOT_SUSPENDED) /* Other quota flags */ #define DQUOT_STATE_LAST (_DQUOT_STATE_FLAGS * MAXQUOTAS) #define DQUOT_QUOTA_SYS_FILE (1 << DQUOT_STATE_LAST) /* Quota file is a special * system file and user cannot * touch it. Filesystem is * responsible for setting * S_NOQUOTA, S_NOATIME flags */ #define DQUOT_NEGATIVE_USAGE (1 << (DQUOT_STATE_LAST + 1)) /* Allow negative quota usage */ /* Do not track dirty dquots in a list */ #define DQUOT_NOLIST_DIRTY (1 << (DQUOT_STATE_LAST + 2)) static inline unsigned int dquot_state_flag(unsigned int flags, int type) { return flags << type; } static inline unsigned int dquot_generic_flag(unsigned int flags, int type) { return (flags >> type) & DQUOT_STATE_FLAGS; } /* Bitmap of quota types where flag is set in flags */ static __always_inline unsigned dquot_state_types(unsigned flags, unsigned flag) { BUILD_BUG_ON_NOT_POWER_OF_2(flag); return (flags / flag) & ((1 << MAXQUOTAS) - 1); } #ifdef CONFIG_QUOTA_NETLINK_INTERFACE extern void quota_send_warning(struct kqid qid, dev_t dev, const char warntype); #else static inline void quota_send_warning(struct kqid qid, dev_t dev, const char warntype) { return; } #endif /* CONFIG_QUOTA_NETLINK_INTERFACE */ struct quota_info { unsigned int flags; /* Flags for diskquotas on this device */ struct rw_semaphore dqio_sem; /* Lock quota file while I/O in progress */ struct inode *files[MAXQUOTAS]; /* inodes of quotafiles */ struct mem_dqinfo info[MAXQUOTAS]; /* Information for each quota type */ const struct quota_format_ops *ops[MAXQUOTAS]; /* Operations for each type */ }; void register_quota_format(struct quota_format_type *fmt); void unregister_quota_format(struct quota_format_type *fmt); struct quota_module_name { int qm_fmt_id; char *qm_mod_name; }; #define INIT_QUOTA_MODULE_NAMES {\ {QFMT_VFS_OLD, "quota_v1"},\ {QFMT_VFS_V0, "quota_v2"},\ {QFMT_VFS_V1, "quota_v2"},\ {0, NULL}} #endif /* _QUOTA_ */ |
| 3136 41 1266 6 564 2734 79 2723 2716 1010 2360 2732 2494 2495 313 153 24 153 160 183 152 153 31 7 7 291 292 7 7 6 7 7 7 571 564 564 565 7 292 7 7 7 557 237 326 2618 41 1270 2614 6940 6883 2614 2614 2618 2614 2611 2613 3136 260 3134 3136 3134 259 3136 1282 1279 1283 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. * Authors: David Chinner and Glauber Costa * * Generic LRU infrastructure */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/list_lru.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/memcontrol.h> #include "slab.h" #include "internal.h" #ifdef CONFIG_MEMCG static LIST_HEAD(memcg_list_lrus); static DEFINE_MUTEX(list_lrus_mutex); static inline bool list_lru_memcg_aware(struct list_lru *lru) { return lru->memcg_aware; } static void list_lru_register(struct list_lru *lru) { if (!list_lru_memcg_aware(lru)) return; mutex_lock(&list_lrus_mutex); list_add(&lru->list, &memcg_list_lrus); mutex_unlock(&list_lrus_mutex); } static void list_lru_unregister(struct list_lru *lru) { if (!list_lru_memcg_aware(lru)) return; mutex_lock(&list_lrus_mutex); list_del(&lru->list); mutex_unlock(&list_lrus_mutex); } static int lru_shrinker_id(struct list_lru *lru) { return lru->shrinker_id; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { if (list_lru_memcg_aware(lru) && idx >= 0) { struct list_lru_memcg *mlru = xa_load(&lru->xa, idx); return mlru ? &mlru->node[nid] : NULL; } return &lru->node[nid].lru; } #else static void list_lru_register(struct list_lru *lru) { } static void list_lru_unregister(struct list_lru *lru) { } static int lru_shrinker_id(struct list_lru *lru) { return -1; } static inline bool list_lru_memcg_aware(struct list_lru *lru) { return false; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { return &lru->node[nid].lru; } #endif /* CONFIG_MEMCG */ /* The caller must ensure the memcg lifetime. */ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; spin_lock(&nlru->lock); if (list_empty(item)) { l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); list_add_tail(item, &l->list); /* Set shrinker bit if the first element was added */ if (!l->nr_items++) set_shrinker_bit(memcg, nid, lru_shrinker_id(lru)); nlru->nr_items++; spin_unlock(&nlru->lock); return true; } spin_unlock(&nlru->lock); return false; } EXPORT_SYMBOL_GPL(list_lru_add); bool list_lru_add_obj(struct list_lru *lru, struct list_head *item) { bool ret; int nid = page_to_nid(virt_to_page(item)); if (list_lru_memcg_aware(lru)) { rcu_read_lock(); ret = list_lru_add(lru, item, nid, mem_cgroup_from_slab_obj(item)); rcu_read_unlock(); } else { ret = list_lru_add(lru, item, nid, NULL); } return ret; } EXPORT_SYMBOL_GPL(list_lru_add_obj); /* The caller must ensure the memcg lifetime. */ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; spin_lock(&nlru->lock); if (!list_empty(item)) { l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); list_del_init(item); l->nr_items--; nlru->nr_items--; spin_unlock(&nlru->lock); return true; } spin_unlock(&nlru->lock); return false; } EXPORT_SYMBOL_GPL(list_lru_del); bool list_lru_del_obj(struct list_lru *lru, struct list_head *item) { bool ret; int nid = page_to_nid(virt_to_page(item)); if (list_lru_memcg_aware(lru)) { rcu_read_lock(); ret = list_lru_del(lru, item, nid, mem_cgroup_from_slab_obj(item)); rcu_read_unlock(); } else { ret = list_lru_del(lru, item, nid, NULL); } return ret; } EXPORT_SYMBOL_GPL(list_lru_del_obj); void list_lru_isolate(struct list_lru_one *list, struct list_head *item) { list_del_init(item); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate); void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head) { list_move(item, head); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate_move); unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg) { struct list_lru_one *l; long count; rcu_read_lock(); l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); count = l ? READ_ONCE(l->nr_items) : 0; rcu_read_unlock(); if (unlikely(count < 0)) count = 0; return count; } EXPORT_SYMBOL_GPL(list_lru_count_one); unsigned long list_lru_count_node(struct list_lru *lru, int nid) { struct list_lru_node *nlru; nlru = &lru->node[nid]; return nlru->nr_items; } EXPORT_SYMBOL_GPL(list_lru_count_node); static unsigned long __list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; struct list_head *item, *n; unsigned long isolated = 0; restart: l = list_lru_from_memcg_idx(lru, nid, memcg_idx); if (!l) goto out; list_for_each_safe(item, n, &l->list) { enum lru_status ret; /* * decrement nr_to_walk first so that we don't livelock if we * get stuck on large numbers of LRU_RETRY items */ if (!*nr_to_walk) break; --*nr_to_walk; ret = isolate(item, l, &nlru->lock, cb_arg); switch (ret) { case LRU_REMOVED_RETRY: assert_spin_locked(&nlru->lock); fallthrough; case LRU_REMOVED: isolated++; nlru->nr_items--; /* * If the lru lock has been dropped, our list * traversal is now invalid and so we have to * restart from scratch. */ if (ret == LRU_REMOVED_RETRY) goto restart; break; case LRU_ROTATE: list_move_tail(item, &l->list); break; case LRU_SKIP: break; case LRU_RETRY: /* * The lru lock has been dropped, our list traversal is * now invalid and so we have to restart from scratch. */ assert_spin_locked(&nlru->lock); goto restart; case LRU_STOP: assert_spin_locked(&nlru->lock); goto out; default: BUG(); } } out: return isolated; } unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { struct list_lru_node *nlru = &lru->node[nid]; unsigned long ret; spin_lock(&nlru->lock); ret = __list_lru_walk_one(lru, nid, memcg_kmem_id(memcg), isolate, cb_arg, nr_to_walk); spin_unlock(&nlru->lock); return ret; } EXPORT_SYMBOL_GPL(list_lru_walk_one); unsigned long list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { struct list_lru_node *nlru = &lru->node[nid]; unsigned long ret; spin_lock_irq(&nlru->lock); ret = __list_lru_walk_one(lru, nid, memcg_kmem_id(memcg), isolate, cb_arg, nr_to_walk); spin_unlock_irq(&nlru->lock); return ret; } unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { long isolated = 0; isolated += list_lru_walk_one(lru, nid, NULL, isolate, cb_arg, nr_to_walk); #ifdef CONFIG_MEMCG if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { struct list_lru_memcg *mlru; unsigned long index; xa_for_each(&lru->xa, index, mlru) { struct list_lru_node *nlru = &lru->node[nid]; spin_lock(&nlru->lock); isolated += __list_lru_walk_one(lru, nid, index, isolate, cb_arg, nr_to_walk); spin_unlock(&nlru->lock); if (*nr_to_walk <= 0) break; } } #endif return isolated; } EXPORT_SYMBOL_GPL(list_lru_walk_node); static void init_one_lru(struct list_lru_one *l) { INIT_LIST_HEAD(&l->list); l->nr_items = 0; } #ifdef CONFIG_MEMCG static struct list_lru_memcg *memcg_init_list_lru_one(gfp_t gfp) { int nid; struct list_lru_memcg *mlru; mlru = kmalloc(struct_size(mlru, node, nr_node_ids), gfp); if (!mlru) return NULL; for_each_node(nid) init_one_lru(&mlru->node[nid]); return mlru; } static void memcg_list_lru_free(struct list_lru *lru, int src_idx) { struct list_lru_memcg *mlru = xa_erase_irq(&lru->xa, src_idx); /* * The __list_lru_walk_one() can walk the list of this node. * We need kvfree_rcu() here. And the walking of the list * is under lru->node[nid]->lock, which can serve as a RCU * read-side critical section. */ if (mlru) kvfree_rcu(mlru, rcu); } static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { if (memcg_aware) xa_init_flags(&lru->xa, XA_FLAGS_LOCK_IRQ); lru->memcg_aware = memcg_aware; } static void memcg_destroy_list_lru(struct list_lru *lru) { XA_STATE(xas, &lru->xa, 0); struct list_lru_memcg *mlru; if (!list_lru_memcg_aware(lru)) return; xas_lock_irq(&xas); xas_for_each(&xas, mlru, ULONG_MAX) { kfree(mlru); xas_store(&xas, NULL); } xas_unlock_irq(&xas); } static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid, int src_idx, struct mem_cgroup *dst_memcg) { struct list_lru_node *nlru = &lru->node[nid]; int dst_idx = dst_memcg->kmemcg_id; struct list_lru_one *src, *dst; /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, * we have to use IRQ-safe primitives here to avoid deadlock. */ spin_lock_irq(&nlru->lock); src = list_lru_from_memcg_idx(lru, nid, src_idx); if (!src) goto out; dst = list_lru_from_memcg_idx(lru, nid, dst_idx); list_splice_init(&src->list, &dst->list); if (src->nr_items) { dst->nr_items += src->nr_items; set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); src->nr_items = 0; } out: spin_unlock_irq(&nlru->lock); } static void memcg_reparent_list_lru(struct list_lru *lru, int src_idx, struct mem_cgroup *dst_memcg) { int i; for_each_node(i) memcg_reparent_list_lru_node(lru, i, src_idx, dst_memcg); memcg_list_lru_free(lru, src_idx); } void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent) { struct cgroup_subsys_state *css; struct list_lru *lru; int src_idx = memcg->kmemcg_id; /* * Change kmemcg_id of this cgroup and all its descendants to the * parent's id, and then move all entries from this cgroup's list_lrus * to ones of the parent. * * After we have finished, all list_lrus corresponding to this cgroup * are guaranteed to remain empty. So we can safely free this cgroup's * list lrus in memcg_list_lru_free(). * * Changing ->kmemcg_id to the parent can prevent memcg_list_lru_alloc() * from allocating list lrus for this cgroup after memcg_list_lru_free() * call. */ rcu_read_lock(); css_for_each_descendant_pre(css, &memcg->css) { struct mem_cgroup *child; child = mem_cgroup_from_css(css); WRITE_ONCE(child->kmemcg_id, parent->kmemcg_id); } rcu_read_unlock(); mutex_lock(&list_lrus_mutex); list_for_each_entry(lru, &memcg_list_lrus, list) memcg_reparent_list_lru(lru, src_idx, parent); mutex_unlock(&list_lrus_mutex); } static inline bool memcg_list_lru_allocated(struct mem_cgroup *memcg, struct list_lru *lru) { int idx = memcg->kmemcg_id; return idx < 0 || xa_load(&lru->xa, idx); } int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp) { int i; unsigned long flags; struct list_lru_memcg_table { struct list_lru_memcg *mlru; struct mem_cgroup *memcg; } *table; XA_STATE(xas, &lru->xa, 0); if (!list_lru_memcg_aware(lru) || memcg_list_lru_allocated(memcg, lru)) return 0; gfp &= GFP_RECLAIM_MASK; table = kmalloc_array(memcg->css.cgroup->level, sizeof(*table), gfp); if (!table) return -ENOMEM; /* * Because the list_lru can be reparented to the parent cgroup's * list_lru, we should make sure that this cgroup and all its * ancestors have allocated list_lru_memcg. */ for (i = 0; memcg; memcg = parent_mem_cgroup(memcg), i++) { if (memcg_list_lru_allocated(memcg, lru)) break; table[i].memcg = memcg; table[i].mlru = memcg_init_list_lru_one(gfp); if (!table[i].mlru) { while (i--) kfree(table[i].mlru); kfree(table); return -ENOMEM; } } xas_lock_irqsave(&xas, flags); while (i--) { int index = READ_ONCE(table[i].memcg->kmemcg_id); struct list_lru_memcg *mlru = table[i].mlru; xas_set(&xas, index); retry: if (unlikely(index < 0 || xas_error(&xas) || xas_load(&xas))) { kfree(mlru); } else { xas_store(&xas, mlru); if (xas_error(&xas) == -ENOMEM) { xas_unlock_irqrestore(&xas, flags); if (xas_nomem(&xas, gfp)) xas_set_err(&xas, 0); xas_lock_irqsave(&xas, flags); /* * The xas lock has been released, this memcg * can be reparented before us. So reload * memcg id. More details see the comments * in memcg_reparent_list_lrus(). */ index = READ_ONCE(table[i].memcg->kmemcg_id); if (index < 0) xas_set_err(&xas, 0); else if (!xas_error(&xas) && index != xas.xa_index) xas_set(&xas, index); goto retry; } } } /* xas_nomem() is used to free memory instead of memory allocation. */ if (xas.xa_alloc) xas_nomem(&xas, gfp); xas_unlock_irqrestore(&xas, flags); kfree(table); return xas_error(&xas); } #else static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { } static void memcg_destroy_list_lru(struct list_lru *lru) { } #endif /* CONFIG_MEMCG */ int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct lock_class_key *key, struct shrinker *shrinker) { int i; #ifdef CONFIG_MEMCG if (shrinker) lru->shrinker_id = shrinker->id; else lru->shrinker_id = -1; if (mem_cgroup_kmem_disabled()) memcg_aware = false; #endif lru->node = kcalloc(nr_node_ids, sizeof(*lru->node), GFP_KERNEL); if (!lru->node) return -ENOMEM; for_each_node(i) { spin_lock_init(&lru->node[i].lock); if (key) lockdep_set_class(&lru->node[i].lock, key); init_one_lru(&lru->node[i].lru); } memcg_init_list_lru(lru, memcg_aware); list_lru_register(lru); return 0; } EXPORT_SYMBOL_GPL(__list_lru_init); void list_lru_destroy(struct list_lru *lru) { /* Already destroyed or not yet initialized? */ if (!lru->node) return; list_lru_unregister(lru); memcg_destroy_list_lru(lru); kfree(lru->node); lru->node = NULL; #ifdef CONFIG_MEMCG lru->shrinker_id = -1; #endif } EXPORT_SYMBOL_GPL(list_lru_destroy); |
| 4747 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some * particular ordering. One way to make the compiler aware of ordering is to * put the two invocations of READ_ONCE or WRITE_ONCE in different C * statements. * * These two macros will also work on aggregate data types like structs or * unions. * * Their two major use cases are: (1) Mediating communication between * process-level code and irq/NMI handlers, all running on the same CPU, * and (2) Ensuring that the compiler does not fold, spindle, or otherwise * mutilate accesses that either do not require ordering or that interact * with an explicit memory barrier or atomic instruction that provides the * required ordering. */ #ifndef __ASM_GENERIC_RWONCE_H #define __ASM_GENERIC_RWONCE_H #ifndef __ASSEMBLY__ #include <linux/compiler_types.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> /* * Yes, this permits 64-bit accesses on 32-bit architectures. These will * actually be atomic in some cases (namely Armv7 + LPAE), but for others we * rely on the access being split into 2x32-bit accesses for a 32-bit quantity * (e.g. a virtual address) and a strong prevailing wind. */ #define compiletime_assert_rwonce_type(t) \ compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ "Unsupported access size for {READ,WRITE}_ONCE().") /* * Use __READ_ONCE() instead of READ_ONCE() if you do not require any * atomicity. Note that this may result in tears! */ #ifndef __READ_ONCE #define __READ_ONCE(x) (*(const volatile __unqual_scalar_typeof(x) *)&(x)) #endif #define READ_ONCE(x) \ ({ \ compiletime_assert_rwonce_type(x); \ __READ_ONCE(x); \ }) #define __WRITE_ONCE(x, val) \ do { \ *(volatile typeof(x) *)&(x) = (val); \ } while (0) #define WRITE_ONCE(x, val) \ do { \ compiletime_assert_rwonce_type(x); \ __WRITE_ONCE(x, val); \ } while (0) static __no_sanitize_or_inline unsigned long __read_once_word_nocheck(const void *addr) { return __READ_ONCE(*(unsigned long *)addr); } /* * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a * word from memory atomically but without telling KASAN/KCSAN. This is * usually used by unwinding code when walking the stack of a running process. */ #define READ_ONCE_NOCHECK(x) \ ({ \ compiletime_assert(sizeof(x) == sizeof(unsigned long), \ "Unsupported access size for READ_ONCE_NOCHECK()."); \ (typeof(x))__read_once_word_nocheck(&(x)); \ }) static __no_kasan_or_inline unsigned long read_word_at_a_time(const void *addr) { kasan_check_read(addr, 1); return *(unsigned long *)addr; } #endif /* __ASSEMBLY__ */ #endif /* __ASM_GENERIC_RWONCE_H */ |
| 375 3 3 6 6 6 5 5 6 379 816 607 608 607 65 64 426 5 6 6 6 1 1 1014 1480 4 1014 21 21 21 21 455 452 455 455 453 454 455 453 21 21 21 21 21 21 21 21 21 21 21 6 6 6 6 1 68 70 32 33 10 10 6 6 6 6 6 6 6 6 1 1 6 6 5 5 5 6 5 5 5 6 6 6 6 6 6 6 6 5 6 6 6 6 6 6 6 6 6 6 6 6 1 5 5 5 5 5 5 1 1 1 1 1 1 1 1 1 1 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 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 | // 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/sched/ext.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/memblock.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/syscall_user_dispatch.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/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/stackprotector.h> #include <linux/user_events.h> #include <linux/iommu.h> #include <linux/rseq.h> #include <uapi/linux/pidfd.h> #include <linux/pidfs.h> #include <linux/tick.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> #include <kunit/visibility.h> /* * Minimum number of threads to boot the kernel */ #define MIN_THREADS 20 /* * Maximum number of threads */ #define MAX_THREADS FUTEX_TID_MASK /* * 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 */ #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) { } 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); } /* * 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++) { struct vm_struct *tmp = NULL; if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm)) 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; int nr_charged = 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; nr_charged++; } return 0; err: for (i = 0; i < nr_charged; 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) */ /* 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); vma_numab_state_init(new); dup_anon_vma_name(orig, new); return new; } void __vm_area_free(struct vm_area_struct *vma) { vma_numab_state_free(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 release_user_cpus_ptr(tsk); scs_release(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); } #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); VMA_ITERATOR(vmi, mm, 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; /* 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(vmi.mas.tree); for_each_vma(vmi, mpnt) { struct file *file; vma_start_write(mpnt); if (mpnt->vm_flags & VM_DONTCOPY) { retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start, mpnt->vm_end, GFP_KERNEL); if (retval) 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); /* * Link the vma into the MT. After using __mt_dup(), memory * allocation is not necessary here, so it cannot fail. */ vma_iter_bulk_store(&vmi, tmp); mm->map_count++; 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 (vma_is_shared_maywrite(tmp)) 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); } if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); if (retval) { mpnt = vma_next(&vmi); goto loop_out; } } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); loop_out: vma_iter_free(&vmi); if (!retval) { mt_set_in_rcu(vmi.mas.tree); ksm_fork(mm, oldmm); khugepaged_fork(mm, oldmm); } 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(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1); mas_store(&vmi.mas, XA_ZERO_ENTRY); } out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); if (!retval) dup_userfaultfd_complete(&uf); else dup_userfaultfd_fail(&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 = percpu_counter_sum(&mm->rss_stat[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) && !defined(CONFIG_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))) static void do_check_lazy_tlb(void *arg) { struct mm_struct *mm = arg; WARN_ON_ONCE(current->active_mm == mm); } static void do_shoot_lazy_tlb(void *arg) { struct mm_struct *mm = arg; if (current->active_mm == mm) { WARN_ON_ONCE(current->mm); current->active_mm = &init_mm; switch_mm(mm, &init_mm, current); } } static void cleanup_lazy_tlbs(struct mm_struct *mm) { if (!IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) { /* * In this case, lazy tlb mms are refounted and would not reach * __mmdrop until all CPUs have switched away and mmdrop()ed. */ return; } /* * Lazy mm shootdown does not refcount "lazy tlb mm" usage, rather it * requires lazy mm users to switch to another mm when the refcount * drops to zero, before the mm is freed. This requires IPIs here to * switch kernel threads to init_mm. * * archs that use IPIs to flush TLBs can piggy-back that lazy tlb mm * switch with the final userspace teardown TLB flush which leaves the * mm lazy on this CPU but no others, reducing the need for additional * IPIs here. There are cases where a final IPI is still required here, * such as the final mmdrop being performed on a different CPU than the * one exiting, or kernel threads using the mm when userspace exits. * * IPI overheads have not found to be expensive, but they could be * reduced in a number of possible ways, for example (roughly * increasing order of complexity): * - The last lazy reference created by exit_mm() could instead switch * to init_mm, however it's probable this will run on the same CPU * immediately afterwards, so this may not reduce IPIs much. * - A batch of mms requiring IPIs could be gathered and freed at once. * - CPUs store active_mm where it can be remotely checked without a * lock, to filter out false-positives in the cpumask. * - After mm_users or mm_count reaches zero, switching away from the * mm could clear mm_cpumask to reduce some IPIs, perhaps together * with some batching or delaying of the final IPIs. * - A delayed freeing and RCU-like quiescing sequence based on mm * switching to avoid IPIs completely. */ on_each_cpu_mask(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1); if (IS_ENABLED(CONFIG_DEBUG_VM_SHOOT_LAZIES)) on_each_cpu(do_check_lazy_tlb, (void *)mm, 1); } /* * 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); /* Ensure no CPUs are using this as their lazy tlb mm */ cleanup_lazy_tlbs(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); mm_destroy_cid(mm); percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS); 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); sched_ext_free(tsk); 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 __init set_max_threads(unsigned int max_threads_suggested) { u64 threads; unsigned long nr_pages = memblock_estimated_nr_free_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 static void __init 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); } void __init fork_init(void) { int i; #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); /* 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_disk = NULL; tsk->use_memdelay = 0; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID tsk->pasid_activated = 0; #endif #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif #ifdef CONFIG_X86_BUS_LOCK_DETECT tsk->reported_split_lock = 0; #endif #ifdef CONFIG_SCHED_MM_CID tsk->mm_cid = -1; tsk->last_mm_cid = -1; tsk->mm_cid_active = 0; tsk->migrate_from_cpu = -1; #endif 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) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); hugetlb_count_init(mm); if (current->mm) { mm->flags = mmf_init_flags(current->mm->flags); 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; if (mm_alloc_cid(mm, p)) goto fail_cid; if (percpu_counter_init_many(mm->rss_stat, 0, GFP_KERNEL_ACCOUNT, NR_MM_COUNTERS)) goto fail_pcpu; mm->user_ns = get_user_ns(user_ns); lru_gen_init_mm(mm); return mm; fail_pcpu: mm_destroy_cid(mm); fail_cid: destroy_context(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()); } EXPORT_SYMBOL_IF_KUNIT(mm_alloc); 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_folio(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)) __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 * @mm: The mm to change. * @new_exe_file: The new file to use. * * 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 it happens before * the new mm is made visible to anyone. * * 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) get_file(new_exe_file); rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) fput(old_exe_file); return 0; } /** * replace_mm_exe_file - replace a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * 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; } get_file(new_exe_file); /* set the new file */ mmap_write_lock(mm); old_exe_file = rcu_dereference_raw(mm->exe_file); rcu_assign_pointer(mm->exe_file, new_exe_file); mmap_write_unlock(mm); if (old_exe_file) fput(old_exe_file); return 0; } /** * get_mm_exe_file - acquire a reference to the mm's executable file * @mm: The mm of interest. * * 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 = get_file_rcu(&mm->exe_file); rcu_read_unlock(); return exe_file; } /** * get_task_exe_file - acquire a reference to the task's executable file * @task: The task. * * 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 * @task: The task. * * 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; if (task->flags & PF_KTHREAD) return NULL; task_lock(task); mm = task->mm; if (mm) 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_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; sched_mm_cid_fork(tsk); 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); /* "users" and "in_exec" locked for check_unsafe_exec() */ 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, int no_files) { struct files_struct *oldf, *newf; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) return 0; if (no_files) { tsk->files = NULL; return 0; } if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); return 0; } newf = dup_fd(oldf, NULL); if (IS_ERR(newf)) return PTR_ERR(newf); tsk->files = newf; return 0; } 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_HLIST_HEAD(&sig->posix_timers); INIT_HLIST_HEAD(&sig->ignored_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; INIT_LIST_HEAD(&p->rcu_tasks_exit_list); #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 */ } /** * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @ret: Where to return the file for the pidfd. * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * * The helper doesn't perform checks on @pid which makes it useful for pidfds * created via CLONE_PIDFD where @pid has no task attached when the pidfd and * pidfd file are prepared. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { int pidfd; struct file *pidfd_file; pidfd = get_unused_fd_flags(O_CLOEXEC); if (pidfd < 0) return pidfd; pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR); if (IS_ERR(pidfd_file)) { put_unused_fd(pidfd); return PTR_ERR(pidfd_file); } /* * anon_inode_getfile() ignores everything outside of the * O_ACCMODE | O_NONBLOCK mask, set PIDFD_THREAD manually. */ pidfd_file->f_flags |= (flags & PIDFD_THREAD); *ret = pidfd_file; return pidfd; } /** * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @ret: Where to return the pidfd. * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * * The helper verifies that @pid is still in use, without PIDFD_THREAD the * task identified by @pid must be a thread-group leader. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { bool thread = flags & PIDFD_THREAD; if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID)) return -EINVAL; return __pidfd_prepare(pid, flags, ret); } 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. */ __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 (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. */ if (clone_flags & CLONE_DETACHED) 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->user_worker) { /* * Mark us a user worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } if (args->io_thread) p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); 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 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); tick_dep_init_task(p); 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; 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_sched_cancel_fork; 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, args->no_files); 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) { int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0; /* Note that no task has been attached to @pid yet. */ retval = __pidfd_prepare(pid, flags, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; 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; 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. */ retval = sched_cgroup_fork(p, args); if (retval) goto bad_fork_cancel_cgroup; /* * 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_core_free; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_core_free; } /* 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_node, &p->signal->thread_head); } attach_pid(p, PIDTYPE_PID); 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); user_events_fork(p, clone_flags); copy_oom_score_adj(clone_flags, p); return p; bad_fork_core_free: sched_core_free(p); spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); bad_fork_cancel_cgroup: 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_sched_cancel_fork: sched_cancel_fork(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, .user_worker = 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 ((clone_flags & CLONE_PIDFD) && (clone_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); /* * 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_WALKS_MMU) && !(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, const char *name, 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, .name = name, .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 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) 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; } /** * sys_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]; #ifdef __ARCH_BROKEN_SYS_CLONE3 #warning clone3() entry point is missing, please fix return -ENOSYS; #endif 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); } 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_cid_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 */ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp) { struct files_struct *fd = current->files; if ((unshare_flags & CLONE_FILES) && (fd && atomic_read(&fd->count) > 1)) { fd = dup_fd(fd, NULL); if (IS_ERR(fd)) return PTR_ERR(fd); *new_fdp = fd; } 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, &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, ©); 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(const 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; } |
| 1 1 69 1 16 16 16 12 4 16 3 15 1 1 1 1 69 1 70 55 55 4 55 55 15 49 49 12 21 21 10 10 6 10 92 92 13 78 92 92 4 4 4 4 4 77 76 76 2 67 67 77 8 8 8 5 6 5 2 6 1 5 2 4 6 6 6 6 2 5 6 6 8 3 3 3 3 1 3 3 3 3 3 3 3 8 2 2 8 10 10 10 10 10 10 10 10 10 10 10 1 1 1 1 1 1 110 110 110 110 110 2 2 2 2 2 110 111 110 111 110 111 55 115 120 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "alloc_background.h" #include "alloc_foreground.h" #include "backpointers.h" #include "bkey_buf.h" #include "btree_cache.h" #include "btree_io.h" #include "btree_key_cache.h" #include "btree_update.h" #include "btree_update_interior.h" #include "btree_gc.h" #include "btree_write_buffer.h" #include "buckets.h" #include "buckets_waiting_for_journal.h" #include "clock.h" #include "debug.h" #include "disk_accounting.h" #include "ec.h" #include "error.h" #include "lru.h" #include "recovery.h" #include "trace.h" #include "varint.h" #include <linux/kthread.h> #include <linux/math64.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/sched/task.h> #include <linux/sort.h> #include <linux/jiffies.h> static void bch2_discard_one_bucket_fast(struct bch_dev *, u64); /* Persistent alloc info: */ static const unsigned BCH_ALLOC_V1_FIELD_BYTES[] = { #define x(name, bits) [BCH_ALLOC_FIELD_V1_##name] = bits / 8, BCH_ALLOC_FIELDS_V1() #undef x }; struct bkey_alloc_unpacked { u64 journal_seq; u8 gen; u8 oldest_gen; u8 data_type; bool need_discard:1; bool need_inc_gen:1; #define x(_name, _bits) u##_bits _name; BCH_ALLOC_FIELDS_V2() #undef x }; static inline u64 alloc_field_v1_get(const struct bch_alloc *a, const void **p, unsigned field) { unsigned bytes = BCH_ALLOC_V1_FIELD_BYTES[field]; u64 v; if (!(a->fields & (1 << field))) return 0; switch (bytes) { case 1: v = *((const u8 *) *p); break; case 2: v = le16_to_cpup(*p); break; case 4: v = le32_to_cpup(*p); break; case 8: v = le64_to_cpup(*p); break; default: BUG(); } *p += bytes; return v; } static void bch2_alloc_unpack_v1(struct bkey_alloc_unpacked *out, struct bkey_s_c k) { const struct bch_alloc *in = bkey_s_c_to_alloc(k).v; const void *d = in->data; unsigned idx = 0; out->gen = in->gen; #define x(_name, _bits) out->_name = alloc_field_v1_get(in, &d, idx++); BCH_ALLOC_FIELDS_V1() #undef x } static int bch2_alloc_unpack_v2(struct bkey_alloc_unpacked *out, struct bkey_s_c k) { struct bkey_s_c_alloc_v2 a = bkey_s_c_to_alloc_v2(k); const u8 *in = a.v->data; const u8 *end = bkey_val_end(a); unsigned fieldnr = 0; int ret; u64 v; out->gen = a.v->gen; out->oldest_gen = a.v->oldest_gen; out->data_type = a.v->data_type; #define x(_name, _bits) \ if (fieldnr < a.v->nr_fields) { \ ret = bch2_varint_decode_fast(in, end, &v); \ if (ret < 0) \ return ret; \ in += ret; \ } else { \ v = 0; \ } \ out->_name = v; \ if (v != out->_name) \ return -1; \ fieldnr++; BCH_ALLOC_FIELDS_V2() #undef x return 0; } static int bch2_alloc_unpack_v3(struct bkey_alloc_unpacked *out, struct bkey_s_c k) { struct bkey_s_c_alloc_v3 a = bkey_s_c_to_alloc_v3(k); const u8 *in = a.v->data; const u8 *end = bkey_val_end(a); unsigned fieldnr = 0; int ret; u64 v; out->gen = a.v->gen; out->oldest_gen = a.v->oldest_gen; out->data_type = a.v->data_type; out->need_discard = BCH_ALLOC_V3_NEED_DISCARD(a.v); out->need_inc_gen = BCH_ALLOC_V3_NEED_INC_GEN(a.v); out->journal_seq = le64_to_cpu(a.v->journal_seq); #define x(_name, _bits) \ if (fieldnr < a.v->nr_fields) { \ ret = bch2_varint_decode_fast(in, end, &v); \ if (ret < 0) \ return ret; \ in += ret; \ } else { \ v = 0; \ } \ out->_name = v; \ if (v != out->_name) \ return -1; \ fieldnr++; BCH_ALLOC_FIELDS_V2() #undef x return 0; } static struct bkey_alloc_unpacked bch2_alloc_unpack(struct bkey_s_c k) { struct bkey_alloc_unpacked ret = { .gen = 0 }; switch (k.k->type) { case KEY_TYPE_alloc: bch2_alloc_unpack_v1(&ret, k); break; case KEY_TYPE_alloc_v2: bch2_alloc_unpack_v2(&ret, k); break; case KEY_TYPE_alloc_v3: bch2_alloc_unpack_v3(&ret, k); break; } return ret; } static unsigned bch_alloc_v1_val_u64s(const struct bch_alloc *a) { unsigned i, bytes = offsetof(struct bch_alloc, data); for (i = 0; i < ARRAY_SIZE(BCH_ALLOC_V1_FIELD_BYTES); i++) if (a->fields & (1 << i)) bytes += BCH_ALLOC_V1_FIELD_BYTES[i]; return DIV_ROUND_UP(bytes, sizeof(u64)); } int bch2_alloc_v1_validate(struct bch_fs *c, struct bkey_s_c k, enum bch_validate_flags flags) { struct bkey_s_c_alloc a = bkey_s_c_to_alloc(k); int ret = 0; /* allow for unknown fields */ bkey_fsck_err_on(bkey_val_u64s(a.k) < bch_alloc_v1_val_u64s(a.v), c, alloc_v1_val_size_bad, "incorrect value size (%zu < %u)", bkey_val_u64s(a.k), bch_alloc_v1_val_u64s(a.v)); fsck_err: return ret; } int bch2_alloc_v2_validate(struct bch_fs *c, struct bkey_s_c k, enum bch_validate_flags flags) { struct bkey_alloc_unpacked u; int ret = 0; bkey_fsck_err_on(bch2_alloc_unpack_v2(&u, k), c, alloc_v2_unpack_error, "unpack error"); fsck_err: return ret; } int bch2_alloc_v3_validate(struct bch_fs *c, struct bkey_s_c k, enum bch_validate_flags flags) { struct bkey_alloc_unpacked u; int ret = 0; bkey_fsck_err_on(bch2_alloc_unpack_v3(&u, k), c, alloc_v2_unpack_error, "unpack error"); fsck_err: return ret; } int bch2_alloc_v4_validate(struct bch_fs *c, struct bkey_s_c k, enum bch_validate_flags flags) { struct bch_alloc_v4 a; int ret = 0; bkey_val_copy(&a, bkey_s_c_to_alloc_v4(k)); bkey_fsck_err_on(alloc_v4_u64s_noerror(&a) > bkey_val_u64s(k.k), c, alloc_v4_val_size_bad, "bad val size (%u > %zu)", alloc_v4_u64s_noerror(&a), bkey_val_u64s(k.k)); bkey_fsck_err_on(!BCH_ALLOC_V4_BACKPOINTERS_START(&a) && BCH_ALLOC_V4_NR_BACKPOINTERS(&a), c, alloc_v4_backpointers_start_bad, "invalid backpointers_start"); bkey_fsck_err_on(alloc_data_type(a, a.data_type) != a.data_type, c, alloc_key_data_type_bad, "invalid data type (got %u should be %u)", a.data_type, alloc_data_type(a, a.data_type)); for (unsigned i = 0; i < 2; i++) bkey_fsck_err_on(a.io_time[i] > LRU_TIME_MAX, c, alloc_key_io_time_bad, "invalid io_time[%s]: %llu, max %llu", i == READ ? "read" : "write", a.io_time[i], LRU_TIME_MAX); unsigned stripe_sectors = BCH_ALLOC_V4_BACKPOINTERS_START(&a) * sizeof(u64) > offsetof(struct bch_alloc_v4, stripe_sectors) ? a.stripe_sectors : 0; switch (a.data_type) { case BCH_DATA_free: case BCH_DATA_need_gc_gens: case BCH_DATA_need_discard: bkey_fsck_err_on(stripe_sectors || a.dirty_sectors || a.cached_sectors || a.stripe, c, alloc_key_empty_but_have_data, "empty data type free but have data %u.%u.%u %u", stripe_sectors, a.dirty_sectors, a.cached_sectors, a.stripe); break; case BCH_DATA_sb: case BCH_DATA_journal: case BCH_DATA_btree: case BCH_DATA_user: case BCH_DATA_parity: bkey_fsck_err_on(!a.dirty_sectors && !stripe_sectors, c, alloc_key_dirty_sectors_0, "data_type %s but dirty_sectors==0", bch2_data_type_str(a.data_type)); break; case BCH_DATA_cached: bkey_fsck_err_on(!a.cached_sectors || a.dirty_sectors || stripe_sectors || a.stripe, c, alloc_key_cached_inconsistency, "data type inconsistency"); bkey_fsck_err_on(!a.io_time[READ] && c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_to_lru_refs, c, alloc_key_cached_but_read_time_zero, "cached bucket with read_time == 0"); break; case BCH_DATA_stripe: break; } fsck_err: return ret; } void bch2_alloc_v4_swab(struct bkey_s k) { struct bch_alloc_v4 *a = bkey_s_to_alloc_v4(k).v; struct bch_backpointer *bp, *bps; a->journal_seq = swab64(a->journal_seq); a->flags = swab32(a->flags); a->dirty_sectors = swab32(a->dirty_sectors); a->cached_sectors = swab32(a->cached_sectors); a->io_time[0] = swab64(a->io_time[0]); a->io_time[1] = swab64(a->io_time[1]); a->stripe = swab32(a->stripe); a->nr_external_backpointers = swab32(a->nr_external_backpointers); a->stripe_sectors = swab32(a->stripe_sectors); bps = alloc_v4_backpointers(a); for (bp = bps; bp < bps + BCH_ALLOC_V4_NR_BACKPOINTERS(a); bp++) { bp->bucket_offset = swab40(bp->bucket_offset); bp->bucket_len = swab32(bp->bucket_len); bch2_bpos_swab(&bp->pos); } } void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { struct bch_alloc_v4 _a; const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &_a); struct bch_dev *ca = c ? bch2_dev_bucket_tryget_noerror(c, k.k->p) : NULL; prt_newline(out); printbuf_indent_add(out, 2); prt_printf(out, "gen %u oldest_gen %u data_type ", a->gen, a->oldest_gen); bch2_prt_data_type(out, a->data_type); prt_newline(out); prt_printf(out, "journal_seq %llu\n", a->journal_seq); prt_printf(out, "need_discard %llu\n", BCH_ALLOC_V4_NEED_DISCARD(a)); prt_printf(out, "need_inc_gen %llu\n", BCH_ALLOC_V4_NEED_INC_GEN(a)); prt_printf(out, "dirty_sectors %u\n", a->dirty_sectors); prt_printf(out, "stripe_sectors %u\n", a->stripe_sectors); prt_printf(out, "cached_sectors %u\n", a->cached_sectors); prt_printf(out, "stripe %u\n", a->stripe); prt_printf(out, "stripe_redundancy %u\n", a->stripe_redundancy); prt_printf(out, "io_time[READ] %llu\n", a->io_time[READ]); prt_printf(out, "io_time[WRITE] %llu\n", a->io_time[WRITE]); if (ca) prt_printf(out, "fragmentation %llu\n", alloc_lru_idx_fragmentation(*a, ca)); prt_printf(out, "bp_start %llu\n", BCH_ALLOC_V4_BACKPOINTERS_START(a)); printbuf_indent_sub(out, 2); bch2_dev_put(ca); } void __bch2_alloc_to_v4(struct bkey_s_c k, struct bch_alloc_v4 *out) { if (k.k->type == KEY_TYPE_alloc_v4) { void *src, *dst; *out = *bkey_s_c_to_alloc_v4(k).v; src = alloc_v4_backpointers(out); SET_BCH_ALLOC_V4_BACKPOINTERS_START(out, BCH_ALLOC_V4_U64s); dst = alloc_v4_backpointers(out); if (src < dst) memset(src, 0, dst - src); SET_BCH_ALLOC_V4_NR_BACKPOINTERS(out, 0); } else { struct bkey_alloc_unpacked u = bch2_alloc_unpack(k); *out = (struct bch_alloc_v4) { .journal_seq = u.journal_seq, .flags = u.need_discard, .gen = u.gen, .oldest_gen = u.oldest_gen, .data_type = u.data_type, .stripe_redundancy = u.stripe_redundancy, .dirty_sectors = u.dirty_sectors, .cached_sectors = u.cached_sectors, .io_time[READ] = u.read_time, .io_time[WRITE] = u.write_time, .stripe = u.stripe, }; SET_BCH_ALLOC_V4_BACKPOINTERS_START(out, BCH_ALLOC_V4_U64s); } } static noinline struct bkey_i_alloc_v4 * __bch2_alloc_to_v4_mut(struct btree_trans *trans, struct bkey_s_c k) { struct bkey_i_alloc_v4 *ret; ret = bch2_trans_kmalloc(trans, max(bkey_bytes(k.k), sizeof(struct bkey_i_alloc_v4))); if (IS_ERR(ret)) return ret; if (k.k->type == KEY_TYPE_alloc_v4) { void *src, *dst; bkey_reassemble(&ret->k_i, k); src = alloc_v4_backpointers(&ret->v); SET_BCH_ALLOC_V4_BACKPOINTERS_START(&ret->v, BCH_ALLOC_V4_U64s); dst = alloc_v4_backpointers(&ret->v); if (src < dst) memset(src, 0, dst - src); SET_BCH_ALLOC_V4_NR_BACKPOINTERS(&ret->v, 0); set_alloc_v4_u64s(ret); } else { bkey_alloc_v4_init(&ret->k_i); ret->k.p = k.k->p; bch2_alloc_to_v4(k, &ret->v); } return ret; } static inline struct bkey_i_alloc_v4 *bch2_alloc_to_v4_mut_inlined(struct btree_trans *trans, struct bkey_s_c k) { struct bkey_s_c_alloc_v4 a; if (likely(k.k->type == KEY_TYPE_alloc_v4) && ((a = bkey_s_c_to_alloc_v4(k), true) && BCH_ALLOC_V4_NR_BACKPOINTERS(a.v) == 0)) return bch2_bkey_make_mut_noupdate_typed(trans, k, alloc_v4); return __bch2_alloc_to_v4_mut(trans, k); } struct bkey_i_alloc_v4 *bch2_alloc_to_v4_mut(struct btree_trans *trans, struct bkey_s_c k) { return bch2_alloc_to_v4_mut_inlined(trans, k); } struct bkey_i_alloc_v4 * bch2_trans_start_alloc_update_noupdate(struct btree_trans *trans, struct btree_iter *iter, struct bpos pos) { struct bkey_s_c k = bch2_bkey_get_iter(trans, iter, BTREE_ID_alloc, pos, BTREE_ITER_with_updates| BTREE_ITER_cached| BTREE_ITER_intent); int ret = bkey_err(k); if (unlikely(ret)) return ERR_PTR(ret); struct bkey_i_alloc_v4 *a = bch2_alloc_to_v4_mut_inlined(trans, k); ret = PTR_ERR_OR_ZERO(a); if (unlikely(ret)) goto err; return a; err: bch2_trans_iter_exit(trans, iter); return ERR_PTR(ret); } __flatten struct bkey_i_alloc_v4 *bch2_trans_start_alloc_update(struct btree_trans *trans, struct bpos pos, enum btree_iter_update_trigger_flags flags) { struct btree_iter iter; struct bkey_i_alloc_v4 *a = bch2_trans_start_alloc_update_noupdate(trans, &iter, pos); int ret = PTR_ERR_OR_ZERO(a); if (ret) return ERR_PTR(ret); ret = bch2_trans_update(trans, &iter, &a->k_i, flags); bch2_trans_iter_exit(trans, &iter); return unlikely(ret) ? ERR_PTR(ret) : a; } static struct bpos alloc_gens_pos(struct bpos pos, unsigned *offset) { *offset = pos.offset & KEY_TYPE_BUCKET_GENS_MASK; pos.offset >>= KEY_TYPE_BUCKET_GENS_BITS; return pos; } static struct bpos bucket_gens_pos_to_alloc(struct bpos pos, unsigned offset) { pos.offset <<= KEY_TYPE_BUCKET_GENS_BITS; pos.offset += offset; return pos; } static unsigned alloc_gen(struct bkey_s_c k, unsigned offset) { return k.k->type == KEY_TYPE_bucket_gens ? bkey_s_c_to_bucket_gens(k).v->gens[offset] : 0; } int bch2_bucket_gens_validate(struct bch_fs *c, struct bkey_s_c k, enum bch_validate_flags flags) { int ret = 0; bkey_fsck_err_on(bkey_val_bytes(k.k) != sizeof(struct bch_bucket_gens), c, bucket_gens_val_size_bad, "bad val size (%zu != %zu)", bkey_val_bytes(k.k), sizeof(struct bch_bucket_gens)); fsck_err: return ret; } void bch2_bucket_gens_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { struct bkey_s_c_bucket_gens g = bkey_s_c_to_bucket_gens(k); unsigned i; for (i = 0; i < ARRAY_SIZE(g.v->gens); i++) { if (i) prt_char(out, ' '); prt_printf(out, "%u", g.v->gens[i]); } } int bch2_bucket_gens_init(struct bch_fs *c) { struct btree_trans *trans = bch2_trans_get(c); struct bkey_i_bucket_gens g; bool have_bucket_gens_key = false; int ret; ret = for_each_btree_key(trans, iter, BTREE_ID_alloc, POS_MIN, BTREE_ITER_prefetch, k, ({ /* * Not a fsck error because this is checked/repaired by * bch2_check_alloc_key() which runs later: */ if (!bch2_dev_bucket_exists(c, k.k->p)) continue; struct bch_alloc_v4 a; u8 gen = bch2_alloc_to_v4(k, &a)->gen; unsigned offset; struct bpos pos = alloc_gens_pos(iter.pos, &offset); int ret2 = 0; if (have_bucket_gens_key && !bkey_eq(g.k.p, pos)) { ret2 = bch2_btree_insert_trans(trans, BTREE_ID_bucket_gens, &g.k_i, 0) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); if (ret2) goto iter_err; have_bucket_gens_key = false; } if (!have_bucket_gens_key) { bkey_bucket_gens_init(&g.k_i); g.k.p = pos; have_bucket_gens_key = true; } g.v.gens[offset] = gen; iter_err: ret2; })); if (have_bucket_gens_key && !ret) ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, bch2_btree_insert_trans(trans, BTREE_ID_bucket_gens, &g.k_i, 0)); bch2_trans_put(trans); bch_err_fn(c, ret); return ret; } int bch2_alloc_read(struct bch_fs *c) { struct btree_trans *trans = bch2_trans_get(c); struct bch_dev *ca = NULL; int ret; if (c->sb.version_upgrade_complete >= bcachefs_metadata_version_bucket_gens) { ret = for_each_btree_key(trans, iter, BTREE_ID_bucket_gens, POS_MIN, BTREE_ITER_prefetch, k, ({ u64 start = bucket_gens_pos_to_alloc(k.k->p, 0).offset; u64 end = bucket_gens_pos_to_alloc(bpos_nosnap_successor(k.k->p), 0).offset; if (k.k->type != KEY_TYPE_bucket_gens) continue; ca = bch2_dev_iterate(c, ca, k.k->p.inode); /* * Not a fsck error because this is checked/repaired by * bch2_check_alloc_key() which runs later: */ if (!ca) { bch2_btree_iter_set_pos(&iter, POS(k.k->p.inode + 1, 0)); continue; } const struct bch_bucket_gens *g = bkey_s_c_to_bucket_gens(k).v; for (u64 b = max_t(u64, ca->mi.first_bucket, start); b < min_t(u64, ca->mi.nbuckets, end); b++) *bucket_gen(ca, b) = g->gens[b & KEY_TYPE_BUCKET_GENS_MASK]; 0; })); } else { ret = for_each_btree_key(trans, iter, BTREE_ID_alloc, POS_MIN, BTREE_ITER_prefetch, k, ({ ca = bch2_dev_iterate(c, ca, k.k->p.inode); /* * Not a fsck error because this is checked/repaired by * bch2_check_alloc_key() which runs later: */ if (!ca) { bch2_btree_iter_set_pos(&iter, POS(k.k->p.inode + 1, 0)); continue; } if (k.k->p.offset < ca->mi.first_bucket) { bch2_btree_iter_set_pos(&iter, POS(k.k->p.inode, ca->mi.first_bucket)); continue; } if (k.k->p.offset >= ca->mi.nbuckets) { bch2_btree_iter_set_pos(&iter, POS(k.k->p.inode + 1, 0)); continue; } struct bch_alloc_v4 a; *bucket_gen(ca, k.k->p.offset) = bch2_alloc_to_v4(k, &a)->gen; 0; })); } bch2_dev_put(ca); bch2_trans_put(trans); bch_err_fn(c, ret); return ret; } /* Free space/discard btree: */ static int bch2_bucket_do_index(struct btree_trans *trans, struct bch_dev *ca, struct bkey_s_c alloc_k, const struct bch_alloc_v4 *a, bool set) { struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c old; struct bkey_i *k; enum btree_id btree; enum bch_bkey_type old_type = !set ? KEY_TYPE_set : KEY_TYPE_deleted; enum bch_bkey_type new_type = set ? KEY_TYPE_set : KEY_TYPE_deleted; struct printbuf buf = PRINTBUF; int ret; if (a->data_type != BCH_DATA_free && a->data_type != BCH_DATA_need_discard) return 0; k = bch2_trans_kmalloc_nomemzero(trans, sizeof(*k)); if (IS_ERR(k)) return PTR_ERR(k); bkey_init(&k->k); k->k.type = new_type; switch (a->data_type) { case BCH_DATA_free: btree = BTREE_ID_freespace; k->k.p = alloc_freespace_pos(alloc_k.k->p, *a); bch2_key_resize(&k->k, 1); break; case BCH_DATA_need_discard: btree = BTREE_ID_need_discard; k->k.p = alloc_k.k->p; break; default: return 0; } old = bch2_bkey_get_iter(trans, &iter, btree, bkey_start_pos(&k->k), BTREE_ITER_intent); ret = bkey_err(old); if (ret) return ret; if (ca->mi.freespace_initialized && c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info && bch2_trans_inconsistent_on(old.k->type != old_type, trans, "incorrect key when %s %s:%llu:%llu:0 (got %s should be %s)\n" " for %s", set ? "setting" : "clearing", bch2_btree_id_str(btree), iter.pos.inode, iter.pos.offset, bch2_bkey_types[old.k->type], bch2_bkey_types[old_type], (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) { ret = -EIO; goto err; } ret = bch2_trans_update(trans, &iter, k, 0); err: bch2_trans_iter_exit(trans, &iter); printbuf_exit(&buf); return ret; } static noinline int bch2_bucket_gen_update(struct btree_trans *trans, struct bpos bucket, u8 gen) { struct btree_iter iter; unsigned offset; struct bpos pos = alloc_gens_pos(bucket, &offset); struct bkey_i_bucket_gens *g; struct bkey_s_c k; int ret; g = bch2_trans_kmalloc(trans, sizeof(*g)); ret = PTR_ERR_OR_ZERO(g); if (ret) return ret; k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_bucket_gens, pos, BTREE_ITER_intent| BTREE_ITER_with_updates); ret = bkey_err(k); if (ret) return ret; if (k.k->type != KEY_TYPE_bucket_gens) { bkey_bucket_gens_init(&g->k_i); g->k.p = iter.pos; } else { bkey_reassemble(&g->k_i, k); } g->v.gens[offset] = gen; ret = bch2_trans_update(trans, &iter, &g->k_i, 0); bch2_trans_iter_exit(trans, &iter); return ret; } static inline int bch2_dev_data_type_accounting_mod(struct btree_trans *trans, struct bch_dev *ca, enum bch_data_type data_type, s64 delta_buckets, s64 delta_sectors, s64 delta_fragmented, unsigned flags) { struct disk_accounting_pos acc = { .type = BCH_DISK_ACCOUNTING_dev_data_type, .dev_data_type.dev = ca->dev_idx, .dev_data_type.data_type = data_type, }; s64 d[3] = { delta_buckets, delta_sectors, delta_fragmented }; return bch2_disk_accounting_mod(trans, &acc, d, 3, flags & BTREE_TRIGGER_gc); } int bch2_alloc_key_to_dev_counters(struct btree_trans *trans, struct bch_dev *ca, const struct bch_alloc_v4 *old, const struct bch_alloc_v4 *new, unsigned flags) { s64 old_sectors = bch2_bucket_sectors(*old); s64 new_sectors = bch2_bucket_sectors(*new); if (old->data_type != new->data_type) { int ret = bch2_dev_data_type_accounting_mod(trans, ca, new->data_type, 1, new_sectors, bch2_bucket_sectors_fragmented(ca, *new), flags) ?: bch2_dev_data_type_accounting_mod(trans, ca, old->data_type, -1, -old_sectors, -bch2_bucket_sectors_fragmented(ca, *old), flags); if (ret) return ret; } else if (old_sectors != new_sectors) { int ret = bch2_dev_data_type_accounting_mod(trans, ca, new->data_type, 0, new_sectors - old_sectors, bch2_bucket_sectors_fragmented(ca, *new) - bch2_bucket_sectors_fragmented(ca, *old), flags); if (ret) return ret; } s64 old_unstriped = bch2_bucket_sectors_unstriped(*old); s64 new_unstriped = bch2_bucket_sectors_unstriped(*new); if (old_unstriped != new_unstriped) { int ret = bch2_dev_data_type_accounting_mod(trans, ca, BCH_DATA_unstriped, !!new_unstriped - !!old_unstriped, new_unstriped - old_unstriped, 0, flags); if (ret) return ret; } return 0; } int bch2_trigger_alloc(struct btree_trans *trans, enum btree_id btree, unsigned level, struct bkey_s_c old, struct bkey_s new, enum btree_iter_update_trigger_flags flags) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; int ret = 0; struct bch_dev *ca = bch2_dev_bucket_tryget(c, new.k->p); if (!ca) return -EIO; struct bch_alloc_v4 old_a_convert; const struct bch_alloc_v4 *old_a = bch2_alloc_to_v4(old, &old_a_convert); struct bch_alloc_v4 *new_a; if (likely(new.k->type == KEY_TYPE_alloc_v4)) { new_a = bkey_s_to_alloc_v4(new).v; } else { BUG_ON(!(flags & (BTREE_TRIGGER_gc|BTREE_TRIGGER_check_repair))); struct bkey_i_alloc_v4 *new_ka = bch2_alloc_to_v4_mut_inlined(trans, new.s_c); ret = PTR_ERR_OR_ZERO(new_ka); if (unlikely(ret)) goto err; new_a = &new_ka->v; } if (flags & BTREE_TRIGGER_transactional) { alloc_data_type_set(new_a, new_a->data_type); if (bch2_bucket_sectors_total(*new_a) > bch2_bucket_sectors_total(*old_a)) { new_a->io_time[READ] = bch2_current_io_time(c, READ); new_a->io_time[WRITE]= bch2_current_io_time(c, WRITE); SET_BCH_ALLOC_V4_NEED_INC_GEN(new_a, true); SET_BCH_ALLOC_V4_NEED_DISCARD(new_a, true); } if (data_type_is_empty(new_a->data_type) && BCH_ALLOC_V4_NEED_INC_GEN(new_a) && !bch2_bucket_is_open_safe(c, new.k->p.inode, new.k->p.offset)) { new_a->gen++; SET_BCH_ALLOC_V4_NEED_INC_GEN(new_a, false); alloc_data_type_set(new_a, new_a->data_type); } if (old_a->data_type != new_a->data_type || (new_a->data_type == BCH_DATA_free && alloc_freespace_genbits(*old_a) != alloc_freespace_genbits(*new_a))) { ret = bch2_bucket_do_index(trans, ca, old, old_a, false) ?: bch2_bucket_do_index(trans, ca, new.s_c, new_a, true); if (ret) goto err; } if (new_a->data_type == BCH_DATA_cached && !new_a->io_time[READ]) new_a->io_time[READ] = bch2_current_io_time(c, READ); u64 old_lru = alloc_lru_idx_read(*old_a); u64 new_lru = alloc_lru_idx_read(*new_a); if (old_lru != new_lru) { ret = bch2_lru_change(trans, new.k->p.inode, bucket_to_u64(new.k->p), old_lru, new_lru); if (ret) goto err; } old_lru = alloc_lru_idx_fragmentation(*old_a, ca); new_lru = alloc_lru_idx_fragmentation(*new_a, ca); if (old_lru != new_lru) { ret = bch2_lru_change(trans, BCH_LRU_FRAGMENTATION_START, bucket_to_u64(new.k->p), old_lru, new_lru); if (ret) goto err; } if (old_a->gen != new_a->gen) { ret = bch2_bucket_gen_update(trans, new.k->p, new_a->gen); if (ret) goto err; } if ((flags & BTREE_TRIGGER_bucket_invalidate) && old_a->cached_sectors) { ret = bch2_mod_dev_cached_sectors(trans, ca->dev_idx, -((s64) old_a->cached_sectors), flags & BTREE_TRIGGER_gc); if (ret) goto err; } ret = bch2_alloc_key_to_dev_counters(trans, ca, old_a, new_a, flags); if (ret) goto err; } if ((flags & BTREE_TRIGGER_atomic) && (flags & BTREE_TRIGGER_insert)) { u64 journal_seq = trans->journal_res.seq; u64 bucket_journal_seq = new_a->journal_seq; if ((flags & BTREE_TRIGGER_insert) && data_type_is_empty(old_a->data_type) != data_type_is_empty(new_a->data_type) && new.k->type == KEY_TYPE_alloc_v4) { struct bch_alloc_v4 *v = bkey_s_to_alloc_v4(new).v; /* * If the btree updates referring to a bucket weren't flushed * before the bucket became empty again, then the we don't have * to wait on a journal flush before we can reuse the bucket: */ v->journal_seq = bucket_journal_seq = data_type_is_empty(new_a->data_type) && (journal_seq == v->journal_seq || bch2_journal_noflush_seq(&c->journal, v->journal_seq)) ? 0 : journal_seq; } if (!data_type_is_empty(old_a->data_type) && data_type_is_empty(new_a->data_type) && bucket_journal_seq) { ret = bch2_set_bucket_needs_journal_commit(&c->buckets_waiting_for_journal, c->journal.flushed_seq_ondisk, new.k->p.inode, new.k->p.offset, bucket_journal_seq); if (bch2_fs_fatal_err_on(ret, c, "setting bucket_needs_journal_commit: %s", bch2_err_str(ret))) goto err; } if (new_a->gen != old_a->gen) { rcu_read_lock(); u8 *gen = bucket_gen(ca, new.k->p.offset); if (unlikely(!gen)) { rcu_read_unlock(); goto invalid_bucket; } *gen = new_a->gen; rcu_read_unlock(); } #define eval_state(_a, expr) ({ const struct bch_alloc_v4 *a = _a; expr; }) #define statechange(expr) !eval_state(old_a, expr) && eval_state(new_a, expr) #define bucket_flushed(a) (!a->journal_seq || a->journal_seq <= c->journal.flushed_seq_ondisk) if (statechange(a->data_type == BCH_DATA_free) && bucket_flushed(new_a)) closure_wake_up(&c->freelist_wait); if (statechange(a->data_type == BCH_DATA_need_discard) && !bch2_bucket_is_open_safe(c, new.k->p.inode, new.k->p.offset) && bucket_flushed(new_a)) bch2_discard_one_bucket_fast(ca, new.k->p.offset); if (statechange(a->data_type == BCH_DATA_cached) && !bch2_bucket_is_open(c, new.k->p.inode, new.k->p.offset) && should_invalidate_buckets(ca, bch2_dev_usage_read(ca))) bch2_dev_do_invalidates(ca); if (statechange(a->data_type == BCH_DATA_need_gc_gens)) bch2_gc_gens_async(c); } if ((flags & BTREE_TRIGGER_gc) && (flags & BTREE_TRIGGER_insert)) { rcu_read_lock(); struct bucket *g = gc_bucket(ca, new.k->p.offset); if (unlikely(!g)) { rcu_read_unlock(); goto invalid_bucket; } g->gen_valid = 1; g->gen = new_a->gen; rcu_read_unlock(); } err: printbuf_exit(&buf); bch2_dev_put(ca); return ret; invalid_bucket: bch2_fs_inconsistent(c, "reference to invalid bucket\n %s", (bch2_bkey_val_to_text(&buf, c, new.s_c), buf.buf)); ret = -EIO; goto err; } /* * This synthesizes deleted extents for holes, similar to BTREE_ITER_slots for * extents style btrees, but works on non-extents btrees: */ static struct bkey_s_c bch2_get_key_or_hole(struct btree_iter *iter, struct bpos end, struct bkey *hole) { struct bkey_s_c k = bch2_btree_iter_peek_slot(iter); if (bkey_err(k)) return k; if (k.k->type) { return k; } else { struct btree_iter iter2; struct bpos next; bch2_trans_copy_iter(&iter2, iter); struct btree_path *path = btree_iter_path(iter->trans, iter); if (!bpos_eq(path->l[0].b->key.k.p, SPOS_MAX)) end = bkey_min(end, bpos_nosnap_successor(path->l[0].b->key.k.p)); end = bkey_min(end, POS(iter->pos.inode, iter->pos.offset + U32_MAX - 1)); /* * btree node min/max is a closed interval, upto takes a half * open interval: */ k = bch2_btree_iter_peek_upto(&iter2, end); next = iter2.pos; bch2_trans_iter_exit(iter->trans, &iter2); BUG_ON(next.offset >= iter->pos.offset + U32_MAX); if (bkey_err(k)) return k; bkey_init(hole); hole->p = iter->pos; bch2_key_resize(hole, next.offset - iter->pos.offset); return (struct bkey_s_c) { hole, NULL }; } } static bool next_bucket(struct bch_fs *c, struct bch_dev **ca, struct bpos *bucket) { if (*ca) { if (bucket->offset < (*ca)->mi.first_bucket) bucket->offset = (*ca)->mi.first_bucket; if (bucket->offset < (*ca)->mi.nbuckets) return true; bch2_dev_put(*ca); *ca = NULL; bucket->inode++; bucket->offset = 0; } rcu_read_lock(); *ca = __bch2_next_dev_idx(c, bucket->inode, NULL); if (*ca) { *bucket = POS((*ca)->dev_idx, (*ca)->mi.first_bucket); bch2_dev_get(*ca); } rcu_read_unlock(); return *ca != NULL; } static struct bkey_s_c bch2_get_key_or_real_bucket_hole(struct btree_iter *iter, struct bch_dev **ca, struct bkey *hole) { struct bch_fs *c = iter->trans->c; struct bkey_s_c k; again: k = bch2_get_key_or_hole(iter, POS_MAX, hole); if (bkey_err(k)) return k; *ca = bch2_dev_iterate_noerror(c, *ca, k.k->p.inode); if (!k.k->type) { struct bpos hole_start = bkey_start_pos(k.k); if (!*ca || !bucket_valid(*ca, hole_start.offset)) { if (!next_bucket(c, ca, &hole_start)) return bkey_s_c_null; bch2_btree_iter_set_pos(iter, hole_start); goto again; } if (k.k->p.offset > (*ca)->mi.nbuckets) bch2_key_resize(hole, (*ca)->mi.nbuckets - hole_start.offset); } return k; } static noinline_for_stack int bch2_check_alloc_key(struct btree_trans *trans, struct bkey_s_c alloc_k, struct btree_iter *alloc_iter, struct btree_iter *discard_iter, struct btree_iter *freespace_iter, struct btree_iter *bucket_gens_iter) { struct bch_fs *c = trans->c; struct bch_alloc_v4 a_convert; const struct bch_alloc_v4 *a; unsigned discard_key_type, freespace_key_type; unsigned gens_offset; struct bkey_s_c k; struct printbuf buf = PRINTBUF; int ret = 0; struct bch_dev *ca = bch2_dev_bucket_tryget_noerror(c, alloc_k.k->p); if (fsck_err_on(!ca, trans, alloc_key_to_missing_dev_bucket, "alloc key for invalid device:bucket %llu:%llu", alloc_k.k->p.inode, alloc_k.k->p.offset)) ret = bch2_btree_delete_at(trans, alloc_iter, 0); if (!ca) return ret; if (!ca->mi.freespace_initialized) goto out; a = bch2_alloc_to_v4(alloc_k, &a_convert); discard_key_type = a->data_type == BCH_DATA_need_discard ? KEY_TYPE_set : 0; bch2_btree_iter_set_pos(discard_iter, alloc_k.k->p); k = bch2_btree_iter_peek_slot(discard_iter); ret = bkey_err(k); if (ret) goto err; if (fsck_err_on(k.k->type != discard_key_type, trans, need_discard_key_wrong, "incorrect key in need_discard btree (got %s should be %s)\n" " %s", bch2_bkey_types[k.k->type], bch2_bkey_types[discard_key_type], (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) { struct bkey_i *update = bch2_trans_kmalloc(trans, sizeof(*update)); ret = PTR_ERR_OR_ZERO(update); if (ret) goto err; bkey_init(&update->k); update->k.type = discard_key_type; update->k.p = discard_iter->pos; ret = bch2_trans_update(trans, discard_iter, update, 0); if (ret) goto err; } freespace_key_type = a->data_type == BCH_DATA_free ? KEY_TYPE_set : 0; bch2_btree_iter_set_pos(freespace_iter, alloc_freespace_pos(alloc_k.k->p, *a)); k = bch2_btree_iter_peek_slot(freespace_iter); ret = bkey_err(k); if (ret) goto err; if (fsck_err_on(k.k->type != freespace_key_type, trans, freespace_key_wrong, "incorrect key in freespace btree (got %s should be %s)\n" " %s", bch2_bkey_types[k.k->type], bch2_bkey_types[freespace_key_type], (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) { struct bkey_i *update = bch2_trans_kmalloc(trans, sizeof(*update)); ret = PTR_ERR_OR_ZERO(update); if (ret) goto err; bkey_init(&update->k); update->k.type = freespace_key_type; update->k.p = freespace_iter->pos; bch2_key_resize(&update->k, 1); ret = bch2_trans_update(trans, freespace_iter, update, 0); if (ret) goto err; } bch2_btree_iter_set_pos(bucket_gens_iter, alloc_gens_pos(alloc_k.k->p, &gens_offset)); k = bch2_btree_iter_peek_slot(bucket_gens_iter); ret = bkey_err(k); if (ret) goto err; if (fsck_err_on(a->gen != alloc_gen(k, gens_offset), trans, bucket_gens_key_wrong, "incorrect gen in bucket_gens btree (got %u should be %u)\n" " %s", alloc_gen(k, gens_offset), a->gen, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) { struct bkey_i_bucket_gens *g = bch2_trans_kmalloc(trans, sizeof(*g)); ret = PTR_ERR_OR_ZERO(g); if (ret) goto err; if (k.k->type == KEY_TYPE_bucket_gens) { bkey_reassemble(&g->k_i, k); } else { bkey_bucket_gens_init(&g->k_i); g->k.p = alloc_gens_pos(alloc_k.k->p, &gens_offset); } g->v.gens[gens_offset] = a->gen; ret = bch2_trans_update(trans, bucket_gens_iter, &g->k_i, 0); if (ret) goto err; } out: err: fsck_err: bch2_dev_put(ca); printbuf_exit(&buf); return ret; } static noinline_for_stack int bch2_check_alloc_hole_freespace(struct btree_trans *trans, struct bch_dev *ca, struct bpos start, struct bpos *end, struct btree_iter *freespace_iter) { struct bkey_s_c k; struct printbuf buf = PRINTBUF; int ret; if (!ca->mi.freespace_initialized) return 0; bch2_btree_iter_set_pos(freespace_iter, start); k = bch2_btree_iter_peek_slot(freespace_iter); ret = bkey_err(k); if (ret) goto err; *end = bkey_min(k.k->p, *end); if (fsck_err_on(k.k->type != KEY_TYPE_set, trans, freespace_hole_missing, "hole in alloc btree missing in freespace btree\n" " device %llu buckets %llu-%llu", freespace_iter->pos.inode, freespace_iter->pos.offset, end->offset)) { struct bkey_i *update = bch2_trans_kmalloc(trans, sizeof(*update)); ret = PTR_ERR_OR_ZERO(update); if (ret) goto err; bkey_init(&update->k); update->k.type = KEY_TYPE_set; update->k.p = freespace_iter->pos; bch2_key_resize(&update->k, min_t(u64, U32_MAX, end->offset - freespace_iter->pos.offset)); ret = bch2_trans_update(trans, freespace_iter, update, 0); if (ret) goto err; } err: fsck_err: printbuf_exit(&buf); return ret; } static noinline_for_stack int bch2_check_alloc_hole_bucket_gens(struct btree_trans *trans, struct bpos start, struct bpos *end, struct btree_iter *bucket_gens_iter) { struct bkey_s_c k; struct printbuf buf = PRINTBUF; unsigned i, gens_offset, gens_end_offset; int ret; bch2_btree_iter_set_pos(bucket_gens_iter, alloc_gens_pos(start, &gens_offset)); k = bch2_btree_iter_peek_slot(bucket_gens_iter); ret = bkey_err(k); if (ret) goto err; if (bkey_cmp(alloc_gens_pos(start, &gens_offset), alloc_gens_pos(*end, &gens_end_offset))) gens_end_offset = KEY_TYPE_BUCKET_GENS_NR; if (k.k->type == KEY_TYPE_bucket_gens) { struct bkey_i_bucket_gens g; bool need_update = false; bkey_reassemble(&g.k_i, k); for (i = gens_offset; i < gens_end_offset; i++) { if (fsck_err_on(g.v.gens[i], trans, bucket_gens_hole_wrong, "hole in alloc btree at %llu:%llu with nonzero gen in bucket_gens btree (%u)", bucket_gens_pos_to_alloc(k.k->p, i).inode, bucket_gens_pos_to_alloc(k.k->p, i).offset, g.v.gens[i])) { g.v.gens[i] = 0; need_update = true; } } if (need_update) { struct bkey_i *u = bch2_trans_kmalloc(trans, sizeof(g)); ret = PTR_ERR_OR_ZERO(u); if (ret) goto err; memcpy(u, &g, sizeof(g)); ret = bch2_trans_update(trans, bucket_gens_iter, u, 0); if (ret) goto err; } } *end = bkey_min(*end, bucket_gens_pos_to_alloc(bpos_nosnap_successor(k.k->p), 0)); err: fsck_err: printbuf_exit(&buf); return ret; } static noinline_for_stack int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_iter *iter) { struct bch_fs *c = trans->c; struct btree_iter alloc_iter; struct bkey_s_c alloc_k; struct bch_alloc_v4 a_convert; const struct bch_alloc_v4 *a; u64 genbits; struct bpos pos; enum bch_data_type state = iter->btree_id == BTREE_ID_need_discard ? BCH_DATA_need_discard : BCH_DATA_free; struct printbuf buf = PRINTBUF; int ret; pos = iter->pos; pos.offset &= ~(~0ULL << 56); genbits = iter->pos.offset & (~0ULL << 56); alloc_k = bch2_bkey_get_iter(trans, &alloc_iter, BTREE_ID_alloc, pos, 0); ret = bkey_err(alloc_k); if (ret) return ret; if (fsck_err_on(!bch2_dev_bucket_exists(c, pos), trans, need_discard_freespace_key_to_invalid_dev_bucket, "entry in %s btree for nonexistant dev:bucket %llu:%llu", bch2_btree_id_str(iter->btree_id), pos.inode, pos.offset)) goto delete; a = bch2_alloc_to_v4(alloc_k, &a_convert); if (fsck_err_on(a->data_type != state || (state == BCH_DATA_free && genbits != alloc_freespace_genbits(*a)), trans, need_discard_freespace_key_bad, "%s\n incorrectly set at %s:%llu:%llu:0 (free %u, genbits %llu should be %llu)", (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf), bch2_btree_id_str(iter->btree_id), iter->pos.inode, iter->pos.offset, a->data_type == state, genbits >> 56, alloc_freespace_genbits(*a) >> 56)) goto delete; out: fsck_err: bch2_set_btree_iter_dontneed(&alloc_iter); bch2_trans_iter_exit(trans, &alloc_iter); printbuf_exit(&buf); return ret; delete: ret = bch2_btree_delete_extent_at(trans, iter, iter->btree_id == BTREE_ID_freespace ? 1 : 0, 0) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); goto out; } /* * We've already checked that generation numbers in the bucket_gens btree are * valid for buckets that exist; this just checks for keys for nonexistent * buckets. */ static noinline_for_stack int bch2_check_bucket_gens_key(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct bkey_i_bucket_gens g; u64 start = bucket_gens_pos_to_alloc(k.k->p, 0).offset; u64 end = bucket_gens_pos_to_alloc(bpos_nosnap_successor(k.k->p), 0).offset; u64 b; bool need_update = false; struct printbuf buf = PRINTBUF; int ret = 0; BUG_ON(k.k->type != KEY_TYPE_bucket_gens); bkey_reassemble(&g.k_i, k); struct bch_dev *ca = bch2_dev_tryget_noerror(c, k.k->p.inode); if (!ca) { if (fsck_err(trans, bucket_gens_to_invalid_dev, "bucket_gens key for invalid device:\n %s", (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) ret = bch2_btree_delete_at(trans, iter, 0); goto out; } if (fsck_err_on(end <= ca->mi.first_bucket || start >= ca->mi.nbuckets, trans, bucket_gens_to_invalid_buckets, "bucket_gens key for invalid buckets:\n %s", (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { ret = bch2_btree_delete_at(trans, iter, 0); goto out; } for (b = start; b < ca->mi.first_bucket; b++) if (fsck_err_on(g.v.gens[b & KEY_TYPE_BUCKET_GENS_MASK], trans, bucket_gens_nonzero_for_invalid_buckets, "bucket_gens key has nonzero gen for invalid bucket")) { g.v.gens[b & KEY_TYPE_BUCKET_GENS_MASK] = 0; need_update = true; } for (b = ca->mi.nbuckets; b < end; b++) if (fsck_err_on(g.v.gens[b & KEY_TYPE_BUCKET_GENS_MASK], trans, bucket_gens_nonzero_for_invalid_buckets, "bucket_gens key has nonzero gen for invalid bucket")) { g.v.gens[b & KEY_TYPE_BUCKET_GENS_MASK] = 0; need_update = true; } if (need_update) { struct bkey_i *u = bch2_trans_kmalloc(trans, sizeof(g)); ret = PTR_ERR_OR_ZERO(u); if (ret) goto out; memcpy(u, &g, sizeof(g)); ret = bch2_trans_update(trans, iter, u, 0); } out: fsck_err: bch2_dev_put(ca); printbuf_exit(&buf); return ret; } int bch2_check_alloc_info(struct bch_fs *c) { struct btree_trans *trans = bch2_trans_get(c); struct btree_iter iter, discard_iter, freespace_iter, bucket_gens_iter; struct bch_dev *ca = NULL; struct bkey hole; struct bkey_s_c k; int ret = 0; bch2_trans_iter_init(trans, &iter, BTREE_ID_alloc, POS_MIN, BTREE_ITER_prefetch); bch2_trans_iter_init(trans, &discard_iter, BTREE_ID_need_discard, POS_MIN, BTREE_ITER_prefetch); bch2_trans_iter_init(trans, &freespace_iter, BTREE_ID_freespace, POS_MIN, BTREE_ITER_prefetch); bch2_trans_iter_init(trans, &bucket_gens_iter, BTREE_ID_bucket_gens, POS_MIN, BTREE_ITER_prefetch); while (1) { struct bpos next; bch2_trans_begin(trans); k = bch2_get_key_or_real_bucket_hole(&iter, &ca, &hole); ret = bkey_err(k); if (ret) goto bkey_err; if (!k.k) break; if (k.k->type) { next = bpos_nosnap_successor(k.k->p); ret = bch2_check_alloc_key(trans, k, &iter, &discard_iter, &freespace_iter, &bucket_gens_iter); if (ret) goto bkey_err; } else { next = k.k->p; ret = bch2_check_alloc_hole_freespace(trans, ca, bkey_start_pos(k.k), &next, &freespace_iter) ?: bch2_check_alloc_hole_bucket_gens(trans, bkey_start_pos(k.k), &next, &bucket_gens_iter); if (ret) goto bkey_err; } ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); if (ret) goto bkey_err; bch2_btree_iter_set_pos(&iter, next); bkey_err: if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret) break; } bch2_trans_iter_exit(trans, &bucket_gens_iter); bch2_trans_iter_exit(trans, &freespace_iter); bch2_trans_iter_exit(trans, &discard_iter); bch2_trans_iter_exit(trans, &iter); bch2_dev_put(ca); ca = NULL; if (ret < 0) goto err; ret = for_each_btree_key(trans, iter, BTREE_ID_need_discard, POS_MIN, BTREE_ITER_prefetch, k, bch2_check_discard_freespace_key(trans, &iter)); if (ret) goto err; bch2_trans_iter_init(trans, &iter, BTREE_ID_freespace, POS_MIN, BTREE_ITER_prefetch); while (1) { bch2_trans_begin(trans); k = bch2_btree_iter_peek(&iter); if (!k.k) break; ret = bkey_err(k) ?: bch2_check_discard_freespace_key(trans, &iter); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) { ret = 0; continue; } if (ret) { struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, k); bch_err(c, "while checking %s", buf.buf); printbuf_exit(&buf); break; } bch2_btree_iter_set_pos(&iter, bpos_nosnap_successor(iter.pos)); } bch2_trans_iter_exit(trans, &iter); if (ret) goto err; ret = for_each_btree_key_commit(trans, iter, BTREE_ID_bucket_gens, POS_MIN, BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, bch2_check_bucket_gens_key(trans, &iter, k)); err: bch2_trans_put(trans); bch_err_fn(c, ret); return ret; } static int bch2_check_alloc_to_lru_ref(struct btree_trans *trans, struct btree_iter *alloc_iter, struct bkey_buf *last_flushed) { struct bch_fs *c = trans->c; struct bch_alloc_v4 a_convert; const struct bch_alloc_v4 *a; struct bkey_s_c alloc_k; struct printbuf buf = PRINTBUF; int ret; alloc_k = bch2_btree_iter_peek(alloc_iter); if (!alloc_k.k) return 0; ret = bkey_err(alloc_k); if (ret) return ret; struct bch_dev *ca = bch2_dev_tryget_noerror(c, alloc_k.k->p.inode); if (!ca) return 0; a = bch2_alloc_to_v4(alloc_k, &a_convert); u64 lru_idx = alloc_lru_idx_fragmentation(*a, ca); if (lru_idx) { ret = bch2_lru_check_set(trans, BCH_LRU_FRAGMENTATION_START, lru_idx, alloc_k, last_flushed); if (ret) goto err; } if (a->data_type != BCH_DATA_cached) goto err; if (fsck_err_on(!a->io_time[READ], trans, alloc_key_cached_but_read_time_zero, "cached bucket with read_time 0\n" " %s", (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) { struct bkey_i_alloc_v4 *a_mut = bch2_alloc_to_v4_mut(trans, alloc_k); ret = PTR_ERR_OR_ZERO(a_mut); if (ret) goto err; a_mut->v.io_time[READ] = bch2_current_io_time(c, READ); ret = bch2_trans_update(trans, alloc_iter, &a_mut->k_i, BTREE_TRIGGER_norun); if (ret) goto err; a = &a_mut->v; } ret = bch2_lru_check_set(trans, alloc_k.k->p.inode, a->io_time[READ], alloc_k, last_flushed); if (ret) goto err; err: fsck_err: bch2_dev_put(ca); printbuf_exit(&buf); return ret; } int bch2_check_alloc_to_lru_refs(struct bch_fs *c) { struct bkey_buf last_flushed; bch2_bkey_buf_init(&last_flushed); bkey_init(&last_flushed.k->k); int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_alloc, POS_MIN, BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, bch2_check_alloc_to_lru_ref(trans, &iter, &last_flushed))); bch2_bkey_buf_exit(&last_flushed, c); bch_err_fn(c, ret); return ret; } static int discard_in_flight_add(struct bch_dev *ca, u64 bucket, bool in_progress) { int ret; mutex_lock(&ca->discard_buckets_in_flight_lock); darray_for_each(ca->discard_buckets_in_flight, i) if (i->bucket == bucket) { ret = -BCH_ERR_EEXIST_discard_in_flight_add; goto out; } ret = darray_push(&ca->discard_buckets_in_flight, ((struct discard_in_flight) { .in_progress = in_progress, .bucket = bucket, })); out: mutex_unlock(&ca->discard_buckets_in_flight_lock); return ret; } static void discard_in_flight_remove(struct bch_dev *ca, u64 bucket) { mutex_lock(&ca->discard_buckets_in_flight_lock); darray_for_each(ca->discard_buckets_in_flight, i) if (i->bucket == bucket) { BUG_ON(!i->in_progress); darray_remove_item(&ca->discard_buckets_in_flight, i); goto found; } BUG(); found: mutex_unlock(&ca->discard_buckets_in_flight_lock); } struct discard_buckets_state { u64 seen; u64 open; u64 need_journal_commit; u64 discarded; u64 need_journal_commit_this_dev; }; static int bch2_discard_one_bucket(struct btree_trans *trans, struct bch_dev *ca, struct btree_iter *need_discard_iter, struct bpos *discard_pos_done, struct discard_buckets_state *s) { struct bch_fs *c = trans->c; struct bpos pos = need_discard_iter->pos; struct btree_iter iter = { NULL }; struct bkey_s_c k; struct bkey_i_alloc_v4 *a; struct printbuf buf = PRINTBUF; bool discard_locked = false; int ret = 0; if (bch2_bucket_is_open_safe(c, pos.inode, pos.offset)) { s->open++; goto out; } if (bch2_bucket_needs_journal_commit(&c->buckets_waiting_for_journal, c->journal.flushed_seq_ondisk, pos.inode, pos.offset)) { s->need_journal_commit++; s->need_journal_commit_this_dev++; goto out; } k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_alloc, need_discard_iter->pos, BTREE_ITER_cached); ret = bkey_err(k); if (ret) goto out; a = bch2_alloc_to_v4_mut(trans, k); ret = PTR_ERR_OR_ZERO(a); if (ret) goto out; if (bch2_bucket_sectors_total(a->v)) { if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info, trans, "attempting to discard bucket with dirty data\n%s", (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) ret = -EIO; goto out; } if (a->v.data_type != BCH_DATA_need_discard) { if (data_type_is_empty(a->v.data_type) && BCH_ALLOC_V4_NEED_INC_GEN(&a->v)) { a->v.gen++; SET_BCH_ALLOC_V4_NEED_INC_GEN(&a->v, false); goto write; } if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info, trans, "bucket incorrectly set in need_discard btree\n" "%s", (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) ret = -EIO; goto out; } if (a->v.journal_seq > c->journal.flushed_seq_ondisk) { if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info, trans, "clearing need_discard but journal_seq %llu > flushed_seq %llu\n%s", a->v.journal_seq, c->journal.flushed_seq_ondisk, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) ret = -EIO; goto out; } if (discard_in_flight_add(ca, iter.pos.offset, true)) goto out; discard_locked = true; if (!bkey_eq(*discard_pos_done, iter.pos) && ca->mi.discard && !c->opts.nochanges) { /* * This works without any other locks because this is the only * thread that removes items from the need_discard tree */ bch2_trans_unlock_long(trans); blkdev_issue_discard(ca->disk_sb.bdev, k.k->p.offset * ca->mi.bucket_size, ca->mi.bucket_size, GFP_KERNEL); *discard_pos_done = iter.pos; ret = bch2_trans_relock_notrace(trans); if (ret) goto out; } SET_BCH_ALLOC_V4_NEED_DISCARD(&a->v, false); write: alloc_data_type_set(&a->v, a->v.data_type); ret = bch2_trans_update(trans, &iter, &a->k_i, 0) ?: bch2_trans_commit(trans, NULL, NULL, BCH_WATERMARK_btree| BCH_TRANS_COMMIT_no_enospc); if (ret) goto out; count_event(c, bucket_discard); s->discarded++; out: if (discard_locked) discard_in_flight_remove(ca, iter.pos.offset); s->seen++; bch2_trans_iter_exit(trans, &iter); printbuf_exit(&buf); return ret; } static void bch2_do_discards_work(struct work_struct *work) { struct bch_dev *ca = container_of(work, struct bch_dev, discard_work); struct bch_fs *c = ca->fs; struct discard_buckets_state s = {}; struct bpos discard_pos_done = POS_MAX; int ret; /* * We're doing the commit in bch2_discard_one_bucket instead of using * for_each_btree_key_commit() so that we can increment counters after * successful commit: */ ret = bch2_trans_run(c, for_each_btree_key_upto(trans, iter, BTREE_ID_need_discard, POS(ca->dev_idx, 0), POS(ca->dev_idx, U64_MAX), 0, k, bch2_discard_one_bucket(trans, ca, &iter, &discard_pos_done, &s))); trace_discard_buckets(c, s.seen, s.open, s.need_journal_commit, s.discarded, bch2_err_str(ret)); percpu_ref_put(&ca->io_ref); bch2_write_ref_put(c, BCH_WRITE_REF_discard); } void bch2_dev_do_discards(struct bch_dev *ca) { struct bch_fs *c = ca->fs; if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_discard)) return; if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE)) goto put_write_ref; if (queue_work(c->write_ref_wq, &ca->discard_work)) return; percpu_ref_put(&ca->io_ref); put_write_ref: bch2_write_ref_put(c, BCH_WRITE_REF_discard); } void bch2_do_discards(struct bch_fs *c) { for_each_member_device(c, ca) bch2_dev_do_discards(ca); } static int bch2_clear_bucket_needs_discard(struct btree_trans *trans, struct bpos bucket) { struct btree_iter iter; bch2_trans_iter_init(trans, &iter, BTREE_ID_alloc, bucket, BTREE_ITER_intent); struct bkey_s_c k = bch2_btree_iter_peek_slot(&iter); int ret = bkey_err(k); if (ret) goto err; struct bkey_i_alloc_v4 *a = bch2_alloc_to_v4_mut(trans, k); ret = PTR_ERR_OR_ZERO(a); if (ret) goto err; BUG_ON(a->v.dirty_sectors); SET_BCH_ALLOC_V4_NEED_DISCARD(&a->v, false); alloc_data_type_set(&a->v, a->v.data_type); ret = bch2_trans_update(trans, &iter, &a->k_i, 0); err: bch2_trans_iter_exit(trans, &iter); return ret; } static void bch2_do_discards_fast_work(struct work_struct *work) { struct bch_dev *ca = container_of(work, struct bch_dev, discard_fast_work); struct bch_fs *c = ca->fs; while (1) { bool got_bucket = false; u64 bucket; mutex_lock(&ca->discard_buckets_in_flight_lock); darray_for_each(ca->discard_buckets_in_flight, i) { if (i->in_progress) continue; got_bucket = true; bucket = i->bucket; i->in_progress = true; break; } mutex_unlock(&ca->discard_buckets_in_flight_lock); if (!got_bucket) break; if (ca->mi.discard && !c->opts.nochanges) blkdev_issue_discard(ca->disk_sb.bdev, bucket_to_sector(ca, bucket), ca->mi.bucket_size, GFP_KERNEL); int ret = bch2_trans_commit_do(c, NULL, NULL, BCH_WATERMARK_btree| BCH_TRANS_COMMIT_no_enospc, bch2_clear_bucket_needs_discard(trans, POS(ca->dev_idx, bucket))); bch_err_fn(c, ret); discard_in_flight_remove(ca, bucket); if (ret) break; } percpu_ref_put(&ca->io_ref); bch2_write_ref_put(c, BCH_WRITE_REF_discard_fast); } static void bch2_discard_one_bucket_fast(struct bch_dev *ca, u64 bucket) { struct bch_fs *c = ca->fs; if (discard_in_flight_add(ca, bucket, false)) return; if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_discard_fast)) return; if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE)) goto put_ref; if (queue_work(c->write_ref_wq, &ca->discard_fast_work)) return; percpu_ref_put(&ca->io_ref); put_ref: bch2_write_ref_put(c, BCH_WRITE_REF_discard_fast); } static int invalidate_one_bucket(struct btree_trans *trans, struct btree_iter *lru_iter, struct bkey_s_c lru_k, s64 *nr_to_invalidate) { struct bch_fs *c = trans->c; struct bkey_i_alloc_v4 *a = NULL; struct printbuf buf = PRINTBUF; struct bpos bucket = u64_to_bucket(lru_k.k->p.offset); unsigned cached_sectors; int ret = 0; if (*nr_to_invalidate <= 0) return 1; if (!bch2_dev_bucket_exists(c, bucket)) { prt_str(&buf, "lru entry points to invalid bucket"); goto err; } if (bch2_bucket_is_open_safe(c, bucket.inode, bucket.offset)) return 0; a = bch2_trans_start_alloc_update(trans, bucket, BTREE_TRIGGER_bucket_invalidate); ret = PTR_ERR_OR_ZERO(a); if (ret) goto out; /* We expect harmless races here due to the btree write buffer: */ if (lru_pos_time(lru_iter->pos) != alloc_lru_idx_read(a->v)) goto out; BUG_ON(a->v.data_type != BCH_DATA_cached); BUG_ON(a->v.dirty_sectors); if (!a->v.cached_sectors) bch_err(c, "invalidating empty bucket, confused"); cached_sectors = a->v.cached_sectors; SET_BCH_ALLOC_V4_NEED_INC_GEN(&a->v, false); a->v.gen++; a->v.data_type = 0; a->v.dirty_sectors = 0; a->v.stripe_sectors = 0; a->v.cached_sectors = 0; a->v.io_time[READ] = bch2_current_io_time(c, READ); a->v.io_time[WRITE] = bch2_current_io_time(c, WRITE); ret = bch2_trans_commit(trans, NULL, NULL, BCH_WATERMARK_btree| BCH_TRANS_COMMIT_no_enospc); if (ret) goto out; trace_and_count(c, bucket_invalidate, c, bucket.inode, bucket.offset, cached_sectors); --*nr_to_invalidate; out: printbuf_exit(&buf); return ret; err: prt_str(&buf, "\n lru key: "); bch2_bkey_val_to_text(&buf, c, lru_k); prt_str(&buf, "\n lru entry: "); bch2_lru_pos_to_text(&buf, lru_iter->pos); prt_str(&buf, "\n alloc key: "); if (!a) bch2_bpos_to_text(&buf, bucket); else bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&a->k_i)); bch_err(c, "%s", buf.buf); if (c->curr_recovery_pass > BCH_RECOVERY_PASS_check_lrus) { bch2_inconsistent_error(c); ret = -EINVAL; } goto out; } static struct bkey_s_c next_lru_key(struct btree_trans *trans, struct btree_iter *iter, struct bch_dev *ca, bool *wrapped) { struct bkey_s_c k; again: k = bch2_btree_iter_peek_upto(iter, lru_pos(ca->dev_idx, U64_MAX, LRU_TIME_MAX)); if (!k.k && !*wrapped) { bch2_btree_iter_set_pos(iter, lru_pos(ca->dev_idx, 0, 0)); *wrapped = true; goto again; } return k; } static void bch2_do_invalidates_work(struct work_struct *work) { struct bch_dev *ca = container_of(work, struct bch_dev, invalidate_work); struct bch_fs *c = ca->fs; struct btree_trans *trans = bch2_trans_get(c); int ret = 0; ret = bch2_btree_write_buffer_tryflush(trans); if (ret) goto err; s64 nr_to_invalidate = should_invalidate_buckets(ca, bch2_dev_usage_read(ca)); struct btree_iter iter; bool wrapped = false; bch2_trans_iter_init(trans, &iter, BTREE_ID_lru, lru_pos(ca->dev_idx, 0, ((bch2_current_io_time(c, READ) + U32_MAX) & LRU_TIME_MAX)), 0); while (true) { bch2_trans_begin(trans); struct bkey_s_c k = next_lru_key(trans, &iter, ca, &wrapped); ret = bkey_err(k); if (ret) goto restart_err; if (!k.k) break; ret = invalidate_one_bucket(trans, &iter, k, &nr_to_invalidate); restart_err: if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret) break; bch2_btree_iter_advance(&iter); } bch2_trans_iter_exit(trans, &iter); err: bch2_trans_put(trans); percpu_ref_put(&ca->io_ref); bch2_write_ref_put(c, BCH_WRITE_REF_invalidate); } void bch2_dev_do_invalidates(struct bch_dev *ca) { struct bch_fs *c = ca->fs; if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_invalidate)) return; if (!bch2_dev_get_ioref(c, ca->dev_idx, WRITE)) goto put_ref; if (queue_work(c->write_ref_wq, &ca->invalidate_work)) return; percpu_ref_put(&ca->io_ref); put_ref: bch2_write_ref_put(c, BCH_WRITE_REF_invalidate); } void bch2_do_invalidates(struct bch_fs *c) { for_each_member_device(c, ca) bch2_dev_do_invalidates(ca); } int bch2_dev_freespace_init(struct bch_fs *c, struct bch_dev *ca, u64 bucket_start, u64 bucket_end) { struct btree_trans *trans = bch2_trans_get(c); struct btree_iter iter; struct bkey_s_c k; struct bkey hole; struct bpos end = POS(ca->dev_idx, bucket_end); struct bch_member *m; unsigned long last_updated = jiffies; int ret; BUG_ON(bucket_start > bucket_end); BUG_ON(bucket_end > ca->mi.nbuckets); bch2_trans_iter_init(trans, &iter, BTREE_ID_alloc, POS(ca->dev_idx, max_t(u64, ca->mi.first_bucket, bucket_start)), BTREE_ITER_prefetch); /* * Scan the alloc btree for every bucket on @ca, and add buckets to the * freespace/need_discard/need_gc_gens btrees as needed: */ while (1) { if (time_after(jiffies, last_updated + HZ * 10)) { bch_info(ca, "%s: currently at %llu/%llu", __func__, iter.pos.offset, ca->mi.nbuckets); last_updated = jiffies; } bch2_trans_begin(trans); if (bkey_ge(iter.pos, end)) { ret = 0; break; } k = bch2_get_key_or_hole(&iter, end, &hole); ret = bkey_err(k); if (ret) goto bkey_err; if (k.k->type) { /* * We process live keys in the alloc btree one at a * time: */ struct bch_alloc_v4 a_convert; const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &a_convert); ret = bch2_bucket_do_index(trans, ca, k, a, true) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); if (ret) goto bkey_err; bch2_btree_iter_advance(&iter); } else { struct bkey_i *freespace; freespace = bch2_trans_kmalloc(trans, sizeof(*freespace)); ret = PTR_ERR_OR_ZERO(freespace); if (ret) goto bkey_err; bkey_init(&freespace->k); freespace->k.type = KEY_TYPE_set; freespace->k.p = k.k->p; freespace->k.size = k.k->size; ret = bch2_btree_insert_trans(trans, BTREE_ID_freespace, freespace, 0) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); if (ret) goto bkey_err; bch2_btree_iter_set_pos(&iter, k.k->p); } bkey_err: if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret) break; } bch2_trans_iter_exit(trans, &iter); bch2_trans_put(trans); if (ret < 0) { bch_err_msg(ca, ret, "initializing free space"); return ret; } mutex_lock(&c->sb_lock); m = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx); SET_BCH_MEMBER_FREESPACE_INITIALIZED(m, true); mutex_unlock(&c->sb_lock); return 0; } int bch2_fs_freespace_init(struct bch_fs *c) { int ret = 0; bool doing_init = false; /* * We can crash during the device add path, so we need to check this on * every mount: */ for_each_member_device(c, ca) { if (ca->mi.freespace_initialized) continue; if (!doing_init) { bch_info(c, "initializing freespace"); doing_init = true; } ret = bch2_dev_freespace_init(c, ca, 0, ca->mi.nbuckets); if (ret) { bch2_dev_put(ca); bch_err_fn(c, ret); return ret; } } if (doing_init) { mutex_lock(&c->sb_lock); bch2_write_super(c); mutex_unlock(&c->sb_lock); bch_verbose(c, "done initializing freespace"); } return 0; } /* device removal */ int bch2_dev_remove_alloc(struct bch_fs *c, struct bch_dev *ca) { struct bpos start = POS(ca->dev_idx, 0); struct bpos end = POS(ca->dev_idx, U64_MAX); int ret; /* * We clear the LRU and need_discard btrees first so that we don't race * with bch2_do_invalidates() and bch2_do_discards() */ ret = bch2_dev_remove_stripes(c, ca->dev_idx) ?: bch2_btree_delete_range(c, BTREE_ID_lru, start, end, BTREE_TRIGGER_norun, NULL) ?: bch2_btree_delete_range(c, BTREE_ID_need_discard, start, end, BTREE_TRIGGER_norun, NULL) ?: bch2_btree_delete_range(c, BTREE_ID_freespace, start, end, BTREE_TRIGGER_norun, NULL) ?: bch2_btree_delete_range(c, BTREE_ID_backpointers, start, end, BTREE_TRIGGER_norun, NULL) ?: bch2_btree_delete_range(c, BTREE_ID_bucket_gens, start, end, BTREE_TRIGGER_norun, NULL) ?: bch2_btree_delete_range(c, BTREE_ID_alloc, start, end, BTREE_TRIGGER_norun, NULL) ?: bch2_dev_usage_remove(c, ca->dev_idx); bch_err_msg(ca, ret, "removing dev alloc info"); return ret; } /* Bucket IO clocks: */ static int __bch2_bucket_io_time_reset(struct btree_trans *trans, unsigned dev, size_t bucket_nr, int rw) { struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_i_alloc_v4 *a = bch2_trans_start_alloc_update_noupdate(trans, &iter, POS(dev, bucket_nr)); int ret = PTR_ERR_OR_ZERO(a); if (ret) return ret; u64 now = bch2_current_io_time(c, rw); if (a->v.io_time[rw] == now) goto out; a->v.io_time[rw] = now; ret = bch2_trans_update(trans, &iter, &a->k_i, 0) ?: bch2_trans_commit(trans, NULL, NULL, 0); out: bch2_trans_iter_exit(trans, &iter); return ret; } int bch2_bucket_io_time_reset(struct btree_trans *trans, unsigned dev, size_t bucket_nr, int rw) { if (bch2_trans_relock(trans)) bch2_trans_begin(trans); return nested_lockrestart_do(trans, __bch2_bucket_io_time_reset(trans, dev, bucket_nr, rw)); } /* Startup/shutdown (ro/rw): */ void bch2_recalc_capacity(struct bch_fs *c) { u64 capacity = 0, reserved_sectors = 0, gc_reserve; unsigned bucket_size_max = 0; unsigned long ra_pages = 0; lockdep_assert_held(&c->state_lock); for_each_online_member(c, ca) { struct backing_dev_info *bdi = ca->disk_sb.bdev->bd_disk->bdi; ra_pages += bdi->ra_pages; } bch2_set_ra_pages(c, ra_pages); for_each_rw_member(c, ca) { u64 dev_reserve = 0; /* * We need to reserve buckets (from the number * of currently available buckets) against * foreground writes so that mainly copygc can * make forward progress. * * We need enough to refill the various reserves * from scratch - copygc will use its entire * reserve all at once, then run against when * its reserve is refilled (from the formerly * available buckets). * * This reserve is just used when considering if * allocations for foreground writes must wait - * not -ENOSPC calculations. */ dev_reserve += ca->nr_btree_reserve * 2; dev_reserve += ca->mi.nbuckets >> 6; /* copygc reserve */ dev_reserve += 1; /* btree write point */ dev_reserve += 1; /* copygc write point */ dev_reserve += 1; /* rebalance write point */ dev_reserve *= ca->mi.bucket_size; capacity += bucket_to_sector(ca, ca->mi.nbuckets - ca->mi.first_bucket); reserved_sectors += dev_reserve * 2; bucket_size_max = max_t(unsigned, bucket_size_max, ca->mi.bucket_size); } gc_reserve = c->opts.gc_reserve_bytes ? c->opts.gc_reserve_bytes >> 9 : div64_u64(capacity * c->opts.gc_reserve_percent, 100); reserved_sectors = max(gc_reserve, reserved_sectors); reserved_sectors = min(reserved_sectors, capacity); c->reserved = reserved_sectors; c->capacity = capacity - reserved_sectors; c->bucket_size_max = bucket_size_max; /* Wake up case someone was waiting for buckets */ closure_wake_up(&c->freelist_wait); } u64 bch2_min_rw_member_capacity(struct bch_fs *c) { u64 ret = U64_MAX; for_each_rw_member(c, ca) ret = min(ret, ca->mi.nbuckets * ca->mi.bucket_size); return ret; } static bool bch2_dev_has_open_write_point(struct bch_fs *c, struct bch_dev *ca) { struct open_bucket *ob; bool ret = false; for (ob = c->open_buckets; ob < c->open_buckets + ARRAY_SIZE(c->open_buckets); ob++) { spin_lock(&ob->lock); if (ob->valid && !ob->on_partial_list && ob->dev == ca->dev_idx) ret = true; spin_unlock(&ob->lock); } return ret; } /* device goes ro: */ void bch2_dev_allocator_remove(struct bch_fs *c, struct bch_dev *ca) { lockdep_assert_held(&c->state_lock); /* First, remove device from allocation groups: */ for (unsigned i = 0; i < ARRAY_SIZE(c->rw_devs); i++) clear_bit(ca->dev_idx, c->rw_devs[i].d); c->rw_devs_change_count++; /* * Capacity is calculated based off of devices in allocation groups: */ bch2_recalc_capacity(c); bch2_open_buckets_stop(c, ca, false); /* * Wake up threads that were blocked on allocation, so they can notice * the device can no longer be removed and the capacity has changed: */ closure_wake_up(&c->freelist_wait); /* * journal_res_get() can block waiting for free space in the journal - * it needs to notice there may not be devices to allocate from anymore: */ wake_up(&c->journal.wait); /* Now wait for any in flight writes: */ closure_wait_event(&c->open_buckets_wait, !bch2_dev_has_open_write_point(c, ca)); } /* device goes rw: */ void bch2_dev_allocator_add(struct bch_fs *c, struct bch_dev *ca) { lockdep_assert_held(&c->state_lock); for (unsigned i = 0; i < ARRAY_SIZE(c->rw_devs); i++) if (ca->mi.data_allowed & (1 << i)) set_bit(ca->dev_idx, c->rw_devs[i].d); c->rw_devs_change_count++; } void bch2_dev_allocator_background_exit(struct bch_dev *ca) { darray_exit(&ca->discard_buckets_in_flight); } void bch2_dev_allocator_background_init(struct bch_dev *ca) { mutex_init(&ca->discard_buckets_in_flight_lock); INIT_WORK(&ca->discard_work, bch2_do_discards_work); INIT_WORK(&ca->discard_fast_work, bch2_do_discards_fast_work); INIT_WORK(&ca->invalidate_work, bch2_do_invalidates_work); } void bch2_fs_allocator_background_init(struct bch_fs *c) { spin_lock_init(&c->freelist_lock); } |
| 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2020 Facebook */ #include <linux/fs.h> #include <linux/anon_inodes.h> #include <linux/filter.h> #include <linux/bpf.h> #include <linux/rcupdate_trace.h> struct bpf_iter_target_info { struct list_head list; const struct bpf_iter_reg *reg_info; u32 btf_id; /* cached value */ }; struct bpf_iter_link { struct bpf_link link; struct bpf_iter_aux_info aux; struct bpf_iter_target_info *tinfo; }; struct bpf_iter_priv_data { struct bpf_iter_target_info *tinfo; const struct bpf_iter_seq_info *seq_info; struct bpf_prog *prog; u64 session_id; u64 seq_num; bool done_stop; u8 target_private[] __aligned(8); }; static struct list_head targets = LIST_HEAD_INIT(targets); static DEFINE_MUTEX(targets_mutex); /* protect bpf_iter_link changes */ static DEFINE_MUTEX(link_mutex); /* incremented on every opened seq_file */ static atomic64_t session_id; static int prepare_seq_file(struct file *file, struct bpf_iter_link *link, const struct bpf_iter_seq_info *seq_info); static void bpf_iter_inc_seq_num(struct seq_file *seq) { struct bpf_iter_priv_data *iter_priv; iter_priv = container_of(seq->private, struct bpf_iter_priv_data, target_private); iter_priv->seq_num++; } static void bpf_iter_dec_seq_num(struct seq_file *seq) { struct bpf_iter_priv_data *iter_priv; iter_priv = container_of(seq->private, struct bpf_iter_priv_data, target_private); iter_priv->seq_num--; } static void bpf_iter_done_stop(struct seq_file *seq) { struct bpf_iter_priv_data *iter_priv; iter_priv = container_of(seq->private, struct bpf_iter_priv_data, target_private); iter_priv->done_stop = true; } static inline bool bpf_iter_target_support_resched(const struct bpf_iter_target_info *tinfo) { return tinfo->reg_info->feature & BPF_ITER_RESCHED; } static bool bpf_iter_support_resched(struct seq_file *seq) { struct bpf_iter_priv_data *iter_priv; iter_priv = container_of(seq->private, struct bpf_iter_priv_data, target_private); return bpf_iter_target_support_resched(iter_priv->tinfo); } /* maximum visited objects before bailing out */ #define MAX_ITER_OBJECTS 1000000 /* bpf_seq_read, a customized and simpler version for bpf iterator. * The following are differences from seq_read(): * . fixed buffer size (PAGE_SIZE) * . assuming NULL ->llseek() * . stop() may call bpf program, handling potential overflow there */ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; size_t n, offs, copied = 0; int err = 0, num_objs = 0; bool can_resched; void *p; mutex_lock(&seq->lock); if (!seq->buf) { seq->size = PAGE_SIZE << 3; seq->buf = kvmalloc(seq->size, GFP_KERNEL); if (!seq->buf) { err = -ENOMEM; goto done; } } if (seq->count) { n = min(seq->count, size); err = copy_to_user(buf, seq->buf + seq->from, n); if (err) { err = -EFAULT; goto done; } seq->count -= n; seq->from += n; copied = n; goto done; } seq->from = 0; p = seq->op->start(seq, &seq->index); if (!p) goto stop; if (IS_ERR(p)) { err = PTR_ERR(p); seq->op->stop(seq, p); seq->count = 0; goto done; } err = seq->op->show(seq, p); if (err > 0) { /* object is skipped, decrease seq_num, so next * valid object can reuse the same seq_num. */ bpf_iter_dec_seq_num(seq); seq->count = 0; } else if (err < 0 || seq_has_overflowed(seq)) { if (!err) err = -E2BIG; seq->op->stop(seq, p); seq->count = 0; goto done; } can_resched = bpf_iter_support_resched(seq); while (1) { loff_t pos = seq->index; num_objs++; offs = seq->count; p = seq->op->next(seq, p, &seq->index); if (pos == seq->index) { pr_info_ratelimited("buggy seq_file .next function %ps " "did not updated position index\n", seq->op->next); seq->index++; } if (IS_ERR_OR_NULL(p)) break; /* got a valid next object, increase seq_num */ bpf_iter_inc_seq_num(seq); if (seq->count >= size) break; if (num_objs >= MAX_ITER_OBJECTS) { if (offs == 0) { err = -EAGAIN; seq->op->stop(seq, p); goto done; } break; } err = seq->op->show(seq, p); if (err > 0) { bpf_iter_dec_seq_num(seq); seq->count = offs; } else if (err < 0 || seq_has_overflowed(seq)) { seq->count = offs; if (offs == 0) { if (!err) err = -E2BIG; seq->op->stop(seq, p); goto done; } break; } if (can_resched) cond_resched(); } stop: offs = seq->count; if (IS_ERR(p)) { seq->op->stop(seq, NULL); err = PTR_ERR(p); goto done; } /* bpf program called if !p */ seq->op->stop(seq, p); if (!p) { if (!seq_has_overflowed(seq)) { bpf_iter_done_stop(seq); } else { seq->count = offs; if (offs == 0) { err = -E2BIG; goto done; } } } n = min(seq->count, size); err = copy_to_user(buf, seq->buf, n); if (err) { err = -EFAULT; goto done; } copied = n; seq->count -= n; seq->from = n; done: if (!copied) copied = err; else *ppos += copied; mutex_unlock(&seq->lock); return copied; } static const struct bpf_iter_seq_info * __get_seq_info(struct bpf_iter_link *link) { const struct bpf_iter_seq_info *seq_info; if (link->aux.map) { seq_info = link->aux.map->ops->iter_seq_info; if (seq_info) return seq_info; } return link->tinfo->reg_info->seq_info; } static int iter_open(struct inode *inode, struct file *file) { struct bpf_iter_link *link = inode->i_private; return prepare_seq_file(file, link, __get_seq_info(link)); } static int iter_release(struct inode *inode, struct file *file) { struct bpf_iter_priv_data *iter_priv; struct seq_file *seq; seq = file->private_data; if (!seq) return 0; iter_priv = container_of(seq->private, struct bpf_iter_priv_data, target_private); if (iter_priv->seq_info->fini_seq_private) iter_priv->seq_info->fini_seq_private(seq->private); bpf_prog_put(iter_priv->prog); seq->private = iter_priv; return seq_release_private(inode, file); } const struct file_operations bpf_iter_fops = { .open = iter_open, .read = bpf_seq_read, .release = iter_release, }; /* The argument reg_info will be cached in bpf_iter_target_info. * The common practice is to declare target reg_info as * a const static variable and passed as an argument to * bpf_iter_reg_target(). */ int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info) { struct bpf_iter_target_info *tinfo; tinfo = kzalloc(sizeof(*tinfo), GFP_KERNEL); if (!tinfo) return -ENOMEM; tinfo->reg_info = reg_info; INIT_LIST_HEAD(&tinfo->list); mutex_lock(&targets_mutex); list_add(&tinfo->list, &targets); mutex_unlock(&targets_mutex); return 0; } void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info) { struct bpf_iter_target_info *tinfo; bool found = false; mutex_lock(&targets_mutex); list_for_each_entry(tinfo, &targets, list) { if (reg_info == tinfo->reg_info) { list_del(&tinfo->list); kfree(tinfo); found = true; break; } } mutex_unlock(&targets_mutex); WARN_ON(found == false); } static void cache_btf_id(struct bpf_iter_target_info *tinfo, struct bpf_prog *prog) { tinfo->btf_id = prog->aux->attach_btf_id; } bool bpf_iter_prog_supported(struct bpf_prog *prog) { const char *attach_fname = prog->aux->attach_func_name; struct bpf_iter_target_info *tinfo = NULL, *iter; u32 prog_btf_id = prog->aux->attach_btf_id; const char *prefix = BPF_ITER_FUNC_PREFIX; int prefix_len = strlen(prefix); if (strncmp(attach_fname, prefix, prefix_len)) return false; mutex_lock(&targets_mutex); list_for_each_entry(iter, &targets, list) { if (iter->btf_id && iter->btf_id == prog_btf_id) { tinfo = iter; break; } if (!strcmp(attach_fname + prefix_len, iter->reg_info->target)) { cache_btf_id(iter, prog); tinfo = iter; break; } } mutex_unlock(&targets_mutex); if (tinfo) { prog->aux->ctx_arg_info_size = tinfo->reg_info->ctx_arg_info_size; prog->aux->ctx_arg_info = tinfo->reg_info->ctx_arg_info; } return tinfo != NULL; } const struct bpf_func_proto * bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_iter_target_info *tinfo; const struct bpf_func_proto *fn = NULL; mutex_lock(&targets_mutex); list_for_each_entry(tinfo, &targets, list) { if (tinfo->btf_id == prog->aux->attach_btf_id) { const struct bpf_iter_reg *reg_info; reg_info = tinfo->reg_info; if (reg_info->get_func_proto) fn = reg_info->get_func_proto(func_id, prog); break; } } mutex_unlock(&targets_mutex); return fn; } static void bpf_iter_link_release(struct bpf_link *link) { struct bpf_iter_link *iter_link = container_of(link, struct bpf_iter_link, link); if (iter_link->tinfo->reg_info->detach_target) iter_link->tinfo->reg_info->detach_target(&iter_link->aux); } static void bpf_iter_link_dealloc(struct bpf_link *link) { struct bpf_iter_link *iter_link = container_of(link, struct bpf_iter_link, link); kfree(iter_link); } static int bpf_iter_link_replace(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { int ret = 0; mutex_lock(&link_mutex); if (old_prog && link->prog != old_prog) { ret = -EPERM; goto out_unlock; } if (link->prog->type != new_prog->type || link->prog->expected_attach_type != new_prog->expected_attach_type || link->prog->aux->attach_btf_id != new_prog->aux->attach_btf_id) { ret = -EINVAL; goto out_unlock; } old_prog = xchg(&link->prog, new_prog); bpf_prog_put(old_prog); out_unlock: mutex_unlock(&link_mutex); return ret; } static void bpf_iter_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_iter_link *iter_link = container_of(link, struct bpf_iter_link, link); bpf_iter_show_fdinfo_t show_fdinfo; seq_printf(seq, "target_name:\t%s\n", iter_link->tinfo->reg_info->target); show_fdinfo = iter_link->tinfo->reg_info->show_fdinfo; if (show_fdinfo) show_fdinfo(&iter_link->aux, seq); } static int bpf_iter_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_iter_link *iter_link = container_of(link, struct bpf_iter_link, link); char __user *ubuf = u64_to_user_ptr(info->iter.target_name); bpf_iter_fill_link_info_t fill_link_info; u32 ulen = info->iter.target_name_len; const char *target_name; u32 target_len; if (!ulen ^ !ubuf) return -EINVAL; target_name = iter_link->tinfo->reg_info->target; target_len = strlen(target_name); info->iter.target_name_len = target_len + 1; if (ubuf) { if (ulen >= target_len + 1) { if (copy_to_user(ubuf, target_name, target_len + 1)) return -EFAULT; } else { char zero = '\0'; if (copy_to_user(ubuf, target_name, ulen - 1)) return -EFAULT; if (put_user(zero, ubuf + ulen - 1)) return -EFAULT; return -ENOSPC; } } fill_link_info = iter_link->tinfo->reg_info->fill_link_info; if (fill_link_info) return fill_link_info(&iter_link->aux, info); return 0; } static const struct bpf_link_ops bpf_iter_link_lops = { .release = bpf_iter_link_release, .dealloc = bpf_iter_link_dealloc, .update_prog = bpf_iter_link_replace, .show_fdinfo = bpf_iter_link_show_fdinfo, .fill_link_info = bpf_iter_link_fill_link_info, }; bool bpf_link_is_iter(struct bpf_link *link) { return link->ops == &bpf_iter_link_lops; } int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog) { struct bpf_iter_target_info *tinfo = NULL, *iter; struct bpf_link_primer link_primer; union bpf_iter_link_info linfo; struct bpf_iter_link *link; u32 prog_btf_id, linfo_len; bpfptr_t ulinfo; int err; if (attr->link_create.target_fd || attr->link_create.flags) return -EINVAL; memset(&linfo, 0, sizeof(union bpf_iter_link_info)); ulinfo = make_bpfptr(attr->link_create.iter_info, uattr.is_kernel); linfo_len = attr->link_create.iter_info_len; if (bpfptr_is_null(ulinfo) ^ !linfo_len) return -EINVAL; if (!bpfptr_is_null(ulinfo)) { err = bpf_check_uarg_tail_zero(ulinfo, sizeof(linfo), linfo_len); if (err) return err; linfo_len = min_t(u32, linfo_len, sizeof(linfo)); if (copy_from_bpfptr(&linfo, ulinfo, linfo_len)) return -EFAULT; } prog_btf_id = prog->aux->attach_btf_id; mutex_lock(&targets_mutex); list_for_each_entry(iter, &targets, list) { if (iter->btf_id == prog_btf_id) { tinfo = iter; break; } } mutex_unlock(&targets_mutex); if (!tinfo) return -ENOENT; /* Only allow sleepable program for resched-able iterator */ if (prog->sleepable && !bpf_iter_target_support_resched(tinfo)) return -EINVAL; link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN); if (!link) return -ENOMEM; bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog); link->tinfo = tinfo; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); return err; } if (tinfo->reg_info->attach_target) { err = tinfo->reg_info->attach_target(prog, &linfo, &link->aux); if (err) { bpf_link_cleanup(&link_primer); return err; } } return bpf_link_settle(&link_primer); } static void init_seq_meta(struct bpf_iter_priv_data *priv_data, struct bpf_iter_target_info *tinfo, const struct bpf_iter_seq_info *seq_info, struct bpf_prog *prog) { priv_data->tinfo = tinfo; priv_data->seq_info = seq_info; priv_data->prog = prog; priv_data->session_id = atomic64_inc_return(&session_id); priv_data->seq_num = 0; priv_data->done_stop = false; } static int prepare_seq_file(struct file *file, struct bpf_iter_link *link, const struct bpf_iter_seq_info *seq_info) { struct bpf_iter_priv_data *priv_data; struct bpf_iter_target_info *tinfo; struct bpf_prog *prog; u32 total_priv_dsize; struct seq_file *seq; int err = 0; mutex_lock(&link_mutex); prog = link->link.prog; bpf_prog_inc(prog); mutex_unlock(&link_mutex); tinfo = link->tinfo; total_priv_dsize = offsetof(struct bpf_iter_priv_data, target_private) + seq_info->seq_priv_size; priv_data = __seq_open_private(file, seq_info->seq_ops, total_priv_dsize); if (!priv_data) { err = -ENOMEM; goto release_prog; } if (seq_info->init_seq_private) { err = seq_info->init_seq_private(priv_data->target_private, &link->aux); if (err) goto release_seq_file; } init_seq_meta(priv_data, tinfo, seq_info, prog); seq = file->private_data; seq->private = priv_data->target_private; return 0; release_seq_file: seq_release_private(file->f_inode, file); file->private_data = NULL; release_prog: bpf_prog_put(prog); return err; } int bpf_iter_new_fd(struct bpf_link *link) { struct bpf_iter_link *iter_link; struct file *file; unsigned int flags; int err, fd; if (link->ops != &bpf_iter_link_lops) return -EINVAL; flags = O_RDONLY | O_CLOEXEC; fd = get_unused_fd_flags(flags); if (fd < 0) return fd; file = anon_inode_getfile("bpf_iter", &bpf_iter_fops, NULL, flags); if (IS_ERR(file)) { err = PTR_ERR(file); goto free_fd; } iter_link = container_of(link, struct bpf_iter_link, link); err = prepare_seq_file(file, iter_link, __get_seq_info(iter_link)); if (err) goto free_file; fd_install(fd, file); return fd; free_file: fput(file); free_fd: put_unused_fd(fd); return err; } struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop) { struct bpf_iter_priv_data *iter_priv; struct seq_file *seq; void *seq_priv; seq = meta->seq; if (seq->file->f_op != &bpf_iter_fops) return NULL; seq_priv = seq->private; iter_priv = container_of(seq_priv, struct bpf_iter_priv_data, target_private); if (in_stop && iter_priv->done_stop) return NULL; meta->session_id = iter_priv->session_id; meta->seq_num = iter_priv->seq_num; return iter_priv->prog; } int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx) { struct bpf_run_ctx run_ctx, *old_run_ctx; int ret; if (prog->sleepable) { rcu_read_lock_trace(); migrate_disable(); might_fault(); old_run_ctx = bpf_set_run_ctx(&run_ctx); ret = bpf_prog_run(prog, ctx); bpf_reset_run_ctx(old_run_ctx); migrate_enable(); rcu_read_unlock_trace(); } else { rcu_read_lock(); migrate_disable(); old_run_ctx = bpf_set_run_ctx(&run_ctx); ret = bpf_prog_run(prog, ctx); bpf_reset_run_ctx(old_run_ctx); migrate_enable(); rcu_read_unlock(); } /* bpf program can only return 0 or 1: * 0 : okay * 1 : retry the same object * The bpf_iter_run_prog() return value * will be seq_ops->show() return value. */ return ret == 0 ? 0 : -EAGAIN; } BPF_CALL_4(bpf_for_each_map_elem, struct bpf_map *, map, void *, callback_fn, void *, callback_ctx, u64, flags) { return map->ops->map_for_each_callback(map, callback_fn, callback_ctx, flags); } const struct bpf_func_proto bpf_for_each_map_elem_proto = { .func = bpf_for_each_map_elem, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_FUNC, .arg3_type = ARG_PTR_TO_STACK_OR_NULL, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_loop, u32, nr_loops, void *, callback_fn, void *, callback_ctx, u64, flags) { bpf_callback_t callback = (bpf_callback_t)callback_fn; u64 ret; u32 i; /* Note: these safety checks are also verified when bpf_loop * is inlined, be careful to modify this code in sync. See * function verifier.c:inline_bpf_loop. */ if (flags) return -EINVAL; if (nr_loops > BPF_MAX_LOOPS) return -E2BIG; for (i = 0; i < nr_loops; i++) { ret = callback((u64)i, (u64)(long)callback_ctx, 0, 0, 0); /* return value: 0 - continue, 1 - stop and return */ if (ret) return i + 1; } return i; } const struct bpf_func_proto bpf_loop_proto = { .func = bpf_loop, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_FUNC, .arg3_type = ARG_PTR_TO_STACK_OR_NULL, .arg4_type = ARG_ANYTHING, }; struct bpf_iter_num_kern { int cur; /* current value, inclusive */ int end; /* final value, exclusive */ } __aligned(8); __bpf_kfunc_start_defs(); __bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end) { struct bpf_iter_num_kern *s = (void *)it; BUILD_BUG_ON(sizeof(struct bpf_iter_num_kern) != sizeof(struct bpf_iter_num)); BUILD_BUG_ON(__alignof__(struct bpf_iter_num_kern) != __alignof__(struct bpf_iter_num)); /* start == end is legit, it's an empty range and we'll just get NULL * on first (and any subsequent) bpf_iter_num_next() call */ if (start > end) { s->cur = s->end = 0; return -EINVAL; } /* avoid overflows, e.g., if start == INT_MIN and end == INT_MAX */ if ((s64)end - (s64)start > BPF_MAX_LOOPS) { s->cur = s->end = 0; return -E2BIG; } /* user will call bpf_iter_num_next() first, * which will set s->cur to exactly start value; * underflow shouldn't matter */ s->cur = start - 1; s->end = end; return 0; } __bpf_kfunc int *bpf_iter_num_next(struct bpf_iter_num* it) { struct bpf_iter_num_kern *s = (void *)it; /* check failed initialization or if we are done (same behavior); * need to be careful about overflow, so convert to s64 for checks, * e.g., if s->cur == s->end == INT_MAX, we can't just do * s->cur + 1 >= s->end */ if ((s64)(s->cur + 1) >= s->end) { s->cur = s->end = 0; return NULL; } s->cur++; return &s->cur; } __bpf_kfunc void bpf_iter_num_destroy(struct bpf_iter_num *it) { struct bpf_iter_num_kern *s = (void *)it; s->cur = s->end = 0; } __bpf_kfunc_end_defs(); |
| 1 1 1 1 2 3 2 1 1 2 3 3 1 3 3 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org> * Copyright 2001-2006 Ian Kent <raven@themaw.net> */ #include "autofs_i.h" /* Check if a dentry can be expired */ static inline int autofs_can_expire(struct dentry *dentry, unsigned long timeout, unsigned int how) { struct autofs_info *ino = autofs_dentry_ino(dentry); /* dentry in the process of being deleted */ if (ino == NULL) return 0; if (!(how & AUTOFS_EXP_IMMEDIATE)) { /* Too young to die */ if (!timeout || time_after(ino->last_used + timeout, jiffies)) return 0; } return 1; } /* Check a mount point for busyness */ static int autofs_mount_busy(struct vfsmount *mnt, struct dentry *dentry, unsigned int how) { struct dentry *top = dentry; struct path path = {.mnt = mnt, .dentry = dentry}; int status = 1; pr_debug("dentry %p %pd\n", dentry, dentry); path_get(&path); if (!follow_down_one(&path)) goto done; if (is_autofs_dentry(path.dentry)) { struct autofs_sb_info *sbi = autofs_sbi(path.dentry->d_sb); /* This is an autofs submount, we can't expire it */ if (autofs_type_indirect(sbi->type)) goto done; } /* Not a submount, has a forced expire been requested */ if (how & AUTOFS_EXP_FORCED) { status = 0; goto done; } /* Update the expiry counter if fs is busy */ if (!may_umount_tree(path.mnt)) { struct autofs_info *ino; ino = autofs_dentry_ino(top); ino->last_used = jiffies; goto done; } status = 0; done: pr_debug("returning = %d\n", status); path_put(&path); return status; } /* p->d_lock held */ static struct dentry *positive_after(struct dentry *p, struct dentry *child) { child = child ? d_next_sibling(child) : d_first_child(p); hlist_for_each_entry_from(child, d_sib) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { dget_dlock(child); spin_unlock(&child->d_lock); return child; } spin_unlock(&child->d_lock); } return NULL; } /* * Calculate and dget next entry in the subdirs list under root. */ static struct dentry *get_next_positive_subdir(struct dentry *prev, struct dentry *root) { struct autofs_sb_info *sbi = autofs_sbi(root->d_sb); struct dentry *q; spin_lock(&sbi->lookup_lock); spin_lock(&root->d_lock); q = positive_after(root, prev); spin_unlock(&root->d_lock); spin_unlock(&sbi->lookup_lock); dput(prev); return q; } /* * Calculate and dget next entry in top down tree traversal. */ static struct dentry *get_next_positive_dentry(struct dentry *prev, struct dentry *root) { struct autofs_sb_info *sbi = autofs_sbi(root->d_sb); struct dentry *p = prev, *ret = NULL, *d = NULL; if (prev == NULL) return dget(root); spin_lock(&sbi->lookup_lock); spin_lock(&p->d_lock); while (1) { struct dentry *parent; ret = positive_after(p, d); if (ret || p == root) break; parent = p->d_parent; spin_unlock(&p->d_lock); spin_lock(&parent->d_lock); d = p; p = parent; } spin_unlock(&p->d_lock); spin_unlock(&sbi->lookup_lock); dput(prev); return ret; } /* * Check a direct mount point for busyness. * Direct mounts have similar expiry semantics to tree mounts. * The tree is not busy iff no mountpoints are busy and there are no * autofs submounts. */ static int autofs_direct_busy(struct vfsmount *mnt, struct dentry *top, unsigned long timeout, unsigned int how) { pr_debug("top %p %pd\n", top, top); /* Forced expire, user space handles busy mounts */ if (how & AUTOFS_EXP_FORCED) return 0; /* If it's busy update the expiry counters */ if (!may_umount_tree(mnt)) { struct autofs_info *ino; ino = autofs_dentry_ino(top); if (ino) ino->last_used = jiffies; return 1; } /* Timeout of a direct mount is determined by its top dentry */ if (!autofs_can_expire(top, timeout, how)) return 1; return 0; } /* * Check a directory tree of mount points for busyness * The tree is not busy iff no mountpoints are busy */ static int autofs_tree_busy(struct vfsmount *mnt, struct dentry *top, unsigned long timeout, unsigned int how) { struct autofs_info *top_ino = autofs_dentry_ino(top); struct dentry *p; pr_debug("top %p %pd\n", top, top); /* Negative dentry - give up */ if (!simple_positive(top)) return 1; p = NULL; while ((p = get_next_positive_dentry(p, top))) { pr_debug("dentry %p %pd\n", p, p); /* * Is someone visiting anywhere in the subtree ? * If there's no mount we need to check the usage * count for the autofs dentry. * If the fs is busy update the expiry counter. */ if (d_mountpoint(p)) { if (autofs_mount_busy(mnt, p, how)) { top_ino->last_used = jiffies; dput(p); return 1; } } else { struct autofs_info *ino = autofs_dentry_ino(p); unsigned int ino_count = READ_ONCE(ino->count); /* allow for dget above and top is already dgot */ if (p == top) ino_count += 2; else ino_count++; if (d_count(p) > ino_count) { top_ino->last_used = jiffies; dput(p); return 1; } } } /* Forced expire, user space handles busy mounts */ if (how & AUTOFS_EXP_FORCED) return 0; /* Timeout of a tree mount is ultimately determined by its top dentry */ if (!autofs_can_expire(top, timeout, how)) return 1; return 0; } static struct dentry *autofs_check_leaves(struct vfsmount *mnt, struct dentry *parent, unsigned long timeout, unsigned int how) { struct dentry *p; pr_debug("parent %p %pd\n", parent, parent); p = NULL; while ((p = get_next_positive_dentry(p, parent))) { pr_debug("dentry %p %pd\n", p, p); if (d_mountpoint(p)) { /* Can we umount this guy */ if (autofs_mount_busy(mnt, p, how)) continue; /* This isn't a submount so if a forced expire * has been requested, user space handles busy * mounts */ if (how & AUTOFS_EXP_FORCED) return p; /* Can we expire this guy */ if (autofs_can_expire(p, timeout, how)) return p; } } return NULL; } /* Check if we can expire a direct mount (possibly a tree) */ static struct dentry *autofs_expire_direct(struct super_block *sb, struct vfsmount *mnt, struct autofs_sb_info *sbi, unsigned int how) { struct dentry *root = dget(sb->s_root); struct autofs_info *ino; unsigned long timeout; if (!root) return NULL; timeout = sbi->exp_timeout; if (!autofs_direct_busy(mnt, root, timeout, how)) { spin_lock(&sbi->fs_lock); ino = autofs_dentry_ino(root); /* No point expiring a pending mount */ if (ino->flags & AUTOFS_INF_PENDING) { spin_unlock(&sbi->fs_lock); goto out; } ino->flags |= AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); synchronize_rcu(); if (!autofs_direct_busy(mnt, root, timeout, how)) { spin_lock(&sbi->fs_lock); ino->flags |= AUTOFS_INF_EXPIRING; init_completion(&ino->expire_complete); spin_unlock(&sbi->fs_lock); return root; } spin_lock(&sbi->fs_lock); ino->flags &= ~AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); } out: dput(root); return NULL; } /* Check if 'dentry' should expire, or return a nearby * dentry that is suitable. * If returned dentry is different from arg dentry, * then a dget() reference was taken, else not. */ static struct dentry *should_expire(struct dentry *dentry, struct vfsmount *mnt, unsigned long timeout, unsigned int how) { struct autofs_info *ino = autofs_dentry_ino(dentry); unsigned int ino_count; /* No point expiring a pending mount */ if (ino->flags & AUTOFS_INF_PENDING) return NULL; /* * Case 1: (i) indirect mount or top level pseudo direct mount * (autofs-4.1). * (ii) indirect mount with offset mount, check the "/" * offset (autofs-5.0+). */ if (d_mountpoint(dentry)) { pr_debug("checking mountpoint %p %pd\n", dentry, dentry); /* Can we umount this guy */ if (autofs_mount_busy(mnt, dentry, how)) return NULL; /* This isn't a submount so if a forced expire * has been requested, user space handles busy * mounts */ if (how & AUTOFS_EXP_FORCED) return dentry; /* Can we expire this guy */ if (autofs_can_expire(dentry, timeout, how)) return dentry; return NULL; } if (d_is_symlink(dentry)) { pr_debug("checking symlink %p %pd\n", dentry, dentry); /* Forced expire, user space handles busy mounts */ if (how & AUTOFS_EXP_FORCED) return dentry; /* * A symlink can't be "busy" in the usual sense so * just check last used for expire timeout. */ if (autofs_can_expire(dentry, timeout, how)) return dentry; return NULL; } if (autofs_empty(ino)) return NULL; /* Case 2: tree mount, expire iff entire tree is not busy */ if (!(how & AUTOFS_EXP_LEAVES)) { /* Not a forced expire? */ if (!(how & AUTOFS_EXP_FORCED)) { /* ref-walk currently on this dentry? */ ino_count = READ_ONCE(ino->count) + 1; if (d_count(dentry) > ino_count) return NULL; } if (!autofs_tree_busy(mnt, dentry, timeout, how)) return dentry; /* * Case 3: pseudo direct mount, expire individual leaves * (autofs-4.1). */ } else { struct dentry *expired; /* Not a forced expire? */ if (!(how & AUTOFS_EXP_FORCED)) { /* ref-walk currently on this dentry? */ ino_count = READ_ONCE(ino->count) + 1; if (d_count(dentry) > ino_count) return NULL; } expired = autofs_check_leaves(mnt, dentry, timeout, how); if (expired) { if (expired == dentry) dput(dentry); return expired; } } return NULL; } /* * Find an eligible tree to time-out * A tree is eligible if :- * - it is unused by any user process * - it has been unused for exp_timeout time */ static struct dentry *autofs_expire_indirect(struct super_block *sb, struct vfsmount *mnt, struct autofs_sb_info *sbi, unsigned int how) { unsigned long timeout; struct dentry *root = sb->s_root; struct dentry *dentry; struct dentry *expired; struct dentry *found; struct autofs_info *ino; if (!root) return NULL; dentry = NULL; while ((dentry = get_next_positive_subdir(dentry, root))) { spin_lock(&sbi->fs_lock); ino = autofs_dentry_ino(dentry); if (ino->flags & AUTOFS_INF_WANT_EXPIRE) { spin_unlock(&sbi->fs_lock); continue; } spin_unlock(&sbi->fs_lock); if (ino->flags & AUTOFS_INF_EXPIRE_SET) timeout = ino->exp_timeout; else timeout = sbi->exp_timeout; expired = should_expire(dentry, mnt, timeout, how); if (!expired) continue; spin_lock(&sbi->fs_lock); ino = autofs_dentry_ino(expired); ino->flags |= AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); synchronize_rcu(); /* Make sure a reference is not taken on found if * things have changed. */ how &= ~AUTOFS_EXP_LEAVES; found = should_expire(expired, mnt, timeout, how); if (found != expired) { // something has changed, continue dput(found); goto next; } if (expired != dentry) dput(dentry); spin_lock(&sbi->fs_lock); goto found; next: spin_lock(&sbi->fs_lock); ino->flags &= ~AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); if (expired != dentry) dput(expired); } return NULL; found: pr_debug("returning %p %pd\n", expired, expired); ino->flags |= AUTOFS_INF_EXPIRING; init_completion(&ino->expire_complete); spin_unlock(&sbi->fs_lock); return expired; } int autofs_expire_wait(const struct path *path, int rcu_walk) { struct dentry *dentry = path->dentry; struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); int status; int state; /* Block on any pending expire */ if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE)) return 0; if (rcu_walk) return -ECHILD; retry: spin_lock(&sbi->fs_lock); state = ino->flags & (AUTOFS_INF_WANT_EXPIRE | AUTOFS_INF_EXPIRING); if (state == AUTOFS_INF_WANT_EXPIRE) { spin_unlock(&sbi->fs_lock); /* * Possibly being selected for expire, wait until * it's selected or not. */ schedule_timeout_uninterruptible(HZ/10); goto retry; } if (state & AUTOFS_INF_EXPIRING) { spin_unlock(&sbi->fs_lock); pr_debug("waiting for expire %p name=%pd\n", dentry, dentry); status = autofs_wait(sbi, path, NFY_NONE); wait_for_completion(&ino->expire_complete); pr_debug("expire done status=%d\n", status); if (d_unhashed(dentry)) return -EAGAIN; return status; } spin_unlock(&sbi->fs_lock); return 0; } /* Perform an expiry operation */ int autofs_expire_run(struct super_block *sb, struct vfsmount *mnt, struct autofs_sb_info *sbi, struct autofs_packet_expire __user *pkt_p) { struct autofs_packet_expire pkt; struct autofs_info *ino; struct dentry *dentry; int ret = 0; memset(&pkt, 0, sizeof(pkt)); pkt.hdr.proto_version = sbi->version; pkt.hdr.type = autofs_ptype_expire; dentry = autofs_expire_indirect(sb, mnt, sbi, 0); if (!dentry) return -EAGAIN; pkt.len = dentry->d_name.len; memcpy(pkt.name, dentry->d_name.name, pkt.len); pkt.name[pkt.len] = '\0'; if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire))) ret = -EFAULT; spin_lock(&sbi->fs_lock); ino = autofs_dentry_ino(dentry); /* avoid rapid-fire expire attempts if expiry fails */ ino->last_used = jiffies; ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE); complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); dput(dentry); return ret; } int autofs_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, struct autofs_sb_info *sbi, unsigned int how) { struct dentry *dentry; int ret = -EAGAIN; if (autofs_type_trigger(sbi->type)) dentry = autofs_expire_direct(sb, mnt, sbi, how); else dentry = autofs_expire_indirect(sb, mnt, sbi, how); if (dentry) { struct autofs_info *ino = autofs_dentry_ino(dentry); const struct path path = { .mnt = mnt, .dentry = dentry }; /* This is synchronous because it makes the daemon a * little easier */ ret = autofs_wait(sbi, &path, NFY_EXPIRE); spin_lock(&sbi->fs_lock); /* avoid rapid-fire expire attempts if expiry fails */ ino->last_used = jiffies; ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE); complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); dput(dentry); } return ret; } /* * Call repeatedly until it returns -EAGAIN, meaning there's nothing * more to be done. */ int autofs_expire_multi(struct super_block *sb, struct vfsmount *mnt, struct autofs_sb_info *sbi, int __user *arg) { unsigned int how = 0; if (arg && get_user(how, arg)) return -EFAULT; return autofs_do_expire_multi(sb, mnt, sbi, how); } |
| 30 30 30 33 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 | // SPDX-License-Identifier: GPL-2.0 #include <crypto/internal/hash.h> #include <linux/init.h> #include <linux/module.h> #include <linux/xxhash.h> #include <linux/unaligned.h> #define XXHASH64_BLOCK_SIZE 32 #define XXHASH64_DIGEST_SIZE 8 struct xxhash64_tfm_ctx { u64 seed; }; struct xxhash64_desc_ctx { struct xxh64_state xxhstate; }; static int xxhash64_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { struct xxhash64_tfm_ctx *tctx = crypto_shash_ctx(tfm); if (keylen != sizeof(tctx->seed)) return -EINVAL; tctx->seed = get_unaligned_le64(key); return 0; } static int xxhash64_init(struct shash_desc *desc) { struct xxhash64_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); struct xxhash64_desc_ctx *dctx = shash_desc_ctx(desc); xxh64_reset(&dctx->xxhstate, tctx->seed); return 0; } static int xxhash64_update(struct shash_desc *desc, const u8 *data, unsigned int length) { struct xxhash64_desc_ctx *dctx = shash_desc_ctx(desc); xxh64_update(&dctx->xxhstate, data, length); return 0; } static int xxhash64_final(struct shash_desc *desc, u8 *out) { struct xxhash64_desc_ctx *dctx = shash_desc_ctx(desc); put_unaligned_le64(xxh64_digest(&dctx->xxhstate), out); return 0; } static int xxhash64_digest(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) { struct xxhash64_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); put_unaligned_le64(xxh64(data, length, tctx->seed), out); return 0; } static struct shash_alg alg = { .digestsize = XXHASH64_DIGEST_SIZE, .setkey = xxhash64_setkey, .init = xxhash64_init, .update = xxhash64_update, .final = xxhash64_final, .digest = xxhash64_digest, .descsize = sizeof(struct xxhash64_desc_ctx), .base = { .cra_name = "xxhash64", .cra_driver_name = "xxhash64-generic", .cra_priority = 100, .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, .cra_blocksize = XXHASH64_BLOCK_SIZE, .cra_ctxsize = sizeof(struct xxhash64_tfm_ctx), .cra_module = THIS_MODULE, } }; static int __init xxhash_mod_init(void) { return crypto_register_shash(&alg); } static void __exit xxhash_mod_fini(void) { crypto_unregister_shash(&alg); } subsys_initcall(xxhash_mod_init); module_exit(xxhash_mod_fini); MODULE_AUTHOR("Nikolay Borisov <nborisov@suse.com>"); MODULE_DESCRIPTION("xxhash calculations wrapper for lib/xxhash.c"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CRYPTO("xxhash64"); MODULE_ALIAS_CRYPTO("xxhash64-generic"); |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 4 4 4 4 4 4 4 4 2 4 4 4 4 4 4 4 4 4 4 4 4 4 4 3 4 4 4 4 4 4 4 4 4 3 4 4 4 4 4 4 4 4 4 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 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 | // 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_RO(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_RO(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 = get_random_u32_below(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 = get_random_u32_below(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 = get_random_u32_below(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 __rcu **mc_hash; struct ip_mc_list *im; ASSERT_RTNL(); mc_hash = rtnl_dereference(in_dev->mc_hash); if (mc_hash) { u32 hash = hash_32((__force u32)addr, MC_HASH_SZ_LOG); for (im = rtnl_dereference(mc_hash[hash]); im; im = rtnl_dereference(im->next_hash)) { if (im->multiaddr == addr) break; } } else { for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) break; } } if (im) { 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, RT_SCOPE_UNIVERSE); 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(const struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif, int sdif) { const 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_test_bit(MC_ALL, sk); 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); } 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 } |
| 11 4 10 3 11 11 10 10 5 10 11 11 11 10 3 5 5 5 5 5 5 5 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hpfs/buffer.c * * Mikulas Patocka (mikulas@artax.karlin.mff.cuni.cz), 1998-1999 * * general buffer i/o */ #include <linux/sched.h> #include <linux/slab.h> #include <linux/blkdev.h> #include "hpfs_fn.h" secno hpfs_search_hotfix_map(struct super_block *s, secno sec) { unsigned i; struct hpfs_sb_info *sbi = hpfs_sb(s); for (i = 0; unlikely(i < sbi->n_hotfixes); i++) { if (sbi->hotfix_from[i] == sec) { return sbi->hotfix_to[i]; } } return sec; } unsigned hpfs_search_hotfix_map_for_range(struct super_block *s, secno sec, unsigned n) { unsigned i; struct hpfs_sb_info *sbi = hpfs_sb(s); for (i = 0; unlikely(i < sbi->n_hotfixes); i++) { if (sbi->hotfix_from[i] >= sec && sbi->hotfix_from[i] < sec + n) { n = sbi->hotfix_from[i] - sec; } } return n; } void hpfs_prefetch_sectors(struct super_block *s, unsigned secno, int n) { struct buffer_head *bh; struct blk_plug plug; if (n <= 0 || unlikely(secno >= hpfs_sb(s)->sb_fs_size)) return; if (unlikely(hpfs_search_hotfix_map_for_range(s, secno, n) != n)) return; bh = sb_find_get_block(s, secno); if (bh) { if (buffer_uptodate(bh)) { brelse(bh); return; } brelse(bh); } blk_start_plug(&plug); while (n > 0) { if (unlikely(secno >= hpfs_sb(s)->sb_fs_size)) break; sb_breadahead(s, secno); secno++; n--; } blk_finish_plug(&plug); } /* Map a sector into a buffer and return pointers to it and to the buffer. */ void *hpfs_map_sector(struct super_block *s, unsigned secno, struct buffer_head **bhp, int ahead) { struct buffer_head *bh; hpfs_lock_assert(s); hpfs_prefetch_sectors(s, secno, ahead); cond_resched(); *bhp = bh = sb_bread(s, hpfs_search_hotfix_map(s, secno)); if (bh != NULL) return bh->b_data; else { pr_err("%s(): read error\n", __func__); return NULL; } } /* Like hpfs_map_sector but don't read anything */ void *hpfs_get_sector(struct super_block *s, unsigned secno, struct buffer_head **bhp) { struct buffer_head *bh; /*return hpfs_map_sector(s, secno, bhp, 0);*/ hpfs_lock_assert(s); cond_resched(); if ((*bhp = bh = sb_getblk(s, hpfs_search_hotfix_map(s, secno))) != NULL) { if (!buffer_uptodate(bh)) wait_on_buffer(bh); set_buffer_uptodate(bh); return bh->b_data; } else { pr_err("%s(): getblk failed\n", __func__); return NULL; } } /* Map 4 sectors into a 4buffer and return pointers to it and to the buffer. */ void *hpfs_map_4sectors(struct super_block *s, unsigned secno, struct quad_buffer_head *qbh, int ahead) { char *data; hpfs_lock_assert(s); cond_resched(); if (secno & 3) { pr_err("%s(): unaligned read\n", __func__); return NULL; } hpfs_prefetch_sectors(s, secno, 4 + ahead); if (!hpfs_map_sector(s, secno + 0, &qbh->bh[0], 0)) goto bail0; if (!hpfs_map_sector(s, secno + 1, &qbh->bh[1], 0)) goto bail1; if (!hpfs_map_sector(s, secno + 2, &qbh->bh[2], 0)) goto bail2; if (!hpfs_map_sector(s, secno + 3, &qbh->bh[3], 0)) goto bail3; if (likely(qbh->bh[1]->b_data == qbh->bh[0]->b_data + 1 * 512) && likely(qbh->bh[2]->b_data == qbh->bh[0]->b_data + 2 * 512) && likely(qbh->bh[3]->b_data == qbh->bh[0]->b_data + 3 * 512)) { return qbh->data = qbh->bh[0]->b_data; } qbh->data = data = kmalloc(2048, GFP_NOFS); if (!data) { pr_err("%s(): out of memory\n", __func__); goto bail4; } memcpy(data + 0 * 512, qbh->bh[0]->b_data, 512); memcpy(data + 1 * 512, qbh->bh[1]->b_data, 512); memcpy(data + 2 * 512, qbh->bh[2]->b_data, 512); memcpy(data + 3 * 512, qbh->bh[3]->b_data, 512); return data; bail4: brelse(qbh->bh[3]); bail3: brelse(qbh->bh[2]); bail2: brelse(qbh->bh[1]); bail1: brelse(qbh->bh[0]); bail0: return NULL; } /* Don't read sectors */ void *hpfs_get_4sectors(struct super_block *s, unsigned secno, struct quad_buffer_head *qbh) { cond_resched(); hpfs_lock_assert(s); if (secno & 3) { pr_err("%s(): unaligned read\n", __func__); return NULL; } if (!hpfs_get_sector(s, secno + 0, &qbh->bh[0])) goto bail0; if (!hpfs_get_sector(s, secno + 1, &qbh->bh[1])) goto bail1; if (!hpfs_get_sector(s, secno + 2, &qbh->bh[2])) goto bail2; if (!hpfs_get_sector(s, secno + 3, &qbh->bh[3])) goto bail3; if (likely(qbh->bh[1]->b_data == qbh->bh[0]->b_data + 1 * 512) && likely(qbh->bh[2]->b_data == qbh->bh[0]->b_data + 2 * 512) && likely(qbh->bh[3]->b_data == qbh->bh[0]->b_data + 3 * 512)) { return qbh->data = qbh->bh[0]->b_data; } if (!(qbh->data = kmalloc(2048, GFP_NOFS))) { pr_err("%s(): out of memory\n", __func__); goto bail4; } return qbh->data; bail4: brelse(qbh->bh[3]); bail3: brelse(qbh->bh[2]); bail2: brelse(qbh->bh[1]); bail1: brelse(qbh->bh[0]); bail0: return NULL; } void hpfs_brelse4(struct quad_buffer_head *qbh) { if (unlikely(qbh->data != qbh->bh[0]->b_data)) kfree(qbh->data); brelse(qbh->bh[0]); brelse(qbh->bh[1]); brelse(qbh->bh[2]); brelse(qbh->bh[3]); } void hpfs_mark_4buffers_dirty(struct quad_buffer_head *qbh) { if (unlikely(qbh->data != qbh->bh[0]->b_data)) { memcpy(qbh->bh[0]->b_data, qbh->data + 0 * 512, 512); memcpy(qbh->bh[1]->b_data, qbh->data + 1 * 512, 512); memcpy(qbh->bh[2]->b_data, qbh->data + 2 * 512, 512); memcpy(qbh->bh[3]->b_data, qbh->data + 3 * 512, 512); } mark_buffer_dirty(qbh->bh[0]); mark_buffer_dirty(qbh->bh[1]); mark_buffer_dirty(qbh->bh[2]); mark_buffer_dirty(qbh->bh[3]); } |
| 19 14 19 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 | /* * linux/fs/nls/nls_cp865.c * * Charset cp865 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00e4, 0x00e0, 0x00e5, 0x00e7, 0x00ea, 0x00eb, 0x00e8, 0x00ef, 0x00ee, 0x00ec, 0x00c4, 0x00c5, /* 0x90*/ 0x00c9, 0x00e6, 0x00c6, 0x00f4, 0x00f6, 0x00f2, 0x00fb, 0x00f9, 0x00ff, 0x00d6, 0x00dc, 0x00f8, 0x00a3, 0x00d8, 0x20a7, 0x0192, /* 0xa0*/ 0x00e1, 0x00ed, 0x00f3, 0x00fa, 0x00f1, 0x00d1, 0x00aa, 0x00ba, 0x00bf, 0x2310, 0x00ac, 0x00bd, 0x00bc, 0x00a1, 0x00ab, 0x00a4, /* 0xb0*/ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556, 0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, 0x2510, /* 0xc0*/ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567, /* 0xd0*/ 0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b, 0x256a, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580, /* 0xe0*/ 0x03b1, 0x00df, 0x0393, 0x03c0, 0x03a3, 0x03c3, 0x00b5, 0x03c4, 0x03a6, 0x0398, 0x03a9, 0x03b4, 0x221e, 0x03c6, 0x03b5, 0x2229, /* 0xf0*/ 0x2261, 0x00b1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00f7, 0x2248, 0x00b0, 0x2219, 0x00b7, 0x221a, 0x207f, 0x00b2, 0x25a0, 0x00a0, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xff, 0xad, 0x00, 0x9c, 0xaf, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0xa6, 0xae, 0xaa, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0xf8, 0xf1, 0xfd, 0x00, 0x00, 0xe6, 0x00, 0xfa, /* 0xb0-0xb7 */ 0x00, 0x00, 0xa7, 0x00, 0xac, 0xab, 0x00, 0xa8, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x8e, 0x8f, 0x92, 0x80, /* 0xc0-0xc7 */ 0x00, 0x90, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0xa5, 0x00, 0x00, 0x00, 0x00, 0x99, 0x00, /* 0xd0-0xd7 */ 0x9d, 0x00, 0x00, 0x00, 0x9a, 0x00, 0x00, 0xe1, /* 0xd8-0xdf */ 0x85, 0xa0, 0x83, 0x00, 0x84, 0x86, 0x91, 0x87, /* 0xe0-0xe7 */ 0x8a, 0x82, 0x88, 0x89, 0x8d, 0xa1, 0x8c, 0x8b, /* 0xe8-0xef */ 0x00, 0xa4, 0x95, 0xa2, 0x93, 0x00, 0x94, 0xf6, /* 0xf0-0xf7 */ 0x9b, 0x97, 0xa3, 0x96, 0x81, 0x00, 0x00, 0x98, /* 0xf8-0xff */ }; static const unsigned char page01[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x9f, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ }; static const unsigned char page03[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0xe2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0xe9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0xe4, 0x00, 0x00, 0xe8, 0x00, /* 0xa0-0xa7 */ 0x00, 0xea, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0xe0, 0x00, 0x00, 0xeb, 0xee, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0xe3, 0x00, 0x00, 0xe5, 0xe7, 0x00, 0xed, 0x00, /* 0xc0-0xc7 */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x9e, /* 0xa0-0xa7 */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0xf9, 0xfb, 0x00, 0x00, 0x00, 0xec, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0xef, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0xf7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0xf0, 0x00, 0x00, 0xf3, 0xf2, 0x00, 0x00, /* 0x60-0x67 */ }; static const unsigned char page23[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xa9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0xf4, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ }; static const unsigned char page25[256] = { 0xc4, 0x00, 0xb3, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xbf, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd9, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0xb4, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0xc2, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0xc1, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0xc5, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xcd, 0xba, 0xd5, 0xd6, 0xc9, 0xb8, 0xb7, 0xbb, /* 0x50-0x57 */ 0xd4, 0xd3, 0xc8, 0xbe, 0xbd, 0xbc, 0xc6, 0xc7, /* 0x58-0x5f */ 0xcc, 0xb5, 0xb6, 0xb9, 0xd1, 0xd2, 0xcb, 0xcf, /* 0x60-0x67 */ 0xd0, 0xca, 0xd8, 0xd7, 0xce, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xdf, 0x00, 0x00, 0x00, 0xdc, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0xdb, 0x00, 0x00, 0x00, 0xdd, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0xde, 0xb0, 0xb1, 0xb2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, page01, NULL, page03, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, NULL, page22, page23, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x87, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x84, 0x86, /* 0x88-0x8f */ 0x82, 0x91, 0x91, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x94, 0x81, 0x9b, 0x9c, 0x9b, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa4, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0x00, 0xe3, 0xe5, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xed, 0x00, 0x00, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x9a, 0x90, 0x00, 0x8e, 0x00, 0x8f, 0x80, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x92, 0x92, 0x00, 0x99, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x99, 0x9a, 0x9d, 0x9c, 0x9d, 0x9e, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0xa5, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0x00, 0xe1, 0xe2, 0x00, 0xe4, 0xe4, 0x00, 0x00, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0x00, 0xec, 0xe8, 0x00, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp865", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp865(void) { return register_nls(&table); } static void __exit exit_nls_cp865(void) { unregister_nls(&table); } module_init(init_nls_cp865) module_exit(exit_nls_cp865) MODULE_DESCRIPTION("NLS Codepage 865 (Norwegian, Danish)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 4 5 5 1 3 2 5 5 5 5 5 5 5 4 5 5 5 5 5 5 5 5 4 4 4 4 2 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* procfs files for key database enumeration * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/init.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <asm/errno.h> #include "internal.h" static void *proc_keys_start(struct seq_file *p, loff_t *_pos); static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos); static void proc_keys_stop(struct seq_file *p, void *v); static int proc_keys_show(struct seq_file *m, void *v); static const struct seq_operations proc_keys_ops = { .start = proc_keys_start, .next = proc_keys_next, .stop = proc_keys_stop, .show = proc_keys_show, }; static void *proc_key_users_start(struct seq_file *p, loff_t *_pos); static void *proc_key_users_next(struct seq_file *p, void *v, loff_t *_pos); static void proc_key_users_stop(struct seq_file *p, void *v); static int proc_key_users_show(struct seq_file *m, void *v); static const struct seq_operations proc_key_users_ops = { .start = proc_key_users_start, .next = proc_key_users_next, .stop = proc_key_users_stop, .show = proc_key_users_show, }; /* * Declare the /proc files. */ static int __init key_proc_init(void) { struct proc_dir_entry *p; p = proc_create_seq("keys", 0, NULL, &proc_keys_ops); if (!p) panic("Cannot create /proc/keys\n"); p = proc_create_seq("key-users", 0, NULL, &proc_key_users_ops); if (!p) panic("Cannot create /proc/key-users\n"); return 0; } __initcall(key_proc_init); /* * Implement "/proc/keys" to provide a list of the keys on the system that * grant View permission to the caller. */ static struct rb_node *key_serial_next(struct seq_file *p, struct rb_node *n) { struct user_namespace *user_ns = seq_user_ns(p); n = rb_next(n); while (n) { struct key *key = rb_entry(n, struct key, serial_node); if (kuid_has_mapping(user_ns, key->user->uid)) break; n = rb_next(n); } return n; } static struct key *find_ge_key(struct seq_file *p, key_serial_t id) { struct user_namespace *user_ns = seq_user_ns(p); struct rb_node *n = key_serial_tree.rb_node; struct key *minkey = NULL; while (n) { struct key *key = rb_entry(n, struct key, serial_node); if (id < key->serial) { if (!minkey || minkey->serial > key->serial) minkey = key; n = n->rb_left; } else if (id > key->serial) { n = n->rb_right; } else { minkey = key; break; } key = NULL; } if (!minkey) return NULL; for (;;) { if (kuid_has_mapping(user_ns, minkey->user->uid)) return minkey; n = rb_next(&minkey->serial_node); if (!n) return NULL; minkey = rb_entry(n, struct key, serial_node); } } static void *proc_keys_start(struct seq_file *p, loff_t *_pos) __acquires(key_serial_lock) { key_serial_t pos = *_pos; struct key *key; spin_lock(&key_serial_lock); if (*_pos > INT_MAX) return NULL; key = find_ge_key(p, pos); if (!key) return NULL; *_pos = key->serial; return &key->serial_node; } static inline key_serial_t key_node_serial(struct rb_node *n) { struct key *key = rb_entry(n, struct key, serial_node); return key->serial; } static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos) { struct rb_node *n; n = key_serial_next(p, v); if (n) *_pos = key_node_serial(n); else (*_pos)++; return n; } static void proc_keys_stop(struct seq_file *p, void *v) __releases(key_serial_lock) { spin_unlock(&key_serial_lock); } static int proc_keys_show(struct seq_file *m, void *v) { struct rb_node *_p = v; struct key *key = rb_entry(_p, struct key, serial_node); unsigned long flags; key_ref_t key_ref, skey_ref; time64_t now, expiry; char xbuf[16]; short state; u64 timo; int rc; struct keyring_search_context ctx = { .index_key = key->index_key, .cred = m->file->f_cred, .match_data.cmp = lookup_user_key_possessed, .match_data.raw_data = key, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, .flags = (KEYRING_SEARCH_NO_STATE_CHECK | KEYRING_SEARCH_RECURSE), }; key_ref = make_key_ref(key, 0); /* determine if the key is possessed by this process (a test we can * skip if the key does not indicate the possessor can view it */ if (key->perm & KEY_POS_VIEW) { rcu_read_lock(); skey_ref = search_cred_keyrings_rcu(&ctx); rcu_read_unlock(); if (!IS_ERR(skey_ref)) { key_ref_put(skey_ref); key_ref = make_key_ref(key, 1); } } /* check whether the current task is allowed to view the key */ rc = key_task_permission(key_ref, ctx.cred, KEY_NEED_VIEW); if (rc < 0) return 0; now = ktime_get_real_seconds(); rcu_read_lock(); /* come up with a suitable timeout value */ expiry = READ_ONCE(key->expiry); if (expiry == TIME64_MAX) { memcpy(xbuf, "perm", 5); } else if (now >= expiry) { memcpy(xbuf, "expd", 5); } else { timo = expiry - now; if (timo < 60) sprintf(xbuf, "%llus", timo); else if (timo < 60*60) sprintf(xbuf, "%llum", div_u64(timo, 60)); else if (timo < 60*60*24) sprintf(xbuf, "%lluh", div_u64(timo, 60 * 60)); else if (timo < 60*60*24*7) sprintf(xbuf, "%llud", div_u64(timo, 60 * 60 * 24)); else sprintf(xbuf, "%lluw", div_u64(timo, 60 * 60 * 24 * 7)); } state = key_read_state(key); #define showflag(FLAGS, LETTER, FLAG) \ ((FLAGS & (1 << FLAG)) ? LETTER : '-') flags = READ_ONCE(key->flags); seq_printf(m, "%08x %c%c%c%c%c%c%c %5d %4s %08x %5d %5d %-9.9s ", key->serial, state != KEY_IS_UNINSTANTIATED ? 'I' : '-', showflag(flags, 'R', KEY_FLAG_REVOKED), showflag(flags, 'D', KEY_FLAG_DEAD), showflag(flags, 'Q', KEY_FLAG_IN_QUOTA), showflag(flags, 'U', KEY_FLAG_USER_CONSTRUCT), state < 0 ? 'N' : '-', showflag(flags, 'i', KEY_FLAG_INVALIDATED), refcount_read(&key->usage), xbuf, key->perm, from_kuid_munged(seq_user_ns(m), key->uid), from_kgid_munged(seq_user_ns(m), key->gid), key->type->name); #undef showflag if (key->type->describe) key->type->describe(key, m); seq_putc(m, '\n'); rcu_read_unlock(); return 0; } static struct rb_node *__key_user_next(struct user_namespace *user_ns, struct rb_node *n) { while (n) { struct key_user *user = rb_entry(n, struct key_user, node); if (kuid_has_mapping(user_ns, user->uid)) break; n = rb_next(n); } return n; } static struct rb_node *key_user_next(struct user_namespace *user_ns, struct rb_node *n) { return __key_user_next(user_ns, rb_next(n)); } static struct rb_node *key_user_first(struct user_namespace *user_ns, struct rb_root *r) { struct rb_node *n = rb_first(r); return __key_user_next(user_ns, n); } static void *proc_key_users_start(struct seq_file *p, loff_t *_pos) __acquires(key_user_lock) { struct rb_node *_p; loff_t pos = *_pos; spin_lock(&key_user_lock); _p = key_user_first(seq_user_ns(p), &key_user_tree); while (pos > 0 && _p) { pos--; _p = key_user_next(seq_user_ns(p), _p); } return _p; } static void *proc_key_users_next(struct seq_file *p, void *v, loff_t *_pos) { (*_pos)++; return key_user_next(seq_user_ns(p), (struct rb_node *)v); } static void proc_key_users_stop(struct seq_file *p, void *v) __releases(key_user_lock) { spin_unlock(&key_user_lock); } static int proc_key_users_show(struct seq_file *m, void *v) { struct rb_node *_p = v; struct key_user *user = rb_entry(_p, struct key_user, node); unsigned maxkeys = uid_eq(user->uid, GLOBAL_ROOT_UID) ? key_quota_root_maxkeys : key_quota_maxkeys; unsigned maxbytes = uid_eq(user->uid, GLOBAL_ROOT_UID) ? key_quota_root_maxbytes : key_quota_maxbytes; seq_printf(m, "%5u: %5d %d/%d %d/%d %d/%d\n", from_kuid_munged(seq_user_ns(m), user->uid), refcount_read(&user->usage), atomic_read(&user->nkeys), atomic_read(&user->nikeys), user->qnkeys, maxkeys, user->qnbytes, maxbytes); return 0; } |
| 80 4 52 6 505 237 519 519 520 519 9 512 8 507 507 14 36 118 111 8 117 48 5 3 48 41 7 28 48 48 6 4 45 45 43 2 1 3 43 43 11 38 1 2 7 30 10 8 27 3 7 25 45 38 42 43 54 8 8 8 2 6 62 1 48 40 41 29 34 34 32 1 26 31 38 38 29 9 21 48 47 45 5 5 5 2 3 43 45 44 2 34 35 17 36 29 29 14 12 2 399 399 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/dir.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/dir.c * * Copyright (C) 1991, 1992 Linus Torvalds * * ext4 directory handling functions * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 * * Hash Tree Directory indexing (c) 2001 Daniel Phillips * */ #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/slab.h> #include <linux/iversion.h> #include <linux/unicode.h> #include "ext4.h" #include "xattr.h" static int ext4_dx_readdir(struct file *, struct dir_context *); /** * is_dx_dir() - check if a directory is using htree indexing * @inode: directory inode * * Check if the given dir-inode refers to an htree-indexed directory * (or a directory which could potentially get converted to use htree * indexing). * * Return 1 if it is a dx dir, 0 if not */ static int is_dx_dir(struct inode *inode) { struct super_block *sb = inode->i_sb; if (ext4_has_feature_dir_index(inode->i_sb) && ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) || ((inode->i_size >> sb->s_blocksize_bits) == 1) || ext4_has_inline_data(inode))) return 1; return 0; } static bool is_fake_dir_entry(struct ext4_dir_entry_2 *de) { /* Check if . or .. , or skip if namelen is 0 */ if ((de->name_len > 0) && (de->name_len <= 2) && (de->name[0] == '.') && (de->name[1] == '.' || de->name[1] == '\0')) return true; /* Check if this is a csum entry */ if (de->file_type == EXT4_FT_DIR_CSUM) return true; return false; } /* * Return 0 if the directory entry is OK, and 1 if there is a problem * * Note: this is the opposite of what ext2 and ext3 historically returned... * * bh passed here can be an inode block or a dir data block, depending * on the inode inline data flag. */ int __ext4_check_dir_entry(const char *function, unsigned int line, struct inode *dir, struct file *filp, struct ext4_dir_entry_2 *de, struct buffer_head *bh, char *buf, int size, unsigned int offset) { const char *error_msg = NULL; const int rlen = ext4_rec_len_from_disk(de->rec_len, dir->i_sb->s_blocksize); const int next_offset = ((char *) de - buf) + rlen; bool fake = is_fake_dir_entry(de); bool has_csum = ext4_has_metadata_csum(dir->i_sb); if (unlikely(rlen < ext4_dir_rec_len(1, fake ? NULL : dir))) error_msg = "rec_len is smaller than minimal"; else if (unlikely(rlen % 4 != 0)) error_msg = "rec_len % 4 != 0"; else if (unlikely(rlen < ext4_dir_rec_len(de->name_len, fake ? NULL : dir))) error_msg = "rec_len is too small for name_len"; else if (unlikely(next_offset > size)) error_msg = "directory entry overrun"; else if (unlikely(next_offset > size - ext4_dir_rec_len(1, has_csum ? NULL : dir) && next_offset != size)) error_msg = "directory entry too close to block end"; else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; else return 0; if (filp) ext4_error_file(filp, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u, " "inode=%u, rec_len=%d, size=%d fake=%d", error_msg, offset, le32_to_cpu(de->inode), rlen, size, fake); else ext4_error_inode(dir, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u, " "inode=%u, rec_len=%d, size=%d fake=%d", error_msg, offset, le32_to_cpu(de->inode), rlen, size, fake); return 1; } static int ext4_readdir(struct file *file, struct dir_context *ctx) { unsigned int offset; int i; struct ext4_dir_entry_2 *de; int err; struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct buffer_head *bh = NULL; struct fscrypt_str fstr = FSTR_INIT(NULL, 0); struct dir_private_info *info = file->private_data; err = fscrypt_prepare_readdir(inode); if (err) return err; if (is_dx_dir(inode)) { err = ext4_dx_readdir(file, ctx); if (err != ERR_BAD_DX_DIR) return err; /* Can we just clear INDEX flag to ignore htree information? */ if (!ext4_has_metadata_csum(sb)) { /* * We don't set the inode dirty flag since it's not * critical that it gets flushed back to the disk. */ ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); } } if (ext4_has_inline_data(inode)) { int has_inline_data = 1; err = ext4_read_inline_dir(file, ctx, &has_inline_data); if (has_inline_data) return err; } if (IS_ENCRYPTED(inode)) { err = fscrypt_fname_alloc_buffer(EXT4_NAME_LEN, &fstr); if (err < 0) return err; } while (ctx->pos < inode->i_size) { struct ext4_map_blocks map; if (fatal_signal_pending(current)) { err = -ERESTARTSYS; goto errout; } cond_resched(); offset = ctx->pos & (sb->s_blocksize - 1); map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb); map.m_len = 1; err = ext4_map_blocks(NULL, inode, &map, 0); if (err == 0) { /* m_len should never be zero but let's avoid * an infinite loop if it somehow is */ if (map.m_len == 0) map.m_len = 1; ctx->pos += map.m_len * sb->s_blocksize; continue; } if (err > 0) { pgoff_t index = map.m_pblk >> (PAGE_SHIFT - inode->i_blkbits); if (!ra_has_index(&file->f_ra, index)) page_cache_sync_readahead( sb->s_bdev->bd_mapping, &file->f_ra, file, index, 1); file->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT; bh = ext4_bread(NULL, inode, map.m_lblk, 0); if (IS_ERR(bh)) { err = PTR_ERR(bh); bh = NULL; goto errout; } } if (!bh) { /* corrupt size? Maybe no more blocks to read */ if (ctx->pos > inode->i_blocks << 9) break; ctx->pos += sb->s_blocksize - offset; continue; } /* Check the checksum */ if (!buffer_verified(bh) && !ext4_dirblock_csum_verify(inode, bh)) { EXT4_ERROR_FILE(file, 0, "directory fails checksum " "at offset %llu", (unsigned long long)ctx->pos); ctx->pos += sb->s_blocksize - offset; brelse(bh); bh = NULL; continue; } set_buffer_verified(bh); /* If the dir block has changed since the last call to * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the block * to make sure. */ if (!inode_eq_iversion(inode, info->cookie)) { for (i = 0; i < sb->s_blocksize && i < offset; ) { de = (struct ext4_dir_entry_2 *) (bh->b_data + i); /* It's too expensive to do a full * dirent test each time round this * loop, but we do have to test at * least that it is non-zero. A * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) < ext4_dir_rec_len(1, inode)) break; i += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); } offset = i; ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1)) | offset; info->cookie = inode_query_iversion(inode); } while (ctx->pos < inode->i_size && offset < sb->s_blocksize) { de = (struct ext4_dir_entry_2 *) (bh->b_data + offset); if (ext4_check_dir_entry(inode, file, de, bh, bh->b_data, bh->b_size, offset)) { /* * On error, skip to the next block */ ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1; break; } offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); if (le32_to_cpu(de->inode)) { if (!IS_ENCRYPTED(inode)) { if (!dir_emit(ctx, de->name, de->name_len, le32_to_cpu(de->inode), get_dtype(sb, de->file_type))) goto done; } else { int save_len = fstr.len; struct fscrypt_str de_name = FSTR_INIT(de->name, de->name_len); u32 hash; u32 minor_hash; if (IS_CASEFOLDED(inode)) { hash = EXT4_DIRENT_HASH(de); minor_hash = EXT4_DIRENT_MINOR_HASH(de); } else { hash = 0; minor_hash = 0; } /* Directory is encrypted */ err = fscrypt_fname_disk_to_usr(inode, hash, minor_hash, &de_name, &fstr); de_name = fstr; fstr.len = save_len; if (err) goto errout; if (!dir_emit(ctx, de_name.name, de_name.len, le32_to_cpu(de->inode), get_dtype(sb, de->file_type))) goto done; } } ctx->pos += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); } if ((ctx->pos < inode->i_size) && !dir_relax_shared(inode)) goto done; brelse(bh); bh = NULL; } done: err = 0; errout: fscrypt_fname_free_buffer(&fstr); brelse(bh); return err; } static inline int is_32bit_api(void) { #ifdef CONFIG_COMPAT return in_compat_syscall(); #else return (BITS_PER_LONG == 32); #endif } /* * These functions convert from the major/minor hash to an f_pos * value for dx directories * * Upper layer (for example NFS) should specify FMODE_32BITHASH or * FMODE_64BITHASH explicitly. On the other hand, we allow ext4 to be mounted * directly on both 32-bit and 64-bit nodes, under such case, neither * FMODE_32BITHASH nor FMODE_64BITHASH is specified. */ static inline loff_t hash2pos(struct file *filp, __u32 major, __u32 minor) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return major >> 1; else return ((__u64)(major >> 1) << 32) | (__u64)minor; } static inline __u32 pos2maj_hash(struct file *filp, loff_t pos) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return (pos << 1) & 0xffffffff; else return ((pos >> 32) << 1) & 0xffffffff; } static inline __u32 pos2min_hash(struct file *filp, loff_t pos) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return 0; else return pos & 0xffffffff; } /* * Return 32- or 64-bit end-of-file for dx directories */ static inline loff_t ext4_get_htree_eof(struct file *filp) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return EXT4_HTREE_EOF_32BIT; else return EXT4_HTREE_EOF_64BIT; } /* * ext4_dir_llseek() calls generic_file_llseek_size to handle htree * directories, where the "offset" is in terms of the filename hash * value instead of the byte offset. * * Because we may return a 64-bit hash that is well beyond offset limits, * we need to pass the max hash as the maximum allowable offset in * the htree directory case. * * For non-htree, ext4_llseek already chooses the proper max offset. */ static loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; struct dir_private_info *info = file->private_data; int dx_dir = is_dx_dir(inode); loff_t ret, htree_max = ext4_get_htree_eof(file); if (likely(dx_dir)) ret = generic_file_llseek_size(file, offset, whence, htree_max, htree_max); else ret = ext4_llseek(file, offset, whence); info->cookie = inode_peek_iversion(inode) - 1; return ret; } /* * This structure holds the nodes of the red-black tree used to store * the directory entry in hash order. */ struct fname { __u32 hash; __u32 minor_hash; struct rb_node rb_hash; struct fname *next; __u32 inode; __u8 name_len; __u8 file_type; char name[] __counted_by(name_len); }; /* * This function implements a non-recursive way of freeing all of the * nodes in the red-black tree. */ static void free_rb_tree_fname(struct rb_root *root) { struct fname *fname, *next; rbtree_postorder_for_each_entry_safe(fname, next, root, rb_hash) while (fname) { struct fname *old = fname; fname = fname->next; kfree(old); } *root = RB_ROOT; } static void ext4_htree_init_dir_info(struct file *filp, loff_t pos) { struct dir_private_info *p = filp->private_data; if (is_dx_dir(file_inode(filp)) && !p->initialized) { p->curr_hash = pos2maj_hash(filp, pos); p->curr_minor_hash = pos2min_hash(filp, pos); p->initialized = true; } } void ext4_htree_free_dir_info(struct dir_private_info *p) { free_rb_tree_fname(&p->root); kfree(p); } /* * Given a directory entry, enter it into the fname rb tree. * * When filename encryption is enabled, the dirent will hold the * encrypted filename, while the htree will hold decrypted filename. * The decrypted filename is passed in via ent_name. parameter. */ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, __u32 minor_hash, struct ext4_dir_entry_2 *dirent, struct fscrypt_str *ent_name) { struct rb_node **p, *parent = NULL; struct fname *fname, *new_fn; struct dir_private_info *info; info = dir_file->private_data; p = &info->root.rb_node; /* Create and allocate the fname structure */ new_fn = kzalloc(struct_size(new_fn, name, ent_name->len + 1), GFP_KERNEL); if (!new_fn) return -ENOMEM; new_fn->hash = hash; new_fn->minor_hash = minor_hash; new_fn->inode = le32_to_cpu(dirent->inode); new_fn->name_len = ent_name->len; new_fn->file_type = dirent->file_type; memcpy(new_fn->name, ent_name->name, ent_name->len); while (*p) { parent = *p; fname = rb_entry(parent, struct fname, rb_hash); /* * If the hash and minor hash match up, then we put * them on a linked list. This rarely happens... */ if ((new_fn->hash == fname->hash) && (new_fn->minor_hash == fname->minor_hash)) { new_fn->next = fname->next; fname->next = new_fn; return 0; } if (new_fn->hash < fname->hash) p = &(*p)->rb_left; else if (new_fn->hash > fname->hash) p = &(*p)->rb_right; else if (new_fn->minor_hash < fname->minor_hash) p = &(*p)->rb_left; else /* if (new_fn->minor_hash > fname->minor_hash) */ p = &(*p)->rb_right; } rb_link_node(&new_fn->rb_hash, parent, p); rb_insert_color(&new_fn->rb_hash, &info->root); return 0; } /* * This is a helper function for ext4_dx_readdir. It calls filldir * for all entries on the fname linked list. (Normally there is only * one entry on the linked list, unless there are 62 bit hash collisions.) */ static int call_filldir(struct file *file, struct dir_context *ctx, struct fname *fname) { struct dir_private_info *info = file->private_data; struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; if (!fname) { ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: comm %s: " "called with null fname?!?", __func__, __LINE__, inode->i_ino, current->comm); return 0; } ctx->pos = hash2pos(file, fname->hash, fname->minor_hash); while (fname) { if (!dir_emit(ctx, fname->name, fname->name_len, fname->inode, get_dtype(sb, fname->file_type))) { info->extra_fname = fname; return 1; } fname = fname->next; } return 0; } static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) { struct dir_private_info *info = file->private_data; struct inode *inode = file_inode(file); struct fname *fname; int ret = 0; ext4_htree_init_dir_info(file, ctx->pos); if (ctx->pos == ext4_get_htree_eof(file)) return 0; /* EOF */ /* Some one has messed with f_pos; reset the world */ if (info->last_pos != ctx->pos) { free_rb_tree_fname(&info->root); info->curr_node = NULL; info->extra_fname = NULL; info->curr_hash = pos2maj_hash(file, ctx->pos); info->curr_minor_hash = pos2min_hash(file, ctx->pos); } /* * If there are any leftover names on the hash collision * chain, return them first. */ if (info->extra_fname) { if (call_filldir(file, ctx, info->extra_fname)) goto finished; info->extra_fname = NULL; goto next_node; } else if (!info->curr_node) info->curr_node = rb_first(&info->root); while (1) { /* * Fill the rbtree if we have no more entries, * or the inode has changed since we last read in the * cached entries. */ if ((!info->curr_node) || !inode_eq_iversion(inode, info->cookie)) { info->curr_node = NULL; free_rb_tree_fname(&info->root); info->cookie = inode_query_iversion(inode); ret = ext4_htree_fill_tree(file, info->curr_hash, info->curr_minor_hash, &info->next_hash); if (ret < 0) goto finished; if (ret == 0) { ctx->pos = ext4_get_htree_eof(file); break; } info->curr_node = rb_first(&info->root); } fname = rb_entry(info->curr_node, struct fname, rb_hash); info->curr_hash = fname->hash; info->curr_minor_hash = fname->minor_hash; if (call_filldir(file, ctx, fname)) break; next_node: info->curr_node = rb_next(info->curr_node); if (info->curr_node) { fname = rb_entry(info->curr_node, struct fname, rb_hash); info->curr_hash = fname->hash; info->curr_minor_hash = fname->minor_hash; } else { if (info->next_hash == ~0) { ctx->pos = ext4_get_htree_eof(file); break; } info->curr_hash = info->next_hash; info->curr_minor_hash = 0; } } finished: info->last_pos = ctx->pos; return ret < 0 ? ret : 0; } static int ext4_release_dir(struct inode *inode, struct file *filp) { if (filp->private_data) ext4_htree_free_dir_info(filp->private_data); return 0; } int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, int buf_size) { struct ext4_dir_entry_2 *de; int rlen; unsigned int offset = 0; char *top; de = buf; top = buf + buf_size; while ((char *) de < top) { if (ext4_check_dir_entry(dir, NULL, de, bh, buf, buf_size, offset)) return -EFSCORRUPTED; rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); de = (struct ext4_dir_entry_2 *)((char *)de + rlen); offset += rlen; } if ((char *) de > top) return -EFSCORRUPTED; return 0; } static int ext4_dir_open(struct inode *inode, struct file *file) { struct dir_private_info *info; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; file->private_data = info; return 0; } const struct file_operations ext4_dir_operations = { .open = ext4_dir_open, .llseek = ext4_dir_llseek, .read = generic_read_dir, .iterate_shared = ext4_readdir, .unlocked_ioctl = ext4_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext4_compat_ioctl, #endif .fsync = ext4_sync_file, .release = ext4_release_dir, }; |
| 25 15 24 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 | /* * linux/fs/nls/nls_cp737.c * * Charset cp737 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0391, 0x0392, 0x0393, 0x0394, 0x0395, 0x0396, 0x0397, 0x0398, 0x0399, 0x039a, 0x039b, 0x039c, 0x039d, 0x039e, 0x039f, 0x03a0, /* 0x90*/ 0x03a1, 0x03a3, 0x03a4, 0x03a5, 0x03a6, 0x03a7, 0x03a8, 0x03a9, 0x03b1, 0x03b2, 0x03b3, 0x03b4, 0x03b5, 0x03b6, 0x03b7, 0x03b8, /* 0xa0*/ 0x03b9, 0x03ba, 0x03bb, 0x03bc, 0x03bd, 0x03be, 0x03bf, 0x03c0, 0x03c1, 0x03c3, 0x03c2, 0x03c4, 0x03c5, 0x03c6, 0x03c7, 0x03c8, /* 0xb0*/ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556, 0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, 0x2510, /* 0xc0*/ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567, /* 0xd0*/ 0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b, 0x256a, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580, /* 0xe0*/ 0x03c9, 0x03ac, 0x03ad, 0x03ae, 0x03ca, 0x03af, 0x03cc, 0x03cd, 0x03cb, 0x03ce, 0x0386, 0x0388, 0x0389, 0x038a, 0x038c, 0x038e, /* 0xf0*/ 0x038f, 0x00b1, 0x2265, 0x2264, 0x03aa, 0x03ab, 0x00f7, 0x2248, 0x00b0, 0x2219, 0x00b7, 0x221a, 0x207f, 0x00b2, 0x25a0, 0x00a0, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0xf8, 0xf1, 0xfd, 0x00, 0x00, 0x00, 0x00, 0xfa, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf6, /* 0xf0-0xf7 */ }; static const unsigned char page03[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xea, 0x00, /* 0x80-0x87 */ 0xeb, 0xec, 0xed, 0x00, 0xee, 0x00, 0xef, 0xf0, /* 0x88-0x8f */ 0x00, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, /* 0x90-0x97 */ 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, /* 0x98-0x9f */ 0x8f, 0x90, 0x00, 0x91, 0x92, 0x93, 0x94, 0x95, /* 0xa0-0xa7 */ 0x96, 0x97, 0xf4, 0xf5, 0xe1, 0xe2, 0xe3, 0xe5, /* 0xa8-0xaf */ 0x00, 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, /* 0xb0-0xb7 */ 0x9f, 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, /* 0xb8-0xbf */ 0xa7, 0xa8, 0xaa, 0xa9, 0xab, 0xac, 0xad, 0xae, /* 0xc0-0xc7 */ 0xaf, 0xe0, 0xe4, 0xe8, 0xe6, 0xe7, 0xe9, 0x00, /* 0xc8-0xcf */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, /* 0x78-0x7f */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0xf9, 0xfb, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0xf7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0xf3, 0xf2, 0x00, 0x00, /* 0x60-0x67 */ }; static const unsigned char page25[256] = { 0xc4, 0x00, 0xb3, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xbf, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd9, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0xb4, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0xc2, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0xc1, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0xc5, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xcd, 0xba, 0xd5, 0xd6, 0xc9, 0xb8, 0xb7, 0xbb, /* 0x50-0x57 */ 0xd4, 0xd3, 0xc8, 0xbe, 0xbd, 0xbc, 0xc6, 0xc7, /* 0x58-0x5f */ 0xcc, 0xb5, 0xb6, 0xb9, 0xd1, 0xd2, 0xcb, 0xcf, /* 0x60-0x67 */ 0xd0, 0xca, 0xd8, 0xd7, 0xce, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xdf, 0x00, 0x00, 0x00, 0xdc, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0xdb, 0x00, 0x00, 0x00, 0xdd, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0xde, 0xb0, 0xb1, 0xb2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, page03, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, NULL, page22, NULL, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x80-0x87 */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0x88-0x8f */ 0xa8, 0xa9, 0xab, 0xac, 0xad, 0xae, 0xaf, 0xe0, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xe1, 0xe2, 0xe3, 0xe5, 0xe6, 0xe7, /* 0xe8-0xef */ 0xe9, 0xf1, 0xf2, 0xf3, 0xe4, 0xe8, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x98-0x9f */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0xa0-0xa7 */ 0x90, 0x91, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0x97, 0xea, 0xeb, 0xec, 0xf4, 0xed, 0xee, 0xef, /* 0xe0-0xe7 */ 0xf5, 0xf0, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp737", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp737(void) { return register_nls(&table); } static void __exit exit_nls_cp737(void) { unregister_nls(&table); } module_init(init_nls_cp737) module_exit(exit_nls_cp737) MODULE_DESCRIPTION("NLS Codepage 737 (Greek)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 10 226 167 59 214 88 302 302 302 302 302 302 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 2 2 2 2 1 2 2 226 226 62 62 25 41 2 61 2 62 62 62 62 168 4 164 164 1 164 164 230 55 130 4 164 164 164 164 164 230 1 1 2 2 2 2 229 2 230 62 15 68 230 80 230 230 230 5 248 2 1 1 243 2 1 243 243 242 318 317 318 318 248 309 312 312 311 311 311 311 2 2 126 40 84 126 126 119 120 7 7 322 322 322 2 244 253 307 307 2 288 242 304 32 251 252 252 252 251 252 252 251 252 252 252 251 252 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_ialloc.h" #include "xfs_ialloc_btree.h" #include "xfs_alloc.h" #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_bmap.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_icreate_item.h" #include "xfs_icache.h" #include "xfs_trace.h" #include "xfs_log.h" #include "xfs_rmap.h" #include "xfs_ag.h" #include "xfs_health.h" /* * Lookup a record by ino in the btree given by cur. */ int /* error */ xfs_inobt_lookup( struct xfs_btree_cur *cur, /* btree cursor */ xfs_agino_t ino, /* starting inode of chunk */ xfs_lookup_t dir, /* <=, >=, == */ int *stat) /* success/failure */ { cur->bc_rec.i.ir_startino = ino; cur->bc_rec.i.ir_holemask = 0; cur->bc_rec.i.ir_count = 0; cur->bc_rec.i.ir_freecount = 0; cur->bc_rec.i.ir_free = 0; return xfs_btree_lookup(cur, dir, stat); } /* * Update the record referred to by cur to the value given. * This either works (return 0) or gets an EFSCORRUPTED error. */ STATIC int /* error */ xfs_inobt_update( struct xfs_btree_cur *cur, /* btree cursor */ xfs_inobt_rec_incore_t *irec) /* btree record */ { union xfs_btree_rec rec; rec.inobt.ir_startino = cpu_to_be32(irec->ir_startino); if (xfs_has_sparseinodes(cur->bc_mp)) { rec.inobt.ir_u.sp.ir_holemask = cpu_to_be16(irec->ir_holemask); rec.inobt.ir_u.sp.ir_count = irec->ir_count; rec.inobt.ir_u.sp.ir_freecount = irec->ir_freecount; } else { /* ir_holemask/ir_count not supported on-disk */ rec.inobt.ir_u.f.ir_freecount = cpu_to_be32(irec->ir_freecount); } rec.inobt.ir_free = cpu_to_be64(irec->ir_free); return xfs_btree_update(cur, &rec); } /* Convert on-disk btree record to incore inobt record. */ void xfs_inobt_btrec_to_irec( struct xfs_mount *mp, const union xfs_btree_rec *rec, struct xfs_inobt_rec_incore *irec) { irec->ir_startino = be32_to_cpu(rec->inobt.ir_startino); if (xfs_has_sparseinodes(mp)) { irec->ir_holemask = be16_to_cpu(rec->inobt.ir_u.sp.ir_holemask); irec->ir_count = rec->inobt.ir_u.sp.ir_count; irec->ir_freecount = rec->inobt.ir_u.sp.ir_freecount; } else { /* * ir_holemask/ir_count not supported on-disk. Fill in hardcoded * values for full inode chunks. */ irec->ir_holemask = XFS_INOBT_HOLEMASK_FULL; irec->ir_count = XFS_INODES_PER_CHUNK; irec->ir_freecount = be32_to_cpu(rec->inobt.ir_u.f.ir_freecount); } irec->ir_free = be64_to_cpu(rec->inobt.ir_free); } /* Compute the freecount of an incore inode record. */ uint8_t xfs_inobt_rec_freecount( const struct xfs_inobt_rec_incore *irec) { uint64_t realfree = irec->ir_free; if (xfs_inobt_issparse(irec->ir_holemask)) realfree &= xfs_inobt_irec_to_allocmask(irec); return hweight64(realfree); } /* Simple checks for inode records. */ xfs_failaddr_t xfs_inobt_check_irec( struct xfs_perag *pag, const struct xfs_inobt_rec_incore *irec) { /* Record has to be properly aligned within the AG. */ if (!xfs_verify_agino(pag, irec->ir_startino)) return __this_address; if (!xfs_verify_agino(pag, irec->ir_startino + XFS_INODES_PER_CHUNK - 1)) return __this_address; if (irec->ir_count < XFS_INODES_PER_HOLEMASK_BIT || irec->ir_count > XFS_INODES_PER_CHUNK) return __this_address; if (irec->ir_freecount > XFS_INODES_PER_CHUNK) return __this_address; if (xfs_inobt_rec_freecount(irec) != irec->ir_freecount) return __this_address; return NULL; } static inline int xfs_inobt_complain_bad_rec( struct xfs_btree_cur *cur, xfs_failaddr_t fa, const struct xfs_inobt_rec_incore *irec) { struct xfs_mount *mp = cur->bc_mp; xfs_warn(mp, "%sbt record corruption in AG %d detected at %pS!", cur->bc_ops->name, cur->bc_group->xg_gno, fa); xfs_warn(mp, "start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x", irec->ir_startino, irec->ir_count, irec->ir_freecount, irec->ir_free, irec->ir_holemask); xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } /* * Get the data from the pointed-to record. */ int xfs_inobt_get_rec( struct xfs_btree_cur *cur, struct xfs_inobt_rec_incore *irec, int *stat) { struct xfs_mount *mp = cur->bc_mp; union xfs_btree_rec *rec; xfs_failaddr_t fa; int error; error = xfs_btree_get_rec(cur, &rec, stat); if (error || *stat == 0) return error; xfs_inobt_btrec_to_irec(mp, rec, irec); fa = xfs_inobt_check_irec(to_perag(cur->bc_group), irec); if (fa) return xfs_inobt_complain_bad_rec(cur, fa, irec); return 0; } /* * Insert a single inobt record. Cursor must already point to desired location. */ int xfs_inobt_insert_rec( struct xfs_btree_cur *cur, uint16_t holemask, uint8_t count, int32_t freecount, xfs_inofree_t free, int *stat) { cur->bc_rec.i.ir_holemask = holemask; cur->bc_rec.i.ir_count = count; cur->bc_rec.i.ir_freecount = freecount; cur->bc_rec.i.ir_free = free; return xfs_btree_insert(cur, stat); } /* * Insert records describing a newly allocated inode chunk into the inobt. */ STATIC int xfs_inobt_insert( struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, xfs_agino_t newino, xfs_agino_t newlen, bool is_finobt) { struct xfs_btree_cur *cur; xfs_agino_t thisino; int i; int error; if (is_finobt) cur = xfs_finobt_init_cursor(pag, tp, agbp); else cur = xfs_inobt_init_cursor(pag, tp, agbp); for (thisino = newino; thisino < newino + newlen; thisino += XFS_INODES_PER_CHUNK) { error = xfs_inobt_lookup(cur, thisino, XFS_LOOKUP_EQ, &i); if (error) { xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); return error; } ASSERT(i == 0); error = xfs_inobt_insert_rec(cur, XFS_INOBT_HOLEMASK_FULL, XFS_INODES_PER_CHUNK, XFS_INODES_PER_CHUNK, XFS_INOBT_ALL_FREE, &i); if (error) { xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); return error; } ASSERT(i == 1); } xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); return 0; } /* * Verify that the number of free inodes in the AGI is correct. */ #ifdef DEBUG static int xfs_check_agi_freecount( struct xfs_btree_cur *cur) { if (cur->bc_nlevels == 1) { xfs_inobt_rec_incore_t rec; int freecount = 0; int error; int i; error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i); if (error) return error; do { error = xfs_inobt_get_rec(cur, &rec, &i); if (error) return error; if (i) { freecount += rec.ir_freecount; error = xfs_btree_increment(cur, 0, &i); if (error) return error; } } while (i == 1); if (!xfs_is_shutdown(cur->bc_mp)) { ASSERT(freecount == to_perag(cur->bc_group)->pagi_freecount); } } return 0; } #else #define xfs_check_agi_freecount(cur) 0 #endif /* * Initialise a new set of inodes. When called without a transaction context * (e.g. from recovery) we initiate a delayed write of the inode buffers rather * than logging them (which in a transaction context puts them into the AIL * for writeback rather than the xfsbufd queue). */ int xfs_ialloc_inode_init( struct xfs_mount *mp, struct xfs_trans *tp, struct list_head *buffer_list, int icount, xfs_agnumber_t agno, xfs_agblock_t agbno, xfs_agblock_t length, unsigned int gen) { struct xfs_buf *fbuf; struct xfs_dinode *free; int nbufs; int version; int i, j; xfs_daddr_t d; xfs_ino_t ino = 0; int error; /* * Loop over the new block(s), filling in the inodes. For small block * sizes, manipulate the inodes in buffers which are multiples of the * blocks size. */ nbufs = length / M_IGEO(mp)->blocks_per_cluster; /* * Figure out what version number to use in the inodes we create. If * the superblock version has caught up to the one that supports the new * inode format, then use the new inode version. Otherwise use the old * version so that old kernels will continue to be able to use the file * system. * * For v3 inodes, we also need to write the inode number into the inode, * so calculate the first inode number of the chunk here as * XFS_AGB_TO_AGINO() only works within a filesystem block, not * across multiple filesystem blocks (such as a cluster) and so cannot * be used in the cluster buffer loop below. * * Further, because we are writing the inode directly into the buffer * and calculating a CRC on the entire inode, we have ot log the entire * inode so that the entire range the CRC covers is present in the log. * That means for v3 inode we log the entire buffer rather than just the * inode cores. */ if (xfs_has_v3inodes(mp)) { version = 3; ino = XFS_AGINO_TO_INO(mp, agno, XFS_AGB_TO_AGINO(mp, agbno)); /* * log the initialisation that is about to take place as an * logical operation. This means the transaction does not * need to log the physical changes to the inode buffers as log * recovery will know what initialisation is actually needed. * Hence we only need to log the buffers as "ordered" buffers so * they track in the AIL as if they were physically logged. */ if (tp) xfs_icreate_log(tp, agno, agbno, icount, mp->m_sb.sb_inodesize, length, gen); } else version = 2; for (j = 0; j < nbufs; j++) { /* * Get the block. */ d = XFS_AGB_TO_DADDR(mp, agno, agbno + (j * M_IGEO(mp)->blocks_per_cluster)); error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize * M_IGEO(mp)->blocks_per_cluster, XBF_UNMAPPED, &fbuf); if (error) return error; /* Initialize the inode buffers and log them appropriately. */ fbuf->b_ops = &xfs_inode_buf_ops; xfs_buf_zero(fbuf, 0, BBTOB(fbuf->b_length)); for (i = 0; i < M_IGEO(mp)->inodes_per_cluster; i++) { int ioffset = i << mp->m_sb.sb_inodelog; free = xfs_make_iptr(mp, fbuf, i); free->di_magic = cpu_to_be16(XFS_DINODE_MAGIC); free->di_version = version; free->di_gen = cpu_to_be32(gen); free->di_next_unlinked = cpu_to_be32(NULLAGINO); if (version == 3) { free->di_ino = cpu_to_be64(ino); ino++; uuid_copy(&free->di_uuid, &mp->m_sb.sb_meta_uuid); xfs_dinode_calc_crc(mp, free); } else if (tp) { /* just log the inode core */ xfs_trans_log_buf(tp, fbuf, ioffset, ioffset + XFS_DINODE_SIZE(mp) - 1); } } if (tp) { /* * Mark the buffer as an inode allocation buffer so it * sticks in AIL at the point of this allocation * transaction. This ensures the they are on disk before * the tail of the log can be moved past this * transaction (i.e. by preventing relogging from moving * it forward in the log). */ xfs_trans_inode_alloc_buf(tp, fbuf); if (version == 3) { /* * Mark the buffer as ordered so that they are * not physically logged in the transaction but * still tracked in the AIL as part of the * transaction and pin the log appropriately. */ xfs_trans_ordered_buf(tp, fbuf); } } else { fbuf->b_flags |= XBF_DONE; xfs_buf_delwri_queue(fbuf, buffer_list); xfs_buf_relse(fbuf); } } return 0; } /* * Align startino and allocmask for a recently allocated sparse chunk such that * they are fit for insertion (or merge) into the on-disk inode btrees. * * Background: * * When enabled, sparse inode support increases the inode alignment from cluster * size to inode chunk size. This means that the minimum range between two * non-adjacent inode records in the inobt is large enough for a full inode * record. This allows for cluster sized, cluster aligned block allocation * without need to worry about whether the resulting inode record overlaps with * another record in the tree. Without this basic rule, we would have to deal * with the consequences of overlap by potentially undoing recent allocations in * the inode allocation codepath. * * Because of this alignment rule (which is enforced on mount), there are two * inobt possibilities for newly allocated sparse chunks. One is that the * aligned inode record for the chunk covers a range of inodes not already * covered in the inobt (i.e., it is safe to insert a new sparse record). The * other is that a record already exists at the aligned startino that considers * the newly allocated range as sparse. In the latter case, record content is * merged in hope that sparse inode chunks fill to full chunks over time. */ STATIC void xfs_align_sparse_ino( struct xfs_mount *mp, xfs_agino_t *startino, uint16_t *allocmask) { xfs_agblock_t agbno; xfs_agblock_t mod; int offset; agbno = XFS_AGINO_TO_AGBNO(mp, *startino); mod = agbno % mp->m_sb.sb_inoalignmt; if (!mod) return; /* calculate the inode offset and align startino */ offset = XFS_AGB_TO_AGINO(mp, mod); *startino -= offset; /* * Since startino has been aligned down, left shift allocmask such that * it continues to represent the same physical inodes relative to the * new startino. */ *allocmask <<= offset / XFS_INODES_PER_HOLEMASK_BIT; } /* * Determine whether the source inode record can merge into the target. Both * records must be sparse, the inode ranges must match and there must be no * allocation overlap between the records. */ STATIC bool __xfs_inobt_can_merge( struct xfs_inobt_rec_incore *trec, /* tgt record */ struct xfs_inobt_rec_incore *srec) /* src record */ { uint64_t talloc; uint64_t salloc; /* records must cover the same inode range */ if (trec->ir_startino != srec->ir_startino) return false; /* both records must be sparse */ if (!xfs_inobt_issparse(trec->ir_holemask) || !xfs_inobt_issparse(srec->ir_holemask)) return false; /* both records must track some inodes */ if (!trec->ir_count || !srec->ir_count) return false; /* can't exceed capacity of a full record */ if (trec->ir_count + srec->ir_count > XFS_INODES_PER_CHUNK) return false; /* verify there is no allocation overlap */ talloc = xfs_inobt_irec_to_allocmask(trec); salloc = xfs_inobt_irec_to_allocmask(srec); if (talloc & salloc) return false; return true; } /* * Merge the source inode record into the target. The caller must call * __xfs_inobt_can_merge() to ensure the merge is valid. */ STATIC void __xfs_inobt_rec_merge( struct xfs_inobt_rec_incore *trec, /* target */ struct xfs_inobt_rec_incore *srec) /* src */ { ASSERT(trec->ir_startino == srec->ir_startino); /* combine the counts */ trec->ir_count += srec->ir_count; trec->ir_freecount += srec->ir_freecount; /* * Merge the holemask and free mask. For both fields, 0 bits refer to * allocated inodes. We combine the allocated ranges with bitwise AND. */ trec->ir_holemask &= srec->ir_holemask; trec->ir_free &= srec->ir_free; } /* * Insert a new sparse inode chunk into the associated inode allocation btree. * The inode record for the sparse chunk is pre-aligned to a startino that * should match any pre-existing sparse inode record in the tree. This allows * sparse chunks to fill over time. * * If no preexisting record exists, the provided record is inserted. * If there is a preexisting record, the provided record is merged with the * existing record and updated in place. The merged record is returned in nrec. * * It is considered corruption if a merge is requested and not possible. Given * the sparse inode alignment constraints, this should never happen. */ STATIC int xfs_inobt_insert_sprec( struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, struct xfs_inobt_rec_incore *nrec) /* in/out: new/merged rec. */ { struct xfs_mount *mp = pag_mount(pag); struct xfs_btree_cur *cur; int error; int i; struct xfs_inobt_rec_incore rec; cur = xfs_inobt_init_cursor(pag, tp, agbp); /* the new record is pre-aligned so we know where to look */ error = xfs_inobt_lookup(cur, nrec->ir_startino, XFS_LOOKUP_EQ, &i); if (error) goto error; /* if nothing there, insert a new record and return */ if (i == 0) { error = xfs_inobt_insert_rec(cur, nrec->ir_holemask, nrec->ir_count, nrec->ir_freecount, nrec->ir_free, &i); if (error) goto error; if (XFS_IS_CORRUPT(mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error; } goto out; } /* * A record exists at this startino. Merge the records. */ error = xfs_inobt_get_rec(cur, &rec, &i); if (error) goto error; if (XFS_IS_CORRUPT(mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error; } if (XFS_IS_CORRUPT(mp, rec.ir_startino != nrec->ir_startino)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error; } /* * This should never fail. If we have coexisting records that * cannot merge, something is seriously wrong. */ if (XFS_IS_CORRUPT(mp, !__xfs_inobt_can_merge(nrec, &rec))) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error; } trace_xfs_irec_merge_pre(pag, &rec, nrec); /* merge to nrec to output the updated record */ __xfs_inobt_rec_merge(nrec, &rec); trace_xfs_irec_merge_post(pag, nrec); error = xfs_inobt_rec_check_count(mp, nrec); if (error) goto error; error = xfs_inobt_update(cur, nrec); if (error) goto error; out: xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); return 0; error: xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); return error; } /* * Insert a new sparse inode chunk into the free inode btree. The inode * record for the sparse chunk is pre-aligned to a startino that should match * any pre-existing sparse inode record in the tree. This allows sparse chunks * to fill over time. * * The new record is always inserted, overwriting a pre-existing record if * there is one. */ STATIC int xfs_finobt_insert_sprec( struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, struct xfs_inobt_rec_incore *nrec) /* in/out: new rec. */ { struct xfs_mount *mp = pag_mount(pag); struct xfs_btree_cur *cur; int error; int i; cur = xfs_finobt_init_cursor(pag, tp, agbp); /* the new record is pre-aligned so we know where to look */ error = xfs_inobt_lookup(cur, nrec->ir_startino, XFS_LOOKUP_EQ, &i); if (error) goto error; /* if nothing there, insert a new record and return */ if (i == 0) { error = xfs_inobt_insert_rec(cur, nrec->ir_holemask, nrec->ir_count, nrec->ir_freecount, nrec->ir_free, &i); if (error) goto error; if (XFS_IS_CORRUPT(mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error; } } else { error = xfs_inobt_update(cur, nrec); if (error) goto error; } xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); return 0; error: xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); return error; } /* * Allocate new inodes in the allocation group specified by agbp. Returns 0 if * inodes were allocated in this AG; -EAGAIN if there was no space in this AG so * the caller knows it can try another AG, a hard -ENOSPC when over the maximum * inode count threshold, or the usual negative error code for other errors. */ STATIC int xfs_ialloc_ag_alloc( struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp) { struct xfs_agi *agi; struct xfs_alloc_arg args; int error; xfs_agino_t newino; /* new first inode's number */ xfs_agino_t newlen; /* new number of inodes */ int isaligned = 0; /* inode allocation at stripe */ /* unit boundary */ /* init. to full chunk */ struct xfs_inobt_rec_incore rec; struct xfs_ino_geometry *igeo = M_IGEO(tp->t_mountp); uint16_t allocmask = (uint16_t) -1; int do_sparse = 0; memset(&args, 0, sizeof(args)); args.tp = tp; args.mp = tp->t_mountp; args.fsbno = NULLFSBLOCK; args.oinfo = XFS_RMAP_OINFO_INODES; args.pag = pag; #ifdef DEBUG /* randomly do sparse inode allocations */ if (xfs_has_sparseinodes(tp->t_mountp) && igeo->ialloc_min_blks < igeo->ialloc_blks) do_sparse = get_random_u32_below(2); #endif /* * Locking will ensure that we don't have two callers in here * at one time. */ newlen = igeo->ialloc_inos; if (igeo->maxicount && percpu_counter_read_positive(&args.mp->m_icount) + newlen > igeo->maxicount) return -ENOSPC; args.minlen = args.maxlen = igeo->ialloc_blks; /* * First try to allocate inodes contiguous with the last-allocated * chunk of inodes. If the filesystem is striped, this will fill * an entire stripe unit with inodes. */ agi = agbp->b_addr; newino = be32_to_cpu(agi->agi_newino); args.agbno = XFS_AGINO_TO_AGBNO(args.mp, newino) + igeo->ialloc_blks; if (do_sparse) goto sparse_alloc; if (likely(newino != NULLAGINO && (args.agbno < be32_to_cpu(agi->agi_length)))) { args.prod = 1; /* * We need to take into account alignment here to ensure that * we don't modify the free list if we fail to have an exact * block. If we don't have an exact match, and every oher * attempt allocation attempt fails, we'll end up cancelling * a dirty transaction and shutting down. * * For an exact allocation, alignment must be 1, * however we need to take cluster alignment into account when * fixing up the freelist. Use the minalignslop field to * indicate that extra blocks might be required for alignment, * but not to use them in the actual exact allocation. */ args.alignment = 1; args.minalignslop = igeo->cluster_align - 1; /* Allow space for the inode btree to split. */ args.minleft = igeo->inobt_maxlevels; error = xfs_alloc_vextent_exact_bno(&args, xfs_agbno_to_fsb(pag, args.agbno)); if (error) return error; /* * This request might have dirtied the transaction if the AG can * satisfy the request, but the exact block was not available. * If the allocation did fail, subsequent requests will relax * the exact agbno requirement and increase the alignment * instead. It is critical that the total size of the request * (len + alignment + slop) does not increase from this point * on, so reset minalignslop to ensure it is not included in * subsequent requests. */ args.minalignslop = 0; } if (unlikely(args.fsbno == NULLFSBLOCK)) { /* * Set the alignment for the allocation. * If stripe alignment is turned on then align at stripe unit * boundary. * If the cluster size is smaller than a filesystem block * then we're doing I/O for inodes in filesystem block size * pieces, so don't need alignment anyway. */ isaligned = 0; if (igeo->ialloc_align) { ASSERT(!xfs_has_noalign(args.mp)); args.alignment = args.mp->m_dalign; isaligned = 1; } else args.alignment = igeo->cluster_align; /* * Allocate a fixed-size extent of inodes. */ args.prod = 1; /* * Allow space for the inode btree to split. */ args.minleft = igeo->inobt_maxlevels; error = xfs_alloc_vextent_near_bno(&args, xfs_agbno_to_fsb(pag, be32_to_cpu(agi->agi_root))); if (error) return error; } /* * If stripe alignment is turned on, then try again with cluster * alignment. */ if (isaligned && args.fsbno == NULLFSBLOCK) { args.alignment = igeo->cluster_align; error = xfs_alloc_vextent_near_bno(&args, xfs_agbno_to_fsb(pag, be32_to_cpu(agi->agi_root))); if (error) return error; } /* * Finally, try a sparse allocation if the filesystem supports it and * the sparse allocation length is smaller than a full chunk. */ if (xfs_has_sparseinodes(args.mp) && igeo->ialloc_min_blks < igeo->ialloc_blks && args.fsbno == NULLFSBLOCK) { sparse_alloc: args.alignment = args.mp->m_sb.sb_spino_align; args.prod = 1; args.minlen = igeo->ialloc_min_blks; args.maxlen = args.minlen; /* * The inode record will be aligned to full chunk size. We must * prevent sparse allocation from AG boundaries that result in * invalid inode records, such as records that start at agbno 0 * or extend beyond the AG. * * Set min agbno to the first aligned, non-zero agbno and max to * the last aligned agbno that is at least one full chunk from * the end of the AG. */ args.min_agbno = args.mp->m_sb.sb_inoalignmt; args.max_agbno = round_down(args.mp->m_sb.sb_agblocks, args.mp->m_sb.sb_inoalignmt) - igeo->ialloc_blks; error = xfs_alloc_vextent_near_bno(&args, xfs_agbno_to_fsb(pag, be32_to_cpu(agi->agi_root))); if (error) return error; newlen = XFS_AGB_TO_AGINO(args.mp, args.len); ASSERT(newlen <= XFS_INODES_PER_CHUNK); allocmask = (1 << (newlen / XFS_INODES_PER_HOLEMASK_BIT)) - 1; } if (args.fsbno == NULLFSBLOCK) return -EAGAIN; ASSERT(args.len == args.minlen); /* * Stamp and write the inode buffers. * * Seed the new inode cluster with a random generation number. This * prevents short-term reuse of generation numbers if a chunk is * freed and then immediately reallocated. We use random numbers * rather than a linear progression to prevent the next generation * number from being easily guessable. */ error = xfs_ialloc_inode_init(args.mp, tp, NULL, newlen, pag_agno(pag), args.agbno, args.len, get_random_u32()); if (error) return error; /* * Convert the results. */ newino = XFS_AGB_TO_AGINO(args.mp, args.agbno); if (xfs_inobt_issparse(~allocmask)) { /* * We've allocated a sparse chunk. Align the startino and mask. */ xfs_align_sparse_ino(args.mp, &newino, &allocmask); rec.ir_startino = newino; rec.ir_holemask = ~allocmask; rec.ir_count = newlen; rec.ir_freecount = newlen; rec.ir_free = XFS_INOBT_ALL_FREE; /* * Insert the sparse record into the inobt and allow for a merge * if necessary. If a merge does occur, rec is updated to the * merged record. */ error = xfs_inobt_insert_sprec(pag, tp, agbp, &rec); if (error == -EFSCORRUPTED) { xfs_alert(args.mp, "invalid sparse inode record: ino 0x%llx holemask 0x%x count %u", xfs_agino_to_ino(pag, rec.ir_startino), rec.ir_holemask, rec.ir_count); xfs_force_shutdown(args.mp, SHUTDOWN_CORRUPT_INCORE); } if (error) return error; /* * We can't merge the part we've just allocated as for the inobt * due to finobt semantics. The original record may or may not * exist independent of whether physical inodes exist in this * sparse chunk. * * We must update the finobt record based on the inobt record. * rec contains the fully merged and up to date inobt record * from the previous call. Set merge false to replace any * existing record with this one. */ if (xfs_has_finobt(args.mp)) { error = xfs_finobt_insert_sprec(pag, tp, agbp, &rec); if (error) return error; } } else { /* full chunk - insert new records to both btrees */ error = xfs_inobt_insert(pag, tp, agbp, newino, newlen, false); if (error) return error; if (xfs_has_finobt(args.mp)) { error = xfs_inobt_insert(pag, tp, agbp, newino, newlen, true); if (error) return error; } } /* * Update AGI counts and newino. */ be32_add_cpu(&agi->agi_count, newlen); be32_add_cpu(&agi->agi_freecount, newlen); pag->pagi_freecount += newlen; pag->pagi_count += newlen; agi->agi_newino = cpu_to_be32(newino); /* * Log allocation group header fields */ xfs_ialloc_log_agi(tp, agbp, XFS_AGI_COUNT | XFS_AGI_FREECOUNT | XFS_AGI_NEWINO); /* * Modify/log superblock values for inode count and inode free count. */ xfs_trans_mod_sb(tp, XFS_TRANS_SB_ICOUNT, (long)newlen); xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, (long)newlen); return 0; } /* * Try to retrieve the next record to the left/right from the current one. */ STATIC int xfs_ialloc_next_rec( struct xfs_btree_cur *cur, xfs_inobt_rec_incore_t *rec, int *done, int left) { int error; int i; if (left) error = xfs_btree_decrement(cur, 0, &i); else error = xfs_btree_increment(cur, 0, &i); if (error) return error; *done = !i; if (i) { error = xfs_inobt_get_rec(cur, rec, &i); if (error) return error; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } } return 0; } STATIC int xfs_ialloc_get_rec( struct xfs_btree_cur *cur, xfs_agino_t agino, xfs_inobt_rec_incore_t *rec, int *done) { int error; int i; error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_EQ, &i); if (error) return error; *done = !i; if (i) { error = xfs_inobt_get_rec(cur, rec, &i); if (error) return error; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } } return 0; } /* * Return the offset of the first free inode in the record. If the inode chunk * is sparsely allocated, we convert the record holemask to inode granularity * and mask off the unallocated regions from the inode free mask. */ STATIC int xfs_inobt_first_free_inode( struct xfs_inobt_rec_incore *rec) { xfs_inofree_t realfree; /* if there are no holes, return the first available offset */ if (!xfs_inobt_issparse(rec->ir_holemask)) return xfs_lowbit64(rec->ir_free); realfree = xfs_inobt_irec_to_allocmask(rec); realfree &= rec->ir_free; return xfs_lowbit64(realfree); } /* * If this AG has corrupt inodes, check if allocating this inode would fail * with corruption errors. Returns 0 if we're clear, or EAGAIN to try again * somewhere else. */ static int xfs_dialloc_check_ino( struct xfs_perag *pag, struct xfs_trans *tp, xfs_ino_t ino) { struct xfs_imap imap; struct xfs_buf *bp; int error; error = xfs_imap(pag, tp, ino, &imap, 0); if (error) return -EAGAIN; error = xfs_imap_to_bp(pag_mount(pag), tp, &imap, &bp); if (error) return -EAGAIN; xfs_trans_brelse(tp, bp); return 0; } /* * Allocate an inode using the inobt-only algorithm. */ STATIC int xfs_dialloc_ag_inobt( struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, xfs_ino_t parent, xfs_ino_t *inop) { struct xfs_mount *mp = tp->t_mountp; struct xfs_agi *agi = agbp->b_addr; xfs_agnumber_t pagno = XFS_INO_TO_AGNO(mp, parent); xfs_agino_t pagino = XFS_INO_TO_AGINO(mp, parent); struct xfs_btree_cur *cur, *tcur; struct xfs_inobt_rec_incore rec, trec; xfs_ino_t ino; int error; int offset; int i, j; int searchdistance = 10; ASSERT(xfs_perag_initialised_agi(pag)); ASSERT(xfs_perag_allows_inodes(pag)); ASSERT(pag->pagi_freecount > 0); restart_pagno: cur = xfs_inobt_init_cursor(pag, tp, agbp); /* * If pagino is 0 (this is the root inode allocation) use newino. * This must work because we've just allocated some. */ if (!pagino) pagino = be32_to_cpu(agi->agi_newino); error = xfs_check_agi_freecount(cur); if (error) goto error0; /* * If in the same AG as the parent, try to get near the parent. */ if (pagno == pag_agno(pag)) { int doneleft; /* done, to the left */ int doneright; /* done, to the right */ error = xfs_inobt_lookup(cur, pagino, XFS_LOOKUP_LE, &i); if (error) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } error = xfs_inobt_get_rec(cur, &rec, &j); if (error) goto error0; if (XFS_IS_CORRUPT(mp, j != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } if (rec.ir_freecount > 0) { /* * Found a free inode in the same chunk * as the parent, done. */ goto alloc_inode; } /* * In the same AG as parent, but parent's chunk is full. */ /* duplicate the cursor, search left & right simultaneously */ error = xfs_btree_dup_cursor(cur, &tcur); if (error) goto error0; /* * Skip to last blocks looked up if same parent inode. */ if (pagino != NULLAGINO && pag->pagl_pagino == pagino && pag->pagl_leftrec != NULLAGINO && pag->pagl_rightrec != NULLAGINO) { error = xfs_ialloc_get_rec(tcur, pag->pagl_leftrec, &trec, &doneleft); if (error) goto error1; error = xfs_ialloc_get_rec(cur, pag->pagl_rightrec, &rec, &doneright); if (error) goto error1; } else { /* search left with tcur, back up 1 record */ error = xfs_ialloc_next_rec(tcur, &trec, &doneleft, 1); if (error) goto error1; /* search right with cur, go forward 1 record. */ error = xfs_ialloc_next_rec(cur, &rec, &doneright, 0); if (error) goto error1; } /* * Loop until we find an inode chunk with a free inode. */ while (--searchdistance > 0 && (!doneleft || !doneright)) { int useleft; /* using left inode chunk this time */ /* figure out the closer block if both are valid. */ if (!doneleft && !doneright) { useleft = pagino - (trec.ir_startino + XFS_INODES_PER_CHUNK - 1) < rec.ir_startino - pagino; } else { useleft = !doneleft; } /* free inodes to the left? */ if (useleft && trec.ir_freecount) { xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); cur = tcur; pag->pagl_leftrec = trec.ir_startino; pag->pagl_rightrec = rec.ir_startino; pag->pagl_pagino = pagino; rec = trec; goto alloc_inode; } /* free inodes to the right? */ if (!useleft && rec.ir_freecount) { xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); pag->pagl_leftrec = trec.ir_startino; pag->pagl_rightrec = rec.ir_startino; pag->pagl_pagino = pagino; goto alloc_inode; } /* get next record to check */ if (useleft) { error = xfs_ialloc_next_rec(tcur, &trec, &doneleft, 1); } else { error = xfs_ialloc_next_rec(cur, &rec, &doneright, 0); } if (error) goto error1; } if (searchdistance <= 0) { /* * Not in range - save last search * location and allocate a new inode */ xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); pag->pagl_leftrec = trec.ir_startino; pag->pagl_rightrec = rec.ir_startino; pag->pagl_pagino = pagino; } else { /* * We've reached the end of the btree. because * we are only searching a small chunk of the * btree each search, there is obviously free * inodes closer to the parent inode than we * are now. restart the search again. */ pag->pagl_pagino = NULLAGINO; pag->pagl_leftrec = NULLAGINO; pag->pagl_rightrec = NULLAGINO; xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); goto restart_pagno; } } /* * In a different AG from the parent. * See if the most recently allocated block has any free. */ if (agi->agi_newino != cpu_to_be32(NULLAGINO)) { error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino), XFS_LOOKUP_EQ, &i); if (error) goto error0; if (i == 1) { error = xfs_inobt_get_rec(cur, &rec, &j); if (error) goto error0; if (j == 1 && rec.ir_freecount > 0) { /* * The last chunk allocated in the group * still has a free inode. */ goto alloc_inode; } } } /* * None left in the last group, search the whole AG */ error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i); if (error) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } for (;;) { error = xfs_inobt_get_rec(cur, &rec, &i); if (error) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } if (rec.ir_freecount > 0) break; error = xfs_btree_increment(cur, 0, &i); if (error) goto error0; if (XFS_IS_CORRUPT(mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } } alloc_inode: offset = xfs_inobt_first_free_inode(&rec); ASSERT(offset >= 0); ASSERT(offset < XFS_INODES_PER_CHUNK); ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) % XFS_INODES_PER_CHUNK) == 0); ino = xfs_agino_to_ino(pag, rec.ir_startino + offset); if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) { error = xfs_dialloc_check_ino(pag, tp, ino); if (error) goto error0; } rec.ir_free &= ~XFS_INOBT_MASK(offset); rec.ir_freecount--; error = xfs_inobt_update(cur, &rec); if (error) goto error0; be32_add_cpu(&agi->agi_freecount, -1); xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT); pag->pagi_freecount--; error = xfs_check_agi_freecount(cur); if (error) goto error0; xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1); *inop = ino; return 0; error1: xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR); error0: xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); return error; } /* * Use the free inode btree to allocate an inode based on distance from the * parent. Note that the provided cursor may be deleted and replaced. */ STATIC int xfs_dialloc_ag_finobt_near( xfs_agino_t pagino, struct xfs_btree_cur **ocur, struct xfs_inobt_rec_incore *rec) { struct xfs_btree_cur *lcur = *ocur; /* left search cursor */ struct xfs_btree_cur *rcur; /* right search cursor */ struct xfs_inobt_rec_incore rrec; int error; int i, j; error = xfs_inobt_lookup(lcur, pagino, XFS_LOOKUP_LE, &i); if (error) return error; if (i == 1) { error = xfs_inobt_get_rec(lcur, rec, &i); if (error) return error; if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1)) { xfs_btree_mark_sick(lcur); return -EFSCORRUPTED; } /* * See if we've landed in the parent inode record. The finobt * only tracks chunks with at least one free inode, so record * existence is enough. */ if (pagino >= rec->ir_startino && pagino < (rec->ir_startino + XFS_INODES_PER_CHUNK)) return 0; } error = xfs_btree_dup_cursor(lcur, &rcur); if (error) return error; error = xfs_inobt_lookup(rcur, pagino, XFS_LOOKUP_GE, &j); if (error) goto error_rcur; if (j == 1) { error = xfs_inobt_get_rec(rcur, &rrec, &j); if (error) goto error_rcur; if (XFS_IS_CORRUPT(lcur->bc_mp, j != 1)) { xfs_btree_mark_sick(lcur); error = -EFSCORRUPTED; goto error_rcur; } } if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1 && j != 1)) { xfs_btree_mark_sick(lcur); error = -EFSCORRUPTED; goto error_rcur; } if (i == 1 && j == 1) { /* * Both the left and right records are valid. Choose the closer * inode chunk to the target. */ if ((pagino - rec->ir_startino + XFS_INODES_PER_CHUNK - 1) > (rrec.ir_startino - pagino)) { *rec = rrec; xfs_btree_del_cursor(lcur, XFS_BTREE_NOERROR); *ocur = rcur; } else { xfs_btree_del_cursor(rcur, XFS_BTREE_NOERROR); } } else if (j == 1) { /* only the right record is valid */ *rec = rrec; xfs_btree_del_cursor(lcur, XFS_BTREE_NOERROR); *ocur = rcur; } else if (i == 1) { /* only the left record is valid */ xfs_btree_del_cursor(rcur, XFS_BTREE_NOERROR); } return 0; error_rcur: xfs_btree_del_cursor(rcur, XFS_BTREE_ERROR); return error; } /* * Use the free inode btree to find a free inode based on a newino hint. If * the hint is NULL, find the first free inode in the AG. */ STATIC int xfs_dialloc_ag_finobt_newino( struct xfs_agi *agi, struct xfs_btree_cur *cur, struct xfs_inobt_rec_incore *rec) { int error; int i; if (agi->agi_newino != cpu_to_be32(NULLAGINO)) { error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino), XFS_LOOKUP_EQ, &i); if (error) return error; if (i == 1) { error = xfs_inobt_get_rec(cur, rec, &i); if (error) return error; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } return 0; } } /* * Find the first inode available in the AG. */ error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i); if (error) return error; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } error = xfs_inobt_get_rec(cur, rec, &i); if (error) return error; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } return 0; } /* * Update the inobt based on a modification made to the finobt. Also ensure that * the records from both trees are equivalent post-modification. */ STATIC int xfs_dialloc_ag_update_inobt( struct xfs_btree_cur *cur, /* inobt cursor */ struct xfs_inobt_rec_incore *frec, /* finobt record */ int offset) /* inode offset */ { struct xfs_inobt_rec_incore rec; int error; int i; error = xfs_inobt_lookup(cur, frec->ir_startino, XFS_LOOKUP_EQ, &i); if (error) return error; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } error = xfs_inobt_get_rec(cur, &rec, &i); if (error) return error; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } ASSERT((XFS_AGINO_TO_OFFSET(cur->bc_mp, rec.ir_startino) % XFS_INODES_PER_CHUNK) == 0); rec.ir_free &= ~XFS_INOBT_MASK(offset); rec.ir_freecount--; if (XFS_IS_CORRUPT(cur->bc_mp, rec.ir_free != frec->ir_free || rec.ir_freecount != frec->ir_freecount)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } return xfs_inobt_update(cur, &rec); } /* * Allocate an inode using the free inode btree, if available. Otherwise, fall * back to the inobt search algorithm. * * The caller selected an AG for us, and made sure that free inodes are * available. */ static int xfs_dialloc_ag( struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, xfs_ino_t parent, xfs_ino_t *inop) { struct xfs_mount *mp = tp->t_mountp; struct xfs_agi *agi = agbp->b_addr; xfs_agnumber_t pagno = XFS_INO_TO_AGNO(mp, parent); xfs_agino_t pagino = XFS_INO_TO_AGINO(mp, parent); struct xfs_btree_cur *cur; /* finobt cursor */ struct xfs_btree_cur *icur; /* inobt cursor */ struct xfs_inobt_rec_incore rec; xfs_ino_t ino; int error; int offset; int i; if (!xfs_has_finobt(mp)) return xfs_dialloc_ag_inobt(pag, tp, agbp, parent, inop); /* * If pagino is 0 (this is the root inode allocation) use newino. * This must work because we've just allocated some. */ if (!pagino) pagino = be32_to_cpu(agi->agi_newino); cur = xfs_finobt_init_cursor(pag, tp, agbp); error = xfs_check_agi_freecount(cur); if (error) goto error_cur; /* * The search algorithm depends on whether we're in the same AG as the * parent. If so, find the closest available inode to the parent. If * not, consider the agi hint or find the first free inode in the AG. */ if (pag_agno(pag) == pagno) error = xfs_dialloc_ag_finobt_near(pagino, &cur, &rec); else error = xfs_dialloc_ag_finobt_newino(agi, cur, &rec); if (error) goto error_cur; offset = xfs_inobt_first_free_inode(&rec); ASSERT(offset >= 0); ASSERT(offset < XFS_INODES_PER_CHUNK); ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) % XFS_INODES_PER_CHUNK) == 0); ino = xfs_agino_to_ino(pag, rec.ir_startino + offset); if (xfs_ag_has_sickness(pag, XFS_SICK_AG_INODES)) { error = xfs_dialloc_check_ino(pag, tp, ino); if (error) goto error_cur; } /* * Modify or remove the finobt record. */ rec.ir_free &= ~XFS_INOBT_MASK(offset); rec.ir_freecount--; if (rec.ir_freecount) error = xfs_inobt_update(cur, &rec); else error = xfs_btree_delete(cur, &i); if (error) goto error_cur; /* * The finobt has now been updated appropriately. We haven't updated the * agi and superblock yet, so we can create an inobt cursor and validate * the original freecount. If all is well, make the equivalent update to * the inobt using the finobt record and offset information. */ icur = xfs_inobt_init_cursor(pag, tp, agbp); error = xfs_check_agi_freecount(icur); if (error) goto error_icur; error = xfs_dialloc_ag_update_inobt(icur, &rec, offset); if (error) goto error_icur; /* * Both trees have now been updated. We must update the perag and * superblock before we can check the freecount for each btree. */ be32_add_cpu(&agi->agi_freecount, -1); xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT); pag->pagi_freecount--; xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1); error = xfs_check_agi_freecount(icur); if (error) goto error_icur; error = xfs_check_agi_freecount(cur); if (error) goto error_icur; xfs_btree_del_cursor(icur, XFS_BTREE_NOERROR); xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); *inop = ino; return 0; error_icur: xfs_btree_del_cursor(icur, XFS_BTREE_ERROR); error_cur: xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); return error; } static int xfs_dialloc_roll( struct xfs_trans **tpp, struct xfs_buf *agibp) { struct xfs_trans *tp = *tpp; struct xfs_dquot_acct *dqinfo; int error; /* * Hold to on to the agibp across the commit so no other allocation can * come in and take the free inodes we just allocated for our caller. */ xfs_trans_bhold(tp, agibp); /* * We want the quota changes to be associated with the next transaction, * NOT this one. So, detach the dqinfo from this and attach it to the * next transaction. */ dqinfo = tp->t_dqinfo; tp->t_dqinfo = NULL; error = xfs_trans_roll(&tp); /* Re-attach the quota info that we detached from prev trx. */ tp->t_dqinfo = dqinfo; /* * Join the buffer even on commit error so that the buffer is released * when the caller cancels the transaction and doesn't have to handle * this error case specially. */ xfs_trans_bjoin(tp, agibp); *tpp = tp; return error; } static bool xfs_dialloc_good_ag( struct xfs_perag *pag, struct xfs_trans *tp, umode_t mode, int flags, bool ok_alloc) { struct xfs_mount *mp = tp->t_mountp; xfs_extlen_t ineed; xfs_extlen_t longest = 0; int needspace; int error; if (!pag) return false; if (!xfs_perag_allows_inodes(pag)) return false; if (!xfs_perag_initialised_agi(pag)) { error = xfs_ialloc_read_agi(pag, tp, 0, NULL); if (error) return false; } if (pag->pagi_freecount) return true; if (!ok_alloc) return false; if (!xfs_perag_initialised_agf(pag)) { error = xfs_alloc_read_agf(pag, tp, flags, NULL); if (error) return false; } /* * Check that there is enough free space for the file plus a chunk of * inodes if we need to allocate some. If this is the first pass across * the AGs, take into account the potential space needed for alignment * of inode chunks when checking the longest contiguous free space in * the AG - this prevents us from getting ENOSPC because we have free * space larger than ialloc_blks but alignment constraints prevent us * from using it. * * If we can't find an AG with space for full alignment slack to be * taken into account, we must be near ENOSPC in all AGs. Hence we * don't include alignment for the second pass and so if we fail * allocation due to alignment issues then it is most likely a real * ENOSPC condition. * * XXX(dgc): this calculation is now bogus thanks to the per-ag * reservations that xfs_alloc_fix_freelist() now does via * xfs_alloc_space_available(). When the AG fills up, pagf_freeblks will * be more than large enough for the check below to succeed, but * xfs_alloc_space_available() will fail because of the non-zero * metadata reservation and hence we won't actually be able to allocate * more inodes in this AG. We do soooo much unnecessary work near ENOSPC * because of this. */ ineed = M_IGEO(mp)->ialloc_min_blks; if (flags && ineed > 1) ineed += M_IGEO(mp)->cluster_align; longest = pag->pagf_longest; if (!longest) longest = pag->pagf_flcount > 0; needspace = S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode); if (pag->pagf_freeblks < needspace + ineed || longest < ineed) return false; return true; } static int xfs_dialloc_try_ag( struct xfs_perag *pag, struct xfs_trans **tpp, xfs_ino_t parent, xfs_ino_t *new_ino, bool ok_alloc) { struct xfs_buf *agbp; xfs_ino_t ino; int error; /* * Then read in the AGI buffer and recheck with the AGI buffer * lock held. */ error = xfs_ialloc_read_agi(pag, *tpp, 0, &agbp); if (error) return error; if (!pag->pagi_freecount) { if (!ok_alloc) { error = -EAGAIN; goto out_release; } error = xfs_ialloc_ag_alloc(pag, *tpp, agbp); if (error < 0) goto out_release; /* * We successfully allocated space for an inode cluster in this * AG. Roll the transaction so that we can allocate one of the * new inodes. */ ASSERT(pag->pagi_freecount > 0); error = xfs_dialloc_roll(tpp, agbp); if (error) goto out_release; } /* Allocate an inode in the found AG */ error = xfs_dialloc_ag(pag, *tpp, agbp, parent, &ino); if (!error) *new_ino = ino; return error; out_release: xfs_trans_brelse(*tpp, agbp); return error; } /* * Pick an AG for the new inode. * * Directories, symlinks, and regular files frequently allocate at least one * block, so factor that potential expansion when we examine whether an AG has * enough space for file creation. Try to keep metadata files all in the same * AG. */ static inline xfs_agnumber_t xfs_dialloc_pick_ag( struct xfs_mount *mp, struct xfs_inode *dp, umode_t mode) { xfs_agnumber_t start_agno; if (!dp) return 0; if (xfs_is_metadir_inode(dp)) { if (mp->m_sb.sb_logstart) return XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart); return 0; } if (S_ISDIR(mode)) return (atomic_inc_return(&mp->m_agirotor) - 1) % mp->m_maxagi; start_agno = XFS_INO_TO_AGNO(mp, dp->i_ino); if (start_agno >= mp->m_maxagi) start_agno = 0; return start_agno; } /* * Allocate an on-disk inode. * * Mode is used to tell whether the new inode is a directory and hence where to * locate it. The on-disk inode that is allocated will be returned in @new_ino * on success, otherwise an error will be set to indicate the failure (e.g. * -ENOSPC). */ int xfs_dialloc( struct xfs_trans **tpp, const struct xfs_icreate_args *args, xfs_ino_t *new_ino) { struct xfs_mount *mp = (*tpp)->t_mountp; struct xfs_perag *pag; struct xfs_ino_geometry *igeo = M_IGEO(mp); xfs_ino_t ino = NULLFSINO; xfs_ino_t parent = args->pip ? args->pip->i_ino : 0; xfs_agnumber_t agno; xfs_agnumber_t start_agno; umode_t mode = args->mode & S_IFMT; bool ok_alloc = true; bool low_space = false; int flags; int error = 0; start_agno = xfs_dialloc_pick_ag(mp, args->pip, mode); /* * If we have already hit the ceiling of inode blocks then clear * ok_alloc so we scan all available agi structures for a free * inode. * * Read rough value of mp->m_icount by percpu_counter_read_positive, * which will sacrifice the preciseness but improve the performance. */ if (igeo->maxicount && percpu_counter_read_positive(&mp->m_icount) + igeo->ialloc_inos > igeo->maxicount) { ok_alloc = false; } /* * If we are near to ENOSPC, we want to prefer allocation from AGs that * have free inodes in them rather than use up free space allocating new * inode chunks. Hence we turn off allocation for the first non-blocking * pass through the AGs if we are near ENOSPC to consume free inodes * that we can immediately allocate, but then we allow allocation on the * second pass if we fail to find an AG with free inodes in it. */ if (percpu_counter_read_positive(&mp->m_fdblocks) < mp->m_low_space[XFS_LOWSP_1_PCNT]) { ok_alloc = false; low_space = true; } /* * Loop until we find an allocation group that either has free inodes * or in which we can allocate some inodes. Iterate through the * allocation groups upward, wrapping at the end. */ flags = XFS_ALLOC_FLAG_TRYLOCK; retry: for_each_perag_wrap_at(mp, start_agno, mp->m_maxagi, agno, pag) { if (xfs_dialloc_good_ag(pag, *tpp, mode, flags, ok_alloc)) { error = xfs_dialloc_try_ag(pag, tpp, parent, &ino, ok_alloc); if (error != -EAGAIN) break; error = 0; } if (xfs_is_shutdown(mp)) { error = -EFSCORRUPTED; break; } } if (pag) xfs_perag_rele(pag); if (error) return error; if (ino == NULLFSINO) { if (flags) { flags = 0; if (low_space) ok_alloc = true; goto retry; } return -ENOSPC; } /* * Protect against obviously corrupt allocation btree records. Later * xfs_iget checks will catch re-allocation of other active in-memory * and on-disk inodes. If we don't catch reallocating the parent inode * here we will deadlock in xfs_iget() so we have to do these checks * first. */ if (ino == parent || !xfs_verify_dir_ino(mp, ino)) { xfs_alert(mp, "Allocated a known in-use inode 0x%llx!", ino); xfs_agno_mark_sick(mp, XFS_INO_TO_AGNO(mp, ino), XFS_SICK_AG_INOBT); return -EFSCORRUPTED; } *new_ino = ino; return 0; } /* * Free the blocks of an inode chunk. We must consider that the inode chunk * might be sparse and only free the regions that are allocated as part of the * chunk. */ static int xfs_difree_inode_chunk( struct xfs_trans *tp, struct xfs_perag *pag, struct xfs_inobt_rec_incore *rec) { struct xfs_mount *mp = tp->t_mountp; xfs_agblock_t sagbno = XFS_AGINO_TO_AGBNO(mp, rec->ir_startino); int startidx, endidx; int nextbit; xfs_agblock_t agbno; int contigblk; DECLARE_BITMAP(holemask, XFS_INOBT_HOLEMASK_BITS); if (!xfs_inobt_issparse(rec->ir_holemask)) { /* not sparse, calculate extent info directly */ return xfs_free_extent_later(tp, xfs_agbno_to_fsb(pag, sagbno), M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE, 0); } /* holemask is only 16-bits (fits in an unsigned long) */ ASSERT(sizeof(rec->ir_holemask) <= sizeof(holemask[0])); holemask[0] = rec->ir_holemask; /* * Find contiguous ranges of zeroes (i.e., allocated regions) in the * holemask and convert the start/end index of each range to an extent. * We start with the start and end index both pointing at the first 0 in * the mask. */ startidx = endidx = find_first_zero_bit(holemask, XFS_INOBT_HOLEMASK_BITS); nextbit = startidx + 1; while (startidx < XFS_INOBT_HOLEMASK_BITS) { int error; nextbit = find_next_zero_bit(holemask, XFS_INOBT_HOLEMASK_BITS, nextbit); /* * If the next zero bit is contiguous, update the end index of * the current range and continue. */ if (nextbit != XFS_INOBT_HOLEMASK_BITS && nextbit == endidx + 1) { endidx = nextbit; goto next; } /* * nextbit is not contiguous with the current end index. Convert * the current start/end to an extent and add it to the free * list. */ agbno = sagbno + (startidx * XFS_INODES_PER_HOLEMASK_BIT) / mp->m_sb.sb_inopblock; contigblk = ((endidx - startidx + 1) * XFS_INODES_PER_HOLEMASK_BIT) / mp->m_sb.sb_inopblock; ASSERT(agbno % mp->m_sb.sb_spino_align == 0); ASSERT(contigblk % mp->m_sb.sb_spino_align == 0); error = xfs_free_extent_later(tp, xfs_agbno_to_fsb(pag, agbno), contigblk, &XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE, 0); if (error) return error; /* reset range to current bit and carry on... */ startidx = endidx = nextbit; next: nextbit++; } return 0; } STATIC int xfs_difree_inobt( struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, xfs_agino_t agino, struct xfs_icluster *xic, struct xfs_inobt_rec_incore *orec) { struct xfs_mount *mp = pag_mount(pag); struct xfs_agi *agi = agbp->b_addr; struct xfs_btree_cur *cur; struct xfs_inobt_rec_incore rec; int ilen; int error; int i; int off; ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC)); ASSERT(XFS_AGINO_TO_AGBNO(mp, agino) < be32_to_cpu(agi->agi_length)); /* * Initialize the cursor. */ cur = xfs_inobt_init_cursor(pag, tp, agbp); error = xfs_check_agi_freecount(cur); if (error) goto error0; /* * Look for the entry describing this inode. */ if ((error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i))) { xfs_warn(mp, "%s: xfs_inobt_lookup() returned error %d.", __func__, error); goto error0; } if (XFS_IS_CORRUPT(mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } error = xfs_inobt_get_rec(cur, &rec, &i); if (error) { xfs_warn(mp, "%s: xfs_inobt_get_rec() returned error %d.", __func__, error); goto error0; } if (XFS_IS_CORRUPT(mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } /* * Get the offset in the inode chunk. */ off = agino - rec.ir_startino; ASSERT(off >= 0 && off < XFS_INODES_PER_CHUNK); ASSERT(!(rec.ir_free & XFS_INOBT_MASK(off))); /* * Mark the inode free & increment the count. */ rec.ir_free |= XFS_INOBT_MASK(off); rec.ir_freecount++; /* * When an inode chunk is free, it becomes eligible for removal. Don't * remove the chunk if the block size is large enough for multiple inode * chunks (that might not be free). */ if (!xfs_has_ikeep(mp) && rec.ir_free == XFS_INOBT_ALL_FREE && mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) { xic->deleted = true; xic->first_ino = xfs_agino_to_ino(pag, rec.ir_startino); xic->alloc = xfs_inobt_irec_to_allocmask(&rec); /* * Remove the inode cluster from the AGI B+Tree, adjust the * AGI and Superblock inode counts, and mark the disk space * to be freed when the transaction is committed. */ ilen = rec.ir_freecount; be32_add_cpu(&agi->agi_count, -ilen); be32_add_cpu(&agi->agi_freecount, -(ilen - 1)); xfs_ialloc_log_agi(tp, agbp, XFS_AGI_COUNT | XFS_AGI_FREECOUNT); pag->pagi_freecount -= ilen - 1; pag->pagi_count -= ilen; xfs_trans_mod_sb(tp, XFS_TRANS_SB_ICOUNT, -ilen); xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -(ilen - 1)); if ((error = xfs_btree_delete(cur, &i))) { xfs_warn(mp, "%s: xfs_btree_delete returned error %d.", __func__, error); goto error0; } error = xfs_difree_inode_chunk(tp, pag, &rec); if (error) goto error0; } else { xic->deleted = false; error = xfs_inobt_update(cur, &rec); if (error) { xfs_warn(mp, "%s: xfs_inobt_update returned error %d.", __func__, error); goto error0; } /* * Change the inode free counts and log the ag/sb changes. */ be32_add_cpu(&agi->agi_freecount, 1); xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT); pag->pagi_freecount++; xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, 1); } error = xfs_check_agi_freecount(cur); if (error) goto error0; *orec = rec; xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); return 0; error0: xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); return error; } /* * Free an inode in the free inode btree. */ STATIC int xfs_difree_finobt( struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agbp, xfs_agino_t agino, struct xfs_inobt_rec_incore *ibtrec) /* inobt record */ { struct xfs_mount *mp = pag_mount(pag); struct xfs_btree_cur *cur; struct xfs_inobt_rec_incore rec; int offset = agino - ibtrec->ir_startino; int error; int i; cur = xfs_finobt_init_cursor(pag, tp, agbp); error = xfs_inobt_lookup(cur, ibtrec->ir_startino, XFS_LOOKUP_EQ, &i); if (error) goto error; if (i == 0) { /* * If the record does not exist in the finobt, we must have just * freed an inode in a previously fully allocated chunk. If not, * something is out of sync. */ if (XFS_IS_CORRUPT(mp, ibtrec->ir_freecount != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error; } error = xfs_inobt_insert_rec(cur, ibtrec->ir_holemask, ibtrec->ir_count, ibtrec->ir_freecount, ibtrec->ir_free, &i); if (error) goto error; ASSERT(i == 1); goto out; } /* * Read and update the existing record. We could just copy the ibtrec * across here, but that would defeat the purpose of having redundant * metadata. By making the modifications independently, we can catch * corruptions that we wouldn't see if we just copied from one record * to another. */ error = xfs_inobt_get_rec(cur, &rec, &i); if (error) goto error; if (XFS_IS_CORRUPT(mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error; } rec.ir_free |= XFS_INOBT_MASK(offset); rec.ir_freecount++; if (XFS_IS_CORRUPT(mp, rec.ir_free != ibtrec->ir_free || rec.ir_freecount != ibtrec->ir_freecount)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error; } /* * The content of inobt records should always match between the inobt * and finobt. The lifecycle of records in the finobt is different from * the inobt in that the finobt only tracks records with at least one * free inode. Hence, if all of the inodes are free and we aren't * keeping inode chunks permanently on disk, remove the record. * Otherwise, update the record with the new information. * * Note that we currently can't free chunks when the block size is large * enough for multiple chunks. Leave the finobt record to remain in sync * with the inobt. */ if (!xfs_has_ikeep(mp) && rec.ir_free == XFS_INOBT_ALL_FREE && mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) { error = xfs_btree_delete(cur, &i); if (error) goto error; ASSERT(i == 1); } else { error = xfs_inobt_update(cur, &rec); if (error) goto error; } out: error = xfs_check_agi_freecount(cur); if (error) goto error; xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); return 0; error: xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); return error; } /* * Free disk inode. Carefully avoids touching the incore inode, all * manipulations incore are the caller's responsibility. * The on-disk inode is not changed by this operation, only the * btree (free inode mask) is changed. */ int xfs_difree( struct xfs_trans *tp, struct xfs_perag *pag, xfs_ino_t inode, struct xfs_icluster *xic) { /* REFERENCED */ xfs_agblock_t agbno; /* block number containing inode */ struct xfs_buf *agbp; /* buffer for allocation group header */ xfs_agino_t agino; /* allocation group inode number */ int error; /* error return value */ struct xfs_mount *mp = tp->t_mountp; struct xfs_inobt_rec_incore rec;/* btree record */ /* * Break up inode number into its components. */ if (pag_agno(pag) != XFS_INO_TO_AGNO(mp, inode)) { xfs_warn(mp, "%s: agno != pag_agno(pag) (%d != %d).", __func__, XFS_INO_TO_AGNO(mp, inode), pag_agno(pag)); ASSERT(0); return -EINVAL; } agino = XFS_INO_TO_AGINO(mp, inode); if (inode != xfs_agino_to_ino(pag, agino)) { xfs_warn(mp, "%s: inode != xfs_agino_to_ino() (%llu != %llu).", __func__, (unsigned long long)inode, (unsigned long long)xfs_agino_to_ino(pag, agino)); ASSERT(0); return -EINVAL; } agbno = XFS_AGINO_TO_AGBNO(mp, agino); if (agbno >= mp->m_sb.sb_agblocks) { xfs_warn(mp, "%s: agbno >= mp->m_sb.sb_agblocks (%d >= %d).", __func__, agbno, mp->m_sb.sb_agblocks); ASSERT(0); return -EINVAL; } /* * Get the allocation group header. */ error = xfs_ialloc_read_agi(pag, tp, 0, &agbp); if (error) { xfs_warn(mp, "%s: xfs_ialloc_read_agi() returned error %d.", __func__, error); return error; } /* * Fix up the inode allocation btree. */ error = xfs_difree_inobt(pag, tp, agbp, agino, xic, &rec); if (error) goto error0; /* * Fix up the free inode btree. */ if (xfs_has_finobt(mp)) { error = xfs_difree_finobt(pag, tp, agbp, agino, &rec); if (error) goto error0; } return 0; error0: return error; } STATIC int xfs_imap_lookup( struct xfs_perag *pag, struct xfs_trans *tp, xfs_agino_t agino, xfs_agblock_t agbno, xfs_agblock_t *chunk_agbno, xfs_agblock_t *offset_agbno, int flags) { struct xfs_mount *mp = pag_mount(pag); struct xfs_inobt_rec_incore rec; struct xfs_btree_cur *cur; struct xfs_buf *agbp; int error; int i; error = xfs_ialloc_read_agi(pag, tp, 0, &agbp); if (error) { xfs_alert(mp, "%s: xfs_ialloc_read_agi() returned error %d, agno %d", __func__, error, pag_agno(pag)); return error; } /* * Lookup the inode record for the given agino. If the record cannot be * found, then it's an invalid inode number and we should abort. Once * we have a record, we need to ensure it contains the inode number * we are looking up. */ cur = xfs_inobt_init_cursor(pag, tp, agbp); error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i); if (!error) { if (i) error = xfs_inobt_get_rec(cur, &rec, &i); if (!error && i == 0) error = -EINVAL; } xfs_trans_brelse(tp, agbp); xfs_btree_del_cursor(cur, error); if (error) return error; /* check that the returned record contains the required inode */ if (rec.ir_startino > agino || rec.ir_startino + M_IGEO(mp)->ialloc_inos <= agino) return -EINVAL; /* for untrusted inodes check it is allocated first */ if ((flags & XFS_IGET_UNTRUSTED) && (rec.ir_free & XFS_INOBT_MASK(agino - rec.ir_startino))) return -EINVAL; *chunk_agbno = XFS_AGINO_TO_AGBNO(mp, rec.ir_startino); *offset_agbno = agbno - *chunk_agbno; return 0; } /* * Return the location of the inode in imap, for mapping it into a buffer. */ int xfs_imap( struct xfs_perag *pag, struct xfs_trans *tp, xfs_ino_t ino, /* inode to locate */ struct xfs_imap *imap, /* location map structure */ uint flags) /* flags for inode btree lookup */ { struct xfs_mount *mp = pag_mount(pag); xfs_agblock_t agbno; /* block number of inode in the alloc group */ xfs_agino_t agino; /* inode number within alloc group */ xfs_agblock_t chunk_agbno; /* first block in inode chunk */ xfs_agblock_t cluster_agbno; /* first block in inode cluster */ int error; /* error code */ int offset; /* index of inode in its buffer */ xfs_agblock_t offset_agbno; /* blks from chunk start to inode */ ASSERT(ino != NULLFSINO); /* * Split up the inode number into its parts. */ agino = XFS_INO_TO_AGINO(mp, ino); agbno = XFS_AGINO_TO_AGBNO(mp, agino); if (agbno >= mp->m_sb.sb_agblocks || ino != xfs_agino_to_ino(pag, agino)) { error = -EINVAL; #ifdef DEBUG /* * Don't output diagnostic information for untrusted inodes * as they can be invalid without implying corruption. */ if (flags & XFS_IGET_UNTRUSTED) return error; if (agbno >= mp->m_sb.sb_agblocks) { xfs_alert(mp, "%s: agbno (0x%llx) >= mp->m_sb.sb_agblocks (0x%lx)", __func__, (unsigned long long)agbno, (unsigned long)mp->m_sb.sb_agblocks); } if (ino != xfs_agino_to_ino(pag, agino)) { xfs_alert(mp, "%s: ino (0x%llx) != xfs_agino_to_ino() (0x%llx)", __func__, ino, xfs_agino_to_ino(pag, agino)); } xfs_stack_trace(); #endif /* DEBUG */ return error; } /* * For bulkstat and handle lookups, we have an untrusted inode number * that we have to verify is valid. We cannot do this just by reading * the inode buffer as it may have been unlinked and removed leaving * inodes in stale state on disk. Hence we have to do a btree lookup * in all cases where an untrusted inode number is passed. */ if (flags & XFS_IGET_UNTRUSTED) { error = xfs_imap_lookup(pag, tp, agino, agbno, &chunk_agbno, &offset_agbno, flags); if (error) return error; goto out_map; } /* * If the inode cluster size is the same as the blocksize or * smaller we get to the buffer by simple arithmetics. */ if (M_IGEO(mp)->blocks_per_cluster == 1) { offset = XFS_INO_TO_OFFSET(mp, ino); ASSERT(offset < mp->m_sb.sb_inopblock); imap->im_blkno = xfs_agbno_to_daddr(pag, agbno); imap->im_len = XFS_FSB_TO_BB(mp, 1); imap->im_boffset = (unsigned short)(offset << mp->m_sb.sb_inodelog); return 0; } /* * If the inode chunks are aligned then use simple maths to * find the location. Otherwise we have to do a btree * lookup to find the location. */ if (M_IGEO(mp)->inoalign_mask) { offset_agbno = agbno & M_IGEO(mp)->inoalign_mask; chunk_agbno = agbno - offset_agbno; } else { error = xfs_imap_lookup(pag, tp, agino, agbno, &chunk_agbno, &offset_agbno, flags); if (error) return error; } out_map: ASSERT(agbno >= chunk_agbno); cluster_agbno = chunk_agbno + ((offset_agbno / M_IGEO(mp)->blocks_per_cluster) * M_IGEO(mp)->blocks_per_cluster); offset = ((agbno - cluster_agbno) * mp->m_sb.sb_inopblock) + XFS_INO_TO_OFFSET(mp, ino); imap->im_blkno = xfs_agbno_to_daddr(pag, cluster_agbno); imap->im_len = XFS_FSB_TO_BB(mp, M_IGEO(mp)->blocks_per_cluster); imap->im_boffset = (unsigned short)(offset << mp->m_sb.sb_inodelog); /* * If the inode number maps to a block outside the bounds * of the file system then return NULL rather than calling * read_buf and panicing when we get an error from the * driver. */ if ((imap->im_blkno + imap->im_len) > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) { xfs_alert(mp, "%s: (im_blkno (0x%llx) + im_len (0x%llx)) > sb_dblocks (0x%llx)", __func__, (unsigned long long) imap->im_blkno, (unsigned long long) imap->im_len, XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)); return -EINVAL; } return 0; } /* * Log specified fields for the ag hdr (inode section). The growth of the agi * structure over time requires that we interpret the buffer as two logical * regions delineated by the end of the unlinked list. This is due to the size * of the hash table and its location in the middle of the agi. * * For example, a request to log a field before agi_unlinked and a field after * agi_unlinked could cause us to log the entire hash table and use an excessive * amount of log space. To avoid this behavior, log the region up through * agi_unlinked in one call and the region after agi_unlinked through the end of * the structure in another. */ void xfs_ialloc_log_agi( struct xfs_trans *tp, struct xfs_buf *bp, uint32_t fields) { int first; /* first byte number */ int last; /* last byte number */ static const short offsets[] = { /* field starting offsets */ /* keep in sync with bit definitions */ offsetof(xfs_agi_t, agi_magicnum), offsetof(xfs_agi_t, agi_versionnum), offsetof(xfs_agi_t, agi_seqno), offsetof(xfs_agi_t, agi_length), offsetof(xfs_agi_t, agi_count), offsetof(xfs_agi_t, agi_root), offsetof(xfs_agi_t, agi_level), offsetof(xfs_agi_t, agi_freecount), offsetof(xfs_agi_t, agi_newino), offsetof(xfs_agi_t, agi_dirino), offsetof(xfs_agi_t, agi_unlinked), offsetof(xfs_agi_t, agi_free_root), offsetof(xfs_agi_t, agi_free_level), offsetof(xfs_agi_t, agi_iblocks), sizeof(xfs_agi_t) }; #ifdef DEBUG struct xfs_agi *agi = bp->b_addr; ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC)); #endif /* * Compute byte offsets for the first and last fields in the first * region and log the agi buffer. This only logs up through * agi_unlinked. */ if (fields & XFS_AGI_ALL_BITS_R1) { xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS_R1, &first, &last); xfs_trans_log_buf(tp, bp, first, last); } /* * Mask off the bits in the first region and calculate the first and * last field offsets for any bits in the second region. */ fields &= ~XFS_AGI_ALL_BITS_R1; if (fields) { xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS_R2, &first, &last); xfs_trans_log_buf(tp, bp, first, last); } } static xfs_failaddr_t xfs_agi_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; struct xfs_agi *agi = bp->b_addr; xfs_failaddr_t fa; uint32_t agi_seqno = be32_to_cpu(agi->agi_seqno); uint32_t agi_length = be32_to_cpu(agi->agi_length); int i; if (xfs_has_crc(mp)) { if (!uuid_equal(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid)) return __this_address; if (!xfs_log_check_lsn(mp, be64_to_cpu(agi->agi_lsn))) return __this_address; } /* * Validate the magic number of the agi block. */ if (!xfs_verify_magic(bp, agi->agi_magicnum)) return __this_address; if (!XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum))) return __this_address; fa = xfs_validate_ag_length(bp, agi_seqno, agi_length); if (fa) return fa; if (be32_to_cpu(agi->agi_level) < 1 || be32_to_cpu(agi->agi_level) > M_IGEO(mp)->inobt_maxlevels) return __this_address; if (xfs_has_finobt(mp) && (be32_to_cpu(agi->agi_free_level) < 1 || be32_to_cpu(agi->agi_free_level) > M_IGEO(mp)->inobt_maxlevels)) return __this_address; for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) { if (agi->agi_unlinked[i] == cpu_to_be32(NULLAGINO)) continue; if (!xfs_verify_ino(mp, be32_to_cpu(agi->agi_unlinked[i]))) return __this_address; } return NULL; } static void xfs_agi_read_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; if (xfs_has_crc(mp) && !xfs_buf_verify_cksum(bp, XFS_AGI_CRC_OFF)) xfs_verifier_error(bp, -EFSBADCRC, __this_address); else { fa = xfs_agi_verify(bp); if (XFS_TEST_ERROR(fa, mp, XFS_ERRTAG_IALLOC_READ_AGI)) xfs_verifier_error(bp, -EFSCORRUPTED, fa); } } static void xfs_agi_write_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; struct xfs_agi *agi = bp->b_addr; xfs_failaddr_t fa; fa = xfs_agi_verify(bp); if (fa) { xfs_verifier_error(bp, -EFSCORRUPTED, fa); return; } if (!xfs_has_crc(mp)) return; if (bip) agi->agi_lsn = cpu_to_be64(bip->bli_item.li_lsn); xfs_buf_update_cksum(bp, XFS_AGI_CRC_OFF); } const struct xfs_buf_ops xfs_agi_buf_ops = { .name = "xfs_agi", .magic = { cpu_to_be32(XFS_AGI_MAGIC), cpu_to_be32(XFS_AGI_MAGIC) }, .verify_read = xfs_agi_read_verify, .verify_write = xfs_agi_write_verify, .verify_struct = xfs_agi_verify, }; /* * Read in the allocation group header (inode allocation section) */ int xfs_read_agi( struct xfs_perag *pag, struct xfs_trans *tp, xfs_buf_flags_t flags, struct xfs_buf **agibpp) { struct xfs_mount *mp = pag_mount(pag); int error; trace_xfs_read_agi(pag); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, XFS_AG_DADDR(mp, pag_agno(pag), XFS_AGI_DADDR(mp)), XFS_FSS_TO_BB(mp, 1), flags, agibpp, &xfs_agi_buf_ops); if (xfs_metadata_is_sick(error)) xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI); if (error) return error; if (tp) xfs_trans_buf_set_type(tp, *agibpp, XFS_BLFT_AGI_BUF); xfs_buf_set_ref(*agibpp, XFS_AGI_REF); return 0; } /* * Read in the agi and initialise the per-ag data. If the caller supplies a * @agibpp, return the locked AGI buffer to them, otherwise release it. */ int xfs_ialloc_read_agi( struct xfs_perag *pag, struct xfs_trans *tp, int flags, struct xfs_buf **agibpp) { struct xfs_buf *agibp; struct xfs_agi *agi; int error; trace_xfs_ialloc_read_agi(pag); error = xfs_read_agi(pag, tp, (flags & XFS_IALLOC_FLAG_TRYLOCK) ? XBF_TRYLOCK : 0, &agibp); if (error) return error; agi = agibp->b_addr; if (!xfs_perag_initialised_agi(pag)) { pag->pagi_freecount = be32_to_cpu(agi->agi_freecount); pag->pagi_count = be32_to_cpu(agi->agi_count); set_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate); } /* * It's possible for these to be out of sync if * we are in the middle of a forced shutdown. */ ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) || xfs_is_shutdown(pag_mount(pag))); if (agibpp) *agibpp = agibp; else xfs_trans_brelse(tp, agibp); return 0; } /* How many inodes are backed by inode clusters ondisk? */ STATIC int xfs_ialloc_count_ondisk( struct xfs_btree_cur *cur, xfs_agino_t low, xfs_agino_t high, unsigned int *allocated) { struct xfs_inobt_rec_incore irec; unsigned int ret = 0; int has_record; int error; error = xfs_inobt_lookup(cur, low, XFS_LOOKUP_LE, &has_record); if (error) return error; while (has_record) { unsigned int i, hole_idx; error = xfs_inobt_get_rec(cur, &irec, &has_record); if (error) return error; if (irec.ir_startino > high) break; for (i = 0; i < XFS_INODES_PER_CHUNK; i++) { if (irec.ir_startino + i < low) continue; if (irec.ir_startino + i > high) break; hole_idx = i / XFS_INODES_PER_HOLEMASK_BIT; if (!(irec.ir_holemask & (1U << hole_idx))) ret++; } error = xfs_btree_increment(cur, 0, &has_record); if (error) return error; } *allocated = ret; return 0; } /* Is there an inode record covering a given extent? */ int xfs_ialloc_has_inodes_at_extent( struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, enum xbtree_recpacking *outcome) { xfs_agino_t agino; xfs_agino_t last_agino; unsigned int allocated; int error; agino = XFS_AGB_TO_AGINO(cur->bc_mp, bno); last_agino = XFS_AGB_TO_AGINO(cur->bc_mp, bno + len) - 1; error = xfs_ialloc_count_ondisk(cur, agino, last_agino, &allocated); if (error) return error; if (allocated == 0) *outcome = XBTREE_RECPACKING_EMPTY; else if (allocated == last_agino - agino + 1) *outcome = XBTREE_RECPACKING_FULL; else *outcome = XBTREE_RECPACKING_SPARSE; return 0; } struct xfs_ialloc_count_inodes { xfs_agino_t count; xfs_agino_t freecount; }; /* Record inode counts across all inobt records. */ STATIC int xfs_ialloc_count_inodes_rec( struct xfs_btree_cur *cur, const union xfs_btree_rec *rec, void *priv) { struct xfs_inobt_rec_incore irec; struct xfs_ialloc_count_inodes *ci = priv; xfs_failaddr_t fa; xfs_inobt_btrec_to_irec(cur->bc_mp, rec, &irec); fa = xfs_inobt_check_irec(to_perag(cur->bc_group), &irec); if (fa) return xfs_inobt_complain_bad_rec(cur, fa, &irec); ci->count += irec.ir_count; ci->freecount += irec.ir_freecount; return 0; } /* Count allocated and free inodes under an inobt. */ int xfs_ialloc_count_inodes( struct xfs_btree_cur *cur, xfs_agino_t *count, xfs_agino_t *freecount) { struct xfs_ialloc_count_inodes ci = {0}; int error; ASSERT(xfs_btree_is_ino(cur->bc_ops)); error = xfs_btree_query_all(cur, xfs_ialloc_count_inodes_rec, &ci); if (error) return error; *count = ci.count; *freecount = ci.freecount; return 0; } /* * Initialize inode-related geometry information. * * Compute the inode btree min and max levels and set maxicount. * * Set the inode cluster size. This may still be overridden by the file * system block size if it is larger than the chosen cluster size. * * For v5 filesystems, scale the cluster size with the inode size to keep a * constant ratio of inode per cluster buffer, but only if mkfs has set the * inode alignment value appropriately for larger cluster sizes. * * Then compute the inode cluster alignment information. */ void xfs_ialloc_setup_geometry( struct xfs_mount *mp) { struct xfs_sb *sbp = &mp->m_sb; struct xfs_ino_geometry *igeo = M_IGEO(mp); uint64_t icount; uint inodes; igeo->new_diflags2 = 0; if (xfs_has_bigtime(mp)) igeo->new_diflags2 |= XFS_DIFLAG2_BIGTIME; if (xfs_has_large_extent_counts(mp)) igeo->new_diflags2 |= XFS_DIFLAG2_NREXT64; /* Compute inode btree geometry. */ igeo->agino_log = sbp->sb_inopblog + sbp->sb_agblklog; igeo->inobt_mxr[0] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, true); igeo->inobt_mxr[1] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, false); igeo->inobt_mnr[0] = igeo->inobt_mxr[0] / 2; igeo->inobt_mnr[1] = igeo->inobt_mxr[1] / 2; igeo->ialloc_inos = max_t(uint16_t, XFS_INODES_PER_CHUNK, sbp->sb_inopblock); igeo->ialloc_blks = igeo->ialloc_inos >> sbp->sb_inopblog; if (sbp->sb_spino_align) igeo->ialloc_min_blks = sbp->sb_spino_align; else igeo->ialloc_min_blks = igeo->ialloc_blks; /* Compute and fill in value of m_ino_geo.inobt_maxlevels. */ inodes = (1LL << XFS_INO_AGINO_BITS(mp)) >> XFS_INODES_PER_CHUNK_LOG; igeo->inobt_maxlevels = xfs_btree_compute_maxlevels(igeo->inobt_mnr, inodes); ASSERT(igeo->inobt_maxlevels <= xfs_iallocbt_maxlevels_ondisk()); /* * Set the maximum inode count for this filesystem, being careful not * to use obviously garbage sb_inopblog/sb_inopblock values. Regular * users should never get here due to failing sb verification, but * certain users (xfs_db) need to be usable even with corrupt metadata. */ if (sbp->sb_imax_pct && igeo->ialloc_blks) { /* * Make sure the maximum inode count is a multiple * of the units we allocate inodes in. */ icount = sbp->sb_dblocks * sbp->sb_imax_pct; do_div(icount, 100); do_div(icount, igeo->ialloc_blks); igeo->maxicount = XFS_FSB_TO_INO(mp, icount * igeo->ialloc_blks); } else { igeo->maxicount = 0; } /* * Compute the desired size of an inode cluster buffer size, which * starts at 8K and (on v5 filesystems) scales up with larger inode * sizes. * * Preserve the desired inode cluster size because the sparse inodes * feature uses that desired size (not the actual size) to compute the * sparse inode alignment. The mount code validates this value, so we * cannot change the behavior. */ igeo->inode_cluster_size_raw = XFS_INODE_BIG_CLUSTER_SIZE; if (xfs_has_v3inodes(mp)) { int new_size = igeo->inode_cluster_size_raw; new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE; if (mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, new_size)) igeo->inode_cluster_size_raw = new_size; } /* Calculate inode cluster ratios. */ if (igeo->inode_cluster_size_raw > mp->m_sb.sb_blocksize) igeo->blocks_per_cluster = XFS_B_TO_FSBT(mp, igeo->inode_cluster_size_raw); else igeo->blocks_per_cluster = 1; igeo->inode_cluster_size = XFS_FSB_TO_B(mp, igeo->blocks_per_cluster); igeo->inodes_per_cluster = XFS_FSB_TO_INO(mp, igeo->blocks_per_cluster); /* Calculate inode cluster alignment. */ if (xfs_has_align(mp) && mp->m_sb.sb_inoalignmt >= igeo->blocks_per_cluster) igeo->cluster_align = mp->m_sb.sb_inoalignmt; else igeo->cluster_align = 1; igeo->inoalign_mask = igeo->cluster_align - 1; igeo->cluster_align_inodes = XFS_FSB_TO_INO(mp, igeo->cluster_align); /* * If we are using stripe alignment, check whether * the stripe unit is a multiple of the inode alignment */ if (mp->m_dalign && igeo->inoalign_mask && !(mp->m_dalign & igeo->inoalign_mask)) igeo->ialloc_align = mp->m_dalign; else igeo->ialloc_align = 0; if (mp->m_sb.sb_blocksize > PAGE_SIZE) igeo->min_folio_order = mp->m_sb.sb_blocklog - PAGE_SHIFT; else igeo->min_folio_order = 0; } /* Compute the location of the root directory inode that is laid out by mkfs. */ xfs_ino_t xfs_ialloc_calc_rootino( struct xfs_mount *mp, int sunit) { struct xfs_ino_geometry *igeo = M_IGEO(mp); xfs_agblock_t first_bno; /* * Pre-calculate the geometry of AG 0. We know what it looks like * because libxfs knows how to create allocation groups now. * * first_bno is the first block in which mkfs could possibly have * allocated the root directory inode, once we factor in the metadata * that mkfs formats before it. Namely, the four AG headers... */ first_bno = howmany(4 * mp->m_sb.sb_sectsize, mp->m_sb.sb_blocksize); /* ...the two free space btree roots... */ first_bno += 2; /* ...the inode btree root... */ first_bno += 1; /* ...the initial AGFL... */ first_bno += xfs_alloc_min_freelist(mp, NULL); /* ...the free inode btree root... */ if (xfs_has_finobt(mp)) first_bno++; /* ...the reverse mapping btree root... */ if (xfs_has_rmapbt(mp)) first_bno++; /* ...the reference count btree... */ if (xfs_has_reflink(mp)) first_bno++; /* * ...and the log, if it is allocated in the first allocation group. * * This can happen with filesystems that only have a single * allocation group, or very odd geometries created by old mkfs * versions on very small filesystems. */ if (xfs_ag_contains_log(mp, 0)) first_bno += mp->m_sb.sb_logblocks; /* * Now round first_bno up to whatever allocation alignment is given * by the filesystem or was passed in. */ if (xfs_has_dalign(mp) && igeo->ialloc_align > 0) first_bno = roundup(first_bno, sunit); else if (xfs_has_align(mp) && mp->m_sb.sb_inoalignmt > 1) first_bno = roundup(first_bno, mp->m_sb.sb_inoalignmt); return XFS_AGINO_TO_INO(mp, 0, XFS_AGB_TO_AGINO(mp, first_bno)); } /* * Ensure there are not sparse inode clusters that cross the new EOAG. * * This is a no-op for non-spinode filesystems since clusters are always fully * allocated and checking the bnobt suffices. However, a spinode filesystem * could have a record where the upper inodes are free blocks. If those blocks * were removed from the filesystem, the inode record would extend beyond EOAG, * which will be flagged as corruption. */ int xfs_ialloc_check_shrink( struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf *agibp, xfs_agblock_t new_length) { struct xfs_inobt_rec_incore rec; struct xfs_btree_cur *cur; xfs_agino_t agino; int has; int error; if (!xfs_has_sparseinodes(pag_mount(pag))) return 0; cur = xfs_inobt_init_cursor(pag, tp, agibp); /* Look up the inobt record that would correspond to the new EOFS. */ agino = XFS_AGB_TO_AGINO(pag_mount(pag), new_length); error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &has); if (error || !has) goto out; error = xfs_inobt_get_rec(cur, &rec, &has); if (error) goto out; if (!has) { xfs_ag_mark_sick(pag, XFS_SICK_AG_INOBT); error = -EFSCORRUPTED; goto out; } /* If the record covers inodes that would be beyond EOFS, bail out. */ if (rec.ir_startino + XFS_INODES_PER_CHUNK > agino) { error = -ENOSPC; goto out; } out: xfs_btree_del_cursor(cur, error); return error; } |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 | // SPDX-License-Identifier: GPL-2.0 /* * Central processing for nfsd. * * Authors: Olaf Kirch (okir@monad.swb.de) * * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */ #include <linux/sched/signal.h> #include <linux/freezer.h> #include <linux/module.h> #include <linux/fs_struct.h> #include <linux/swap.h> #include <linux/siphash.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/svc_xprt.h> #include <linux/lockd/bind.h> #include <linux/nfsacl.h> #include <linux/nfslocalio.h> #include <linux/seq_file.h> #include <linux/inetdevice.h> #include <net/addrconf.h> #include <net/ipv6.h> #include <net/net_namespace.h> #include "nfsd.h" #include "cache.h" #include "vfs.h" #include "netns.h" #include "filecache.h" #include "trace.h" #define NFSDDBG_FACILITY NFSDDBG_SVC atomic_t nfsd_th_cnt = ATOMIC_INIT(0); static int nfsd(void *vrqstp); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static int nfsd_acl_rpcbind_set(struct net *, const struct svc_program *, u32, int, unsigned short, unsigned short); static __be32 nfsd_acl_init_request(struct svc_rqst *, const struct svc_program *, struct svc_process_info *); #endif static int nfsd_rpcbind_set(struct net *, const struct svc_program *, u32, int, unsigned short, unsigned short); static __be32 nfsd_init_request(struct svc_rqst *, const struct svc_program *, struct svc_process_info *); /* * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and some members * of the svc_serv struct such as ->sv_temp_socks and ->sv_permsocks. * * Finally, the nfsd_mutex also protects some of the global variables that are * accessed when nfsd starts and that are settable via the write_* routines in * nfsctl.c. In particular: * * user_recovery_dirname * user_lease_time * nfsd_versions */ DEFINE_MUTEX(nfsd_mutex); /* * nfsd_drc_lock protects nfsd_drc_max_pages and nfsd_drc_pages_used. * nfsd_drc_max_pages limits the total amount of memory available for * version 4.1 DRC caches. * nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage. */ DEFINE_SPINLOCK(nfsd_drc_lock); unsigned long nfsd_drc_max_mem; unsigned long nfsd_drc_mem_used; #if IS_ENABLED(CONFIG_NFS_LOCALIO) static const struct svc_version *localio_versions[] = { [1] = &localio_version1, }; #define NFSD_LOCALIO_NRVERS ARRAY_SIZE(localio_versions) #endif /* CONFIG_NFS_LOCALIO */ #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static const struct svc_version *nfsd_acl_version[] = { # if defined(CONFIG_NFSD_V2_ACL) [2] = &nfsd_acl_version2, # endif # if defined(CONFIG_NFSD_V3_ACL) [3] = &nfsd_acl_version3, # endif }; #define NFSD_ACL_MINVERS 2 #define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version) #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ static const struct svc_version *nfsd_version[NFSD_MAXVERS+1] = { #if defined(CONFIG_NFSD_V2) [2] = &nfsd_version2, #endif [3] = &nfsd_version3, #if defined(CONFIG_NFSD_V4) [4] = &nfsd_version4, #endif }; struct svc_program nfsd_programs[] = { { .pg_prog = NFS_PROGRAM, /* program number */ .pg_nvers = NFSD_MAXVERS+1, /* nr of entries in nfsd_version */ .pg_vers = nfsd_version, /* version table */ .pg_name = "nfsd", /* program name */ .pg_class = "nfsd", /* authentication class */ .pg_authenticate = svc_set_client, /* export authentication */ .pg_init_request = nfsd_init_request, .pg_rpcbind_set = nfsd_rpcbind_set, }, #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) { .pg_prog = NFS_ACL_PROGRAM, .pg_nvers = NFSD_ACL_NRVERS, .pg_vers = nfsd_acl_version, .pg_name = "nfsacl", .pg_class = "nfsd", .pg_authenticate = svc_set_client, .pg_init_request = nfsd_acl_init_request, .pg_rpcbind_set = nfsd_acl_rpcbind_set, }, #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ #if IS_ENABLED(CONFIG_NFS_LOCALIO) { .pg_prog = NFS_LOCALIO_PROGRAM, .pg_nvers = NFSD_LOCALIO_NRVERS, .pg_vers = localio_versions, .pg_name = "nfslocalio", .pg_class = "nfsd", .pg_authenticate = svc_set_client, .pg_init_request = svc_generic_init_request, .pg_rpcbind_set = svc_generic_rpcbind_set, } #endif /* CONFIG_NFS_LOCALIO */ }; bool nfsd_support_version(int vers) { if (vers >= NFSD_MINVERS && vers <= NFSD_MAXVERS) return nfsd_version[vers] != NULL; return false; } int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change) { if (vers < NFSD_MINVERS || vers > NFSD_MAXVERS) return 0; switch(change) { case NFSD_SET: nn->nfsd_versions[vers] = nfsd_support_version(vers); break; case NFSD_CLEAR: nn->nfsd_versions[vers] = false; break; case NFSD_TEST: return nn->nfsd_versions[vers]; case NFSD_AVAIL: return nfsd_support_version(vers); } return 0; } static void nfsd_adjust_nfsd_versions4(struct nfsd_net *nn) { unsigned i; for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++) { if (nn->nfsd4_minorversions[i]) return; } nfsd_vers(nn, 4, NFSD_CLEAR); } int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change) { if (minorversion > NFSD_SUPPORTED_MINOR_VERSION && change != NFSD_AVAIL) return -1; switch(change) { case NFSD_SET: nfsd_vers(nn, 4, NFSD_SET); nn->nfsd4_minorversions[minorversion] = nfsd_vers(nn, 4, NFSD_TEST); break; case NFSD_CLEAR: nn->nfsd4_minorversions[minorversion] = false; nfsd_adjust_nfsd_versions4(nn); break; case NFSD_TEST: return nn->nfsd4_minorversions[minorversion]; case NFSD_AVAIL: return minorversion <= NFSD_SUPPORTED_MINOR_VERSION && nfsd_vers(nn, 4, NFSD_AVAIL); } return 0; } bool nfsd_serv_try_get(struct net *net) __must_hold(rcu) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); return (nn && percpu_ref_tryget_live(&nn->nfsd_serv_ref)); } void nfsd_serv_put(struct net *net) __must_hold(rcu) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); percpu_ref_put(&nn->nfsd_serv_ref); } static void nfsd_serv_done(struct percpu_ref *ref) { struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref); complete(&nn->nfsd_serv_confirm_done); } static void nfsd_serv_free(struct percpu_ref *ref) { struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref); complete(&nn->nfsd_serv_free_done); } /* * Maximum number of nfsd processes */ #define NFSD_MAXSERVS 8192 int nfsd_nrthreads(struct net *net) { int rv = 0; struct nfsd_net *nn = net_generic(net, nfsd_net_id); mutex_lock(&nfsd_mutex); if (nn->nfsd_serv) rv = nn->nfsd_serv->sv_nrthreads; mutex_unlock(&nfsd_mutex); return rv; } static int nfsd_init_socks(struct net *net, const struct cred *cred) { int error; struct nfsd_net *nn = net_generic(net, nfsd_net_id); if (!list_empty(&nn->nfsd_serv->sv_permsocks)) return 0; error = svc_xprt_create(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT, SVC_SOCK_DEFAULTS, cred); if (error < 0) return error; error = svc_xprt_create(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT, SVC_SOCK_DEFAULTS, cred); if (error < 0) return error; return 0; } static int nfsd_users = 0; static int nfsd_startup_generic(void) { int ret; if (nfsd_users++) return 0; ret = nfsd_file_cache_init(); if (ret) goto dec_users; ret = nfs4_state_start(); if (ret) goto out_file_cache; return 0; out_file_cache: nfsd_file_cache_shutdown(); dec_users: nfsd_users--; return ret; } static void nfsd_shutdown_generic(void) { if (--nfsd_users) return; nfs4_state_shutdown(); nfsd_file_cache_shutdown(); } static bool nfsd_needs_lockd(struct nfsd_net *nn) { return nfsd_vers(nn, 2, NFSD_TEST) || nfsd_vers(nn, 3, NFSD_TEST); } /** * nfsd_copy_write_verifier - Atomically copy a write verifier * @verf: buffer in which to receive the verifier cookie * @nn: NFS net namespace * * This function provides a wait-free mechanism for copying the * namespace's write verifier without tearing it. */ void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn) { unsigned int seq; do { seq = read_seqbegin(&nn->writeverf_lock); memcpy(verf, nn->writeverf, sizeof(nn->writeverf)); } while (read_seqretry(&nn->writeverf_lock, seq)); } static void nfsd_reset_write_verifier_locked(struct nfsd_net *nn) { struct timespec64 now; u64 verf; /* * Because the time value is hashed, y2038 time_t overflow * is irrelevant in this usage. */ ktime_get_raw_ts64(&now); verf = siphash_2u64(now.tv_sec, now.tv_nsec, &nn->siphash_key); memcpy(nn->writeverf, &verf, sizeof(nn->writeverf)); } /** * nfsd_reset_write_verifier - Generate a new write verifier * @nn: NFS net namespace * * This function updates the ->writeverf field of @nn. This field * contains an opaque cookie that, according to Section 18.32.3 of * RFC 8881, "the client can use to determine whether a server has * changed instance state (e.g., server restart) between a call to * WRITE and a subsequent call to either WRITE or COMMIT. This * cookie MUST be unchanged during a single instance of the NFSv4.1 * server and MUST be unique between instances of the NFSv4.1 * server." */ void nfsd_reset_write_verifier(struct nfsd_net *nn) { write_seqlock(&nn->writeverf_lock); nfsd_reset_write_verifier_locked(nn); write_sequnlock(&nn->writeverf_lock); } /* * Crank up a set of per-namespace resources for a new NFSD instance, * including lockd, a duplicate reply cache, an open file cache * instance, and a cache of NFSv4 state objects. */ static int nfsd_startup_net(struct net *net, const struct cred *cred) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); int ret; if (nn->nfsd_net_up) return 0; ret = nfsd_startup_generic(); if (ret) return ret; ret = nfsd_init_socks(net, cred); if (ret) goto out_socks; if (nfsd_needs_lockd(nn) && !nn->lockd_up) { ret = lockd_up(net, cred); if (ret) goto out_socks; nn->lockd_up = true; } ret = nfsd_file_cache_start_net(net); if (ret) goto out_lockd; ret = nfsd_reply_cache_init(nn); if (ret) goto out_filecache; ret = nfs4_state_start_net(net); if (ret) goto out_reply_cache; #ifdef CONFIG_NFSD_V4_2_INTER_SSC nfsd4_ssc_init_umount_work(nn); #endif nn->nfsd_net_up = true; return 0; out_reply_cache: nfsd_reply_cache_shutdown(nn); out_filecache: nfsd_file_cache_shutdown_net(net); out_lockd: if (nn->lockd_up) { lockd_down(net); nn->lockd_up = false; } out_socks: nfsd_shutdown_generic(); return ret; } static void nfsd_shutdown_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); if (!nn->nfsd_net_up) return; nfsd_export_flush(net); nfs4_state_shutdown_net(net); nfsd_reply_cache_shutdown(nn); nfsd_file_cache_shutdown_net(net); if (nn->lockd_up) { lockd_down(net); nn->lockd_up = false; } percpu_ref_exit(&nn->nfsd_serv_ref); nn->nfsd_net_up = false; nfsd_shutdown_generic(); } static DEFINE_SPINLOCK(nfsd_notifier_lock); static int nfsd_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; struct net_device *dev = ifa->ifa_dev->dev; struct net *net = dev_net(dev); struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct sockaddr_in sin; if (event != NETDEV_DOWN || !nn->nfsd_serv) goto out; spin_lock(&nfsd_notifier_lock); if (nn->nfsd_serv) { dprintk("nfsd_inetaddr_event: removed %pI4\n", &ifa->ifa_local); sin.sin_family = AF_INET; sin.sin_addr.s_addr = ifa->ifa_local; svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin); } spin_unlock(&nfsd_notifier_lock); out: return NOTIFY_DONE; } static struct notifier_block nfsd_inetaddr_notifier = { .notifier_call = nfsd_inetaddr_event, }; #if IS_ENABLED(CONFIG_IPV6) static int nfsd_inet6addr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; struct net_device *dev = ifa->idev->dev; struct net *net = dev_net(dev); struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct sockaddr_in6 sin6; if (event != NETDEV_DOWN || !nn->nfsd_serv) goto out; spin_lock(&nfsd_notifier_lock); if (nn->nfsd_serv) { dprintk("nfsd_inet6addr_event: removed %pI6\n", &ifa->addr); sin6.sin6_family = AF_INET6; sin6.sin6_addr = ifa->addr; if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL) sin6.sin6_scope_id = ifa->idev->dev->ifindex; svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6); } spin_unlock(&nfsd_notifier_lock); out: return NOTIFY_DONE; } static struct notifier_block nfsd_inet6addr_notifier = { .notifier_call = nfsd_inet6addr_event, }; #endif /* Only used under nfsd_mutex, so this atomic may be overkill: */ static atomic_t nfsd_notifier_refcount = ATOMIC_INIT(0); /** * nfsd_destroy_serv - tear down NFSD's svc_serv for a namespace * @net: network namespace the NFS service is associated with */ void nfsd_destroy_serv(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv = nn->nfsd_serv; lockdep_assert_held(&nfsd_mutex); percpu_ref_kill_and_confirm(&nn->nfsd_serv_ref, nfsd_serv_done); wait_for_completion(&nn->nfsd_serv_confirm_done); wait_for_completion(&nn->nfsd_serv_free_done); /* percpu_ref_exit is called in nfsd_shutdown_net */ spin_lock(&nfsd_notifier_lock); nn->nfsd_serv = NULL; spin_unlock(&nfsd_notifier_lock); /* check if the notifier still has clients */ if (atomic_dec_return(&nfsd_notifier_refcount) == 0) { unregister_inetaddr_notifier(&nfsd_inetaddr_notifier); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&nfsd_inet6addr_notifier); #endif } svc_xprt_destroy_all(serv, net); /* * write_ports can create the server without actually starting * any threads--if we get shut down before any threads are * started, then nfsd_destroy_serv will be run before any of this * other initialization has been done except the rpcb information. */ svc_rpcb_cleanup(serv, net); nfsd_shutdown_net(net); svc_destroy(&serv); } void nfsd_reset_versions(struct nfsd_net *nn) { int i; for (i = 0; i <= NFSD_MAXVERS; i++) if (nfsd_vers(nn, i, NFSD_TEST)) return; for (i = 0; i <= NFSD_MAXVERS; i++) if (i != 4) nfsd_vers(nn, i, NFSD_SET); else { int minor = 0; while (nfsd_minorversion(nn, minor, NFSD_SET) >= 0) minor++; } } /* * Each session guarantees a negotiated per slot memory cache for replies * which in turn consumes memory beyond the v2/v3/v4.0 server. A dedicated * NFSv4.1 server might want to use more memory for a DRC than a machine * with mutiple services. * * Impose a hard limit on the number of pages for the DRC which varies * according to the machines free pages. This is of course only a default. * * For now this is a #defined shift which could be under admin control * in the future. */ static void set_max_drc(void) { #define NFSD_DRC_SIZE_SHIFT 7 nfsd_drc_max_mem = (nr_free_buffer_pages() >> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE; nfsd_drc_mem_used = 0; dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem); } static int nfsd_get_default_max_blksize(void) { struct sysinfo i; unsigned long long target; unsigned long ret; si_meminfo(&i); target = (i.totalram - i.totalhigh) << PAGE_SHIFT; /* * Aim for 1/4096 of memory per thread This gives 1MB on 4Gig * machines, but only uses 32K on 128M machines. Bottom out at * 8K on 32M and smaller. Of course, this is only a default. */ target >>= 12; ret = NFSSVC_MAXBLKSIZE; while (ret > target && ret >= 8*1024*2) ret /= 2; return ret; } void nfsd_shutdown_threads(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv; mutex_lock(&nfsd_mutex); serv = nn->nfsd_serv; if (serv == NULL) { mutex_unlock(&nfsd_mutex); return; } /* Kill outstanding nfsd threads */ svc_set_num_threads(serv, NULL, 0); nfsd_destroy_serv(net); mutex_unlock(&nfsd_mutex); } struct svc_rqst *nfsd_current_rqst(void) { if (kthread_func(current) == nfsd) return kthread_data(current); return NULL; } int nfsd_create_serv(struct net *net) { int error; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv; WARN_ON(!mutex_is_locked(&nfsd_mutex)); if (nn->nfsd_serv) return 0; error = percpu_ref_init(&nn->nfsd_serv_ref, nfsd_serv_free, 0, GFP_KERNEL); if (error) return error; init_completion(&nn->nfsd_serv_free_done); init_completion(&nn->nfsd_serv_confirm_done); if (nfsd_max_blksize == 0) nfsd_max_blksize = nfsd_get_default_max_blksize(); nfsd_reset_versions(nn); serv = svc_create_pooled(nfsd_programs, ARRAY_SIZE(nfsd_programs), &nn->nfsd_svcstats, nfsd_max_blksize, nfsd); if (serv == NULL) return -ENOMEM; serv->sv_maxconn = nn->max_connections; error = svc_bind(serv, net); if (error < 0) { svc_destroy(&serv); return error; } spin_lock(&nfsd_notifier_lock); nn->nfsd_serv = serv; spin_unlock(&nfsd_notifier_lock); set_max_drc(); /* check if the notifier is already set */ if (atomic_inc_return(&nfsd_notifier_refcount) == 1) { register_inetaddr_notifier(&nfsd_inetaddr_notifier); #if IS_ENABLED(CONFIG_IPV6) register_inet6addr_notifier(&nfsd_inet6addr_notifier); #endif } nfsd_reset_write_verifier(nn); return 0; } int nfsd_nrpools(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); if (nn->nfsd_serv == NULL) return 0; else return nn->nfsd_serv->sv_nrpools; } int nfsd_get_nrthreads(int n, int *nthreads, struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv = nn->nfsd_serv; int i; if (serv) for (i = 0; i < serv->sv_nrpools && i < n; i++) nthreads[i] = serv->sv_pools[i].sp_nrthreads; return 0; } /** * nfsd_set_nrthreads - set the number of running threads in the net's service * @n: number of array members in @nthreads * @nthreads: array of thread counts for each pool * @net: network namespace to operate within * * This function alters the number of running threads for the given network * namespace in each pool. If passed an array longer then the number of pools * the extra pool settings are ignored. If passed an array shorter than the * number of pools, the missing values are interpreted as 0's. * * Returns 0 on success or a negative errno on error. */ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) { int i = 0; int tot = 0; int err = 0; struct nfsd_net *nn = net_generic(net, nfsd_net_id); lockdep_assert_held(&nfsd_mutex); if (nn->nfsd_serv == NULL || n <= 0) return 0; /* * Special case: When n == 1, pass in NULL for the pool, so that the * change is distributed equally among them. */ if (n == 1) return svc_set_num_threads(nn->nfsd_serv, NULL, nthreads[0]); if (n > nn->nfsd_serv->sv_nrpools) n = nn->nfsd_serv->sv_nrpools; /* enforce a global maximum number of threads */ tot = 0; for (i = 0; i < n; i++) { nthreads[i] = min(nthreads[i], NFSD_MAXSERVS); tot += nthreads[i]; } if (tot > NFSD_MAXSERVS) { /* total too large: scale down requested numbers */ for (i = 0; i < n && tot > 0; i++) { int new = nthreads[i] * NFSD_MAXSERVS / tot; tot -= (nthreads[i] - new); nthreads[i] = new; } for (i = 0; i < n && tot > 0; i++) { nthreads[i]--; tot--; } } /* apply the new numbers */ for (i = 0; i < n; i++) { err = svc_set_num_threads(nn->nfsd_serv, &nn->nfsd_serv->sv_pools[i], nthreads[i]); if (err) goto out; } /* Anything undefined in array is considered to be 0 */ for (i = n; i < nn->nfsd_serv->sv_nrpools; ++i) { err = svc_set_num_threads(nn->nfsd_serv, &nn->nfsd_serv->sv_pools[i], 0); if (err) goto out; } out: return err; } /** * nfsd_svc: start up or shut down the nfsd server * @n: number of array members in @nthreads * @nthreads: array of thread counts for each pool * @net: network namespace to operate within * @cred: credentials to use for xprt creation * @scope: server scope value (defaults to nodename) * * Adjust the number of threads in each pool and return the new * total number of threads in the service. */ int nfsd_svc(int n, int *nthreads, struct net *net, const struct cred *cred, const char *scope) { int error; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv; lockdep_assert_held(&nfsd_mutex); dprintk("nfsd: creating service\n"); strscpy(nn->nfsd_name, scope ? scope : utsname()->nodename, sizeof(nn->nfsd_name)); error = nfsd_create_serv(net); if (error) goto out; serv = nn->nfsd_serv; error = nfsd_startup_net(net, cred); if (error) goto out_put; error = nfsd_set_nrthreads(n, nthreads, net); if (error) goto out_put; error = serv->sv_nrthreads; out_put: if (serv->sv_nrthreads == 0) nfsd_destroy_serv(net); out: return error; } #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static bool nfsd_support_acl_version(int vers) { if (vers >= NFSD_ACL_MINVERS && vers < NFSD_ACL_NRVERS) return nfsd_acl_version[vers] != NULL; return false; } static int nfsd_acl_rpcbind_set(struct net *net, const struct svc_program *progp, u32 version, int family, unsigned short proto, unsigned short port) { if (!nfsd_support_acl_version(version) || !nfsd_vers(net_generic(net, nfsd_net_id), version, NFSD_TEST)) return 0; return svc_generic_rpcbind_set(net, progp, version, family, proto, port); } static __be32 nfsd_acl_init_request(struct svc_rqst *rqstp, const struct svc_program *progp, struct svc_process_info *ret) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); int i; if (likely(nfsd_support_acl_version(rqstp->rq_vers) && nfsd_vers(nn, rqstp->rq_vers, NFSD_TEST))) return svc_generic_init_request(rqstp, progp, ret); ret->mismatch.lovers = NFSD_ACL_NRVERS; for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++) { if (nfsd_support_acl_version(rqstp->rq_vers) && nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.lovers = i; break; } } if (ret->mismatch.lovers == NFSD_ACL_NRVERS) return rpc_prog_unavail; ret->mismatch.hivers = NFSD_ACL_MINVERS; for (i = NFSD_ACL_NRVERS - 1; i >= NFSD_ACL_MINVERS; i--) { if (nfsd_support_acl_version(rqstp->rq_vers) && nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.hivers = i; break; } } return rpc_prog_mismatch; } #endif static int nfsd_rpcbind_set(struct net *net, const struct svc_program *progp, u32 version, int family, unsigned short proto, unsigned short port) { if (!nfsd_vers(net_generic(net, nfsd_net_id), version, NFSD_TEST)) return 0; return svc_generic_rpcbind_set(net, progp, version, family, proto, port); } static __be32 nfsd_init_request(struct svc_rqst *rqstp, const struct svc_program *progp, struct svc_process_info *ret) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); int i; if (likely(nfsd_vers(nn, rqstp->rq_vers, NFSD_TEST))) return svc_generic_init_request(rqstp, progp, ret); ret->mismatch.lovers = NFSD_MAXVERS + 1; for (i = NFSD_MINVERS; i <= NFSD_MAXVERS; i++) { if (nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.lovers = i; break; } } if (ret->mismatch.lovers > NFSD_MAXVERS) return rpc_prog_unavail; ret->mismatch.hivers = NFSD_MINVERS; for (i = NFSD_MAXVERS; i >= NFSD_MINVERS; i--) { if (nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.hivers = i; break; } } return rpc_prog_mismatch; } /* * This is the NFS server kernel thread */ static int nfsd(void *vrqstp) { struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp; struct svc_xprt *perm_sock = list_entry(rqstp->rq_server->sv_permsocks.next, typeof(struct svc_xprt), xpt_list); struct net *net = perm_sock->xpt_net; struct nfsd_net *nn = net_generic(net, nfsd_net_id); /* At this point, the thread shares current->fs * with the init process. We need to create files with the * umask as defined by the client instead of init's umask. */ svc_thread_init_status(rqstp, unshare_fs_struct()); current->fs->umask = 0; atomic_inc(&nfsd_th_cnt); set_freezable(); /* * The main request loop */ while (!svc_thread_should_stop(rqstp)) { /* Update sv_maxconn if it has changed */ rqstp->rq_server->sv_maxconn = nn->max_connections; svc_recv(rqstp); nfsd_file_net_dispose(nn); } atomic_dec(&nfsd_th_cnt); /* Release the thread */ svc_exit_thread(rqstp); return 0; } /** * nfsd_dispatch - Process an NFS or NFSACL or LOCALIO Request * @rqstp: incoming request * * This RPC dispatcher integrates the NFS server's duplicate reply cache. * * Return values: * %0: Processing complete; do not send a Reply * %1: Processing complete; send Reply in rqstp->rq_res */ int nfsd_dispatch(struct svc_rqst *rqstp) { const struct svc_procedure *proc = rqstp->rq_procinfo; __be32 *statp = rqstp->rq_accept_statp; struct nfsd_cacherep *rp; unsigned int start, len; __be32 *nfs_reply; /* * Give the xdr decoder a chance to change this if it wants * (necessary in the NFSv4.0 compound case) */ rqstp->rq_cachetype = proc->pc_cachetype; /* * ->pc_decode advances the argument stream past the NFS * Call header, so grab the header's starting location and * size now for the call to nfsd_cache_lookup(). */ start = xdr_stream_pos(&rqstp->rq_arg_stream); len = xdr_stream_remaining(&rqstp->rq_arg_stream); if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; /* * Release rq_status_counter setting it to an odd value after the rpc * request has been properly parsed. rq_status_counter is used to * notify the consumers if the rqstp fields are stable * (rq_status_counter is odd) or not meaningful (rq_status_counter * is even). */ smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter | 1); rp = NULL; switch (nfsd_cache_lookup(rqstp, start, len, &rp)) { case RC_DOIT: break; case RC_REPLY: goto out_cached_reply; case RC_DROPIT: goto out_dropit; } nfs_reply = xdr_inline_decode(&rqstp->rq_res_stream, 0); *statp = proc->pc_func(rqstp); if (test_bit(RQ_DROPME, &rqstp->rq_flags)) goto out_update_drop; if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; /* * Release rq_status_counter setting it to an even value after the rpc * request has been properly processed. */ smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter + 1); nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, nfs_reply); out_cached_reply: return 1; out_decode_err: trace_nfsd_garbage_args_err(rqstp); *statp = rpc_garbage_args; return 1; out_update_drop: nfsd_cache_update(rqstp, rp, RC_NOCACHE, NULL); out_dropit: return 0; out_encode_err: trace_nfsd_cant_encode_err(rqstp); nfsd_cache_update(rqstp, rp, RC_NOCACHE, NULL); *statp = rpc_system_err; return 1; } /** * nfssvc_decode_voidarg - Decode void arguments * @rqstp: Server RPC transaction context * @xdr: XDR stream positioned at arguments to decode * * Return values: * %false: Arguments were not valid * %true: Decoding was successful */ bool nfssvc_decode_voidarg(struct svc_rqst *rqstp, struct xdr_stream *xdr) { return true; } /** * nfssvc_encode_voidres - Encode void results * @rqstp: Server RPC transaction context * @xdr: XDR stream into which to encode results * * Return values: * %false: Local error while encoding * %true: Encoding was successful */ bool nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { return true; } |
| 185 4 184 184 10 181 13 171 181 187 187 180 5 54 61 18 24 1 2 55 27 5 60 18 176 169 3 4 48 6 17 39 52 5 8 8 49 48 1 48 48 41 7 7 4 3 5 44 4 44 3 42 47 5 5 4 1 1 1 1 5 5 5 5 2 2 2 2 1 1 2 5 2 2 2 2 2 2 2 1 1 1 1 2 5 5 5 5 5 5 1 4 5 1 4 5 8 8 8 8 8 1 7 8 7 1 1 7 8 51 1 51 38 6 32 32 38 38 34 6 6 2 36 9 4 23 27 17 18 18 11 2 2 1 4 1 6 18 17 3 16 2 2 1 1 1 2 2 2 2 2 2 2 36 31 5 13 13 13 11 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2005 */ /* * jfs_xtree.c: extent allocation descriptor B+-tree manager */ #include <linux/fs.h> #include <linux/module.h> #include <linux/quotaops.h> #include <linux/seq_file.h> #include "jfs_incore.h" #include "jfs_filsys.h" #include "jfs_metapage.h" #include "jfs_dmap.h" #include "jfs_dinode.h" #include "jfs_superblock.h" #include "jfs_debug.h" /* * xtree local flag */ #define XT_INSERT 0x00000001 /* * xtree key/entry comparison: extent offset * * return: * -1: k < start of extent * 0: start_of_extent <= k <= end_of_extent * 1: k > end_of_extent */ #define XT_CMP(CMP, K, X, OFFSET64)\ {\ OFFSET64 = offsetXAD(X);\ (CMP) = ((K) >= OFFSET64 + lengthXAD(X)) ? 1 :\ ((K) < OFFSET64) ? -1 : 0;\ } /* write a xad entry */ #define XT_PUTENTRY(XAD, FLAG, OFF, LEN, ADDR)\ {\ (XAD)->flag = (FLAG);\ XADoffset((XAD), (OFF));\ XADlength((XAD), (LEN));\ XADaddress((XAD), (ADDR));\ } #define XT_PAGE(IP, MP) BT_PAGE(IP, MP, xtpage_t, i_xtroot) /* get page buffer for specified block address */ /* ToDo: Replace this ugly macro with a function */ #define XT_GETPAGE(IP, BN, MP, SIZE, P, RC) \ do { \ BT_GETPAGE(IP, BN, MP, xtpage_t, SIZE, P, RC, i_xtroot); \ if (!(RC)) { \ if ((le16_to_cpu((P)->header.nextindex) < XTENTRYSTART) || \ (le16_to_cpu((P)->header.nextindex) > \ le16_to_cpu((P)->header.maxentry)) || \ (le16_to_cpu((P)->header.maxentry) > \ (((BN) == 0) ? XTROOTMAXSLOT : PSIZE >> L2XTSLOTSIZE))) { \ jfs_error((IP)->i_sb, \ "XT_GETPAGE: xtree page corrupt\n"); \ BT_PUTPAGE(MP); \ MP = NULL; \ RC = -EIO; \ } \ } \ } while (0) /* for consistency */ #define XT_PUTPAGE(MP) BT_PUTPAGE(MP) #define XT_GETSEARCH(IP, LEAF, BN, MP, P, INDEX) \ BT_GETSEARCH(IP, LEAF, BN, MP, xtpage_t, P, INDEX, i_xtroot) /* xtree entry parameter descriptor */ struct xtsplit { struct metapage *mp; s16 index; u8 flag; s64 off; s64 addr; int len; struct pxdlist *pxdlist; }; /* * statistics */ #ifdef CONFIG_JFS_STATISTICS static struct { uint search; uint fastSearch; uint split; } xtStat; #endif /* * forward references */ static int xtSearch(struct inode *ip, s64 xoff, s64 *next, int *cmpp, struct btstack * btstack, int flag); static int xtSplitUp(tid_t tid, struct inode *ip, struct xtsplit * split, struct btstack * btstack); static int xtSplitPage(tid_t tid, struct inode *ip, struct xtsplit * split, struct metapage ** rmpp, s64 * rbnp); static int xtSplitRoot(tid_t tid, struct inode *ip, struct xtsplit * split, struct metapage ** rmpp); /* * xtLookup() * * function: map a single page into a physical extent; */ int xtLookup(struct inode *ip, s64 lstart, s64 llen, int *pflag, s64 * paddr, s32 * plen, int no_check) { int rc = 0; struct btstack btstack; int cmp; s64 bn; struct metapage *mp; xtpage_t *p; int index; xad_t *xad; s64 next, size, xoff, xend; int xlen; s64 xaddr; *paddr = 0; *plen = llen; if (!no_check) { /* is lookup offset beyond eof ? */ size = ((u64) ip->i_size + (JFS_SBI(ip->i_sb)->bsize - 1)) >> JFS_SBI(ip->i_sb)->l2bsize; if (lstart >= size) return 0; } /* * search for the xad entry covering the logical extent */ //search: if ((rc = xtSearch(ip, lstart, &next, &cmp, &btstack, 0))) { jfs_err("xtLookup: xtSearch returned %d", rc); return rc; } /* * compute the physical extent covering logical extent * * N.B. search may have failed (e.g., hole in sparse file), * and returned the index of the next entry. */ /* retrieve search result */ XT_GETSEARCH(ip, btstack.top, bn, mp, p, index); /* is xad found covering start of logical extent ? * lstart is a page start address, * i.e., lstart cannot start in a hole; */ if (cmp) { if (next) *plen = min(next - lstart, llen); goto out; } /* * lxd covered by xad */ xad = &p->xad[index]; xoff = offsetXAD(xad); xlen = lengthXAD(xad); xend = xoff + xlen; xaddr = addressXAD(xad); /* initialize new pxd */ *pflag = xad->flag; *paddr = xaddr + (lstart - xoff); /* a page must be fully covered by an xad */ *plen = min(xend - lstart, llen); out: XT_PUTPAGE(mp); return rc; } /* * xtSearch() * * function: search for the xad entry covering specified offset. * * parameters: * ip - file object; * xoff - extent offset; * nextp - address of next extent (if any) for search miss * cmpp - comparison result: * btstack - traverse stack; * flag - search process flag (XT_INSERT); * * returns: * btstack contains (bn, index) of search path traversed to the entry. * *cmpp is set to result of comparison with the entry returned. * the page containing the entry is pinned at exit. */ static int xtSearch(struct inode *ip, s64 xoff, s64 *nextp, int *cmpp, struct btstack * btstack, int flag) { struct jfs_inode_info *jfs_ip = JFS_IP(ip); int rc = 0; int cmp = 1; /* init for empty page */ s64 bn; /* block number */ struct metapage *mp; /* page buffer */ xtpage_t *p; /* page */ xad_t *xad; int base, index, lim, btindex; struct btframe *btsp; int nsplit = 0; /* number of pages to split */ s64 t64; s64 next = 0; INCREMENT(xtStat.search); BT_CLR(btstack); btstack->nsplit = 0; /* * search down tree from root: * * between two consecutive entries of <Ki, Pi> and <Kj, Pj> of * internal page, child page Pi contains entry with k, Ki <= K < Kj. * * if entry with search key K is not found * internal page search find the entry with largest key Ki * less than K which point to the child page to search; * leaf page search find the entry with smallest key Kj * greater than K so that the returned index is the position of * the entry to be shifted right for insertion of new entry. * for empty tree, search key is greater than any key of the tree. * * by convention, root bn = 0. */ for (bn = 0;;) { /* get/pin the page to search */ XT_GETPAGE(ip, bn, mp, PSIZE, p, rc); if (rc) return rc; /* try sequential access heuristics with the previous * access entry in target leaf page: * once search narrowed down into the target leaf, * key must either match an entry in the leaf or * key entry does not exist in the tree; */ //fastSearch: if ((jfs_ip->btorder & BT_SEQUENTIAL) && (p->header.flag & BT_LEAF) && (index = jfs_ip->btindex) < le16_to_cpu(p->header.nextindex)) { xad = &p->xad[index]; t64 = offsetXAD(xad); if (xoff < t64 + lengthXAD(xad)) { if (xoff >= t64) { *cmpp = 0; goto out; } /* stop sequential access heuristics */ goto binarySearch; } else { /* (t64 + lengthXAD(xad)) <= xoff */ /* try next sequential entry */ index++; if (index < le16_to_cpu(p->header.nextindex)) { xad++; t64 = offsetXAD(xad); if (xoff < t64 + lengthXAD(xad)) { if (xoff >= t64) { *cmpp = 0; goto out; } /* miss: key falls between * previous and this entry */ *cmpp = 1; next = t64; goto out; } /* (xoff >= t64 + lengthXAD(xad)); * matching entry may be further out: * stop heuristic search */ /* stop sequential access heuristics */ goto binarySearch; } /* (index == p->header.nextindex); * miss: key entry does not exist in * the target leaf/tree */ *cmpp = 1; goto out; } /* * if hit, return index of the entry found, and * if miss, where new entry with search key is * to be inserted; */ out: /* compute number of pages to split */ if (flag & XT_INSERT) { if (p->header.nextindex == /* little-endian */ p->header.maxentry) nsplit++; else nsplit = 0; btstack->nsplit = nsplit; } /* save search result */ btsp = btstack->top; btsp->bn = bn; btsp->index = index; btsp->mp = mp; /* update sequential access heuristics */ jfs_ip->btindex = index; if (nextp) *nextp = next; INCREMENT(xtStat.fastSearch); return 0; } /* well, ... full search now */ binarySearch: lim = le16_to_cpu(p->header.nextindex) - XTENTRYSTART; /* * binary search with search key K on the current page */ for (base = XTENTRYSTART; lim; lim >>= 1) { index = base + (lim >> 1); XT_CMP(cmp, xoff, &p->xad[index], t64); if (cmp == 0) { /* * search hit */ /* search hit - leaf page: * return the entry found */ if (p->header.flag & BT_LEAF) { *cmpp = cmp; /* compute number of pages to split */ if (flag & XT_INSERT) { if (p->header.nextindex == p->header.maxentry) nsplit++; else nsplit = 0; btstack->nsplit = nsplit; } /* save search result */ btsp = btstack->top; btsp->bn = bn; btsp->index = index; btsp->mp = mp; /* init sequential access heuristics */ btindex = jfs_ip->btindex; if (index == btindex || index == btindex + 1) jfs_ip->btorder = BT_SEQUENTIAL; else jfs_ip->btorder = BT_RANDOM; jfs_ip->btindex = index; return 0; } /* search hit - internal page: * descend/search its child page */ if (index < le16_to_cpu(p->header.nextindex)-1) next = offsetXAD(&p->xad[index + 1]); goto next; } if (cmp > 0) { base = index + 1; --lim; } } /* * search miss * * base is the smallest index with key (Kj) greater than * search key (K) and may be zero or maxentry index. */ if (base < le16_to_cpu(p->header.nextindex)) next = offsetXAD(&p->xad[base]); /* * search miss - leaf page: * * return location of entry (base) where new entry with * search key K is to be inserted. */ if (p->header.flag & BT_LEAF) { *cmpp = cmp; /* compute number of pages to split */ if (flag & XT_INSERT) { if (p->header.nextindex == p->header.maxentry) nsplit++; else nsplit = 0; btstack->nsplit = nsplit; } /* save search result */ btsp = btstack->top; btsp->bn = bn; btsp->index = base; btsp->mp = mp; /* init sequential access heuristics */ btindex = jfs_ip->btindex; if (base == btindex || base == btindex + 1) jfs_ip->btorder = BT_SEQUENTIAL; else jfs_ip->btorder = BT_RANDOM; jfs_ip->btindex = base; if (nextp) *nextp = next; return 0; } /* * search miss - non-leaf page: * * if base is non-zero, decrement base by one to get the parent * entry of the child page to search. */ index = base ? base - 1 : base; /* * go down to child page */ next: /* update number of pages to split */ if (p->header.nextindex == p->header.maxentry) nsplit++; else nsplit = 0; /* push (bn, index) of the parent page/entry */ if (BT_STACK_FULL(btstack)) { jfs_error(ip->i_sb, "stack overrun!\n"); XT_PUTPAGE(mp); return -EIO; } BT_PUSH(btstack, bn, index); /* get the child page block number */ bn = addressXAD(&p->xad[index]); /* unpin the parent page */ XT_PUTPAGE(mp); } } /* * xtInsert() * * function: * * parameter: * tid - transaction id; * ip - file object; * xflag - extent flag (XAD_NOTRECORDED): * xoff - extent offset; * xlen - extent length; * xaddrp - extent address pointer (in/out): * if (*xaddrp) * caller allocated data extent at *xaddrp; * else * allocate data extent and return its xaddr; * flag - * * return: */ int xtInsert(tid_t tid, /* transaction id */ struct inode *ip, int xflag, s64 xoff, s32 xlen, s64 * xaddrp, int flag) { int rc = 0; s64 xaddr, hint; struct metapage *mp; /* meta-page buffer */ xtpage_t *p; /* base B+-tree index page */ s64 bn; int index, nextindex; struct btstack btstack; /* traverse stack */ struct xtsplit split; /* split information */ xad_t *xad; int cmp; s64 next; struct tlock *tlck; struct xtlock *xtlck; jfs_info("xtInsert: nxoff:0x%lx nxlen:0x%x", (ulong) xoff, xlen); /* * search for the entry location at which to insert: * * xtFastSearch() and xtSearch() both returns (leaf page * pinned, index at which to insert). * n.b. xtSearch() may return index of maxentry of * the full page. */ if ((rc = xtSearch(ip, xoff, &next, &cmp, &btstack, XT_INSERT))) return rc; /* retrieve search result */ XT_GETSEARCH(ip, btstack.top, bn, mp, p, index); /* This test must follow XT_GETSEARCH since mp must be valid if * we branch to out: */ if ((cmp == 0) || (next && (xlen > next - xoff))) { rc = -EEXIST; goto out; } /* * allocate data extent requested * * allocation hint: last xad */ if ((xaddr = *xaddrp) == 0) { if (index > XTENTRYSTART) { xad = &p->xad[index - 1]; hint = addressXAD(xad) + lengthXAD(xad) - 1; } else hint = 0; if ((rc = dquot_alloc_block(ip, xlen))) goto out; if ((rc = dbAlloc(ip, hint, (s64) xlen, &xaddr))) { dquot_free_block(ip, xlen); goto out; } } /* * insert entry for new extent */ xflag |= XAD_NEW; /* * if the leaf page is full, split the page and * propagate up the router entry for the new page from split * * The xtSplitUp() will insert the entry and unpin the leaf page. */ nextindex = le16_to_cpu(p->header.nextindex); if (nextindex == le16_to_cpu(p->header.maxentry)) { split.mp = mp; split.index = index; split.flag = xflag; split.off = xoff; split.len = xlen; split.addr = xaddr; split.pxdlist = NULL; if ((rc = xtSplitUp(tid, ip, &split, &btstack))) { /* undo data extent allocation */ if (*xaddrp == 0) { dbFree(ip, xaddr, (s64) xlen); dquot_free_block(ip, xlen); } return rc; } *xaddrp = xaddr; return 0; } /* * insert the new entry into the leaf page */ /* * acquire a transaction lock on the leaf page; * * action: xad insertion/extension; */ BT_MARK_DIRTY(mp, ip); /* if insert into middle, shift right remaining entries. */ if (index < nextindex) memmove(&p->xad[index + 1], &p->xad[index], (nextindex - index) * sizeof(xad_t)); /* insert the new entry: mark the entry NEW */ xad = &p->xad[index]; XT_PUTENTRY(xad, xflag, xoff, xlen, xaddr); /* advance next available entry index */ le16_add_cpu(&p->header.nextindex, 1); /* Don't log it if there are no links to the file */ if (!test_cflag(COMMIT_Nolink, ip)) { tlck = txLock(tid, ip, mp, tlckXTREE | tlckGROW); xtlck = (struct xtlock *) & tlck->lock; xtlck->lwm.offset = (xtlck->lwm.offset) ? min(index, (int)xtlck->lwm.offset) : index; xtlck->lwm.length = le16_to_cpu(p->header.nextindex) - xtlck->lwm.offset; } *xaddrp = xaddr; out: /* unpin the leaf page */ XT_PUTPAGE(mp); return rc; } /* * xtSplitUp() * * function: * split full pages as propagating insertion up the tree * * parameter: * tid - transaction id; * ip - file object; * split - entry parameter descriptor; * btstack - traverse stack from xtSearch() * * return: */ static int xtSplitUp(tid_t tid, struct inode *ip, struct xtsplit * split, struct btstack * btstack) { int rc = 0; struct metapage *smp; xtpage_t *sp; /* split page */ struct metapage *rmp; s64 rbn; /* new right page block number */ struct metapage *rcmp; xtpage_t *rcp; /* right child page */ s64 rcbn; /* right child page block number */ int skip; /* index of entry of insertion */ int nextindex; /* next available entry index of p */ struct btframe *parent; /* parent page entry on traverse stack */ xad_t *xad; s64 xaddr; int xlen; int nsplit; /* number of pages split */ struct pxdlist pxdlist; pxd_t *pxd; struct tlock *tlck; struct xtlock *xtlck; smp = split->mp; sp = XT_PAGE(ip, smp); /* is inode xtree root extension/inline EA area free ? */ if ((sp->header.flag & BT_ROOT) && (!S_ISDIR(ip->i_mode)) && (le16_to_cpu(sp->header.maxentry) < XTROOTMAXSLOT) && (JFS_IP(ip)->mode2 & INLINEEA)) { sp->header.maxentry = cpu_to_le16(XTROOTMAXSLOT); JFS_IP(ip)->mode2 &= ~INLINEEA; BT_MARK_DIRTY(smp, ip); /* * acquire a transaction lock on the leaf page; * * action: xad insertion/extension; */ /* if insert into middle, shift right remaining entries. */ skip = split->index; nextindex = le16_to_cpu(sp->header.nextindex); if (skip < nextindex) memmove(&sp->xad[skip + 1], &sp->xad[skip], (nextindex - skip) * sizeof(xad_t)); /* insert the new entry: mark the entry NEW */ xad = &sp->xad[skip]; XT_PUTENTRY(xad, split->flag, split->off, split->len, split->addr); /* advance next available entry index */ le16_add_cpu(&sp->header.nextindex, 1); /* Don't log it if there are no links to the file */ if (!test_cflag(COMMIT_Nolink, ip)) { tlck = txLock(tid, ip, smp, tlckXTREE | tlckGROW); xtlck = (struct xtlock *) & tlck->lock; xtlck->lwm.offset = (xtlck->lwm.offset) ? min(skip, (int)xtlck->lwm.offset) : skip; xtlck->lwm.length = le16_to_cpu(sp->header.nextindex) - xtlck->lwm.offset; } return 0; } /* * allocate new index blocks to cover index page split(s) * * allocation hint: ? */ if (split->pxdlist == NULL) { nsplit = btstack->nsplit; split->pxdlist = &pxdlist; pxdlist.maxnpxd = pxdlist.npxd = 0; pxd = &pxdlist.pxd[0]; xlen = JFS_SBI(ip->i_sb)->nbperpage; for (; nsplit > 0; nsplit--, pxd++) { if ((rc = dbAlloc(ip, (s64) 0, (s64) xlen, &xaddr)) == 0) { PXDaddress(pxd, xaddr); PXDlength(pxd, xlen); pxdlist.maxnpxd++; continue; } /* undo allocation */ XT_PUTPAGE(smp); return rc; } } /* * Split leaf page <sp> into <sp> and a new right page <rp>. * * The split routines insert the new entry into the leaf page, * and acquire txLock as appropriate. * return <rp> pinned and its block number <rpbn>. */ rc = (sp->header.flag & BT_ROOT) ? xtSplitRoot(tid, ip, split, &rmp) : xtSplitPage(tid, ip, split, &rmp, &rbn); XT_PUTPAGE(smp); if (rc) return -EIO; /* * propagate up the router entry for the leaf page just split * * insert a router entry for the new page into the parent page, * propagate the insert/split up the tree by walking back the stack * of (bn of parent page, index of child page entry in parent page) * that were traversed during the search for the page that split. * * the propagation of insert/split up the tree stops if the root * splits or the page inserted into doesn't have to split to hold * the new entry. * * the parent entry for the split page remains the same, and * a new entry is inserted at its right with the first key and * block number of the new right page. * * There are a maximum of 3 pages pinned at any time: * right child, left parent and right parent (when the parent splits) * to keep the child page pinned while working on the parent. * make sure that all pins are released at exit. */ while ((parent = BT_POP(btstack)) != NULL) { /* parent page specified by stack frame <parent> */ /* keep current child pages <rcp> pinned */ rcmp = rmp; rcbn = rbn; rcp = XT_PAGE(ip, rcmp); /* * insert router entry in parent for new right child page <rp> */ /* get/pin the parent page <sp> */ XT_GETPAGE(ip, parent->bn, smp, PSIZE, sp, rc); if (rc) { XT_PUTPAGE(rcmp); return rc; } /* * The new key entry goes ONE AFTER the index of parent entry, * because the split was to the right. */ skip = parent->index + 1; /* * split or shift right remaining entries of the parent page */ nextindex = le16_to_cpu(sp->header.nextindex); /* * parent page is full - split the parent page */ if (nextindex == le16_to_cpu(sp->header.maxentry)) { /* init for parent page split */ split->mp = smp; split->index = skip; /* index at insert */ split->flag = XAD_NEW; split->off = offsetXAD(&rcp->xad[XTENTRYSTART]); split->len = JFS_SBI(ip->i_sb)->nbperpage; split->addr = rcbn; /* unpin previous right child page */ XT_PUTPAGE(rcmp); /* The split routines insert the new entry, * and acquire txLock as appropriate. * return <rp> pinned and its block number <rpbn>. */ rc = (sp->header.flag & BT_ROOT) ? xtSplitRoot(tid, ip, split, &rmp) : xtSplitPage(tid, ip, split, &rmp, &rbn); if (rc) { XT_PUTPAGE(smp); return rc; } XT_PUTPAGE(smp); /* keep new child page <rp> pinned */ } /* * parent page is not full - insert in parent page */ else { /* * insert router entry in parent for the right child * page from the first entry of the right child page: */ /* * acquire a transaction lock on the parent page; * * action: router xad insertion; */ BT_MARK_DIRTY(smp, ip); /* * if insert into middle, shift right remaining entries */ if (skip < nextindex) memmove(&sp->xad[skip + 1], &sp->xad[skip], (nextindex - skip) << L2XTSLOTSIZE); /* insert the router entry */ xad = &sp->xad[skip]; XT_PUTENTRY(xad, XAD_NEW, offsetXAD(&rcp->xad[XTENTRYSTART]), JFS_SBI(ip->i_sb)->nbperpage, rcbn); /* advance next available entry index. */ le16_add_cpu(&sp->header.nextindex, 1); /* Don't log it if there are no links to the file */ if (!test_cflag(COMMIT_Nolink, ip)) { tlck = txLock(tid, ip, smp, tlckXTREE | tlckGROW); xtlck = (struct xtlock *) & tlck->lock; xtlck->lwm.offset = (xtlck->lwm.offset) ? min(skip, (int)xtlck->lwm.offset) : skip; xtlck->lwm.length = le16_to_cpu(sp->header.nextindex) - xtlck->lwm.offset; } /* unpin parent page */ XT_PUTPAGE(smp); /* exit propagate up */ break; } } /* unpin current right page */ XT_PUTPAGE(rmp); return 0; } /* * xtSplitPage() * * function: * split a full non-root page into * original/split/left page and new right page * i.e., the original/split page remains as left page. * * parameter: * int tid, * struct inode *ip, * struct xtsplit *split, * struct metapage **rmpp, * u64 *rbnp, * * return: * Pointer to page in which to insert or NULL on error. */ static int xtSplitPage(tid_t tid, struct inode *ip, struct xtsplit * split, struct metapage ** rmpp, s64 * rbnp) { int rc = 0; struct metapage *smp; xtpage_t *sp; struct metapage *rmp; xtpage_t *rp; /* new right page allocated */ s64 rbn; /* new right page block number */ struct metapage *mp; xtpage_t *p; s64 nextbn; int skip, maxentry, middle, righthalf, n; xad_t *xad; struct pxdlist *pxdlist; pxd_t *pxd; struct tlock *tlck; struct xtlock *sxtlck = NULL, *rxtlck = NULL; int quota_allocation = 0; smp = split->mp; sp = XT_PAGE(ip, smp); INCREMENT(xtStat.split); pxdlist = split->pxdlist; pxd = &pxdlist->pxd[pxdlist->npxd]; pxdlist->npxd++; rbn = addressPXD(pxd); /* Allocate blocks to quota. */ rc = dquot_alloc_block(ip, lengthPXD(pxd)); if (rc) goto clean_up; quota_allocation += lengthPXD(pxd); /* * allocate the new right page for the split */ rmp = get_metapage(ip, rbn, PSIZE, 1); if (rmp == NULL) { rc = -EIO; goto clean_up; } jfs_info("xtSplitPage: ip:0x%p smp:0x%p rmp:0x%p", ip, smp, rmp); BT_MARK_DIRTY(rmp, ip); /* * action: new page; */ rp = (xtpage_t *) rmp->data; rp->header.self = *pxd; rp->header.flag = sp->header.flag & BT_TYPE; rp->header.maxentry = sp->header.maxentry; /* little-endian */ rp->header.nextindex = cpu_to_le16(XTENTRYSTART); BT_MARK_DIRTY(smp, ip); /* Don't log it if there are no links to the file */ if (!test_cflag(COMMIT_Nolink, ip)) { /* * acquire a transaction lock on the new right page; */ tlck = txLock(tid, ip, rmp, tlckXTREE | tlckNEW); rxtlck = (struct xtlock *) & tlck->lock; rxtlck->lwm.offset = XTENTRYSTART; /* * acquire a transaction lock on the split page */ tlck = txLock(tid, ip, smp, tlckXTREE | tlckGROW); sxtlck = (struct xtlock *) & tlck->lock; } /* * initialize/update sibling pointers of <sp> and <rp> */ nextbn = le64_to_cpu(sp->header.next); rp->header.next = cpu_to_le64(nextbn); rp->header.prev = cpu_to_le64(addressPXD(&sp->header.self)); sp->header.next = cpu_to_le64(rbn); skip = split->index; /* * sequential append at tail (after last entry of last page) * * if splitting the last page on a level because of appending * a entry to it (skip is maxentry), it's likely that the access is * sequential. adding an empty page on the side of the level is less * work and can push the fill factor much higher than normal. * if we're wrong it's no big deal - we will do the split the right * way next time. * (it may look like it's equally easy to do a similar hack for * reverse sorted data, that is, split the tree left, but it's not. * Be my guest.) */ if (nextbn == 0 && skip == le16_to_cpu(sp->header.maxentry)) { /* * acquire a transaction lock on the new/right page; * * action: xad insertion; */ /* insert entry at the first entry of the new right page */ xad = &rp->xad[XTENTRYSTART]; XT_PUTENTRY(xad, split->flag, split->off, split->len, split->addr); rp->header.nextindex = cpu_to_le16(XTENTRYSTART + 1); if (!test_cflag(COMMIT_Nolink, ip)) { /* rxtlck->lwm.offset = XTENTRYSTART; */ rxtlck->lwm.length = 1; } *rmpp = rmp; *rbnp = rbn; jfs_info("xtSplitPage: sp:0x%p rp:0x%p", sp, rp); return 0; } /* * non-sequential insert (at possibly middle page) */ /* * update previous pointer of old next/right page of <sp> */ if (nextbn != 0) { XT_GETPAGE(ip, nextbn, mp, PSIZE, p, rc); if (rc) { XT_PUTPAGE(rmp); goto clean_up; } BT_MARK_DIRTY(mp, ip); /* * acquire a transaction lock on the next page; * * action:sibling pointer update; */ if (!test_cflag(COMMIT_Nolink, ip)) tlck = txLock(tid, ip, mp, tlckXTREE | tlckRELINK); p->header.prev = cpu_to_le64(rbn); /* sibling page may have been updated previously, or * it may be updated later; */ XT_PUTPAGE(mp); } /* * split the data between the split and new/right pages */ maxentry = le16_to_cpu(sp->header.maxentry); middle = maxentry >> 1; righthalf = maxentry - middle; /* * skip index in old split/left page - insert into left page: */ if (skip <= middle) { /* move right half of split page to the new right page */ memmove(&rp->xad[XTENTRYSTART], &sp->xad[middle], righthalf << L2XTSLOTSIZE); /* shift right tail of left half to make room for new entry */ if (skip < middle) memmove(&sp->xad[skip + 1], &sp->xad[skip], (middle - skip) << L2XTSLOTSIZE); /* insert new entry */ xad = &sp->xad[skip]; XT_PUTENTRY(xad, split->flag, split->off, split->len, split->addr); /* update page header */ sp->header.nextindex = cpu_to_le16(middle + 1); if (!test_cflag(COMMIT_Nolink, ip)) { sxtlck->lwm.offset = (sxtlck->lwm.offset) ? min(skip, (int)sxtlck->lwm.offset) : skip; } rp->header.nextindex = cpu_to_le16(XTENTRYSTART + righthalf); } /* * skip index in new right page - insert into right page: */ else { /* move left head of right half to right page */ n = skip - middle; memmove(&rp->xad[XTENTRYSTART], &sp->xad[middle], n << L2XTSLOTSIZE); /* insert new entry */ n += XTENTRYSTART; xad = &rp->xad[n]; XT_PUTENTRY(xad, split->flag, split->off, split->len, split->addr); /* move right tail of right half to right page */ if (skip < maxentry) memmove(&rp->xad[n + 1], &sp->xad[skip], (maxentry - skip) << L2XTSLOTSIZE); /* update page header */ sp->header.nextindex = cpu_to_le16(middle); if (!test_cflag(COMMIT_Nolink, ip)) { sxtlck->lwm.offset = (sxtlck->lwm.offset) ? min(middle, (int)sxtlck->lwm.offset) : middle; } rp->header.nextindex = cpu_to_le16(XTENTRYSTART + righthalf + 1); } if (!test_cflag(COMMIT_Nolink, ip)) { sxtlck->lwm.length = le16_to_cpu(sp->header.nextindex) - sxtlck->lwm.offset; /* rxtlck->lwm.offset = XTENTRYSTART; */ rxtlck->lwm.length = le16_to_cpu(rp->header.nextindex) - XTENTRYSTART; } *rmpp = rmp; *rbnp = rbn; jfs_info("xtSplitPage: sp:0x%p rp:0x%p", sp, rp); return rc; clean_up: /* Rollback quota allocation. */ if (quota_allocation) dquot_free_block(ip, quota_allocation); return (rc); } /* * xtSplitRoot() * * function: * split the full root page into original/root/split page and new * right page * i.e., root remains fixed in tree anchor (inode) and the root is * copied to a single new right child page since root page << * non-root page, and the split root page contains a single entry * for the new right child page. * * parameter: * int tid, * struct inode *ip, * struct xtsplit *split, * struct metapage **rmpp) * * return: * Pointer to page in which to insert or NULL on error. */ static int xtSplitRoot(tid_t tid, struct inode *ip, struct xtsplit * split, struct metapage ** rmpp) { xtpage_t *sp; struct metapage *rmp; xtpage_t *rp; s64 rbn; int skip, nextindex; xad_t *xad; pxd_t *pxd; struct pxdlist *pxdlist; struct tlock *tlck; struct xtlock *xtlck; int rc; sp = (xtpage_t *) &JFS_IP(ip)->i_xtroot; INCREMENT(xtStat.split); /* * allocate a single (right) child page */ pxdlist = split->pxdlist; pxd = &pxdlist->pxd[pxdlist->npxd]; pxdlist->npxd++; rbn = addressPXD(pxd); rmp = get_metapage(ip, rbn, PSIZE, 1); if (rmp == NULL) return -EIO; /* Allocate blocks to quota. */ rc = dquot_alloc_block(ip, lengthPXD(pxd)); if (rc) { release_metapage(rmp); return rc; } jfs_info("xtSplitRoot: ip:0x%p rmp:0x%p", ip, rmp); /* * acquire a transaction lock on the new right page; * * action: new page; */ BT_MARK_DIRTY(rmp, ip); rp = (xtpage_t *) rmp->data; rp->header.flag = (sp->header.flag & BT_LEAF) ? BT_LEAF : BT_INTERNAL; rp->header.self = *pxd; rp->header.nextindex = cpu_to_le16(XTENTRYSTART); rp->header.maxentry = cpu_to_le16(PSIZE >> L2XTSLOTSIZE); /* initialize sibling pointers */ rp->header.next = 0; rp->header.prev = 0; /* * copy the in-line root page into new right page extent */ nextindex = le16_to_cpu(sp->header.maxentry); memmove(&rp->xad[XTENTRYSTART], &sp->xad[XTENTRYSTART], (nextindex - XTENTRYSTART) << L2XTSLOTSIZE); /* * insert the new entry into the new right/child page * (skip index in the new right page will not change) */ skip = split->index; /* if insert into middle, shift right remaining entries */ if (skip != nextindex) memmove(&rp->xad[skip + 1], &rp->xad[skip], (nextindex - skip) * sizeof(xad_t)); xad = &rp->xad[skip]; XT_PUTENTRY(xad, split->flag, split->off, split->len, split->addr); /* update page header */ rp->header.nextindex = cpu_to_le16(nextindex + 1); if (!test_cflag(COMMIT_Nolink, ip)) { tlck = txLock(tid, ip, rmp, tlckXTREE | tlckNEW); xtlck = (struct xtlock *) & tlck->lock; xtlck->lwm.offset = XTENTRYSTART; xtlck->lwm.length = le16_to_cpu(rp->header.nextindex) - XTENTRYSTART; } /* * reset the root * * init root with the single entry for the new right page * set the 1st entry offset to 0, which force the left-most key * at any level of the tree to be less than any search key. */ /* * acquire a transaction lock on the root page (in-memory inode); * * action: root split; */ BT_MARK_DIRTY(split->mp, ip); xad = &sp->xad[XTENTRYSTART]; XT_PUTENTRY(xad, XAD_NEW, 0, JFS_SBI(ip->i_sb)->nbperpage, rbn); /* update page header of root */ sp->header.flag &= ~BT_LEAF; sp->header.flag |= BT_INTERNAL; sp->header.nextindex = cpu_to_le16(XTENTRYSTART + 1); if (!test_cflag(COMMIT_Nolink, ip)) { tlck = txLock(tid, ip, split->mp, tlckXTREE | tlckGROW); xtlck = (struct xtlock *) & tlck->lock; xtlck->lwm.offset = XTENTRYSTART; xtlck->lwm.length = 1; } *rmpp = rmp; jfs_info("xtSplitRoot: sp:0x%p rp:0x%p", sp, rp); return 0; } /* * xtExtend() * * function: extend in-place; * * note: existing extent may or may not have been committed. * caller is responsible for pager buffer cache update, and * working block allocation map update; * update pmap: alloc whole extended extent; */ int xtExtend(tid_t tid, /* transaction id */ struct inode *ip, s64 xoff, /* delta extent offset */ s32 xlen, /* delta extent length */ int flag) { int rc = 0; int cmp; struct metapage *mp; /* meta-page buffer */ xtpage_t *p; /* base B+-tree index page */ s64 bn; int index, nextindex, len; struct btstack btstack; /* traverse stack */ struct xtsplit split; /* split information */ xad_t *xad; s64 xaddr; struct tlock *tlck; struct xtlock *xtlck = NULL; jfs_info("xtExtend: nxoff:0x%lx nxlen:0x%x", (ulong) xoff, xlen); /* there must exist extent to be extended */ if ((rc = xtSearch(ip, xoff - 1, NULL, &cmp, &btstack, XT_INSERT))) return rc; /* retrieve search result */ XT_GETSEARCH(ip, btstack.top, bn, mp, p, index); if (cmp != 0) { XT_PUTPAGE(mp); jfs_error(ip->i_sb, "xtSearch did not find extent\n"); return -EIO; } /* extension must be contiguous */ xad = &p->xad[index]; if ((offsetXAD(xad) + lengthXAD(xad)) != xoff) { XT_PUTPAGE(mp); jfs_error(ip->i_sb, "extension is not contiguous\n"); return -EIO; } /* * acquire a transaction lock on the leaf page; * * action: xad insertion/extension; */ BT_MARK_DIRTY(mp, ip); if (!test_cflag(COMMIT_Nolink, ip)) { tlck = txLock(tid, ip, mp, tlckXTREE | tlckGROW); xtlck = (struct xtlock *) & tlck->lock; } /* extend will overflow extent ? */ xlen = lengthXAD(xad) + xlen; if ((len = xlen - MAXXLEN) <= 0) goto extendOld; /* * extent overflow: insert entry for new extent */ //insertNew: xoff = offsetXAD(xad) + MAXXLEN; xaddr = addressXAD(xad) + MAXXLEN; nextindex = le16_to_cpu(p->header.nextindex); /* * if the leaf page is full, insert the new entry and * propagate up the router entry for the new page from split * * The xtSplitUp() will insert the entry and unpin the leaf page. */ if (nextindex == le16_to_cpu(p->header.maxentry)) { /* xtSpliUp() unpins leaf pages */ split.mp = mp; split.index = index + 1; split.flag = XAD_NEW; split.off = xoff; /* split offset */ split.len = len; split.addr = xaddr; split.pxdlist = NULL; if ((rc = xtSplitUp(tid, ip, &split, &btstack))) return rc; /* get back old page */ XT_GETPAGE(ip, bn, mp, PSIZE, p, rc); if (rc) return rc; /* * if leaf root has been split, original root has been * copied to new child page, i.e., original entry now * resides on the new child page; */ if (p->header.flag & BT_INTERNAL) { ASSERT(p->header.nextindex == cpu_to_le16(XTENTRYSTART + 1)); xad = &p->xad[XTENTRYSTART]; bn = addressXAD(xad); XT_PUTPAGE(mp); /* get new child page */ XT_GETPAGE(ip, bn, mp, PSIZE, p, rc); if (rc) return rc; BT_MARK_DIRTY(mp, ip); if (!test_cflag(COMMIT_Nolink, ip)) { tlck = txLock(tid, ip, mp, tlckXTREE|tlckGROW); xtlck = (struct xtlock *) & tlck->lock; } } } /* * insert the new entry into the leaf page */ else { /* insert the new entry: mark the entry NEW */ xad = &p->xad[index + 1]; XT_PUTENTRY(xad, XAD_NEW, xoff, len, xaddr); /* advance next available entry index */ le16_add_cpu(&p->header.nextindex, 1); } /* get back old entry */ xad = &p->xad[index]; xlen = MAXXLEN; /* * extend old extent */ extendOld: XADlength(xad, xlen); if (!(xad->flag & XAD_NEW)) xad->flag |= XAD_EXTENDED; if (!test_cflag(COMMIT_Nolink, ip)) { xtlck->lwm.offset = (xtlck->lwm.offset) ? min(index, (int)xtlck->lwm.offset) : index; xtlck->lwm.length = le16_to_cpu(p->header.nextindex) - xtlck->lwm.offset; } /* unpin the leaf page */ XT_PUTPAGE(mp); return rc; } /* * xtUpdate() * * function: update XAD; * * update extent for allocated_but_not_recorded or * compressed extent; * * parameter: * nxad - new XAD; * logical extent of the specified XAD must be completely * contained by an existing XAD; */ int xtUpdate(tid_t tid, struct inode *ip, xad_t * nxad) { /* new XAD */ int rc = 0; int cmp; struct metapage *mp; /* meta-page buffer */ xtpage_t *p; /* base B+-tree index page */ s64 bn; int index0, index, newindex, nextindex; struct btstack btstack; /* traverse stack */ struct xtsplit split; /* split information */ xad_t *xad, *lxad, *rxad; int xflag; s64 nxoff, xoff; int nxlen, xlen, lxlen, rxlen; s64 nxaddr, xaddr; struct tlock *tlck; struct xtlock *xtlck = NULL; int newpage = 0; /* there must exist extent to be tailgated */ nxoff = offsetXAD(nxad); nxlen = lengthXAD(nxad); nxaddr = addressXAD(nxad); if ((rc = xtSearch(ip, nxoff, NULL, &cmp, &btstack, XT_INSERT))) return rc; /* retrieve search result */ XT_GETSEARCH(ip, btstack.top, bn, mp, p, index0); if (cmp != 0) { XT_PUTPAGE(mp); jfs_error(ip->i_sb, "Could not find extent\n"); return -EIO; } BT_MARK_DIRTY(mp, ip); /* * acquire tlock of the leaf page containing original entry */ if (!test_cflag(COMMIT_Nolink, ip)) { tlck = txLock(tid, ip, mp, tlckXTREE | tlckGROW); xtlck = (struct xtlock *) & tlck->lock; } xad = &p->xad[index0]; xflag = xad->flag; xoff = offsetXAD(xad); xlen = lengthXAD(xad); xaddr = addressXAD(xad); /* nXAD must be completely contained within XAD */ if ((xoff > nxoff) || (nxoff + nxlen > xoff + xlen)) { XT_PUTPAGE(mp); jfs_error(ip->i_sb, "nXAD in not completely contained within XAD\n"); return -EIO; } index = index0; newindex = index + 1; nextindex = le16_to_cpu(p->header.nextindex); if (xoff < nxoff) goto coalesceRight; /* * coalesce with left XAD */ /* is XAD first entry of page ? */ if (index == XTENTRYSTART) goto replace; /* is nXAD logically and physically contiguous with lXAD ? */ lxad = &p->xad[index - 1]; lxlen = lengthXAD(lxad); if (!(lxad->flag & XAD_NOTRECORDED) && (nxoff == offsetXAD(lxad) + lxlen) && (nxaddr == addressXAD(lxad) + lxlen) && (lxlen + nxlen < MAXXLEN)) { /* extend right lXAD */ index0 = index - 1; XADlength(lxad, lxlen + nxlen); /* If we just merged two extents together, need to make sure the * right extent gets logged. If the left one is marked XAD_NEW, * then we know it will be logged. Otherwise, mark as * XAD_EXTENDED */ if (!(lxad->flag & XAD_NEW)) lxad->flag |= XAD_EXTENDED; if (xlen > nxlen) { /* truncate XAD */ XADoffset(xad, xoff + nxlen); XADlength(xad, xlen - nxlen); XADaddress(xad, xaddr + nxlen); goto out; } else { /* (xlen == nxlen) */ /* remove XAD */ if (index < nextindex - 1) memmove(&p->xad[index], &p->xad[index + 1], (nextindex - index - 1) << L2XTSLOTSIZE); p->header.nextindex = cpu_to_le16(le16_to_cpu(p->header.nextindex) - 1); index = index0; newindex = index + 1; nextindex = le16_to_cpu(p->header.nextindex); xoff = nxoff = offsetXAD(lxad); xlen = nxlen = lxlen + nxlen; xaddr = nxaddr = addressXAD(lxad); goto coalesceRight; } } /* * replace XAD with nXAD */ replace: /* (nxoff == xoff) */ if (nxlen == xlen) { /* replace XAD with nXAD:recorded */ *xad = *nxad; xad->flag = xflag & ~XAD_NOTRECORDED; goto coalesceRight; } else /* (nxlen < xlen) */ goto updateLeft; /* * coalesce with right XAD */ coalesceRight: /* (xoff <= nxoff) */ /* is XAD last entry of page ? */ if (newindex == nextindex) { if (xoff == nxoff) goto out; goto updateRight; } /* is nXAD logically and physically contiguous with rXAD ? */ rxad = &p->xad[index + 1]; rxlen = lengthXAD(rxad); if (!(rxad->flag & XAD_NOTRECORDED) && (nxoff + nxlen == offsetXAD(rxad)) && (nxaddr + nxlen == addressXAD(rxad)) && (rxlen + nxlen < MAXXLEN)) { /* extend left rXAD */ XADoffset(rxad, nxoff); XADlength(rxad, rxlen + nxlen); XADaddress(rxad, nxaddr); /* If we just merged two extents together, need to make sure * the left extent gets logged. If the right one is marked * XAD_NEW, then we know it will be logged. Otherwise, mark as * XAD_EXTENDED */ if (!(rxad->flag & XAD_NEW)) rxad->flag |= XAD_EXTENDED; if (xlen > nxlen) /* truncate XAD */ XADlength(xad, xlen - nxlen); else { /* (xlen == nxlen) */ /* remove XAD */ memmove(&p->xad[index], &p->xad[index + 1], (nextindex - index - 1) << L2XTSLOTSIZE); p->header.nextindex = cpu_to_le16(le16_to_cpu(p->header.nextindex) - 1); } goto out; } else if (xoff == nxoff) goto out; if (xoff >= nxoff) { XT_PUTPAGE(mp); jfs_error(ip->i_sb, "xoff >= nxoff\n"); return -EIO; } /* * split XAD into (lXAD, nXAD): * * |---nXAD---> * --|----------XAD----------|-- * |-lXAD-| */ updateRight: /* (xoff < nxoff) */ /* truncate old XAD as lXAD:not_recorded */ xad = &p->xad[index]; XADlength(xad, nxoff - xoff); /* insert nXAD:recorded */ if (nextindex == le16_to_cpu(p->header.maxentry)) { /* xtSpliUp() unpins leaf pages */ split.mp = mp; split.index = newindex; split.flag = xflag & ~XAD_NOTRECORDED; split.off = nxoff; split.len = nxlen; split.addr = nxaddr; split.pxdlist = NULL; if ((rc = xtSplitUp(tid, ip, &split, &btstack))) return rc; /* get back old page */ XT_GETPAGE(ip, bn, mp, PSIZE, p, rc); if (rc) return rc; /* * if leaf root has been split, original root has been * copied to new child page, i.e., original entry now * resides on the new child page; */ if (p->header.flag & BT_INTERNAL) { ASSERT(p->header.nextindex == cpu_to_le16(XTENTRYSTART + 1)); xad = &p->xad[XTENTRYSTART]; bn = addressXAD(xad); XT_PUTPAGE(mp); /* get new child page */ XT_GETPAGE(ip, bn, mp, PSIZE, p, rc); if (rc) return rc; BT_MARK_DIRTY(mp, ip); if (!test_cflag(COMMIT_Nolink, ip)) { tlck = txLock(tid, ip, mp, tlckXTREE|tlckGROW); xtlck = (struct xtlock *) & tlck->lock; } } else { /* is nXAD on new page ? */ if (newindex > (le16_to_cpu(p->header.maxentry) >> 1)) { newindex = newindex - le16_to_cpu(p->header.nextindex) + XTENTRYSTART; newpage = 1; } } } else { /* if insert into middle, shift right remaining entries */ if (newindex < nextindex) memmove(&p->xad[newindex + 1], &p->xad[newindex], (nextindex - newindex) << L2XTSLOTSIZE); /* insert the entry */ xad = &p->xad[newindex]; *xad = *nxad; xad->flag = xflag & ~XAD_NOTRECORDED; /* advance next available entry index. */ p->header.nextindex = cpu_to_le16(le16_to_cpu(p->header.nextindex) + 1); } /* * does nXAD force 3-way split ? * * |---nXAD--->| * --|----------XAD-------------|-- * |-lXAD-| |-rXAD -| */ if (nxoff + nxlen == xoff + xlen) goto out; /* reorient nXAD as XAD for further split XAD into (nXAD, rXAD) */ if (newpage) { /* close out old page */ if (!test_cflag(COMMIT_Nolink, ip)) { xtlck->lwm.offset = (xtlck->lwm.offset) ? min(index0, (int)xtlck->lwm.offset) : index0; xtlck->lwm.length = le16_to_cpu(p->header.nextindex) - xtlck->lwm.offset; } bn = le64_to_cpu(p->header.next); XT_PUTPAGE(mp); /* get new right page */ XT_GETPAGE(ip, bn, mp, PSIZE, p, rc); if (rc) return rc; BT_MARK_DIRTY(mp, ip); if (!test_cflag(COMMIT_Nolink, ip)) { tlck = txLock(tid, ip, mp, tlckXTREE | tlckGROW); xtlck = (struct xtlock *) & tlck->lock; } index0 = index = newindex; } else index++; newindex = index + 1; nextindex = le16_to_cpu(p->header.nextindex); xlen = xlen - (nxoff - xoff); xoff = nxoff; xaddr = nxaddr; /* recompute split pages */ if (nextindex == le16_to_cpu(p->header.maxentry)) { XT_PUTPAGE(mp); if ((rc = xtSearch(ip, nxoff, NULL, &cmp, &btstack, XT_INSERT))) return rc; /* retrieve search result */ XT_GETSEARCH(ip, btstack.top, bn, mp, p, index0); if (cmp != 0) { XT_PUTPAGE(mp); jfs_error(ip->i_sb, "xtSearch failed\n"); return -EIO; } if (index0 != index) { XT_PUTPAGE(mp); jfs_error(ip->i_sb, "unexpected value of index\n"); return -EIO; } } /* * split XAD into (nXAD, rXAD) * * ---nXAD---| * --|----------XAD----------|-- * |-rXAD-| */ updateLeft: /* (nxoff == xoff) && (nxlen < xlen) */ /* update old XAD with nXAD:recorded */ xad = &p->xad[index]; *xad = *nxad; xad->flag = xflag & ~XAD_NOTRECORDED; /* insert rXAD:not_recorded */ xoff = xoff + nxlen; xlen = xlen - nxlen; xaddr = xaddr + nxlen; if (nextindex == le16_to_cpu(p->header.maxentry)) { /* printf("xtUpdate.updateLeft.split p:0x%p\n", p); */ /* xtSpliUp() unpins leaf pages */ split.mp = mp; split.index = newindex; split.flag = xflag; split.off = xoff; split.len = xlen; split.addr = xaddr; split.pxdlist = NULL; if ((rc = xtSplitUp(tid, ip, &split, &btstack))) return rc; /* get back old page */ XT_GETPAGE(ip, bn, mp, PSIZE, p, rc); if (rc) return rc; /* * if leaf root has been split, original root has been * copied to new child page, i.e., original entry now * resides on the new child page; */ if (p->header.flag & BT_INTERNAL) { ASSERT(p->header.nextindex == cpu_to_le16(XTENTRYSTART + 1)); xad = &p->xad[XTENTRYSTART]; bn = addressXAD(xad); XT_PUTPAGE(mp); /* get new child page */ XT_GETPAGE(ip, bn, mp, PSIZE, p, rc); if (rc) return rc; BT_MARK_DIRTY(mp, ip); if (!test_cflag(COMMIT_Nolink, ip)) { tlck = txLock(tid, ip, mp, tlckXTREE|tlckGROW); xtlck = (struct xtlock *) & tlck->lock; } } } else { /* if insert into middle, shift right remaining entries */ if (newindex < nextindex) memmove(&p->xad[newindex + 1], &p->xad[newindex], (nextindex - newindex) << L2XTSLOTSIZE); /* insert the entry */ xad = &p->xad[newindex]; XT_PUTENTRY(xad, xflag, xoff, xlen, xaddr); /* advance next available entry index. */ p->header.nextindex = cpu_to_le16(le16_to_cpu(p->header.nextindex) + 1); } out: if (!test_cflag(COMMIT_Nolink, ip)) { xtlck->lwm.offset = (xtlck->lwm.offset) ? min(index0, (int)xtlck->lwm.offset) : index0; xtlck->lwm.length = le16_to_cpu(p->header.nextindex) - xtlck->lwm.offset; } /* unpin the leaf page */ XT_PUTPAGE(mp); return rc; } /* * xtAppend() * * function: grow in append mode from contiguous region specified ; * * parameter: * tid - transaction id; * ip - file object; * xflag - extent flag: * xoff - extent offset; * maxblocks - max extent length; * xlen - extent length (in/out); * xaddrp - extent address pointer (in/out): * flag - * * return: */ int xtAppend(tid_t tid, /* transaction id */ struct inode *ip, int xflag, s64 xoff, s32 maxblocks, s32 * xlenp, /* (in/out) */ s64 * xaddrp, /* (in/out) */ int flag) { int rc = 0; struct metapage *mp; /* meta-page buffer */ xtpage_t *p; /* base B+-tree index page */ s64 bn, xaddr; int index, nextindex; struct btstack btstack; /* traverse stack */ struct xtsplit split; /* split information */ xad_t *xad; int cmp; struct tlock *tlck; struct xtlock *xtlck; int nsplit, nblocks, xlen; struct pxdlist pxdlist; pxd_t *pxd; s64 next; xaddr = *xaddrp; xlen = *xlenp; jfs_info("xtAppend: xoff:0x%lx maxblocks:%d xlen:%d xaddr:0x%lx", (ulong) xoff, maxblocks, xlen, (ulong) xaddr); /* * search for the entry location at which to insert: * * xtFastSearch() and xtSearch() both returns (leaf page * pinned, index at which to insert). * n.b. xtSearch() may return index of maxentry of * the full page. */ if ((rc = xtSearch(ip, xoff, &next, &cmp, &btstack, XT_INSERT))) return rc; /* retrieve search result */ XT_GETSEARCH(ip, btstack.top, bn, mp, p, index); if (cmp == 0) { rc = -EEXIST; goto out; } if (next) xlen = min(xlen, (int)(next - xoff)); //insert: /* * insert entry for new extent */ xflag |= XAD_NEW; /* * if the leaf page is full, split the page and * propagate up the router entry for the new page from split * * The xtSplitUp() will insert the entry and unpin the leaf page. */ nextindex = le16_to_cpu(p->header.nextindex); if (nextindex < le16_to_cpu(p->header.maxentry)) goto insertLeaf; /* * allocate new index blocks to cover index page split(s) */ nsplit = btstack.nsplit; split.pxdlist = &pxdlist; pxdlist.maxnpxd = pxdlist.npxd = 0; pxd = &pxdlist.pxd[0]; nblocks = JFS_SBI(ip->i_sb)->nbperpage; for (; nsplit > 0; nsplit--, pxd++, xaddr += nblocks, maxblocks -= nblocks) { if ((rc = dbAllocBottomUp(ip, xaddr, (s64) nblocks)) == 0) { PXDaddress(pxd, xaddr); PXDlength(pxd, nblocks); pxdlist.maxnpxd++; continue; } /* undo allocation */ goto out; } xlen = min(xlen, maxblocks); /* * allocate data extent requested */ if ((rc = dbAllocBottomUp(ip, xaddr, (s64) xlen))) goto out; split.mp = mp; split.index = index; split.flag = xflag; split.off = xoff; split.len = xlen; split.addr = xaddr; if ((rc = xtSplitUp(tid, ip, &split, &btstack))) { /* undo data extent allocation */ dbFree(ip, *xaddrp, (s64) * xlenp); return rc; } *xaddrp = xaddr; *xlenp = xlen; return 0; /* * insert the new entry into the leaf page */ insertLeaf: /* * allocate data extent requested */ if ((rc = dbAllocBottomUp(ip, xaddr, (s64) xlen))) goto out; BT_MARK_DIRTY(mp, ip); /* * acquire a transaction lock on the leaf page; * * action: xad insertion/extension; */ tlck = txLock(tid, ip, mp, tlckXTREE | tlckGROW); xtlck = (struct xtlock *) & tlck->lock; /* insert the new entry: mark the entry NEW */ xad = &p->xad[index]; XT_PUTENTRY(xad, xflag, xoff, xlen, xaddr); /* advance next available entry index */ le16_add_cpu(&p->header.nextindex, 1); xtlck->lwm.offset = (xtlck->lwm.offset) ? min(index,(int) xtlck->lwm.offset) : index; xtlck->lwm.length = le16_to_cpu(p->header.nextindex) - xtlck->lwm.offset; *xaddrp = xaddr; *xlenp = xlen; out: /* unpin the leaf page */ XT_PUTPAGE(mp); return rc; } /* * xtInitRoot() * * initialize file root (inline in inode) */ void xtInitRoot(tid_t tid, struct inode *ip) { xtroot_t *p; /* * acquire a transaction lock on the root * * action: */ txLock(tid, ip, (struct metapage *) &JFS_IP(ip)->bxflag, tlckXTREE | tlckNEW); p = &JFS_IP(ip)->i_xtroot; p->header.flag = DXD_INDEX | BT_ROOT | BT_LEAF; p->header.nextindex = cpu_to_le16(XTENTRYSTART); if (S_ISDIR(ip->i_mode)) p->header.maxentry = cpu_to_le16(XTROOTINITSLOT_DIR); else { p->header.maxentry = cpu_to_le16(XTROOTINITSLOT); ip->i_size = 0; } return; } /* * We can run into a deadlock truncating a file with a large number of * xtree pages (large fragmented file). A robust fix would entail a * reservation system where we would reserve a number of metadata pages * and tlocks which we would be guaranteed without a deadlock. Without * this, a partial fix is to limit number of metadata pages we will lock * in a single transaction. Currently we will truncate the file so that * no more than 50 leaf pages will be locked. The caller of xtTruncate * will be responsible for ensuring that the current transaction gets * committed, and that subsequent transactions are created to truncate * the file further if needed. */ #define MAX_TRUNCATE_LEAVES 50 /* * xtTruncate() * * function: * traverse for truncation logging backward bottom up; * terminate at the last extent entry at the current subtree * root page covering new down size. * truncation may occur within the last extent entry. * * parameter: * int tid, * struct inode *ip, * s64 newsize, * int type) {PWMAP, PMAP, WMAP; DELETE, TRUNCATE} * * return: * * note: * PWMAP: * 1. truncate (non-COMMIT_NOLINK file) * by jfs_truncate() or jfs_open(O_TRUNC): * xtree is updated; * 2. truncate index table of directory when last entry removed * map update via tlock at commit time; * PMAP: * Call xtTruncate_pmap instead * WMAP: * 1. remove (free zero link count) on last reference release * (pmap has been freed at commit zero link count); * 2. truncate (COMMIT_NOLINK file, i.e., tmp file): * xtree is updated; * map update directly at truncation time; * * if (DELETE) * no LOG_NOREDOPAGE is required (NOREDOFILE is sufficient); * else if (TRUNCATE) * must write LOG_NOREDOPAGE for deleted index page; * * pages may already have been tlocked by anonymous transactions * during file growth (i.e., write) before truncation; * * except last truncated entry, deleted entries remains as is * in the page (nextindex is updated) for other use * (e.g., log/update allocation map): this avoid copying the page * info but delay free of pages; * */ s64 xtTruncate(tid_t tid, struct inode *ip, s64 newsize, int flag) { int rc = 0; s64 teof; struct metapage *mp; xtpage_t *p; s64 bn; int index, nextindex; xad_t *xad; s64 xoff, xaddr; int xlen, len, freexlen; struct btstack btstack; struct btframe *parent; struct tblock *tblk = NULL; struct tlock *tlck = NULL; struct xtlock *xtlck = NULL; struct xdlistlock xadlock; /* maplock for COMMIT_WMAP */ struct pxd_lock *pxdlock; /* maplock for COMMIT_WMAP */ s64 nfreed; int freed, log; int locked_leaves = 0; /* save object truncation type */ if (tid) { tblk = tid_to_tblock(tid); tblk->xflag |= flag; } nfreed = 0; flag &= COMMIT_MAP; assert(flag != COMMIT_PMAP); if (flag == COMMIT_PWMAP) log = 1; else { log = 0; xadlock.flag = mlckFREEXADLIST; xadlock.index = 1; } /* * if the newsize is not an integral number of pages, * the file between newsize and next page boundary will * be cleared. * if truncating into a file hole, it will cause * a full block to be allocated for the logical block. */ /* * release page blocks of truncated region <teof, eof> * * free the data blocks from the leaf index blocks. * delete the parent index entries corresponding to * the freed child data/index blocks. * free the index blocks themselves which aren't needed * in new sized file. * * index blocks are updated only if the blocks are to be * retained in the new sized file. * if type is PMAP, the data and index pages are NOT * freed, and the data and index blocks are NOT freed * from working map. * (this will allow continued access of data/index of * temporary file (zerolink count file truncated to zero-length)). */ teof = (newsize + (JFS_SBI(ip->i_sb)->bsize - 1)) >> JFS_SBI(ip->i_sb)->l2bsize; /* clear stack */ BT_CLR(&btstack); /* * start with root * * root resides in the inode */ bn = 0; /* * first access of each page: */ getPage: XT_GETPAGE(ip, bn, mp, PSIZE, p, rc); if (rc) return rc; /* process entries backward from last index */ index = le16_to_cpu(p->header.nextindex) - 1; /* Since this is the rightmost page at this level, and we may have * already freed a page that was formerly to the right, let's make * sure that the next pointer is zero. */ if (p->header.next) { if (log) /* * Make sure this change to the header is logged. * If we really truncate this leaf, the flag * will be changed to tlckTRUNCATE */ tlck = txLock(tid, ip, mp, tlckXTREE|tlckGROW); BT_MARK_DIRTY(mp, ip); p->header.next = 0; } if (p->header.flag & BT_INTERNAL) goto getChild; /* * leaf page */ freed = 0; /* does region covered by leaf page precede Teof ? */ xad = &p->xad[index]; xoff = offsetXAD(xad); xlen = lengthXAD(xad); if (teof >= xoff + xlen) { XT_PUTPAGE(mp); goto getParent; } /* (re)acquire tlock of the leaf page */ if (log) { if (++locked_leaves > MAX_TRUNCATE_LEAVES) { /* * We need to limit the size of the transaction * to avoid exhausting pagecache & tlocks */ XT_PUTPAGE(mp); newsize = (xoff + xlen) << JFS_SBI(ip->i_sb)->l2bsize; goto getParent; } tlck = txLock(tid, ip, mp, tlckXTREE); tlck->type = tlckXTREE | tlckTRUNCATE; xtlck = (struct xtlock *) & tlck->lock; xtlck->hwm.offset = le16_to_cpu(p->header.nextindex) - 1; } BT_MARK_DIRTY(mp, ip); /* * scan backward leaf page entries */ for (; index >= XTENTRYSTART; index--) { xad = &p->xad[index]; xoff = offsetXAD(xad); xlen = lengthXAD(xad); xaddr = addressXAD(xad); /* * The "data" for a directory is indexed by the block * device's address space. This metadata must be invalidated * here */ if (S_ISDIR(ip->i_mode) && (teof == 0)) invalidate_xad_metapages(ip, *xad); /* * entry beyond eof: continue scan of current page * xad * ---|---=======-------> * eof */ if (teof < xoff) { nfreed += xlen; continue; } /* * (xoff <= teof): last entry to be deleted from page; * If other entries remain in page: keep and update the page. */ /* * eof == entry_start: delete the entry * xad * -------|=======-------> * eof * */ if (teof == xoff) { nfreed += xlen; if (index == XTENTRYSTART) break; nextindex = index; } /* * eof within the entry: truncate the entry. * xad * -------===|===-------> * eof */ else if (teof < xoff + xlen) { /* update truncated entry */ len = teof - xoff; freexlen = xlen - len; XADlength(xad, len); /* save pxd of truncated extent in tlck */ xaddr += len; if (log) { /* COMMIT_PWMAP */ xtlck->lwm.offset = (xtlck->lwm.offset) ? min(index, (int)xtlck->lwm.offset) : index; xtlck->lwm.length = index + 1 - xtlck->lwm.offset; xtlck->twm.offset = index; pxdlock = (struct pxd_lock *) & xtlck->pxdlock; pxdlock->flag = mlckFREEPXD; PXDaddress(&pxdlock->pxd, xaddr); PXDlength(&pxdlock->pxd, freexlen); } /* free truncated extent */ else { /* COMMIT_WMAP */ pxdlock = (struct pxd_lock *) & xadlock; pxdlock->flag = mlckFREEPXD; PXDaddress(&pxdlock->pxd, xaddr); PXDlength(&pxdlock->pxd, freexlen); txFreeMap(ip, pxdlock, NULL, COMMIT_WMAP); /* reset map lock */ xadlock.flag = mlckFREEXADLIST; } /* current entry is new last entry; */ nextindex = index + 1; nfreed += freexlen; } /* * eof beyond the entry: * xad * -------=======---|---> * eof */ else { /* (xoff + xlen < teof) */ nextindex = index + 1; } if (nextindex < le16_to_cpu(p->header.nextindex)) { if (!log) { /* COMMIT_WAMP */ xadlock.xdlist = &p->xad[nextindex]; xadlock.count = le16_to_cpu(p->header.nextindex) - nextindex; txFreeMap(ip, (struct maplock *) & xadlock, NULL, COMMIT_WMAP); } p->header.nextindex = cpu_to_le16(nextindex); } XT_PUTPAGE(mp); /* assert(freed == 0); */ goto getParent; } /* end scan of leaf page entries */ freed = 1; /* * leaf page become empty: free the page if type != PMAP */ if (log) { /* COMMIT_PWMAP */ /* txCommit() with tlckFREE: * free data extents covered by leaf [XTENTRYSTART:hwm); * invalidate leaf if COMMIT_PWMAP; * if (TRUNCATE), will write LOG_NOREDOPAGE; */ tlck->type = tlckXTREE | tlckFREE; } else { /* COMMIT_WAMP */ /* free data extents covered by leaf */ xadlock.xdlist = &p->xad[XTENTRYSTART]; xadlock.count = le16_to_cpu(p->header.nextindex) - XTENTRYSTART; txFreeMap(ip, (struct maplock *) & xadlock, NULL, COMMIT_WMAP); } if (p->header.flag & BT_ROOT) { p->header.flag &= ~BT_INTERNAL; p->header.flag |= BT_LEAF; p->header.nextindex = cpu_to_le16(XTENTRYSTART); XT_PUTPAGE(mp); /* debug */ goto out; } else { if (log) { /* COMMIT_PWMAP */ /* page will be invalidated at tx completion */ XT_PUTPAGE(mp); } else { /* COMMIT_WMAP */ if (mp->lid) lid_to_tlock(mp->lid)->flag |= tlckFREELOCK; /* invalidate empty leaf page */ discard_metapage(mp); } } /* * the leaf page become empty: delete the parent entry * for the leaf page if the parent page is to be kept * in the new sized file. */ /* * go back up to the parent page */ getParent: /* pop/restore parent entry for the current child page */ if ((parent = BT_POP(&btstack)) == NULL) /* current page must have been root */ goto out; /* get back the parent page */ bn = parent->bn; XT_GETPAGE(ip, bn, mp, PSIZE, p, rc); if (rc) return rc; index = parent->index; /* * child page was not empty: */ if (freed == 0) { /* has any entry deleted from parent ? */ if (index < le16_to_cpu(p->header.nextindex) - 1) { /* (re)acquire tlock on the parent page */ if (log) { /* COMMIT_PWMAP */ /* txCommit() with tlckTRUNCATE: * free child extents covered by parent [); */ tlck = txLock(tid, ip, mp, tlckXTREE); xtlck = (struct xtlock *) & tlck->lock; if (!(tlck->type & tlckTRUNCATE)) { xtlck->hwm.offset = le16_to_cpu(p->header. nextindex) - 1; tlck->type = tlckXTREE | tlckTRUNCATE; } } else { /* COMMIT_WMAP */ /* free child extents covered by parent */ xadlock.xdlist = &p->xad[index + 1]; xadlock.count = le16_to_cpu(p->header.nextindex) - index - 1; txFreeMap(ip, (struct maplock *) & xadlock, NULL, COMMIT_WMAP); } BT_MARK_DIRTY(mp, ip); p->header.nextindex = cpu_to_le16(index + 1); } XT_PUTPAGE(mp); goto getParent; } /* * child page was empty: */ nfreed += lengthXAD(&p->xad[index]); /* * During working map update, child page's tlock must be handled * before parent's. This is because the parent's tlock will cause * the child's disk space to be marked available in the wmap, so * it's important that the child page be released by that time. * * ToDo: tlocks should be on doubly-linked list, so we can * quickly remove it and add it to the end. */ /* * Move parent page's tlock to the end of the tid's tlock list */ if (log && mp->lid && (tblk->last != mp->lid) && lid_to_tlock(mp->lid)->tid) { lid_t lid = mp->lid; struct tlock *prev; tlck = lid_to_tlock(lid); if (tblk->next == lid) tblk->next = tlck->next; else { for (prev = lid_to_tlock(tblk->next); prev->next != lid; prev = lid_to_tlock(prev->next)) { assert(prev->next); } prev->next = tlck->next; } lid_to_tlock(tblk->last)->next = lid; tlck->next = 0; tblk->last = lid; } /* * parent page become empty: free the page */ if (index == XTENTRYSTART) { if (log) { /* COMMIT_PWMAP */ /* txCommit() with tlckFREE: * free child extents covered by parent; * invalidate parent if COMMIT_PWMAP; */ tlck = txLock(tid, ip, mp, tlckXTREE); xtlck = (struct xtlock *) & tlck->lock; xtlck->hwm.offset = le16_to_cpu(p->header.nextindex) - 1; tlck->type = tlckXTREE | tlckFREE; } else { /* COMMIT_WMAP */ /* free child extents covered by parent */ xadlock.xdlist = &p->xad[XTENTRYSTART]; xadlock.count = le16_to_cpu(p->header.nextindex) - XTENTRYSTART; txFreeMap(ip, (struct maplock *) & xadlock, NULL, COMMIT_WMAP); } BT_MARK_DIRTY(mp, ip); if (p->header.flag & BT_ROOT) { p->header.flag &= ~BT_INTERNAL; p->header.flag |= BT_LEAF; p->header.nextindex = cpu_to_le16(XTENTRYSTART); if (le16_to_cpu(p->header.maxentry) == XTROOTMAXSLOT) { /* * Shrink root down to allow inline * EA (otherwise fsck complains) */ p->header.maxentry = cpu_to_le16(XTROOTINITSLOT); JFS_IP(ip)->mode2 |= INLINEEA; } XT_PUTPAGE(mp); /* debug */ goto out; } else { if (log) { /* COMMIT_PWMAP */ /* page will be invalidated at tx completion */ XT_PUTPAGE(mp); } else { /* COMMIT_WMAP */ if (mp->lid) lid_to_tlock(mp->lid)->flag |= tlckFREELOCK; /* invalidate parent page */ discard_metapage(mp); } /* parent has become empty and freed: * go back up to its parent page */ /* freed = 1; */ goto getParent; } } /* * parent page still has entries for front region; */ else { /* try truncate region covered by preceding entry * (process backward) */ index--; /* go back down to the child page corresponding * to the entry */ goto getChild; } /* * internal page: go down to child page of current entry */ getChild: /* save current parent entry for the child page */ if (BT_STACK_FULL(&btstack)) { jfs_error(ip->i_sb, "stack overrun!\n"); XT_PUTPAGE(mp); return -EIO; } BT_PUSH(&btstack, bn, index); /* get child page */ xad = &p->xad[index]; bn = addressXAD(xad); /* * first access of each internal entry: */ /* release parent page */ XT_PUTPAGE(mp); /* process the child page */ goto getPage; out: /* * update file resource stat */ /* set size */ if (S_ISDIR(ip->i_mode) && !newsize) ip->i_size = 1; /* fsck hates zero-length directories */ else ip->i_size = newsize; /* update quota allocation to reflect freed blocks */ dquot_free_block(ip, nfreed); /* * free tlock of invalidated pages */ if (flag == COMMIT_WMAP) txFreelock(ip); return newsize; } /* * xtTruncate_pmap() * * function: * Perform truncate to zero length for deleted file, leaving the * xtree and working map untouched. This allows the file to * be accessed via open file handles, while the delete of the file * is committed to disk. * * parameter: * tid_t tid, * struct inode *ip, * s64 committed_size) * * return: new committed size * * note: * * To avoid deadlock by holding too many transaction locks, the * truncation may be broken up into multiple transactions. * The committed_size keeps track of part of the file has been * freed from the pmaps. */ s64 xtTruncate_pmap(tid_t tid, struct inode *ip, s64 committed_size) { s64 bn; struct btstack btstack; int cmp; int index; int locked_leaves = 0; struct metapage *mp; xtpage_t *p; struct btframe *parent; int rc; struct tblock *tblk; struct tlock *tlck = NULL; xad_t *xad; int xlen; s64 xoff; struct xtlock *xtlck = NULL; /* save object truncation type */ tblk = tid_to_tblock(tid); tblk->xflag |= COMMIT_PMAP; /* clear stack */ BT_CLR(&btstack); if (committed_size) { xoff = (committed_size >> JFS_SBI(ip->i_sb)->l2bsize) - 1; rc = xtSearch(ip, xoff, NULL, &cmp, &btstack, 0); if (rc) return rc; XT_GETSEARCH(ip, btstack.top, bn, mp, p, index); if (cmp != 0) { XT_PUTPAGE(mp); jfs_error(ip->i_sb, "did not find extent\n"); return -EIO; } } else { /* * start with root * * root resides in the inode */ bn = 0; /* * first access of each page: */ getPage: XT_GETPAGE(ip, bn, mp, PSIZE, p, rc); if (rc) return rc; /* process entries backward from last index */ index = le16_to_cpu(p->header.nextindex) - 1; if (p->header.flag & BT_INTERNAL) goto getChild; } /* * leaf page */ if (++locked_leaves > MAX_TRUNCATE_LEAVES) { /* * We need to limit the size of the transaction * to avoid exhausting pagecache & tlocks */ xad = &p->xad[index]; xoff = offsetXAD(xad); xlen = lengthXAD(xad); XT_PUTPAGE(mp); return (xoff + xlen) << JFS_SBI(ip->i_sb)->l2bsize; } tlck = txLock(tid, ip, mp, tlckXTREE); tlck->type = tlckXTREE | tlckFREE; xtlck = (struct xtlock *) & tlck->lock; xtlck->hwm.offset = index; XT_PUTPAGE(mp); /* * go back up to the parent page */ getParent: /* pop/restore parent entry for the current child page */ if ((parent = BT_POP(&btstack)) == NULL) /* current page must have been root */ goto out; /* get back the parent page */ bn = parent->bn; XT_GETPAGE(ip, bn, mp, PSIZE, p, rc); if (rc) return rc; index = parent->index; /* * parent page become empty: free the page */ if (index == XTENTRYSTART) { /* txCommit() with tlckFREE: * free child extents covered by parent; * invalidate parent if COMMIT_PWMAP; */ tlck = txLock(tid, ip, mp, tlckXTREE); xtlck = (struct xtlock *) & tlck->lock; xtlck->hwm.offset = le16_to_cpu(p->header.nextindex) - 1; tlck->type = tlckXTREE | tlckFREE; XT_PUTPAGE(mp); if (p->header.flag & BT_ROOT) { goto out; } else { goto getParent; } } /* * parent page still has entries for front region; */ else index--; /* * internal page: go down to child page of current entry */ getChild: /* save current parent entry for the child page */ if (BT_STACK_FULL(&btstack)) { jfs_error(ip->i_sb, "stack overrun!\n"); XT_PUTPAGE(mp); return -EIO; } BT_PUSH(&btstack, bn, index); /* get child page */ xad = &p->xad[index]; bn = addressXAD(xad); /* * first access of each internal entry: */ /* release parent page */ XT_PUTPAGE(mp); /* process the child page */ goto getPage; out: return 0; } #ifdef CONFIG_JFS_STATISTICS int jfs_xtstat_proc_show(struct seq_file *m, void *v) { seq_printf(m, "JFS Xtree statistics\n" "====================\n" "searches = %d\n" "fast searches = %d\n" "splits = %d\n", xtStat.search, xtStat.fastSearch, xtStat.split); return 0; } #endif |
| 1 1 1 1 11 11 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 11 11 11 11 1 1 1 1 1 1 1 1 1 1 1 1 11 11 1 11 11 11 11 10 10 2 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 57 57 120 119 119 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "bkey_buf.h" #include "btree_locking.h" #include "btree_update.h" #include "btree_update_interior.h" #include "btree_write_buffer.h" #include "disk_accounting.h" #include "error.h" #include "extents.h" #include "journal.h" #include "journal_io.h" #include "journal_reclaim.h" #include <linux/prefetch.h> #include <linux/sort.h> static int bch2_btree_write_buffer_journal_flush(struct journal *, struct journal_entry_pin *, u64); static int bch2_journal_keys_to_write_buffer(struct bch_fs *, struct journal_buf *); static inline bool __wb_key_ref_cmp(const struct wb_key_ref *l, const struct wb_key_ref *r) { return (cmp_int(l->hi, r->hi) ?: cmp_int(l->mi, r->mi) ?: cmp_int(l->lo, r->lo)) >= 0; } static inline bool wb_key_ref_cmp(const struct wb_key_ref *l, const struct wb_key_ref *r) { #ifdef CONFIG_X86_64 int cmp; asm("mov (%[l]), %%rax;" "sub (%[r]), %%rax;" "mov 8(%[l]), %%rax;" "sbb 8(%[r]), %%rax;" "mov 16(%[l]), %%rax;" "sbb 16(%[r]), %%rax;" : "=@ccae" (cmp) : [l] "r" (l), [r] "r" (r) : "rax", "cc"); EBUG_ON(cmp != __wb_key_ref_cmp(l, r)); return cmp; #else return __wb_key_ref_cmp(l, r); #endif } static int wb_key_seq_cmp(const void *_l, const void *_r) { const struct btree_write_buffered_key *l = _l; const struct btree_write_buffered_key *r = _r; return cmp_int(l->journal_seq, r->journal_seq); } /* Compare excluding idx, the low 24 bits: */ static inline bool wb_key_eq(const void *_l, const void *_r) { const struct wb_key_ref *l = _l; const struct wb_key_ref *r = _r; return !((l->hi ^ r->hi)| (l->mi ^ r->mi)| ((l->lo >> 24) ^ (r->lo >> 24))); } static noinline void wb_sort(struct wb_key_ref *base, size_t num) { size_t n = num, a = num / 2; if (!a) /* num < 2 || size == 0 */ return; for (;;) { size_t b, c, d; if (a) /* Building heap: sift down --a */ --a; else if (--n) /* Sorting: Extract root to --n */ swap(base[0], base[n]); else /* Sort complete */ break; /* * Sift element at "a" down into heap. This is the * "bottom-up" variant, which significantly reduces * calls to cmp_func(): we find the sift-down path all * the way to the leaves (one compare per level), then * backtrack to find where to insert the target element. * * Because elements tend to sift down close to the leaves, * this uses fewer compares than doing two per level * on the way down. (A bit more than half as many on * average, 3/4 worst-case.) */ for (b = a; c = 2*b + 1, (d = c + 1) < n;) b = wb_key_ref_cmp(base + c, base + d) ? c : d; if (d == n) /* Special case last leaf with no sibling */ b = c; /* Now backtrack from "b" to the correct location for "a" */ while (b != a && wb_key_ref_cmp(base + a, base + b)) b = (b - 1) / 2; c = b; /* Where "a" belongs */ while (b != a) { /* Shift it into place */ b = (b - 1) / 2; swap(base[b], base[c]); } } } static noinline int wb_flush_one_slowpath(struct btree_trans *trans, struct btree_iter *iter, struct btree_write_buffered_key *wb) { struct btree_path *path = btree_iter_path(trans, iter); bch2_btree_node_unlock_write(trans, path, path->l[0].b); trans->journal_res.seq = wb->journal_seq; return bch2_trans_update(trans, iter, &wb->k, BTREE_UPDATE_internal_snapshot_node) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc| BCH_TRANS_COMMIT_no_check_rw| BCH_TRANS_COMMIT_no_journal_res| BCH_TRANS_COMMIT_journal_reclaim); } static inline int wb_flush_one(struct btree_trans *trans, struct btree_iter *iter, struct btree_write_buffered_key *wb, bool *write_locked, bool *accounting_accumulated, size_t *fast) { struct btree_path *path; int ret; EBUG_ON(!wb->journal_seq); EBUG_ON(!trans->c->btree_write_buffer.flushing.pin.seq); EBUG_ON(trans->c->btree_write_buffer.flushing.pin.seq > wb->journal_seq); ret = bch2_btree_iter_traverse(iter); if (ret) return ret; if (!*accounting_accumulated && wb->k.k.type == KEY_TYPE_accounting) { struct bkey u; struct bkey_s_c k = bch2_btree_path_peek_slot_exact(btree_iter_path(trans, iter), &u); if (k.k->type == KEY_TYPE_accounting) bch2_accounting_accumulate(bkey_i_to_accounting(&wb->k), bkey_s_c_to_accounting(k)); } *accounting_accumulated = true; /* * We can't clone a path that has write locks: unshare it now, before * set_pos and traverse(): */ if (btree_iter_path(trans, iter)->ref > 1) iter->path = __bch2_btree_path_make_mut(trans, iter->path, true, _THIS_IP_); path = btree_iter_path(trans, iter); if (!*write_locked) { ret = bch2_btree_node_lock_write(trans, path, &path->l[0].b->c); if (ret) return ret; bch2_btree_node_prep_for_write(trans, path, path->l[0].b); *write_locked = true; } if (unlikely(!bch2_btree_node_insert_fits(path->l[0].b, wb->k.k.u64s))) { *write_locked = false; return wb_flush_one_slowpath(trans, iter, wb); } bch2_btree_insert_key_leaf(trans, path, &wb->k, wb->journal_seq); (*fast)++; return 0; } /* * Update a btree with a write buffered key using the journal seq of the * original write buffer insert. * * It is not safe to rejournal the key once it has been inserted into the write * buffer because that may break recovery ordering. For example, the key may * have already been modified in the active write buffer in a seq that comes * before the current transaction. If we were to journal this key again and * crash, recovery would process updates in the wrong order. */ static int btree_write_buffered_insert(struct btree_trans *trans, struct btree_write_buffered_key *wb) { struct btree_iter iter; int ret; bch2_trans_iter_init(trans, &iter, wb->btree, bkey_start_pos(&wb->k.k), BTREE_ITER_cached|BTREE_ITER_intent); trans->journal_res.seq = wb->journal_seq; ret = bch2_btree_iter_traverse(&iter) ?: bch2_trans_update(trans, &iter, &wb->k, BTREE_UPDATE_internal_snapshot_node); bch2_trans_iter_exit(trans, &iter); return ret; } static void move_keys_from_inc_to_flushing(struct btree_write_buffer *wb) { struct bch_fs *c = container_of(wb, struct bch_fs, btree_write_buffer); struct journal *j = &c->journal; if (!wb->inc.keys.nr) return; bch2_journal_pin_add(j, wb->inc.keys.data[0].journal_seq, &wb->flushing.pin, bch2_btree_write_buffer_journal_flush); darray_resize(&wb->flushing.keys, min_t(size_t, 1U << 20, wb->flushing.keys.nr + wb->inc.keys.nr)); darray_resize(&wb->sorted, wb->flushing.keys.size); if (!wb->flushing.keys.nr && wb->sorted.size >= wb->inc.keys.nr) { swap(wb->flushing.keys, wb->inc.keys); goto out; } size_t nr = min(darray_room(wb->flushing.keys), wb->sorted.size - wb->flushing.keys.nr); nr = min(nr, wb->inc.keys.nr); memcpy(&darray_top(wb->flushing.keys), wb->inc.keys.data, sizeof(wb->inc.keys.data[0]) * nr); memmove(wb->inc.keys.data, wb->inc.keys.data + nr, sizeof(wb->inc.keys.data[0]) * (wb->inc.keys.nr - nr)); wb->flushing.keys.nr += nr; wb->inc.keys.nr -= nr; out: if (!wb->inc.keys.nr) bch2_journal_pin_drop(j, &wb->inc.pin); else bch2_journal_pin_update(j, wb->inc.keys.data[0].journal_seq, &wb->inc.pin, bch2_btree_write_buffer_journal_flush); if (j->watermark) { spin_lock(&j->lock); bch2_journal_set_watermark(j); spin_unlock(&j->lock); } BUG_ON(wb->sorted.size < wb->flushing.keys.nr); } static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans) { struct bch_fs *c = trans->c; struct journal *j = &c->journal; struct btree_write_buffer *wb = &c->btree_write_buffer; struct btree_iter iter = { NULL }; size_t overwritten = 0, fast = 0, slowpath = 0, could_not_insert = 0; bool write_locked = false; bool accounting_replay_done = test_bit(BCH_FS_accounting_replay_done, &c->flags); int ret = 0; ret = bch2_journal_error(&c->journal); if (ret) return ret; bch2_trans_unlock(trans); bch2_trans_begin(trans); mutex_lock(&wb->inc.lock); move_keys_from_inc_to_flushing(wb); mutex_unlock(&wb->inc.lock); for (size_t i = 0; i < wb->flushing.keys.nr; i++) { wb->sorted.data[i].idx = i; wb->sorted.data[i].btree = wb->flushing.keys.data[i].btree; memcpy(&wb->sorted.data[i].pos, &wb->flushing.keys.data[i].k.k.p, sizeof(struct bpos)); } wb->sorted.nr = wb->flushing.keys.nr; /* * We first sort so that we can detect and skip redundant updates, and * then we attempt to flush in sorted btree order, as this is most * efficient. * * However, since we're not flushing in the order they appear in the * journal we won't be able to drop our journal pin until everything is * flushed - which means this could deadlock the journal if we weren't * passing BCH_TRANS_COMMIT_journal_reclaim. This causes the update to fail * if it would block taking a journal reservation. * * If that happens, simply skip the key so we can optimistically insert * as many keys as possible in the fast path. */ wb_sort(wb->sorted.data, wb->sorted.nr); darray_for_each(wb->sorted, i) { struct btree_write_buffered_key *k = &wb->flushing.keys.data[i->idx]; for (struct wb_key_ref *n = i + 1; n < min(i + 4, &darray_top(wb->sorted)); n++) prefetch(&wb->flushing.keys.data[n->idx]); BUG_ON(!k->journal_seq); if (!accounting_replay_done && k->k.k.type == KEY_TYPE_accounting) { slowpath++; continue; } if (i + 1 < &darray_top(wb->sorted) && wb_key_eq(i, i + 1)) { struct btree_write_buffered_key *n = &wb->flushing.keys.data[i[1].idx]; if (k->k.k.type == KEY_TYPE_accounting && n->k.k.type == KEY_TYPE_accounting) bch2_accounting_accumulate(bkey_i_to_accounting(&n->k), bkey_i_to_s_c_accounting(&k->k)); overwritten++; n->journal_seq = min_t(u64, n->journal_seq, k->journal_seq); k->journal_seq = 0; continue; } if (write_locked) { struct btree_path *path = btree_iter_path(trans, &iter); if (path->btree_id != i->btree || bpos_gt(k->k.k.p, path->l[0].b->key.k.p)) { bch2_btree_node_unlock_write(trans, path, path->l[0].b); write_locked = false; ret = lockrestart_do(trans, bch2_btree_iter_traverse(&iter) ?: bch2_foreground_maybe_merge(trans, iter.path, 0, BCH_WATERMARK_reclaim| BCH_TRANS_COMMIT_journal_reclaim| BCH_TRANS_COMMIT_no_check_rw| BCH_TRANS_COMMIT_no_enospc)); if (ret) goto err; } } if (!iter.path || iter.btree_id != k->btree) { bch2_trans_iter_exit(trans, &iter); bch2_trans_iter_init(trans, &iter, k->btree, k->k.k.p, BTREE_ITER_intent|BTREE_ITER_all_snapshots); } bch2_btree_iter_set_pos(&iter, k->k.k.p); btree_iter_path(trans, &iter)->preserve = false; bool accounting_accumulated = false; do { if (race_fault()) { ret = -BCH_ERR_journal_reclaim_would_deadlock; break; } ret = wb_flush_one(trans, &iter, k, &write_locked, &accounting_accumulated, &fast); if (!write_locked) bch2_trans_begin(trans); } while (bch2_err_matches(ret, BCH_ERR_transaction_restart)); if (!ret) { k->journal_seq = 0; } else if (ret == -BCH_ERR_journal_reclaim_would_deadlock) { slowpath++; ret = 0; } else break; } if (write_locked) { struct btree_path *path = btree_iter_path(trans, &iter); bch2_btree_node_unlock_write(trans, path, path->l[0].b); } bch2_trans_iter_exit(trans, &iter); if (ret) goto err; if (slowpath) { /* * Flush in the order they were present in the journal, so that * we can release journal pins: * The fastpath zapped the seq of keys that were successfully flushed so * we can skip those here. */ trace_and_count(c, write_buffer_flush_slowpath, trans, slowpath, wb->flushing.keys.nr); sort(wb->flushing.keys.data, wb->flushing.keys.nr, sizeof(wb->flushing.keys.data[0]), wb_key_seq_cmp, NULL); darray_for_each(wb->flushing.keys, i) { if (!i->journal_seq) continue; if (!accounting_replay_done && i->k.k.type == KEY_TYPE_accounting) { could_not_insert++; continue; } if (!could_not_insert) bch2_journal_pin_update(j, i->journal_seq, &wb->flushing.pin, bch2_btree_write_buffer_journal_flush); bch2_trans_begin(trans); ret = commit_do(trans, NULL, NULL, BCH_WATERMARK_reclaim| BCH_TRANS_COMMIT_journal_reclaim| BCH_TRANS_COMMIT_no_check_rw| BCH_TRANS_COMMIT_no_enospc| BCH_TRANS_COMMIT_no_journal_res , btree_write_buffered_insert(trans, i)); if (ret) goto err; i->journal_seq = 0; } /* * If journal replay hasn't finished with accounting keys we * can't flush accounting keys at all - condense them and leave * them for next time. * * Q: Can the write buffer overflow? * A Shouldn't be any actual risk. It's just new accounting * updates that the write buffer can't flush, and those are only * going to be generated by interior btree node updates as * journal replay has to split/rewrite nodes to make room for * its updates. * * And for those new acounting updates, updates to the same * counters get accumulated as they're flushed from the journal * to the write buffer - see the patch for eytzingcer tree * accumulated. So we could only overflow if the number of * distinct counters touched somehow was very large. */ if (could_not_insert) { struct btree_write_buffered_key *dst = wb->flushing.keys.data; darray_for_each(wb->flushing.keys, i) if (i->journal_seq) *dst++ = *i; wb->flushing.keys.nr = dst - wb->flushing.keys.data; } } err: if (ret || !could_not_insert) { bch2_journal_pin_drop(j, &wb->flushing.pin); wb->flushing.keys.nr = 0; } bch2_fs_fatal_err_on(ret, c, "%s", bch2_err_str(ret)); trace_write_buffer_flush(trans, wb->flushing.keys.nr, overwritten, fast, 0); return ret; } static int fetch_wb_keys_from_journal(struct bch_fs *c, u64 seq) { struct journal *j = &c->journal; struct journal_buf *buf; int ret = 0; while (!ret && (buf = bch2_next_write_buffer_flush_journal_buf(j, seq))) { ret = bch2_journal_keys_to_write_buffer(c, buf); mutex_unlock(&j->buf_lock); } return ret; } static int btree_write_buffer_flush_seq(struct btree_trans *trans, u64 seq, bool *did_work) { struct bch_fs *c = trans->c; struct btree_write_buffer *wb = &c->btree_write_buffer; int ret = 0, fetch_from_journal_err; do { bch2_trans_unlock(trans); fetch_from_journal_err = fetch_wb_keys_from_journal(c, seq); *did_work |= wb->inc.keys.nr || wb->flushing.keys.nr; /* * On memory allocation failure, bch2_btree_write_buffer_flush_locked() * is not guaranteed to empty wb->inc: */ mutex_lock(&wb->flushing.lock); ret = bch2_btree_write_buffer_flush_locked(trans); mutex_unlock(&wb->flushing.lock); } while (!ret && (fetch_from_journal_err || (wb->inc.pin.seq && wb->inc.pin.seq <= seq) || (wb->flushing.pin.seq && wb->flushing.pin.seq <= seq))); return ret; } static int bch2_btree_write_buffer_journal_flush(struct journal *j, struct journal_entry_pin *_pin, u64 seq) { struct bch_fs *c = container_of(j, struct bch_fs, journal); bool did_work = false; return bch2_trans_run(c, btree_write_buffer_flush_seq(trans, seq, &did_work)); } int bch2_btree_write_buffer_flush_sync(struct btree_trans *trans) { struct bch_fs *c = trans->c; bool did_work = false; trace_and_count(c, write_buffer_flush_sync, trans, _RET_IP_); return btree_write_buffer_flush_seq(trans, journal_cur_seq(&c->journal), &did_work); } /* * The write buffer requires flushing when going RO: keys in the journal for the * write buffer don't have a journal pin yet */ bool bch2_btree_write_buffer_flush_going_ro(struct bch_fs *c) { if (bch2_journal_error(&c->journal)) return false; bool did_work = false; bch2_trans_run(c, btree_write_buffer_flush_seq(trans, journal_cur_seq(&c->journal), &did_work)); return did_work; } int bch2_btree_write_buffer_flush_nocheck_rw(struct btree_trans *trans) { struct bch_fs *c = trans->c; struct btree_write_buffer *wb = &c->btree_write_buffer; int ret = 0; if (mutex_trylock(&wb->flushing.lock)) { ret = bch2_btree_write_buffer_flush_locked(trans); mutex_unlock(&wb->flushing.lock); } return ret; } int bch2_btree_write_buffer_tryflush(struct btree_trans *trans) { struct bch_fs *c = trans->c; if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_btree_write_buffer)) return -BCH_ERR_erofs_no_writes; int ret = bch2_btree_write_buffer_flush_nocheck_rw(trans); bch2_write_ref_put(c, BCH_WRITE_REF_btree_write_buffer); return ret; } /* * In check and repair code, when checking references to write buffer btrees we * need to issue a flush before we have a definitive error: this issues a flush * if this is a key we haven't yet checked. */ int bch2_btree_write_buffer_maybe_flush(struct btree_trans *trans, struct bkey_s_c referring_k, struct bkey_buf *last_flushed) { struct bch_fs *c = trans->c; struct bkey_buf tmp; int ret = 0; bch2_bkey_buf_init(&tmp); if (!bkey_and_val_eq(referring_k, bkey_i_to_s_c(last_flushed->k))) { bch2_bkey_buf_reassemble(&tmp, c, referring_k); if (bkey_is_btree_ptr(referring_k.k)) { bch2_trans_unlock(trans); bch2_btree_interior_updates_flush(c); } ret = bch2_btree_write_buffer_flush_sync(trans); if (ret) goto err; bch2_bkey_buf_copy(last_flushed, c, tmp.k); ret = -BCH_ERR_transaction_restart_write_buffer_flush; } err: bch2_bkey_buf_exit(&tmp, c); return ret; } static void bch2_btree_write_buffer_flush_work(struct work_struct *work) { struct bch_fs *c = container_of(work, struct bch_fs, btree_write_buffer.flush_work); struct btree_write_buffer *wb = &c->btree_write_buffer; int ret; mutex_lock(&wb->flushing.lock); do { ret = bch2_trans_run(c, bch2_btree_write_buffer_flush_locked(trans)); } while (!ret && bch2_btree_write_buffer_should_flush(c)); mutex_unlock(&wb->flushing.lock); bch2_write_ref_put(c, BCH_WRITE_REF_btree_write_buffer); } static void wb_accounting_sort(struct btree_write_buffer *wb) { eytzinger0_sort(wb->accounting.data, wb->accounting.nr, sizeof(wb->accounting.data[0]), wb_key_cmp, NULL); } int bch2_accounting_key_to_wb_slowpath(struct bch_fs *c, enum btree_id btree, struct bkey_i_accounting *k) { struct btree_write_buffer *wb = &c->btree_write_buffer; struct btree_write_buffered_key new = { .btree = btree }; bkey_copy(&new.k, &k->k_i); int ret = darray_push(&wb->accounting, new); if (ret) return ret; wb_accounting_sort(wb); return 0; } int bch2_journal_key_to_wb_slowpath(struct bch_fs *c, struct journal_keys_to_wb *dst, enum btree_id btree, struct bkey_i *k) { struct btree_write_buffer *wb = &c->btree_write_buffer; int ret; retry: ret = darray_make_room_gfp(&dst->wb->keys, 1, GFP_KERNEL); if (!ret && dst->wb == &wb->flushing) ret = darray_resize(&wb->sorted, wb->flushing.keys.size); if (unlikely(ret)) { if (dst->wb == &c->btree_write_buffer.flushing) { mutex_unlock(&dst->wb->lock); dst->wb = &c->btree_write_buffer.inc; bch2_journal_pin_add(&c->journal, dst->seq, &dst->wb->pin, bch2_btree_write_buffer_journal_flush); goto retry; } return ret; } dst->room = darray_room(dst->wb->keys); if (dst->wb == &wb->flushing) dst->room = min(dst->room, wb->sorted.size - wb->flushing.keys.nr); BUG_ON(!dst->room); BUG_ON(!dst->seq); struct btree_write_buffered_key *wb_k = &darray_top(dst->wb->keys); wb_k->journal_seq = dst->seq; wb_k->btree = btree; bkey_copy(&wb_k->k, k); dst->wb->keys.nr++; dst->room--; return 0; } void bch2_journal_keys_to_write_buffer_start(struct bch_fs *c, struct journal_keys_to_wb *dst, u64 seq) { struct btree_write_buffer *wb = &c->btree_write_buffer; if (mutex_trylock(&wb->flushing.lock)) { mutex_lock(&wb->inc.lock); move_keys_from_inc_to_flushing(wb); /* * Attempt to skip wb->inc, and add keys directly to * wb->flushing, saving us a copy later: */ if (!wb->inc.keys.nr) { dst->wb = &wb->flushing; } else { mutex_unlock(&wb->flushing.lock); dst->wb = &wb->inc; } } else { mutex_lock(&wb->inc.lock); dst->wb = &wb->inc; } dst->room = darray_room(dst->wb->keys); if (dst->wb == &wb->flushing) dst->room = min(dst->room, wb->sorted.size - wb->flushing.keys.nr); dst->seq = seq; bch2_journal_pin_add(&c->journal, seq, &dst->wb->pin, bch2_btree_write_buffer_journal_flush); darray_for_each(wb->accounting, i) memset(&i->k.v, 0, bkey_val_bytes(&i->k.k)); } int bch2_journal_keys_to_write_buffer_end(struct bch_fs *c, struct journal_keys_to_wb *dst) { struct btree_write_buffer *wb = &c->btree_write_buffer; unsigned live_accounting_keys = 0; int ret = 0; darray_for_each(wb->accounting, i) if (!bch2_accounting_key_is_zero(bkey_i_to_s_c_accounting(&i->k))) { i->journal_seq = dst->seq; live_accounting_keys++; ret = __bch2_journal_key_to_wb(c, dst, i->btree, &i->k); if (ret) break; } if (live_accounting_keys * 2 < wb->accounting.nr) { struct btree_write_buffered_key *dst = wb->accounting.data; darray_for_each(wb->accounting, src) if (!bch2_accounting_key_is_zero(bkey_i_to_s_c_accounting(&src->k))) *dst++ = *src; wb->accounting.nr = dst - wb->accounting.data; wb_accounting_sort(wb); } if (!dst->wb->keys.nr) bch2_journal_pin_drop(&c->journal, &dst->wb->pin); if (bch2_btree_write_buffer_should_flush(c) && __bch2_write_ref_tryget(c, BCH_WRITE_REF_btree_write_buffer) && !queue_work(system_unbound_wq, &c->btree_write_buffer.flush_work)) bch2_write_ref_put(c, BCH_WRITE_REF_btree_write_buffer); if (dst->wb == &wb->flushing) mutex_unlock(&wb->flushing.lock); mutex_unlock(&wb->inc.lock); return ret; } static int bch2_journal_keys_to_write_buffer(struct bch_fs *c, struct journal_buf *buf) { struct journal_keys_to_wb dst; int ret = 0; bch2_journal_keys_to_write_buffer_start(c, &dst, le64_to_cpu(buf->data->seq)); for_each_jset_entry_type(entry, buf->data, BCH_JSET_ENTRY_write_buffer_keys) { jset_entry_for_each_key(entry, k) { ret = bch2_journal_key_to_wb(c, &dst, entry->btree_id, k); if (ret) goto out; } entry->type = BCH_JSET_ENTRY_btree_keys; } spin_lock(&c->journal.lock); buf->need_flush_to_write_buffer = false; spin_unlock(&c->journal.lock); out: ret = bch2_journal_keys_to_write_buffer_end(c, &dst) ?: ret; return ret; } static int wb_keys_resize(struct btree_write_buffer_keys *wb, size_t new_size) { if (wb->keys.size >= new_size) return 0; if (!mutex_trylock(&wb->lock)) return -EINTR; int ret = darray_resize(&wb->keys, new_size); mutex_unlock(&wb->lock); return ret; } int bch2_btree_write_buffer_resize(struct bch_fs *c, size_t new_size) { struct btree_write_buffer *wb = &c->btree_write_buffer; return wb_keys_resize(&wb->flushing, new_size) ?: wb_keys_resize(&wb->inc, new_size); } void bch2_fs_btree_write_buffer_exit(struct bch_fs *c) { struct btree_write_buffer *wb = &c->btree_write_buffer; BUG_ON((wb->inc.keys.nr || wb->flushing.keys.nr) && !bch2_journal_error(&c->journal)); darray_exit(&wb->accounting); darray_exit(&wb->sorted); darray_exit(&wb->flushing.keys); darray_exit(&wb->inc.keys); } int bch2_fs_btree_write_buffer_init(struct bch_fs *c) { struct btree_write_buffer *wb = &c->btree_write_buffer; mutex_init(&wb->inc.lock); mutex_init(&wb->flushing.lock); INIT_WORK(&wb->flush_work, bch2_btree_write_buffer_flush_work); /* Will be resized by journal as needed: */ unsigned initial_size = 1 << 16; return darray_make_room(&wb->inc.keys, initial_size) ?: darray_make_room(&wb->flushing.keys, initial_size) ?: darray_make_room(&wb->sorted, initial_size); } |
| 5649 328 801 342 264 802 286 497 5618 5611 5611 110 5629 5435 5435 6 5 221 221 221 316 2004 1679 154 1 2005 833 1834 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Percpu refcounts: * (C) 2012 Google, Inc. * Author: Kent Overstreet <koverstreet@google.com> * * This implements a refcount with similar semantics to atomic_t - atomic_inc(), * atomic_dec_and_test() - but percpu. * * There's one important difference between percpu refs and normal atomic_t * refcounts; you have to keep track of your initial refcount, and then when you * start shutting down you call percpu_ref_kill() _before_ dropping the initial * refcount. * * The refcount will have a range of 0 to ((1U << 31) - 1), i.e. one bit less * than an atomic_t - this is because of the way shutdown works, see * percpu_ref_kill()/PERCPU_COUNT_BIAS. * * Before you call percpu_ref_kill(), percpu_ref_put() does not check for the * refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill() * puts the ref back in single atomic_t mode, collecting the per cpu refs and * issuing the appropriate barriers, and then marks the ref as shutting down so * that percpu_ref_put() will check for the ref hitting 0. After it returns, * it's safe to drop the initial ref. * * USAGE: * * See fs/aio.c for some example usage; it's used there for struct kioctx, which * is created when userspaces calls io_setup(), and destroyed when userspace * calls io_destroy() or the process exits. * * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it * removes the kioctx from the proccess's table of kioctxs and kills percpu_ref. * After that, there can't be any new users of the kioctx (from lookup_ioctx()) * and it's then safe to drop the initial ref with percpu_ref_put(). * * Note that the free path, free_ioctx(), needs to go through explicit call_rcu() * to synchronize with RCU protected lookup_ioctx(). percpu_ref operations don't * imply RCU grace periods of any kind and if a user wants to combine percpu_ref * with RCU protection, it must be done explicitly. * * Code that does a two stage shutdown like this often needs some kind of * explicit synchronization to ensure the initial refcount can only be dropped * once - percpu_ref_kill() does this for you, it returns true once and false if * someone else already called it. The aio code uses it this way, but it's not * necessary if the code has some other mechanism to synchronize teardown. * around. */ #ifndef _LINUX_PERCPU_REFCOUNT_H #define _LINUX_PERCPU_REFCOUNT_H #include <linux/atomic.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/types.h> #include <linux/gfp.h> struct percpu_ref; typedef void (percpu_ref_func_t)(struct percpu_ref *); /* flags set in the lower bits of percpu_ref->percpu_count_ptr */ enum { __PERCPU_REF_ATOMIC = 1LU << 0, /* operating in atomic mode */ __PERCPU_REF_DEAD = 1LU << 1, /* (being) killed */ __PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD, __PERCPU_REF_FLAG_BITS = 2, }; /* @flags for percpu_ref_init() */ enum { /* * Start w/ ref == 1 in atomic mode. Can be switched to percpu * operation using percpu_ref_switch_to_percpu(). If initialized * with this flag, the ref will stay in atomic mode until * percpu_ref_switch_to_percpu() is invoked on it. * Implies ALLOW_REINIT. */ PERCPU_REF_INIT_ATOMIC = 1 << 0, /* * Start dead w/ ref == 0 in atomic mode. Must be revived with * percpu_ref_reinit() before used. Implies INIT_ATOMIC and * ALLOW_REINIT. */ PERCPU_REF_INIT_DEAD = 1 << 1, /* * Allow switching from atomic mode to percpu mode. */ PERCPU_REF_ALLOW_REINIT = 1 << 2, }; struct percpu_ref_data { atomic_long_t count; percpu_ref_func_t *release; percpu_ref_func_t *confirm_switch; bool force_atomic:1; bool allow_reinit:1; struct rcu_head rcu; struct percpu_ref *ref; }; struct percpu_ref { /* * The low bit of the pointer indicates whether the ref is in percpu * mode; if set, then get/put will manipulate the atomic_t. */ unsigned long percpu_count_ptr; /* * 'percpu_ref' is often embedded into user structure, and only * 'percpu_count_ptr' is required in fast path, move other fields * into 'percpu_ref_data', so we can reduce memory footprint in * fast path. */ struct percpu_ref_data *data; }; int __must_check percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, unsigned int flags, gfp_t gfp); void percpu_ref_exit(struct percpu_ref *ref); void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch); void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref); void percpu_ref_switch_to_percpu(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); void percpu_ref_resurrect(struct percpu_ref *ref); void percpu_ref_reinit(struct percpu_ref *ref); bool percpu_ref_is_zero(struct percpu_ref *ref); /** * percpu_ref_kill - drop the initial ref * @ref: percpu_ref to kill * * Must be used to drop the initial ref on a percpu refcount; must be called * precisely once before shutdown. * * Switches @ref into atomic mode before gathering up the percpu counters * and dropping the initial ref. * * There are no implied RCU grace periods between kill and release. */ static inline void percpu_ref_kill(struct percpu_ref *ref) { percpu_ref_kill_and_confirm(ref, NULL); } /* * Internal helper. Don't use outside percpu-refcount proper. The * function doesn't return the pointer and let the caller test it for NULL * because doing so forces the compiler to generate two conditional * branches as it can't assume that @ref->percpu_count is not NULL. */ static inline bool __ref_is_percpu(struct percpu_ref *ref, unsigned long __percpu **percpu_countp) { unsigned long percpu_ptr; /* * The value of @ref->percpu_count_ptr is tested for * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then * used as a pointer. If the compiler generates a separate fetch * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in * between contaminating the pointer value, meaning that * READ_ONCE() is required when fetching it. * * The dependency ordering from the READ_ONCE() pairs * with smp_store_release() in __percpu_ref_switch_to_percpu(). */ percpu_ptr = READ_ONCE(ref->percpu_count_ptr); /* * Theoretically, the following could test just ATOMIC; however, * then we'd have to mask off DEAD separately as DEAD may be * visible without ATOMIC if we race with percpu_ref_kill(). DEAD * implies ATOMIC anyway. Test them together. */ if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD)) return false; *percpu_countp = (unsigned long __percpu *)percpu_ptr; return true; } /** * percpu_ref_get_many - increment a percpu refcount * @ref: percpu_ref to get * @nr: number of references to get * * Analogous to atomic_long_add(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_add(*percpu_count, nr); else atomic_long_add(nr, &ref->data->count); rcu_read_unlock(); } /** * percpu_ref_get - increment a percpu refcount * @ref: percpu_ref to get * * Analogous to atomic_long_inc(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get(struct percpu_ref *ref) { percpu_ref_get_many(ref, 1); } /** * percpu_ref_tryget_many - try to increment a percpu refcount * @ref: percpu_ref to try-get * @nr: number of references to get * * Increment a percpu refcount by @nr unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; bool ret; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_add(*percpu_count, nr); ret = true; } else { ret = atomic_long_add_unless(&ref->data->count, nr, 0); } rcu_read_unlock(); return ret; } /** * percpu_ref_tryget - try to increment a percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget(struct percpu_ref *ref) { return percpu_ref_tryget_many(ref, 1); } /** * percpu_ref_tryget_live_rcu - same as percpu_ref_tryget_live() but the * caller is responsible for taking RCU. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_live_rcu(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; bool ret = false; WARN_ON_ONCE(!rcu_read_lock_held()); if (likely(__ref_is_percpu(ref, &percpu_count))) { this_cpu_inc(*percpu_count); ret = true; } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { ret = atomic_long_inc_not_zero(&ref->data->count); } return ret; } /** * percpu_ref_tryget_live - try to increment a live percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless it has already been killed. Returns * %true on success; %false on failure. * * Completion of percpu_ref_kill() in itself doesn't guarantee that this * function will fail. For such guarantee, percpu_ref_kill_and_confirm() * should be used. After the confirm_kill callback is invoked, it's * guaranteed that no new reference will be given out by * percpu_ref_tryget_live(). * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) { bool ret = false; rcu_read_lock(); ret = percpu_ref_tryget_live_rcu(ref); rcu_read_unlock(); return ret; } /** * percpu_ref_put_many - decrement a percpu refcount * @ref: percpu_ref to put * @nr: number of references to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_sub(*percpu_count, nr); else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count))) ref->data->release(ref); rcu_read_unlock(); } /** * percpu_ref_put - decrement a percpu refcount * @ref: percpu_ref to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put(struct percpu_ref *ref) { percpu_ref_put_many(ref, 1); } /** * percpu_ref_is_dying - test whether a percpu refcount is dying or dead * @ref: percpu_ref to test * * Returns %true if @ref is dying or dead. * * This function is safe to call as long as @ref is between init and exit * and the caller is responsible for synchronizing against state changes. */ static inline bool percpu_ref_is_dying(struct percpu_ref *ref) { return ref->percpu_count_ptr & __PERCPU_REF_DEAD; } #endif |
| 582 8397 4317 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Sleepable Read-Copy Update mechanism for mutual exclusion * * Copyright (C) IBM Corporation, 2006 * Copyright (C) Fujitsu, 2012 * * Author: Paul McKenney <paulmck@linux.ibm.com> * Lai Jiangshan <laijs@cn.fujitsu.com> * * For detailed explanation of Read-Copy Update mechanism see - * Documentation/RCU/ *.txt * */ #ifndef _LINUX_SRCU_H #define _LINUX_SRCU_H #include <linux/mutex.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/rcu_segcblist.h> struct srcu_struct; #ifdef CONFIG_DEBUG_LOCK_ALLOC int __init_srcu_struct(struct srcu_struct *ssp, const char *name, struct lock_class_key *key); #define init_srcu_struct(ssp) \ ({ \ static struct lock_class_key __srcu_key; \ \ __init_srcu_struct((ssp), #ssp, &__srcu_key); \ }) #define __SRCU_DEP_MAP_INIT(srcu_name) .dep_map = { .name = #srcu_name }, #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ int init_srcu_struct(struct srcu_struct *ssp); #define __SRCU_DEP_MAP_INIT(srcu_name) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_TINY_SRCU #include <linux/srcutiny.h> #elif defined(CONFIG_TREE_SRCU) #include <linux/srcutree.h> #else #error "Unknown SRCU implementation specified to kernel configuration" #endif void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void (*func)(struct rcu_head *head)); void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); #ifdef CONFIG_TINY_SRCU #define __srcu_read_lock_lite __srcu_read_lock #define __srcu_read_unlock_lite __srcu_read_unlock #else // #ifdef CONFIG_TINY_SRCU int __srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) __releases(ssp); #endif // #else // #ifdef CONFIG_TINY_SRCU void synchronize_srcu(struct srcu_struct *ssp); #define SRCU_GET_STATE_COMPLETED 0x1 /** * get_completed_synchronize_srcu - Return a pre-completed polled state cookie * * Returns a value that poll_state_synchronize_srcu() will always treat * as a cookie whose grace period has already completed. */ static inline unsigned long get_completed_synchronize_srcu(void) { return SRCU_GET_STATE_COMPLETED; } unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); // Maximum number of unsigned long values corresponding to // not-yet-completed SRCU grace periods. #define NUM_ACTIVE_SRCU_POLL_OLDSTATE 2 /** * same_state_synchronize_srcu - Are two old-state values identical? * @oldstate1: First old-state value. * @oldstate2: Second old-state value. * * The two old-state values must have been obtained from either * get_state_synchronize_srcu(), start_poll_synchronize_srcu(), or * get_completed_synchronize_srcu(). Returns @true if the two values are * identical and @false otherwise. This allows structures whose lifetimes * are tracked by old-state values to push these values to a list header, * allowing those structures to be slightly smaller. */ static inline bool same_state_synchronize_srcu(unsigned long oldstate1, unsigned long oldstate2) { return oldstate1 == oldstate2; } #ifdef CONFIG_NEED_SRCU_NMI_SAFE int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp); #else static inline int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) { return __srcu_read_lock(ssp); } static inline void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) { __srcu_read_unlock(ssp, idx); } #endif /* CONFIG_NEED_SRCU_NMI_SAFE */ void srcu_init(void); #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * srcu_read_lock_held - might we be in SRCU read-side critical section? * @ssp: The srcu_struct structure to check * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, * this assumes we are in an SRCU read-side critical section unless it can * prove otherwise. * * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. * * Note that SRCU is based on its own statemachine and it doesn't * relies on normal RCU, it can be called from the CPU which * is in the idle loop from an RCU point of view or offline. */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { if (!debug_lockdep_rcu_enabled()) return 1; return lock_is_held(&ssp->dep_map); } /* * Annotations provide deadlock detection for SRCU. * * Similar to other lockdep annotations, except there is an additional * srcu_lock_sync(), which is basically an empty *write*-side critical section, * see lock_sync() for more information. */ /* Annotates a srcu_read_lock() */ static inline void srcu_lock_acquire(struct lockdep_map *map) { lock_map_acquire_read(map); } /* Annotates a srcu_read_lock() */ static inline void srcu_lock_release(struct lockdep_map *map) { lock_map_release(map); } /* Annotates a synchronize_srcu() */ static inline void srcu_lock_sync(struct lockdep_map *map) { lock_map_sync(map); } #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { return 1; } #define srcu_lock_acquire(m) do { } while (0) #define srcu_lock_release(m) do { } while (0) #define srcu_lock_sync(m) do { } while (0) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /** * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * @c: condition to check for update-side use * * If PROVE_RCU is enabled, invoking this outside of an RCU read-side * critical section will result in an RCU-lockdep splat, unless @c evaluates * to 1. The @c argument will normally be a logical expression containing * lockdep_is_held() calls. */ #define srcu_dereference_check(p, ssp, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || srcu_read_lock_held(ssp), __rcu) /** * srcu_dereference - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * * Makes rcu_dereference_check() do the dirty work. If PROVE_RCU * is enabled, invoking this outside of an RCU read-side critical * section will result in an RCU-lockdep splat. */ #define srcu_dereference(p, ssp) srcu_dereference_check((p), (ssp), 0) /** * srcu_dereference_notrace - no tracing and no lockdep calls from here * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. */ #define srcu_dereference_notrace(p, ssp) srcu_dereference_check((p), (ssp), 1) /** * srcu_read_lock - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section. Note that SRCU read-side * critical sections may be nested. However, it is illegal to * call anything that waits on an SRCU grace period for the same * srcu_struct, whether directly or indirectly. Please note that * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). * * The return value from srcu_read_lock() must be passed unaltered * to the matching srcu_read_unlock(). Note that srcu_read_lock() and * the matching srcu_read_unlock() must occur in the same context, for * example, it is illegal to invoke srcu_read_unlock() in an irq handler * if the matching srcu_read_lock() was invoked in process context. Or, * for that matter to invoke srcu_read_unlock() from one task and the * matching srcu_read_lock() from another. */ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); srcu_lock_acquire(&ssp->dep_map); return retval; } /** * srcu_read_lock_lite - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section, but for a light-weight * smp_mb()-free reader. See srcu_read_lock() for more information. * * If srcu_read_lock_lite() is ever used on an srcu_struct structure, * then none of the other flavors may be used, whether before, during, * or after. Note that grace-period auto-expediting is disabled for _lite * srcu_struct structures because auto-expedited grace periods invoke * synchronize_rcu_expedited(), IPIs and all. * * Note that srcu_read_lock_lite() can be invoked only from those contexts * where RCU is watching, that is, from contexts where it would be legal * to invoke rcu_read_lock(). Otherwise, lockdep will complain. */ static inline int srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor_lite(ssp); retval = __srcu_read_lock_lite(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; } /** * srcu_read_lock_nmisafe - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section, but in an NMI-safe manner. * See srcu_read_lock() for more information. * * If srcu_read_lock_nmisafe() is ever used on an srcu_struct structure, * then none of the other flavors may be used, whether before, during, * or after. */ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); retval = __srcu_read_lock_nmisafe(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; } /* Used by tracing, cannot be traced and cannot invoke lockdep. */ static inline notrace int srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); return retval; } /** * srcu_down_read - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter a semaphore-like SRCU read-side critical section. Note that * SRCU read-side critical sections may be nested. However, it is * illegal to call anything that waits on an SRCU grace period for the * same srcu_struct, whether directly or indirectly. Please note that * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). But if you want lockdep to help you * keep this stuff straight, you should instead use srcu_read_lock(). * * The semaphore-like nature of srcu_down_read() means that the matching * srcu_up_read() can be invoked from some other context, for example, * from some other task or from an irq handler. However, neither * srcu_down_read() nor srcu_up_read() may be invoked from an NMI handler. * * Calls to srcu_down_read() may be nested, similar to the manner in * which calls to down_read() may be nested. */ static inline int srcu_down_read(struct srcu_struct *ssp) __acquires(ssp) { WARN_ON_ONCE(in_nmi()); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); return __srcu_read_lock(ssp); } /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section. */ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); srcu_lock_release(&ssp->dep_map); __srcu_read_unlock(ssp, idx); } /** * srcu_read_unlock_lite - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit a light-weight SRCU read-side critical section. */ static inline void srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_LITE); srcu_lock_release(&ssp->dep_map); __srcu_read_unlock_lite(ssp, idx); } /** * srcu_read_unlock_nmisafe - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section, but in an NMI-safe manner. */ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); rcu_lock_release(&ssp->dep_map); __srcu_read_unlock_nmisafe(ssp, idx); } /* Used by tracing, cannot be traced and cannot call lockdep. */ static inline notrace void srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp) { srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } /** * srcu_up_read - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section, but not necessarily from * the same context as the maching srcu_down_read(). */ static inline void srcu_up_read(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); WARN_ON_ONCE(in_nmi()); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } /** * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock * * Converts the preceding srcu_read_unlock into a two-way memory barrier. * * Call this after srcu_read_unlock, to guarantee that all memory operations * that occur after smp_mb__after_srcu_read_unlock will appear to happen after * the preceding srcu_read_unlock. */ static inline void smp_mb__after_srcu_read_unlock(void) { /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } /** * smp_mb__after_srcu_read_lock - ensure full ordering after srcu_read_lock * * Converts the preceding srcu_read_lock into a two-way memory barrier. * * Call this after srcu_read_lock, to guarantee that all memory operations * that occur after smp_mb__after_srcu_read_lock will appear to happen after * the preceding srcu_read_lock. */ static inline void smp_mb__after_srcu_read_lock(void) { /* __srcu_read_lock has smp_mb() internally so nothing to do here. */ } DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct, _T->idx = srcu_read_lock(_T->lock), srcu_read_unlock(_T->lock, _T->idx), int idx) #endif |
| 1120 1494 186 1428 773 239 1494 1118 5 17 18 17 154 3 2 46 61 459 566 460 113 116 113 16 243 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HIGHMEM_H #define _LINUX_HIGHMEM_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/bug.h> #include <linux/cacheflush.h> #include <linux/kmsan.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include "highmem-internal.h" /** * kmap - Map a page for long term usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can only be invoked from preemptible task context because on 32bit * systems with CONFIG_HIGHMEM enabled this function might sleep. * * For systems with CONFIG_HIGHMEM=n and for pages in the low memory area * this returns the virtual address of the direct kernel mapping. * * The returned virtual address is globally visible and valid up to the * point where it is unmapped via kunmap(). The pointer can be handed to * other contexts. * * For highmem pages on 32bit systems this can be slow as the mapping space * is limited and protected by a global lock. In case that there is no * mapping slot available the function blocks until a slot is released via * kunmap(). */ static inline void *kmap(struct page *page); /** * kunmap - Unmap the virtual address mapped by kmap() * @page: Pointer to the page which was mapped by kmap() * * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of * pages in the low memory area. */ static inline void kunmap(struct page *page); /** * kmap_to_page - Get the page for a kmap'ed address * @addr: The address to look up * * Returns: The page which is mapped to @addr. */ static inline struct page *kmap_to_page(void *addr); /** * kmap_flush_unused - Flush all unused kmap mappings in order to * remove stray mappings */ static inline void kmap_flush_unused(void); /** * kmap_local_page - Map a page for temporary usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can be invoked from any context, including interrupts. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation: * * addr1 = kmap_local_page(page1); * addr2 = kmap_local_page(page2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While kmap_local_page() is significantly faster than kmap() for the highmem * case it comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_page() can rely on this side effect. */ static inline void *kmap_local_page(struct page *page); /** * kmap_local_folio - Map a page in this folio for temporary usage * @folio: The folio containing the page. * @offset: The byte offset within the folio which identifies the page. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation:: * * addr1 = kmap_local_folio(folio1, offset1); * addr2 = kmap_local_folio(folio2, offset2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While it is significantly faster than kmap() for the highmem case it * comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_folio() can rely on this side effect. * * Context: Can be invoked from any context. * Return: The virtual address of @offset. */ static inline void *kmap_local_folio(struct folio *folio, size_t offset); /** * kmap_atomic - Atomically map a page for temporary usage - Deprecated! * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * In fact a wrapper around kmap_local_page() which also disables pagefaults * and, depending on PREEMPT_RT configuration, also CPU migration and * preemption. Therefore users should not count on the latter two side effects. * * Mappings should always be released by kunmap_atomic(). * * Do not use in new code. Use kmap_local_page() instead. * * It is used in atomic context when code wants to access the contents of a * page that might be allocated from high memory (see __GFP_HIGHMEM), for * example a page in the pagecache. The API has two functions, and they * can be used in a manner similar to the following:: * * // Find the page of interest. * struct page *page = find_get_page(mapping, offset); * * // Gain access to the contents of that page. * void *vaddr = kmap_atomic(page); * * // Do something to the contents of that page. * memset(vaddr, 0, PAGE_SIZE); * * // Unmap that page. * kunmap_atomic(vaddr); * * Note that the kunmap_atomic() call takes the result of the kmap_atomic() * call, not the argument. * * If you need to map two pages because you want to copy from one page to * another you need to keep the kmap_atomic calls strictly nested, like: * * vaddr1 = kmap_atomic(page1); * vaddr2 = kmap_atomic(page2); * * memcpy(vaddr1, vaddr2, PAGE_SIZE); * * kunmap_atomic(vaddr2); * kunmap_atomic(vaddr1); */ static inline void *kmap_atomic(struct page *page); /* Highmem related interfaces for management code */ static inline unsigned long nr_free_highpages(void); static inline unsigned long totalhigh_pages(void); #ifndef ARCH_HAS_FLUSH_ANON_PAGE static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) { } #endif #ifndef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE static inline void flush_kernel_vmap_range(void *vaddr, int size) { } static inline void invalidate_kernel_vmap_range(void *vaddr, int size) { } #endif /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */ #ifndef clear_user_highpage static inline void clear_user_highpage(struct page *page, unsigned long vaddr) { void *addr = kmap_local_page(page); clear_user_page(addr, vaddr, page); kunmap_local(addr); } #endif #ifndef vma_alloc_zeroed_movable_folio /** * vma_alloc_zeroed_movable_folio - Allocate a zeroed page for a VMA. * @vma: The VMA the page is to be allocated for. * @vaddr: The virtual address the page will be inserted into. * * This function will allocate a page suitable for inserting into this * VMA at this virtual address. It may be allocated from highmem or * the movable zone. An architecture may provide its own implementation. * * Return: A folio containing one allocated and zeroed page or NULL if * we are out of memory. */ static inline struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { struct folio *folio; folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr, false); if (folio) clear_user_highpage(&folio->page, vaddr); return folio; } #endif static inline void clear_highpage(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kaddr); kunmap_local(kaddr); } static inline void clear_highpage_kasan_tagged(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kasan_reset_tag(kaddr)); kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE static inline void tag_clear_highpage(struct page *page) { } #endif /* * If we pass in a base or tail page, we can zero up to PAGE_SIZE. * If we pass in a head page, we can zero up to the size of the compound page. */ #ifdef CONFIG_HIGHMEM void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2); #else static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { void *kaddr = kmap_local_page(page); unsigned int i; BUG_ON(end1 > page_size(page) || end2 > page_size(page)); if (end1 > start1) memset(kaddr + start1, 0, end1 - start1); if (end2 > start2) memset(kaddr + start2, 0, end2 - start2); kunmap_local(kaddr); for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } #endif static inline void zero_user_segment(struct page *page, unsigned start, unsigned end) { zero_user_segments(page, start, end, 0, 0); } static inline void zero_user(struct page *page, unsigned start, unsigned size) { zero_user_segments(page, start, start + size, 0, 0); } #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE static inline void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifndef __HAVE_ARCH_COPY_HIGHPAGE static inline void copy_highpage(struct page *to, struct page *from) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_page(vto, vfrom); kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifdef copy_mc_to_kernel /* * If architecture supports machine check exception handling, define the * #MC versions of copy_user_highpage and copy_highpage. They copy a memory * page with #MC in source page (@from) handled, and return the number * of bytes not copied if there was a #MC, otherwise 0 for success. */ static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); if (ret) memory_failure_queue(page_to_pfn(from), 0); return ret; } static inline int copy_mc_highpage(struct page *to, struct page *from) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); if (ret) memory_failure_queue(page_to_pfn(from), 0); return ret; } #else static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { copy_user_highpage(to, from, vaddr, vma); return 0; } static inline int copy_mc_highpage(struct page *to, struct page *from) { copy_highpage(to, from); return 0; } #endif static inline void memcpy_page(struct page *dst_page, size_t dst_off, struct page *src_page, size_t src_off, size_t len) { char *dst = kmap_local_page(dst_page); char *src = kmap_local_page(src_page); VM_BUG_ON(dst_off + len > PAGE_SIZE || src_off + len > PAGE_SIZE); memcpy(dst + dst_off, src + src_off, len); kunmap_local(src); kunmap_local(dst); } static inline void memset_page(struct page *page, size_t offset, int val, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, val, len); kunmap_local(addr); } static inline void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) { char *from = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to, from + offset, len); kunmap_local(from); } static inline void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len) { char *to = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to + offset, from, len); flush_dcache_page(page); kunmap_local(to); } static inline void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, 0, len); flush_dcache_page(page); kunmap_local(addr); } /** * memcpy_from_folio - Copy a range of bytes from a folio. * @to: The memory to copy to. * @folio: The folio to read from. * @offset: The first byte in the folio to read. * @len: The number of bytes to copy. */ static inline void memcpy_from_folio(char *to, struct folio *folio, size_t offset, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { const char *from = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_highmem(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(from); to += chunk; offset += chunk; len -= chunk; } while (len > 0); } /** * memcpy_to_folio - Copy a range of bytes to a folio. * @folio: The folio to write to. * @offset: The first byte in the folio to store to. * @from: The memory to copy from. * @len: The number of bytes to copy. */ static inline void memcpy_to_folio(struct folio *folio, size_t offset, const char *from, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { char *to = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_highmem(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(to); from += chunk; offset += chunk; len -= chunk; } while (len > 0); flush_dcache_folio(folio); } /** * folio_zero_tail - Zero the tail of a folio. * @folio: The folio to zero. * @offset: The byte offset in the folio to start zeroing at. * @kaddr: The address the folio is currently mapped to. * * If you have already used kmap_local_folio() to map a folio, written * some data to it and now need to zero the end of the folio (and flush * the dcache), you can use this function. If you do not have the * folio kmapped (eg the folio has been partially populated by DMA), * use folio_zero_range() or folio_zero_segment() instead. * * Return: An address which can be passed to kunmap_local(). */ static inline __must_check void *folio_zero_tail(struct folio *folio, size_t offset, void *kaddr) { size_t len = folio_size(folio) - offset; if (folio_test_highmem(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memset(kaddr, 0, max); kunmap_local(kaddr); len -= max; offset += max; max = PAGE_SIZE; kaddr = kmap_local_folio(folio, offset); } } memset(kaddr, 0, len); flush_dcache_folio(folio); return kaddr; } /** * folio_fill_tail - Copy some data to a folio and pad with zeroes. * @folio: The destination folio. * @offset: The offset into @folio at which to start copying. * @from: The data to copy. * @len: How many bytes of data to copy. * * This function is most useful for filesystems which support inline data. * When they want to copy data from the inode into the page cache, this * function does everything for them. It supports large folios even on * HIGHMEM configurations. */ static inline void folio_fill_tail(struct folio *folio, size_t offset, const char *from, size_t len) { char *to = kmap_local_folio(folio, offset); VM_BUG_ON(offset + len > folio_size(folio)); if (folio_test_highmem(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memcpy(to, from, max); kunmap_local(to); len -= max; from += max; offset += max; max = PAGE_SIZE; to = kmap_local_folio(folio, offset); } } memcpy(to, from, len); to = folio_zero_tail(folio, offset + len, to + len); kunmap_local(to); } /** * memcpy_from_file_folio - Copy some bytes from a file folio. * @to: The destination buffer. * @folio: The folio to copy from. * @pos: The position in the file. * @len: The maximum number of bytes to copy. * * Copy up to @len bytes from this folio. This may be limited by PAGE_SIZE * if the folio comes from HIGHMEM, and by the size of the folio. * * Return: The number of bytes copied from the folio. */ static inline size_t memcpy_from_file_folio(char *to, struct folio *folio, loff_t pos, size_t len) { size_t offset = offset_in_folio(folio, pos); char *from = kmap_local_folio(folio, offset); if (folio_test_highmem(folio)) { offset = offset_in_page(offset); len = min_t(size_t, len, PAGE_SIZE - offset); } else len = min(len, folio_size(folio) - offset); memcpy(to, from, len); kunmap_local(from); return len; } /** * folio_zero_segments() - Zero two byte ranges in a folio. * @folio: The folio to write to. * @start1: The first byte to zero. * @xend1: One more than the last byte in the first range. * @start2: The first byte to zero in the second range. * @xend2: One more than the last byte in the second range. */ static inline void folio_zero_segments(struct folio *folio, size_t start1, size_t xend1, size_t start2, size_t xend2) { zero_user_segments(&folio->page, start1, xend1, start2, xend2); } /** * folio_zero_segment() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @xend: One more than the last byte to zero. */ static inline void folio_zero_segment(struct folio *folio, size_t start, size_t xend) { zero_user_segments(&folio->page, start, xend, 0, 0); } /** * folio_zero_range() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @length: The number of bytes to zero. */ static inline void folio_zero_range(struct folio *folio, size_t start, size_t length) { zero_user_segments(&folio->page, start, start + length, 0, 0); } /** * folio_release_kmap - Unmap a folio and drop a refcount. * @folio: The folio to release. * @addr: The address previously returned by a call to kmap_local_folio(). * * It is common, eg in directory handling to kmap a folio. This function * unmaps the folio and drops the refcount that was being held to keep the * folio alive while we accessed it. */ static inline void folio_release_kmap(struct folio *folio, void *addr) { kunmap_local(addr); folio_put(folio); } static inline void unmap_and_put_page(struct page *page, void *addr) { folio_release_kmap(page_folio(page), addr); } #endif /* _LINUX_HIGHMEM_H */ |
| 5 5 5 2 172 172 96 172 172 171 176 57 3 58 58 58 58 58 114 112 114 112 11 114 113 1 114 19 114 114 114 4 2 4 4 4 4 11 11 11 11 1 3 7 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 /* * fs/proc_namespace.c - handling of /proc/<pid>/{mounts,mountinfo,mountstats} * * In fact, that's a piece of procfs; it's *almost* isolated from * the rest of fs/proc, but has rather close relationships with * fs/namespace.c, thus here instead of fs/proc * */ #include <linux/mnt_namespace.h> #include <linux/nsproxy.h> #include <linux/security.h> #include <linux/fs_struct.h> #include <linux/sched/task.h> #include "proc/internal.h" /* only for get_proc_task() in ->open() */ #include "pnode.h" #include "internal.h" static __poll_t mounts_poll(struct file *file, poll_table *wait) { struct seq_file *m = file->private_data; struct proc_mounts *p = m->private; struct mnt_namespace *ns = p->ns; __poll_t res = EPOLLIN | EPOLLRDNORM; int event; poll_wait(file, &p->ns->poll, wait); event = READ_ONCE(ns->event); if (m->poll_event != event) { m->poll_event = event; res |= EPOLLERR | EPOLLPRI; } return res; } struct proc_fs_opts { int flag; const char *str; }; static int show_sb_opts(struct seq_file *m, struct super_block *sb) { static const struct proc_fs_opts fs_opts[] = { { SB_SYNCHRONOUS, ",sync" }, { SB_DIRSYNC, ",dirsync" }, { SB_MANDLOCK, ",mand" }, { SB_LAZYTIME, ",lazytime" }, { 0, NULL } }; const struct proc_fs_opts *fs_infop; for (fs_infop = fs_opts; fs_infop->flag; fs_infop++) { if (sb->s_flags & fs_infop->flag) seq_puts(m, fs_infop->str); } return security_sb_show_options(m, sb); } static void show_vfsmnt_opts(struct seq_file *m, struct vfsmount *mnt) { static const struct proc_fs_opts mnt_opts[] = { { MNT_NOSUID, ",nosuid" }, { MNT_NODEV, ",nodev" }, { MNT_NOEXEC, ",noexec" }, { MNT_NOATIME, ",noatime" }, { MNT_NODIRATIME, ",nodiratime" }, { MNT_RELATIME, ",relatime" }, { MNT_NOSYMFOLLOW, ",nosymfollow" }, { 0, NULL } }; const struct proc_fs_opts *fs_infop; for (fs_infop = mnt_opts; fs_infop->flag; fs_infop++) { if (mnt->mnt_flags & fs_infop->flag) seq_puts(m, fs_infop->str); } if (is_idmapped_mnt(mnt)) seq_puts(m, ",idmapped"); } static inline void mangle(struct seq_file *m, const char *s) { seq_escape(m, s, " \t\n\\#"); } static void show_type(struct seq_file *m, struct super_block *sb) { mangle(m, sb->s_type->name); if (sb->s_subtype) { seq_putc(m, '.'); mangle(m, sb->s_subtype); } } static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt) { struct proc_mounts *p = m->private; struct mount *r = real_mount(mnt); struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; struct super_block *sb = mnt_path.dentry->d_sb; int err; if (sb->s_op->show_devname) { err = sb->s_op->show_devname(m, mnt_path.dentry); if (err) goto out; } else { mangle(m, r->mnt_devname ? r->mnt_devname : "none"); } seq_putc(m, ' '); /* mountpoints outside of chroot jail will give SEQ_SKIP on this */ err = seq_path_root(m, &mnt_path, &p->root, " \t\n\\"); if (err) goto out; seq_putc(m, ' '); show_type(m, sb); seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw"); err = show_sb_opts(m, sb); if (err) goto out; show_vfsmnt_opts(m, mnt); if (sb->s_op->show_options) err = sb->s_op->show_options(m, mnt_path.dentry); seq_puts(m, " 0 0\n"); out: return err; } static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) { struct proc_mounts *p = m->private; struct mount *r = real_mount(mnt); struct super_block *sb = mnt->mnt_sb; struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; int err; seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id, MAJOR(sb->s_dev), MINOR(sb->s_dev)); err = show_path(m, mnt->mnt_root); if (err) goto out; seq_putc(m, ' '); /* mountpoints outside of chroot jail will give SEQ_SKIP on this */ err = seq_path_root(m, &mnt_path, &p->root, " \t\n\\"); if (err) goto out; seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw"); show_vfsmnt_opts(m, mnt); /* Tagged fields ("foo:X" or "bar") */ if (IS_MNT_SHARED(r)) seq_printf(m, " shared:%i", r->mnt_group_id); if (IS_MNT_SLAVE(r)) { int master = r->mnt_master->mnt_group_id; int dom = get_dominating_id(r, &p->root); seq_printf(m, " master:%i", master); if (dom && dom != master) seq_printf(m, " propagate_from:%i", dom); } if (IS_MNT_UNBINDABLE(r)) seq_puts(m, " unbindable"); /* Filesystem specific data */ seq_puts(m, " - "); show_type(m, sb); seq_putc(m, ' '); if (sb->s_op->show_devname) { err = sb->s_op->show_devname(m, mnt->mnt_root); if (err) goto out; } else { mangle(m, r->mnt_devname ? r->mnt_devname : "none"); } seq_puts(m, sb_rdonly(sb) ? " ro" : " rw"); err = show_sb_opts(m, sb); if (err) goto out; if (sb->s_op->show_options) err = sb->s_op->show_options(m, mnt->mnt_root); seq_putc(m, '\n'); out: return err; } static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt) { struct proc_mounts *p = m->private; struct mount *r = real_mount(mnt); struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; struct super_block *sb = mnt_path.dentry->d_sb; int err; /* device */ if (sb->s_op->show_devname) { seq_puts(m, "device "); err = sb->s_op->show_devname(m, mnt_path.dentry); if (err) goto out; } else { if (r->mnt_devname) { seq_puts(m, "device "); mangle(m, r->mnt_devname); } else seq_puts(m, "no device"); } /* mount point */ seq_puts(m, " mounted on "); /* mountpoints outside of chroot jail will give SEQ_SKIP on this */ err = seq_path_root(m, &mnt_path, &p->root, " \t\n\\"); if (err) goto out; seq_putc(m, ' '); /* file system type */ seq_puts(m, "with fstype "); show_type(m, sb); /* optional statistics */ if (sb->s_op->show_stats) { seq_putc(m, ' '); err = sb->s_op->show_stats(m, mnt_path.dentry); } seq_putc(m, '\n'); out: return err; } static int mounts_open_common(struct inode *inode, struct file *file, int (*show)(struct seq_file *, struct vfsmount *)) { struct task_struct *task = get_proc_task(inode); struct nsproxy *nsp; struct mnt_namespace *ns = NULL; struct path root; struct proc_mounts *p; struct seq_file *m; int ret = -EINVAL; if (!task) goto err; task_lock(task); nsp = task->nsproxy; if (!nsp || !nsp->mnt_ns) { task_unlock(task); put_task_struct(task); goto err; } ns = nsp->mnt_ns; get_mnt_ns(ns); if (!task->fs) { task_unlock(task); put_task_struct(task); ret = -ENOENT; goto err_put_ns; } get_fs_root(task->fs, &root); task_unlock(task); put_task_struct(task); ret = seq_open_private(file, &mounts_op, sizeof(struct proc_mounts)); if (ret) goto err_put_path; m = file->private_data; m->poll_event = ns->event; p = m->private; p->ns = ns; p->root = root; p->show = show; return 0; err_put_path: path_put(&root); err_put_ns: put_mnt_ns(ns); err: return ret; } static int mounts_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; struct proc_mounts *p = m->private; path_put(&p->root); put_mnt_ns(p->ns); return seq_release_private(inode, file); } static int mounts_open(struct inode *inode, struct file *file) { return mounts_open_common(inode, file, show_vfsmnt); } static int mountinfo_open(struct inode *inode, struct file *file) { return mounts_open_common(inode, file, show_mountinfo); } static int mountstats_open(struct inode *inode, struct file *file) { return mounts_open_common(inode, file, show_vfsstat); } const struct file_operations proc_mounts_operations = { .open = mounts_open, .read_iter = seq_read_iter, .splice_read = copy_splice_read, .llseek = seq_lseek, .release = mounts_release, .poll = mounts_poll, }; const struct file_operations proc_mountinfo_operations = { .open = mountinfo_open, .read_iter = seq_read_iter, .splice_read = copy_splice_read, .llseek = seq_lseek, .release = mounts_release, .poll = mounts_poll, }; const struct file_operations proc_mountstats_operations = { .open = mountstats_open, .read_iter = seq_read_iter, .splice_read = copy_splice_read, .llseek = seq_lseek, .release = mounts_release, }; |
| 1 2 1 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 | // SPDX-License-Identifier: GPL-2.0-only /* * Common framework for low-level network console, dump, and debugger code * * Sep 8 2003 Matt Mackall <mpm@selenic.com> * * based on the netconsole code from: * * Copyright (C) 2001 Ingo Molnar <mingo@redhat.com> * Copyright (C) 2002 Red Hat, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/moduleparam.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> #include <linux/if_arp.h> #include <linux/inetdevice.h> #include <linux/inet.h> #include <linux/interrupt.h> #include <linux/netpoll.h> #include <linux/sched.h> #include <linux/delay.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/if_vlan.h> #include <net/tcp.h> #include <net/udp.h> #include <net/addrconf.h> #include <net/ndisc.h> #include <net/ip6_checksum.h> #include <linux/unaligned.h> #include <trace/events/napi.h> #include <linux/kconfig.h> /* * We maintain a small pool of fully-sized skbs, to make sure the * message gets out even in extreme OOM situations. */ #define MAX_UDP_CHUNK 1460 #define MAX_SKBS 32 #define USEC_PER_POLL 50 #define MAX_SKB_SIZE \ (sizeof(struct ethhdr) + \ sizeof(struct iphdr) + \ sizeof(struct udphdr) + \ MAX_UDP_CHUNK) static void zap_completion_queue(void); static unsigned int carrier_timeout = 4; module_param(carrier_timeout, uint, 0644); #define np_info(np, fmt, ...) \ pr_info("%s: " fmt, np->name, ##__VA_ARGS__) #define np_err(np, fmt, ...) \ pr_err("%s: " fmt, np->name, ##__VA_ARGS__) #define np_notice(np, fmt, ...) \ pr_notice("%s: " fmt, np->name, ##__VA_ARGS__) static netdev_tx_t netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) { netdev_tx_t status = NETDEV_TX_OK; netdev_features_t features; features = netif_skb_features(skb); if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) { skb = __vlan_hwaccel_push_inside(skb); if (unlikely(!skb)) { /* This is actually a packet drop, but we * don't want the code that calls this * function to try and operate on a NULL skb. */ goto out; } } status = netdev_start_xmit(skb, dev, txq, false); out: return status; } static void queue_process(struct work_struct *work) { struct netpoll_info *npinfo = container_of(work, struct netpoll_info, tx_work.work); struct sk_buff *skb; unsigned long flags; while ((skb = skb_dequeue(&npinfo->txq))) { struct net_device *dev = skb->dev; struct netdev_queue *txq; unsigned int q_index; if (!netif_device_present(dev) || !netif_running(dev)) { kfree_skb(skb); continue; } local_irq_save(flags); /* check if skb->queue_mapping is still valid */ q_index = skb_get_queue_mapping(skb); if (unlikely(q_index >= dev->real_num_tx_queues)) { q_index = q_index % dev->real_num_tx_queues; skb_set_queue_mapping(skb, q_index); } txq = netdev_get_tx_queue(dev, q_index); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (netif_xmit_frozen_or_stopped(txq) || !dev_xmit_complete(netpoll_start_xmit(skb, dev, txq))) { skb_queue_head(&npinfo->txq, skb); HARD_TX_UNLOCK(dev, txq); local_irq_restore(flags); schedule_delayed_work(&npinfo->tx_work, HZ/10); return; } HARD_TX_UNLOCK(dev, txq); local_irq_restore(flags); } } static int netif_local_xmit_active(struct net_device *dev) { int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id()) return 1; } return 0; } static void poll_one_napi(struct napi_struct *napi) { int work; /* If we set this bit but see that it has already been set, * that indicates that napi has been disabled and we need * to abort this operation */ if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state)) return; /* We explicitly pass the polling call a budget of 0 to * indicate that we are clearing the Tx path only. */ work = napi->poll(napi, 0); WARN_ONCE(work, "%pS exceeded budget in poll\n", napi->poll); trace_napi_poll(napi, work, 0); clear_bit(NAPI_STATE_NPSVC, &napi->state); } static void poll_napi(struct net_device *dev) { struct napi_struct *napi; int cpu = smp_processor_id(); list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { if (cmpxchg(&napi->poll_owner, -1, cpu) == -1) { poll_one_napi(napi); smp_store_release(&napi->poll_owner, -1); } } } void netpoll_poll_dev(struct net_device *dev) { struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); const struct net_device_ops *ops; /* Don't do any rx activity if the dev_lock mutex is held * the dev_open/close paths use this to block netpoll activity * while changing device state */ if (!ni || down_trylock(&ni->dev_lock)) return; /* Some drivers will take the same locks in poll and xmit, * we can't poll if local CPU is already in xmit. */ if (!netif_running(dev) || netif_local_xmit_active(dev)) { up(&ni->dev_lock); return; } ops = dev->netdev_ops; if (ops->ndo_poll_controller) ops->ndo_poll_controller(dev); poll_napi(dev); up(&ni->dev_lock); zap_completion_queue(); } EXPORT_SYMBOL(netpoll_poll_dev); void netpoll_poll_disable(struct net_device *dev) { struct netpoll_info *ni; might_sleep(); ni = rtnl_dereference(dev->npinfo); if (ni) down(&ni->dev_lock); } void netpoll_poll_enable(struct net_device *dev) { struct netpoll_info *ni; ni = rtnl_dereference(dev->npinfo); if (ni) up(&ni->dev_lock); } static void refill_skbs(struct netpoll *np) { struct sk_buff_head *skb_pool; struct sk_buff *skb; unsigned long flags; skb_pool = &np->skb_pool; spin_lock_irqsave(&skb_pool->lock, flags); while (skb_pool->qlen < MAX_SKBS) { skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC); if (!skb) break; __skb_queue_tail(skb_pool, skb); } spin_unlock_irqrestore(&skb_pool->lock, flags); } static void zap_completion_queue(void) { unsigned long flags; struct softnet_data *sd = &get_cpu_var(softnet_data); if (sd->completion_queue) { struct sk_buff *clist; local_irq_save(flags); clist = sd->completion_queue; sd->completion_queue = NULL; local_irq_restore(flags); while (clist != NULL) { struct sk_buff *skb = clist; clist = clist->next; if (!skb_irq_freeable(skb)) { refcount_set(&skb->users, 1); dev_kfree_skb_any(skb); /* put this one back */ } else { __kfree_skb(skb); } } } put_cpu_var(softnet_data); } static struct sk_buff *find_skb(struct netpoll *np, int len, int reserve) { int count = 0; struct sk_buff *skb; zap_completion_queue(); refill_skbs(np); repeat: skb = alloc_skb(len, GFP_ATOMIC); if (!skb) skb = skb_dequeue(&np->skb_pool); if (!skb) { if (++count < 10) { netpoll_poll_dev(np->dev); goto repeat; } return NULL; } refcount_set(&skb->users, 1); skb_reserve(skb, reserve); return skb; } static int netpoll_owner_active(struct net_device *dev) { struct napi_struct *napi; list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { if (READ_ONCE(napi->poll_owner) == smp_processor_id()) return 1; } return 0; } /* call with IRQ disabled */ static netdev_tx_t __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) { netdev_tx_t status = NETDEV_TX_BUSY; struct net_device *dev; unsigned long tries; /* It is up to the caller to keep npinfo alive. */ struct netpoll_info *npinfo; lockdep_assert_irqs_disabled(); dev = np->dev; npinfo = rcu_dereference_bh(dev->npinfo); if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) { dev_kfree_skb_irq(skb); return NET_XMIT_DROP; } /* don't get messages out of order, and no recursion */ if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) { struct netdev_queue *txq; txq = netdev_core_pick_tx(dev, skb, NULL); /* try until next clock tick */ for (tries = jiffies_to_usecs(1)/USEC_PER_POLL; tries > 0; --tries) { if (HARD_TX_TRYLOCK(dev, txq)) { if (!netif_xmit_stopped(txq)) status = netpoll_start_xmit(skb, dev, txq); HARD_TX_UNLOCK(dev, txq); if (dev_xmit_complete(status)) break; } /* tickle device maybe there is some cleanup */ netpoll_poll_dev(np->dev); udelay(USEC_PER_POLL); } WARN_ONCE(!irqs_disabled(), "netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pS)\n", dev->name, dev->netdev_ops->ndo_start_xmit); } if (!dev_xmit_complete(status)) { skb_queue_tail(&npinfo->txq, skb); schedule_delayed_work(&npinfo->tx_work,0); } return NETDEV_TX_OK; } netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) { unsigned long flags; netdev_tx_t ret; if (unlikely(!np)) { dev_kfree_skb_irq(skb); ret = NET_XMIT_DROP; } else { local_irq_save(flags); ret = __netpoll_send_skb(np, skb); local_irq_restore(flags); } return ret; } EXPORT_SYMBOL(netpoll_send_skb); void netpoll_send_udp(struct netpoll *np, const char *msg, int len) { int total_len, ip_len, udp_len; struct sk_buff *skb; struct udphdr *udph; struct iphdr *iph; struct ethhdr *eth; static atomic_t ip_ident; struct ipv6hdr *ip6h; if (!IS_ENABLED(CONFIG_PREEMPT_RT)) WARN_ON_ONCE(!irqs_disabled()); udp_len = len + sizeof(*udph); if (np->ipv6) ip_len = udp_len + sizeof(*ip6h); else ip_len = udp_len + sizeof(*iph); total_len = ip_len + LL_RESERVED_SPACE(np->dev); skb = find_skb(np, total_len + np->dev->needed_tailroom, total_len - len); if (!skb) return; skb_copy_to_linear_data(skb, msg, len); skb_put(skb, len); skb_push(skb, sizeof(*udph)); skb_reset_transport_header(skb); udph = udp_hdr(skb); udph->source = htons(np->local_port); udph->dest = htons(np->remote_port); udph->len = htons(udp_len); if (np->ipv6) { udph->check = 0; udph->check = csum_ipv6_magic(&np->local_ip.in6, &np->remote_ip.in6, udp_len, IPPROTO_UDP, csum_partial(udph, udp_len, 0)); if (udph->check == 0) udph->check = CSUM_MANGLED_0; skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); /* ip6h->version = 6; ip6h->priority = 0; */ *(unsigned char *)ip6h = 0x60; ip6h->flow_lbl[0] = 0; ip6h->flow_lbl[1] = 0; ip6h->flow_lbl[2] = 0; ip6h->payload_len = htons(sizeof(struct udphdr) + len); ip6h->nexthdr = IPPROTO_UDP; ip6h->hop_limit = 32; ip6h->saddr = np->local_ip.in6; ip6h->daddr = np->remote_ip.in6; eth = skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); skb->protocol = eth->h_proto = htons(ETH_P_IPV6); } else { udph->check = 0; udph->check = csum_tcpudp_magic(np->local_ip.ip, np->remote_ip.ip, udp_len, IPPROTO_UDP, csum_partial(udph, udp_len, 0)); if (udph->check == 0) udph->check = CSUM_MANGLED_0; skb_push(skb, sizeof(*iph)); skb_reset_network_header(skb); iph = ip_hdr(skb); /* iph->version = 4; iph->ihl = 5; */ *(unsigned char *)iph = 0x45; iph->tos = 0; put_unaligned(htons(ip_len), &(iph->tot_len)); iph->id = htons(atomic_inc_return(&ip_ident)); iph->frag_off = 0; iph->ttl = 64; iph->protocol = IPPROTO_UDP; iph->check = 0; put_unaligned(np->local_ip.ip, &(iph->saddr)); put_unaligned(np->remote_ip.ip, &(iph->daddr)); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); eth = skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); skb->protocol = eth->h_proto = htons(ETH_P_IP); } ether_addr_copy(eth->h_source, np->dev->dev_addr); ether_addr_copy(eth->h_dest, np->remote_mac); skb->dev = np->dev; netpoll_send_skb(np, skb); } EXPORT_SYMBOL(netpoll_send_udp); void netpoll_print_options(struct netpoll *np) { np_info(np, "local port %d\n", np->local_port); if (np->ipv6) np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6); else np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip); np_info(np, "interface '%s'\n", np->dev_name); np_info(np, "remote port %d\n", np->remote_port); if (np->ipv6) np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6); else np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip); np_info(np, "remote ethernet address %pM\n", np->remote_mac); } EXPORT_SYMBOL(netpoll_print_options); static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr) { const char *end; if (!strchr(str, ':') && in4_pton(str, -1, (void *)addr, -1, &end) > 0) { if (!*end) return 0; } if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) { #if IS_ENABLED(CONFIG_IPV6) if (!*end) return 1; #else return -1; #endif } return -1; } static void skb_pool_flush(struct netpoll *np) { struct sk_buff_head *skb_pool; skb_pool = &np->skb_pool; skb_queue_purge_reason(skb_pool, SKB_CONSUMED); } int netpoll_parse_options(struct netpoll *np, char *opt) { char *cur=opt, *delim; int ipv6; bool ipversion_set = false; if (*cur != '@') { if ((delim = strchr(cur, '@')) == NULL) goto parse_failed; *delim = 0; if (kstrtou16(cur, 10, &np->local_port)) goto parse_failed; cur = delim; } cur++; if (*cur != '/') { ipversion_set = true; if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip); if (ipv6 < 0) goto parse_failed; else np->ipv6 = (bool)ipv6; cur = delim; } cur++; if (*cur != ',') { /* parse out dev name */ if ((delim = strchr(cur, ',')) == NULL) goto parse_failed; *delim = 0; strscpy(np->dev_name, cur, sizeof(np->dev_name)); cur = delim; } cur++; if (*cur != '@') { /* dst port */ if ((delim = strchr(cur, '@')) == NULL) goto parse_failed; *delim = 0; if (*cur == ' ' || *cur == '\t') np_info(np, "warning: whitespace is not allowed\n"); if (kstrtou16(cur, 10, &np->remote_port)) goto parse_failed; cur = delim; } cur++; /* dst ip */ if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); if (ipv6 < 0) goto parse_failed; else if (ipversion_set && np->ipv6 != (bool)ipv6) goto parse_failed; else np->ipv6 = (bool)ipv6; cur = delim + 1; if (*cur != 0) { /* MAC address */ if (!mac_pton(cur, np->remote_mac)) goto parse_failed; } netpoll_print_options(np); return 0; parse_failed: np_info(np, "couldn't parse config at '%s'!\n", cur); return -1; } EXPORT_SYMBOL(netpoll_parse_options); int __netpoll_setup(struct netpoll *np, struct net_device *ndev) { struct netpoll_info *npinfo; const struct net_device_ops *ops; int err; if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { np_err(np, "%s doesn't support polling, aborting\n", ndev->name); err = -ENOTSUPP; goto out; } if (!rcu_access_pointer(ndev->npinfo)) { npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL); if (!npinfo) { err = -ENOMEM; goto out; } sema_init(&npinfo->dev_lock, 1); skb_queue_head_init(&npinfo->txq); INIT_DELAYED_WORK(&npinfo->tx_work, queue_process); refcount_set(&npinfo->refcnt, 1); ops = ndev->netdev_ops; if (ops->ndo_netpoll_setup) { err = ops->ndo_netpoll_setup(ndev); if (err) goto free_npinfo; } } else { npinfo = rtnl_dereference(ndev->npinfo); refcount_inc(&npinfo->refcnt); } np->dev = ndev; strscpy(np->dev_name, ndev->name, IFNAMSIZ); npinfo->netpoll = np; /* last thing to do is link it to the net device structure */ rcu_assign_pointer(ndev->npinfo, npinfo); return 0; free_npinfo: kfree(npinfo); out: return err; } EXPORT_SYMBOL_GPL(__netpoll_setup); int netpoll_setup(struct netpoll *np) { struct net_device *ndev = NULL; bool ip_overwritten = false; struct in_device *in_dev; int err; skb_queue_head_init(&np->skb_pool); rtnl_lock(); if (np->dev_name[0]) { struct net *net = current->nsproxy->net_ns; ndev = __dev_get_by_name(net, np->dev_name); } if (!ndev) { np_err(np, "%s doesn't exist, aborting\n", np->dev_name); err = -ENODEV; goto unlock; } netdev_hold(ndev, &np->dev_tracker, GFP_KERNEL); if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); err = -EBUSY; goto put; } if (!netif_running(ndev)) { unsigned long atmost; np_info(np, "device %s not up yet, forcing it\n", np->dev_name); err = dev_open(ndev, NULL); if (err) { np_err(np, "failed to open %s\n", ndev->name); goto put; } rtnl_unlock(); atmost = jiffies + carrier_timeout * HZ; while (!netif_carrier_ok(ndev)) { if (time_after(jiffies, atmost)) { np_notice(np, "timeout waiting for carrier\n"); break; } msleep(1); } rtnl_lock(); } if (!np->local_ip.ip) { if (!np->ipv6) { const struct in_ifaddr *ifa; in_dev = __in_dev_get_rtnl(ndev); if (!in_dev) goto put_noaddr; ifa = rtnl_dereference(in_dev->ifa_list); if (!ifa) { put_noaddr: np_err(np, "no IP address for %s, aborting\n", np->dev_name); err = -EDESTADDRREQ; goto put; } np->local_ip.ip = ifa->ifa_local; ip_overwritten = true; np_info(np, "local IP %pI4\n", &np->local_ip.ip); } else { #if IS_ENABLED(CONFIG_IPV6) struct inet6_dev *idev; err = -EDESTADDRREQ; idev = __in6_dev_get(ndev); if (idev) { struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); list_for_each_entry(ifp, &idev->addr_list, if_list) { if (!!(ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) != !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL)) continue; np->local_ip.in6 = ifp->addr; ip_overwritten = true; err = 0; break; } read_unlock_bh(&idev->lock); } if (err) { np_err(np, "no IPv6 address for %s, aborting\n", np->dev_name); goto put; } else np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6); #else np_err(np, "IPv6 is not supported %s, aborting\n", np->dev_name); err = -EINVAL; goto put; #endif } } /* fill up the skb queue */ refill_skbs(np); err = __netpoll_setup(np, ndev); if (err) goto flush; rtnl_unlock(); return 0; flush: skb_pool_flush(np); put: DEBUG_NET_WARN_ON_ONCE(np->dev); if (ip_overwritten) memset(&np->local_ip, 0, sizeof(np->local_ip)); netdev_put(ndev, &np->dev_tracker); unlock: rtnl_unlock(); return err; } EXPORT_SYMBOL(netpoll_setup); static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head) { struct netpoll_info *npinfo = container_of(rcu_head, struct netpoll_info, rcu); skb_queue_purge(&npinfo->txq); /* we can't call cancel_delayed_work_sync here, as we are in softirq */ cancel_delayed_work(&npinfo->tx_work); /* clean after last, unfinished work */ __skb_queue_purge(&npinfo->txq); /* now cancel it again */ cancel_delayed_work(&npinfo->tx_work); kfree(npinfo); } void __netpoll_cleanup(struct netpoll *np) { struct netpoll_info *npinfo; npinfo = rtnl_dereference(np->dev->npinfo); if (!npinfo) return; if (refcount_dec_and_test(&npinfo->refcnt)) { const struct net_device_ops *ops; ops = np->dev->netdev_ops; if (ops->ndo_netpoll_cleanup) ops->ndo_netpoll_cleanup(np->dev); RCU_INIT_POINTER(np->dev->npinfo, NULL); call_rcu(&npinfo->rcu, rcu_cleanup_netpoll_info); } else RCU_INIT_POINTER(np->dev->npinfo, NULL); skb_pool_flush(np); } EXPORT_SYMBOL_GPL(__netpoll_cleanup); void __netpoll_free(struct netpoll *np) { ASSERT_RTNL(); /* Wait for transmitting packets to finish before freeing. */ synchronize_rcu(); __netpoll_cleanup(np); kfree(np); } EXPORT_SYMBOL_GPL(__netpoll_free); void do_netpoll_cleanup(struct netpoll *np) { __netpoll_cleanup(np); netdev_put(np->dev, &np->dev_tracker); np->dev = NULL; } EXPORT_SYMBOL(do_netpoll_cleanup); void netpoll_cleanup(struct netpoll *np) { rtnl_lock(); if (!np->dev) goto out; do_netpoll_cleanup(np); out: rtnl_unlock(); } EXPORT_SYMBOL(netpoll_cleanup); |
| 2 4 3 1 2 1 3 1 5 5 4 1 1 4 1 3 4 4 4 4 10 10 3 1 4 1 1 2 2 2 1 1 1 1 1 1 1 2 2 1 1 1 1 1 1 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/ceph/ceph_debug.h> #include <linux/backing-dev.h> #include <linux/ctype.h> #include <linux/fs.h> #include <linux/inet.h> #include <linux/in6.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/statfs.h> #include <linux/string.h> #include "super.h" #include "mds_client.h" #include "cache.h" #include "crypto.h" #include <linux/ceph/ceph_features.h> #include <linux/ceph/decode.h> #include <linux/ceph/mon_client.h> #include <linux/ceph/auth.h> #include <linux/ceph/debugfs.h> #include <uapi/linux/magic.h> static DEFINE_SPINLOCK(ceph_fsc_lock); static LIST_HEAD(ceph_fsc_list); /* * Ceph superblock operations * * Handle the basics of mounting, unmounting. */ /* * super ops */ static void ceph_put_super(struct super_block *s) { struct ceph_fs_client *fsc = ceph_sb_to_fs_client(s); doutc(fsc->client, "begin\n"); ceph_fscrypt_free_dummy_policy(fsc); ceph_mdsc_close_sessions(fsc->mdsc); doutc(fsc->client, "done\n"); } static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) { struct ceph_fs_client *fsc = ceph_inode_to_fs_client(d_inode(dentry)); struct ceph_mon_client *monc = &fsc->client->monc; struct ceph_statfs st; int i, err; u64 data_pool; doutc(fsc->client, "begin\n"); if (fsc->mdsc->mdsmap->m_num_data_pg_pools == 1) { data_pool = fsc->mdsc->mdsmap->m_data_pg_pools[0]; } else { data_pool = CEPH_NOPOOL; } err = ceph_monc_do_statfs(monc, data_pool, &st); if (err < 0) return err; /* fill in kstatfs */ buf->f_type = CEPH_SUPER_MAGIC; /* ?? */ /* * Express utilization in terms of large blocks to avoid * overflow on 32-bit machines. */ buf->f_frsize = 1 << CEPH_BLOCK_SHIFT; /* * By default use root quota for stats; fallback to overall filesystem * usage if using 'noquotadf' mount option or if the root dir doesn't * have max_bytes quota set. */ if (ceph_test_mount_opt(fsc, NOQUOTADF) || !ceph_quota_update_statfs(fsc, buf)) { buf->f_blocks = le64_to_cpu(st.kb) >> (CEPH_BLOCK_SHIFT-10); buf->f_bfree = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10); buf->f_bavail = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10); } /* * NOTE: for the time being, we make bsize == frsize to humor * not-yet-ancient versions of glibc that are broken. * Someday, we will probably want to report a real block * size... whatever that may mean for a network file system! */ buf->f_bsize = buf->f_frsize; buf->f_files = le64_to_cpu(st.num_objects); buf->f_ffree = -1; buf->f_namelen = NAME_MAX; /* Must convert the fsid, for consistent values across arches */ buf->f_fsid.val[0] = 0; mutex_lock(&monc->mutex); for (i = 0 ; i < sizeof(monc->monmap->fsid) / sizeof(__le32) ; ++i) buf->f_fsid.val[0] ^= le32_to_cpu(((__le32 *)&monc->monmap->fsid)[i]); mutex_unlock(&monc->mutex); /* fold the fs_cluster_id into the upper bits */ buf->f_fsid.val[1] = monc->fs_cluster_id; doutc(fsc->client, "done\n"); return 0; } static int ceph_sync_fs(struct super_block *sb, int wait) { struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb); struct ceph_client *cl = fsc->client; if (!wait) { doutc(cl, "(non-blocking)\n"); ceph_flush_dirty_caps(fsc->mdsc); ceph_flush_cap_releases(fsc->mdsc); doutc(cl, "(non-blocking) done\n"); return 0; } doutc(cl, "(blocking)\n"); ceph_osdc_sync(&fsc->client->osdc); ceph_mdsc_sync(fsc->mdsc); doutc(cl, "(blocking) done\n"); return 0; } /* * mount options */ enum { Opt_wsize, Opt_rsize, Opt_rasize, Opt_caps_wanted_delay_min, Opt_caps_wanted_delay_max, Opt_caps_max, Opt_readdir_max_entries, Opt_readdir_max_bytes, Opt_congestion_kb, /* int args above */ Opt_snapdirname, Opt_mds_namespace, Opt_recover_session, Opt_source, Opt_mon_addr, Opt_test_dummy_encryption, /* string args above */ Opt_dirstat, Opt_rbytes, Opt_asyncreaddir, Opt_dcache, Opt_ino32, Opt_fscache, Opt_poolperm, Opt_require_active_mds, Opt_acl, Opt_quotadf, Opt_copyfrom, Opt_wsync, Opt_pagecache, Opt_sparseread, }; enum ceph_recover_session_mode { ceph_recover_session_no, ceph_recover_session_clean }; static const struct constant_table ceph_param_recover[] = { { "no", ceph_recover_session_no }, { "clean", ceph_recover_session_clean }, {} }; static const struct fs_parameter_spec ceph_mount_parameters[] = { fsparam_flag_no ("acl", Opt_acl), fsparam_flag_no ("asyncreaddir", Opt_asyncreaddir), fsparam_s32 ("caps_max", Opt_caps_max), fsparam_u32 ("caps_wanted_delay_max", Opt_caps_wanted_delay_max), fsparam_u32 ("caps_wanted_delay_min", Opt_caps_wanted_delay_min), fsparam_u32 ("write_congestion_kb", Opt_congestion_kb), fsparam_flag_no ("copyfrom", Opt_copyfrom), fsparam_flag_no ("dcache", Opt_dcache), fsparam_flag_no ("dirstat", Opt_dirstat), fsparam_flag_no ("fsc", Opt_fscache), // fsc|nofsc fsparam_string ("fsc", Opt_fscache), // fsc=... fsparam_flag_no ("ino32", Opt_ino32), fsparam_string ("mds_namespace", Opt_mds_namespace), fsparam_string ("mon_addr", Opt_mon_addr), fsparam_flag_no ("poolperm", Opt_poolperm), fsparam_flag_no ("quotadf", Opt_quotadf), fsparam_u32 ("rasize", Opt_rasize), fsparam_flag_no ("rbytes", Opt_rbytes), fsparam_u32 ("readdir_max_bytes", Opt_readdir_max_bytes), fsparam_u32 ("readdir_max_entries", Opt_readdir_max_entries), fsparam_enum ("recover_session", Opt_recover_session, ceph_param_recover), fsparam_flag_no ("require_active_mds", Opt_require_active_mds), fsparam_u32 ("rsize", Opt_rsize), fsparam_string ("snapdirname", Opt_snapdirname), fsparam_string ("source", Opt_source), fsparam_flag ("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_string ("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_u32 ("wsize", Opt_wsize), fsparam_flag_no ("wsync", Opt_wsync), fsparam_flag_no ("pagecache", Opt_pagecache), fsparam_flag_no ("sparseread", Opt_sparseread), {} }; struct ceph_parse_opts_ctx { struct ceph_options *copts; struct ceph_mount_options *opts; }; /* * Remove adjacent slashes and then the trailing slash, unless it is * the only remaining character. * * E.g. "//dir1////dir2///" --> "/dir1/dir2", "///" --> "/". */ static void canonicalize_path(char *path) { int i, j = 0; for (i = 0; path[i] != '\0'; i++) { if (path[i] != '/' || j < 1 || path[j - 1] != '/') path[j++] = path[i]; } if (j > 1 && path[j - 1] == '/') j--; path[j] = '\0'; } /* * Check if the mds namespace in ceph_mount_options matches * the passed in namespace string. First time match (when * ->mds_namespace is NULL) is treated specially, since * ->mds_namespace needs to be initialized by the caller. */ static int namespace_equals(struct ceph_mount_options *fsopt, const char *namespace, size_t len) { return !(fsopt->mds_namespace && (strlen(fsopt->mds_namespace) != len || strncmp(fsopt->mds_namespace, namespace, len))); } static int ceph_parse_old_source(const char *dev_name, const char *dev_name_end, struct fs_context *fc) { int r; struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_mount_options *fsopt = pctx->opts; if (*dev_name_end != ':') return invalfc(fc, "separator ':' missing in source"); r = ceph_parse_mon_ips(dev_name, dev_name_end - dev_name, pctx->copts, fc->log.log, ','); if (r) return r; fsopt->new_dev_syntax = false; return 0; } static int ceph_parse_new_source(const char *dev_name, const char *dev_name_end, struct fs_context *fc) { size_t len; struct ceph_fsid fsid; struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_mount_options *fsopt = pctx->opts; char *fsid_start, *fs_name_start; if (*dev_name_end != '=') { dout("separator '=' missing in source"); return -EINVAL; } fsid_start = strchr(dev_name, '@'); if (!fsid_start) return invalfc(fc, "missing cluster fsid"); ++fsid_start; /* start of cluster fsid */ fs_name_start = strchr(fsid_start, '.'); if (!fs_name_start) return invalfc(fc, "missing file system name"); if (ceph_parse_fsid(fsid_start, &fsid)) return invalfc(fc, "Invalid FSID"); ++fs_name_start; /* start of file system name */ len = dev_name_end - fs_name_start; if (!namespace_equals(fsopt, fs_name_start, len)) return invalfc(fc, "Mismatching mds_namespace"); kfree(fsopt->mds_namespace); fsopt->mds_namespace = kstrndup(fs_name_start, len, GFP_KERNEL); if (!fsopt->mds_namespace) return -ENOMEM; dout("file system (mds namespace) '%s'\n", fsopt->mds_namespace); fsopt->new_dev_syntax = true; return 0; } /* * Parse the source parameter for new device format. Distinguish the device * spec from the path. Try parsing new device format and fallback to old * format if needed. * * New device syntax will looks like: * <device_spec>=/<path> * where * <device_spec> is name@fsid.fsname * <path> is optional, but if present must begin with '/' * (monitor addresses are passed via mount option) * * Old device syntax is: * <server_spec>[,<server_spec>...]:[<path>] * where * <server_spec> is <ip>[:<port>] * <path> is optional, but if present must begin with '/' */ static int ceph_parse_source(struct fs_parameter *param, struct fs_context *fc) { struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_mount_options *fsopt = pctx->opts; char *dev_name = param->string, *dev_name_end; int ret; dout("'%s'\n", dev_name); if (!dev_name || !*dev_name) return invalfc(fc, "Empty source"); dev_name_end = strchr(dev_name, '/'); if (dev_name_end) { /* * The server_path will include the whole chars from userland * including the leading '/'. */ kfree(fsopt->server_path); fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL); if (!fsopt->server_path) return -ENOMEM; canonicalize_path(fsopt->server_path); } else { dev_name_end = dev_name + strlen(dev_name); } dev_name_end--; /* back up to separator */ if (dev_name_end < dev_name) return invalfc(fc, "Path missing in source"); dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name); if (fsopt->server_path) dout("server path '%s'\n", fsopt->server_path); dout("trying new device syntax"); ret = ceph_parse_new_source(dev_name, dev_name_end, fc); if (ret) { if (ret != -EINVAL) return ret; dout("trying old device syntax"); ret = ceph_parse_old_source(dev_name, dev_name_end, fc); if (ret) return ret; } fc->source = param->string; param->string = NULL; return 0; } static int ceph_parse_mon_addr(struct fs_parameter *param, struct fs_context *fc) { struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_mount_options *fsopt = pctx->opts; kfree(fsopt->mon_addr); fsopt->mon_addr = param->string; param->string = NULL; return ceph_parse_mon_ips(fsopt->mon_addr, strlen(fsopt->mon_addr), pctx->copts, fc->log.log, '/'); } static int ceph_parse_mount_param(struct fs_context *fc, struct fs_parameter *param) { struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_mount_options *fsopt = pctx->opts; struct fs_parse_result result; unsigned int mode; int token, ret; ret = ceph_parse_param(param, pctx->copts, fc->log.log); if (ret != -ENOPARAM) return ret; token = fs_parse(fc, ceph_mount_parameters, param, &result); dout("%s: fs_parse '%s' token %d\n",__func__, param->key, token); if (token < 0) return token; switch (token) { case Opt_snapdirname: kfree(fsopt->snapdir_name); fsopt->snapdir_name = param->string; param->string = NULL; break; case Opt_mds_namespace: if (!namespace_equals(fsopt, param->string, strlen(param->string))) return invalfc(fc, "Mismatching mds_namespace"); kfree(fsopt->mds_namespace); fsopt->mds_namespace = param->string; param->string = NULL; break; case Opt_recover_session: mode = result.uint_32; if (mode == ceph_recover_session_no) fsopt->flags &= ~CEPH_MOUNT_OPT_CLEANRECOVER; else if (mode == ceph_recover_session_clean) fsopt->flags |= CEPH_MOUNT_OPT_CLEANRECOVER; else BUG(); break; case Opt_source: if (fc->source) return invalfc(fc, "Multiple sources specified"); return ceph_parse_source(param, fc); case Opt_mon_addr: return ceph_parse_mon_addr(param, fc); case Opt_wsize: if (result.uint_32 < PAGE_SIZE || result.uint_32 > CEPH_MAX_WRITE_SIZE) goto out_of_range; fsopt->wsize = ALIGN(result.uint_32, PAGE_SIZE); break; case Opt_rsize: if (result.uint_32 < PAGE_SIZE || result.uint_32 > CEPH_MAX_READ_SIZE) goto out_of_range; fsopt->rsize = ALIGN(result.uint_32, PAGE_SIZE); break; case Opt_rasize: fsopt->rasize = ALIGN(result.uint_32, PAGE_SIZE); break; case Opt_caps_wanted_delay_min: if (result.uint_32 < 1) goto out_of_range; fsopt->caps_wanted_delay_min = result.uint_32; break; case Opt_caps_wanted_delay_max: if (result.uint_32 < 1) goto out_of_range; fsopt->caps_wanted_delay_max = result.uint_32; break; case Opt_caps_max: if (result.int_32 < 0) goto out_of_range; fsopt->caps_max = result.int_32; break; case Opt_readdir_max_entries: if (result.uint_32 < 1) goto out_of_range; fsopt->max_readdir = result.uint_32; break; case Opt_readdir_max_bytes: if (result.uint_32 < PAGE_SIZE && result.uint_32 != 0) goto out_of_range; fsopt->max_readdir_bytes = result.uint_32; break; case Opt_congestion_kb: if (result.uint_32 < 1024) /* at least 1M */ goto out_of_range; fsopt->congestion_kb = result.uint_32; break; case Opt_dirstat: if (!result.negated) fsopt->flags |= CEPH_MOUNT_OPT_DIRSTAT; else fsopt->flags &= ~CEPH_MOUNT_OPT_DIRSTAT; break; case Opt_rbytes: if (!result.negated) fsopt->flags |= CEPH_MOUNT_OPT_RBYTES; else fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES; break; case Opt_asyncreaddir: if (!result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_NOASYNCREADDIR; else fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR; break; case Opt_dcache: if (!result.negated) fsopt->flags |= CEPH_MOUNT_OPT_DCACHE; else fsopt->flags &= ~CEPH_MOUNT_OPT_DCACHE; break; case Opt_ino32: if (!result.negated) fsopt->flags |= CEPH_MOUNT_OPT_INO32; else fsopt->flags &= ~CEPH_MOUNT_OPT_INO32; break; case Opt_fscache: #ifdef CONFIG_CEPH_FSCACHE kfree(fsopt->fscache_uniq); fsopt->fscache_uniq = NULL; if (result.negated) { fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE; } else { fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; fsopt->fscache_uniq = param->string; param->string = NULL; } break; #else return invalfc(fc, "fscache support is disabled"); #endif case Opt_poolperm: if (!result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_NOPOOLPERM; else fsopt->flags |= CEPH_MOUNT_OPT_NOPOOLPERM; break; case Opt_require_active_mds: if (!result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_MOUNTWAIT; else fsopt->flags |= CEPH_MOUNT_OPT_MOUNTWAIT; break; case Opt_quotadf: if (!result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_NOQUOTADF; else fsopt->flags |= CEPH_MOUNT_OPT_NOQUOTADF; break; case Opt_copyfrom: if (!result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_NOCOPYFROM; else fsopt->flags |= CEPH_MOUNT_OPT_NOCOPYFROM; break; case Opt_acl: if (!result.negated) { #ifdef CONFIG_CEPH_FS_POSIX_ACL fc->sb_flags |= SB_POSIXACL; #else return invalfc(fc, "POSIX ACL support is disabled"); #endif } else { fc->sb_flags &= ~SB_POSIXACL; } break; case Opt_wsync: if (!result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_ASYNC_DIROPS; else fsopt->flags |= CEPH_MOUNT_OPT_ASYNC_DIROPS; break; case Opt_pagecache: if (result.negated) fsopt->flags |= CEPH_MOUNT_OPT_NOPAGECACHE; else fsopt->flags &= ~CEPH_MOUNT_OPT_NOPAGECACHE; break; case Opt_sparseread: if (result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_SPARSEREAD; else fsopt->flags |= CEPH_MOUNT_OPT_SPARSEREAD; break; case Opt_test_dummy_encryption: #ifdef CONFIG_FS_ENCRYPTION fscrypt_free_dummy_policy(&fsopt->dummy_enc_policy); ret = fscrypt_parse_test_dummy_encryption(param, &fsopt->dummy_enc_policy); if (ret == -EINVAL) { warnfc(fc, "Value of option \"%s\" is unrecognized", param->key); } else if (ret == -EEXIST) { warnfc(fc, "Conflicting test_dummy_encryption options"); ret = -EINVAL; } #else warnfc(fc, "FS encryption not supported: test_dummy_encryption mount option ignored"); #endif break; default: BUG(); } return 0; out_of_range: return invalfc(fc, "%s out of range", param->key); } static void destroy_mount_options(struct ceph_mount_options *args) { dout("destroy_mount_options %p\n", args); if (!args) return; kfree(args->snapdir_name); kfree(args->mds_namespace); kfree(args->server_path); kfree(args->fscache_uniq); kfree(args->mon_addr); fscrypt_free_dummy_policy(&args->dummy_enc_policy); kfree(args); } static int strcmp_null(const char *s1, const char *s2) { if (!s1 && !s2) return 0; if (s1 && !s2) return -1; if (!s1 && s2) return 1; return strcmp(s1, s2); } static int compare_mount_options(struct ceph_mount_options *new_fsopt, struct ceph_options *new_opt, struct ceph_fs_client *fsc) { struct ceph_mount_options *fsopt1 = new_fsopt; struct ceph_mount_options *fsopt2 = fsc->mount_options; int ofs = offsetof(struct ceph_mount_options, snapdir_name); int ret; ret = memcmp(fsopt1, fsopt2, ofs); if (ret) return ret; ret = strcmp_null(fsopt1->snapdir_name, fsopt2->snapdir_name); if (ret) return ret; ret = strcmp_null(fsopt1->mds_namespace, fsopt2->mds_namespace); if (ret) return ret; ret = strcmp_null(fsopt1->server_path, fsopt2->server_path); if (ret) return ret; ret = strcmp_null(fsopt1->fscache_uniq, fsopt2->fscache_uniq); if (ret) return ret; ret = strcmp_null(fsopt1->mon_addr, fsopt2->mon_addr); if (ret) return ret; return ceph_compare_options(new_opt, fsc->client); } /** * ceph_show_options - Show mount options in /proc/mounts * @m: seq_file to write to * @root: root of that (sub)tree */ static int ceph_show_options(struct seq_file *m, struct dentry *root) { struct ceph_fs_client *fsc = ceph_sb_to_fs_client(root->d_sb); struct ceph_mount_options *fsopt = fsc->mount_options; size_t pos; int ret; /* a comma between MNT/MS and client options */ seq_putc(m, ','); pos = m->count; ret = ceph_print_client_options(m, fsc->client, false); if (ret) return ret; /* retract our comma if no client options */ if (m->count == pos) m->count--; if (fsopt->flags & CEPH_MOUNT_OPT_DIRSTAT) seq_puts(m, ",dirstat"); if ((fsopt->flags & CEPH_MOUNT_OPT_RBYTES)) seq_puts(m, ",rbytes"); if (fsopt->flags & CEPH_MOUNT_OPT_NOASYNCREADDIR) seq_puts(m, ",noasyncreaddir"); if ((fsopt->flags & CEPH_MOUNT_OPT_DCACHE) == 0) seq_puts(m, ",nodcache"); if (fsopt->flags & CEPH_MOUNT_OPT_INO32) seq_puts(m, ",ino32"); if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE) { seq_show_option(m, "fsc", fsopt->fscache_uniq); } if (fsopt->flags & CEPH_MOUNT_OPT_NOPOOLPERM) seq_puts(m, ",nopoolperm"); if (fsopt->flags & CEPH_MOUNT_OPT_NOQUOTADF) seq_puts(m, ",noquotadf"); #ifdef CONFIG_CEPH_FS_POSIX_ACL if (root->d_sb->s_flags & SB_POSIXACL) seq_puts(m, ",acl"); else seq_puts(m, ",noacl"); #endif if ((fsopt->flags & CEPH_MOUNT_OPT_NOCOPYFROM) == 0) seq_puts(m, ",copyfrom"); /* dump mds_namespace when old device syntax is in use */ if (fsopt->mds_namespace && !fsopt->new_dev_syntax) seq_show_option(m, "mds_namespace", fsopt->mds_namespace); if (fsopt->mon_addr) seq_printf(m, ",mon_addr=%s", fsopt->mon_addr); if (fsopt->flags & CEPH_MOUNT_OPT_CLEANRECOVER) seq_show_option(m, "recover_session", "clean"); if (!(fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS)) seq_puts(m, ",wsync"); if (fsopt->flags & CEPH_MOUNT_OPT_NOPAGECACHE) seq_puts(m, ",nopagecache"); if (fsopt->flags & CEPH_MOUNT_OPT_SPARSEREAD) seq_puts(m, ",sparseread"); fscrypt_show_test_dummy_encryption(m, ',', root->d_sb); if (fsopt->wsize != CEPH_MAX_WRITE_SIZE) seq_printf(m, ",wsize=%u", fsopt->wsize); if (fsopt->rsize != CEPH_MAX_READ_SIZE) seq_printf(m, ",rsize=%u", fsopt->rsize); if (fsopt->rasize != CEPH_RASIZE_DEFAULT) seq_printf(m, ",rasize=%u", fsopt->rasize); if (fsopt->congestion_kb != default_congestion_kb()) seq_printf(m, ",write_congestion_kb=%u", fsopt->congestion_kb); if (fsopt->caps_max) seq_printf(m, ",caps_max=%d", fsopt->caps_max); if (fsopt->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT) seq_printf(m, ",caps_wanted_delay_min=%u", fsopt->caps_wanted_delay_min); if (fsopt->caps_wanted_delay_max != CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT) seq_printf(m, ",caps_wanted_delay_max=%u", fsopt->caps_wanted_delay_max); if (fsopt->max_readdir != CEPH_MAX_READDIR_DEFAULT) seq_printf(m, ",readdir_max_entries=%u", fsopt->max_readdir); if (fsopt->max_readdir_bytes != CEPH_MAX_READDIR_BYTES_DEFAULT) seq_printf(m, ",readdir_max_bytes=%u", fsopt->max_readdir_bytes); if (strcmp(fsopt->snapdir_name, CEPH_SNAPDIRNAME_DEFAULT)) seq_show_option(m, "snapdirname", fsopt->snapdir_name); return 0; } /* * handle any mon messages the standard library doesn't understand. * return error if we don't either. */ static int extra_mon_dispatch(struct ceph_client *client, struct ceph_msg *msg) { struct ceph_fs_client *fsc = client->private; int type = le16_to_cpu(msg->hdr.type); switch (type) { case CEPH_MSG_MDS_MAP: ceph_mdsc_handle_mdsmap(fsc->mdsc, msg); return 0; case CEPH_MSG_FS_MAP_USER: ceph_mdsc_handle_fsmap(fsc->mdsc, msg); return 0; default: return -1; } } /* * create a new fs client * * Success or not, this function consumes @fsopt and @opt. */ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, struct ceph_options *opt) { struct ceph_fs_client *fsc; int err; fsc = kzalloc(sizeof(*fsc), GFP_KERNEL); if (!fsc) { err = -ENOMEM; goto fail; } fsc->client = ceph_create_client(opt, fsc); if (IS_ERR(fsc->client)) { err = PTR_ERR(fsc->client); goto fail; } opt = NULL; /* fsc->client now owns this */ fsc->client->extra_mon_dispatch = extra_mon_dispatch; ceph_set_opt(fsc->client, ABORT_ON_FULL); if (!fsopt->mds_namespace) { ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_MDSMAP, 0, true); } else { ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_FSMAP, 0, false); } fsc->mount_options = fsopt; fsc->sb = NULL; fsc->mount_state = CEPH_MOUNT_MOUNTING; fsc->filp_gen = 1; fsc->have_copy_from2 = true; atomic_long_set(&fsc->writeback_count, 0); fsc->write_congested = false; err = -ENOMEM; /* * The number of concurrent works can be high but they don't need * to be processed in parallel, limit concurrency. */ fsc->inode_wq = alloc_workqueue("ceph-inode", WQ_UNBOUND, 0); if (!fsc->inode_wq) goto fail_client; fsc->cap_wq = alloc_workqueue("ceph-cap", 0, 1); if (!fsc->cap_wq) goto fail_inode_wq; hash_init(fsc->async_unlink_conflict); spin_lock_init(&fsc->async_unlink_conflict_lock); spin_lock(&ceph_fsc_lock); list_add_tail(&fsc->metric_wakeup, &ceph_fsc_list); spin_unlock(&ceph_fsc_lock); return fsc; fail_inode_wq: destroy_workqueue(fsc->inode_wq); fail_client: ceph_destroy_client(fsc->client); fail: kfree(fsc); if (opt) ceph_destroy_options(opt); destroy_mount_options(fsopt); return ERR_PTR(err); } static void flush_fs_workqueues(struct ceph_fs_client *fsc) { flush_workqueue(fsc->inode_wq); flush_workqueue(fsc->cap_wq); } static void destroy_fs_client(struct ceph_fs_client *fsc) { doutc(fsc->client, "%p\n", fsc); spin_lock(&ceph_fsc_lock); list_del(&fsc->metric_wakeup); spin_unlock(&ceph_fsc_lock); ceph_mdsc_destroy(fsc); destroy_workqueue(fsc->inode_wq); destroy_workqueue(fsc->cap_wq); destroy_mount_options(fsc->mount_options); ceph_destroy_client(fsc->client); kfree(fsc); dout("%s: %p done\n", __func__, fsc); } /* * caches */ struct kmem_cache *ceph_inode_cachep; struct kmem_cache *ceph_cap_cachep; struct kmem_cache *ceph_cap_snap_cachep; struct kmem_cache *ceph_cap_flush_cachep; struct kmem_cache *ceph_dentry_cachep; struct kmem_cache *ceph_file_cachep; struct kmem_cache *ceph_dir_file_cachep; struct kmem_cache *ceph_mds_request_cachep; mempool_t *ceph_wb_pagevec_pool; static void ceph_inode_init_once(void *foo) { struct ceph_inode_info *ci = foo; inode_init_once(&ci->netfs.inode); } static int __init init_caches(void) { int error = -ENOMEM; ceph_inode_cachep = kmem_cache_create("ceph_inode_info", sizeof(struct ceph_inode_info), __alignof__(struct ceph_inode_info), SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, ceph_inode_init_once); if (!ceph_inode_cachep) return -ENOMEM; ceph_cap_cachep = KMEM_CACHE(ceph_cap, 0); if (!ceph_cap_cachep) goto bad_cap; ceph_cap_snap_cachep = KMEM_CACHE(ceph_cap_snap, 0); if (!ceph_cap_snap_cachep) goto bad_cap_snap; ceph_cap_flush_cachep = KMEM_CACHE(ceph_cap_flush, SLAB_RECLAIM_ACCOUNT); if (!ceph_cap_flush_cachep) goto bad_cap_flush; ceph_dentry_cachep = KMEM_CACHE(ceph_dentry_info, SLAB_RECLAIM_ACCOUNT); if (!ceph_dentry_cachep) goto bad_dentry; ceph_file_cachep = KMEM_CACHE(ceph_file_info, 0); if (!ceph_file_cachep) goto bad_file; ceph_dir_file_cachep = KMEM_CACHE(ceph_dir_file_info, 0); if (!ceph_dir_file_cachep) goto bad_dir_file; ceph_mds_request_cachep = KMEM_CACHE(ceph_mds_request, 0); if (!ceph_mds_request_cachep) goto bad_mds_req; ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10, (CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT) * sizeof(struct page *)); if (!ceph_wb_pagevec_pool) goto bad_pagevec_pool; return 0; bad_pagevec_pool: kmem_cache_destroy(ceph_mds_request_cachep); bad_mds_req: kmem_cache_destroy(ceph_dir_file_cachep); bad_dir_file: kmem_cache_destroy(ceph_file_cachep); bad_file: kmem_cache_destroy(ceph_dentry_cachep); bad_dentry: kmem_cache_destroy(ceph_cap_flush_cachep); bad_cap_flush: kmem_cache_destroy(ceph_cap_snap_cachep); bad_cap_snap: kmem_cache_destroy(ceph_cap_cachep); bad_cap: kmem_cache_destroy(ceph_inode_cachep); return error; } static void destroy_caches(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(ceph_inode_cachep); kmem_cache_destroy(ceph_cap_cachep); kmem_cache_destroy(ceph_cap_snap_cachep); kmem_cache_destroy(ceph_cap_flush_cachep); kmem_cache_destroy(ceph_dentry_cachep); kmem_cache_destroy(ceph_file_cachep); kmem_cache_destroy(ceph_dir_file_cachep); kmem_cache_destroy(ceph_mds_request_cachep); mempool_destroy(ceph_wb_pagevec_pool); } static void __ceph_umount_begin(struct ceph_fs_client *fsc) { ceph_osdc_abort_requests(&fsc->client->osdc, -EIO); ceph_mdsc_force_umount(fsc->mdsc); fsc->filp_gen++; // invalidate open files } /* * ceph_umount_begin - initiate forced umount. Tear down the * mount, skipping steps that may hang while waiting for server(s). */ void ceph_umount_begin(struct super_block *sb) { struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb); doutc(fsc->client, "starting forced umount\n"); if (!fsc) return; fsc->mount_state = CEPH_MOUNT_SHUTDOWN; __ceph_umount_begin(fsc); } static const struct super_operations ceph_super_ops = { .alloc_inode = ceph_alloc_inode, .free_inode = ceph_free_inode, .write_inode = ceph_write_inode, .drop_inode = generic_delete_inode, .evict_inode = ceph_evict_inode, .sync_fs = ceph_sync_fs, .put_super = ceph_put_super, .show_options = ceph_show_options, .statfs = ceph_statfs, .umount_begin = ceph_umount_begin, }; /* * Bootstrap mount by opening the root directory. Note the mount * @started time from caller, and time out if this takes too long. */ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc, const char *path, unsigned long started) { struct ceph_client *cl = fsc->client; struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req = NULL; int err; struct dentry *root; /* open dir */ doutc(cl, "opening '%s'\n", path); req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, USE_ANY_MDS); if (IS_ERR(req)) return ERR_CAST(req); req->r_path1 = kstrdup(path, GFP_NOFS); if (!req->r_path1) { root = ERR_PTR(-ENOMEM); goto out; } req->r_ino1.ino = CEPH_INO_ROOT; req->r_ino1.snap = CEPH_NOSNAP; req->r_started = started; req->r_timeout = fsc->client->options->mount_timeout; req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INODE); req->r_num_caps = 2; err = ceph_mdsc_do_request(mdsc, NULL, req); if (err == 0) { struct inode *inode = req->r_target_inode; req->r_target_inode = NULL; doutc(cl, "success\n"); root = d_make_root(inode); if (!root) { root = ERR_PTR(-ENOMEM); goto out; } doutc(cl, "success, root dentry is %p\n", root); } else { root = ERR_PTR(err); } out: ceph_mdsc_put_request(req); return root; } #ifdef CONFIG_FS_ENCRYPTION static int ceph_apply_test_dummy_encryption(struct super_block *sb, struct fs_context *fc, struct ceph_mount_options *fsopt) { struct ceph_fs_client *fsc = sb->s_fs_info; if (!fscrypt_is_dummy_policy_set(&fsopt->dummy_enc_policy)) return 0; /* No changing encryption context on remount. */ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE && !fscrypt_is_dummy_policy_set(&fsc->fsc_dummy_enc_policy)) { if (fscrypt_dummy_policies_equal(&fsopt->dummy_enc_policy, &fsc->fsc_dummy_enc_policy)) return 0; errorfc(fc, "Can't set test_dummy_encryption on remount"); return -EINVAL; } /* Also make sure fsopt doesn't contain a conflicting value. */ if (fscrypt_is_dummy_policy_set(&fsc->fsc_dummy_enc_policy)) { if (fscrypt_dummy_policies_equal(&fsopt->dummy_enc_policy, &fsc->fsc_dummy_enc_policy)) return 0; errorfc(fc, "Conflicting test_dummy_encryption options"); return -EINVAL; } fsc->fsc_dummy_enc_policy = fsopt->dummy_enc_policy; memset(&fsopt->dummy_enc_policy, 0, sizeof(fsopt->dummy_enc_policy)); warnfc(fc, "test_dummy_encryption mode enabled"); return 0; } #else static int ceph_apply_test_dummy_encryption(struct super_block *sb, struct fs_context *fc, struct ceph_mount_options *fsopt) { return 0; } #endif /* * mount: join the ceph cluster, and open root directory. */ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc, struct fs_context *fc) { struct ceph_client *cl = fsc->client; int err; unsigned long started = jiffies; /* note the start time */ struct dentry *root; doutc(cl, "mount start %p\n", fsc); mutex_lock(&fsc->client->mount_mutex); if (!fsc->sb->s_root) { const char *path = fsc->mount_options->server_path ? fsc->mount_options->server_path + 1 : ""; err = __ceph_open_session(fsc->client, started); if (err < 0) goto out; /* setup fscache */ if (fsc->mount_options->flags & CEPH_MOUNT_OPT_FSCACHE) { err = ceph_fscache_register_fs(fsc, fc); if (err < 0) goto out; } err = ceph_apply_test_dummy_encryption(fsc->sb, fc, fsc->mount_options); if (err) goto out; doutc(cl, "mount opening path '%s'\n", path); ceph_fs_debugfs_init(fsc); root = open_root_dentry(fsc, path, started); if (IS_ERR(root)) { err = PTR_ERR(root); goto out; } fsc->sb->s_root = dget(root); } else { root = dget(fsc->sb->s_root); } fsc->mount_state = CEPH_MOUNT_MOUNTED; doutc(cl, "mount success\n"); mutex_unlock(&fsc->client->mount_mutex); return root; out: mutex_unlock(&fsc->client->mount_mutex); ceph_fscrypt_free_dummy_policy(fsc); return ERR_PTR(err); } static int ceph_set_super(struct super_block *s, struct fs_context *fc) { struct ceph_fs_client *fsc = s->s_fs_info; struct ceph_client *cl = fsc->client; int ret; doutc(cl, "%p\n", s); s->s_maxbytes = MAX_LFS_FILESIZE; s->s_xattr = ceph_xattr_handlers; fsc->sb = s; fsc->max_file_size = 1ULL << 40; /* temp value until we get mdsmap */ s->s_op = &ceph_super_ops; s->s_d_op = &ceph_dentry_ops; s->s_export_op = &ceph_export_ops; s->s_time_gran = 1; s->s_time_min = 0; s->s_time_max = U32_MAX; s->s_flags |= SB_NODIRATIME | SB_NOATIME; ceph_fscrypt_set_ops(s); ret = set_anon_super_fc(s, fc); if (ret != 0) fsc->sb = NULL; return ret; } /* * share superblock if same fs AND options */ static int ceph_compare_super(struct super_block *sb, struct fs_context *fc) { struct ceph_fs_client *new = fc->s_fs_info; struct ceph_mount_options *fsopt = new->mount_options; struct ceph_options *opt = new->client->options; struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb); struct ceph_client *cl = fsc->client; doutc(cl, "%p\n", sb); if (compare_mount_options(fsopt, opt, fsc)) { doutc(cl, "monitor(s)/mount options don't match\n"); return 0; } if ((opt->flags & CEPH_OPT_FSID) && ceph_fsid_compare(&opt->fsid, &fsc->client->fsid)) { doutc(cl, "fsid doesn't match\n"); return 0; } if (fc->sb_flags != (sb->s_flags & ~SB_BORN)) { doutc(cl, "flags differ\n"); return 0; } if (fsc->blocklisted && !ceph_test_mount_opt(fsc, CLEANRECOVER)) { doutc(cl, "client is blocklisted (and CLEANRECOVER is not set)\n"); return 0; } if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) { doutc(cl, "client has been forcibly unmounted\n"); return 0; } return 1; } /* * construct our own bdi so we can control readahead, etc. */ static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc) { int err; err = super_setup_bdi_name(sb, "ceph-%ld", atomic_long_inc_return(&bdi_seq)); if (err) return err; /* set ra_pages based on rasize mount option? */ sb->s_bdi->ra_pages = fsc->mount_options->rasize >> PAGE_SHIFT; /* set io_pages based on max osd read size */ sb->s_bdi->io_pages = fsc->mount_options->rsize >> PAGE_SHIFT; return 0; } static int ceph_get_tree(struct fs_context *fc) { struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_mount_options *fsopt = pctx->opts; struct super_block *sb; struct ceph_fs_client *fsc; struct dentry *res; int (*compare_super)(struct super_block *, struct fs_context *) = ceph_compare_super; int err; dout("ceph_get_tree\n"); if (!fc->source) return invalfc(fc, "No source"); if (fsopt->new_dev_syntax && !fsopt->mon_addr) return invalfc(fc, "No monitor address"); /* create client (which we may/may not use) */ fsc = create_fs_client(pctx->opts, pctx->copts); pctx->opts = NULL; pctx->copts = NULL; if (IS_ERR(fsc)) { err = PTR_ERR(fsc); goto out_final; } err = ceph_mdsc_init(fsc); if (err < 0) goto out; if (ceph_test_opt(fsc->client, NOSHARE)) compare_super = NULL; fc->s_fs_info = fsc; sb = sget_fc(fc, compare_super, ceph_set_super); fc->s_fs_info = NULL; if (IS_ERR(sb)) { err = PTR_ERR(sb); goto out; } if (ceph_sb_to_fs_client(sb) != fsc) { destroy_fs_client(fsc); fsc = ceph_sb_to_fs_client(sb); dout("get_sb got existing client %p\n", fsc); } else { dout("get_sb using new client %p\n", fsc); err = ceph_setup_bdi(sb, fsc); if (err < 0) goto out_splat; } res = ceph_real_mount(fsc, fc); if (IS_ERR(res)) { err = PTR_ERR(res); goto out_splat; } doutc(fsc->client, "root %p inode %p ino %llx.%llx\n", res, d_inode(res), ceph_vinop(d_inode(res))); fc->root = fsc->sb->s_root; return 0; out_splat: if (!ceph_mdsmap_is_cluster_available(fsc->mdsc->mdsmap)) { pr_info("No mds server is up or the cluster is laggy\n"); err = -EHOSTUNREACH; } ceph_mdsc_close_sessions(fsc->mdsc); deactivate_locked_super(sb); goto out_final; out: destroy_fs_client(fsc); out_final: dout("ceph_get_tree fail %d\n", err); return err; } static void ceph_free_fc(struct fs_context *fc) { struct ceph_parse_opts_ctx *pctx = fc->fs_private; if (pctx) { destroy_mount_options(pctx->opts); ceph_destroy_options(pctx->copts); kfree(pctx); } } static int ceph_reconfigure_fc(struct fs_context *fc) { int err; struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_mount_options *fsopt = pctx->opts; struct super_block *sb = fc->root->d_sb; struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb); err = ceph_apply_test_dummy_encryption(sb, fc, fsopt); if (err) return err; if (fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS) ceph_set_mount_opt(fsc, ASYNC_DIROPS); else ceph_clear_mount_opt(fsc, ASYNC_DIROPS); if (fsopt->flags & CEPH_MOUNT_OPT_SPARSEREAD) ceph_set_mount_opt(fsc, SPARSEREAD); else ceph_clear_mount_opt(fsc, SPARSEREAD); if (strcmp_null(fsc->mount_options->mon_addr, fsopt->mon_addr)) { kfree(fsc->mount_options->mon_addr); fsc->mount_options->mon_addr = fsopt->mon_addr; fsopt->mon_addr = NULL; pr_notice_client(fsc->client, "monitor addresses recorded, but not used for reconnection"); } sync_filesystem(sb); return 0; } static const struct fs_context_operations ceph_context_ops = { .free = ceph_free_fc, .parse_param = ceph_parse_mount_param, .get_tree = ceph_get_tree, .reconfigure = ceph_reconfigure_fc, }; /* * Set up the filesystem mount context. */ static int ceph_init_fs_context(struct fs_context *fc) { struct ceph_parse_opts_ctx *pctx; struct ceph_mount_options *fsopt; pctx = kzalloc(sizeof(*pctx), GFP_KERNEL); if (!pctx) return -ENOMEM; pctx->copts = ceph_alloc_options(); if (!pctx->copts) goto nomem; pctx->opts = kzalloc(sizeof(*pctx->opts), GFP_KERNEL); if (!pctx->opts) goto nomem; fsopt = pctx->opts; fsopt->flags = CEPH_MOUNT_OPT_DEFAULT; fsopt->wsize = CEPH_MAX_WRITE_SIZE; fsopt->rsize = CEPH_MAX_READ_SIZE; fsopt->rasize = CEPH_RASIZE_DEFAULT; fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL); if (!fsopt->snapdir_name) goto nomem; fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT; fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT; fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT; fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT; fsopt->congestion_kb = default_congestion_kb(); #ifdef CONFIG_CEPH_FS_POSIX_ACL fc->sb_flags |= SB_POSIXACL; #endif fc->fs_private = pctx; fc->ops = &ceph_context_ops; return 0; nomem: destroy_mount_options(pctx->opts); ceph_destroy_options(pctx->copts); kfree(pctx); return -ENOMEM; } /* * Return true if it successfully increases the blocker counter, * or false if the mdsc is in stopping and flushed state. */ static bool __inc_stopping_blocker(struct ceph_mds_client *mdsc) { spin_lock(&mdsc->stopping_lock); if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING) { spin_unlock(&mdsc->stopping_lock); return false; } atomic_inc(&mdsc->stopping_blockers); spin_unlock(&mdsc->stopping_lock); return true; } static void __dec_stopping_blocker(struct ceph_mds_client *mdsc) { spin_lock(&mdsc->stopping_lock); if (!atomic_dec_return(&mdsc->stopping_blockers) && mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING) complete_all(&mdsc->stopping_waiter); spin_unlock(&mdsc->stopping_lock); } /* For metadata IO requests */ bool ceph_inc_mds_stopping_blocker(struct ceph_mds_client *mdsc, struct ceph_mds_session *session) { mutex_lock(&session->s_mutex); inc_session_sequence(session); mutex_unlock(&session->s_mutex); return __inc_stopping_blocker(mdsc); } void ceph_dec_mds_stopping_blocker(struct ceph_mds_client *mdsc) { __dec_stopping_blocker(mdsc); } /* For data IO requests */ bool ceph_inc_osd_stopping_blocker(struct ceph_mds_client *mdsc) { return __inc_stopping_blocker(mdsc); } void ceph_dec_osd_stopping_blocker(struct ceph_mds_client *mdsc) { __dec_stopping_blocker(mdsc); } static void ceph_kill_sb(struct super_block *s) { struct ceph_fs_client *fsc = ceph_sb_to_fs_client(s); struct ceph_client *cl = fsc->client; struct ceph_mds_client *mdsc = fsc->mdsc; bool wait; doutc(cl, "%p\n", s); ceph_mdsc_pre_umount(mdsc); flush_fs_workqueues(fsc); /* * Though the kill_anon_super() will finally trigger the * sync_filesystem() anyway, we still need to do it here and * then bump the stage of shutdown. This will allow us to * drop any further message, which will increase the inodes' * i_count reference counters but makes no sense any more, * from MDSs. * * Without this when evicting the inodes it may fail in the * kill_anon_super(), which will trigger a warning when * destroying the fscrypt keyring and then possibly trigger * a further crash in ceph module when the iput() tries to * evict the inodes later. */ sync_filesystem(s); spin_lock(&mdsc->stopping_lock); mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHING; wait = !!atomic_read(&mdsc->stopping_blockers); spin_unlock(&mdsc->stopping_lock); if (wait && atomic_read(&mdsc->stopping_blockers)) { long timeleft = wait_for_completion_killable_timeout( &mdsc->stopping_waiter, fsc->client->options->mount_timeout); if (!timeleft) /* timed out */ pr_warn_client(cl, "umount timed out, %ld\n", timeleft); else if (timeleft < 0) /* killed */ pr_warn_client(cl, "umount was killed, %ld\n", timeleft); } mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; kill_anon_super(s); fsc->client->extra_mon_dispatch = NULL; ceph_fs_debugfs_cleanup(fsc); ceph_fscache_unregister_fs(fsc); destroy_fs_client(fsc); } static struct file_system_type ceph_fs_type = { .owner = THIS_MODULE, .name = "ceph", .init_fs_context = ceph_init_fs_context, .kill_sb = ceph_kill_sb, .fs_flags = FS_RENAME_DOES_D_MOVE | FS_ALLOW_IDMAP, }; MODULE_ALIAS_FS("ceph"); int ceph_force_reconnect(struct super_block *sb) { struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb); int err = 0; fsc->mount_state = CEPH_MOUNT_RECOVER; __ceph_umount_begin(fsc); /* Make sure all page caches get invalidated. * see remove_session_caps_cb() */ flush_workqueue(fsc->inode_wq); /* In case that we were blocklisted. This also reset * all mon/osd connections */ ceph_reset_client_addr(fsc->client); ceph_osdc_clear_abort_err(&fsc->client->osdc); fsc->blocklisted = false; fsc->mount_state = CEPH_MOUNT_MOUNTED; if (sb->s_root) { err = __ceph_do_getattr(d_inode(sb->s_root), NULL, CEPH_STAT_CAP_INODE, true); } return err; } static int __init init_ceph(void) { int ret = init_caches(); if (ret) goto out; ceph_flock_init(); ret = register_filesystem(&ceph_fs_type); if (ret) goto out_caches; pr_info("loaded (mds proto %d)\n", CEPH_MDSC_PROTOCOL); return 0; out_caches: destroy_caches(); out: return ret; } static void __exit exit_ceph(void) { dout("exit_ceph\n"); unregister_filesystem(&ceph_fs_type); destroy_caches(); } static int param_set_metrics(const char *val, const struct kernel_param *kp) { struct ceph_fs_client *fsc; int ret; ret = param_set_bool(val, kp); if (ret) { pr_err("Failed to parse sending metrics switch value '%s'\n", val); return ret; } else if (!disable_send_metrics) { // wake up all the mds clients spin_lock(&ceph_fsc_lock); list_for_each_entry(fsc, &ceph_fsc_list, metric_wakeup) { metric_schedule_delayed(&fsc->mdsc->metric); } spin_unlock(&ceph_fsc_lock); } return 0; } static const struct kernel_param_ops param_ops_metrics = { .set = param_set_metrics, .get = param_get_bool, }; bool disable_send_metrics = false; module_param_cb(disable_send_metrics, ¶m_ops_metrics, &disable_send_metrics, 0644); MODULE_PARM_DESC(disable_send_metrics, "Enable sending perf metrics to ceph cluster (default: on)"); /* for both v1 and v2 syntax */ static bool mount_support = true; static const struct kernel_param_ops param_ops_mount_syntax = { .get = param_get_bool, }; module_param_cb(mount_syntax_v1, ¶m_ops_mount_syntax, &mount_support, 0444); module_param_cb(mount_syntax_v2, ¶m_ops_mount_syntax, &mount_support, 0444); bool enable_unsafe_idmap = false; module_param(enable_unsafe_idmap, bool, 0644); MODULE_PARM_DESC(enable_unsafe_idmap, "Allow to use idmapped mounts with MDS without CEPHFS_FEATURE_HAS_OWNER_UIDGID"); module_init(init_ceph); module_exit(exit_ceph); MODULE_AUTHOR("Sage Weil <sage@newdream.net>"); MODULE_AUTHOR("Yehuda Sadeh <yehuda@hq.newdream.net>"); MODULE_AUTHOR("Patience Warnick <patience@newdream.net>"); MODULE_DESCRIPTION("Ceph filesystem for Linux"); MODULE_LICENSE("GPL"); |
| 662 1 1 659 25 634 635 636 238 6 232 232 3 3 640 3 639 641 168 640 641 639 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/main.c - Where the driver meets power management. * * Copyright (c) 2003 Patrick Mochel * Copyright (c) 2003 Open Source Development Lab * * The driver model core calls device_pm_add() when a device is registered. * This will initialize the embedded device_pm_info object in the device * and add it to the list of power-controlled devices. sysfs entries for * controlling device power management will also be added. * * A separate list is used for keeping track of power info, because the power * domain dependencies may differ from the ancestral dependencies that the * subsystem list maintains. */ #define pr_fmt(fmt) "PM: " fmt #define dev_fmt pr_fmt #include <linux/device.h> #include <linux/export.h> #include <linux/mutex.h> #include <linux/pm.h> #include <linux/pm_runtime.h> #include <linux/pm-trace.h> #include <linux/pm_wakeirq.h> #include <linux/interrupt.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/async.h> #include <linux/suspend.h> #include <trace/events/power.h> #include <linux/cpufreq.h> #include <linux/devfreq.h> #include <linux/timer.h> #include "../base.h" #include "power.h" typedef int (*pm_callback_t)(struct device *); #define list_for_each_entry_rcu_locked(pos, head, member) \ list_for_each_entry_rcu(pos, head, member, \ device_links_read_lock_held()) /* * The entries in the dpm_list list are in a depth first order, simply * because children are guaranteed to be discovered after parents, and * are inserted at the back of the list on discovery. * * Since device_pm_add() may be called with a device lock held, * we must never try to acquire a device lock while holding * dpm_list_mutex. */ LIST_HEAD(dpm_list); static LIST_HEAD(dpm_prepared_list); static LIST_HEAD(dpm_suspended_list); static LIST_HEAD(dpm_late_early_list); static LIST_HEAD(dpm_noirq_list); static DEFINE_MUTEX(dpm_list_mtx); static pm_message_t pm_transition; static int async_error; static const char *pm_verb(int event) { switch (event) { case PM_EVENT_SUSPEND: return "suspend"; case PM_EVENT_RESUME: return "resume"; case PM_EVENT_FREEZE: return "freeze"; case PM_EVENT_QUIESCE: return "quiesce"; case PM_EVENT_HIBERNATE: return "hibernate"; case PM_EVENT_THAW: return "thaw"; case PM_EVENT_RESTORE: return "restore"; case PM_EVENT_RECOVER: return "recover"; default: return "(unknown PM event)"; } } /** * device_pm_sleep_init - Initialize system suspend-related device fields. * @dev: Device object being initialized. */ void device_pm_sleep_init(struct device *dev) { dev->power.is_prepared = false; dev->power.is_suspended = false; dev->power.is_noirq_suspended = false; dev->power.is_late_suspended = false; init_completion(&dev->power.completion); complete_all(&dev->power.completion); dev->power.wakeup = NULL; INIT_LIST_HEAD(&dev->power.entry); } /** * device_pm_lock - Lock the list of active devices used by the PM core. */ void device_pm_lock(void) { mutex_lock(&dpm_list_mtx); } /** * device_pm_unlock - Unlock the list of active devices used by the PM core. */ void device_pm_unlock(void) { mutex_unlock(&dpm_list_mtx); } /** * device_pm_add - Add a device to the PM core's list of active devices. * @dev: Device to add to the list. */ void device_pm_add(struct device *dev) { /* Skip PM setup/initialization. */ if (device_pm_not_required(dev)) return; pr_debug("Adding info for %s:%s\n", dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); device_pm_check_callbacks(dev); mutex_lock(&dpm_list_mtx); if (dev->parent && dev->parent->power.is_prepared) dev_warn(dev, "parent %s should not be sleeping\n", dev_name(dev->parent)); list_add_tail(&dev->power.entry, &dpm_list); dev->power.in_dpm_list = true; mutex_unlock(&dpm_list_mtx); } /** * device_pm_remove - Remove a device from the PM core's list of active devices. * @dev: Device to be removed from the list. */ void device_pm_remove(struct device *dev) { if (device_pm_not_required(dev)) return; pr_debug("Removing info for %s:%s\n", dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); complete_all(&dev->power.completion); mutex_lock(&dpm_list_mtx); list_del_init(&dev->power.entry); dev->power.in_dpm_list = false; mutex_unlock(&dpm_list_mtx); device_wakeup_disable(dev); pm_runtime_remove(dev); device_pm_check_callbacks(dev); } /** * device_pm_move_before - Move device in the PM core's list of active devices. * @deva: Device to move in dpm_list. * @devb: Device @deva should come before. */ void device_pm_move_before(struct device *deva, struct device *devb) { pr_debug("Moving %s:%s before %s:%s\n", deva->bus ? deva->bus->name : "No Bus", dev_name(deva), devb->bus ? devb->bus->name : "No Bus", dev_name(devb)); /* Delete deva from dpm_list and reinsert before devb. */ list_move_tail(&deva->power.entry, &devb->power.entry); } /** * device_pm_move_after - Move device in the PM core's list of active devices. * @deva: Device to move in dpm_list. * @devb: Device @deva should come after. */ void device_pm_move_after(struct device *deva, struct device *devb) { pr_debug("Moving %s:%s after %s:%s\n", deva->bus ? deva->bus->name : "No Bus", dev_name(deva), devb->bus ? devb->bus->name : "No Bus", dev_name(devb)); /* Delete deva from dpm_list and reinsert after devb. */ list_move(&deva->power.entry, &devb->power.entry); } /** * device_pm_move_last - Move device to end of the PM core's list of devices. * @dev: Device to move in dpm_list. */ void device_pm_move_last(struct device *dev) { pr_debug("Moving %s:%s to end of list\n", dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); list_move_tail(&dev->power.entry, &dpm_list); } static ktime_t initcall_debug_start(struct device *dev, void *cb) { if (!pm_print_times_enabled) return 0; dev_info(dev, "calling %ps @ %i, parent: %s\n", cb, task_pid_nr(current), dev->parent ? dev_name(dev->parent) : "none"); return ktime_get(); } static void initcall_debug_report(struct device *dev, ktime_t calltime, void *cb, int error) { ktime_t rettime; if (!pm_print_times_enabled) return; rettime = ktime_get(); dev_info(dev, "%ps returned %d after %Ld usecs\n", cb, error, (unsigned long long)ktime_us_delta(rettime, calltime)); } /** * dpm_wait - Wait for a PM operation to complete. * @dev: Device to wait for. * @async: If unset, wait only if the device's power.async_suspend flag is set. */ static void dpm_wait(struct device *dev, bool async) { if (!dev) return; if (async || (pm_async_enabled && dev->power.async_suspend)) wait_for_completion(&dev->power.completion); } static int dpm_wait_fn(struct device *dev, void *async_ptr) { dpm_wait(dev, *((bool *)async_ptr)); return 0; } static void dpm_wait_for_children(struct device *dev, bool async) { device_for_each_child(dev, &async, dpm_wait_fn); } static void dpm_wait_for_suppliers(struct device *dev, bool async) { struct device_link *link; int idx; idx = device_links_read_lock(); /* * If the supplier goes away right after we've checked the link to it, * we'll wait for its completion to change the state, but that's fine, * because the only things that will block as a result are the SRCU * callbacks freeing the link objects for the links in the list we're * walking. */ list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node) if (READ_ONCE(link->status) != DL_STATE_DORMANT) dpm_wait(link->supplier, async); device_links_read_unlock(idx); } static bool dpm_wait_for_superior(struct device *dev, bool async) { struct device *parent; /* * If the device is resumed asynchronously and the parent's callback * deletes both the device and the parent itself, the parent object may * be freed while this function is running, so avoid that by reference * counting the parent once more unless the device has been deleted * already (in which case return right away). */ mutex_lock(&dpm_list_mtx); if (!device_pm_initialized(dev)) { mutex_unlock(&dpm_list_mtx); return false; } parent = get_device(dev->parent); mutex_unlock(&dpm_list_mtx); dpm_wait(parent, async); put_device(parent); dpm_wait_for_suppliers(dev, async); /* * If the parent's callback has deleted the device, attempting to resume * it would be invalid, so avoid doing that then. */ return device_pm_initialized(dev); } static void dpm_wait_for_consumers(struct device *dev, bool async) { struct device_link *link; int idx; idx = device_links_read_lock(); /* * The status of a device link can only be changed from "dormant" by a * probe, but that cannot happen during system suspend/resume. In * theory it can change to "dormant" at that time, but then it is * reasonable to wait for the target device anyway (eg. if it goes * away, it's better to wait for it to go away completely and then * continue instead of trying to continue in parallel with its * unregistration). */ list_for_each_entry_rcu_locked(link, &dev->links.consumers, s_node) if (READ_ONCE(link->status) != DL_STATE_DORMANT) dpm_wait(link->consumer, async); device_links_read_unlock(idx); } static void dpm_wait_for_subordinate(struct device *dev, bool async) { dpm_wait_for_children(dev, async); dpm_wait_for_consumers(dev, async); } /** * pm_op - Return the PM operation appropriate for given PM event. * @ops: PM operations to choose from. * @state: PM transition of the system being carried out. */ static pm_callback_t pm_op(const struct dev_pm_ops *ops, pm_message_t state) { switch (state.event) { #ifdef CONFIG_SUSPEND case PM_EVENT_SUSPEND: return ops->suspend; case PM_EVENT_RESUME: return ops->resume; #endif /* CONFIG_SUSPEND */ #ifdef CONFIG_HIBERNATE_CALLBACKS case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return ops->freeze; case PM_EVENT_HIBERNATE: return ops->poweroff; case PM_EVENT_THAW: case PM_EVENT_RECOVER: return ops->thaw; case PM_EVENT_RESTORE: return ops->restore; #endif /* CONFIG_HIBERNATE_CALLBACKS */ } return NULL; } /** * pm_late_early_op - Return the PM operation appropriate for given PM event. * @ops: PM operations to choose from. * @state: PM transition of the system being carried out. * * Runtime PM is disabled for @dev while this function is being executed. */ static pm_callback_t pm_late_early_op(const struct dev_pm_ops *ops, pm_message_t state) { switch (state.event) { #ifdef CONFIG_SUSPEND case PM_EVENT_SUSPEND: return ops->suspend_late; case PM_EVENT_RESUME: return ops->resume_early; #endif /* CONFIG_SUSPEND */ #ifdef CONFIG_HIBERNATE_CALLBACKS case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return ops->freeze_late; case PM_EVENT_HIBERNATE: return ops->poweroff_late; case PM_EVENT_THAW: case PM_EVENT_RECOVER: return ops->thaw_early; case PM_EVENT_RESTORE: return ops->restore_early; #endif /* CONFIG_HIBERNATE_CALLBACKS */ } return NULL; } /** * pm_noirq_op - Return the PM operation appropriate for given PM event. * @ops: PM operations to choose from. * @state: PM transition of the system being carried out. * * The driver of @dev will not receive interrupts while this function is being * executed. */ static pm_callback_t pm_noirq_op(const struct dev_pm_ops *ops, pm_message_t state) { switch (state.event) { #ifdef CONFIG_SUSPEND case PM_EVENT_SUSPEND: return ops->suspend_noirq; case PM_EVENT_RESUME: return ops->resume_noirq; #endif /* CONFIG_SUSPEND */ #ifdef CONFIG_HIBERNATE_CALLBACKS case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return ops->freeze_noirq; case PM_EVENT_HIBERNATE: return ops->poweroff_noirq; case PM_EVENT_THAW: case PM_EVENT_RECOVER: return ops->thaw_noirq; case PM_EVENT_RESTORE: return ops->restore_noirq; #endif /* CONFIG_HIBERNATE_CALLBACKS */ } return NULL; } static void pm_dev_dbg(struct device *dev, pm_message_t state, const char *info) { dev_dbg(dev, "%s%s%s driver flags: %x\n", info, pm_verb(state.event), ((state.event & PM_EVENT_SLEEP) && device_may_wakeup(dev)) ? ", may wakeup" : "", dev->power.driver_flags); } static void pm_dev_err(struct device *dev, pm_message_t state, const char *info, int error) { dev_err(dev, "failed to %s%s: error %d\n", pm_verb(state.event), info, error); } static void dpm_show_time(ktime_t starttime, pm_message_t state, int error, const char *info) { ktime_t calltime; u64 usecs64; int usecs; calltime = ktime_get(); usecs64 = ktime_to_ns(ktime_sub(calltime, starttime)); do_div(usecs64, NSEC_PER_USEC); usecs = usecs64; if (usecs == 0) usecs = 1; pm_pr_dbg("%s%s%s of devices %s after %ld.%03ld msecs\n", info ?: "", info ? " " : "", pm_verb(state.event), error ? "aborted" : "complete", usecs / USEC_PER_MSEC, usecs % USEC_PER_MSEC); } static int dpm_run_callback(pm_callback_t cb, struct device *dev, pm_message_t state, const char *info) { ktime_t calltime; int error; if (!cb) return 0; calltime = initcall_debug_start(dev, cb); pm_dev_dbg(dev, state, info); trace_device_pm_callback_start(dev, info, state.event); error = cb(dev); trace_device_pm_callback_end(dev, error); suspend_report_result(dev, cb, error); initcall_debug_report(dev, calltime, cb, error); return error; } #ifdef CONFIG_DPM_WATCHDOG struct dpm_watchdog { struct device *dev; struct task_struct *tsk; struct timer_list timer; }; #define DECLARE_DPM_WATCHDOG_ON_STACK(wd) \ struct dpm_watchdog wd /** * dpm_watchdog_handler - Driver suspend / resume watchdog handler. * @t: The timer that PM watchdog depends on. * * Called when a driver has timed out suspending or resuming. * There's not much we can do here to recover so panic() to * capture a crash-dump in pstore. */ static void dpm_watchdog_handler(struct timer_list *t) { struct dpm_watchdog *wd = from_timer(wd, t, timer); dev_emerg(wd->dev, "**** DPM device timeout ****\n"); show_stack(wd->tsk, NULL, KERN_EMERG); panic("%s %s: unrecoverable failure\n", dev_driver_string(wd->dev), dev_name(wd->dev)); } /** * dpm_watchdog_set - Enable pm watchdog for given device. * @wd: Watchdog. Must be allocated on the stack. * @dev: Device to handle. */ static void dpm_watchdog_set(struct dpm_watchdog *wd, struct device *dev) { struct timer_list *timer = &wd->timer; wd->dev = dev; wd->tsk = current; timer_setup_on_stack(timer, dpm_watchdog_handler, 0); /* use same timeout value for both suspend and resume */ timer->expires = jiffies + HZ * CONFIG_DPM_WATCHDOG_TIMEOUT; add_timer(timer); } /** * dpm_watchdog_clear - Disable suspend/resume watchdog. * @wd: Watchdog to disable. */ static void dpm_watchdog_clear(struct dpm_watchdog *wd) { struct timer_list *timer = &wd->timer; del_timer_sync(timer); destroy_timer_on_stack(timer); } #else #define DECLARE_DPM_WATCHDOG_ON_STACK(wd) #define dpm_watchdog_set(x, y) #define dpm_watchdog_clear(x) #endif /*------------------------- Resume routines -------------------------*/ /** * dev_pm_skip_resume - System-wide device resume optimization check. * @dev: Target device. * * Return: * - %false if the transition under way is RESTORE. * - Return value of dev_pm_skip_suspend() if the transition under way is THAW. * - The logical negation of %power.must_resume otherwise (that is, when the * transition under way is RESUME). */ bool dev_pm_skip_resume(struct device *dev) { if (pm_transition.event == PM_EVENT_RESTORE) return false; if (pm_transition.event == PM_EVENT_THAW) return dev_pm_skip_suspend(dev); return !dev->power.must_resume; } static bool is_async(struct device *dev) { return dev->power.async_suspend && pm_async_enabled && !pm_trace_is_enabled(); } static bool dpm_async_fn(struct device *dev, async_func_t func) { reinit_completion(&dev->power.completion); if (is_async(dev)) { dev->power.async_in_progress = true; get_device(dev); if (async_schedule_dev_nocall(func, dev)) return true; put_device(dev); } /* * Because async_schedule_dev_nocall() above has returned false or it * has not been called at all, func() is not running and it is safe to * update the async_in_progress flag without extra synchronization. */ dev->power.async_in_progress = false; return false; } /** * device_resume_noirq - Execute a "noirq resume" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. * * The driver of @dev will not receive interrupts while this function is being * executed. */ static void device_resume_noirq(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; bool skip_resume; int error = 0; TRACE_DEVICE(dev); TRACE_RESUME(0); if (dev->power.syscore || dev->power.direct_complete) goto Out; if (!dev->power.is_noirq_suspended) goto Out; if (!dpm_wait_for_superior(dev, async)) goto Out; skip_resume = dev_pm_skip_resume(dev); /* * If the driver callback is skipped below or by the middle layer * callback and device_resume_early() also skips the driver callback for * this device later, it needs to appear as "suspended" to PM-runtime, * so change its status accordingly. * * Otherwise, the device is going to be resumed, so set its PM-runtime * status to "active", but do that only if DPM_FLAG_SMART_SUSPEND is set * to avoid confusing drivers that don't use it. */ if (skip_resume) pm_runtime_set_suspended(dev); else if (dev_pm_skip_suspend(dev)) pm_runtime_set_active(dev); if (dev->pm_domain) { info = "noirq power domain "; callback = pm_noirq_op(&dev->pm_domain->ops, state); } else if (dev->type && dev->type->pm) { info = "noirq type "; callback = pm_noirq_op(dev->type->pm, state); } else if (dev->class && dev->class->pm) { info = "noirq class "; callback = pm_noirq_op(dev->class->pm, state); } else if (dev->bus && dev->bus->pm) { info = "noirq bus "; callback = pm_noirq_op(dev->bus->pm, state); } if (callback) goto Run; if (skip_resume) goto Skip; if (dev->driver && dev->driver->pm) { info = "noirq driver "; callback = pm_noirq_op(dev->driver->pm, state); } Run: error = dpm_run_callback(callback, dev, state, info); Skip: dev->power.is_noirq_suspended = false; Out: complete_all(&dev->power.completion); TRACE_RESUME(error); if (error) { async_error = error; dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async noirq" : " noirq", error); } } static void async_resume_noirq(void *data, async_cookie_t cookie) { struct device *dev = data; device_resume_noirq(dev, pm_transition, true); put_device(dev); } static void dpm_noirq_resume_devices(pm_message_t state) { struct device *dev; ktime_t starttime = ktime_get(); trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, true); async_error = 0; pm_transition = state; mutex_lock(&dpm_list_mtx); /* * Trigger the resume of "async" devices upfront so they don't have to * wait for the "non-async" ones they don't depend on. */ list_for_each_entry(dev, &dpm_noirq_list, power.entry) dpm_async_fn(dev, async_resume_noirq); while (!list_empty(&dpm_noirq_list)) { dev = to_device(dpm_noirq_list.next); list_move_tail(&dev->power.entry, &dpm_late_early_list); if (!dev->power.async_in_progress) { get_device(dev); mutex_unlock(&dpm_list_mtx); device_resume_noirq(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); } } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); dpm_show_time(starttime, state, 0, "noirq"); if (async_error) dpm_save_failed_step(SUSPEND_RESUME_NOIRQ); trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false); } /** * dpm_resume_noirq - Execute "noirq resume" callbacks for all devices. * @state: PM transition of the system being carried out. * * Invoke the "noirq" resume callbacks for all devices in dpm_noirq_list and * allow device drivers' interrupt handlers to be called. */ void dpm_resume_noirq(pm_message_t state) { dpm_noirq_resume_devices(state); resume_device_irqs(); device_wakeup_disarm_wake_irqs(); } /** * device_resume_early - Execute an "early resume" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. * * Runtime PM is disabled for @dev while this function is being executed. */ static void device_resume_early(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; int error = 0; TRACE_DEVICE(dev); TRACE_RESUME(0); if (dev->power.syscore || dev->power.direct_complete) goto Out; if (!dev->power.is_late_suspended) goto Out; if (!dpm_wait_for_superior(dev, async)) goto Out; if (dev->pm_domain) { info = "early power domain "; callback = pm_late_early_op(&dev->pm_domain->ops, state); } else if (dev->type && dev->type->pm) { info = "early type "; callback = pm_late_early_op(dev->type->pm, state); } else if (dev->class && dev->class->pm) { info = "early class "; callback = pm_late_early_op(dev->class->pm, state); } else if (dev->bus && dev->bus->pm) { info = "early bus "; callback = pm_late_early_op(dev->bus->pm, state); } if (callback) goto Run; if (dev_pm_skip_resume(dev)) goto Skip; if (dev->driver && dev->driver->pm) { info = "early driver "; callback = pm_late_early_op(dev->driver->pm, state); } Run: error = dpm_run_callback(callback, dev, state, info); Skip: dev->power.is_late_suspended = false; Out: TRACE_RESUME(error); pm_runtime_enable(dev); complete_all(&dev->power.completion); if (error) { async_error = error; dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async early" : " early", error); } } static void async_resume_early(void *data, async_cookie_t cookie) { struct device *dev = data; device_resume_early(dev, pm_transition, true); put_device(dev); } /** * dpm_resume_early - Execute "early resume" callbacks for all devices. * @state: PM transition of the system being carried out. */ void dpm_resume_early(pm_message_t state) { struct device *dev; ktime_t starttime = ktime_get(); trace_suspend_resume(TPS("dpm_resume_early"), state.event, true); async_error = 0; pm_transition = state; mutex_lock(&dpm_list_mtx); /* * Trigger the resume of "async" devices upfront so they don't have to * wait for the "non-async" ones they don't depend on. */ list_for_each_entry(dev, &dpm_late_early_list, power.entry) dpm_async_fn(dev, async_resume_early); while (!list_empty(&dpm_late_early_list)) { dev = to_device(dpm_late_early_list.next); list_move_tail(&dev->power.entry, &dpm_suspended_list); if (!dev->power.async_in_progress) { get_device(dev); mutex_unlock(&dpm_list_mtx); device_resume_early(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); } } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); dpm_show_time(starttime, state, 0, "early"); if (async_error) dpm_save_failed_step(SUSPEND_RESUME_EARLY); trace_suspend_resume(TPS("dpm_resume_early"), state.event, false); } /** * dpm_resume_start - Execute "noirq" and "early" device callbacks. * @state: PM transition of the system being carried out. */ void dpm_resume_start(pm_message_t state) { dpm_resume_noirq(state); dpm_resume_early(state); } EXPORT_SYMBOL_GPL(dpm_resume_start); /** * device_resume - Execute "resume" callbacks for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. */ static void device_resume(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; int error = 0; DECLARE_DPM_WATCHDOG_ON_STACK(wd); TRACE_DEVICE(dev); TRACE_RESUME(0); if (dev->power.syscore) goto Complete; if (dev->power.direct_complete) { /* Match the pm_runtime_disable() in __device_suspend(). */ pm_runtime_enable(dev); goto Complete; } if (!dpm_wait_for_superior(dev, async)) goto Complete; dpm_watchdog_set(&wd, dev); device_lock(dev); /* * This is a fib. But we'll allow new children to be added below * a resumed device, even if the device hasn't been completed yet. */ dev->power.is_prepared = false; if (!dev->power.is_suspended) goto Unlock; if (dev->pm_domain) { info = "power domain "; callback = pm_op(&dev->pm_domain->ops, state); goto Driver; } if (dev->type && dev->type->pm) { info = "type "; callback = pm_op(dev->type->pm, state); goto Driver; } if (dev->class && dev->class->pm) { info = "class "; callback = pm_op(dev->class->pm, state); goto Driver; } if (dev->bus) { if (dev->bus->pm) { info = "bus "; callback = pm_op(dev->bus->pm, state); } else if (dev->bus->resume) { info = "legacy bus "; callback = dev->bus->resume; goto End; } } Driver: if (!callback && dev->driver && dev->driver->pm) { info = "driver "; callback = pm_op(dev->driver->pm, state); } End: error = dpm_run_callback(callback, dev, state, info); dev->power.is_suspended = false; Unlock: device_unlock(dev); dpm_watchdog_clear(&wd); Complete: complete_all(&dev->power.completion); TRACE_RESUME(error); if (error) { async_error = error; dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async" : "", error); } } static void async_resume(void *data, async_cookie_t cookie) { struct device *dev = data; device_resume(dev, pm_transition, true); put_device(dev); } /** * dpm_resume - Execute "resume" callbacks for non-sysdev devices. * @state: PM transition of the system being carried out. * * Execute the appropriate "resume" callback for all devices whose status * indicates that they are suspended. */ void dpm_resume(pm_message_t state) { struct device *dev; ktime_t starttime = ktime_get(); trace_suspend_resume(TPS("dpm_resume"), state.event, true); might_sleep(); pm_transition = state; async_error = 0; mutex_lock(&dpm_list_mtx); /* * Trigger the resume of "async" devices upfront so they don't have to * wait for the "non-async" ones they don't depend on. */ list_for_each_entry(dev, &dpm_suspended_list, power.entry) dpm_async_fn(dev, async_resume); while (!list_empty(&dpm_suspended_list)) { dev = to_device(dpm_suspended_list.next); list_move_tail(&dev->power.entry, &dpm_prepared_list); if (!dev->power.async_in_progress) { get_device(dev); mutex_unlock(&dpm_list_mtx); device_resume(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); } } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); dpm_show_time(starttime, state, 0, NULL); if (async_error) dpm_save_failed_step(SUSPEND_RESUME); cpufreq_resume(); devfreq_resume(); trace_suspend_resume(TPS("dpm_resume"), state.event, false); } /** * device_complete - Complete a PM transition for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. */ static void device_complete(struct device *dev, pm_message_t state) { void (*callback)(struct device *) = NULL; const char *info = NULL; if (dev->power.syscore) goto out; device_lock(dev); if (dev->pm_domain) { info = "completing power domain "; callback = dev->pm_domain->ops.complete; } else if (dev->type && dev->type->pm) { info = "completing type "; callback = dev->type->pm->complete; } else if (dev->class && dev->class->pm) { info = "completing class "; callback = dev->class->pm->complete; } else if (dev->bus && dev->bus->pm) { info = "completing bus "; callback = dev->bus->pm->complete; } if (!callback && dev->driver && dev->driver->pm) { info = "completing driver "; callback = dev->driver->pm->complete; } if (callback) { pm_dev_dbg(dev, state, info); callback(dev); } device_unlock(dev); out: pm_runtime_put(dev); } /** * dpm_complete - Complete a PM transition for all non-sysdev devices. * @state: PM transition of the system being carried out. * * Execute the ->complete() callbacks for all devices whose PM status is not * DPM_ON (this allows new devices to be registered). */ void dpm_complete(pm_message_t state) { struct list_head list; trace_suspend_resume(TPS("dpm_complete"), state.event, true); might_sleep(); INIT_LIST_HEAD(&list); mutex_lock(&dpm_list_mtx); while (!list_empty(&dpm_prepared_list)) { struct device *dev = to_device(dpm_prepared_list.prev); get_device(dev); dev->power.is_prepared = false; list_move(&dev->power.entry, &list); mutex_unlock(&dpm_list_mtx); trace_device_pm_callback_start(dev, "", state.event); device_complete(dev, state); trace_device_pm_callback_end(dev, 0); put_device(dev); mutex_lock(&dpm_list_mtx); } list_splice(&list, &dpm_list); mutex_unlock(&dpm_list_mtx); /* Allow device probing and trigger re-probing of deferred devices */ device_unblock_probing(); trace_suspend_resume(TPS("dpm_complete"), state.event, false); } /** * dpm_resume_end - Execute "resume" callbacks and complete system transition. * @state: PM transition of the system being carried out. * * Execute "resume" callbacks for all devices and complete the PM transition of * the system. */ void dpm_resume_end(pm_message_t state) { dpm_resume(state); dpm_complete(state); } EXPORT_SYMBOL_GPL(dpm_resume_end); /*------------------------- Suspend routines -------------------------*/ /** * resume_event - Return a "resume" message for given "suspend" sleep state. * @sleep_state: PM message representing a sleep state. * * Return a PM message representing the resume event corresponding to given * sleep state. */ static pm_message_t resume_event(pm_message_t sleep_state) { switch (sleep_state.event) { case PM_EVENT_SUSPEND: return PMSG_RESUME; case PM_EVENT_FREEZE: case PM_EVENT_QUIESCE: return PMSG_RECOVER; case PM_EVENT_HIBERNATE: return PMSG_RESTORE; } return PMSG_ON; } static void dpm_superior_set_must_resume(struct device *dev) { struct device_link *link; int idx; if (dev->parent) dev->parent->power.must_resume = true; idx = device_links_read_lock(); list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node) link->supplier->power.must_resume = true; device_links_read_unlock(idx); } /** * device_suspend_noirq - Execute a "noirq suspend" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being suspended asynchronously. * * The driver of @dev will not receive interrupts while this function is being * executed. */ static int device_suspend_noirq(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; int error = 0; TRACE_DEVICE(dev); TRACE_SUSPEND(0); dpm_wait_for_subordinate(dev, async); if (async_error) goto Complete; if (dev->power.syscore || dev->power.direct_complete) goto Complete; if (dev->pm_domain) { info = "noirq power domain "; callback = pm_noirq_op(&dev->pm_domain->ops, state); } else if (dev->type && dev->type->pm) { info = "noirq type "; callback = pm_noirq_op(dev->type->pm, state); } else if (dev->class && dev->class->pm) { info = "noirq class "; callback = pm_noirq_op(dev->class->pm, state); } else if (dev->bus && dev->bus->pm) { info = "noirq bus "; callback = pm_noirq_op(dev->bus->pm, state); } if (callback) goto Run; if (dev_pm_skip_suspend(dev)) goto Skip; if (dev->driver && dev->driver->pm) { info = "noirq driver "; callback = pm_noirq_op(dev->driver->pm, state); } Run: error = dpm_run_callback(callback, dev, state, info); if (error) { async_error = error; dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async noirq" : " noirq", error); goto Complete; } Skip: dev->power.is_noirq_suspended = true; /* * Skipping the resume of devices that were in use right before the * system suspend (as indicated by their PM-runtime usage counters) * would be suboptimal. Also resume them if doing that is not allowed * to be skipped. */ if (atomic_read(&dev->power.usage_count) > 1 || !(dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME) && dev->power.may_skip_resume)) dev->power.must_resume = true; if (dev->power.must_resume) dpm_superior_set_must_resume(dev); Complete: complete_all(&dev->power.completion); TRACE_SUSPEND(error); return error; } static void async_suspend_noirq(void *data, async_cookie_t cookie) { struct device *dev = data; device_suspend_noirq(dev, pm_transition, true); put_device(dev); } static int dpm_noirq_suspend_devices(pm_message_t state) { ktime_t starttime = ktime_get(); int error = 0; trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, true); pm_transition = state; async_error = 0; mutex_lock(&dpm_list_mtx); while (!list_empty(&dpm_late_early_list)) { struct device *dev = to_device(dpm_late_early_list.prev); list_move(&dev->power.entry, &dpm_noirq_list); if (dpm_async_fn(dev, async_suspend_noirq)) continue; get_device(dev); mutex_unlock(&dpm_list_mtx); error = device_suspend_noirq(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); if (!error) error = async_error; if (error) dpm_save_failed_step(SUSPEND_SUSPEND_NOIRQ); dpm_show_time(starttime, state, error, "noirq"); trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, false); return error; } /** * dpm_suspend_noirq - Execute "noirq suspend" callbacks for all devices. * @state: PM transition of the system being carried out. * * Prevent device drivers' interrupt handlers from being called and invoke * "noirq" suspend callbacks for all non-sysdev devices. */ int dpm_suspend_noirq(pm_message_t state) { int ret; device_wakeup_arm_wake_irqs(); suspend_device_irqs(); ret = dpm_noirq_suspend_devices(state); if (ret) dpm_resume_noirq(resume_event(state)); return ret; } static void dpm_propagate_wakeup_to_parent(struct device *dev) { struct device *parent = dev->parent; if (!parent) return; spin_lock_irq(&parent->power.lock); if (device_wakeup_path(dev) && !parent->power.ignore_children) parent->power.wakeup_path = true; spin_unlock_irq(&parent->power.lock); } /** * device_suspend_late - Execute a "late suspend" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being suspended asynchronously. * * Runtime PM is disabled for @dev while this function is being executed. */ static int device_suspend_late(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; int error = 0; TRACE_DEVICE(dev); TRACE_SUSPEND(0); __pm_runtime_disable(dev, false); dpm_wait_for_subordinate(dev, async); if (async_error) goto Complete; if (pm_wakeup_pending()) { async_error = -EBUSY; goto Complete; } if (dev->power.syscore || dev->power.direct_complete) goto Complete; if (dev->pm_domain) { info = "late power domain "; callback = pm_late_early_op(&dev->pm_domain->ops, state); } else if (dev->type && dev->type->pm) { info = "late type "; callback = pm_late_early_op(dev->type->pm, state); } else if (dev->class && dev->class->pm) { info = "late class "; callback = pm_late_early_op(dev->class->pm, state); } else if (dev->bus && dev->bus->pm) { info = "late bus "; callback = pm_late_early_op(dev->bus->pm, state); } if (callback) goto Run; if (dev_pm_skip_suspend(dev)) goto Skip; if (dev->driver && dev->driver->pm) { info = "late driver "; callback = pm_late_early_op(dev->driver->pm, state); } Run: error = dpm_run_callback(callback, dev, state, info); if (error) { async_error = error; dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async late" : " late", error); goto Complete; } dpm_propagate_wakeup_to_parent(dev); Skip: dev->power.is_late_suspended = true; Complete: TRACE_SUSPEND(error); complete_all(&dev->power.completion); return error; } static void async_suspend_late(void *data, async_cookie_t cookie) { struct device *dev = data; device_suspend_late(dev, pm_transition, true); put_device(dev); } /** * dpm_suspend_late - Execute "late suspend" callbacks for all devices. * @state: PM transition of the system being carried out. */ int dpm_suspend_late(pm_message_t state) { ktime_t starttime = ktime_get(); int error = 0; trace_suspend_resume(TPS("dpm_suspend_late"), state.event, true); pm_transition = state; async_error = 0; wake_up_all_idle_cpus(); mutex_lock(&dpm_list_mtx); while (!list_empty(&dpm_suspended_list)) { struct device *dev = to_device(dpm_suspended_list.prev); list_move(&dev->power.entry, &dpm_late_early_list); if (dpm_async_fn(dev, async_suspend_late)) continue; get_device(dev); mutex_unlock(&dpm_list_mtx); error = device_suspend_late(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); if (!error) error = async_error; if (error) { dpm_save_failed_step(SUSPEND_SUSPEND_LATE); dpm_resume_early(resume_event(state)); } dpm_show_time(starttime, state, error, "late"); trace_suspend_resume(TPS("dpm_suspend_late"), state.event, false); return error; } /** * dpm_suspend_end - Execute "late" and "noirq" device suspend callbacks. * @state: PM transition of the system being carried out. */ int dpm_suspend_end(pm_message_t state) { ktime_t starttime = ktime_get(); int error; error = dpm_suspend_late(state); if (error) goto out; error = dpm_suspend_noirq(state); if (error) dpm_resume_early(resume_event(state)); out: dpm_show_time(starttime, state, error, "end"); return error; } EXPORT_SYMBOL_GPL(dpm_suspend_end); /** * legacy_suspend - Execute a legacy (bus or class) suspend callback for device. * @dev: Device to suspend. * @state: PM transition of the system being carried out. * @cb: Suspend callback to execute. * @info: string description of caller. */ static int legacy_suspend(struct device *dev, pm_message_t state, int (*cb)(struct device *dev, pm_message_t state), const char *info) { int error; ktime_t calltime; calltime = initcall_debug_start(dev, cb); trace_device_pm_callback_start(dev, info, state.event); error = cb(dev, state); trace_device_pm_callback_end(dev, error); suspend_report_result(dev, cb, error); initcall_debug_report(dev, calltime, cb, error); return error; } static void dpm_clear_superiors_direct_complete(struct device *dev) { struct device_link *link; int idx; if (dev->parent) { spin_lock_irq(&dev->parent->power.lock); dev->parent->power.direct_complete = false; spin_unlock_irq(&dev->parent->power.lock); } idx = device_links_read_lock(); list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node) { spin_lock_irq(&link->supplier->power.lock); link->supplier->power.direct_complete = false; spin_unlock_irq(&link->supplier->power.lock); } device_links_read_unlock(idx); } /** * device_suspend - Execute "suspend" callbacks for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being suspended asynchronously. */ static int device_suspend(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; int error = 0; DECLARE_DPM_WATCHDOG_ON_STACK(wd); TRACE_DEVICE(dev); TRACE_SUSPEND(0); dpm_wait_for_subordinate(dev, async); if (async_error) { dev->power.direct_complete = false; goto Complete; } /* * Wait for possible runtime PM transitions of the device in progress * to complete and if there's a runtime resume request pending for it, * resume it before proceeding with invoking the system-wide suspend * callbacks for it. * * If the system-wide suspend callbacks below change the configuration * of the device, they must disable runtime PM for it or otherwise * ensure that its runtime-resume callbacks will not be confused by that * change in case they are invoked going forward. */ pm_runtime_barrier(dev); if (pm_wakeup_pending()) { dev->power.direct_complete = false; async_error = -EBUSY; goto Complete; } if (dev->power.syscore) goto Complete; /* Avoid direct_complete to let wakeup_path propagate. */ if (device_may_wakeup(dev) || device_wakeup_path(dev)) dev->power.direct_complete = false; if (dev->power.direct_complete) { if (pm_runtime_status_suspended(dev)) { pm_runtime_disable(dev); if (pm_runtime_status_suspended(dev)) { pm_dev_dbg(dev, state, "direct-complete "); goto Complete; } pm_runtime_enable(dev); } dev->power.direct_complete = false; } dev->power.may_skip_resume = true; dev->power.must_resume = !dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME); dpm_watchdog_set(&wd, dev); device_lock(dev); if (dev->pm_domain) { info = "power domain "; callback = pm_op(&dev->pm_domain->ops, state); goto Run; } if (dev->type && dev->type->pm) { info = "type "; callback = pm_op(dev->type->pm, state); goto Run; } if (dev->class && dev->class->pm) { info = "class "; callback = pm_op(dev->class->pm, state); goto Run; } if (dev->bus) { if (dev->bus->pm) { info = "bus "; callback = pm_op(dev->bus->pm, state); } else if (dev->bus->suspend) { pm_dev_dbg(dev, state, "legacy bus "); error = legacy_suspend(dev, state, dev->bus->suspend, "legacy bus "); goto End; } } Run: if (!callback && dev->driver && dev->driver->pm) { info = "driver "; callback = pm_op(dev->driver->pm, state); } error = dpm_run_callback(callback, dev, state, info); End: if (!error) { dev->power.is_suspended = true; if (device_may_wakeup(dev)) dev->power.wakeup_path = true; dpm_propagate_wakeup_to_parent(dev); dpm_clear_superiors_direct_complete(dev); } device_unlock(dev); dpm_watchdog_clear(&wd); Complete: if (error) { async_error = error; dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async" : "", error); } complete_all(&dev->power.completion); TRACE_SUSPEND(error); return error; } static void async_suspend(void *data, async_cookie_t cookie) { struct device *dev = data; device_suspend(dev, pm_transition, true); put_device(dev); } /** * dpm_suspend - Execute "suspend" callbacks for all non-sysdev devices. * @state: PM transition of the system being carried out. */ int dpm_suspend(pm_message_t state) { ktime_t starttime = ktime_get(); int error = 0; trace_suspend_resume(TPS("dpm_suspend"), state.event, true); might_sleep(); devfreq_suspend(); cpufreq_suspend(); pm_transition = state; async_error = 0; mutex_lock(&dpm_list_mtx); while (!list_empty(&dpm_prepared_list)) { struct device *dev = to_device(dpm_prepared_list.prev); list_move(&dev->power.entry, &dpm_suspended_list); if (dpm_async_fn(dev, async_suspend)) continue; get_device(dev); mutex_unlock(&dpm_list_mtx); error = device_suspend(dev, state, false); put_device(dev); mutex_lock(&dpm_list_mtx); if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); if (!error) error = async_error; if (error) dpm_save_failed_step(SUSPEND_SUSPEND); dpm_show_time(starttime, state, error, NULL); trace_suspend_resume(TPS("dpm_suspend"), state.event, false); return error; } /** * device_prepare - Prepare a device for system power transition. * @dev: Device to handle. * @state: PM transition of the system being carried out. * * Execute the ->prepare() callback(s) for given device. No new children of the * device may be registered after this function has returned. */ static int device_prepare(struct device *dev, pm_message_t state) { int (*callback)(struct device *) = NULL; int ret = 0; /* * If a device's parent goes into runtime suspend at the wrong time, * it won't be possible to resume the device. To prevent this we * block runtime suspend here, during the prepare phase, and allow * it again during the complete phase. */ pm_runtime_get_noresume(dev); if (dev->power.syscore) return 0; device_lock(dev); dev->power.wakeup_path = false; if (dev->power.no_pm_callbacks) goto unlock; if (dev->pm_domain) callback = dev->pm_domain->ops.prepare; else if (dev->type && dev->type->pm) callback = dev->type->pm->prepare; else if (dev->class && dev->class->pm) callback = dev->class->pm->prepare; else if (dev->bus && dev->bus->pm) callback = dev->bus->pm->prepare; if (!callback && dev->driver && dev->driver->pm) callback = dev->driver->pm->prepare; if (callback) ret = callback(dev); unlock: device_unlock(dev); if (ret < 0) { suspend_report_result(dev, callback, ret); pm_runtime_put(dev); return ret; } /* * A positive return value from ->prepare() means "this device appears * to be runtime-suspended and its state is fine, so if it really is * runtime-suspended, you can leave it in that state provided that you * will do the same thing with all of its descendants". This only * applies to suspend transitions, however. */ spin_lock_irq(&dev->power.lock); dev->power.direct_complete = state.event == PM_EVENT_SUSPEND && (ret > 0 || dev->power.no_pm_callbacks) && !dev_pm_test_driver_flags(dev, DPM_FLAG_NO_DIRECT_COMPLETE); spin_unlock_irq(&dev->power.lock); return 0; } /** * dpm_prepare - Prepare all non-sysdev devices for a system PM transition. * @state: PM transition of the system being carried out. * * Execute the ->prepare() callback(s) for all devices. */ int dpm_prepare(pm_message_t state) { int error = 0; trace_suspend_resume(TPS("dpm_prepare"), state.event, true); might_sleep(); /* * Give a chance for the known devices to complete their probes, before * disable probing of devices. This sync point is important at least * at boot time + hibernation restore. */ wait_for_device_probe(); /* * It is unsafe if probing of devices will happen during suspend or * hibernation and system behavior will be unpredictable in this case. * So, let's prohibit device's probing here and defer their probes * instead. The normal behavior will be restored in dpm_complete(). */ device_block_probing(); mutex_lock(&dpm_list_mtx); while (!list_empty(&dpm_list) && !error) { struct device *dev = to_device(dpm_list.next); get_device(dev); mutex_unlock(&dpm_list_mtx); trace_device_pm_callback_start(dev, "", state.event); error = device_prepare(dev, state); trace_device_pm_callback_end(dev, error); mutex_lock(&dpm_list_mtx); if (!error) { dev->power.is_prepared = true; if (!list_empty(&dev->power.entry)) list_move_tail(&dev->power.entry, &dpm_prepared_list); } else if (error == -EAGAIN) { error = 0; } else { dev_info(dev, "not prepared for power transition: code %d\n", error); } mutex_unlock(&dpm_list_mtx); put_device(dev); mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); trace_suspend_resume(TPS("dpm_prepare"), state.event, false); return error; } /** * dpm_suspend_start - Prepare devices for PM transition and suspend them. * @state: PM transition of the system being carried out. * * Prepare all non-sysdev devices for system PM transition and execute "suspend" * callbacks for them. */ int dpm_suspend_start(pm_message_t state) { ktime_t starttime = ktime_get(); int error; error = dpm_prepare(state); if (error) dpm_save_failed_step(SUSPEND_PREPARE); else error = dpm_suspend(state); dpm_show_time(starttime, state, error, "start"); return error; } EXPORT_SYMBOL_GPL(dpm_suspend_start); void __suspend_report_result(const char *function, struct device *dev, void *fn, int ret) { if (ret) dev_err(dev, "%s(): %ps returns %d\n", function, fn, ret); } EXPORT_SYMBOL_GPL(__suspend_report_result); /** * device_pm_wait_for_dev - Wait for suspend/resume of a device to complete. * @subordinate: Device that needs to wait for @dev. * @dev: Device to wait for. */ int device_pm_wait_for_dev(struct device *subordinate, struct device *dev) { dpm_wait(dev, subordinate->power.async_suspend); return async_error; } EXPORT_SYMBOL_GPL(device_pm_wait_for_dev); /** * dpm_for_each_dev - device iterator. * @data: data for the callback. * @fn: function to be called for each device. * * Iterate over devices in dpm_list, and call @fn for each device, * passing it @data. */ void dpm_for_each_dev(void *data, void (*fn)(struct device *, void *)) { struct device *dev; if (!fn) return; device_pm_lock(); list_for_each_entry(dev, &dpm_list, power.entry) fn(dev, data); device_pm_unlock(); } EXPORT_SYMBOL_GPL(dpm_for_each_dev); static bool pm_ops_is_empty(const struct dev_pm_ops *ops) { if (!ops) return true; return !ops->prepare && !ops->suspend && !ops->suspend_late && !ops->suspend_noirq && !ops->resume_noirq && !ops->resume_early && !ops->resume && !ops->complete; } void device_pm_check_callbacks(struct device *dev) { unsigned long flags; spin_lock_irqsave(&dev->power.lock, flags); dev->power.no_pm_callbacks = (!dev->bus || (pm_ops_is_empty(dev->bus->pm) && !dev->bus->suspend && !dev->bus->resume)) && (!dev->class || pm_ops_is_empty(dev->class->pm)) && (!dev->type || pm_ops_is_empty(dev->type->pm)) && (!dev->pm_domain || pm_ops_is_empty(&dev->pm_domain->ops)) && (!dev->driver || (pm_ops_is_empty(dev->driver->pm) && !dev->driver->suspend && !dev->driver->resume)); spin_unlock_irqrestore(&dev->power.lock, flags); } bool dev_pm_skip_suspend(struct device *dev) { return dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) && pm_runtime_status_suspended(dev); } |
| 369 369 369 21 21 12 15 358 310 278 352 359 2 310 356 213 160 365 364 227 26 36 2 358 6 247 156 202 84 1 1 83 83 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hfsplus/bfind.c * * Copyright (C) 2001 * Brad Boyer (flar@allandria.com) * (C) 2003 Ardis Technologies <roman@ardistech.com> * * Search routines for btrees */ #include <linux/slab.h> #include "hfsplus_fs.h" int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) { void *ptr; fd->tree = tree; fd->bnode = NULL; ptr = kmalloc(tree->max_key_len * 2 + 4, GFP_KERNEL); if (!ptr) return -ENOMEM; fd->search_key = ptr; fd->key = ptr + tree->max_key_len + 2; hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0)); mutex_lock_nested(&tree->tree_lock, hfsplus_btree_lock_class(tree)); return 0; } void hfs_find_exit(struct hfs_find_data *fd) { hfs_bnode_put(fd->bnode); kfree(fd->search_key); hfs_dbg(BNODE_REFS, "find_exit: %d (%p)\n", fd->tree->cnid, __builtin_return_address(0)); mutex_unlock(&fd->tree->tree_lock); fd->tree = NULL; } int hfs_find_1st_rec_by_cnid(struct hfs_bnode *bnode, struct hfs_find_data *fd, int *begin, int *end, int *cur_rec) { __be32 cur_cnid; __be32 search_cnid; if (bnode->tree->cnid == HFSPLUS_EXT_CNID) { cur_cnid = fd->key->ext.cnid; search_cnid = fd->search_key->ext.cnid; } else if (bnode->tree->cnid == HFSPLUS_CAT_CNID) { cur_cnid = fd->key->cat.parent; search_cnid = fd->search_key->cat.parent; } else if (bnode->tree->cnid == HFSPLUS_ATTR_CNID) { cur_cnid = fd->key->attr.cnid; search_cnid = fd->search_key->attr.cnid; } else { cur_cnid = 0; /* used-uninitialized warning */ search_cnid = 0; BUG(); } if (cur_cnid == search_cnid) { (*end) = (*cur_rec); if ((*begin) == (*end)) return 1; } else { if (be32_to_cpu(cur_cnid) < be32_to_cpu(search_cnid)) (*begin) = (*cur_rec) + 1; else (*end) = (*cur_rec) - 1; } return 0; } int hfs_find_rec_by_key(struct hfs_bnode *bnode, struct hfs_find_data *fd, int *begin, int *end, int *cur_rec) { int cmpval; cmpval = bnode->tree->keycmp(fd->key, fd->search_key); if (!cmpval) { (*end) = (*cur_rec); return 1; } if (cmpval < 0) (*begin) = (*cur_rec) + 1; else *(end) = (*cur_rec) - 1; return 0; } /* Find the record in bnode that best matches key (not greater than...)*/ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd, search_strategy_t rec_found) { u16 off, len, keylen; int rec; int b, e; int res; BUG_ON(!rec_found); b = 0; e = bnode->num_recs - 1; res = -ENOENT; do { rec = (e + b) / 2; len = hfs_brec_lenoff(bnode, rec, &off); keylen = hfs_brec_keylen(bnode, rec); if (keylen == 0) { res = -EINVAL; goto fail; } hfs_bnode_read(bnode, fd->key, off, keylen); if (rec_found(bnode, fd, &b, &e, &rec)) { res = 0; goto done; } } while (b <= e); if (rec != e && e >= 0) { len = hfs_brec_lenoff(bnode, e, &off); keylen = hfs_brec_keylen(bnode, e); if (keylen == 0) { res = -EINVAL; goto fail; } hfs_bnode_read(bnode, fd->key, off, keylen); } done: fd->record = e; fd->keyoffset = off; fd->keylength = keylen; fd->entryoffset = off + keylen; fd->entrylength = len - keylen; fail: return res; } /* Traverse a B*Tree from the root to a leaf finding best fit to key */ /* Return allocated copy of node found, set recnum to best record */ int hfs_brec_find(struct hfs_find_data *fd, search_strategy_t do_key_compare) { struct hfs_btree *tree; struct hfs_bnode *bnode; u32 nidx, parent; __be32 data; int height, res; tree = fd->tree; if (fd->bnode) hfs_bnode_put(fd->bnode); fd->bnode = NULL; nidx = tree->root; if (!nidx) return -ENOENT; height = tree->depth; res = 0; parent = 0; for (;;) { bnode = hfs_bnode_find(tree, nidx); if (IS_ERR(bnode)) { res = PTR_ERR(bnode); bnode = NULL; break; } if (bnode->height != height) goto invalid; if (bnode->type != (--height ? HFS_NODE_INDEX : HFS_NODE_LEAF)) goto invalid; bnode->parent = parent; res = __hfs_brec_find(bnode, fd, do_key_compare); if (!height) break; if (fd->record < 0) goto release; parent = nidx; hfs_bnode_read(bnode, &data, fd->entryoffset, 4); nidx = be32_to_cpu(data); hfs_bnode_put(bnode); } fd->bnode = bnode; return res; invalid: pr_err("inconsistency in B*Tree (%d,%d,%d,%u,%u)\n", height, bnode->height, bnode->type, nidx, parent); res = -EIO; release: hfs_bnode_put(bnode); return res; } int hfs_brec_read(struct hfs_find_data *fd, void *rec, int rec_len) { int res; res = hfs_brec_find(fd, hfs_find_rec_by_key); if (res) return res; if (fd->entrylength > rec_len) return -EINVAL; hfs_bnode_read(fd->bnode, rec, fd->entryoffset, fd->entrylength); return 0; } int hfs_brec_goto(struct hfs_find_data *fd, int cnt) { struct hfs_btree *tree; struct hfs_bnode *bnode; int idx, res = 0; u16 off, len, keylen; bnode = fd->bnode; tree = bnode->tree; if (cnt < 0) { cnt = -cnt; while (cnt > fd->record) { cnt -= fd->record + 1; fd->record = bnode->num_recs - 1; idx = bnode->prev; if (!idx) { res = -ENOENT; goto out; } hfs_bnode_put(bnode); bnode = hfs_bnode_find(tree, idx); if (IS_ERR(bnode)) { res = PTR_ERR(bnode); bnode = NULL; goto out; } } fd->record -= cnt; } else { while (cnt >= bnode->num_recs - fd->record) { cnt -= bnode->num_recs - fd->record; fd->record = 0; idx = bnode->next; if (!idx) { res = -ENOENT; goto out; } hfs_bnode_put(bnode); bnode = hfs_bnode_find(tree, idx); if (IS_ERR(bnode)) { res = PTR_ERR(bnode); bnode = NULL; goto out; } } fd->record += cnt; } len = hfs_brec_lenoff(bnode, fd->record, &off); keylen = hfs_brec_keylen(bnode, fd->record); if (keylen == 0) { res = -EINVAL; goto out; } fd->keyoffset = off; fd->keylength = keylen; fd->entryoffset = off + keylen; fd->entrylength = len - keylen; hfs_bnode_read(bnode, fd->key, off, keylen); out: fd->bnode = bnode; return res; } |
| 69 3 67 70 70 70 71 2 67 69 68 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 | // SPDX-License-Identifier: GPL-2.0-only /* * umh - the kernel usermode helper */ #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/fs_struct.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 <linux/initrd.h> #include <linux/freezer.h> #include <trace/events/module.h> static kernel_cap_t usermodehelper_bset = CAP_FULL_SET; static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET; static DEFINE_SPINLOCK(umh_sysctl_lock); static DECLARE_RWSEM(umhelper_sem); static void call_usermodehelper_freeinfo(struct subprocess_info *info) { if (info->cleanup) (*info->cleanup)(info); kfree(info); } static void umh_complete(struct subprocess_info *sub_info) { struct completion *comp = xchg(&sub_info->complete, NULL); /* * See call_usermodehelper_exec(). If xchg() returns NULL * we own sub_info, the UMH_KILLABLE caller has gone away * or the caller used UMH_NO_WAIT. */ if (comp) complete(comp); else call_usermodehelper_freeinfo(sub_info); } /* * This is the task which runs the usermode application */ static int call_usermodehelper_exec_async(void *data) { struct subprocess_info *sub_info = data; struct cred *new; int retval; spin_lock_irq(¤t->sighand->siglock); flush_signal_handlers(current, 1); spin_unlock_irq(¤t->sighand->siglock); /* * Initial kernel threads share ther FS with init, in order to * get the init root directory. But we've now created a new * thread that is going to execve a user process and has its own * 'struct fs_struct'. Reset umask to the default. */ current->fs->umask = 0022; /* * Our parent (unbound workqueue) runs with elevated scheduling * priority. Avoid propagating that into the userspace child. */ set_user_nice(current, 0); retval = -ENOMEM; new = prepare_kernel_cred(current); if (!new) goto out; spin_lock(&umh_sysctl_lock); new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset); new->cap_inheritable = cap_intersect(usermodehelper_inheritable, new->cap_inheritable); spin_unlock(&umh_sysctl_lock); if (sub_info->init) { retval = sub_info->init(sub_info, new); if (retval) { abort_creds(new); goto out; } } commit_creds(new); wait_for_initramfs(); retval = kernel_execve(sub_info->path, (const char *const *)sub_info->argv, (const char *const *)sub_info->envp); out: sub_info->retval = retval; /* * call_usermodehelper_exec_sync() will call umh_complete * if UHM_WAIT_PROC. */ if (!(sub_info->wait & UMH_WAIT_PROC)) umh_complete(sub_info); if (!retval) return 0; do_exit(0); } /* Handles UMH_WAIT_PROC. */ static void call_usermodehelper_exec_sync(struct subprocess_info *sub_info) { pid_t pid; /* If SIGCLD is ignored do_wait won't populate the status. */ kernel_sigaction(SIGCHLD, SIG_DFL); pid = user_mode_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD); if (pid < 0) sub_info->retval = pid; else kernel_wait(pid, &sub_info->retval); /* Restore default kernel sig handler */ kernel_sigaction(SIGCHLD, SIG_IGN); umh_complete(sub_info); } /* * We need to create the usermodehelper kernel thread from a task that is affine * to an optimized set of CPUs (or nohz housekeeping ones) such that they * inherit a widest affinity irrespective of call_usermodehelper() callers with * possibly reduced affinity (eg: per-cpu workqueues). We don't want * usermodehelper targets to contend a busy CPU. * * Unbound workqueues provide such wide affinity and allow to block on * UMH_WAIT_PROC requests without blocking pending request (up to some limit). * * Besides, workqueues provide the privilege level that caller might not have * to perform the usermodehelper request. * */ static void call_usermodehelper_exec_work(struct work_struct *work) { struct subprocess_info *sub_info = container_of(work, struct subprocess_info, work); if (sub_info->wait & UMH_WAIT_PROC) { call_usermodehelper_exec_sync(sub_info); } else { pid_t pid; /* * Use CLONE_PARENT to reparent it to kthreadd; we do not * want to pollute current->children, and we need a parent * that always ignores SIGCHLD to ensure auto-reaping. */ pid = user_mode_thread(call_usermodehelper_exec_async, sub_info, CLONE_PARENT | SIGCHLD); if (pid < 0) { sub_info->retval = pid; umh_complete(sub_info); } } } /* * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY * (used for preventing user land processes from being created after the user * land has been frozen during a system-wide hibernation or suspend operation). * Should always be manipulated under umhelper_sem acquired for write. */ static enum umh_disable_depth usermodehelper_disabled = UMH_DISABLED; /* Number of helpers running */ static atomic_t running_helpers = ATOMIC_INIT(0); /* * Wait queue head used by usermodehelper_disable() to wait for all running * helpers to finish. */ static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq); /* * Used by usermodehelper_read_lock_wait() to wait for usermodehelper_disabled * to become 'false'. */ static DECLARE_WAIT_QUEUE_HEAD(usermodehelper_disabled_waitq); /* * Time to wait for running_helpers to become zero before the setting of * usermodehelper_disabled in usermodehelper_disable() fails */ #define RUNNING_HELPERS_TIMEOUT (5 * HZ) int usermodehelper_read_trylock(void) { DEFINE_WAIT(wait); int ret = 0; down_read(&umhelper_sem); for (;;) { prepare_to_wait(&usermodehelper_disabled_waitq, &wait, TASK_INTERRUPTIBLE); if (!usermodehelper_disabled) break; if (usermodehelper_disabled == UMH_DISABLED) ret = -EAGAIN; up_read(&umhelper_sem); if (ret) break; schedule(); try_to_freeze(); down_read(&umhelper_sem); } finish_wait(&usermodehelper_disabled_waitq, &wait); return ret; } EXPORT_SYMBOL_GPL(usermodehelper_read_trylock); long usermodehelper_read_lock_wait(long timeout) { DEFINE_WAIT(wait); if (timeout < 0) return -EINVAL; down_read(&umhelper_sem); for (;;) { prepare_to_wait(&usermodehelper_disabled_waitq, &wait, TASK_UNINTERRUPTIBLE); if (!usermodehelper_disabled) break; up_read(&umhelper_sem); timeout = schedule_timeout(timeout); if (!timeout) break; down_read(&umhelper_sem); } finish_wait(&usermodehelper_disabled_waitq, &wait); return timeout; } EXPORT_SYMBOL_GPL(usermodehelper_read_lock_wait); void usermodehelper_read_unlock(void) { up_read(&umhelper_sem); } EXPORT_SYMBOL_GPL(usermodehelper_read_unlock); /** * __usermodehelper_set_disable_depth - Modify usermodehelper_disabled. * @depth: New value to assign to usermodehelper_disabled. * * Change the value of usermodehelper_disabled (under umhelper_sem locked for * writing) and wakeup tasks waiting for it to change. */ void __usermodehelper_set_disable_depth(enum umh_disable_depth depth) { down_write(&umhelper_sem); usermodehelper_disabled = depth; wake_up(&usermodehelper_disabled_waitq); up_write(&umhelper_sem); } /** * __usermodehelper_disable - Prevent new helpers from being started. * @depth: New value to assign to usermodehelper_disabled. * * Set usermodehelper_disabled to @depth and wait for running helpers to exit. */ int __usermodehelper_disable(enum umh_disable_depth depth) { long retval; if (!depth) return -EINVAL; down_write(&umhelper_sem); usermodehelper_disabled = depth; up_write(&umhelper_sem); /* * From now on call_usermodehelper_exec() won't start any new * helpers, so it is sufficient if running_helpers turns out to * be zero at one point (it may be increased later, but that * doesn't matter). */ retval = wait_event_timeout(running_helpers_waitq, atomic_read(&running_helpers) == 0, RUNNING_HELPERS_TIMEOUT); if (retval) return 0; __usermodehelper_set_disable_depth(UMH_ENABLED); return -EAGAIN; } static void helper_lock(void) { atomic_inc(&running_helpers); smp_mb__after_atomic(); } static void helper_unlock(void) { if (atomic_dec_and_test(&running_helpers)) wake_up(&running_helpers_waitq); } /** * call_usermodehelper_setup - prepare to call a usermode helper * @path: path to usermode executable * @argv: arg vector for process * @envp: environment for process * @gfp_mask: gfp mask for memory allocation * @init: an init function * @cleanup: a cleanup function * @data: arbitrary context sensitive data * * Returns either %NULL on allocation failure, or a subprocess_info * structure. This should be passed to call_usermodehelper_exec to * exec the process and free the structure. * * The init function is used to customize the helper process prior to * exec. A non-zero return code causes the process to error out, exit, * and return the failure to the calling process * * The cleanup function is just before the subprocess_info is about to * be freed. This can be used for freeing the argv and envp. The * Function must be runnable in either a process context or the * context in which call_usermodehelper_exec is called. */ struct subprocess_info *call_usermodehelper_setup(const char *path, char **argv, char **envp, gfp_t gfp_mask, int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *info), void *data) { struct subprocess_info *sub_info; sub_info = kzalloc(sizeof(struct subprocess_info), gfp_mask); if (!sub_info) goto out; INIT_WORK(&sub_info->work, call_usermodehelper_exec_work); #ifdef CONFIG_STATIC_USERMODEHELPER sub_info->path = CONFIG_STATIC_USERMODEHELPER_PATH; #else sub_info->path = path; #endif sub_info->argv = argv; sub_info->envp = envp; sub_info->cleanup = cleanup; sub_info->init = init; sub_info->data = data; out: return sub_info; } EXPORT_SYMBOL(call_usermodehelper_setup); /** * call_usermodehelper_exec - start a usermode application * @sub_info: information about the subprocess * @wait: wait for the application to finish and return status. * when UMH_NO_WAIT don't wait at all, but you get no useful error back * when the program couldn't be exec'ed. This makes it safe to call * from interrupt context. * * Runs a user-space application. The application is started * asynchronously if wait is not set, and runs as a child of system workqueues. * (ie. it runs with full root capabilities and optimized affinity). * * Note: successful return value does not guarantee the helper was called at * all. You can't rely on sub_info->{init,cleanup} being called even for * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers * into a successful no-op. */ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) { unsigned int state = TASK_UNINTERRUPTIBLE; DECLARE_COMPLETION_ONSTACK(done); int retval = 0; if (!sub_info->path) { call_usermodehelper_freeinfo(sub_info); return -EINVAL; } helper_lock(); if (usermodehelper_disabled) { retval = -EBUSY; goto out; } /* * If there is no binary for us to call, then just return and get out of * here. This allows us to set STATIC_USERMODEHELPER_PATH to "" and * disable all call_usermodehelper() calls. */ if (strlen(sub_info->path) == 0) goto out; /* * Set the completion pointer only if there is a waiter. * This makes it possible to use umh_complete to free * the data structure in case of UMH_NO_WAIT. */ sub_info->complete = (wait == UMH_NO_WAIT) ? NULL : &done; sub_info->wait = wait; queue_work(system_unbound_wq, &sub_info->work); if (wait == UMH_NO_WAIT) /* task has freed sub_info */ goto unlock; if (wait & UMH_FREEZABLE) state |= TASK_FREEZABLE; if (wait & UMH_KILLABLE) { retval = wait_for_completion_state(&done, state | TASK_KILLABLE); if (!retval) goto wait_done; /* umh_complete() will see NULL and free sub_info */ if (xchg(&sub_info->complete, NULL)) goto unlock; /* * fallthrough; in case of -ERESTARTSYS now do uninterruptible * wait_for_completion_state(). Since umh_complete() shall call * complete() in a moment if xchg() above returned NULL, this * uninterruptible wait_for_completion_state() will not block * SIGKILL'ed processes for long. */ } wait_for_completion_state(&done, state); wait_done: retval = sub_info->retval; out: call_usermodehelper_freeinfo(sub_info); unlock: helper_unlock(); return retval; } EXPORT_SYMBOL(call_usermodehelper_exec); /** * call_usermodehelper() - prepare and start a usermode application * @path: path to usermode executable * @argv: arg vector for process * @envp: environment for process * @wait: wait for the application to finish and return status. * when UMH_NO_WAIT don't wait at all, but you get no useful error back * when the program couldn't be exec'ed. This makes it safe to call * from interrupt context. * * This function is the equivalent to use call_usermodehelper_setup() and * call_usermodehelper_exec(). */ int call_usermodehelper(const char *path, char **argv, char **envp, int wait) { struct subprocess_info *info; gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL; info = call_usermodehelper_setup(path, argv, envp, gfp_mask, NULL, NULL, NULL); if (info == NULL) return -ENOMEM; return call_usermodehelper_exec(info, wait); } EXPORT_SYMBOL(call_usermodehelper); #if defined(CONFIG_SYSCTL) static int proc_cap_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; unsigned long cap_array[2]; kernel_cap_t new_cap, *cap; int err; if (write && (!capable(CAP_SETPCAP) || !capable(CAP_SYS_MODULE))) return -EPERM; /* * convert from the global kernel_cap_t to the ulong array to print to * userspace if this is a read. * * Legacy format: capabilities are exposed as two 32-bit values */ cap = table->data; spin_lock(&umh_sysctl_lock); cap_array[0] = (u32) cap->val; cap_array[1] = cap->val >> 32; spin_unlock(&umh_sysctl_lock); t = *table; t.data = &cap_array; /* * actually read or write and array of ulongs from userspace. Remember * these are least significant 32 bits first */ err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos); if (err < 0) return err; new_cap.val = (u32)cap_array[0]; new_cap.val += (u64)cap_array[1] << 32; /* * Drop everything not in the new_cap (but don't add things) */ if (write) { spin_lock(&umh_sysctl_lock); *cap = cap_intersect(*cap, new_cap); spin_unlock(&umh_sysctl_lock); } return 0; } static struct ctl_table usermodehelper_table[] = { { .procname = "bset", .data = &usermodehelper_bset, .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, { .procname = "inheritable", .data = &usermodehelper_inheritable, .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, }; static int __init init_umh_sysctls(void) { register_sysctl_init("kernel/usermodehelper", usermodehelper_table); return 0; } early_initcall(init_umh_sysctls); #endif /* CONFIG_SYSCTL */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * stackglue.c * * Code which implements an OCFS2 specific interface to underlying * cluster stacks. * * Copyright (C) 2007, 2009 Oracle. All rights reserved. */ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/kmod.h> #include <linux/fs.h> #include <linux/kobject.h> #include <linux/sysfs.h> #include <linux/sysctl.h> #include "ocfs2_fs.h" #include "stackglue.h" #define OCFS2_STACK_PLUGIN_O2CB "o2cb" #define OCFS2_STACK_PLUGIN_USER "user" #define OCFS2_MAX_HB_CTL_PATH 256 static struct ocfs2_protocol_version locking_max_version; static DEFINE_SPINLOCK(ocfs2_stack_lock); static LIST_HEAD(ocfs2_stack_list); static char cluster_stack_name[OCFS2_STACK_LABEL_LEN + 1]; static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl"; /* * The stack currently in use. If not null, active_stack->sp_count > 0, * the module is pinned, and the locking protocol cannot be changed. */ static struct ocfs2_stack_plugin *active_stack; static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name) { struct ocfs2_stack_plugin *p; assert_spin_locked(&ocfs2_stack_lock); list_for_each_entry(p, &ocfs2_stack_list, sp_list) { if (!strcmp(p->sp_name, name)) return p; } return NULL; } static int ocfs2_stack_driver_request(const char *stack_name, const char *plugin_name) { int rc; struct ocfs2_stack_plugin *p; spin_lock(&ocfs2_stack_lock); /* * If the stack passed by the filesystem isn't the selected one, * we can't continue. */ if (strcmp(stack_name, cluster_stack_name)) { rc = -EBUSY; goto out; } if (active_stack) { /* * If the active stack isn't the one we want, it cannot * be selected right now. */ if (!strcmp(active_stack->sp_name, plugin_name)) rc = 0; else rc = -EBUSY; goto out; } p = ocfs2_stack_lookup(plugin_name); if (!p || !try_module_get(p->sp_owner)) { rc = -ENOENT; goto out; } active_stack = p; rc = 0; out: /* If we found it, pin it */ if (!rc) active_stack->sp_count++; spin_unlock(&ocfs2_stack_lock); return rc; } /* * This function looks up the appropriate stack and makes it active. If * there is no stack, it tries to load it. It will fail if the stack still * cannot be found. It will also fail if a different stack is in use. */ static int ocfs2_stack_driver_get(const char *stack_name) { int rc; char *plugin_name = OCFS2_STACK_PLUGIN_O2CB; /* * Classic stack does not pass in a stack name. This is * compatible with older tools as well. */ if (!stack_name || !*stack_name) stack_name = OCFS2_STACK_PLUGIN_O2CB; if (strlen(stack_name) != OCFS2_STACK_LABEL_LEN) { printk(KERN_ERR "ocfs2 passed an invalid cluster stack label: \"%s\"\n", stack_name); return -EINVAL; } /* Anything that isn't the classic stack is a user stack */ if (strcmp(stack_name, OCFS2_STACK_PLUGIN_O2CB)) plugin_name = OCFS2_STACK_PLUGIN_USER; rc = ocfs2_stack_driver_request(stack_name, plugin_name); if (rc == -ENOENT) { request_module("ocfs2_stack_%s", plugin_name); rc = ocfs2_stack_driver_request(stack_name, plugin_name); } if (rc == -ENOENT) { printk(KERN_ERR "ocfs2: Cluster stack driver \"%s\" cannot be found\n", plugin_name); } else if (rc == -EBUSY) { printk(KERN_ERR "ocfs2: A different cluster stack is in use\n"); } return rc; } static void ocfs2_stack_driver_put(void) { spin_lock(&ocfs2_stack_lock); BUG_ON(active_stack == NULL); BUG_ON(active_stack->sp_count == 0); active_stack->sp_count--; if (!active_stack->sp_count) { module_put(active_stack->sp_owner); active_stack = NULL; } spin_unlock(&ocfs2_stack_lock); } int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin) { int rc; spin_lock(&ocfs2_stack_lock); if (!ocfs2_stack_lookup(plugin->sp_name)) { plugin->sp_count = 0; plugin->sp_max_proto = locking_max_version; list_add(&plugin->sp_list, &ocfs2_stack_list); printk(KERN_INFO "ocfs2: Registered cluster interface %s\n", plugin->sp_name); rc = 0; } else { printk(KERN_ERR "ocfs2: Stack \"%s\" already registered\n", plugin->sp_name); rc = -EEXIST; } spin_unlock(&ocfs2_stack_lock); return rc; } EXPORT_SYMBOL_GPL(ocfs2_stack_glue_register); void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin) { struct ocfs2_stack_plugin *p; spin_lock(&ocfs2_stack_lock); p = ocfs2_stack_lookup(plugin->sp_name); if (p) { BUG_ON(p != plugin); BUG_ON(plugin == active_stack); BUG_ON(plugin->sp_count != 0); list_del_init(&plugin->sp_list); printk(KERN_INFO "ocfs2: Unregistered cluster interface %s\n", plugin->sp_name); } else { printk(KERN_ERR "Stack \"%s\" is not registered\n", plugin->sp_name); } spin_unlock(&ocfs2_stack_lock); } EXPORT_SYMBOL_GPL(ocfs2_stack_glue_unregister); void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_proto) { struct ocfs2_stack_plugin *p; spin_lock(&ocfs2_stack_lock); if (memcmp(max_proto, &locking_max_version, sizeof(struct ocfs2_protocol_version))) { BUG_ON(locking_max_version.pv_major != 0); locking_max_version = *max_proto; list_for_each_entry(p, &ocfs2_stack_list, sp_list) { p->sp_max_proto = locking_max_version; } } spin_unlock(&ocfs2_stack_lock); } EXPORT_SYMBOL_GPL(ocfs2_stack_glue_set_max_proto_version); /* * The ocfs2_dlm_lock() and ocfs2_dlm_unlock() functions take no argument * for the ast and bast functions. They will pass the lksb to the ast * and bast. The caller can wrap the lksb with their own structure to * get more information. */ int ocfs2_dlm_lock(struct ocfs2_cluster_connection *conn, int mode, struct ocfs2_dlm_lksb *lksb, u32 flags, void *name, unsigned int namelen) { if (!lksb->lksb_conn) lksb->lksb_conn = conn; else BUG_ON(lksb->lksb_conn != conn); return active_stack->sp_ops->dlm_lock(conn, mode, lksb, flags, name, namelen); } EXPORT_SYMBOL_GPL(ocfs2_dlm_lock); int ocfs2_dlm_unlock(struct ocfs2_cluster_connection *conn, struct ocfs2_dlm_lksb *lksb, u32 flags) { BUG_ON(lksb->lksb_conn == NULL); return active_stack->sp_ops->dlm_unlock(conn, lksb, flags); } EXPORT_SYMBOL_GPL(ocfs2_dlm_unlock); int ocfs2_dlm_lock_status(struct ocfs2_dlm_lksb *lksb) { return active_stack->sp_ops->lock_status(lksb); } EXPORT_SYMBOL_GPL(ocfs2_dlm_lock_status); int ocfs2_dlm_lvb_valid(struct ocfs2_dlm_lksb *lksb) { return active_stack->sp_ops->lvb_valid(lksb); } EXPORT_SYMBOL_GPL(ocfs2_dlm_lvb_valid); void *ocfs2_dlm_lvb(struct ocfs2_dlm_lksb *lksb) { return active_stack->sp_ops->lock_lvb(lksb); } EXPORT_SYMBOL_GPL(ocfs2_dlm_lvb); void ocfs2_dlm_dump_lksb(struct ocfs2_dlm_lksb *lksb) { active_stack->sp_ops->dump_lksb(lksb); } EXPORT_SYMBOL_GPL(ocfs2_dlm_dump_lksb); int ocfs2_stack_supports_plocks(void) { return active_stack && active_stack->sp_ops->plock; } EXPORT_SYMBOL_GPL(ocfs2_stack_supports_plocks); /* * ocfs2_plock() can only be safely called if * ocfs2_stack_supports_plocks() returned true */ int ocfs2_plock(struct ocfs2_cluster_connection *conn, u64 ino, struct file *file, int cmd, struct file_lock *fl) { WARN_ON_ONCE(active_stack->sp_ops->plock == NULL); if (active_stack->sp_ops->plock) return active_stack->sp_ops->plock(conn, ino, file, cmd, fl); return -EOPNOTSUPP; } EXPORT_SYMBOL_GPL(ocfs2_plock); int ocfs2_cluster_connect(const char *stack_name, const char *cluster_name, int cluster_name_len, const char *group, int grouplen, struct ocfs2_locking_protocol *lproto, void (*recovery_handler)(int node_num, void *recovery_data), void *recovery_data, struct ocfs2_cluster_connection **conn) { int rc = 0; struct ocfs2_cluster_connection *new_conn; BUG_ON(group == NULL); BUG_ON(conn == NULL); BUG_ON(recovery_handler == NULL); if (grouplen > GROUP_NAME_MAX) { rc = -EINVAL; goto out; } if (memcmp(&lproto->lp_max_version, &locking_max_version, sizeof(struct ocfs2_protocol_version))) { rc = -EINVAL; goto out; } new_conn = kzalloc(sizeof(struct ocfs2_cluster_connection), GFP_KERNEL); if (!new_conn) { rc = -ENOMEM; goto out; } strscpy(new_conn->cc_name, group, GROUP_NAME_MAX + 1); new_conn->cc_namelen = grouplen; if (cluster_name_len) strscpy(new_conn->cc_cluster_name, cluster_name, CLUSTER_NAME_MAX + 1); new_conn->cc_cluster_name_len = cluster_name_len; new_conn->cc_recovery_handler = recovery_handler; new_conn->cc_recovery_data = recovery_data; new_conn->cc_proto = lproto; /* Start the new connection at our maximum compatibility level */ new_conn->cc_version = lproto->lp_max_version; /* This will pin the stack driver if successful */ rc = ocfs2_stack_driver_get(stack_name); if (rc) goto out_free; rc = active_stack->sp_ops->connect(new_conn); if (rc) { ocfs2_stack_driver_put(); goto out_free; } *conn = new_conn; out_free: if (rc) kfree(new_conn); out: return rc; } EXPORT_SYMBOL_GPL(ocfs2_cluster_connect); /* The caller will ensure all nodes have the same cluster stack */ int ocfs2_cluster_connect_agnostic(const char *group, int grouplen, struct ocfs2_locking_protocol *lproto, void (*recovery_handler)(int node_num, void *recovery_data), void *recovery_data, struct ocfs2_cluster_connection **conn) { char *stack_name = NULL; if (cluster_stack_name[0]) stack_name = cluster_stack_name; return ocfs2_cluster_connect(stack_name, NULL, 0, group, grouplen, lproto, recovery_handler, recovery_data, conn); } EXPORT_SYMBOL_GPL(ocfs2_cluster_connect_agnostic); /* If hangup_pending is 0, the stack driver will be dropped */ int ocfs2_cluster_disconnect(struct ocfs2_cluster_connection *conn, int hangup_pending) { int ret; BUG_ON(conn == NULL); ret = active_stack->sp_ops->disconnect(conn); /* XXX Should we free it anyway? */ if (!ret) { kfree(conn); if (!hangup_pending) ocfs2_stack_driver_put(); } return ret; } EXPORT_SYMBOL_GPL(ocfs2_cluster_disconnect); /* * Leave the group for this filesystem. This is executed by a userspace * program (stored in ocfs2_hb_ctl_path). */ static void ocfs2_leave_group(const char *group) { int ret; char *argv[5], *envp[3]; argv[0] = ocfs2_hb_ctl_path; argv[1] = "-K"; argv[2] = "-u"; argv[3] = (char *)group; argv[4] = NULL; /* minimal command environment taken from cpu_run_sbin_hotplug */ envp[0] = "HOME=/"; envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; envp[2] = NULL; ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC); if (ret < 0) { printk(KERN_ERR "ocfs2: Error %d running user helper " "\"%s %s %s %s\"\n", ret, argv[0], argv[1], argv[2], argv[3]); } } /* * Hangup is a required post-umount. ocfs2-tools software expects the * filesystem to call "ocfs2_hb_ctl" during unmount. This happens * regardless of whether the DLM got started, so we can't do it * in ocfs2_cluster_disconnect(). The ocfs2_leave_group() function does * the actual work. */ void ocfs2_cluster_hangup(const char *group, int grouplen) { BUG_ON(group == NULL); BUG_ON(group[grouplen] != '\0'); ocfs2_leave_group(group); /* cluster_disconnect() was called with hangup_pending==1 */ ocfs2_stack_driver_put(); } EXPORT_SYMBOL_GPL(ocfs2_cluster_hangup); int ocfs2_cluster_this_node(struct ocfs2_cluster_connection *conn, unsigned int *node) { return active_stack->sp_ops->this_node(conn, node); } EXPORT_SYMBOL_GPL(ocfs2_cluster_this_node); /* * Sysfs bits */ static ssize_t ocfs2_max_locking_protocol_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { ssize_t ret = 0; spin_lock(&ocfs2_stack_lock); if (locking_max_version.pv_major) ret = snprintf(buf, PAGE_SIZE, "%u.%u\n", locking_max_version.pv_major, locking_max_version.pv_minor); spin_unlock(&ocfs2_stack_lock); return ret; } static struct kobj_attribute ocfs2_attr_max_locking_protocol = __ATTR(max_locking_protocol, S_IRUGO, ocfs2_max_locking_protocol_show, NULL); static ssize_t ocfs2_loaded_cluster_plugins_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { ssize_t ret = 0, total = 0, remain = PAGE_SIZE; struct ocfs2_stack_plugin *p; spin_lock(&ocfs2_stack_lock); list_for_each_entry(p, &ocfs2_stack_list, sp_list) { ret = snprintf(buf, remain, "%s\n", p->sp_name); if (ret >= remain) { /* snprintf() didn't fit */ total = -E2BIG; break; } total += ret; remain -= ret; } spin_unlock(&ocfs2_stack_lock); return total; } static struct kobj_attribute ocfs2_attr_loaded_cluster_plugins = __ATTR(loaded_cluster_plugins, S_IRUGO, ocfs2_loaded_cluster_plugins_show, NULL); static ssize_t ocfs2_active_cluster_plugin_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { ssize_t ret = 0; spin_lock(&ocfs2_stack_lock); if (active_stack) { ret = snprintf(buf, PAGE_SIZE, "%s\n", active_stack->sp_name); if (ret >= PAGE_SIZE) ret = -E2BIG; } spin_unlock(&ocfs2_stack_lock); return ret; } static struct kobj_attribute ocfs2_attr_active_cluster_plugin = __ATTR(active_cluster_plugin, S_IRUGO, ocfs2_active_cluster_plugin_show, NULL); static ssize_t ocfs2_cluster_stack_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { ssize_t ret; spin_lock(&ocfs2_stack_lock); ret = snprintf(buf, PAGE_SIZE, "%s\n", cluster_stack_name); spin_unlock(&ocfs2_stack_lock); return ret; } static ssize_t ocfs2_cluster_stack_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { size_t len = count; ssize_t ret; if (len == 0) return len; if (buf[len - 1] == '\n') len--; if ((len != OCFS2_STACK_LABEL_LEN) || (strnlen(buf, len) != len)) return -EINVAL; spin_lock(&ocfs2_stack_lock); if (active_stack) { if (!strncmp(buf, cluster_stack_name, len)) ret = count; else ret = -EBUSY; } else { memcpy(cluster_stack_name, buf, len); ret = count; } spin_unlock(&ocfs2_stack_lock); return ret; } static struct kobj_attribute ocfs2_attr_cluster_stack = __ATTR(cluster_stack, S_IRUGO | S_IWUSR, ocfs2_cluster_stack_show, ocfs2_cluster_stack_store); static ssize_t ocfs2_dlm_recover_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE, "1\n"); } static struct kobj_attribute ocfs2_attr_dlm_recover_support = __ATTR(dlm_recover_callback_support, S_IRUGO, ocfs2_dlm_recover_show, NULL); static struct attribute *ocfs2_attrs[] = { &ocfs2_attr_max_locking_protocol.attr, &ocfs2_attr_loaded_cluster_plugins.attr, &ocfs2_attr_active_cluster_plugin.attr, &ocfs2_attr_cluster_stack.attr, &ocfs2_attr_dlm_recover_support.attr, NULL, }; static const struct attribute_group ocfs2_attr_group = { .attrs = ocfs2_attrs, }; struct kset *ocfs2_kset; EXPORT_SYMBOL_GPL(ocfs2_kset); static void ocfs2_sysfs_exit(void) { kset_unregister(ocfs2_kset); } static int ocfs2_sysfs_init(void) { int ret; ocfs2_kset = kset_create_and_add("ocfs2", NULL, fs_kobj); if (!ocfs2_kset) return -ENOMEM; ret = sysfs_create_group(&ocfs2_kset->kobj, &ocfs2_attr_group); if (ret) goto error; return 0; error: kset_unregister(ocfs2_kset); return ret; } /* * Sysctl bits * * The sysctl lives at /proc/sys/fs/ocfs2/nm/hb_ctl_path. The 'nm' doesn't * make as much sense in a multiple cluster stack world, but it's safer * and easier to preserve the name. */ static struct ctl_table ocfs2_nm_table[] = { { .procname = "hb_ctl_path", .data = ocfs2_hb_ctl_path, .maxlen = OCFS2_MAX_HB_CTL_PATH, .mode = 0644, .proc_handler = proc_dostring, }, }; static struct ctl_table_header *ocfs2_table_header; /* * Initialization */ static int __init ocfs2_stack_glue_init(void) { int ret; strcpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB); ocfs2_table_header = register_sysctl("fs/ocfs2/nm", ocfs2_nm_table); if (!ocfs2_table_header) { printk(KERN_ERR "ocfs2 stack glue: unable to register sysctl\n"); return -ENOMEM; /* or something. */ } ret = ocfs2_sysfs_init(); if (ret) unregister_sysctl_table(ocfs2_table_header); return ret; } static void __exit ocfs2_stack_glue_exit(void) { memset(&locking_max_version, 0, sizeof(struct ocfs2_protocol_version)); ocfs2_sysfs_exit(); if (ocfs2_table_header) unregister_sysctl_table(ocfs2_table_header); } MODULE_AUTHOR("Oracle"); MODULE_DESCRIPTION("ocfs2 cluster stack glue layer"); MODULE_LICENSE("GPL"); module_init(ocfs2_stack_glue_init); module_exit(ocfs2_stack_glue_exit); |
| 127 127 126 61 62 4 19 55 53 4 38 30 19 19 53 53 53 53 53 53 53 53 18 41 57 35 44 19 53 2 2740 127 62 3 1 44 16 61 61 2890 2894 2897 19 2893 2866 50 127 18 127 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991-1998 Linus Torvalds * Re-organised Feb 1998 Russell King * Copyright (C) 2020 Christoph Hellwig */ #include <linux/fs.h> #include <linux/major.h> #include <linux/slab.h> #include <linux/ctype.h> #include <linux/vmalloc.h> #include <linux/raid/detect.h> #include "check.h" static int (*const check_part[])(struct parsed_partitions *) = { /* * Probe partition formats with tables at disk address 0 * that also have an ADFS boot block at 0xdc0. */ #ifdef CONFIG_ACORN_PARTITION_ICS adfspart_check_ICS, #endif #ifdef CONFIG_ACORN_PARTITION_POWERTEC adfspart_check_POWERTEC, #endif #ifdef CONFIG_ACORN_PARTITION_EESOX adfspart_check_EESOX, #endif /* * Now move on to formats that only have partition info at * disk address 0xdc0. Since these may also have stale * PC/BIOS partition tables, they need to come before * the msdos entry. */ #ifdef CONFIG_ACORN_PARTITION_CUMANA adfspart_check_CUMANA, #endif #ifdef CONFIG_ACORN_PARTITION_ADFS adfspart_check_ADFS, #endif #ifdef CONFIG_CMDLINE_PARTITION cmdline_partition, #endif #ifdef CONFIG_OF_PARTITION of_partition, /* cmdline have priority to OF */ #endif #ifdef CONFIG_EFI_PARTITION efi_partition, /* this must come before msdos */ #endif #ifdef CONFIG_SGI_PARTITION sgi_partition, #endif #ifdef CONFIG_LDM_PARTITION ldm_partition, /* this must come before msdos */ #endif #ifdef CONFIG_MSDOS_PARTITION msdos_partition, #endif #ifdef CONFIG_OSF_PARTITION osf_partition, #endif #ifdef CONFIG_SUN_PARTITION sun_partition, #endif #ifdef CONFIG_AMIGA_PARTITION amiga_partition, #endif #ifdef CONFIG_ATARI_PARTITION atari_partition, #endif #ifdef CONFIG_MAC_PARTITION mac_partition, #endif #ifdef CONFIG_ULTRIX_PARTITION ultrix_partition, #endif #ifdef CONFIG_IBM_PARTITION ibm_partition, #endif #ifdef CONFIG_KARMA_PARTITION karma_partition, #endif #ifdef CONFIG_SYSV68_PARTITION sysv68_partition, #endif NULL }; static struct parsed_partitions *allocate_partitions(struct gendisk *hd) { struct parsed_partitions *state; int nr = DISK_MAX_PARTS; state = kzalloc(sizeof(*state), GFP_KERNEL); if (!state) return NULL; state->parts = vzalloc(array_size(nr, sizeof(state->parts[0]))); if (!state->parts) { kfree(state); return NULL; } state->limit = nr; return state; } static void free_partitions(struct parsed_partitions *state) { vfree(state->parts); kfree(state); } static struct parsed_partitions *check_partition(struct gendisk *hd) { struct parsed_partitions *state; int i, res, err; state = allocate_partitions(hd); if (!state) return NULL; state->pp_buf = (char *)__get_free_page(GFP_KERNEL); if (!state->pp_buf) { free_partitions(state); return NULL; } state->pp_buf[0] = '\0'; state->disk = hd; snprintf(state->name, BDEVNAME_SIZE, "%s", hd->disk_name); snprintf(state->pp_buf, PAGE_SIZE, " %s:", state->name); if (isdigit(state->name[strlen(state->name)-1])) sprintf(state->name, "p"); i = res = err = 0; while (!res && check_part[i]) { memset(state->parts, 0, state->limit * sizeof(state->parts[0])); res = check_part[i++](state); if (res < 0) { /* * We have hit an I/O error which we don't report now. * But record it, and let the others do their job. */ err = res; res = 0; } } if (res > 0) { printk(KERN_INFO "%s", state->pp_buf); free_page((unsigned long)state->pp_buf); return state; } if (state->access_beyond_eod) err = -ENOSPC; /* * The partition is unrecognized. So report I/O errors if there were any */ if (err) res = err; if (res) { strlcat(state->pp_buf, " unable to read partition table\n", PAGE_SIZE); printk(KERN_INFO "%s", state->pp_buf); } free_page((unsigned long)state->pp_buf); free_partitions(state); return ERR_PTR(res); } static ssize_t part_partition_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", bdev_partno(dev_to_bdev(dev))); } static ssize_t part_start_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%llu\n", dev_to_bdev(dev)->bd_start_sect); } static ssize_t part_ro_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", bdev_read_only(dev_to_bdev(dev))); } static ssize_t part_alignment_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%u\n", bdev_alignment_offset(dev_to_bdev(dev))); } static ssize_t part_discard_alignment_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%u\n", bdev_discard_alignment(dev_to_bdev(dev))); } static DEVICE_ATTR(partition, 0444, part_partition_show, NULL); static DEVICE_ATTR(start, 0444, part_start_show, NULL); static DEVICE_ATTR(size, 0444, part_size_show, NULL); static DEVICE_ATTR(ro, 0444, part_ro_show, NULL); static DEVICE_ATTR(alignment_offset, 0444, part_alignment_offset_show, NULL); static DEVICE_ATTR(discard_alignment, 0444, part_discard_alignment_show, NULL); static DEVICE_ATTR(stat, 0444, part_stat_show, NULL); static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, 0644, part_fail_show, part_fail_store); #endif static struct attribute *part_attrs[] = { &dev_attr_partition.attr, &dev_attr_start.attr, &dev_attr_size.attr, &dev_attr_ro.attr, &dev_attr_alignment_offset.attr, &dev_attr_discard_alignment.attr, &dev_attr_stat.attr, &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif NULL }; static const struct attribute_group part_attr_group = { .attrs = part_attrs, }; static const struct attribute_group *part_attr_groups[] = { &part_attr_group, #ifdef CONFIG_BLK_DEV_IO_TRACE &blk_trace_attr_group, #endif NULL }; static void part_release(struct device *dev) { put_disk(dev_to_bdev(dev)->bd_disk); bdev_drop(dev_to_bdev(dev)); } static int part_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct block_device *part = dev_to_bdev(dev); add_uevent_var(env, "PARTN=%u", bdev_partno(part)); if (part->bd_meta_info && part->bd_meta_info->volname[0]) add_uevent_var(env, "PARTNAME=%s", part->bd_meta_info->volname); if (part->bd_meta_info && part->bd_meta_info->uuid[0]) add_uevent_var(env, "PARTUUID=%s", part->bd_meta_info->uuid); return 0; } const struct device_type part_type = { .name = "partition", .groups = part_attr_groups, .release = part_release, .uevent = part_uevent, }; void drop_partition(struct block_device *part) { lockdep_assert_held(&part->bd_disk->open_mutex); xa_erase(&part->bd_disk->part_tbl, bdev_partno(part)); kobject_put(part->bd_holder_dir); device_del(&part->bd_device); put_device(&part->bd_device); } static ssize_t whole_disk_show(struct device *dev, struct device_attribute *attr, char *buf) { return 0; } static const DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL); /* * Must be called either with open_mutex held, before a disk can be opened or * after all disk users are gone. */ static struct block_device *add_partition(struct gendisk *disk, int partno, sector_t start, sector_t len, int flags, struct partition_meta_info *info) { dev_t devt = MKDEV(0, 0); struct device *ddev = disk_to_dev(disk); struct device *pdev; struct block_device *bdev; const char *dname; int err; lockdep_assert_held(&disk->open_mutex); if (partno >= DISK_MAX_PARTS) return ERR_PTR(-EINVAL); /* * Partitions are not supported on zoned block devices that are used as * such. */ if (bdev_is_zoned(disk->part0)) { pr_warn("%s: partitions not supported on host managed zoned block device\n", disk->disk_name); return ERR_PTR(-ENXIO); } if (xa_load(&disk->part_tbl, partno)) return ERR_PTR(-EBUSY); /* ensure we always have a reference to the whole disk */ get_device(disk_to_dev(disk)); err = -ENOMEM; bdev = bdev_alloc(disk, partno); if (!bdev) goto out_put_disk; bdev->bd_start_sect = start; bdev_set_nr_sectors(bdev, len); pdev = &bdev->bd_device; dname = dev_name(ddev); if (isdigit(dname[strlen(dname) - 1])) dev_set_name(pdev, "%sp%d", dname, partno); else dev_set_name(pdev, "%s%d", dname, partno); device_initialize(pdev); pdev->class = &block_class; pdev->type = &part_type; pdev->parent = ddev; /* in consecutive minor range? */ if (bdev_partno(bdev) < disk->minors) { devt = MKDEV(disk->major, disk->first_minor + bdev_partno(bdev)); } else { err = blk_alloc_ext_minor(); if (err < 0) goto out_put; devt = MKDEV(BLOCK_EXT_MAJOR, err); } pdev->devt = devt; if (info) { err = -ENOMEM; bdev->bd_meta_info = kmemdup(info, sizeof(*info), GFP_KERNEL); if (!bdev->bd_meta_info) goto out_put; } /* delay uevent until 'holders' subdir is created */ dev_set_uevent_suppress(pdev, 1); err = device_add(pdev); if (err) goto out_put; err = -ENOMEM; bdev->bd_holder_dir = kobject_create_and_add("holders", &pdev->kobj); if (!bdev->bd_holder_dir) goto out_del; dev_set_uevent_suppress(pdev, 0); if (flags & ADDPART_FLAG_WHOLEDISK) { err = device_create_file(pdev, &dev_attr_whole_disk); if (err) goto out_del; } if (flags & ADDPART_FLAG_READONLY) bdev_set_flag(bdev, BD_READ_ONLY); /* everything is up and running, commence */ err = xa_insert(&disk->part_tbl, partno, bdev, GFP_KERNEL); if (err) goto out_del; bdev_add(bdev, devt); /* suppress uevent if the disk suppresses it */ if (!dev_get_uevent_suppress(ddev)) kobject_uevent(&pdev->kobj, KOBJ_ADD); return bdev; out_del: kobject_put(bdev->bd_holder_dir); device_del(pdev); out_put: put_device(pdev); return ERR_PTR(err); out_put_disk: put_disk(disk); return ERR_PTR(err); } static bool partition_overlaps(struct gendisk *disk, sector_t start, sector_t length, int skip_partno) { struct block_device *part; bool overlap = false; unsigned long idx; rcu_read_lock(); xa_for_each_start(&disk->part_tbl, idx, part, 1) { if (bdev_partno(part) != skip_partno && start < part->bd_start_sect + bdev_nr_sectors(part) && start + length > part->bd_start_sect) { overlap = true; break; } } rcu_read_unlock(); return overlap; } int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, sector_t length) { struct block_device *part; int ret; mutex_lock(&disk->open_mutex); if (!disk_live(disk)) { ret = -ENXIO; goto out; } if (disk->flags & GENHD_FL_NO_PART) { ret = -EINVAL; goto out; } if (partition_overlaps(disk, start, length, -1)) { ret = -EBUSY; goto out; } part = add_partition(disk, partno, start, length, ADDPART_FLAG_NONE, NULL); ret = PTR_ERR_OR_ZERO(part); out: mutex_unlock(&disk->open_mutex); return ret; } int bdev_del_partition(struct gendisk *disk, int partno) { struct block_device *part = NULL; int ret = -ENXIO; mutex_lock(&disk->open_mutex); part = xa_load(&disk->part_tbl, partno); if (!part) goto out_unlock; ret = -EBUSY; if (atomic_read(&part->bd_openers)) goto out_unlock; /* * We verified that @part->bd_openers is zero above and so * @part->bd_holder{_ops} can't be set. And since we hold * @disk->open_mutex the device can't be claimed by anyone. * * So no need to call @part->bd_holder_ops->mark_dead() here. * Just delete the partition and invalidate it. */ bdev_unhash(part); invalidate_bdev(part); drop_partition(part); ret = 0; out_unlock: mutex_unlock(&disk->open_mutex); return ret; } int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start, sector_t length) { struct block_device *part = NULL; int ret = -ENXIO; mutex_lock(&disk->open_mutex); part = xa_load(&disk->part_tbl, partno); if (!part) goto out_unlock; ret = -EINVAL; if (start != part->bd_start_sect) goto out_unlock; ret = -EBUSY; if (partition_overlaps(disk, start, length, partno)) goto out_unlock; bdev_set_nr_sectors(part, length); ret = 0; out_unlock: mutex_unlock(&disk->open_mutex); return ret; } static bool disk_unlock_native_capacity(struct gendisk *disk) { if (!disk->fops->unlock_native_capacity || test_and_set_bit(GD_NATIVE_CAPACITY, &disk->state)) { printk(KERN_CONT "truncated\n"); return false; } printk(KERN_CONT "enabling native capacity\n"); disk->fops->unlock_native_capacity(disk); return true; } static bool blk_add_partition(struct gendisk *disk, struct parsed_partitions *state, int p) { sector_t size = state->parts[p].size; sector_t from = state->parts[p].from; struct block_device *part; if (!size) return true; if (from >= get_capacity(disk)) { printk(KERN_WARNING "%s: p%d start %llu is beyond EOD, ", disk->disk_name, p, (unsigned long long) from); if (disk_unlock_native_capacity(disk)) return false; return true; } if (from + size > get_capacity(disk)) { printk(KERN_WARNING "%s: p%d size %llu extends beyond EOD, ", disk->disk_name, p, (unsigned long long) size); if (disk_unlock_native_capacity(disk)) return false; /* * We can not ignore partitions of broken tables created by for * example camera firmware, but we limit them to the end of the * disk to avoid creating invalid block devices. */ size = get_capacity(disk) - from; } part = add_partition(disk, p, from, size, state->parts[p].flags, &state->parts[p].info); if (IS_ERR(part)) { if (PTR_ERR(part) != -ENXIO) { printk(KERN_ERR " %s: p%d could not be added: %pe\n", disk->disk_name, p, part); } return true; } if (IS_BUILTIN(CONFIG_BLK_DEV_MD) && (state->parts[p].flags & ADDPART_FLAG_RAID)) md_autodetect_dev(part->bd_dev); return true; } static int blk_add_partitions(struct gendisk *disk) { struct parsed_partitions *state; int ret = -EAGAIN, p; if (!disk_has_partscan(disk)) return 0; state = check_partition(disk); if (!state) return 0; if (IS_ERR(state)) { /* * I/O error reading the partition table. If we tried to read * beyond EOD, retry after unlocking the native capacity. */ if (PTR_ERR(state) == -ENOSPC) { printk(KERN_WARNING "%s: partition table beyond EOD, ", disk->disk_name); if (disk_unlock_native_capacity(disk)) return -EAGAIN; } return -EIO; } /* * Partitions are not supported on host managed zoned block devices. */ if (bdev_is_zoned(disk->part0)) { pr_warn("%s: ignoring partition table on host managed zoned block device\n", disk->disk_name); ret = 0; goto out_free_state; } /* * If we read beyond EOD, try unlocking native capacity even if the * partition table was successfully read as we could be missing some * partitions. */ if (state->access_beyond_eod) { printk(KERN_WARNING "%s: partition table partially beyond EOD, ", disk->disk_name); if (disk_unlock_native_capacity(disk)) goto out_free_state; } /* tell userspace that the media / partition table may have changed */ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); for (p = 1; p < state->limit; p++) if (!blk_add_partition(disk, state, p)) goto out_free_state; ret = 0; out_free_state: free_partitions(state); return ret; } int bdev_disk_changed(struct gendisk *disk, bool invalidate) { struct block_device *part; unsigned long idx; int ret = 0; lockdep_assert_held(&disk->open_mutex); if (!disk_live(disk)) return -ENXIO; rescan: if (disk->open_partitions) return -EBUSY; sync_blockdev(disk->part0); invalidate_bdev(disk->part0); xa_for_each_start(&disk->part_tbl, idx, part, 1) { /* * Remove the block device from the inode hash, so that * it cannot be looked up any more even when openers * still hold references. */ bdev_unhash(part); /* * If @disk->open_partitions isn't elevated but there's * still an active holder of that block device things * are broken. */ WARN_ON_ONCE(atomic_read(&part->bd_openers)); invalidate_bdev(part); drop_partition(part); } clear_bit(GD_NEED_PART_SCAN, &disk->state); /* * Historically we only set the capacity to zero for devices that * support partitions (independ of actually having partitions created). * Doing that is rather inconsistent, but changing it broke legacy * udisks polling for legacy ide-cdrom devices. Use the crude check * below to get the sane behavior for most device while not breaking * userspace for this particular setup. */ if (invalidate) { if (!(disk->flags & GENHD_FL_NO_PART) || !(disk->flags & GENHD_FL_REMOVABLE)) set_capacity(disk, 0); } if (get_capacity(disk)) { ret = blk_add_partitions(disk); if (ret == -EAGAIN) goto rescan; } else if (invalidate) { /* * Tell userspace that the media / partition table may have * changed. */ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); } return ret; } /* * Only exported for loop and dasd for historic reasons. Don't use in new * code! */ EXPORT_SYMBOL_GPL(bdev_disk_changed); void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p) { struct address_space *mapping = state->disk->part0->bd_mapping; struct folio *folio; if (n >= get_capacity(state->disk)) { state->access_beyond_eod = true; goto out; } folio = read_mapping_folio(mapping, n >> PAGE_SECTORS_SHIFT, NULL); if (IS_ERR(folio)) goto out; p->v = folio; return folio_address(folio) + offset_in_folio(folio, n * SECTOR_SIZE); out: p->v = NULL; return NULL; } |
| 2 5 3 3 3 3 3 3 1 2 2 2 2 2 2 2 2 2 2 2 2 1 2 2 3 3 3 3 3 3 3 3 3 2 5 4 3 2 3 3 2 2 2 2 2 2 2 5 5 5 4 1 6 7 5 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 | // SPDX-License-Identifier: 0BSD /* * .xz Stream decoder * * Author: Lasse Collin <lasse.collin@tukaani.org> */ #include "xz_private.h" #include "xz_stream.h" /* Hash used to validate the Index field */ struct xz_dec_hash { vli_type unpadded; vli_type uncompressed; uint32_t crc32; }; struct xz_dec { /* Position in dec_main() */ enum { SEQ_STREAM_HEADER, SEQ_BLOCK_START, SEQ_BLOCK_HEADER, SEQ_BLOCK_UNCOMPRESS, SEQ_BLOCK_PADDING, SEQ_BLOCK_CHECK, SEQ_INDEX, SEQ_INDEX_PADDING, SEQ_INDEX_CRC32, SEQ_STREAM_FOOTER } sequence; /* Position in variable-length integers and Check fields */ uint32_t pos; /* Variable-length integer decoded by dec_vli() */ vli_type vli; /* Saved in_pos and out_pos */ size_t in_start; size_t out_start; /* CRC32 value in Block or Index */ uint32_t crc32; /* Type of the integrity check calculated from uncompressed data */ enum xz_check check_type; /* Operation mode */ enum xz_mode mode; /* * True if the next call to xz_dec_run() is allowed to return * XZ_BUF_ERROR. */ bool allow_buf_error; /* Information stored in Block Header */ struct { /* * Value stored in the Compressed Size field, or * VLI_UNKNOWN if Compressed Size is not present. */ vli_type compressed; /* * Value stored in the Uncompressed Size field, or * VLI_UNKNOWN if Uncompressed Size is not present. */ vli_type uncompressed; /* Size of the Block Header field */ uint32_t size; } block_header; /* Information collected when decoding Blocks */ struct { /* Observed compressed size of the current Block */ vli_type compressed; /* Observed uncompressed size of the current Block */ vli_type uncompressed; /* Number of Blocks decoded so far */ vli_type count; /* * Hash calculated from the Block sizes. This is used to * validate the Index field. */ struct xz_dec_hash hash; } block; /* Variables needed when verifying the Index field */ struct { /* Position in dec_index() */ enum { SEQ_INDEX_COUNT, SEQ_INDEX_UNPADDED, SEQ_INDEX_UNCOMPRESSED } sequence; /* Size of the Index in bytes */ vli_type size; /* Number of Records (matches block.count in valid files) */ vli_type count; /* * Hash calculated from the Records (matches block.hash in * valid files). */ struct xz_dec_hash hash; } index; /* * Temporary buffer needed to hold Stream Header, Block Header, * and Stream Footer. The Block Header is the biggest (1 KiB) * so we reserve space according to that. buf[] has to be aligned * to a multiple of four bytes; the size_t variables before it * should guarantee this. */ struct { size_t pos; size_t size; uint8_t buf[1024]; } temp; struct xz_dec_lzma2 *lzma2; #ifdef XZ_DEC_BCJ struct xz_dec_bcj *bcj; bool bcj_active; #endif }; #ifdef XZ_DEC_ANY_CHECK /* Sizes of the Check field with different Check IDs */ static const uint8_t check_sizes[16] = { 0, 4, 4, 4, 8, 8, 8, 16, 16, 16, 32, 32, 32, 64, 64, 64 }; #endif /* * Fill s->temp by copying data starting from b->in[b->in_pos]. Caller * must have set s->temp.pos to indicate how much data we are supposed * to copy into s->temp.buf. Return true once s->temp.pos has reached * s->temp.size. */ static bool fill_temp(struct xz_dec *s, struct xz_buf *b) { size_t copy_size = min_t(size_t, b->in_size - b->in_pos, s->temp.size - s->temp.pos); memcpy(s->temp.buf + s->temp.pos, b->in + b->in_pos, copy_size); b->in_pos += copy_size; s->temp.pos += copy_size; if (s->temp.pos == s->temp.size) { s->temp.pos = 0; return true; } return false; } /* Decode a variable-length integer (little-endian base-128 encoding) */ static enum xz_ret dec_vli(struct xz_dec *s, const uint8_t *in, size_t *in_pos, size_t in_size) { uint8_t byte; if (s->pos == 0) s->vli = 0; while (*in_pos < in_size) { byte = in[*in_pos]; ++*in_pos; s->vli |= (vli_type)(byte & 0x7F) << s->pos; if ((byte & 0x80) == 0) { /* Don't allow non-minimal encodings. */ if (byte == 0 && s->pos != 0) return XZ_DATA_ERROR; s->pos = 0; return XZ_STREAM_END; } s->pos += 7; if (s->pos == 7 * VLI_BYTES_MAX) return XZ_DATA_ERROR; } return XZ_OK; } /* * Decode the Compressed Data field from a Block. Update and validate * the observed compressed and uncompressed sizes of the Block so that * they don't exceed the values possibly stored in the Block Header * (validation assumes that no integer overflow occurs, since vli_type * is normally uint64_t). Update the CRC32 if presence of the CRC32 * field was indicated in Stream Header. * * Once the decoding is finished, validate that the observed sizes match * the sizes possibly stored in the Block Header. Update the hash and * Block count, which are later used to validate the Index field. */ static enum xz_ret dec_block(struct xz_dec *s, struct xz_buf *b) { enum xz_ret ret; s->in_start = b->in_pos; s->out_start = b->out_pos; #ifdef XZ_DEC_BCJ if (s->bcj_active) ret = xz_dec_bcj_run(s->bcj, s->lzma2, b); else #endif ret = xz_dec_lzma2_run(s->lzma2, b); s->block.compressed += b->in_pos - s->in_start; s->block.uncompressed += b->out_pos - s->out_start; /* * There is no need to separately check for VLI_UNKNOWN, since * the observed sizes are always smaller than VLI_UNKNOWN. */ if (s->block.compressed > s->block_header.compressed || s->block.uncompressed > s->block_header.uncompressed) return XZ_DATA_ERROR; if (s->check_type == XZ_CHECK_CRC32) s->crc32 = xz_crc32(b->out + s->out_start, b->out_pos - s->out_start, s->crc32); if (ret == XZ_STREAM_END) { if (s->block_header.compressed != VLI_UNKNOWN && s->block_header.compressed != s->block.compressed) return XZ_DATA_ERROR; if (s->block_header.uncompressed != VLI_UNKNOWN && s->block_header.uncompressed != s->block.uncompressed) return XZ_DATA_ERROR; s->block.hash.unpadded += s->block_header.size + s->block.compressed; #ifdef XZ_DEC_ANY_CHECK s->block.hash.unpadded += check_sizes[s->check_type]; #else if (s->check_type == XZ_CHECK_CRC32) s->block.hash.unpadded += 4; #endif s->block.hash.uncompressed += s->block.uncompressed; s->block.hash.crc32 = xz_crc32( (const uint8_t *)&s->block.hash, sizeof(s->block.hash), s->block.hash.crc32); ++s->block.count; } return ret; } /* Update the Index size and the CRC32 value. */ static void index_update(struct xz_dec *s, const struct xz_buf *b) { size_t in_used = b->in_pos - s->in_start; s->index.size += in_used; s->crc32 = xz_crc32(b->in + s->in_start, in_used, s->crc32); } /* * Decode the Number of Records, Unpadded Size, and Uncompressed Size * fields from the Index field. That is, Index Padding and CRC32 are not * decoded by this function. * * This can return XZ_OK (more input needed), XZ_STREAM_END (everything * successfully decoded), or XZ_DATA_ERROR (input is corrupt). */ static enum xz_ret dec_index(struct xz_dec *s, struct xz_buf *b) { enum xz_ret ret; do { ret = dec_vli(s, b->in, &b->in_pos, b->in_size); if (ret != XZ_STREAM_END) { index_update(s, b); return ret; } switch (s->index.sequence) { case SEQ_INDEX_COUNT: s->index.count = s->vli; /* * Validate that the Number of Records field * indicates the same number of Records as * there were Blocks in the Stream. */ if (s->index.count != s->block.count) return XZ_DATA_ERROR; s->index.sequence = SEQ_INDEX_UNPADDED; break; case SEQ_INDEX_UNPADDED: s->index.hash.unpadded += s->vli; s->index.sequence = SEQ_INDEX_UNCOMPRESSED; break; case SEQ_INDEX_UNCOMPRESSED: s->index.hash.uncompressed += s->vli; s->index.hash.crc32 = xz_crc32( (const uint8_t *)&s->index.hash, sizeof(s->index.hash), s->index.hash.crc32); --s->index.count; s->index.sequence = SEQ_INDEX_UNPADDED; break; } } while (s->index.count > 0); return XZ_STREAM_END; } /* * Validate that the next four input bytes match the value of s->crc32. * s->pos must be zero when starting to validate the first byte. */ static enum xz_ret crc32_validate(struct xz_dec *s, struct xz_buf *b) { do { if (b->in_pos == b->in_size) return XZ_OK; if (((s->crc32 >> s->pos) & 0xFF) != b->in[b->in_pos++]) return XZ_DATA_ERROR; s->pos += 8; } while (s->pos < 32); s->crc32 = 0; s->pos = 0; return XZ_STREAM_END; } #ifdef XZ_DEC_ANY_CHECK /* * Skip over the Check field when the Check ID is not supported. * Returns true once the whole Check field has been skipped over. */ static bool check_skip(struct xz_dec *s, struct xz_buf *b) { while (s->pos < check_sizes[s->check_type]) { if (b->in_pos == b->in_size) return false; ++b->in_pos; ++s->pos; } s->pos = 0; return true; } #endif /* Decode the Stream Header field (the first 12 bytes of the .xz Stream). */ static enum xz_ret dec_stream_header(struct xz_dec *s) { if (!memeq(s->temp.buf, HEADER_MAGIC, HEADER_MAGIC_SIZE)) return XZ_FORMAT_ERROR; if (xz_crc32(s->temp.buf + HEADER_MAGIC_SIZE, 2, 0) != get_le32(s->temp.buf + HEADER_MAGIC_SIZE + 2)) return XZ_DATA_ERROR; if (s->temp.buf[HEADER_MAGIC_SIZE] != 0) return XZ_OPTIONS_ERROR; /* * Of integrity checks, we support only none (Check ID = 0) and * CRC32 (Check ID = 1). However, if XZ_DEC_ANY_CHECK is defined, * we will accept other check types too, but then the check won't * be verified and a warning (XZ_UNSUPPORTED_CHECK) will be given. */ if (s->temp.buf[HEADER_MAGIC_SIZE + 1] > XZ_CHECK_MAX) return XZ_OPTIONS_ERROR; s->check_type = s->temp.buf[HEADER_MAGIC_SIZE + 1]; #ifdef XZ_DEC_ANY_CHECK if (s->check_type > XZ_CHECK_CRC32) return XZ_UNSUPPORTED_CHECK; #else if (s->check_type > XZ_CHECK_CRC32) return XZ_OPTIONS_ERROR; #endif return XZ_OK; } /* Decode the Stream Footer field (the last 12 bytes of the .xz Stream) */ static enum xz_ret dec_stream_footer(struct xz_dec *s) { if (!memeq(s->temp.buf + 10, FOOTER_MAGIC, FOOTER_MAGIC_SIZE)) return XZ_DATA_ERROR; if (xz_crc32(s->temp.buf + 4, 6, 0) != get_le32(s->temp.buf)) return XZ_DATA_ERROR; /* * Validate Backward Size. Note that we never added the size of the * Index CRC32 field to s->index.size, thus we use s->index.size / 4 * instead of s->index.size / 4 - 1. */ if ((s->index.size >> 2) != get_le32(s->temp.buf + 4)) return XZ_DATA_ERROR; if (s->temp.buf[8] != 0 || s->temp.buf[9] != s->check_type) return XZ_DATA_ERROR; /* * Use XZ_STREAM_END instead of XZ_OK to be more convenient * for the caller. */ return XZ_STREAM_END; } /* Decode the Block Header and initialize the filter chain. */ static enum xz_ret dec_block_header(struct xz_dec *s) { enum xz_ret ret; /* * Validate the CRC32. We know that the temp buffer is at least * eight bytes so this is safe. */ s->temp.size -= 4; if (xz_crc32(s->temp.buf, s->temp.size, 0) != get_le32(s->temp.buf + s->temp.size)) return XZ_DATA_ERROR; s->temp.pos = 2; /* * Catch unsupported Block Flags. We support only one or two filters * in the chain, so we catch that with the same test. */ #ifdef XZ_DEC_BCJ if (s->temp.buf[1] & 0x3E) #else if (s->temp.buf[1] & 0x3F) #endif return XZ_OPTIONS_ERROR; /* Compressed Size */ if (s->temp.buf[1] & 0x40) { if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size) != XZ_STREAM_END) return XZ_DATA_ERROR; s->block_header.compressed = s->vli; } else { s->block_header.compressed = VLI_UNKNOWN; } /* Uncompressed Size */ if (s->temp.buf[1] & 0x80) { if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size) != XZ_STREAM_END) return XZ_DATA_ERROR; s->block_header.uncompressed = s->vli; } else { s->block_header.uncompressed = VLI_UNKNOWN; } #ifdef XZ_DEC_BCJ /* If there are two filters, the first one must be a BCJ filter. */ s->bcj_active = s->temp.buf[1] & 0x01; if (s->bcj_active) { if (s->temp.size - s->temp.pos < 2) return XZ_OPTIONS_ERROR; ret = xz_dec_bcj_reset(s->bcj, s->temp.buf[s->temp.pos++]); if (ret != XZ_OK) return ret; /* * We don't support custom start offset, * so Size of Properties must be zero. */ if (s->temp.buf[s->temp.pos++] != 0x00) return XZ_OPTIONS_ERROR; } #endif /* Valid Filter Flags always take at least two bytes. */ if (s->temp.size - s->temp.pos < 2) return XZ_DATA_ERROR; /* Filter ID = LZMA2 */ if (s->temp.buf[s->temp.pos++] != 0x21) return XZ_OPTIONS_ERROR; /* Size of Properties = 1-byte Filter Properties */ if (s->temp.buf[s->temp.pos++] != 0x01) return XZ_OPTIONS_ERROR; /* Filter Properties contains LZMA2 dictionary size. */ if (s->temp.size - s->temp.pos < 1) return XZ_DATA_ERROR; ret = xz_dec_lzma2_reset(s->lzma2, s->temp.buf[s->temp.pos++]); if (ret != XZ_OK) return ret; /* The rest must be Header Padding. */ while (s->temp.pos < s->temp.size) if (s->temp.buf[s->temp.pos++] != 0x00) return XZ_OPTIONS_ERROR; s->temp.pos = 0; s->block.compressed = 0; s->block.uncompressed = 0; return XZ_OK; } static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b) { enum xz_ret ret; /* * Store the start position for the case when we are in the middle * of the Index field. */ s->in_start = b->in_pos; while (true) { switch (s->sequence) { case SEQ_STREAM_HEADER: /* * Stream Header is copied to s->temp, and then * decoded from there. This way if the caller * gives us only little input at a time, we can * still keep the Stream Header decoding code * simple. Similar approach is used in many places * in this file. */ if (!fill_temp(s, b)) return XZ_OK; /* * If dec_stream_header() returns * XZ_UNSUPPORTED_CHECK, it is still possible * to continue decoding if working in multi-call * mode. Thus, update s->sequence before calling * dec_stream_header(). */ s->sequence = SEQ_BLOCK_START; ret = dec_stream_header(s); if (ret != XZ_OK) return ret; fallthrough; case SEQ_BLOCK_START: /* We need one byte of input to continue. */ if (b->in_pos == b->in_size) return XZ_OK; /* See if this is the beginning of the Index field. */ if (b->in[b->in_pos] == 0) { s->in_start = b->in_pos++; s->sequence = SEQ_INDEX; break; } /* * Calculate the size of the Block Header and * prepare to decode it. */ s->block_header.size = ((uint32_t)b->in[b->in_pos] + 1) * 4; s->temp.size = s->block_header.size; s->temp.pos = 0; s->sequence = SEQ_BLOCK_HEADER; fallthrough; case SEQ_BLOCK_HEADER: if (!fill_temp(s, b)) return XZ_OK; ret = dec_block_header(s); if (ret != XZ_OK) return ret; s->sequence = SEQ_BLOCK_UNCOMPRESS; fallthrough; case SEQ_BLOCK_UNCOMPRESS: ret = dec_block(s, b); if (ret != XZ_STREAM_END) return ret; s->sequence = SEQ_BLOCK_PADDING; fallthrough; case SEQ_BLOCK_PADDING: /* * Size of Compressed Data + Block Padding * must be a multiple of four. We don't need * s->block.compressed for anything else * anymore, so we use it here to test the size * of the Block Padding field. */ while (s->block.compressed & 3) { if (b->in_pos == b->in_size) return XZ_OK; if (b->in[b->in_pos++] != 0) return XZ_DATA_ERROR; ++s->block.compressed; } s->sequence = SEQ_BLOCK_CHECK; fallthrough; case SEQ_BLOCK_CHECK: if (s->check_type == XZ_CHECK_CRC32) { ret = crc32_validate(s, b); if (ret != XZ_STREAM_END) return ret; } #ifdef XZ_DEC_ANY_CHECK else if (!check_skip(s, b)) { return XZ_OK; } #endif s->sequence = SEQ_BLOCK_START; break; case SEQ_INDEX: ret = dec_index(s, b); if (ret != XZ_STREAM_END) return ret; s->sequence = SEQ_INDEX_PADDING; fallthrough; case SEQ_INDEX_PADDING: while ((s->index.size + (b->in_pos - s->in_start)) & 3) { if (b->in_pos == b->in_size) { index_update(s, b); return XZ_OK; } if (b->in[b->in_pos++] != 0) return XZ_DATA_ERROR; } /* Finish the CRC32 value and Index size. */ index_update(s, b); /* Compare the hashes to validate the Index field. */ if (!memeq(&s->block.hash, &s->index.hash, sizeof(s->block.hash))) return XZ_DATA_ERROR; s->sequence = SEQ_INDEX_CRC32; fallthrough; case SEQ_INDEX_CRC32: ret = crc32_validate(s, b); if (ret != XZ_STREAM_END) return ret; s->temp.size = STREAM_HEADER_SIZE; s->sequence = SEQ_STREAM_FOOTER; fallthrough; case SEQ_STREAM_FOOTER: if (!fill_temp(s, b)) return XZ_OK; return dec_stream_footer(s); } } /* Never reached */ } /* * xz_dec_run() is a wrapper for dec_main() to handle some special cases in * multi-call and single-call decoding. * * In multi-call mode, we must return XZ_BUF_ERROR when it seems clear that we * are not going to make any progress anymore. This is to prevent the caller * from calling us infinitely when the input file is truncated or otherwise * corrupt. Since zlib-style API allows that the caller fills the input buffer * only when the decoder doesn't produce any new output, we have to be careful * to avoid returning XZ_BUF_ERROR too easily: XZ_BUF_ERROR is returned only * after the second consecutive call to xz_dec_run() that makes no progress. * * In single-call mode, if we couldn't decode everything and no error * occurred, either the input is truncated or the output buffer is too small. * Since we know that the last input byte never produces any output, we know * that if all the input was consumed and decoding wasn't finished, the file * must be corrupt. Otherwise the output buffer has to be too small or the * file is corrupt in a way that decoding it produces too big output. * * If single-call decoding fails, we reset b->in_pos and b->out_pos back to * their original values. This is because with some filter chains there won't * be any valid uncompressed data in the output buffer unless the decoding * actually succeeds (that's the price to pay of using the output buffer as * the workspace). */ enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b) { size_t in_start; size_t out_start; enum xz_ret ret; if (DEC_IS_SINGLE(s->mode)) xz_dec_reset(s); in_start = b->in_pos; out_start = b->out_pos; ret = dec_main(s, b); if (DEC_IS_SINGLE(s->mode)) { if (ret == XZ_OK) ret = b->in_pos == b->in_size ? XZ_DATA_ERROR : XZ_BUF_ERROR; if (ret != XZ_STREAM_END) { b->in_pos = in_start; b->out_pos = out_start; } } else if (ret == XZ_OK && in_start == b->in_pos && out_start == b->out_pos) { if (s->allow_buf_error) ret = XZ_BUF_ERROR; s->allow_buf_error = true; } else { s->allow_buf_error = false; } return ret; } struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max) { struct xz_dec *s = kmalloc(sizeof(*s), GFP_KERNEL); if (s == NULL) return NULL; s->mode = mode; #ifdef XZ_DEC_BCJ s->bcj = xz_dec_bcj_create(DEC_IS_SINGLE(mode)); if (s->bcj == NULL) goto error_bcj; #endif s->lzma2 = xz_dec_lzma2_create(mode, dict_max); if (s->lzma2 == NULL) goto error_lzma2; xz_dec_reset(s); return s; error_lzma2: #ifdef XZ_DEC_BCJ xz_dec_bcj_end(s->bcj); error_bcj: #endif kfree(s); return NULL; } void xz_dec_reset(struct xz_dec *s) { s->sequence = SEQ_STREAM_HEADER; s->allow_buf_error = false; s->pos = 0; s->crc32 = 0; memzero(&s->block, sizeof(s->block)); memzero(&s->index, sizeof(s->index)); s->temp.pos = 0; s->temp.size = STREAM_HEADER_SIZE; } void xz_dec_end(struct xz_dec *s) { if (s != NULL) { xz_dec_lzma2_end(s->lzma2); #ifdef XZ_DEC_BCJ xz_dec_bcj_end(s->bcj); #endif kfree(s); } } |
| 678 4 2 236 657 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * device.h - generic, centralized driver model * * Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2008-2009 Novell Inc. * * See Documentation/driver-api/driver-model/ for more information. */ #ifndef _DEVICE_H_ #define _DEVICE_H_ #include <linux/dev_printk.h> #include <linux/energy_model.h> #include <linux/ioport.h> #include <linux/kobject.h> #include <linux/klist.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/compiler.h> #include <linux/types.h> #include <linux/mutex.h> #include <linux/pm.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/device/bus.h> #include <linux/device/class.h> #include <linux/device/driver.h> #include <linux/cleanup.h> #include <asm/device.h> struct device; struct device_private; struct device_driver; struct driver_private; struct module; struct class; struct subsys_private; struct device_node; struct fwnode_handle; struct iommu_group; struct dev_pin_info; struct dev_iommu; struct msi_device_data; /** * struct subsys_interface - interfaces to device functions * @name: name of the device function * @subsys: subsystem of the devices to attach to * @node: the list of functions registered at the subsystem * @add_dev: device hookup to device function handler * @remove_dev: device hookup to device function handler * * Simple interfaces attached to a subsystem. Multiple interfaces can * attach to a subsystem and its devices. Unlike drivers, they do not * exclusively claim or control devices. Interfaces usually represent * a specific functionality of a subsystem/class of devices. */ struct subsys_interface { const char *name; const struct bus_type *subsys; struct list_head node; int (*add_dev)(struct device *dev, struct subsys_interface *sif); void (*remove_dev)(struct device *dev, struct subsys_interface *sif); }; int subsys_interface_register(struct subsys_interface *sif); void subsys_interface_unregister(struct subsys_interface *sif); int subsys_system_register(const struct bus_type *subsys, const struct attribute_group **groups); int subsys_virtual_register(const struct bus_type *subsys, const struct attribute_group **groups); /* * The type of device, "struct device" is embedded in. A class * or bus can contain devices of different types * like "partitions" and "disks", "mouse" and "event". * This identifies the device type and carries type-specific * information, equivalent to the kobj_type of a kobject. * If "name" is specified, the uevent will contain it in * the DEVTYPE variable. */ struct device_type { const char *name; const struct attribute_group **groups; int (*uevent)(const struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid); void (*release)(struct device *dev); const struct dev_pm_ops *pm; }; /** * struct device_attribute - Interface for exporting device attributes. * @attr: sysfs attribute definition. * @show: Show handler. * @store: Store handler. */ struct device_attribute { struct attribute attr; ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf); ssize_t (*store)(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); }; /** * struct dev_ext_attribute - Exported device attribute with extra context. * @attr: Exported device attribute. * @var: Pointer to context. */ struct dev_ext_attribute { struct device_attribute attr; void *var; }; ssize_t device_show_ulong(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_ulong(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_int(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_int(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_bool(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_string(struct device *dev, struct device_attribute *attr, char *buf); /** * DEVICE_ATTR - Define a device attribute. * @_name: Attribute name. * @_mode: File mode. * @_show: Show handler. Optional, but mandatory if attribute is readable. * @_store: Store handler. Optional, but mandatory if attribute is writable. * * Convenience macro for defining a struct device_attribute. * * For example, ``DEVICE_ATTR(foo, 0644, foo_show, foo_store);`` expands to: * * .. code-block:: c * * struct device_attribute dev_attr_foo = { * .attr = { .name = "foo", .mode = 0644 }, * .show = foo_show, * .store = foo_store, * }; */ #define DEVICE_ATTR(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store) /** * DEVICE_ATTR_PREALLOC - Define a preallocated device attribute. * @_name: Attribute name. * @_mode: File mode. * @_show: Show handler. Optional, but mandatory if attribute is readable. * @_store: Store handler. Optional, but mandatory if attribute is writable. * * Like DEVICE_ATTR(), but ``SYSFS_PREALLOC`` is set on @_mode. */ #define DEVICE_ATTR_PREALLOC(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_PREALLOC(_name, _mode, _show, _store) /** * DEVICE_ATTR_RW - Define a read-write device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0644, @_show is <_name>_show, * and @_store is <_name>_store. */ #define DEVICE_ATTR_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW(_name) /** * DEVICE_ATTR_ADMIN_RW - Define an admin-only read-write device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR_RW(), but @_mode is 0600. */ #define DEVICE_ATTR_ADMIN_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW_MODE(_name, 0600) /** * DEVICE_ATTR_RO - Define a readable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0444 and @_show is <_name>_show. */ #define DEVICE_ATTR_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO(_name) /** * DEVICE_ATTR_ADMIN_RO - Define an admin-only readable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR_RO(), but @_mode is 0400. */ #define DEVICE_ATTR_ADMIN_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO_MODE(_name, 0400) /** * DEVICE_ATTR_WO - Define an admin-only writable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0200 and @_store is <_name>_store. */ #define DEVICE_ATTR_WO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_WO(_name) /** * DEVICE_ULONG_ATTR - Define a device attribute backed by an unsigned long. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of unsigned long. * * Like DEVICE_ATTR(), but @_show and @_store are automatically provided * such that reads and writes to the attribute from userspace affect @_var. */ #define DEVICE_ULONG_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) } /** * DEVICE_INT_ATTR - Define a device attribute backed by an int. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of int. * * Like DEVICE_ULONG_ATTR(), but @_var is an int. */ #define DEVICE_INT_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_int, device_store_int), &(_var) } /** * DEVICE_BOOL_ATTR - Define a device attribute backed by a bool. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of bool. * * Like DEVICE_ULONG_ATTR(), but @_var is a bool. */ #define DEVICE_BOOL_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_bool, device_store_bool), &(_var) } /** * DEVICE_STRING_ATTR_RO - Define a device attribute backed by a r/o string. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of string. * * Like DEVICE_ULONG_ATTR(), but @_var is a string. Because the length of the * string allocation is unknown, the attribute must be read-only. */ #define DEVICE_STRING_ATTR_RO(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, (_mode) & ~0222, device_show_string, NULL), (_var) } #define DEVICE_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) int device_create_file(struct device *device, const struct device_attribute *entry); void device_remove_file(struct device *dev, const struct device_attribute *attr); bool device_remove_file_self(struct device *dev, const struct device_attribute *attr); int __must_check device_create_bin_file(struct device *dev, const struct bin_attribute *attr); void device_remove_bin_file(struct device *dev, const struct bin_attribute *attr); /* device resource management */ typedef void (*dr_release_t)(struct device *dev, void *res); typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data); void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid, const char *name) __malloc; #define devres_alloc(release, size, gfp) \ __devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release) #define devres_alloc_node(release, size, gfp, nid) \ __devres_alloc_node(release, size, gfp, nid, #release) void devres_for_each_res(struct device *dev, dr_release_t release, dr_match_t match, void *match_data, void (*fn)(struct device *, void *, void *), void *data); void devres_free(void *res); void devres_add(struct device *dev, void *res); void *devres_find(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); void *devres_get(struct device *dev, void *new_res, dr_match_t match, void *match_data); void *devres_remove(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_destroy(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_release(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); /* devres group */ void * __must_check devres_open_group(struct device *dev, void *id, gfp_t gfp); void devres_close_group(struct device *dev, void *id); void devres_remove_group(struct device *dev, void *id); int devres_release_group(struct device *dev, void *id); /* managed devm_k.alloc/kfree for device drivers */ void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __alloc_size(2); void *devm_krealloc(struct device *dev, void *ptr, size_t size, gfp_t gfp) __must_check __realloc_size(3); __printf(3, 0) char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, va_list ap) __malloc; __printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...) __malloc; static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) { return devm_kmalloc(dev, size, gfp | __GFP_ZERO); } static inline void *devm_kmalloc_array(struct device *dev, size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return devm_kmalloc(dev, bytes, flags); } static inline void *devm_kcalloc(struct device *dev, size_t n, size_t size, gfp_t flags) { return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO); } static inline __realloc_size(3, 4) void * __must_check devm_krealloc_array(struct device *dev, void *p, size_t new_n, size_t new_size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; return devm_krealloc(dev, p, bytes, flags); } void devm_kfree(struct device *dev, const void *p); char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc; const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp); void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp) __realloc_size(3); unsigned long devm_get_free_pages(struct device *dev, gfp_t gfp_mask, unsigned int order); void devm_free_pages(struct device *dev, unsigned long addr); #ifdef CONFIG_HAS_IOMEM void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res); void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res); void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, resource_size_t *size); #else static inline void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res) { return ERR_PTR(-EINVAL); } static inline void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res) { return ERR_PTR(-EINVAL); } static inline void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, resource_size_t *size) { return ERR_PTR(-EINVAL); } #endif /* allows to add/remove a custom action to devres stack */ void devm_remove_action(struct device *dev, void (*action)(void *), void *data); void devm_release_action(struct device *dev, void (*action)(void *), void *data); int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name); #define devm_add_action(dev, action, data) \ __devm_add_action(dev, action, data, #action) static inline int __devm_add_action_or_reset(struct device *dev, void (*action)(void *), void *data, const char *name) { int ret; ret = __devm_add_action(dev, action, data, name); if (ret) action(data); return ret; } #define devm_add_action_or_reset(dev, action, data) \ __devm_add_action_or_reset(dev, action, data, #action) /** * devm_alloc_percpu - Resource-managed alloc_percpu * @dev: Device to allocate per-cpu memory for * @type: Type to allocate per-cpu memory for * * Managed alloc_percpu. Per-cpu memory allocated with this function is * automatically freed on driver detach. * * RETURNS: * Pointer to allocated memory on success, NULL on failure. */ #define devm_alloc_percpu(dev, type) \ ((typeof(type) __percpu *)__devm_alloc_percpu((dev), sizeof(type), \ __alignof__(type))) void __percpu *__devm_alloc_percpu(struct device *dev, size_t size, size_t align); void devm_free_percpu(struct device *dev, void __percpu *pdata); struct device_dma_parameters { /* * a low level driver may set these to teach IOMMU code about * sg limitations. */ unsigned int max_segment_size; unsigned int min_align_mask; unsigned long segment_boundary_mask; }; /** * enum device_link_state - Device link states. * @DL_STATE_NONE: The presence of the drivers is not being tracked. * @DL_STATE_DORMANT: None of the supplier/consumer drivers is present. * @DL_STATE_AVAILABLE: The supplier driver is present, but the consumer is not. * @DL_STATE_CONSUMER_PROBE: The consumer is probing (supplier driver present). * @DL_STATE_ACTIVE: Both the supplier and consumer drivers are present. * @DL_STATE_SUPPLIER_UNBIND: The supplier driver is unbinding. */ enum device_link_state { DL_STATE_NONE = -1, DL_STATE_DORMANT = 0, DL_STATE_AVAILABLE, DL_STATE_CONSUMER_PROBE, DL_STATE_ACTIVE, DL_STATE_SUPPLIER_UNBIND, }; /* * Device link flags. * * STATELESS: The core will not remove this link automatically. * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind. * PM_RUNTIME: If set, the runtime PM framework will use this link. * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind. * AUTOPROBE_CONSUMER: Probe consumer driver automatically after supplier binds. * MANAGED: The core tracks presence of supplier/consumer drivers (internal). * SYNC_STATE_ONLY: Link only affects sync_state() behavior. * INFERRED: Inferred from data (eg: firmware) and not from driver actions. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) #define DL_FLAG_PM_RUNTIME BIT(2) #define DL_FLAG_RPM_ACTIVE BIT(3) #define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4) #define DL_FLAG_AUTOPROBE_CONSUMER BIT(5) #define DL_FLAG_MANAGED BIT(6) #define DL_FLAG_SYNC_STATE_ONLY BIT(7) #define DL_FLAG_INFERRED BIT(8) #define DL_FLAG_CYCLE BIT(9) /** * enum dl_dev_state - Device driver presence tracking information. * @DL_DEV_NO_DRIVER: There is no driver attached to the device. * @DL_DEV_PROBING: A driver is probing. * @DL_DEV_DRIVER_BOUND: The driver has been bound to the device. * @DL_DEV_UNBINDING: The driver is unbinding from the device. */ enum dl_dev_state { DL_DEV_NO_DRIVER = 0, DL_DEV_PROBING, DL_DEV_DRIVER_BOUND, DL_DEV_UNBINDING, }; /** * enum device_removable - Whether the device is removable. The criteria for a * device to be classified as removable is determined by its subsystem or bus. * @DEVICE_REMOVABLE_NOT_SUPPORTED: This attribute is not supported for this * device (default). * @DEVICE_REMOVABLE_UNKNOWN: Device location is Unknown. * @DEVICE_FIXED: Device is not removable by the user. * @DEVICE_REMOVABLE: Device is removable by the user. */ enum device_removable { DEVICE_REMOVABLE_NOT_SUPPORTED = 0, /* must be 0 */ DEVICE_REMOVABLE_UNKNOWN, DEVICE_FIXED, DEVICE_REMOVABLE, }; /** * struct dev_links_info - Device data related to device links. * @suppliers: List of links to supplier devices. * @consumers: List of links to consumer devices. * @defer_sync: Hook to global list of devices that have deferred sync_state. * @status: Driver status information. */ struct dev_links_info { struct list_head suppliers; struct list_head consumers; struct list_head defer_sync; enum dl_dev_state status; }; /** * struct dev_msi_info - Device data related to MSI * @domain: The MSI interrupt domain associated to the device * @data: Pointer to MSI device data */ struct dev_msi_info { #ifdef CONFIG_GENERIC_MSI_IRQ struct irq_domain *domain; struct msi_device_data *data; #endif }; /** * enum device_physical_location_panel - Describes which panel surface of the * system's housing the device connection point resides on. * @DEVICE_PANEL_TOP: Device connection point is on the top panel. * @DEVICE_PANEL_BOTTOM: Device connection point is on the bottom panel. * @DEVICE_PANEL_LEFT: Device connection point is on the left panel. * @DEVICE_PANEL_RIGHT: Device connection point is on the right panel. * @DEVICE_PANEL_FRONT: Device connection point is on the front panel. * @DEVICE_PANEL_BACK: Device connection point is on the back panel. * @DEVICE_PANEL_UNKNOWN: The panel with device connection point is unknown. */ enum device_physical_location_panel { DEVICE_PANEL_TOP, DEVICE_PANEL_BOTTOM, DEVICE_PANEL_LEFT, DEVICE_PANEL_RIGHT, DEVICE_PANEL_FRONT, DEVICE_PANEL_BACK, DEVICE_PANEL_UNKNOWN, }; /** * enum device_physical_location_vertical_position - Describes vertical * position of the device connection point on the panel surface. * @DEVICE_VERT_POS_UPPER: Device connection point is at upper part of panel. * @DEVICE_VERT_POS_CENTER: Device connection point is at center part of panel. * @DEVICE_VERT_POS_LOWER: Device connection point is at lower part of panel. */ enum device_physical_location_vertical_position { DEVICE_VERT_POS_UPPER, DEVICE_VERT_POS_CENTER, DEVICE_VERT_POS_LOWER, }; /** * enum device_physical_location_horizontal_position - Describes horizontal * position of the device connection point on the panel surface. * @DEVICE_HORI_POS_LEFT: Device connection point is at left part of panel. * @DEVICE_HORI_POS_CENTER: Device connection point is at center part of panel. * @DEVICE_HORI_POS_RIGHT: Device connection point is at right part of panel. */ enum device_physical_location_horizontal_position { DEVICE_HORI_POS_LEFT, DEVICE_HORI_POS_CENTER, DEVICE_HORI_POS_RIGHT, }; /** * struct device_physical_location - Device data related to physical location * of the device connection point. * @panel: Panel surface of the system's housing that the device connection * point resides on. * @vertical_position: Vertical position of the device connection point within * the panel. * @horizontal_position: Horizontal position of the device connection point * within the panel. * @dock: Set if the device connection point resides in a docking station or * port replicator. * @lid: Set if this device connection point resides on the lid of laptop * system. */ struct device_physical_location { enum device_physical_location_panel panel; enum device_physical_location_vertical_position vertical_position; enum device_physical_location_horizontal_position horizontal_position; bool dock; bool lid; }; /** * struct device - The basic device structure * @parent: The device's "parent" device, the device to which it is attached. * In most cases, a parent device is some sort of bus or host * controller. If parent is NULL, the device, is a top-level device, * which is not usually what you want. * @p: Holds the private data of the driver core portions of the device. * See the comment of the struct device_private for detail. * @kobj: A top-level, abstract class from which other classes are derived. * @init_name: Initial name of the device. * @type: The type of device. * This identifies the device type and carries type-specific * information. * @mutex: Mutex to synchronize calls to its driver. * @bus: Type of bus device is on. * @driver: Which driver has allocated this * @platform_data: Platform data specific to the device. * Example: For devices on custom boards, as typical of embedded * and SOC based hardware, Linux often uses platform_data to point * to board-specific structures describing devices and how they * are wired. That can include what ports are available, chip * variants, which GPIO pins act in what additional roles, and so * on. This shrinks the "Board Support Packages" (BSPs) and * minimizes board-specific #ifdefs in drivers. * @driver_data: Private pointer for driver specific info. * @links: Links to suppliers and consumers of this device. * @power: For device power management. * See Documentation/driver-api/pm/devices.rst for details. * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. * @msi: MSI related data * @numa_node: NUMA node this device is close to. * @dma_ops: DMA mapping operations for this device. * @dma_mask: Dma mask (if dma'ble device). * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all * hardware supports 64-bit addresses for consistent allocations * such descriptors. * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller * DMA limit than the device itself supports. * @dma_range_map: map for DMA memory ranges relative to that of RAM * @dma_parms: A low level driver may set these to teach IOMMU code about * segment limitations. * @dma_pools: Dma pools (if dma'ble device). * @dma_mem: Internal for coherent mem override. * @cma_area: Contiguous memory area for dma allocations * @dma_io_tlb_mem: Software IO TLB allocator. Not for driver use. * @dma_io_tlb_pools: List of transient swiotlb memory pools. * @dma_io_tlb_lock: Protects changes to the list of active pools. * @dma_uses_io_tlb: %true if device has used the software IO TLB. * @archdata: For arch-specific additions. * @of_node: Associated device tree node. * @fwnode: Associated device node supplied by platform firmware. * @devt: For creating the sysfs "dev". * @id: device instance * @devres_lock: Spinlock to protect the resource of the device. * @devres_head: The resources list of the device. * @class: The class of the device. * @groups: Optional attribute groups. * @release: Callback to free the device after all references have * gone away. This should be set by the allocator of the * device (i.e. the bus driver that discovered the device). * @iommu_group: IOMMU group the device belongs to. * @iommu: Per device generic IOMMU runtime data * @physical_location: Describes physical location of the device connection * point in the system housing. * @removable: Whether the device can be removed from the system. This * should be set by the subsystem / bus driver that discovered * the device. * * @offline_disabled: If set, the device is permanently online. * @offline: Set after successful invocation of bus type's .offline(). * @of_node_reused: Set if the device-tree node is shared with an ancestor * device. * @state_synced: The hardware state of this device has been synced to match * the software state of this device by calling the driver/bus * sync_state() callback. * @can_match: The device has matched with a driver at least once or it is in * a bus (like AMBA) which can't check for matching drivers until * other devices probe successfully. * @dma_coherent: this particular device is dma coherent, even if the * architecture supports non-coherent devices. * @dma_ops_bypass: If set to %true then the dma_ops are bypassed for the * streaming DMA operations (->map_* / ->unmap_* / ->sync_*), * and optionall (if the coherent mask is large enough) also * for dma allocations. This flag is managed by the dma ops * instance from ->dma_supported. * @dma_skip_sync: DMA sync operations can be skipped for coherent buffers. * @dma_iommu: Device is using default IOMMU implementation for DMA and * doesn't rely on dma_ops structure. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information * that the device model core needs to model the system. Most subsystems, * however, track additional information about the devices they host. As a * result, it is rare for devices to be represented by bare device structures; * instead, that structure, like kobject structures, is usually embedded within * a higher-level representation of the device. */ struct device { struct kobject kobj; struct device *parent; struct device_private *p; const char *init_name; /* initial name of the device */ const struct device_type *type; const struct bus_type *bus; /* type of bus device is on */ struct device_driver *driver; /* which driver has allocated this device */ void *platform_data; /* Platform specific data, device core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set_drvdata/dev_get_drvdata */ struct mutex mutex; /* mutex to synchronize calls to * its driver. */ struct dev_links_info links; struct dev_pm_info power; struct dev_pm_domain *pm_domain; #ifdef CONFIG_ENERGY_MODEL struct em_perf_domain *em_pd; #endif #ifdef CONFIG_PINCTRL struct dev_pin_info *pins; #endif struct dev_msi_info msi; #ifdef CONFIG_ARCH_HAS_DMA_OPS const struct dma_map_ops *dma_ops; #endif u64 *dma_mask; /* dma mask (if dma'able device) */ u64 coherent_dma_mask;/* Like dma_mask, but for alloc_coherent mappings as not all hardware supports 64 bit addresses for consistent allocations such descriptors. */ u64 bus_dma_limit; /* upstream dma constraint */ const struct bus_dma_region *dma_range_map; struct device_dma_parameters *dma_parms; struct list_head dma_pools; /* dma pools (if dma'ble) */ #ifdef CONFIG_DMA_DECLARE_COHERENT struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ #endif #ifdef CONFIG_DMA_CMA struct cma *cma_area; /* contiguous memory area for dma allocations */ #endif #ifdef CONFIG_SWIOTLB struct io_tlb_mem *dma_io_tlb_mem; #endif #ifdef CONFIG_SWIOTLB_DYNAMIC struct list_head dma_io_tlb_pools; spinlock_t dma_io_tlb_lock; bool dma_uses_io_tlb; #endif /* arch specific additions */ struct dev_archdata archdata; struct device_node *of_node; /* associated device tree node */ struct fwnode_handle *fwnode; /* firmware device node */ #ifdef CONFIG_NUMA int numa_node; /* NUMA node this device is close to */ #endif dev_t devt; /* dev_t, creates the sysfs "dev" */ u32 id; /* device instance */ spinlock_t devres_lock; struct list_head devres_head; const struct class *class; const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); struct iommu_group *iommu_group; struct dev_iommu *iommu; struct device_physical_location *physical_location; enum device_removable removable; bool offline_disabled:1; bool offline:1; bool of_node_reused:1; bool state_synced:1; bool can_match:1; #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) bool dma_coherent:1; #endif #ifdef CONFIG_DMA_OPS_BYPASS bool dma_ops_bypass : 1; #endif #ifdef CONFIG_DMA_NEED_SYNC bool dma_skip_sync:1; #endif #ifdef CONFIG_IOMMU_DMA bool dma_iommu:1; #endif }; /** * struct device_link - Device link representation. * @supplier: The device on the supplier end of the link. * @s_node: Hook to the supplier device's list of links to consumers. * @consumer: The device on the consumer end of the link. * @c_node: Hook to the consumer device's list of links to suppliers. * @link_dev: device used to expose link details in sysfs * @status: The state of the link (with respect to the presence of drivers). * @flags: Link flags. * @rpm_active: Whether or not the consumer device is runtime-PM-active. * @kref: Count repeated addition of the same link. * @rm_work: Work structure used for removing the link. * @supplier_preactivated: Supplier has been made active before consumer probe. */ struct device_link { struct device *supplier; struct list_head s_node; struct device *consumer; struct list_head c_node; struct device link_dev; enum device_link_state status; u32 flags; refcount_t rpm_active; struct kref kref; struct work_struct rm_work; bool supplier_preactivated; /* Owned by consumer probe. */ }; #define kobj_to_dev(__kobj) container_of_const(__kobj, struct device, kobj) /** * device_iommu_mapped - Returns true when the device DMA is translated * by an IOMMU * @dev: Device to perform the check on */ static inline bool device_iommu_mapped(struct device *dev) { return (dev->iommu_group != NULL); } /* Get the wakeup routines, which depend on struct device */ #include <linux/pm_wakeup.h> /** * dev_name - Return a device's name. * @dev: Device with name to get. * Return: The kobject name of the device, or its initial name if unavailable. */ static inline const char *dev_name(const struct device *dev) { /* Use the init name until the kobject becomes available */ if (dev->init_name) return dev->init_name; return kobject_name(&dev->kobj); } /** * dev_bus_name - Return a device's bus/class name, if at all possible * @dev: struct device to get the bus/class name of * * Will return the name of the bus/class the device is attached to. If it is * not attached to a bus/class, an empty string will be returned. */ static inline const char *dev_bus_name(const struct device *dev) { return dev->bus ? dev->bus->name : (dev->class ? dev->class->name : ""); } __printf(2, 3) int dev_set_name(struct device *dev, const char *name, ...); #ifdef CONFIG_NUMA static inline int dev_to_node(struct device *dev) { return dev->numa_node; } static inline void set_dev_node(struct device *dev, int node) { dev->numa_node = node; } #else static inline int dev_to_node(struct device *dev) { return NUMA_NO_NODE; } static inline void set_dev_node(struct device *dev, int node) { } #endif static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) { #ifdef CONFIG_GENERIC_MSI_IRQ return dev->msi.domain; #else return NULL; #endif } static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d) { #ifdef CONFIG_GENERIC_MSI_IRQ dev->msi.domain = d; #endif } static inline void *dev_get_drvdata(const struct device *dev) { return dev->driver_data; } static inline void dev_set_drvdata(struct device *dev, void *data) { dev->driver_data = data; } static inline struct pm_subsys_data *dev_to_psd(struct device *dev) { return dev ? dev->power.subsys_data : NULL; } static inline unsigned int dev_get_uevent_suppress(const struct device *dev) { return dev->kobj.uevent_suppress; } static inline void dev_set_uevent_suppress(struct device *dev, int val) { dev->kobj.uevent_suppress = val; } static inline int device_is_registered(struct device *dev) { return dev->kobj.state_in_sysfs; } static inline void device_enable_async_suspend(struct device *dev) { if (!dev->power.is_prepared) dev->power.async_suspend = true; } static inline void device_disable_async_suspend(struct device *dev) { if (!dev->power.is_prepared) dev->power.async_suspend = false; } static inline bool device_async_suspend_enabled(struct device *dev) { return !!dev->power.async_suspend; } static inline bool device_pm_not_required(struct device *dev) { return dev->power.no_pm; } static inline void device_set_pm_not_required(struct device *dev) { dev->power.no_pm = true; } static inline void dev_pm_syscore_device(struct device *dev, bool val) { #ifdef CONFIG_PM_SLEEP dev->power.syscore = val; #endif } static inline void dev_pm_set_driver_flags(struct device *dev, u32 flags) { dev->power.driver_flags = flags; } static inline bool dev_pm_test_driver_flags(struct device *dev, u32 flags) { return !!(dev->power.driver_flags & flags); } static inline void device_lock(struct device *dev) { mutex_lock(&dev->mutex); } static inline int device_lock_interruptible(struct device *dev) { return mutex_lock_interruptible(&dev->mutex); } static inline int device_trylock(struct device *dev) { return mutex_trylock(&dev->mutex); } static inline void device_unlock(struct device *dev) { mutex_unlock(&dev->mutex); } DEFINE_GUARD(device, struct device *, device_lock(_T), device_unlock(_T)) static inline void device_lock_assert(struct device *dev) { lockdep_assert_held(&dev->mutex); } static inline bool dev_has_sync_state(struct device *dev) { if (!dev) return false; if (dev->driver && dev->driver->sync_state) return true; if (dev->bus && dev->bus->sync_state) return true; return false; } static inline void dev_set_removable(struct device *dev, enum device_removable removable) { dev->removable = removable; } static inline bool dev_is_removable(struct device *dev) { return dev->removable == DEVICE_REMOVABLE; } static inline bool dev_removable_is_valid(struct device *dev) { return dev->removable != DEVICE_REMOVABLE_NOT_SUPPORTED; } /* * High level routines for use by the bus drivers */ int __must_check device_register(struct device *dev); void device_unregister(struct device *dev); void device_initialize(struct device *dev); int __must_check device_add(struct device *dev); void device_del(struct device *dev); DEFINE_FREE(device_del, struct device *, if (_T) device_del(_T)) int device_for_each_child(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); int device_for_each_child_reverse(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); int device_for_each_child_reverse_from(struct device *parent, struct device *from, const void *data, int (*fn)(struct device *, const void *)); struct device *device_find_child(struct device *dev, void *data, int (*match)(struct device *dev, void *data)); struct device *device_find_child_by_name(struct device *parent, const char *name); struct device *device_find_any_child(struct device *parent); int device_rename(struct device *dev, const char *new_name); int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); static inline bool device_supports_offline(struct device *dev) { return dev->bus && dev->bus->offline && dev->bus->online; } #define __device_lock_set_class(dev, name, key) \ do { \ struct device *__d2 __maybe_unused = dev; \ lock_set_class(&__d2->mutex.dep_map, name, key, 0, _THIS_IP_); \ } while (0) /** * device_lock_set_class - Specify a temporary lock class while a device * is attached to a driver * @dev: device to modify * @key: lock class key data * * This must be called with the device_lock() already held, for example * from driver ->probe(). Take care to only override the default * lockdep_no_validate class. */ #ifdef CONFIG_LOCKDEP #define device_lock_set_class(dev, key) \ do { \ struct device *__d = dev; \ dev_WARN_ONCE(__d, !lockdep_match_class(&__d->mutex, \ &__lockdep_no_validate__), \ "overriding existing custom lock class\n"); \ __device_lock_set_class(__d, #key, key); \ } while (0) #else #define device_lock_set_class(dev, key) __device_lock_set_class(dev, #key, key) #endif /** * device_lock_reset_class - Return a device to the default lockdep novalidate state * @dev: device to modify * * This must be called with the device_lock() already held, for example * from driver ->remove(). */ #define device_lock_reset_class(dev) \ do { \ struct device *__d __maybe_unused = dev; \ lock_set_novalidate_class(&__d->mutex.dep_map, "&dev->mutex", \ _THIS_IP_); \ } while (0) void lock_device_hotplug(void); void unlock_device_hotplug(void); int lock_device_hotplug_sysfs(void); int device_offline(struct device *dev); int device_online(struct device *dev); void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void device_set_node(struct device *dev, struct fwnode_handle *fwnode); void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); static inline struct device_node *dev_of_node(struct device *dev) { if (!IS_ENABLED(CONFIG_OF) || !dev) return NULL; return dev->of_node; } static inline int dev_num_vf(struct device *dev) { if (dev->bus && dev->bus->num_vf) return dev->bus->num_vf(dev); return 0; } /* * Root device objects for grouping under /sys/devices */ struct device *__root_device_register(const char *name, struct module *owner); /* This is a macro to avoid include problems with THIS_MODULE */ #define root_device_register(name) \ __root_device_register(name, THIS_MODULE) void root_device_unregister(struct device *root); static inline void *dev_get_platdata(const struct device *dev) { return dev->platform_data; } /* * Manual binding of a device to driver. See drivers/base/bus.c * for information on use. */ int __must_check device_driver_attach(const struct device_driver *drv, struct device *dev); int __must_check device_bind_driver(struct device *dev); void device_release_driver(struct device *dev); int __must_check device_attach(struct device *dev); int __must_check driver_attach(const struct device_driver *drv); void device_initial_probe(struct device *dev); int __must_check device_reprobe(struct device *dev); bool device_is_bound(struct device *dev); /* * Easy functions for dynamically creating devices on the fly */ __printf(5, 6) struct device * device_create(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...); __printf(6, 7) struct device * device_create_with_groups(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); void device_destroy(const struct class *cls, dev_t devt); int __must_check device_add_groups(struct device *dev, const struct attribute_group **groups); void device_remove_groups(struct device *dev, const struct attribute_group **groups); static inline int __must_check device_add_group(struct device *dev, const struct attribute_group *grp) { const struct attribute_group *groups[] = { grp, NULL }; return device_add_groups(dev, groups); } static inline void device_remove_group(struct device *dev, const struct attribute_group *grp) { const struct attribute_group *groups[] = { grp, NULL }; return device_remove_groups(dev, groups); } int __must_check devm_device_add_group(struct device *dev, const struct attribute_group *grp); /* * get_device - atomically increment the reference count for the device. * */ struct device *get_device(struct device *dev); void put_device(struct device *dev); DEFINE_FREE(put_device, struct device *, if (_T) put_device(_T)) bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS int devtmpfs_mount(void); #else static inline int devtmpfs_mount(void) { return 0; } #endif /* drivers/base/power/shutdown.c */ void device_shutdown(void); /* debugging and troubleshooting/diagnostic helpers. */ const char *dev_driver_string(const struct device *dev); /* Device links interface. */ struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags); void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); void device_link_wait_removal(void); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_CHARDEV_MAJOR(major) \ MODULE_ALIAS("char-major-" __stringify(major) "-*") #endif /* _DEVICE_H_ */ |
| 120 120 4 2 120 95 84 14 92 2 91 91 91 8 2 2 76 1 77 3 2 1 5 57 9 1 62 1 63 1 18 68 1 18 69 87 86 10 77 16 69 17 70 75 12 71 16 74 74 67 10 74 74 74 74 81 6 73 18 18 10 6 70 70 59 7 5 5 1 4 4 5 5 5 5 4 1 25 25 18 18 9 9 1 16 1 1 8 8 16 8 8 1 15 17 3 16 18 17 17 17 1 1 1 1 13 13 13 13 12 1 12 12 13 12 9 1 8 7 1 8 1 7 1 1 1 5 1 1 1 1 5 6 5 1 6 5 1 5 1 6 5 1 6 7 1 7 1 1 7 1 7 8 7 1 8 8 8 8 6 2 5 5 5 5 5 5 5 5 5 18 19 19 2 1 2 11 2 7 6 1 5 5 6 11 5 1 10 11 16 1 5 12 5 12 17 17 3 14 5 12 6 10 14 3 16 1 25 25 24 25 25 17 7 24 1 25 1 24 24 1 23 23 14 9 7 16 23 23 20 6 14 20 11 9 18 7 7 7 7 6 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * namei.c * * Create and rename file, directory, symlinks * * Copyright (C) 2002, 2004 Oracle. All rights reserved. * * Portions of this code from linux/fs/ext3/dir.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/dir.c * * Copyright (C) 1991, 1992 Linux Torvalds */ #include <linux/fs.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/highmem.h> #include <linux/quotaops.h> #include <linux/iversion.h> #include <cluster/masklog.h> #include "ocfs2.h" #include "alloc.h" #include "dcache.h" #include "dir.h" #include "dlmglue.h" #include "extent_map.h" #include "file.h" #include "inode.h" #include "journal.h" #include "namei.h" #include "suballoc.h" #include "super.h" #include "symlink.h" #include "sysfile.h" #include "uptodate.h" #include "xattr.h" #include "acl.h" #include "ocfs2_trace.h" #include "ioctl.h" #include "buffer_head_io.h" static int ocfs2_mknod_locked(struct ocfs2_super *osb, struct inode *dir, struct inode *inode, dev_t dev, struct buffer_head **new_fe_bh, struct buffer_head *parent_fe_bh, handle_t *handle, struct ocfs2_alloc_context *inode_ac); static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb, struct inode **ret_orphan_dir, u64 blkno, char *name, struct ocfs2_dir_lookup_result *lookup, bool dio); static int ocfs2_orphan_add(struct ocfs2_super *osb, handle_t *handle, struct inode *inode, struct buffer_head *fe_bh, char *name, struct ocfs2_dir_lookup_result *lookup, struct inode *orphan_dir_inode, bool dio); static int ocfs2_create_symlink_data(struct ocfs2_super *osb, handle_t *handle, struct inode *inode, const char *symname); static int ocfs2_double_lock(struct ocfs2_super *osb, struct buffer_head **bh1, struct inode *inode1, struct buffer_head **bh2, struct inode *inode2, int rename); static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2); /* An orphan dir name is an 8 byte value, printed as a hex string */ #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64))) static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { int status; u64 blkno; struct inode *inode = NULL; struct dentry *ret; struct ocfs2_inode_info *oi; trace_ocfs2_lookup(dir, dentry, dentry->d_name.len, dentry->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno, 0); if (dentry->d_name.len > OCFS2_MAX_FILENAME_LEN) { ret = ERR_PTR(-ENAMETOOLONG); goto bail; } status = ocfs2_inode_lock_nested(dir, NULL, 0, OI_LS_PARENT); if (status < 0) { if (status != -ENOENT) mlog_errno(status); ret = ERR_PTR(status); goto bail; } status = ocfs2_lookup_ino_from_name(dir, dentry->d_name.name, dentry->d_name.len, &blkno); if (status < 0) goto bail_add; inode = ocfs2_iget(OCFS2_SB(dir->i_sb), blkno, 0, 0); if (IS_ERR(inode)) { ret = ERR_PTR(-EACCES); goto bail_unlock; } oi = OCFS2_I(inode); /* Clear any orphaned state... If we were able to look up the * inode from a directory, it certainly can't be orphaned. We * might have the bad state from a node which intended to * orphan this inode but crashed before it could commit the * unlink. */ spin_lock(&oi->ip_lock); oi->ip_flags &= ~OCFS2_INODE_MAYBE_ORPHANED; spin_unlock(&oi->ip_lock); bail_add: ret = d_splice_alias(inode, dentry); if (inode) { /* * If d_splice_alias() finds a DCACHE_DISCONNECTED * dentry, it will d_move() it on top of ourse. The * return value will indicate this however, so in * those cases, we switch them around for the locking * code. * * NOTE: This dentry already has ->d_op set from * ocfs2_get_parent() and ocfs2_get_dentry() */ if (!IS_ERR_OR_NULL(ret)) dentry = ret; status = ocfs2_dentry_attach_lock(dentry, inode, OCFS2_I(dir)->ip_blkno); if (status) { mlog_errno(status); ret = ERR_PTR(status); goto bail_unlock; } } else ocfs2_dentry_attach_gen(dentry); bail_unlock: /* Don't drop the cluster lock until *after* the d_add -- * unlink on another node will message us to remove that * dentry under this lock so otherwise we can race this with * the downconvert thread and have a stale dentry. */ ocfs2_inode_unlock(dir, 0); bail: trace_ocfs2_lookup_ret(ret); return ret; } static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode) { struct inode *inode; int status; inode = new_inode(dir->i_sb); if (!inode) { mlog(ML_ERROR, "new_inode failed!\n"); return ERR_PTR(-ENOMEM); } /* populate as many fields early on as possible - many of * these are used by the support functions here and in * callers. */ if (S_ISDIR(mode)) set_nlink(inode, 2); mode = mode_strip_sgid(&nop_mnt_idmap, dir, mode); inode_init_owner(&nop_mnt_idmap, inode, dir, mode); status = dquot_initialize(inode); if (status) return ERR_PTR(status); return inode; } static void ocfs2_cleanup_add_entry_failure(struct ocfs2_super *osb, struct dentry *dentry, struct inode *inode) { struct ocfs2_dentry_lock *dl = dentry->d_fsdata; ocfs2_simple_drop_lockres(osb, &dl->dl_lockres); ocfs2_lock_res_free(&dl->dl_lockres); BUG_ON(dl->dl_count != 1); spin_lock(&dentry_attach_lock); dentry->d_fsdata = NULL; spin_unlock(&dentry_attach_lock); kfree(dl); iput(inode); } static int ocfs2_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { int status = 0; struct buffer_head *parent_fe_bh = NULL; handle_t *handle = NULL; struct ocfs2_super *osb; struct ocfs2_dinode *dirfe; struct ocfs2_dinode *fe = NULL; struct buffer_head *new_fe_bh = NULL; struct inode *inode = NULL; struct ocfs2_alloc_context *inode_ac = NULL; struct ocfs2_alloc_context *data_ac = NULL; struct ocfs2_alloc_context *meta_ac = NULL; int want_clusters = 0; int want_meta = 0; int xattr_credits = 0; struct ocfs2_security_xattr_info si = { .name = NULL, .enable = 1, }; int did_quota_inode = 0; struct ocfs2_dir_lookup_result lookup = { NULL, }; sigset_t oldset; int did_block_signals = 0; struct ocfs2_dentry_lock *dl = NULL; trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno, (unsigned long)dev, mode); status = dquot_initialize(dir); if (status) { mlog_errno(status); return status; } /* get our super block */ osb = OCFS2_SB(dir->i_sb); status = ocfs2_inode_lock(dir, &parent_fe_bh, 1); if (status < 0) { if (status != -ENOENT) mlog_errno(status); return status; } if (S_ISDIR(mode) && (dir->i_nlink >= ocfs2_link_max(osb))) { status = -EMLINK; goto leave; } dirfe = (struct ocfs2_dinode *) parent_fe_bh->b_data; if (!ocfs2_read_links_count(dirfe)) { /* can't make a file in a deleted directory. */ status = -ENOENT; goto leave; } status = ocfs2_check_dir_for_entry(dir, dentry->d_name.name, dentry->d_name.len); if (status) goto leave; /* get a spot inside the dir. */ status = ocfs2_prepare_dir_for_insert(osb, dir, parent_fe_bh, dentry->d_name.name, dentry->d_name.len, &lookup); if (status < 0) { mlog_errno(status); goto leave; } /* reserve an inode spot */ status = ocfs2_reserve_new_inode(osb, &inode_ac); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto leave; } inode = ocfs2_get_init_inode(dir, mode); if (IS_ERR(inode)) { status = PTR_ERR(inode); inode = NULL; mlog_errno(status); goto leave; } /* get security xattr */ status = ocfs2_init_security_get(inode, dir, &dentry->d_name, &si); if (status) { if (status == -EOPNOTSUPP) si.enable = 0; else { mlog_errno(status); goto leave; } } /* calculate meta data/clusters for setting security and acl xattr */ status = ocfs2_calc_xattr_init(dir, parent_fe_bh, mode, &si, &want_clusters, &xattr_credits, &want_meta); if (status < 0) { mlog_errno(status); goto leave; } /* Reserve a cluster if creating an extent based directory. */ if (S_ISDIR(mode) && !ocfs2_supports_inline_data(osb)) { want_clusters += 1; /* Dir indexing requires extra space as well */ if (ocfs2_supports_indexed_dirs(osb)) want_meta++; } status = ocfs2_reserve_new_metadata_blocks(osb, want_meta, &meta_ac); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto leave; } status = ocfs2_reserve_clusters(osb, want_clusters, &data_ac); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto leave; } handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb, S_ISDIR(mode), xattr_credits)); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; mlog_errno(status); goto leave; } /* Starting to change things, restart is no longer possible. */ ocfs2_block_signals(&oldset); did_block_signals = 1; status = dquot_alloc_inode(inode); if (status) goto leave; did_quota_inode = 1; /* do the real work now. */ status = ocfs2_mknod_locked(osb, dir, inode, dev, &new_fe_bh, parent_fe_bh, handle, inode_ac); if (status < 0) { mlog_errno(status); goto leave; } fe = (struct ocfs2_dinode *) new_fe_bh->b_data; if (S_ISDIR(mode)) { status = ocfs2_fill_new_dir(osb, handle, dir, inode, new_fe_bh, data_ac, meta_ac); if (status < 0) { mlog_errno(status); goto leave; } status = ocfs2_journal_access_di(handle, INODE_CACHE(dir), parent_fe_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto leave; } ocfs2_add_links_count(dirfe, 1); ocfs2_journal_dirty(handle, parent_fe_bh); inc_nlink(dir); } status = ocfs2_init_acl(handle, inode, dir, new_fe_bh, parent_fe_bh, meta_ac, data_ac); if (status < 0) { mlog_errno(status); goto roll_back; } if (si.enable) { status = ocfs2_init_security_set(handle, inode, new_fe_bh, &si, meta_ac, data_ac); if (status < 0) { mlog_errno(status); goto roll_back; } } /* * Do this before adding the entry to the directory. We add * also set d_op after success so that ->d_iput() will cleanup * the dentry lock even if ocfs2_add_entry() fails below. */ status = ocfs2_dentry_attach_lock(dentry, inode, OCFS2_I(dir)->ip_blkno); if (status) { mlog_errno(status); goto roll_back; } dl = dentry->d_fsdata; status = ocfs2_add_entry(handle, dentry, inode, OCFS2_I(inode)->ip_blkno, parent_fe_bh, &lookup); if (status < 0) { mlog_errno(status); goto roll_back; } insert_inode_hash(inode); d_instantiate(dentry, inode); status = 0; roll_back: if (status < 0 && S_ISDIR(mode)) { ocfs2_add_links_count(dirfe, -1); drop_nlink(dir); } leave: if (status < 0 && did_quota_inode) dquot_free_inode(inode); if (handle) { if (status < 0 && fe) ocfs2_set_links_count(fe, 0); ocfs2_commit_trans(osb, handle); } ocfs2_inode_unlock(dir, 1); if (did_block_signals) ocfs2_unblock_signals(&oldset); brelse(new_fe_bh); brelse(parent_fe_bh); kfree(si.value); ocfs2_free_dir_lookup_result(&lookup); if (inode_ac) ocfs2_free_alloc_context(inode_ac); if (data_ac) ocfs2_free_alloc_context(data_ac); if (meta_ac) ocfs2_free_alloc_context(meta_ac); /* * We should call iput after the i_rwsem of the bitmap been * unlocked in ocfs2_free_alloc_context, or the * ocfs2_delete_inode will mutex_lock again. */ if ((status < 0) && inode) { if (dl) ocfs2_cleanup_add_entry_failure(osb, dentry, inode); OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR; clear_nlink(inode); iput(inode); } if (status) mlog_errno(status); return status; } static int __ocfs2_mknod_locked(struct inode *dir, struct inode *inode, dev_t dev, struct buffer_head **new_fe_bh, struct buffer_head *parent_fe_bh, handle_t *handle, struct ocfs2_alloc_context *inode_ac, u64 fe_blkno, u64 suballoc_loc, u16 suballoc_bit) { int status = 0; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct ocfs2_dinode *fe = NULL; struct ocfs2_extent_list *fel; u16 feat; struct ocfs2_inode_info *oi = OCFS2_I(inode); struct timespec64 ts; *new_fe_bh = NULL; /* populate as many fields early on as possible - many of * these are used by the support functions here and in * callers. */ inode->i_ino = ino_from_blkno(osb->sb, fe_blkno); oi->ip_blkno = fe_blkno; spin_lock(&osb->osb_lock); inode->i_generation = osb->s_next_generation++; spin_unlock(&osb->osb_lock); *new_fe_bh = sb_getblk(osb->sb, fe_blkno); if (!*new_fe_bh) { status = -ENOMEM; mlog_errno(status); goto leave; } ocfs2_set_new_buffer_uptodate(INODE_CACHE(inode), *new_fe_bh); status = ocfs2_journal_access_di(handle, INODE_CACHE(inode), *new_fe_bh, OCFS2_JOURNAL_ACCESS_CREATE); if (status < 0) { mlog_errno(status); goto leave; } fe = (struct ocfs2_dinode *) (*new_fe_bh)->b_data; memset(fe, 0, osb->sb->s_blocksize); fe->i_generation = cpu_to_le32(inode->i_generation); fe->i_fs_generation = cpu_to_le32(osb->fs_generation); fe->i_blkno = cpu_to_le64(fe_blkno); fe->i_suballoc_loc = cpu_to_le64(suballoc_loc); fe->i_suballoc_bit = cpu_to_le16(suballoc_bit); fe->i_suballoc_slot = cpu_to_le16(inode_ac->ac_alloc_slot); fe->i_uid = cpu_to_le32(i_uid_read(inode)); fe->i_gid = cpu_to_le32(i_gid_read(inode)); fe->i_mode = cpu_to_le16(inode->i_mode); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) fe->id1.dev1.i_rdev = cpu_to_le64(huge_encode_dev(dev)); ocfs2_set_links_count(fe, inode->i_nlink); fe->i_last_eb_blk = 0; strcpy(fe->i_signature, OCFS2_INODE_SIGNATURE); fe->i_flags |= cpu_to_le32(OCFS2_VALID_FL); ktime_get_coarse_real_ts64(&ts); fe->i_atime = fe->i_ctime = fe->i_mtime = cpu_to_le64(ts.tv_sec); fe->i_mtime_nsec = fe->i_ctime_nsec = fe->i_atime_nsec = cpu_to_le32(ts.tv_nsec); fe->i_dtime = 0; /* * If supported, directories start with inline data. If inline * isn't supported, but indexing is, we start them as indexed. */ feat = le16_to_cpu(fe->i_dyn_features); if (S_ISDIR(inode->i_mode) && ocfs2_supports_inline_data(osb)) { fe->i_dyn_features = cpu_to_le16(feat | OCFS2_INLINE_DATA_FL); fe->id2.i_data.id_count = cpu_to_le16( ocfs2_max_inline_data_with_xattr(osb->sb, fe)); } else { fel = &fe->id2.i_list; fel->l_tree_depth = 0; fel->l_next_free_rec = 0; fel->l_count = cpu_to_le16(ocfs2_extent_recs_per_inode(osb->sb)); } ocfs2_journal_dirty(handle, *new_fe_bh); ocfs2_populate_inode(inode, fe, 1); ocfs2_ci_set_new(osb, INODE_CACHE(inode)); if (!ocfs2_mount_local(osb)) { status = ocfs2_create_new_inode_locks(inode); if (status < 0) mlog_errno(status); } ocfs2_update_inode_fsync_trans(handle, inode, 1); leave: if (status < 0) { if (*new_fe_bh) { brelse(*new_fe_bh); *new_fe_bh = NULL; } } if (status) mlog_errno(status); return status; } static int ocfs2_mknod_locked(struct ocfs2_super *osb, struct inode *dir, struct inode *inode, dev_t dev, struct buffer_head **new_fe_bh, struct buffer_head *parent_fe_bh, handle_t *handle, struct ocfs2_alloc_context *inode_ac) { int status = 0; u64 suballoc_loc, fe_blkno = 0; u16 suballoc_bit; *new_fe_bh = NULL; status = ocfs2_claim_new_inode(handle, dir, parent_fe_bh, inode_ac, &suballoc_loc, &suballoc_bit, &fe_blkno); if (status < 0) { mlog_errno(status); return status; } return __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh, parent_fe_bh, handle, inode_ac, fe_blkno, suballoc_loc, suballoc_bit); } static int ocfs2_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { int ret; trace_ocfs2_mkdir(dir, dentry, dentry->d_name.len, dentry->d_name.name, OCFS2_I(dir)->ip_blkno, mode); ret = ocfs2_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFDIR, 0); if (ret) mlog_errno(ret); return ret; } static int ocfs2_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { int ret; trace_ocfs2_create(dir, dentry, dentry->d_name.len, dentry->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno, mode); ret = ocfs2_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0); if (ret) mlog_errno(ret); return ret; } static int ocfs2_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { handle_t *handle; struct inode *inode = d_inode(old_dentry); struct inode *old_dir = d_inode(old_dentry->d_parent); int err; struct buffer_head *fe_bh = NULL; struct buffer_head *old_dir_bh = NULL; struct buffer_head *parent_fe_bh = NULL; struct ocfs2_dinode *fe = NULL; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct ocfs2_dir_lookup_result lookup = { NULL, }; sigset_t oldset; u64 old_de_ino; trace_ocfs2_link((unsigned long long)OCFS2_I(inode)->ip_blkno, old_dentry->d_name.len, old_dentry->d_name.name, dentry->d_name.len, dentry->d_name.name); if (S_ISDIR(inode->i_mode)) return -EPERM; err = dquot_initialize(dir); if (err) { mlog_errno(err); return err; } err = ocfs2_double_lock(osb, &old_dir_bh, old_dir, &parent_fe_bh, dir, 0); if (err < 0) { if (err != -ENOENT) mlog_errno(err); return err; } /* make sure both dirs have bhs * get an extra ref on old_dir_bh if old==new */ if (!parent_fe_bh) { if (old_dir_bh) { parent_fe_bh = old_dir_bh; get_bh(parent_fe_bh); } else { mlog(ML_ERROR, "%s: no old_dir_bh!\n", osb->uuid_str); err = -EIO; goto out; } } if (!dir->i_nlink) { err = -ENOENT; goto out; } err = ocfs2_lookup_ino_from_name(old_dir, old_dentry->d_name.name, old_dentry->d_name.len, &old_de_ino); if (err) { err = -ENOENT; goto out; } /* * Check whether another node removed the source inode while we * were in the vfs. */ if (old_de_ino != OCFS2_I(inode)->ip_blkno) { err = -ENOENT; goto out; } err = ocfs2_check_dir_for_entry(dir, dentry->d_name.name, dentry->d_name.len); if (err) goto out; err = ocfs2_prepare_dir_for_insert(osb, dir, parent_fe_bh, dentry->d_name.name, dentry->d_name.len, &lookup); if (err < 0) { mlog_errno(err); goto out; } err = ocfs2_inode_lock(inode, &fe_bh, 1); if (err < 0) { if (err != -ENOENT) mlog_errno(err); goto out; } fe = (struct ocfs2_dinode *) fe_bh->b_data; if (ocfs2_read_links_count(fe) >= ocfs2_link_max(osb)) { err = -EMLINK; goto out_unlock_inode; } handle = ocfs2_start_trans(osb, ocfs2_link_credits(osb->sb)); if (IS_ERR(handle)) { err = PTR_ERR(handle); handle = NULL; mlog_errno(err); goto out_unlock_inode; } /* Starting to change things, restart is no longer possible. */ ocfs2_block_signals(&oldset); err = ocfs2_journal_access_di(handle, INODE_CACHE(inode), fe_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (err < 0) { mlog_errno(err); goto out_commit; } inc_nlink(inode); inode_set_ctime_current(inode); ocfs2_set_links_count(fe, inode->i_nlink); fe->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode)); fe->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, fe_bh); err = ocfs2_add_entry(handle, dentry, inode, OCFS2_I(inode)->ip_blkno, parent_fe_bh, &lookup); if (err) { ocfs2_add_links_count(fe, -1); drop_nlink(inode); mlog_errno(err); goto out_commit; } err = ocfs2_dentry_attach_lock(dentry, inode, OCFS2_I(dir)->ip_blkno); if (err) { mlog_errno(err); goto out_commit; } ihold(inode); d_instantiate(dentry, inode); out_commit: ocfs2_commit_trans(osb, handle); ocfs2_unblock_signals(&oldset); out_unlock_inode: ocfs2_inode_unlock(inode, 1); out: ocfs2_double_unlock(old_dir, dir); brelse(fe_bh); brelse(parent_fe_bh); brelse(old_dir_bh); ocfs2_free_dir_lookup_result(&lookup); if (err) mlog_errno(err); return err; } /* * Takes and drops an exclusive lock on the given dentry. This will * force other nodes to drop it. */ static int ocfs2_remote_dentry_delete(struct dentry *dentry) { int ret; ret = ocfs2_dentry_lock(dentry, 1); if (ret) mlog_errno(ret); else ocfs2_dentry_unlock(dentry, 1); return ret; } static inline int ocfs2_inode_is_unlinkable(struct inode *inode) { if (S_ISDIR(inode->i_mode)) { if (inode->i_nlink == 2) return 1; return 0; } if (inode->i_nlink == 1) return 1; return 0; } static int ocfs2_unlink(struct inode *dir, struct dentry *dentry) { int status; int child_locked = 0; bool is_unlinkable = false; struct inode *inode = d_inode(dentry); struct inode *orphan_dir = NULL; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); u64 blkno; struct ocfs2_dinode *fe = NULL; struct buffer_head *fe_bh = NULL; struct buffer_head *parent_node_bh = NULL; handle_t *handle = NULL; char orphan_name[OCFS2_ORPHAN_NAMELEN + 1]; struct ocfs2_dir_lookup_result lookup = { NULL, }; struct ocfs2_dir_lookup_result orphan_insert = { NULL, }; trace_ocfs2_unlink(dir, dentry, dentry->d_name.len, dentry->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno, (unsigned long long)OCFS2_I(inode)->ip_blkno); status = dquot_initialize(dir); if (status) { mlog_errno(status); return status; } BUG_ON(d_inode(dentry->d_parent) != dir); if (inode == osb->root_inode) return -EPERM; status = ocfs2_inode_lock_nested(dir, &parent_node_bh, 1, OI_LS_PARENT); if (status < 0) { if (status != -ENOENT) mlog_errno(status); return status; } status = ocfs2_find_files_on_disk(dentry->d_name.name, dentry->d_name.len, &blkno, dir, &lookup); if (status < 0) { if (status != -ENOENT) mlog_errno(status); goto leave; } if (OCFS2_I(inode)->ip_blkno != blkno) { status = -ENOENT; trace_ocfs2_unlink_noent( (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)blkno, OCFS2_I(inode)->ip_flags); goto leave; } status = ocfs2_inode_lock(inode, &fe_bh, 1); if (status < 0) { if (status != -ENOENT) mlog_errno(status); goto leave; } child_locked = 1; if (S_ISDIR(inode->i_mode)) { if (inode->i_nlink != 2 || !ocfs2_empty_dir(inode)) { status = -ENOTEMPTY; goto leave; } } status = ocfs2_remote_dentry_delete(dentry); if (status < 0) { /* This remote delete should succeed under all normal * circumstances. */ mlog_errno(status); goto leave; } if (ocfs2_inode_is_unlinkable(inode)) { status = ocfs2_prepare_orphan_dir(osb, &orphan_dir, OCFS2_I(inode)->ip_blkno, orphan_name, &orphan_insert, false); if (status < 0) { mlog_errno(status); goto leave; } is_unlinkable = true; } handle = ocfs2_start_trans(osb, ocfs2_unlink_credits(osb->sb)); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; mlog_errno(status); goto leave; } status = ocfs2_journal_access_di(handle, INODE_CACHE(inode), fe_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto leave; } fe = (struct ocfs2_dinode *) fe_bh->b_data; /* delete the name from the parent dir */ status = ocfs2_delete_entry(handle, dir, &lookup); if (status < 0) { mlog_errno(status); goto leave; } if (S_ISDIR(inode->i_mode)) drop_nlink(inode); drop_nlink(inode); ocfs2_set_links_count(fe, inode->i_nlink); ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, fe_bh); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); if (S_ISDIR(inode->i_mode)) drop_nlink(dir); status = ocfs2_mark_inode_dirty(handle, dir, parent_node_bh); if (status < 0) { mlog_errno(status); if (S_ISDIR(inode->i_mode)) inc_nlink(dir); goto leave; } if (is_unlinkable) { status = ocfs2_orphan_add(osb, handle, inode, fe_bh, orphan_name, &orphan_insert, orphan_dir, false); if (status < 0) mlog_errno(status); } leave: if (handle) ocfs2_commit_trans(osb, handle); if (orphan_dir) { /* This was locked for us in ocfs2_prepare_orphan_dir() */ ocfs2_inode_unlock(orphan_dir, 1); inode_unlock(orphan_dir); iput(orphan_dir); } if (child_locked) ocfs2_inode_unlock(inode, 1); ocfs2_inode_unlock(dir, 1); brelse(fe_bh); brelse(parent_node_bh); ocfs2_free_dir_lookup_result(&orphan_insert); ocfs2_free_dir_lookup_result(&lookup); if (status && (status != -ENOTEMPTY) && (status != -ENOENT)) mlog_errno(status); return status; } static int ocfs2_check_if_ancestor(struct ocfs2_super *osb, u64 src_inode_no, u64 dest_inode_no) { int ret = 0, i = 0; u64 parent_inode_no = 0; u64 child_inode_no = src_inode_no; struct inode *child_inode; #define MAX_LOOKUP_TIMES 32 while (1) { child_inode = ocfs2_iget(osb, child_inode_no, 0, 0); if (IS_ERR(child_inode)) { ret = PTR_ERR(child_inode); break; } ret = ocfs2_inode_lock(child_inode, NULL, 0); if (ret < 0) { iput(child_inode); if (ret != -ENOENT) mlog_errno(ret); break; } ret = ocfs2_lookup_ino_from_name(child_inode, "..", 2, &parent_inode_no); ocfs2_inode_unlock(child_inode, 0); iput(child_inode); if (ret < 0) { ret = -ENOENT; break; } if (parent_inode_no == dest_inode_no) { ret = 1; break; } if (parent_inode_no == osb->root_inode->i_ino) { ret = 0; break; } child_inode_no = parent_inode_no; if (++i >= MAX_LOOKUP_TIMES) { mlog_ratelimited(ML_NOTICE, "max lookup times reached, " "filesystem may have nested directories, " "src inode: %llu, dest inode: %llu.\n", (unsigned long long)src_inode_no, (unsigned long long)dest_inode_no); ret = 0; break; } } return ret; } /* * The only place this should be used is rename and link! * if they have the same id, then the 1st one is the only one locked. */ static int ocfs2_double_lock(struct ocfs2_super *osb, struct buffer_head **bh1, struct inode *inode1, struct buffer_head **bh2, struct inode *inode2, int rename) { int status; int inode1_is_ancestor, inode2_is_ancestor; struct ocfs2_inode_info *oi1 = OCFS2_I(inode1); struct ocfs2_inode_info *oi2 = OCFS2_I(inode2); trace_ocfs2_double_lock((unsigned long long)oi1->ip_blkno, (unsigned long long)oi2->ip_blkno); if (*bh1) *bh1 = NULL; if (*bh2) *bh2 = NULL; /* we always want to lock the one with the lower lockid first. * and if they are nested, we lock ancestor first */ if (oi1->ip_blkno != oi2->ip_blkno) { inode1_is_ancestor = ocfs2_check_if_ancestor(osb, oi2->ip_blkno, oi1->ip_blkno); if (inode1_is_ancestor < 0) { status = inode1_is_ancestor; goto bail; } inode2_is_ancestor = ocfs2_check_if_ancestor(osb, oi1->ip_blkno, oi2->ip_blkno); if (inode2_is_ancestor < 0) { status = inode2_is_ancestor; goto bail; } if ((inode1_is_ancestor == 1) || (oi1->ip_blkno < oi2->ip_blkno && inode2_is_ancestor == 0)) { /* switch id1 and id2 around */ swap(bh2, bh1); swap(inode2, inode1); } /* lock id2 */ status = ocfs2_inode_lock_nested(inode2, bh2, 1, rename == 1 ? OI_LS_RENAME1 : OI_LS_PARENT); if (status < 0) { if (status != -ENOENT) mlog_errno(status); goto bail; } } /* lock id1 */ status = ocfs2_inode_lock_nested(inode1, bh1, 1, rename == 1 ? OI_LS_RENAME2 : OI_LS_PARENT); if (status < 0) { /* * An error return must mean that no cluster locks * were held on function exit. */ if (oi1->ip_blkno != oi2->ip_blkno) { ocfs2_inode_unlock(inode2, 1); brelse(*bh2); *bh2 = NULL; } if (status != -ENOENT) mlog_errno(status); } trace_ocfs2_double_lock_end( (unsigned long long)oi1->ip_blkno, (unsigned long long)oi2->ip_blkno); bail: if (status) mlog_errno(status); return status; } static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2) { ocfs2_inode_unlock(inode1, 1); if (inode1 != inode2) ocfs2_inode_unlock(inode2, 1); } static int ocfs2_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { int status = 0, rename_lock = 0, parents_locked = 0, target_exists = 0; int old_child_locked = 0, new_child_locked = 0, update_dot_dot = 0; struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); struct inode *orphan_dir = NULL; struct ocfs2_dinode *newfe = NULL; char orphan_name[OCFS2_ORPHAN_NAMELEN + 1]; struct buffer_head *newfe_bh = NULL; struct buffer_head *old_inode_bh = NULL; struct ocfs2_super *osb = NULL; u64 newfe_blkno, old_de_ino; handle_t *handle = NULL; struct buffer_head *old_dir_bh = NULL; struct buffer_head *new_dir_bh = NULL; u32 old_dir_nlink = old_dir->i_nlink; struct ocfs2_dinode *old_di; struct ocfs2_dir_lookup_result old_inode_dot_dot_res = { NULL, }; struct ocfs2_dir_lookup_result target_lookup_res = { NULL, }; struct ocfs2_dir_lookup_result old_entry_lookup = { NULL, }; struct ocfs2_dir_lookup_result orphan_insert = { NULL, }; struct ocfs2_dir_lookup_result target_insert = { NULL, }; bool should_add_orphan = false; if (flags) return -EINVAL; /* At some point it might be nice to break this function up a * bit. */ trace_ocfs2_rename(old_dir, old_dentry, new_dir, new_dentry, old_dentry->d_name.len, old_dentry->d_name.name, new_dentry->d_name.len, new_dentry->d_name.name); status = dquot_initialize(old_dir); if (status) { mlog_errno(status); goto bail; } status = dquot_initialize(new_dir); if (status) { mlog_errno(status); goto bail; } osb = OCFS2_SB(old_dir->i_sb); if (new_inode) { if (!igrab(new_inode)) BUG(); } /* Assume a directory hierarchy thusly: * a/b/c * a/d * a,b,c, and d are all directories. * * from cwd of 'a' on both nodes: * node1: mv b/c d * node2: mv d b/c * * And that's why, just like the VFS, we need a file system * rename lock. */ if (old_dir != new_dir && S_ISDIR(old_inode->i_mode)) { status = ocfs2_rename_lock(osb); if (status < 0) { mlog_errno(status); goto bail; } rename_lock = 1; /* here we cannot guarantee the inodes haven't just been * changed, so check if they are nested again */ status = ocfs2_check_if_ancestor(osb, new_dir->i_ino, old_inode->i_ino); if (status < 0) { mlog_errno(status); goto bail; } else if (status == 1) { status = -EPERM; trace_ocfs2_rename_not_permitted( (unsigned long long)old_inode->i_ino, (unsigned long long)new_dir->i_ino); goto bail; } } /* if old and new are the same, this'll just do one lock. */ status = ocfs2_double_lock(osb, &old_dir_bh, old_dir, &new_dir_bh, new_dir, 1); if (status < 0) { mlog_errno(status); goto bail; } parents_locked = 1; if (!new_dir->i_nlink) { status = -EACCES; goto bail; } /* make sure both dirs have bhs * get an extra ref on old_dir_bh if old==new */ if (!new_dir_bh) { if (old_dir_bh) { new_dir_bh = old_dir_bh; get_bh(new_dir_bh); } else { mlog(ML_ERROR, "no old_dir_bh!\n"); status = -EIO; goto bail; } } /* * Aside from allowing a meta data update, the locking here * also ensures that the downconvert thread on other nodes * won't have to concurrently downconvert the inode and the * dentry locks. */ status = ocfs2_inode_lock_nested(old_inode, &old_inode_bh, 1, OI_LS_PARENT); if (status < 0) { if (status != -ENOENT) mlog_errno(status); goto bail; } old_child_locked = 1; status = ocfs2_remote_dentry_delete(old_dentry); if (status < 0) { mlog_errno(status); goto bail; } if (S_ISDIR(old_inode->i_mode) && new_dir != old_dir) { u64 old_inode_parent; update_dot_dot = 1; status = ocfs2_find_files_on_disk("..", 2, &old_inode_parent, old_inode, &old_inode_dot_dot_res); if (status) { status = -EIO; goto bail; } if (old_inode_parent != OCFS2_I(old_dir)->ip_blkno) { status = -EIO; goto bail; } if (!new_inode && new_dir->i_nlink >= ocfs2_link_max(osb)) { status = -EMLINK; goto bail; } } status = ocfs2_lookup_ino_from_name(old_dir, old_dentry->d_name.name, old_dentry->d_name.len, &old_de_ino); if (status) { status = -ENOENT; goto bail; } /* * Check for inode number is _not_ due to possible IO errors. * We might rmdir the source, keep it as pwd of some process * and merrily kill the link to whatever was created under the * same name. Goodbye sticky bit ;-< */ if (old_de_ino != OCFS2_I(old_inode)->ip_blkno) { status = -ENOENT; goto bail; } /* check if the target already exists (in which case we need * to delete it */ status = ocfs2_find_files_on_disk(new_dentry->d_name.name, new_dentry->d_name.len, &newfe_blkno, new_dir, &target_lookup_res); /* The only error we allow here is -ENOENT because the new * file not existing is perfectly valid. */ if ((status < 0) && (status != -ENOENT)) { /* If we cannot find the file specified we should just */ /* return the error... */ mlog_errno(status); goto bail; } if (status == 0) target_exists = 1; if (!target_exists && new_inode) { /* * Target was unlinked by another node while we were * waiting to get to ocfs2_rename(). There isn't * anything we can do here to help the situation, so * bubble up the appropriate error. */ status = -ENOENT; goto bail; } /* In case we need to overwrite an existing file, we blow it * away first */ if (target_exists) { /* VFS didn't think there existed an inode here, but * someone else in the cluster must have raced our * rename to create one. Today we error cleanly, in * the future we should consider calling iget to build * a new struct inode for this entry. */ if (!new_inode) { status = -EACCES; trace_ocfs2_rename_target_exists(new_dentry->d_name.len, new_dentry->d_name.name); goto bail; } if (OCFS2_I(new_inode)->ip_blkno != newfe_blkno) { status = -EACCES; trace_ocfs2_rename_disagree( (unsigned long long)OCFS2_I(new_inode)->ip_blkno, (unsigned long long)newfe_blkno, OCFS2_I(new_inode)->ip_flags); goto bail; } status = ocfs2_inode_lock(new_inode, &newfe_bh, 1); if (status < 0) { if (status != -ENOENT) mlog_errno(status); goto bail; } new_child_locked = 1; status = ocfs2_remote_dentry_delete(new_dentry); if (status < 0) { mlog_errno(status); goto bail; } newfe = (struct ocfs2_dinode *) newfe_bh->b_data; trace_ocfs2_rename_over_existing( (unsigned long long)newfe_blkno, newfe_bh, newfe_bh ? (unsigned long long)newfe_bh->b_blocknr : 0ULL); if (S_ISDIR(new_inode->i_mode) || (new_inode->i_nlink == 1)) { status = ocfs2_prepare_orphan_dir(osb, &orphan_dir, OCFS2_I(new_inode)->ip_blkno, orphan_name, &orphan_insert, false); if (status < 0) { mlog_errno(status); goto bail; } should_add_orphan = true; } } else { BUG_ON(d_inode(new_dentry->d_parent) != new_dir); status = ocfs2_check_dir_for_entry(new_dir, new_dentry->d_name.name, new_dentry->d_name.len); if (status) goto bail; status = ocfs2_prepare_dir_for_insert(osb, new_dir, new_dir_bh, new_dentry->d_name.name, new_dentry->d_name.len, &target_insert); if (status < 0) { mlog_errno(status); goto bail; } } handle = ocfs2_start_trans(osb, ocfs2_rename_credits(osb->sb)); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; mlog_errno(status); goto bail; } if (target_exists) { if (S_ISDIR(new_inode->i_mode)) { if (new_inode->i_nlink != 2 || !ocfs2_empty_dir(new_inode)) { status = -ENOTEMPTY; goto bail; } } status = ocfs2_journal_access_di(handle, INODE_CACHE(new_inode), newfe_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; } /* change the dirent to point to the correct inode */ status = ocfs2_update_entry(new_dir, handle, &target_lookup_res, old_inode); if (status < 0) { mlog_errno(status); goto bail; } inode_inc_iversion(new_dir); if (S_ISDIR(new_inode->i_mode)) ocfs2_set_links_count(newfe, 0); else ocfs2_add_links_count(newfe, -1); ocfs2_journal_dirty(handle, newfe_bh); if (should_add_orphan) { status = ocfs2_orphan_add(osb, handle, new_inode, newfe_bh, orphan_name, &orphan_insert, orphan_dir, false); if (status < 0) { mlog_errno(status); goto bail; } } } else { /* if the name was not found in new_dir, add it now */ status = ocfs2_add_entry(handle, new_dentry, old_inode, OCFS2_I(old_inode)->ip_blkno, new_dir_bh, &target_insert); if (status < 0) { mlog_errno(status); goto bail; } } inode_set_ctime_current(old_inode); mark_inode_dirty(old_inode); status = ocfs2_journal_access_di(handle, INODE_CACHE(old_inode), old_inode_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status >= 0) { old_di = (struct ocfs2_dinode *) old_inode_bh->b_data; old_di->i_ctime = cpu_to_le64(inode_get_ctime_sec(old_inode)); old_di->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(old_inode)); ocfs2_journal_dirty(handle, old_inode_bh); } else mlog_errno(status); /* * Now that the name has been added to new_dir, remove the old name. * * We don't keep any directory entry context around until now * because the insert might have changed the type of directory * we're dealing with. */ status = ocfs2_find_entry(old_dentry->d_name.name, old_dentry->d_name.len, old_dir, &old_entry_lookup); if (status) { if (!is_journal_aborted(osb->journal->j_journal)) { ocfs2_error(osb->sb, "new entry %.*s is added, but old entry %.*s " "is not deleted.", new_dentry->d_name.len, new_dentry->d_name.name, old_dentry->d_name.len, old_dentry->d_name.name); } goto bail; } status = ocfs2_delete_entry(handle, old_dir, &old_entry_lookup); if (status < 0) { mlog_errno(status); if (!is_journal_aborted(osb->journal->j_journal)) { ocfs2_error(osb->sb, "new entry %.*s is added, but old entry %.*s " "is not deleted.", new_dentry->d_name.len, new_dentry->d_name.name, old_dentry->d_name.len, old_dentry->d_name.name); } goto bail; } if (new_inode) { drop_nlink(new_inode); inode_set_ctime_current(new_inode); } inode_set_mtime_to_ts(old_dir, inode_set_ctime_current(old_dir)); if (update_dot_dot) { status = ocfs2_update_entry(old_inode, handle, &old_inode_dot_dot_res, new_dir); if (status < 0) { mlog_errno(status); goto bail; } } if (S_ISDIR(old_inode->i_mode)) { drop_nlink(old_dir); if (new_inode) { drop_nlink(new_inode); } else { inc_nlink(new_dir); mark_inode_dirty(new_dir); } } mark_inode_dirty(old_dir); ocfs2_mark_inode_dirty(handle, old_dir, old_dir_bh); if (new_inode) { mark_inode_dirty(new_inode); ocfs2_mark_inode_dirty(handle, new_inode, newfe_bh); } if (old_dir != new_dir) { /* Keep the same times on both directories.*/ inode_set_mtime_to_ts(new_dir, inode_set_ctime_to_ts(new_dir, inode_get_ctime(old_dir))); /* * This will also pick up the i_nlink change from the * block above. */ ocfs2_mark_inode_dirty(handle, new_dir, new_dir_bh); } if (old_dir_nlink != old_dir->i_nlink) { if (!old_dir_bh) { mlog(ML_ERROR, "need to change nlink for old dir " "%llu from %d to %d but bh is NULL!\n", (unsigned long long)OCFS2_I(old_dir)->ip_blkno, (int)old_dir_nlink, old_dir->i_nlink); } else { struct ocfs2_dinode *fe; status = ocfs2_journal_access_di(handle, INODE_CACHE(old_dir), old_dir_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail; } fe = (struct ocfs2_dinode *) old_dir_bh->b_data; ocfs2_set_links_count(fe, old_dir->i_nlink); ocfs2_journal_dirty(handle, old_dir_bh); } } ocfs2_dentry_move(old_dentry, new_dentry, old_dir, new_dir); status = 0; bail: if (handle) ocfs2_commit_trans(osb, handle); if (orphan_dir) { /* This was locked for us in ocfs2_prepare_orphan_dir() */ ocfs2_inode_unlock(orphan_dir, 1); inode_unlock(orphan_dir); iput(orphan_dir); } if (new_child_locked) ocfs2_inode_unlock(new_inode, 1); if (old_child_locked) ocfs2_inode_unlock(old_inode, 1); if (parents_locked) ocfs2_double_unlock(old_dir, new_dir); if (rename_lock) ocfs2_rename_unlock(osb); if (new_inode) sync_mapping_buffers(old_inode->i_mapping); iput(new_inode); ocfs2_free_dir_lookup_result(&target_lookup_res); ocfs2_free_dir_lookup_result(&old_entry_lookup); ocfs2_free_dir_lookup_result(&old_inode_dot_dot_res); ocfs2_free_dir_lookup_result(&orphan_insert); ocfs2_free_dir_lookup_result(&target_insert); brelse(newfe_bh); brelse(old_inode_bh); brelse(old_dir_bh); brelse(new_dir_bh); if (status) mlog_errno(status); return status; } /* * we expect i_size = strlen(symname). Copy symname into the file * data, including the null terminator. */ static int ocfs2_create_symlink_data(struct ocfs2_super *osb, handle_t *handle, struct inode *inode, const char *symname) { struct buffer_head **bhs = NULL; const char *c; struct super_block *sb = osb->sb; u64 p_blkno, p_blocks; int virtual, blocks, status, i, bytes_left; bytes_left = i_size_read(inode) + 1; /* we can't trust i_blocks because we're actually going to * write i_size + 1 bytes. */ blocks = (bytes_left + sb->s_blocksize - 1) >> sb->s_blocksize_bits; trace_ocfs2_create_symlink_data((unsigned long long)inode->i_blocks, i_size_read(inode), blocks); /* Sanity check -- make sure we're going to fit. */ if (bytes_left > ocfs2_clusters_to_bytes(sb, OCFS2_I(inode)->ip_clusters)) { status = -EIO; mlog_errno(status); goto bail; } bhs = kcalloc(blocks, sizeof(struct buffer_head *), GFP_KERNEL); if (!bhs) { status = -ENOMEM; mlog_errno(status); goto bail; } status = ocfs2_extent_map_get_blocks(inode, 0, &p_blkno, &p_blocks, NULL); if (status < 0) { mlog_errno(status); goto bail; } /* links can never be larger than one cluster so we know this * is all going to be contiguous, but do a sanity check * anyway. */ if ((p_blocks << sb->s_blocksize_bits) < bytes_left) { status = -EIO; mlog_errno(status); goto bail; } virtual = 0; while(bytes_left > 0) { c = &symname[virtual * sb->s_blocksize]; bhs[virtual] = sb_getblk(sb, p_blkno); if (!bhs[virtual]) { status = -ENOMEM; mlog_errno(status); goto bail; } ocfs2_set_new_buffer_uptodate(INODE_CACHE(inode), bhs[virtual]); status = ocfs2_journal_access(handle, INODE_CACHE(inode), bhs[virtual], OCFS2_JOURNAL_ACCESS_CREATE); if (status < 0) { mlog_errno(status); goto bail; } memset(bhs[virtual]->b_data, 0, sb->s_blocksize); memcpy(bhs[virtual]->b_data, c, (bytes_left > sb->s_blocksize) ? sb->s_blocksize : bytes_left); ocfs2_journal_dirty(handle, bhs[virtual]); virtual++; p_blkno++; bytes_left -= sb->s_blocksize; } status = 0; bail: if (bhs) { for(i = 0; i < blocks; i++) brelse(bhs[i]); kfree(bhs); } if (status) mlog_errno(status); return status; } static int ocfs2_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { int status, l, credits; u64 newsize; struct ocfs2_super *osb = NULL; struct inode *inode = NULL; struct super_block *sb; struct buffer_head *new_fe_bh = NULL; struct buffer_head *parent_fe_bh = NULL; struct ocfs2_dinode *fe = NULL; struct ocfs2_dinode *dirfe; handle_t *handle = NULL; struct ocfs2_alloc_context *inode_ac = NULL; struct ocfs2_alloc_context *data_ac = NULL; struct ocfs2_alloc_context *xattr_ac = NULL; int want_clusters = 0; int xattr_credits = 0; struct ocfs2_security_xattr_info si = { .name = NULL, .enable = 1, }; int did_quota = 0, did_quota_inode = 0; struct ocfs2_dir_lookup_result lookup = { NULL, }; sigset_t oldset; int did_block_signals = 0; struct ocfs2_dentry_lock *dl = NULL; trace_ocfs2_symlink_begin(dir, dentry, symname, dentry->d_name.len, dentry->d_name.name); status = dquot_initialize(dir); if (status) { mlog_errno(status); goto bail; } sb = dir->i_sb; osb = OCFS2_SB(sb); l = strlen(symname) + 1; credits = ocfs2_calc_symlink_credits(sb); /* lock the parent directory */ status = ocfs2_inode_lock(dir, &parent_fe_bh, 1); if (status < 0) { if (status != -ENOENT) mlog_errno(status); return status; } dirfe = (struct ocfs2_dinode *) parent_fe_bh->b_data; if (!ocfs2_read_links_count(dirfe)) { /* can't make a file in a deleted directory. */ status = -ENOENT; goto bail; } status = ocfs2_check_dir_for_entry(dir, dentry->d_name.name, dentry->d_name.len); if (status) goto bail; status = ocfs2_prepare_dir_for_insert(osb, dir, parent_fe_bh, dentry->d_name.name, dentry->d_name.len, &lookup); if (status < 0) { mlog_errno(status); goto bail; } status = ocfs2_reserve_new_inode(osb, &inode_ac); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto bail; } inode = ocfs2_get_init_inode(dir, S_IFLNK | S_IRWXUGO); if (IS_ERR(inode)) { status = PTR_ERR(inode); inode = NULL; mlog_errno(status); goto bail; } /* get security xattr */ status = ocfs2_init_security_get(inode, dir, &dentry->d_name, &si); if (status) { if (status == -EOPNOTSUPP) si.enable = 0; else { mlog_errno(status); goto bail; } } /* calculate meta data/clusters for setting security xattr */ if (si.enable) { status = ocfs2_calc_security_init(dir, &si, &want_clusters, &xattr_credits, &xattr_ac); if (status < 0) { mlog_errno(status); goto bail; } } /* don't reserve bitmap space for fast symlinks. */ if (l > ocfs2_fast_symlink_chars(sb)) want_clusters += 1; status = ocfs2_reserve_clusters(osb, want_clusters, &data_ac); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto bail; } handle = ocfs2_start_trans(osb, credits + xattr_credits); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; mlog_errno(status); goto bail; } /* Starting to change things, restart is no longer possible. */ ocfs2_block_signals(&oldset); did_block_signals = 1; status = dquot_alloc_inode(inode); if (status) goto bail; did_quota_inode = 1; trace_ocfs2_symlink_create(dir, dentry, dentry->d_name.len, dentry->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno, inode->i_mode); status = ocfs2_mknod_locked(osb, dir, inode, 0, &new_fe_bh, parent_fe_bh, handle, inode_ac); if (status < 0) { mlog_errno(status); goto bail; } fe = (struct ocfs2_dinode *) new_fe_bh->b_data; inode->i_rdev = 0; newsize = l - 1; inode->i_op = &ocfs2_symlink_inode_operations; inode_nohighmem(inode); if (l > ocfs2_fast_symlink_chars(sb)) { u32 offset = 0; status = dquot_alloc_space_nodirty(inode, ocfs2_clusters_to_bytes(osb->sb, 1)); if (status) goto bail; did_quota = 1; inode->i_mapping->a_ops = &ocfs2_aops; status = ocfs2_add_inode_data(osb, inode, &offset, 1, 0, new_fe_bh, handle, data_ac, NULL, NULL); if (status < 0) { if (status != -ENOSPC && status != -EINTR) { mlog(ML_ERROR, "Failed to extend file to %llu\n", (unsigned long long)newsize); mlog_errno(status); status = -ENOSPC; } goto bail; } i_size_write(inode, newsize); inode->i_blocks = ocfs2_inode_sector_count(inode); } else { inode->i_mapping->a_ops = &ocfs2_fast_symlink_aops; memcpy((char *) fe->id2.i_symlink, symname, l); i_size_write(inode, newsize); inode->i_blocks = 0; } status = ocfs2_mark_inode_dirty(handle, inode, new_fe_bh); if (status < 0) { mlog_errno(status); goto bail; } if (!ocfs2_inode_is_fast_symlink(inode)) { status = ocfs2_create_symlink_data(osb, handle, inode, symname); if (status < 0) { mlog_errno(status); goto bail; } } if (si.enable) { status = ocfs2_init_security_set(handle, inode, new_fe_bh, &si, xattr_ac, data_ac); if (status < 0) { mlog_errno(status); goto bail; } } /* * Do this before adding the entry to the directory. We add * also set d_op after success so that ->d_iput() will cleanup * the dentry lock even if ocfs2_add_entry() fails below. */ status = ocfs2_dentry_attach_lock(dentry, inode, OCFS2_I(dir)->ip_blkno); if (status) { mlog_errno(status); goto bail; } dl = dentry->d_fsdata; status = ocfs2_add_entry(handle, dentry, inode, le64_to_cpu(fe->i_blkno), parent_fe_bh, &lookup); if (status < 0) { mlog_errno(status); goto bail; } insert_inode_hash(inode); d_instantiate(dentry, inode); bail: if (status < 0 && did_quota) dquot_free_space_nodirty(inode, ocfs2_clusters_to_bytes(osb->sb, 1)); if (status < 0 && did_quota_inode) dquot_free_inode(inode); if (handle) { if (status < 0 && fe) ocfs2_set_links_count(fe, 0); ocfs2_commit_trans(osb, handle); } ocfs2_inode_unlock(dir, 1); if (did_block_signals) ocfs2_unblock_signals(&oldset); brelse(new_fe_bh); brelse(parent_fe_bh); kfree(si.value); ocfs2_free_dir_lookup_result(&lookup); if (inode_ac) ocfs2_free_alloc_context(inode_ac); if (data_ac) ocfs2_free_alloc_context(data_ac); if (xattr_ac) ocfs2_free_alloc_context(xattr_ac); if ((status < 0) && inode) { if (dl) ocfs2_cleanup_add_entry_failure(osb, dentry, inode); OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR; clear_nlink(inode); iput(inode); } if (status) mlog_errno(status); return status; } static int ocfs2_blkno_stringify(u64 blkno, char *name) { int status, namelen; namelen = snprintf(name, OCFS2_ORPHAN_NAMELEN + 1, "%016llx", (long long)blkno); if (namelen <= 0) { if (namelen) status = namelen; else status = -EINVAL; mlog_errno(status); goto bail; } if (namelen != OCFS2_ORPHAN_NAMELEN) { status = -EINVAL; mlog_errno(status); goto bail; } trace_ocfs2_blkno_stringify(blkno, name, namelen); status = 0; bail: if (status < 0) mlog_errno(status); return status; } static int ocfs2_lookup_lock_orphan_dir(struct ocfs2_super *osb, struct inode **ret_orphan_dir, struct buffer_head **ret_orphan_dir_bh) { struct inode *orphan_dir_inode; struct buffer_head *orphan_dir_bh = NULL; int ret = 0; orphan_dir_inode = ocfs2_get_system_file_inode(osb, ORPHAN_DIR_SYSTEM_INODE, osb->slot_num); if (!orphan_dir_inode) { ret = -ENOENT; mlog_errno(ret); return ret; } inode_lock(orphan_dir_inode); ret = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1); if (ret < 0) { inode_unlock(orphan_dir_inode); iput(orphan_dir_inode); mlog_errno(ret); return ret; } *ret_orphan_dir = orphan_dir_inode; *ret_orphan_dir_bh = orphan_dir_bh; return 0; } static int __ocfs2_prepare_orphan_dir(struct inode *orphan_dir_inode, struct buffer_head *orphan_dir_bh, u64 blkno, char *name, struct ocfs2_dir_lookup_result *lookup, bool dio) { int ret; struct ocfs2_super *osb = OCFS2_SB(orphan_dir_inode->i_sb); int namelen = dio ? (OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN) : OCFS2_ORPHAN_NAMELEN; if (dio) { ret = snprintf(name, OCFS2_DIO_ORPHAN_PREFIX_LEN + 1, "%s", OCFS2_DIO_ORPHAN_PREFIX); if (ret != OCFS2_DIO_ORPHAN_PREFIX_LEN) { ret = -EINVAL; mlog_errno(ret); return ret; } ret = ocfs2_blkno_stringify(blkno, name + OCFS2_DIO_ORPHAN_PREFIX_LEN); } else ret = ocfs2_blkno_stringify(blkno, name); if (ret < 0) { mlog_errno(ret); return ret; } ret = ocfs2_prepare_dir_for_insert(osb, orphan_dir_inode, orphan_dir_bh, name, namelen, lookup); if (ret < 0) { mlog_errno(ret); return ret; } return 0; } /** * ocfs2_prepare_orphan_dir() - Prepare an orphan directory for * insertion of an orphan. * @osb: ocfs2 file system * @ret_orphan_dir: Orphan dir inode - returned locked! * @blkno: Actual block number of the inode to be inserted into orphan dir. * @name: Buffer to store the name of the orphan. * @lookup: dir lookup result, to be passed back into functions like * ocfs2_orphan_add * @dio: Flag indicating if direct IO is being used or not. * * Returns zero on success and the ret_orphan_dir, name and lookup * fields will be populated. * * Returns non-zero on failure. */ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb, struct inode **ret_orphan_dir, u64 blkno, char *name, struct ocfs2_dir_lookup_result *lookup, bool dio) { struct inode *orphan_dir_inode = NULL; struct buffer_head *orphan_dir_bh = NULL; int ret = 0; ret = ocfs2_lookup_lock_orphan_dir(osb, &orphan_dir_inode, &orphan_dir_bh); if (ret < 0) { mlog_errno(ret); return ret; } ret = __ocfs2_prepare_orphan_dir(orphan_dir_inode, orphan_dir_bh, blkno, name, lookup, dio); if (ret < 0) { mlog_errno(ret); goto out; } *ret_orphan_dir = orphan_dir_inode; out: brelse(orphan_dir_bh); if (ret) { ocfs2_inode_unlock(orphan_dir_inode, 1); inode_unlock(orphan_dir_inode); iput(orphan_dir_inode); } if (ret) mlog_errno(ret); return ret; } static int ocfs2_orphan_add(struct ocfs2_super *osb, handle_t *handle, struct inode *inode, struct buffer_head *fe_bh, char *name, struct ocfs2_dir_lookup_result *lookup, struct inode *orphan_dir_inode, bool dio) { struct buffer_head *orphan_dir_bh = NULL; int status = 0; struct ocfs2_dinode *orphan_fe; struct ocfs2_dinode *fe = (struct ocfs2_dinode *) fe_bh->b_data; int namelen = dio ? (OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN) : OCFS2_ORPHAN_NAMELEN; trace_ocfs2_orphan_add_begin( (unsigned long long)OCFS2_I(inode)->ip_blkno); status = ocfs2_read_inode_block(orphan_dir_inode, &orphan_dir_bh); if (status < 0) { mlog_errno(status); goto leave; } status = ocfs2_journal_access_di(handle, INODE_CACHE(orphan_dir_inode), orphan_dir_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto leave; } /* * We're going to journal the change of i_flags and i_orphaned_slot. * It's safe anyway, though some callers may duplicate the journaling. * Journaling within the func just make the logic look more * straightforward. */ status = ocfs2_journal_access_di(handle, INODE_CACHE(inode), fe_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto leave; } /* we're a cluster, and nlink can change on disk from * underneath us... */ orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data; if (S_ISDIR(inode->i_mode)) ocfs2_add_links_count(orphan_fe, 1); set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe)); ocfs2_journal_dirty(handle, orphan_dir_bh); status = __ocfs2_add_entry(handle, orphan_dir_inode, name, namelen, inode, OCFS2_I(inode)->ip_blkno, orphan_dir_bh, lookup); if (status < 0) { mlog_errno(status); goto rollback; } if (dio) { /* Update flag OCFS2_DIO_ORPHANED_FL and record the orphan * slot. */ fe->i_flags |= cpu_to_le32(OCFS2_DIO_ORPHANED_FL); fe->i_dio_orphaned_slot = cpu_to_le16(osb->slot_num); } else { fe->i_flags |= cpu_to_le32(OCFS2_ORPHANED_FL); OCFS2_I(inode)->ip_flags &= ~OCFS2_INODE_SKIP_ORPHAN_DIR; /* Record which orphan dir our inode now resides * in. delete_inode will use this to determine which orphan * dir to lock. */ fe->i_orphaned_slot = cpu_to_le16(osb->slot_num); } ocfs2_journal_dirty(handle, fe_bh); trace_ocfs2_orphan_add_end((unsigned long long)OCFS2_I(inode)->ip_blkno, osb->slot_num); rollback: if (status < 0) { if (S_ISDIR(inode->i_mode)) ocfs2_add_links_count(orphan_fe, -1); set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe)); } leave: brelse(orphan_dir_bh); return status; } /* unlike orphan_add, we expect the orphan dir to already be locked here. */ int ocfs2_orphan_del(struct ocfs2_super *osb, handle_t *handle, struct inode *orphan_dir_inode, struct inode *inode, struct buffer_head *orphan_dir_bh, bool dio) { char name[OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN + 1]; struct ocfs2_dinode *orphan_fe; int status = 0; struct ocfs2_dir_lookup_result lookup = { NULL, }; if (dio) { status = snprintf(name, OCFS2_DIO_ORPHAN_PREFIX_LEN + 1, "%s", OCFS2_DIO_ORPHAN_PREFIX); if (status != OCFS2_DIO_ORPHAN_PREFIX_LEN) { status = -EINVAL; mlog_errno(status); return status; } status = ocfs2_blkno_stringify(OCFS2_I(inode)->ip_blkno, name + OCFS2_DIO_ORPHAN_PREFIX_LEN); } else status = ocfs2_blkno_stringify(OCFS2_I(inode)->ip_blkno, name); if (status < 0) { mlog_errno(status); goto leave; } trace_ocfs2_orphan_del( (unsigned long long)OCFS2_I(orphan_dir_inode)->ip_blkno, name, strlen(name)); status = ocfs2_journal_access_di(handle, INODE_CACHE(orphan_dir_inode), orphan_dir_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto leave; } /* find it's spot in the orphan directory */ status = ocfs2_find_entry(name, strlen(name), orphan_dir_inode, &lookup); if (status) { mlog_errno(status); goto leave; } /* remove it from the orphan directory */ status = ocfs2_delete_entry(handle, orphan_dir_inode, &lookup); if (status < 0) { mlog_errno(status); goto leave; } /* do the i_nlink dance! :) */ orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data; if (S_ISDIR(inode->i_mode)) ocfs2_add_links_count(orphan_fe, -1); set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe)); ocfs2_journal_dirty(handle, orphan_dir_bh); leave: ocfs2_free_dir_lookup_result(&lookup); if (status) mlog_errno(status); return status; } /** * ocfs2_prep_new_orphaned_file() - Prepare the orphan dir to receive a newly * allocated file. This is different from the typical 'add to orphan dir' * operation in that the inode does not yet exist. This is a problem because * the orphan dir stringifies the inode block number to come up with it's * dirent. Obviously if the inode does not yet exist we have a chicken and egg * problem. This function works around it by calling deeper into the orphan * and suballoc code than other callers. Use this only by necessity. * @dir: The directory which this inode will ultimately wind up under - not the * orphan dir! * @dir_bh: buffer_head the @dir inode block * @orphan_name: string of length (CFS2_ORPHAN_NAMELEN + 1). Will be filled * with the string to be used for orphan dirent. Pass back to the orphan dir * code. * @ret_orphan_dir: orphan dir inode returned to be passed back into orphan * dir code. * @ret_di_blkno: block number where the new inode will be allocated. * @orphan_insert: Dir insert context to be passed back into orphan dir code. * @ret_inode_ac: Inode alloc context to be passed back to the allocator. * * Returns zero on success and the ret_orphan_dir, name and lookup * fields will be populated. * * Returns non-zero on failure. */ static int ocfs2_prep_new_orphaned_file(struct inode *dir, struct buffer_head *dir_bh, char *orphan_name, struct inode **ret_orphan_dir, u64 *ret_di_blkno, struct ocfs2_dir_lookup_result *orphan_insert, struct ocfs2_alloc_context **ret_inode_ac) { int ret; u64 di_blkno; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct inode *orphan_dir = NULL; struct buffer_head *orphan_dir_bh = NULL; struct ocfs2_alloc_context *inode_ac = NULL; ret = ocfs2_lookup_lock_orphan_dir(osb, &orphan_dir, &orphan_dir_bh); if (ret < 0) { mlog_errno(ret); return ret; } /* reserve an inode spot */ ret = ocfs2_reserve_new_inode(osb, &inode_ac); if (ret < 0) { if (ret != -ENOSPC) mlog_errno(ret); goto out; } ret = ocfs2_find_new_inode_loc(dir, dir_bh, inode_ac, &di_blkno); if (ret) { mlog_errno(ret); goto out; } ret = __ocfs2_prepare_orphan_dir(orphan_dir, orphan_dir_bh, di_blkno, orphan_name, orphan_insert, false); if (ret < 0) { mlog_errno(ret); goto out; } out: if (ret == 0) { *ret_orphan_dir = orphan_dir; *ret_di_blkno = di_blkno; *ret_inode_ac = inode_ac; /* * orphan_name and orphan_insert are already up to * date via prepare_orphan_dir */ } else { /* Unroll reserve_new_inode* */ if (inode_ac) ocfs2_free_alloc_context(inode_ac); /* Unroll orphan dir locking */ inode_unlock(orphan_dir); ocfs2_inode_unlock(orphan_dir, 1); iput(orphan_dir); } brelse(orphan_dir_bh); return ret; } int ocfs2_create_inode_in_orphan(struct inode *dir, int mode, struct inode **new_inode) { int status, did_quota_inode = 0; struct inode *inode = NULL; struct inode *orphan_dir = NULL; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); handle_t *handle = NULL; char orphan_name[OCFS2_ORPHAN_NAMELEN + 1]; struct buffer_head *parent_di_bh = NULL; struct buffer_head *new_di_bh = NULL; struct ocfs2_alloc_context *inode_ac = NULL; struct ocfs2_dir_lookup_result orphan_insert = { NULL, }; u64 di_blkno, suballoc_loc; u16 suballoc_bit; status = ocfs2_inode_lock(dir, &parent_di_bh, 1); if (status < 0) { if (status != -ENOENT) mlog_errno(status); return status; } status = ocfs2_prep_new_orphaned_file(dir, parent_di_bh, orphan_name, &orphan_dir, &di_blkno, &orphan_insert, &inode_ac); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto leave; } inode = ocfs2_get_init_inode(dir, mode); if (IS_ERR(inode)) { status = PTR_ERR(inode); inode = NULL; mlog_errno(status); goto leave; } handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb, 0, 0)); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; mlog_errno(status); goto leave; } status = dquot_alloc_inode(inode); if (status) goto leave; did_quota_inode = 1; status = ocfs2_claim_new_inode_at_loc(handle, dir, inode_ac, &suballoc_loc, &suballoc_bit, di_blkno); if (status < 0) { mlog_errno(status); goto leave; } clear_nlink(inode); /* do the real work now. */ status = __ocfs2_mknod_locked(dir, inode, 0, &new_di_bh, parent_di_bh, handle, inode_ac, di_blkno, suballoc_loc, suballoc_bit); if (status < 0) { mlog_errno(status); goto leave; } status = ocfs2_orphan_add(osb, handle, inode, new_di_bh, orphan_name, &orphan_insert, orphan_dir, false); if (status < 0) { mlog_errno(status); goto leave; } /* get open lock so that only nodes can't remove it from orphan dir. */ status = ocfs2_open_lock(inode); if (status < 0) mlog_errno(status); insert_inode_hash(inode); leave: if (status < 0 && did_quota_inode) dquot_free_inode(inode); if (handle) ocfs2_commit_trans(osb, handle); if (orphan_dir) { /* This was locked for us in ocfs2_prepare_orphan_dir() */ ocfs2_inode_unlock(orphan_dir, 1); inode_unlock(orphan_dir); iput(orphan_dir); } if ((status < 0) && inode) { clear_nlink(inode); iput(inode); } if (inode_ac) ocfs2_free_alloc_context(inode_ac); brelse(new_di_bh); if (!status) *new_inode = inode; ocfs2_free_dir_lookup_result(&orphan_insert); ocfs2_inode_unlock(dir, 1); brelse(parent_di_bh); return status; } int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb, struct inode *inode) { char orphan_name[OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN + 1]; struct inode *orphan_dir_inode = NULL; struct ocfs2_dir_lookup_result orphan_insert = { NULL, }; struct buffer_head *di_bh = NULL; int status = 0; handle_t *handle = NULL; struct ocfs2_dinode *di = NULL; status = ocfs2_inode_lock(inode, &di_bh, 1); if (status < 0) { mlog_errno(status); goto bail; } di = (struct ocfs2_dinode *) di_bh->b_data; /* * Another append dio crashed? * If so, manually recover it first. */ if (unlikely(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) { status = ocfs2_truncate_file(inode, di_bh, i_size_read(inode)); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto bail_unlock_inode; } status = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0); if (status < 0) { mlog_errno(status); goto bail_unlock_inode; } } status = ocfs2_prepare_orphan_dir(osb, &orphan_dir_inode, OCFS2_I(inode)->ip_blkno, orphan_name, &orphan_insert, true); if (status < 0) { mlog_errno(status); goto bail_unlock_inode; } handle = ocfs2_start_trans(osb, OCFS2_INODE_ADD_TO_ORPHAN_CREDITS); if (IS_ERR(handle)) { status = PTR_ERR(handle); goto bail_unlock_orphan; } status = ocfs2_orphan_add(osb, handle, inode, di_bh, orphan_name, &orphan_insert, orphan_dir_inode, true); if (status) mlog_errno(status); ocfs2_commit_trans(osb, handle); bail_unlock_orphan: ocfs2_inode_unlock(orphan_dir_inode, 1); inode_unlock(orphan_dir_inode); iput(orphan_dir_inode); ocfs2_free_dir_lookup_result(&orphan_insert); bail_unlock_inode: ocfs2_inode_unlock(inode, 1); brelse(di_bh); bail: return status; } int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb, struct inode *inode, struct buffer_head *di_bh, int update_isize, loff_t end) { struct inode *orphan_dir_inode = NULL; struct buffer_head *orphan_dir_bh = NULL; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; handle_t *handle = NULL; int status = 0; orphan_dir_inode = ocfs2_get_system_file_inode(osb, ORPHAN_DIR_SYSTEM_INODE, le16_to_cpu(di->i_dio_orphaned_slot)); if (!orphan_dir_inode) { status = -ENOENT; mlog_errno(status); goto bail; } inode_lock(orphan_dir_inode); status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1); if (status < 0) { inode_unlock(orphan_dir_inode); iput(orphan_dir_inode); mlog_errno(status); goto bail; } handle = ocfs2_start_trans(osb, OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS); if (IS_ERR(handle)) { status = PTR_ERR(handle); goto bail_unlock_orphan; } BUG_ON(!(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))); status = ocfs2_orphan_del(osb, handle, orphan_dir_inode, inode, orphan_dir_bh, true); if (status < 0) { mlog_errno(status); goto bail_commit; } status = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto bail_commit; } di->i_flags &= ~cpu_to_le32(OCFS2_DIO_ORPHANED_FL); di->i_dio_orphaned_slot = 0; if (update_isize) { status = ocfs2_set_inode_size(handle, inode, di_bh, end); if (status) mlog_errno(status); } else ocfs2_journal_dirty(handle, di_bh); bail_commit: ocfs2_commit_trans(osb, handle); bail_unlock_orphan: ocfs2_inode_unlock(orphan_dir_inode, 1); inode_unlock(orphan_dir_inode); brelse(orphan_dir_bh); iput(orphan_dir_inode); bail: return status; } int ocfs2_mv_orphaned_inode_to_new(struct inode *dir, struct inode *inode, struct dentry *dentry) { int status = 0; struct buffer_head *parent_di_bh = NULL; handle_t *handle = NULL; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct ocfs2_dinode *dir_di, *di; struct inode *orphan_dir_inode = NULL; struct buffer_head *orphan_dir_bh = NULL; struct buffer_head *di_bh = NULL; struct ocfs2_dir_lookup_result lookup = { NULL, }; trace_ocfs2_mv_orphaned_inode_to_new(dir, dentry, dentry->d_name.len, dentry->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno, (unsigned long long)OCFS2_I(inode)->ip_blkno); status = ocfs2_inode_lock(dir, &parent_di_bh, 1); if (status < 0) { if (status != -ENOENT) mlog_errno(status); return status; } dir_di = (struct ocfs2_dinode *) parent_di_bh->b_data; if (!dir_di->i_links_count) { /* can't make a file in a deleted directory. */ status = -ENOENT; goto leave; } status = ocfs2_check_dir_for_entry(dir, dentry->d_name.name, dentry->d_name.len); if (status) goto leave; /* get a spot inside the dir. */ status = ocfs2_prepare_dir_for_insert(osb, dir, parent_di_bh, dentry->d_name.name, dentry->d_name.len, &lookup); if (status < 0) { mlog_errno(status); goto leave; } orphan_dir_inode = ocfs2_get_system_file_inode(osb, ORPHAN_DIR_SYSTEM_INODE, osb->slot_num); if (!orphan_dir_inode) { status = -ENOENT; mlog_errno(status); goto leave; } inode_lock(orphan_dir_inode); status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1); if (status < 0) { mlog_errno(status); inode_unlock(orphan_dir_inode); iput(orphan_dir_inode); goto leave; } status = ocfs2_read_inode_block(inode, &di_bh); if (status < 0) { mlog_errno(status); goto orphan_unlock; } handle = ocfs2_start_trans(osb, ocfs2_rename_credits(osb->sb)); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; mlog_errno(status); goto orphan_unlock; } status = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto out_commit; } status = ocfs2_orphan_del(osb, handle, orphan_dir_inode, inode, orphan_dir_bh, false); if (status < 0) { mlog_errno(status); goto out_commit; } di = (struct ocfs2_dinode *)di_bh->b_data; di->i_flags &= ~cpu_to_le32(OCFS2_ORPHANED_FL); di->i_orphaned_slot = 0; set_nlink(inode, 1); ocfs2_set_links_count(di, inode->i_nlink); ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_journal_dirty(handle, di_bh); status = ocfs2_add_entry(handle, dentry, inode, OCFS2_I(inode)->ip_blkno, parent_di_bh, &lookup); if (status < 0) { mlog_errno(status); goto out_commit; } status = ocfs2_dentry_attach_lock(dentry, inode, OCFS2_I(dir)->ip_blkno); if (status) { mlog_errno(status); goto out_commit; } d_instantiate(dentry, inode); status = 0; out_commit: ocfs2_commit_trans(osb, handle); orphan_unlock: ocfs2_inode_unlock(orphan_dir_inode, 1); inode_unlock(orphan_dir_inode); iput(orphan_dir_inode); leave: ocfs2_inode_unlock(dir, 1); brelse(di_bh); brelse(parent_di_bh); brelse(orphan_dir_bh); ocfs2_free_dir_lookup_result(&lookup); if (status) mlog_errno(status); return status; } const struct inode_operations ocfs2_dir_iops = { .create = ocfs2_create, .lookup = ocfs2_lookup, .link = ocfs2_link, .unlink = ocfs2_unlink, .rmdir = ocfs2_unlink, .symlink = ocfs2_symlink, .mkdir = ocfs2_mkdir, .mknod = ocfs2_mknod, .rename = ocfs2_rename, .setattr = ocfs2_setattr, .getattr = ocfs2_getattr, .permission = ocfs2_permission, .listxattr = ocfs2_listxattr, .fiemap = ocfs2_fiemap, .get_inode_acl = ocfs2_iop_get_acl, .set_acl = ocfs2_iop_set_acl, .fileattr_get = ocfs2_fileattr_get, .fileattr_set = ocfs2_fileattr_set, }; |
| 139 99 84 99 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hfsplus/xattr_trusted.c * * Vyacheslav Dubeyko <slava@dubeyko.com> * * Handler for storing security labels as extended attributes. */ #include <linux/security.h> #include <linux/nls.h> #include "hfsplus_fs.h" #include "xattr.h" static int hfsplus_security_getxattr(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *buffer, size_t size) { return hfsplus_getxattr(inode, name, buffer, size, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); } static int hfsplus_security_setxattr(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *buffer, size_t size, int flags) { return hfsplus_setxattr(inode, name, buffer, size, flags, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); } static int hfsplus_initxattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) { const struct xattr *xattr; char *xattr_name; int err = 0; xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, GFP_KERNEL); if (!xattr_name) return -ENOMEM; for (xattr = xattr_array; xattr->name != NULL; xattr++) { if (!strcmp(xattr->name, "")) continue; strcpy(xattr_name, XATTR_SECURITY_PREFIX); strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, xattr->name); memset(xattr_name + XATTR_SECURITY_PREFIX_LEN + strlen(xattr->name), 0, 1); err = __hfsplus_setxattr(inode, xattr_name, xattr->value, xattr->value_len, 0); if (err) break; } kfree(xattr_name); return err; } int hfsplus_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr) { return security_inode_init_security(inode, dir, qstr, &hfsplus_initxattrs, NULL); } const struct xattr_handler hfsplus_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .get = hfsplus_security_getxattr, .set = hfsplus_security_setxattr, }; |
| 676 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2008-2012 Novell Inc. * Copyright (c) 2012-2019 Greg Kroah-Hartman <gregkh@linuxfoundation.org> * Copyright (c) 2012-2019 Linux Foundation * * Core driver model functions and structures that should not be * shared outside of the drivers/base/ directory. * */ #include <linux/notifier.h> /** * struct subsys_private - structure to hold the private to the driver core portions of the bus_type/class structure. * * @subsys - the struct kset that defines this subsystem * @devices_kset - the subsystem's 'devices' directory * @interfaces - list of subsystem interfaces associated * @mutex - protect the devices, and interfaces lists. * * @drivers_kset - the list of drivers associated * @klist_devices - the klist to iterate over the @devices_kset * @klist_drivers - the klist to iterate over the @drivers_kset * @bus_notifier - the bus notifier list for anything that cares about things * on this bus. * @bus - pointer back to the struct bus_type that this structure is associated * with. * @dev_root: Default device to use as the parent. * * @glue_dirs - "glue" directory to put in-between the parent device to * avoid namespace conflicts * @class - pointer back to the struct class that this structure is associated * with. * @lock_key: Lock class key for use by the lock validator * * This structure is the one that is the actual kobject allowing struct * bus_type/class to be statically allocated safely. Nothing outside of the * driver core should ever touch these fields. */ struct subsys_private { struct kset subsys; struct kset *devices_kset; struct list_head interfaces; struct mutex mutex; struct kset *drivers_kset; struct klist klist_devices; struct klist klist_drivers; struct blocking_notifier_head bus_notifier; unsigned int drivers_autoprobe:1; const struct bus_type *bus; struct device *dev_root; struct kset glue_dirs; const struct class *class; struct lock_class_key lock_key; }; #define to_subsys_private(obj) container_of_const(obj, struct subsys_private, subsys.kobj) static inline struct subsys_private *subsys_get(struct subsys_private *sp) { if (sp) kset_get(&sp->subsys); return sp; } static inline void subsys_put(struct subsys_private *sp) { if (sp) kset_put(&sp->subsys); } struct subsys_private *class_to_subsys(const struct class *class); struct driver_private { struct kobject kobj; struct klist klist_devices; struct klist_node knode_bus; struct module_kobject *mkobj; struct device_driver *driver; }; #define to_driver(obj) container_of(obj, struct driver_private, kobj) /** * struct device_private - structure to hold the private to the driver core portions of the device structure. * * @klist_children - klist containing all children of this device * @knode_parent - node in sibling list * @knode_driver - node in driver list * @knode_bus - node in bus list * @knode_class - node in class list * @deferred_probe - entry in deferred_probe_list which is used to retry the * binding of drivers which were unable to get all the resources needed by * the device; typically because it depends on another driver getting * probed first. * @async_driver - pointer to device driver awaiting probe via async_probe * @device - pointer back to the struct device that this structure is * associated with. * @dead - This device is currently either in the process of or has been * removed from the system. Any asynchronous events scheduled for this * device should exit without taking any action. * * Nothing outside of the driver core should ever touch these fields. */ struct device_private { struct klist klist_children; struct klist_node knode_parent; struct klist_node knode_driver; struct klist_node knode_bus; struct klist_node knode_class; struct list_head deferred_probe; const struct device_driver *async_driver; char *deferred_probe_reason; struct device *device; u8 dead:1; }; #define to_device_private_parent(obj) \ container_of(obj, struct device_private, knode_parent) #define to_device_private_driver(obj) \ container_of(obj, struct device_private, knode_driver) #define to_device_private_bus(obj) \ container_of(obj, struct device_private, knode_bus) #define to_device_private_class(obj) \ container_of(obj, struct device_private, knode_class) /* initialisation functions */ int devices_init(void); int buses_init(void); int classes_init(void); int firmware_init(void); #ifdef CONFIG_SYS_HYPERVISOR int hypervisor_init(void); #else static inline int hypervisor_init(void) { return 0; } #endif int platform_bus_init(void); void cpu_dev_init(void); void container_dev_init(void); #ifdef CONFIG_AUXILIARY_BUS void auxiliary_bus_init(void); #else static inline void auxiliary_bus_init(void) { } #endif struct kobject *virtual_device_parent(void); int bus_add_device(struct device *dev); void bus_probe_device(struct device *dev); void bus_remove_device(struct device *dev); void bus_notify(struct device *dev, enum bus_notifier_event value); bool bus_is_registered(const struct bus_type *bus); int bus_add_driver(struct device_driver *drv); void bus_remove_driver(struct device_driver *drv); void device_release_driver_internal(struct device *dev, const struct device_driver *drv, struct device *parent); void driver_detach(const struct device_driver *drv); void driver_deferred_probe_del(struct device *dev); void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf); static inline int driver_match_device(const struct device_driver *drv, struct device *dev) { return drv->bus->match ? drv->bus->match(dev, drv) : 1; } static inline void dev_sync_state(struct device *dev) { if (dev->bus->sync_state) dev->bus->sync_state(dev); else if (dev->driver && dev->driver->sync_state) dev->driver->sync_state(dev); } int driver_add_groups(const struct device_driver *drv, const struct attribute_group **groups); void driver_remove_groups(const struct device_driver *drv, const struct attribute_group **groups); void device_driver_detach(struct device *dev); int devres_release_all(struct device *dev); void device_block_probing(void); void device_unblock_probing(void); void deferred_probe_extend_timeout(void); void driver_deferred_probe_trigger(void); const char *device_get_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp); /* /sys/devices directory */ extern struct kset *devices_kset; void devices_kset_move_last(struct device *dev); #if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS) int module_add_driver(struct module *mod, const struct device_driver *drv); void module_remove_driver(const struct device_driver *drv); #else static inline int module_add_driver(struct module *mod, struct device_driver *drv) { return 0; } static inline void module_remove_driver(struct device_driver *drv) { } #endif #ifdef CONFIG_DEVTMPFS int devtmpfs_init(void); #else static inline int devtmpfs_init(void) { return 0; } #endif #ifdef CONFIG_BLOCK extern const struct class block_class; static inline bool is_blockdev(struct device *dev) { return dev->class == &block_class; } #else static inline bool is_blockdev(struct device *dev) { return false; } #endif /* Device links support */ int device_links_read_lock(void); void device_links_read_unlock(int idx); int device_links_read_lock_held(void); int device_links_check_suppliers(struct device *dev); void device_links_force_bind(struct device *dev); void device_links_driver_bound(struct device *dev); void device_links_driver_cleanup(struct device *dev); void device_links_no_driver(struct device *dev); bool device_links_busy(struct device *dev); void device_links_unbind_consumers(struct device *dev); void fw_devlink_drivers_done(void); void fw_devlink_probing_done(void); /* device pm support */ void device_pm_move_to_tail(struct device *dev); #ifdef CONFIG_DEVTMPFS int devtmpfs_create_node(struct device *dev); int devtmpfs_delete_node(struct device *dev); #else static inline int devtmpfs_create_node(struct device *dev) { return 0; } static inline int devtmpfs_delete_node(struct device *dev) { return 0; } #endif void software_node_notify(struct device *dev); void software_node_notify_remove(struct device *dev); |
| 3 6209 6213 217 5165 5179 218 217 1 218 218 217 217 218 218 7 214 7 1 211 218 215 218 218 1 1 5581 5593 214 1 212 2 2 2 2 2 2 2 2 2 2 1 1 2 2 2 2 1 1 2 2 2 2 2 2 3 3 3 3 3 3 3 3 3 7 7 7 2 2 5343 5339 5577 5593 211 5577 5576 5577 5579 529 5593 5579 5580 229 5578 5580 300 300 5397 5395 1647 1645 1652 1647 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Common Block IO controller cgroup interface * * Based on ideas and code from CFQ, CFS and BFQ: * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> * * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> * Paolo Valente <paolo.valente@unimore.it> * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> * * For policy-specific per-blkcg data: * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it> * Arianna Avanzini <avanzini.arianna@gmail.com> */ #include <linux/ioprio.h> #include <linux/kdev_t.h> #include <linux/module.h> #include <linux/sched/signal.h> #include <linux/err.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/slab.h> #include <linux/delay.h> #include <linux/atomic.h> #include <linux/ctype.h> #include <linux/resume_user_mode.h> #include <linux/psi.h> #include <linux/part_stat.h> #include "blk.h" #include "blk-cgroup.h" #include "blk-ioprio.h" #include "blk-throttle.h" static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu); /* * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation. * blkcg_pol_register_mutex nests outside of it and synchronizes entire * policy [un]register operations including cgroup file additions / * removals. Putting cgroup file registration outside blkcg_pol_mutex * allows grabbing it from cgroup callbacks. */ static DEFINE_MUTEX(blkcg_pol_register_mutex); static DEFINE_MUTEX(blkcg_pol_mutex); struct blkcg blkcg_root; EXPORT_SYMBOL_GPL(blkcg_root); struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css; EXPORT_SYMBOL_GPL(blkcg_root_css); static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ bool blkcg_debug_stats = false; static DEFINE_RAW_SPINLOCK(blkg_stat_lock); #define BLKG_DESTROY_BATCH_SIZE 64 /* * Lockless lists for tracking IO stats update * * New IO stats are stored in the percpu iostat_cpu within blkcg_gq (blkg). * There are multiple blkg's (one for each block device) attached to each * blkcg. The rstat code keeps track of which cpu has IO stats updated, * but it doesn't know which blkg has the updated stats. If there are many * block devices in a system, the cost of iterating all the blkg's to flush * out the IO stats can be high. To reduce such overhead, a set of percpu * lockless lists (lhead) per blkcg are used to track the set of recently * updated iostat_cpu's since the last flush. An iostat_cpu will be put * onto the lockless list on the update side [blk_cgroup_bio_start()] if * not there yet and then removed when being flushed [blkcg_rstat_flush()]. * References to blkg are gotten and then put back in the process to * protect against blkg removal. * * Return: 0 if successful or -ENOMEM if allocation fails. */ static int init_blkcg_llists(struct blkcg *blkcg) { int cpu; blkcg->lhead = alloc_percpu_gfp(struct llist_head, GFP_KERNEL); if (!blkcg->lhead) return -ENOMEM; for_each_possible_cpu(cpu) init_llist_head(per_cpu_ptr(blkcg->lhead, cpu)); return 0; } /** * blkcg_css - find the current css * * Find the css associated with either the kthread or the current task. * This may return a dying css, so it is up to the caller to use tryget logic * to confirm it is alive and well. */ static struct cgroup_subsys_state *blkcg_css(void) { struct cgroup_subsys_state *css; css = kthread_blkcg(); if (css) return css; return task_css(current, io_cgrp_id); } static bool blkcg_policy_enabled(struct request_queue *q, const struct blkcg_policy *pol) { return pol && test_bit(pol->plid, q->blkcg_pols); } static void blkg_free_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, free_work); struct request_queue *q = blkg->q; int i; /* * pd_free_fn() can also be called from blkcg_deactivate_policy(), * in order to make sure pd_free_fn() is called in order, the deletion * of the list blkg->q_node is delayed to here from blkg_destroy(), and * blkcg_mutex is used to synchronize blkg_free_workfn() and * blkcg_deactivate_policy(). */ mutex_lock(&q->blkcg_mutex); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); if (blkg->parent) blkg_put(blkg->parent); spin_lock_irq(&q->queue_lock); list_del_init(&blkg->q_node); spin_unlock_irq(&q->queue_lock); mutex_unlock(&q->blkcg_mutex); blk_put_queue(q); free_percpu(blkg->iostat_cpu); percpu_ref_exit(&blkg->refcnt); kfree(blkg); } /** * blkg_free - free a blkg * @blkg: blkg to free * * Free @blkg which may be partially allocated. */ static void blkg_free(struct blkcg_gq *blkg) { if (!blkg) return; /* * Both ->pd_free_fn() and request queue's release handler may * sleep, so free us by scheduling one work func */ INIT_WORK(&blkg->free_work, blkg_free_workfn); schedule_work(&blkg->free_work); } static void __blkg_release(struct rcu_head *rcu) { struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); struct blkcg *blkcg = blkg->blkcg; int cpu; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO WARN_ON(!bio_list_empty(&blkg->async_bios)); #endif /* * Flush all the non-empty percpu lockless lists before releasing * us, given these stat belongs to us. * * blkg_stat_lock is for serializing blkg stat update */ for_each_possible_cpu(cpu) __blkcg_rstat_flush(blkcg, cpu); /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); blkg_free(blkg); } /* * A group is RCU protected, but having an rcu lock does not mean that one * can access all the fields of blkg and assume these are valid. For * example, don't try to follow throtl_data and request queue links. * * Having a reference to blkg under an rcu allows accesses to only values * local to groups like group stats and group rate limits. */ static void blkg_release(struct percpu_ref *ref) { struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt); call_rcu(&blkg->rcu_head, __blkg_release); } #ifdef CONFIG_BLK_CGROUP_PUNT_BIO static struct workqueue_struct *blkcg_punt_bio_wq; static void blkg_async_bio_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, async_bio_work); struct bio_list bios = BIO_EMPTY_LIST; struct bio *bio; struct blk_plug plug; bool need_plug = false; /* as long as there are pending bios, @blkg can't go away */ spin_lock(&blkg->async_bio_lock); bio_list_merge_init(&bios, &blkg->async_bios); spin_unlock(&blkg->async_bio_lock); /* start plug only when bio_list contains at least 2 bios */ if (bios.head && bios.head->bi_next) { need_plug = true; blk_start_plug(&plug); } while ((bio = bio_list_pop(&bios))) submit_bio(bio); if (need_plug) blk_finish_plug(&plug); } /* * When a shared kthread issues a bio for a cgroup, doing so synchronously can * lead to priority inversions as the kthread can be trapped waiting for that * cgroup. Use this helper instead of submit_bio to punt the actual issuing to * a dedicated per-blkcg work item to avoid such priority inversions. */ void blkcg_punt_bio_submit(struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; if (blkg->parent) { spin_lock(&blkg->async_bio_lock); bio_list_add(&blkg->async_bios, bio); spin_unlock(&blkg->async_bio_lock); queue_work(blkcg_punt_bio_wq, &blkg->async_bio_work); } else { /* never bounce for the root cgroup */ submit_bio(bio); } } EXPORT_SYMBOL_GPL(blkcg_punt_bio_submit); static int __init blkcg_punt_bio_init(void) { blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio", WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND | WQ_SYSFS, 0); if (!blkcg_punt_bio_wq) return -ENOMEM; return 0; } subsys_initcall(blkcg_punt_bio_init); #endif /* CONFIG_BLK_CGROUP_PUNT_BIO */ /** * bio_blkcg_css - return the blkcg CSS associated with a bio * @bio: target bio * * This returns the CSS for the blkcg associated with a bio, or %NULL if not * associated. Callers are expected to either handle %NULL or know association * has been done prior to calling this. */ struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { if (!bio || !bio->bi_blkg) return NULL; return &bio->bi_blkg->blkcg->css; } EXPORT_SYMBOL_GPL(bio_blkcg_css); /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest * * Return the parent blkcg of @blkcg. Can be called anytime. */ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) { return css_to_blkcg(blkcg->css.parent); } /** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with * @disk: gendisk the new blkg is associated with * @gfp_mask: allocation mask to use * * Allocate a new blkg associating @blkcg and @disk. */ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk, gfp_t gfp_mask) { struct blkcg_gq *blkg; int i, cpu; /* alloc and init base part */ blkg = kzalloc_node(sizeof(*blkg), gfp_mask, disk->queue->node); if (!blkg) return NULL; if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask)) goto out_free_blkg; blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask); if (!blkg->iostat_cpu) goto out_exit_refcnt; if (!blk_get_queue(disk->queue)) goto out_free_iostat; blkg->q = disk->queue; INIT_LIST_HEAD(&blkg->q_node); blkg->blkcg = blkcg; blkg->iostat.blkg = blkg; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO spin_lock_init(&blkg->async_bio_lock); bio_list_init(&blkg->async_bios); INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn); #endif u64_stats_init(&blkg->iostat.sync); for_each_possible_cpu(cpu) { u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync); per_cpu_ptr(blkg->iostat_cpu, cpu)->blkg = blkg; } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkg_policy_data *pd; if (!blkcg_policy_enabled(disk->queue, pol)) continue; /* alloc per-policy data and attach it to blkg */ pd = pol->pd_alloc_fn(disk, blkcg, gfp_mask); if (!pd) goto out_free_pds; blkg->pd[i] = pd; pd->blkg = blkg; pd->plid = i; pd->online = false; } return blkg; out_free_pds: while (--i >= 0) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); blk_put_queue(disk->queue); out_free_iostat: free_percpu(blkg->iostat_cpu); out_exit_refcnt: percpu_ref_exit(&blkg->refcnt); out_free_blkg: kfree(blkg); return NULL; } /* * If @new_blkg is %NULL, this function tries to allocate a new one as * necessary using %GFP_NOWAIT. @new_blkg is always consumed on return. */ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk, struct blkcg_gq *new_blkg) { struct blkcg_gq *blkg; int i, ret; lockdep_assert_held(&disk->queue->queue_lock); /* request_queue is dying, do not create/recreate a blkg */ if (blk_queue_dying(disk->queue)) { ret = -ENODEV; goto err_free_blkg; } /* blkg holds a reference to blkcg */ if (!css_tryget_online(&blkcg->css)) { ret = -ENODEV; goto err_free_blkg; } /* allocate */ if (!new_blkg) { new_blkg = blkg_alloc(blkcg, disk, GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto err_put_css; } } blkg = new_blkg; /* link parent */ if (blkcg_parent(blkcg)) { blkg->parent = blkg_lookup(blkcg_parent(blkcg), disk->queue); if (WARN_ON_ONCE(!blkg->parent)) { ret = -ENODEV; goto err_put_css; } blkg_get(blkg->parent); } /* invoke per-policy init */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_init_fn) pol->pd_init_fn(blkg->pd[i]); } /* insert */ spin_lock(&blkcg->lock); ret = radix_tree_insert(&blkcg->blkg_tree, disk->queue->id, blkg); if (likely(!ret)) { hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list); list_add(&blkg->q_node, &disk->queue->blkg_list); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i]) { if (pol->pd_online_fn) pol->pd_online_fn(blkg->pd[i]); blkg->pd[i]->online = true; } } } blkg->online = true; spin_unlock(&blkcg->lock); if (!ret) return blkg; /* @blkg failed fully initialized, use the usual release path */ blkg_put(blkg); return ERR_PTR(ret); err_put_css: css_put(&blkcg->css); err_free_blkg: if (new_blkg) blkg_free(new_blkg); return ERR_PTR(ret); } /** * blkg_lookup_create - lookup blkg, try to create one if not there * @blkcg: blkcg of interest * @disk: gendisk of interest * * Lookup blkg for the @blkcg - @disk pair. If it doesn't exist, try to * create one. blkg creation is performed recursively from blkcg_root such * that all non-root blkg's have access to the parent blkg. This function * should be called under RCU read lock and takes @disk->queue->queue_lock. * * Returns the blkg or the closest blkg if blkg_create() fails as it walks * down from root. */ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; unsigned long flags; WARN_ON_ONCE(!rcu_read_lock_held()); blkg = blkg_lookup(blkcg, q); if (blkg) return blkg; spin_lock_irqsave(&q->queue_lock, flags); blkg = blkg_lookup(blkcg, q); if (blkg) { if (blkcg != &blkcg_root && blkg != rcu_dereference(blkcg->blkg_hint)) rcu_assign_pointer(blkcg->blkg_hint, blkg); goto found; } /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. Returns the closest * blkg to the intended blkg should blkg_create() fail. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent = blkcg_parent(blkcg); struct blkcg_gq *ret_blkg = q->root_blkg; while (parent) { blkg = blkg_lookup(parent, q); if (blkg) { /* remember closest blkg */ ret_blkg = blkg; break; } pos = parent; parent = blkcg_parent(parent); } blkg = blkg_create(pos, disk, NULL); if (IS_ERR(blkg)) { blkg = ret_blkg; break; } if (pos == blkcg) break; } found: spin_unlock_irqrestore(&q->queue_lock, flags); return blkg; } static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; int i; lockdep_assert_held(&blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); /* * blkg stays on the queue list until blkg_free_workfn(), see details in * blkg_free_workfn(), hence this function can be called from * blkcg_destroy_blkgs() first and again from blkg_destroy_all() before * blkg_free_workfn(). */ if (hlist_unhashed(&blkg->blkcg_node)) return; for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && blkg->pd[i]->online) { blkg->pd[i]->online = false; if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[i]); } } blkg->online = false; radix_tree_delete(&blkcg->blkg_tree, blkg->q->id); hlist_del_init_rcu(&blkg->blkcg_node); /* * Both setting lookup hint to and clearing it from @blkg are done * under queue_lock. If it's not pointing to @blkg now, it never * will. Hint assignment itself can race safely. */ if (rcu_access_pointer(blkcg->blkg_hint) == blkg) rcu_assign_pointer(blkcg->blkg_hint, NULL); /* * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. */ percpu_ref_kill(&blkg->refcnt); } static void blkg_destroy_all(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; int count = BLKG_DESTROY_BATCH_SIZE; int i; restart: spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; if (hlist_unhashed(&blkg->blkcg_node)) continue; spin_lock(&blkcg->lock); blkg_destroy(blkg); spin_unlock(&blkcg->lock); /* * in order to avoid holding the spin lock for too long, release * it when a batch of blkgs are destroyed. */ if (!(--count)) { count = BLKG_DESTROY_BATCH_SIZE; spin_unlock_irq(&q->queue_lock); cond_resched(); goto restart; } } /* * Mark policy deactivated since policy offline has been done, and * the free is scheduled, so future blkcg_deactivate_policy() can * be bypassed */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (pol) __clear_bit(pol->plid, q->blkcg_pols); } q->root_blkg = NULL; spin_unlock_irq(&q->queue_lock); } static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] = src->bytes[i]; dst->ios[i] = src->ios[i]; } } static void __blkg_clear_stat(struct blkg_iostat_set *bis) { struct blkg_iostat cur = {0}; unsigned long flags; flags = u64_stats_update_begin_irqsave(&bis->sync); blkg_iostat_set(&bis->cur, &cur); blkg_iostat_set(&bis->last, &cur); u64_stats_update_end_irqrestore(&bis->sync, flags); } static void blkg_clear_stat(struct blkcg_gq *blkg) { int cpu; for_each_possible_cpu(cpu) { struct blkg_iostat_set *s = per_cpu_ptr(blkg->iostat_cpu, cpu); __blkg_clear_stat(s); } __blkg_clear_stat(&blkg->iostat); } static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; int i; mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); /* * Note that stat reset is racy - it doesn't synchronize against * stat updates. This is a debug feature which shouldn't exist * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { blkg_clear_stat(blkg); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_reset_stats_fn) pol->pd_reset_stats_fn(blkg->pd[i]); } } spin_unlock_irq(&blkcg->lock); mutex_unlock(&blkcg_pol_mutex); return 0; } const char *blkg_dev_name(struct blkcg_gq *blkg) { if (!blkg->q->disk) return NULL; return bdi_dev_name(blkg->q->disk->bdi); } /** * blkcg_print_blkgs - helper for printing per-blkg data * @sf: seq_file to print to * @blkcg: blkcg of interest * @prfill: fill function to print out a blkg * @pol: policy in question * @data: data to be passed to @prfill * @show_total: to print out sum of prfill return values or not * * This function invokes @prfill on each blkg of @blkcg if pd for the * policy specified by @pol exists. @prfill is invoked with @sf, the * policy data and @data and the matching queue lock held. If @show_total * is %true, the sum of the return values from @prfill is printed with * "Total" label at the end. * * This is to be used to construct print functions for * cftype->read_seq_string method. */ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int), const struct blkcg_policy *pol, int data, bool show_total) { struct blkcg_gq *blkg; u64 total = 0; rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); if (blkcg_policy_enabled(blkg->q, pol)) total += prfill(sf, blkg->pd[pol->plid], data); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); if (show_total) seq_printf(sf, "Total %llu\n", (unsigned long long)total); } EXPORT_SYMBOL_GPL(blkcg_print_blkgs); /** * __blkg_prfill_u64 - prfill helper for a single u64 value * @sf: seq_file to print to * @pd: policy private data of interest * @v: value to print * * Print @v to @sf for the device associated with @pd. */ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v) { const char *dname = blkg_dev_name(pd->blkg); if (!dname) return 0; seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v); return v; } EXPORT_SYMBOL_GPL(__blkg_prfill_u64); /** * blkg_conf_init - initialize a blkg_conf_ctx * @ctx: blkg_conf_ctx to initialize * @input: input string * * Initialize @ctx which can be used to parse blkg config input string @input. * Once initialized, @ctx can be used with blkg_conf_open_bdev() and * blkg_conf_prep(), and must be cleaned up with blkg_conf_exit(). */ void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input) { *ctx = (struct blkg_conf_ctx){ .input = input }; } EXPORT_SYMBOL_GPL(blkg_conf_init); /** * blkg_conf_open_bdev - parse and open bdev for per-blkg config update * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Parse the device node prefix part, MAJ:MIN, of per-blkg config update from * @ctx->input and get and store the matching bdev in @ctx->bdev. @ctx->body is * set to point past the device node prefix. * * This function may be called multiple times on @ctx and the extra calls become * NOOPs. blkg_conf_prep() implicitly calls this function. Use this function * explicitly if bdev access is needed without resolving the blkcg / policy part * of @ctx->input. Returns -errno on error. */ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx) { char *input = ctx->input; unsigned int major, minor; struct block_device *bdev; int key_len; if (ctx->bdev) return 0; if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2) return -EINVAL; input += key_len; if (!isspace(*input)) return -EINVAL; input = skip_spaces(input); bdev = blkdev_get_no_open(MKDEV(major, minor)); if (!bdev) return -ENODEV; if (bdev_is_partition(bdev)) { blkdev_put_no_open(bdev); return -ENODEV; } mutex_lock(&bdev->bd_queue->rq_qos_mutex); if (!disk_live(bdev->bd_disk)) { blkdev_put_no_open(bdev); mutex_unlock(&bdev->bd_queue->rq_qos_mutex); return -ENODEV; } ctx->body = input; ctx->bdev = bdev; return 0; } /** * blkg_conf_prep - parse and prepare for per-blkg config update * @blkcg: target block cgroup * @pol: target policy * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Parse per-blkg config update from @ctx->input and initialize @ctx * accordingly. On success, @ctx->body points to the part of @ctx->input * following MAJ:MIN, @ctx->bdev points to the target block device and * @ctx->blkg to the blkg being configured. * * blkg_conf_open_bdev() may be called on @ctx beforehand. On success, this * function returns with queue lock held and must be followed by * blkg_conf_exit(). */ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, struct blkg_conf_ctx *ctx) __acquires(&bdev->bd_queue->queue_lock) { struct gendisk *disk; struct request_queue *q; struct blkcg_gq *blkg; int ret; ret = blkg_conf_open_bdev(ctx); if (ret) return ret; disk = ctx->bdev->bd_disk; q = disk->queue; /* * blkcg_deactivate_policy() requires queue to be frozen, we can grab * q_usage_counter to prevent concurrent with blkcg_deactivate_policy(). */ ret = blk_queue_enter(q, 0); if (ret) goto fail; spin_lock_irq(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) { ret = -EOPNOTSUPP; goto fail_unlock; } blkg = blkg_lookup(blkcg, q); if (blkg) goto success; /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent; struct blkcg_gq *new_blkg; parent = blkcg_parent(blkcg); while (parent && !blkg_lookup(parent, q)) { pos = parent; parent = blkcg_parent(parent); } /* Drop locks to do new blkg allocation with GFP_KERNEL. */ spin_unlock_irq(&q->queue_lock); new_blkg = blkg_alloc(pos, disk, GFP_KERNEL); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto fail_exit_queue; } if (radix_tree_preload(GFP_KERNEL)) { blkg_free(new_blkg); ret = -ENOMEM; goto fail_exit_queue; } spin_lock_irq(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) { blkg_free(new_blkg); ret = -EOPNOTSUPP; goto fail_preloaded; } blkg = blkg_lookup(pos, q); if (blkg) { blkg_free(new_blkg); } else { blkg = blkg_create(pos, disk, new_blkg); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); goto fail_preloaded; } } radix_tree_preload_end(); if (pos == blkcg) goto success; } success: blk_queue_exit(q); ctx->blkg = blkg; return 0; fail_preloaded: radix_tree_preload_end(); fail_unlock: spin_unlock_irq(&q->queue_lock); fail_exit_queue: blk_queue_exit(q); fail: /* * If queue was bypassing, we should retry. Do so after a * short msleep(). It isn't strictly necessary but queue * can be bypassing for some time and it's always nice to * avoid busy looping. */ if (ret == -EBUSY) { msleep(10); ret = restart_syscall(); } return ret; } EXPORT_SYMBOL_GPL(blkg_conf_prep); /** * blkg_conf_exit - clean up per-blkg config update * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Clean up after per-blkg config update. This function must be called on all * blkg_conf_ctx's initialized with blkg_conf_init(). */ void blkg_conf_exit(struct blkg_conf_ctx *ctx) __releases(&ctx->bdev->bd_queue->queue_lock) __releases(&ctx->bdev->bd_queue->rq_qos_mutex) { if (ctx->blkg) { spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock); ctx->blkg = NULL; } if (ctx->bdev) { mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex); blkdev_put_no_open(ctx->bdev); ctx->body = NULL; ctx->bdev = NULL; } } EXPORT_SYMBOL_GPL(blkg_conf_exit); static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] += src->bytes[i]; dst->ios[i] += src->ios[i]; } } static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] -= src->bytes[i]; dst->ios[i] -= src->ios[i]; } } static void blkcg_iostat_update(struct blkcg_gq *blkg, struct blkg_iostat *cur, struct blkg_iostat *last) { struct blkg_iostat delta; unsigned long flags; /* propagate percpu delta to global */ flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&delta, cur); blkg_iostat_sub(&delta, last); blkg_iostat_add(&blkg->iostat.cur, &delta); blkg_iostat_add(last, &delta); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) { struct llist_head *lhead = per_cpu_ptr(blkcg->lhead, cpu); struct llist_node *lnode; struct blkg_iostat_set *bisc, *next_bisc; unsigned long flags; rcu_read_lock(); lnode = llist_del_all(lhead); if (!lnode) goto out; /* * For covering concurrent parent blkg update from blkg_release(). * * When flushing from cgroup, cgroup_rstat_lock is always held, so * this lock won't cause contention most of time. */ raw_spin_lock_irqsave(&blkg_stat_lock, flags); /* * Iterate only the iostat_cpu's queued in the lockless list. */ llist_for_each_entry_safe(bisc, next_bisc, lnode, lnode) { struct blkcg_gq *blkg = bisc->blkg; struct blkcg_gq *parent = blkg->parent; struct blkg_iostat cur; unsigned int seq; /* * Order assignment of `next_bisc` from `bisc->lnode.next` in * llist_for_each_entry_safe and clearing `bisc->lqueued` for * avoiding to assign `next_bisc` with new next pointer added * in blk_cgroup_bio_start() in case of re-ordering. * * The pair barrier is implied in llist_add() in blk_cgroup_bio_start(). */ smp_mb(); WRITE_ONCE(bisc->lqueued, false); if (bisc == &blkg->iostat) goto propagate_up; /* propagate up to parent only */ /* fetch the current per-cpu values */ do { seq = u64_stats_fetch_begin(&bisc->sync); blkg_iostat_set(&cur, &bisc->cur); } while (u64_stats_fetch_retry(&bisc->sync, seq)); blkcg_iostat_update(blkg, &cur, &bisc->last); propagate_up: /* propagate global delta to parent (unless that's root) */ if (parent && parent->parent) { blkcg_iostat_update(parent, &blkg->iostat.cur, &blkg->iostat.last); /* * Queue parent->iostat to its blkcg's lockless * list to propagate up to the grandparent if the * iostat hasn't been queued yet. */ if (!parent->iostat.lqueued) { struct llist_head *plhead; plhead = per_cpu_ptr(parent->blkcg->lhead, cpu); llist_add(&parent->iostat.lnode, plhead); parent->iostat.lqueued = true; } } } raw_spin_unlock_irqrestore(&blkg_stat_lock, flags); out: rcu_read_unlock(); } static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) { /* Root-level stats are sourced from system-wide IO stats */ if (cgroup_parent(css->cgroup)) __blkcg_rstat_flush(css_to_blkcg(css), cpu); } /* * We source root cgroup stats from the system-wide stats to avoid * tracking the same information twice and incurring overhead when no * cgroups are defined. For that reason, cgroup_rstat_flush in * blkcg_print_stat does not actually fill out the iostat in the root * cgroup's blkcg_gq. * * However, we would like to re-use the printing code between the root and * non-root cgroups to the extent possible. For that reason, we simulate * flushing the root cgroup's stats by explicitly filling in the iostat * with disk level statistics. */ static void blkcg_fill_root_iostats(void) { struct class_dev_iter iter; struct device *dev; class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct block_device *bdev = dev_to_bdev(dev); struct blkcg_gq *blkg = bdev->bd_disk->queue->root_blkg; struct blkg_iostat tmp; int cpu; unsigned long flags; memset(&tmp, 0, sizeof(tmp)); for_each_possible_cpu(cpu) { struct disk_stats *cpu_dkstats; cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu); tmp.ios[BLKG_IOSTAT_READ] += cpu_dkstats->ios[STAT_READ]; tmp.ios[BLKG_IOSTAT_WRITE] += cpu_dkstats->ios[STAT_WRITE]; tmp.ios[BLKG_IOSTAT_DISCARD] += cpu_dkstats->ios[STAT_DISCARD]; // convert sectors to bytes tmp.bytes[BLKG_IOSTAT_READ] += cpu_dkstats->sectors[STAT_READ] << 9; tmp.bytes[BLKG_IOSTAT_WRITE] += cpu_dkstats->sectors[STAT_WRITE] << 9; tmp.bytes[BLKG_IOSTAT_DISCARD] += cpu_dkstats->sectors[STAT_DISCARD] << 9; } flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&blkg->iostat.cur, &tmp); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } } static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) { struct blkg_iostat_set *bis = &blkg->iostat; u64 rbytes, wbytes, rios, wios, dbytes, dios; const char *dname; unsigned seq; int i; if (!blkg->online) return; dname = blkg_dev_name(blkg); if (!dname) return; seq_printf(s, "%s ", dname); do { seq = u64_stats_fetch_begin(&bis->sync); rbytes = bis->cur.bytes[BLKG_IOSTAT_READ]; wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE]; dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD]; rios = bis->cur.ios[BLKG_IOSTAT_READ]; wios = bis->cur.ios[BLKG_IOSTAT_WRITE]; dios = bis->cur.ios[BLKG_IOSTAT_DISCARD]; } while (u64_stats_fetch_retry(&bis->sync, seq)); if (rbytes || wbytes || rios || wios) { seq_printf(s, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", rbytes, wbytes, rios, wios, dbytes, dios); } if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { seq_printf(s, " use_delay=%d delay_nsec=%llu", atomic_read(&blkg->use_delay), atomic64_read(&blkg->delay_nsec)); } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (!blkg->pd[i] || !pol->pd_stat_fn) continue; pol->pd_stat_fn(blkg->pd[i], s); } seq_puts(s, "\n"); } static int blkcg_print_stat(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct blkcg_gq *blkg; if (!seq_css(sf)->parent) blkcg_fill_root_iostats(); else cgroup_rstat_flush(blkcg->css.cgroup); rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); blkcg_print_one_stat(blkg, sf); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); return 0; } static struct cftype blkcg_files[] = { { .name = "stat", .seq_show = blkcg_print_stat, }, { } /* terminate */ }; static struct cftype blkcg_legacy_files[] = { { .name = "reset_stats", .write_u64 = blkcg_reset_stats, }, { } /* terminate */ }; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css) { return &css_to_blkcg(css)->cgwb_list; } #endif /* * blkcg destruction is a three-stage process. * * 1. Destruction starts. The blkcg_css_offline() callback is invoked * which offlines writeback. Here we tie the next stage of blkg destruction * to the completion of writeback associated with the blkcg. This lets us * avoid punting potentially large amounts of outstanding writeback to root * while maintaining any ongoing policies. The next stage is triggered when * the nr_cgwbs count goes to zero. * * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called * and handles the destruction of blkgs. Here the css reference held by * the blkg is put back eventually allowing blkcg_css_free() to be called. * This work may occur in cgwb_release_workfn() on the cgwb_release * workqueue. Any submitted ios that fail to get the blkg ref will be * punted to the root_blkg. * * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. * This finally frees the blkcg. */ /** * blkcg_destroy_blkgs - responsible for shooting down blkgs * @blkcg: blkcg of interest * * blkgs should be removed while holding both q and blkcg locks. As blkcg lock * is nested inside q lock, this function performs reverse double lock dancing. * Destroying the blkgs releases the reference held on the blkcg's css allowing * blkcg_css_free to eventually be called. * * This is the blkcg counterpart of ioc_release_fn(). */ static void blkcg_destroy_blkgs(struct blkcg *blkcg) { might_sleep(); spin_lock_irq(&blkcg->lock); while (!hlist_empty(&blkcg->blkg_list)) { struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first, struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; if (need_resched() || !spin_trylock(&q->queue_lock)) { /* * Given that the system can accumulate a huge number * of blkgs in pathological cases, check to see if we * need to rescheduling to avoid softlockup. */ spin_unlock_irq(&blkcg->lock); cond_resched(); spin_lock_irq(&blkcg->lock); continue; } blkg_destroy(blkg); spin_unlock(&q->queue_lock); } spin_unlock_irq(&blkcg->lock); } /** * blkcg_pin_online - pin online state * @blkcg_css: blkcg of interest * * While pinned, a blkcg is kept online. This is primarily used to * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline * while an associated cgwb is still active. */ void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css) { refcount_inc(&css_to_blkcg(blkcg_css)->online_pin); } /** * blkcg_unpin_online - unpin online state * @blkcg_css: blkcg of interest * * This is primarily used to impedance-match blkg and cgwb lifetimes so * that blkg doesn't go offline while an associated cgwb is still active. * When this count goes to zero, all active cgwbs have finished so the * blkcg can continue destruction by calling blkcg_destroy_blkgs(). */ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) { struct blkcg *blkcg = css_to_blkcg(blkcg_css); do { if (!refcount_dec_and_test(&blkcg->online_pin)) break; blkcg_destroy_blkgs(blkcg); blkcg = blkcg_parent(blkcg); } while (blkcg); } /** * blkcg_css_offline - cgroup css_offline callback * @css: css of interest * * This function is called when @css is about to go away. Here the cgwbs are * offlined first and only once writeback associated with the blkcg has * finished do we start step 2 (see above). */ static void blkcg_css_offline(struct cgroup_subsys_state *css) { /* this prevents anyone from attaching or migrating to this blkcg */ wb_blkcg_offline(css); /* put the base online pin allowing step 2 to be triggered */ blkcg_unpin_online(css); } static void blkcg_css_free(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); int i; mutex_lock(&blkcg_pol_mutex); list_del(&blkcg->all_blkcgs_node); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); mutex_unlock(&blkcg_pol_mutex); free_percpu(blkcg->lhead); kfree(blkcg); } static struct cgroup_subsys_state * blkcg_css_alloc(struct cgroup_subsys_state *parent_css) { struct blkcg *blkcg; int i; mutex_lock(&blkcg_pol_mutex); if (!parent_css) { blkcg = &blkcg_root; } else { blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL); if (!blkcg) goto unlock; } if (init_blkcg_llists(blkcg)) goto free_blkcg; for (i = 0; i < BLKCG_MAX_POLS ; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkcg_policy_data *cpd; /* * If the policy hasn't been attached yet, wait for it * to be attached before doing anything else. Otherwise, * check if the policy requires any specific per-cgroup * data: if it does, allocate and initialize it. */ if (!pol || !pol->cpd_alloc_fn) continue; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) goto free_pd_blkcg; blkcg->cpd[i] = cpd; cpd->blkcg = blkcg; cpd->plid = i; } spin_lock_init(&blkcg->lock); refcount_set(&blkcg->online_pin, 1); INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN); INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); #endif list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs); mutex_unlock(&blkcg_pol_mutex); return &blkcg->css; free_pd_blkcg: for (i--; i >= 0; i--) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); free_percpu(blkcg->lhead); free_blkcg: if (blkcg != &blkcg_root) kfree(blkcg); unlock: mutex_unlock(&blkcg_pol_mutex); return ERR_PTR(-ENOMEM); } static int blkcg_css_online(struct cgroup_subsys_state *css) { struct blkcg *parent = blkcg_parent(css_to_blkcg(css)); /* * blkcg_pin_online() is used to delay blkcg offline so that blkgs * don't go offline while cgwbs are still active on them. Pin the * parent so that offline always happens towards the root. */ if (parent) blkcg_pin_online(&parent->css); return 0; } void blkg_init_queue(struct request_queue *q) { INIT_LIST_HEAD(&q->blkg_list); mutex_init(&q->blkcg_mutex); } int blkcg_init_disk(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *new_blkg, *blkg; bool preloaded; new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL); if (!new_blkg) return -ENOMEM; preloaded = !radix_tree_preload(GFP_KERNEL); /* Make sure the root blkg exists. */ /* spin_lock_irq can serve as RCU read-side critical section. */ spin_lock_irq(&q->queue_lock); blkg = blkg_create(&blkcg_root, disk, new_blkg); if (IS_ERR(blkg)) goto err_unlock; q->root_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (preloaded) radix_tree_preload_end(); return 0; err_unlock: spin_unlock_irq(&q->queue_lock); if (preloaded) radix_tree_preload_end(); return PTR_ERR(blkg); } void blkcg_exit_disk(struct gendisk *disk) { blkg_destroy_all(disk); blk_throtl_exit(disk); } static void blkcg_exit(struct task_struct *tsk) { if (tsk->throttle_disk) put_disk(tsk->throttle_disk); tsk->throttle_disk = NULL; } struct cgroup_subsys io_cgrp_subsys = { .css_alloc = blkcg_css_alloc, .css_online = blkcg_css_online, .css_offline = blkcg_css_offline, .css_free = blkcg_css_free, .css_rstat_flush = blkcg_rstat_flush, .dfl_cftypes = blkcg_files, .legacy_cftypes = blkcg_legacy_files, .legacy_name = "blkio", .exit = blkcg_exit, #ifdef CONFIG_MEMCG /* * This ensures that, if available, memcg is automatically enabled * together on the default hierarchy so that the owner cgroup can * be retrieved from writeback pages. */ .depends_on = 1 << memory_cgrp_id, #endif }; EXPORT_SYMBOL_GPL(io_cgrp_subsys); /** * blkcg_activate_policy - activate a blkcg policy on a gendisk * @disk: gendisk of interest * @pol: blkcg policy to activate * * Activate @pol on @disk. Requires %GFP_KERNEL context. @disk goes through * bypass mode to populate its blkgs with policy_data for @pol. * * Activation happens with @disk bypassed, so nobody would be accessing blkgs * from IO path. Update of each blkg is protected by both queue and blkcg * locks so that holding either lock and testing blkcg_policy_enabled() is * always enough for dereferencing policy data. * * The caller is responsible for synchronizing [de]activations and policy * [un]registerations. Returns 0 on success, -errno on failure. */ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { struct request_queue *q = disk->queue; struct blkg_policy_data *pd_prealloc = NULL; struct blkcg_gq *blkg, *pinned_blkg = NULL; int ret; if (blkcg_policy_enabled(q, pol)) return 0; /* * Policy is allowed to be registered without pd_alloc_fn/pd_free_fn, * for example, ioprio. Such policy will work on blkcg level, not disk * level, and don't need to be activated. */ if (WARN_ON_ONCE(!pol->pd_alloc_fn || !pol->pd_free_fn)) return -EINVAL; if (queue_is_mq(q)) blk_mq_freeze_queue(q); retry: spin_lock_irq(&q->queue_lock); /* blkg_list is pushed at the head, reverse walk to initialize parents first */ list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) { struct blkg_policy_data *pd; if (blkg->pd[pol->plid]) continue; /* If prealloc matches, use it; otherwise try GFP_NOWAIT */ if (blkg == pinned_blkg) { pd = pd_prealloc; pd_prealloc = NULL; } else { pd = pol->pd_alloc_fn(disk, blkg->blkcg, GFP_NOWAIT | __GFP_NOWARN); } if (!pd) { /* * GFP_NOWAIT failed. Free the existing one and * prealloc for @blkg w/ GFP_KERNEL. */ if (pinned_blkg) blkg_put(pinned_blkg); blkg_get(blkg); pinned_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); pd_prealloc = pol->pd_alloc_fn(disk, blkg->blkcg, GFP_KERNEL); if (pd_prealloc) goto retry; else goto enomem; } spin_lock(&blkg->blkcg->lock); pd->blkg = blkg; pd->plid = pol->plid; blkg->pd[pol->plid] = pd; if (pol->pd_init_fn) pol->pd_init_fn(pd); if (pol->pd_online_fn) pol->pd_online_fn(pd); pd->online = true; spin_unlock(&blkg->blkcg->lock); } __set_bit(pol->plid, q->blkcg_pols); ret = 0; spin_unlock_irq(&q->queue_lock); out: if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); if (pinned_blkg) blkg_put(pinned_blkg); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); return ret; enomem: /* alloc failed, take down everything */ spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; struct blkg_policy_data *pd; spin_lock(&blkcg->lock); pd = blkg->pd[pol->plid]; if (pd) { if (pd->online && pol->pd_offline_fn) pol->pd_offline_fn(pd); pd->online = false; pol->pd_free_fn(pd); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); ret = -ENOMEM; goto out; } EXPORT_SYMBOL_GPL(blkcg_activate_policy); /** * blkcg_deactivate_policy - deactivate a blkcg policy on a gendisk * @disk: gendisk of interest * @pol: blkcg policy to deactivate * * Deactivate @pol on @disk. Follows the same synchronization rules as * blkcg_activate_policy(). */ void blkcg_deactivate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; if (!blkcg_policy_enabled(q, pol)) return; if (queue_is_mq(q)) blk_mq_freeze_queue(q); mutex_lock(&q->blkcg_mutex); spin_lock_irq(&q->queue_lock); __clear_bit(pol->plid, q->blkcg_pols); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { if (blkg->pd[pol->plid]->online && pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); mutex_unlock(&q->blkcg_mutex); if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); } EXPORT_SYMBOL_GPL(blkcg_deactivate_policy); static void blkcg_free_all_cpd(struct blkcg_policy *pol) { struct blkcg *blkcg; list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { if (blkcg->cpd[pol->plid]) { pol->cpd_free_fn(blkcg->cpd[pol->plid]); blkcg->cpd[pol->plid] = NULL; } } } /** * blkcg_policy_register - register a blkcg policy * @pol: blkcg policy to register * * Register @pol with blkcg core. Might sleep and @pol may be modified on * successful registration. Returns 0 on success and -errno on failure. */ int blkcg_policy_register(struct blkcg_policy *pol) { struct blkcg *blkcg; int i, ret; mutex_lock(&blkcg_pol_register_mutex); mutex_lock(&blkcg_pol_mutex); /* find an empty slot */ ret = -ENOSPC; for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; if (i >= BLKCG_MAX_POLS) { pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); goto err_unlock; } /* * Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs, and policy * without pd_alloc_fn/pd_free_fn can't be activated. */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || (!pol->pd_alloc_fn ^ !pol->pd_free_fn)) goto err_unlock; /* register @pol */ pol->plid = i; blkcg_policy[pol->plid] = pol; /* allocate and install cpd's */ if (pol->cpd_alloc_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { struct blkcg_policy_data *cpd; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) goto err_free_cpds; blkcg->cpd[pol->plid] = cpd; cpd->blkcg = blkcg; cpd->plid = pol->plid; } } mutex_unlock(&blkcg_pol_mutex); /* everything is in place, add intf files for the new policy */ if (pol->dfl_cftypes) WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys, pol->dfl_cftypes)); if (pol->legacy_cftypes) WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys, pol->legacy_cftypes)); mutex_unlock(&blkcg_pol_register_mutex); return 0; err_free_cpds: if (pol->cpd_free_fn) blkcg_free_all_cpd(pol); blkcg_policy[pol->plid] = NULL; err_unlock: mutex_unlock(&blkcg_pol_mutex); mutex_unlock(&blkcg_pol_register_mutex); return ret; } EXPORT_SYMBOL_GPL(blkcg_policy_register); /** * blkcg_policy_unregister - unregister a blkcg policy * @pol: blkcg policy to unregister * * Undo blkcg_policy_register(@pol). Might sleep. */ void blkcg_policy_unregister(struct blkcg_policy *pol) { mutex_lock(&blkcg_pol_register_mutex); if (WARN_ON(blkcg_policy[pol->plid] != pol)) goto out_unlock; /* kill the intf files first */ if (pol->dfl_cftypes) cgroup_rm_cftypes(pol->dfl_cftypes); if (pol->legacy_cftypes) cgroup_rm_cftypes(pol->legacy_cftypes); /* remove cpds and unregister */ mutex_lock(&blkcg_pol_mutex); if (pol->cpd_free_fn) blkcg_free_all_cpd(pol); blkcg_policy[pol->plid] = NULL; mutex_unlock(&blkcg_pol_mutex); out_unlock: mutex_unlock(&blkcg_pol_register_mutex); } EXPORT_SYMBOL_GPL(blkcg_policy_unregister); /* * Scale the accumulated delay based on how long it has been since we updated * the delay. We only call this when we are adding delay, in case it's been a * while since we added delay, and when we are checking to see if we need to * delay a task, to account for any delays that may have occurred. */ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now) { u64 old = atomic64_read(&blkg->delay_start); /* negative use_delay means no scaling, see blkcg_set_delay() */ if (atomic_read(&blkg->use_delay) < 0) return; /* * We only want to scale down every second. The idea here is that we * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain * time window. We only want to throttle tasks for recent delay that * has occurred, in 1 second time windows since that's the maximum * things can be throttled. We save the current delay window in * blkg->last_delay so we know what amount is still left to be charged * to the blkg from this point onward. blkg->last_use keeps track of * the use_delay counter. The idea is if we're unthrottling the blkg we * are ok with whatever is happening now, and we can take away more of * the accumulated delay as we've already throttled enough that * everybody is happy with their IO latencies. */ if (time_before64(old + NSEC_PER_SEC, now) && atomic64_try_cmpxchg(&blkg->delay_start, &old, now)) { u64 cur = atomic64_read(&blkg->delay_nsec); u64 sub = min_t(u64, blkg->last_delay, now - old); int cur_use = atomic_read(&blkg->use_delay); /* * We've been unthrottled, subtract a larger chunk of our * accumulated delay. */ if (cur_use < blkg->last_use) sub = max_t(u64, sub, blkg->last_delay >> 1); /* * This shouldn't happen, but handle it anyway. Our delay_nsec * should only ever be growing except here where we subtract out * min(last_delay, 1 second), but lord knows bugs happen and I'd * rather not end up with negative numbers. */ if (unlikely(cur < sub)) { atomic64_set(&blkg->delay_nsec, 0); blkg->last_delay = 0; } else { atomic64_sub(sub, &blkg->delay_nsec); blkg->last_delay = cur - sub; } blkg->last_use = cur_use; } } /* * This is called when we want to actually walk up the hierarchy and check to * see if we need to throttle, and then actually throttle if there is some * accumulated delay. This should only be called upon return to user space so * we're not holding some lock that would induce a priority inversion. */ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay) { unsigned long pflags; bool clamp; u64 now = blk_time_get_ns(); u64 exp; u64 delay_nsec = 0; int tok; while (blkg->parent) { int use_delay = atomic_read(&blkg->use_delay); if (use_delay) { u64 this_delay; blkcg_scale_delay(blkg, now); this_delay = atomic64_read(&blkg->delay_nsec); if (this_delay > delay_nsec) { delay_nsec = this_delay; clamp = use_delay > 0; } } blkg = blkg->parent; } if (!delay_nsec) return; /* * Let's not sleep for all eternity if we've amassed a huge delay. * Swapping or metadata IO can accumulate 10's of seconds worth of * delay, and we want userspace to be able to do _something_ so cap the * delays at 0.25s. If there's 10's of seconds worth of delay then the * tasks will be delayed for 0.25 second for every syscall. If * blkcg_set_delay() was used as indicated by negative use_delay, the * caller is responsible for regulating the range. */ if (clamp) delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC); if (use_memdelay) psi_memstall_enter(&pflags); exp = ktime_add_ns(now, delay_nsec); tok = io_schedule_prepare(); do { __set_current_state(TASK_KILLABLE); if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS)) break; } while (!fatal_signal_pending(current)); io_schedule_finish(tok); if (use_memdelay) psi_memstall_leave(&pflags); } /** * blkcg_maybe_throttle_current - throttle the current task if it has been marked * * This is only called if we've been marked with set_notify_resume(). Obviously * we can be set_notify_resume() for reasons other than blkcg throttling, so we * check to see if current->throttle_disk is set and if not this doesn't do * anything. This should only ever be called by the resume code, it's not meant * to be called by people willy-nilly as it will actually do the work to * throttle the task if it is setup for throttling. */ void blkcg_maybe_throttle_current(void) { struct gendisk *disk = current->throttle_disk; struct blkcg *blkcg; struct blkcg_gq *blkg; bool use_memdelay = current->use_memdelay; if (!disk) return; current->throttle_disk = NULL; current->use_memdelay = false; rcu_read_lock(); blkcg = css_to_blkcg(blkcg_css()); if (!blkcg) goto out; blkg = blkg_lookup(blkcg, disk->queue); if (!blkg) goto out; if (!blkg_tryget(blkg)) goto out; rcu_read_unlock(); blkcg_maybe_throttle_blkg(blkg, use_memdelay); blkg_put(blkg); put_disk(disk); return; out: rcu_read_unlock(); } /** * blkcg_schedule_throttle - this task needs to check for throttling * @disk: disk to throttle * @use_memdelay: do we charge this to memory delay for PSI * * This is called by the IO controller when we know there's delay accumulated * for the blkg for this task. We do not pass the blkg because there are places * we call this that may not have that information, the swapping code for * instance will only have a block_device at that point. This set's the * notify_resume for the task to check and see if it requires throttling before * returning to user space. * * We will only schedule once per syscall. You can call this over and over * again and it will only do the check once upon return to user space, and only * throttle once. If the task needs to be throttled again it'll need to be * re-set at the next time we see the task. */ void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay) { if (unlikely(current->flags & PF_KTHREAD)) return; if (current->throttle_disk != disk) { if (test_bit(GD_DEAD, &disk->state)) return; get_device(disk_to_dev(disk)); if (current->throttle_disk) put_disk(current->throttle_disk); current->throttle_disk = disk; } if (use_memdelay) current->use_memdelay = use_memdelay; set_notify_resume(current); } /** * blkcg_add_delay - add delay to this blkg * @blkg: blkg of interest * @now: the current time in nanoseconds * @delta: how many nanoseconds of delay to add * * Charge @delta to the blkg's current delay accumulation. This is used to * throttle tasks if an IO controller thinks we need more throttling. */ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta) { if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) return; blkcg_scale_delay(blkg, now); atomic64_add(delta, &blkg->delay_nsec); } /** * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @bio: target bio * @css: target css * * As the failure mode here is to walk up the blkg tree, this ensure that the * blkg->parent pointers are always valid. This returns the blkg that it ended * up taking a reference on or %NULL if no reference was taken. */ static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio, struct cgroup_subsys_state *css) { struct blkcg_gq *blkg, *ret_blkg = NULL; rcu_read_lock(); blkg = blkg_lookup_create(css_to_blkcg(css), bio->bi_bdev->bd_disk); while (blkg) { if (blkg_tryget(blkg)) { ret_blkg = blkg; break; } blkg = blkg->parent; } rcu_read_unlock(); return ret_blkg; } /** * bio_associate_blkg_from_css - associate a bio with a specified css * @bio: target bio * @css: target css * * Associate @bio with the blkg found by combining the css's blkg and the * request_queue of the @bio. An association failure is handled by walking up * the blkg tree. Therefore, the blkg associated can be anything between @blkg * and q->root_blkg. This situation only happens when a cgroup is dying and * then the remaining bios will spill to the closest alive blkg. * * A reference will be taken on the blkg and will be released when @bio is * freed. */ void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { if (bio->bi_blkg) blkg_put(bio->bi_blkg); if (css && css->parent) { bio->bi_blkg = blkg_tryget_closest(bio, css); } else { blkg_get(bdev_get_queue(bio->bi_bdev)->root_blkg); bio->bi_blkg = bdev_get_queue(bio->bi_bdev)->root_blkg; } } EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); /** * bio_associate_blkg - associate a bio with a blkg * @bio: target bio * * Associate @bio with the blkg found from the bio's css and request_queue. * If one is not found, bio_lookup_blkg() creates the blkg. If a blkg is * already associated, the css is reused and association redone as the * request_queue may have changed. */ void bio_associate_blkg(struct bio *bio) { struct cgroup_subsys_state *css; if (blk_op_is_passthrough(bio->bi_opf)) return; rcu_read_lock(); if (bio->bi_blkg) css = bio_blkcg_css(bio); else css = blkcg_css(); bio_associate_blkg_from_css(bio, css); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(bio_associate_blkg); /** * bio_clone_blkg_association - clone blkg association from src to dst bio * @dst: destination bio * @src: source bio */ void bio_clone_blkg_association(struct bio *dst, struct bio *src) { if (src->bi_blkg) bio_associate_blkg_from_css(dst, bio_blkcg_css(src)); } EXPORT_SYMBOL_GPL(bio_clone_blkg_association); static int blk_cgroup_io_type(struct bio *bio) { if (op_is_discard(bio->bi_opf)) return BLKG_IOSTAT_DISCARD; if (op_is_write(bio->bi_opf)) return BLKG_IOSTAT_WRITE; return BLKG_IOSTAT_READ; } void blk_cgroup_bio_start(struct bio *bio) { struct blkcg *blkcg = bio->bi_blkg->blkcg; int rwd = blk_cgroup_io_type(bio), cpu; struct blkg_iostat_set *bis; unsigned long flags; if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) return; /* Root-level stats are sourced from system-wide IO stats */ if (!cgroup_parent(blkcg->css.cgroup)) return; cpu = get_cpu(); bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu); flags = u64_stats_update_begin_irqsave(&bis->sync); /* * If the bio is flagged with BIO_CGROUP_ACCT it means this is a split * bio and we would have already accounted for the size of the bio. */ if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { bio_set_flag(bio, BIO_CGROUP_ACCT); bis->cur.bytes[rwd] += bio->bi_iter.bi_size; } bis->cur.ios[rwd]++; /* * If the iostat_cpu isn't in a lockless list, put it into the * list to indicate that a stat update is pending. */ if (!READ_ONCE(bis->lqueued)) { struct llist_head *lhead = this_cpu_ptr(blkcg->lhead); llist_add(&bis->lnode, lhead); WRITE_ONCE(bis->lqueued, true); } u64_stats_update_end_irqrestore(&bis->sync, flags); cgroup_rstat_updated(blkcg->css.cgroup, cpu); put_cpu(); } bool blk_cgroup_congested(void) { struct blkcg *blkcg; bool ret = false; rcu_read_lock(); for (blkcg = css_to_blkcg(blkcg_css()); blkcg; blkcg = blkcg_parent(blkcg)) { if (atomic_read(&blkcg->congestion_count)) { ret = true; break; } } rcu_read_unlock(); return ret; } module_param(blkcg_debug_stats, bool, 0644); MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not"); |
| 3835 3838 32 32 31 206 4131 1146 4737 4732 3565 1 1 1 1 4710 4711 4712 4710 1 4711 4723 4712 3566 3568 3565 118 3456 2025 4318 4318 4318 4324 1843 1847 1847 7 2 5 2 3 1840 8 1018 8845 5 8873 8886 8902 8887 549 11 11 11 8 8 8 7 8 965 8525 5352 8036 575 577 932 2290 3170 3168 3174 2268 3 4 1 1 1 1 32 32 32 32 34 1 3 32 2 32 27 7 2 2 2 1 1 5 2 2 1 4 1 3 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <linux/file_ref.h> #include <net/sock.h> #include "internal.h" /** * __file_ref_put - Slowpath of file_ref_put() * @ref: Pointer to the reference count * @cnt: Current reference count * * Invoked when the reference count is outside of the valid zone. * * Return: * True if this was the last reference with no future references * possible. This signals the caller that it can safely schedule the * object, which is protected by the reference counter, for * deconstruction. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * deconstruct the protected object. */ bool __file_ref_put(file_ref_t *ref, unsigned long cnt) { /* Did this drop the last reference? */ if (likely(cnt == FILE_REF_NOREF)) { /* * Carefully try to set the reference count to FILE_REF_DEAD. * * This can fail if a concurrent get() operation has * elevated it again or the corresponding put() even marked * it dead already. Both are valid situations and do not * require a retry. If this fails the caller is not * allowed to deconstruct the object. */ if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD)) return false; /* * The caller can safely schedule the object for * deconstruction. Provide acquire ordering. */ smp_acquire__after_ctrl_dep(); return true; } /* * If the reference count was already in the dead zone, then this * put() operation is imbalanced. Warn, put the reference count back to * DEAD and tell the caller to not deconstruct the object. */ if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) { atomic_long_set(&ref->refcnt, FILE_REF_DEAD); return false; } /* * This is a put() operation on a saturated refcount. Restore the * mean saturation value and tell the caller to not deconstruct the * object. */ if (cnt > FILE_REF_MAXREF) atomic_long_set(&ref->refcnt, FILE_REF_SATURATED); return false; } EXPORT_SYMBOL_GPL(__file_ref_put); unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) #define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int copy_words) { unsigned int nwords = fdt_words(nfdt); bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, copy_words, nwords); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". */ static struct fdtable *alloc_fdtable(unsigned int slots_wanted) { struct fdtable *fdt; unsigned int nr; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. Since we called only * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab * already gives BITS_PER_LONG slots), the above boils down to * 1. use the smallest power of two large enough to give us that many * slots. * 2. on 32bit skip 64 and 128 - the minimal capacity we want there is * 256 slots (i.e. 1Kb fd array). * 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there * and we are never going to be asked for 64 or less. */ if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256) nr = 256; else nr = roundup_pow_of_two(slots_wanted); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) { nr = round_down(sysctl_nr_open, BITS_PER_LONG); if (nr < slots_wanted) return ERR_PTR(-EMFILE); } fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return ERR_PTR(-ENOMEM); } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 0 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr + 1); /* make sure all fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (IS_ERR(new_fdt)) return PTR_ERR(new_fdt); cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in fd_install() */ smp_wmb(); return 0; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 on success. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int error; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return 0; /* Can we expand? */ if (nr >= sysctl_nr_open) return -EMFILE; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* All good, so we try */ files->resize_in_progress = true; error = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return error; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt, bool set) { if (set) { __set_bit(fd, fdt->close_on_exec); } else { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt, bool set) { __set_bit(fd, fdt->open_fds); __set_close_on_exec(fd, fdt, set); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (test_bit(fd, fdt->full_fds_bits)) __clear_bit(fd, fdt->full_fds_bits); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * punch_hole is optional - when close_range() is asked to unshare * and close, we don't need to copy descriptors in that range, so * a smaller cloned descriptor table might suffice if the last * currently opened descriptor falls into that range. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole) { unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds); if (last == fdt->max_fds) return NR_OPEN_DEFAULT; if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) { last = find_last_bit(fdt->open_fds, punch_hole->from); if (last == punch_hole->from) return NR_OPEN_DEFAULT; } return ALIGN(last + 1, BITS_PER_LONG); } /* * Allocate a new descriptor table and copy contents from the passed in * instance. Returns a pointer to cloned table on success, ERR_PTR() * on failure. For 'punch_hole' see sane_fdtable_size(). */ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) return ERR_PTR(-ENOMEM); atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files); if (IS_ERR(new_fdt)) { kmem_cache_free(files_cachep, newf); return ERR_CAST(new_fdt); } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); } copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; if (f) { get_file(f); } else { /* * The fd may be claimed in the fd bitmap but not yet * instantiated in the files array if a sibling thread * is partway through open(). So make sure that this * fd is available to the new process. */ __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file *file = fdt->fd[i]; if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } void put_files_struct(struct files_struct *files) { if (atomic_dec_and_test(&files->count)) { struct fdtable *fdt = close_files(files); /* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); } } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */ unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; unsigned int bit; /* * Try to avoid looking at the second level bitmap */ bit = find_next_zero_bit(&fdt->open_fds[bitbit], BITS_PER_LONG, start & (BITS_PER_LONG - 1)); if (bit < BITS_PER_LONG) return bit + bitbit * BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; if (bitbit >= maxfd) return maxfd; if (bitbit > start) start = bitbit; return find_next_zero_bit(fdt->open_fds, maxfd, start); } /* * allocate a file descriptor, mark it busy. */ static int alloc_fd(unsigned start, unsigned end, unsigned flags) { struct files_struct *files = current->files; unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (likely(fd < fdt->max_fds)) fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (unlikely(fd >= end)) goto out; if (unlikely(fd >= fdt->max_fds)) { error = expand_files(files, fd); if (error < 0) goto out; goto repeat; } if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt, flags & O_CLOEXEC); error = fd; out: spin_unlock(&files->file_lock); return error; } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return alloc_fd(0, nofile, flags); } int get_unused_fd_flags(unsigned flags) { return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array. * * The VFS is full of places where we drop the files lock between * setting the open_fds bitmap and installing the file in the file * array. At any such point, we are vulnerable to a dup2() race * installing a file in the array before us. We need to detect this and * fput() the struct file we are about to overwrite in this case. * * It should never happen - if we allow dup2() do it, _really_ bad things * will follow. * * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file). */ void fd_install(unsigned int fd, struct file *file) { struct files_struct *files = current->files; struct fdtable *fdt; if (WARN_ON_ONCE(unlikely(file->f_mode & FMODE_BACKING))) return; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); WARN_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } EXPORT_SYMBOL(fd_install); /** * file_close_fd_locked - return file associated with fd * @files: file struct to retrieve file from * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Context: files_lock must be held. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd_locked(struct files_struct *files, unsigned fd) { struct fdtable *fdt = files_fdtable(files); struct file *file; lockdep_assert_held(&files->file_lock); if (fd >= fdt->max_fds) return NULL; fd = array_index_nospec(fd, fdt->max_fds); file = fdt->fd[fd]; if (file) { rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); } return file; } int close_fd(unsigned fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(close_fd); /** * last_fd - return last valid index into fd table * @fdt: File descriptor table. * * Context: Either rcu read lock or files_lock must be held. * * Returns: Last valid index into fdtable. */ static inline unsigned last_fd(struct fdtable *fdt) { return fdt->max_fds - 1; } static inline void __range_cloexec(struct files_struct *cur_fds, unsigned int fd, unsigned int max_fd) { struct fdtable *fdt; /* make sure we're using the correct maximum value */ spin_lock(&cur_fds->file_lock); fdt = files_fdtable(cur_fds); max_fd = min(last_fd(fdt), max_fd); if (fd <= max_fd) bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1); spin_unlock(&cur_fds->file_lock); } static inline void __range_close(struct files_struct *files, unsigned int fd, unsigned int max_fd) { struct file *file; unsigned n; spin_lock(&files->file_lock); n = last_fd(files_fdtable(files)); max_fd = min(max_fd, n); for (; fd <= max_fd; fd++) { file = file_close_fd_locked(files, fd); if (file) { spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } else if (need_resched()) { spin_unlock(&files->file_lock); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } /** * sys_close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * @flags: CLOSE_RANGE flags. * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. * Currently, errors to close a given file descriptor are ignored. */ SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd, unsigned int, flags) { struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~(CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC)) return -EINVAL; if (fd > max_fd) return -EINVAL; if ((flags & CLOSE_RANGE_UNSHARE) && atomic_read(&cur_fds->count) > 1) { struct fd_range range = {fd, max_fd}, *punch_hole = ⦥ /* * If the caller requested all fds to be made cloexec we always * copy all of the file descriptors since they still want to * use them. */ if (flags & CLOSE_RANGE_CLOEXEC) punch_hole = NULL; fds = dup_fd(cur_fds, punch_hole); if (IS_ERR(fds)) return PTR_ERR(fds); /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ swap(cur_fds, fds); } if (flags & CLOSE_RANGE_CLOEXEC) __range_cloexec(cur_fds, fd, max_fd); else __range_close(cur_fds, fd, max_fd); if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one. */ task_lock(me); me->files = cur_fds; task_unlock(me); put_files_struct(fds); } return 0; } /** * file_close_fd - return file associated with fd * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd(unsigned int fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); return file; } void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } static struct file *__get_file_rcu(struct file __rcu **f) { struct file __rcu *file; struct file __rcu *file_reloaded; struct file __rcu *file_reloaded_cmp; file = rcu_dereference_raw(*f); if (!file) return NULL; if (unlikely(!file_ref_get(&file->f_ref))) return ERR_PTR(-EAGAIN); file_reloaded = rcu_dereference_raw(*f); /* * Ensure that all accesses have a dependency on the load from * rcu_dereference_raw() above so we get correct ordering * between reuse/allocation and the pointer check below. */ file_reloaded_cmp = file_reloaded; OPTIMIZER_HIDE_VAR(file_reloaded_cmp); /* * file_ref_get() above provided a full memory barrier when we * acquired a reference. * * This is paired with the write barrier from assigning to the * __rcu protected file pointer so that if that pointer still * matches the current file, we know we have successfully * acquired a reference to the right file. * * If the pointers don't match the file has been reallocated by * SLAB_TYPESAFE_BY_RCU. */ if (file == file_reloaded_cmp) return file_reloaded; fput(file); return ERR_PTR(-EAGAIN); } /** * get_file_rcu - try go get a reference to a file under rcu * @f: the file to get a reference on * * This function tries to get a reference on @f carefully verifying that * @f hasn't been reused. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_rcu(struct file __rcu **f) { for (;;) { struct file __rcu *file; file = __get_file_rcu(f); if (!IS_ERR(file)) return file; } } EXPORT_SYMBOL_GPL(get_file_rcu); /** * get_file_active - try go get a reference to a file * @f: the file to get a reference on * * In contast to get_file_rcu() the pointer itself isn't part of the * reference counting. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_active(struct file **f) { struct file __rcu *file; rcu_read_lock(); file = __get_file_rcu(f); rcu_read_unlock(); if (IS_ERR(file)) file = NULL; return file; } EXPORT_SYMBOL_GPL(get_file_active); static inline struct file *__fget_files_rcu(struct files_struct *files, unsigned int fd, fmode_t mask) { for (;;) { struct file *file; struct fdtable *fdt = rcu_dereference_raw(files->fdt); struct file __rcu **fdentry; unsigned long nospec_mask; /* Mask is a 0 for invalid fd's, ~0 for valid ones */ nospec_mask = array_index_mask_nospec(fd, fdt->max_fds); /* * fdentry points to the 'fd' offset, or fdt->fd[0]. * Loading from fdt->fd[0] is always safe, because the * array always exists. */ fdentry = fdt->fd + (fd & nospec_mask); /* Do the load, then mask any invalid result */ file = rcu_dereference_raw(*fdentry); file = (void *)(nospec_mask & (unsigned long)file); if (unlikely(!file)) return NULL; /* * Ok, we have a file pointer that was valid at * some point, but it might have become stale since. * * We need to confirm it by incrementing the refcount * and then check the lookup again. * * file_ref_get() gives us a full memory barrier. We * only really need an 'acquire' one to protect the * loads below, but we don't have that. */ if (unlikely(!file_ref_get(&file->f_ref))) continue; /* * Such a race can take two forms: * * (a) the file ref already went down to zero and the * file hasn't been reused yet or the file count * isn't zero but the file has already been reused. * * (b) the file table entry has changed under us. * Note that we don't need to re-check the 'fdt->fd' * pointer having changed, because it always goes * hand-in-hand with 'fdt'. * * If so, we need to put our ref and try again. */ if (unlikely(file != rcu_dereference_raw(*fdentry)) || unlikely(rcu_dereference_raw(files->fdt) != fdt)) { fput(file); continue; } /* * This isn't the file we're looking for or we're not * allowed to get a reference to it. */ if (unlikely(file->f_mode & mask)) { fput(file); return NULL; } /* * Ok, we have a ref to the file, and checked that it * still exists. */ return file; } } static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask) { struct file *file; rcu_read_lock(); file = __fget_files_rcu(files, fd, mask); rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask) { return __fget_files(current->files, fd, mask); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0); } EXPORT_SYMBOL(fget_raw); struct file *fget_task(struct task_struct *task, unsigned int fd) { struct file *file = NULL; task_lock(task); if (task->files) file = __fget_files(task->files, fd, 0); task_unlock(task); return file; } struct file *fget_task_next(struct task_struct *task, unsigned int *ret_fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; unsigned int fd = *ret_fd; struct file *file = NULL; task_lock(task); files = task->files; if (files) { rcu_read_lock(); for (; fd < files_fdtable(files)->max_fds; fd++) { file = __fget_files_rcu(files, fd, 0); if (file) break; } rcu_read_unlock(); } task_unlock(task); *ret_fd = fd; return file; } EXPORT_SYMBOL(fget_task_next); /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. * * (As an exception to rule 2, you can call filp_close between fget_light and * fput_light provided that you capture a real refcount with get_file before * the call to filp_close, and ensure that this real refcount is fput *after* * the fput_light call.) * * See also the documentation in rust/kernel/file.rs. */ static inline struct fd __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; /* * If another thread is concurrently calling close_fd() followed * by put_files_struct(), we must not observe the old table * entry combined with the new refcount - otherwise we could * return a file that is concurrently being freed. * * atomic_read_acquire() pairs with atomic_dec_and_test() in * put_files_struct(). */ if (likely(atomic_read_acquire(&files->count) == 1)) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return EMPTY_FD; return BORROWED_FD(file); } else { file = __fget_files(files, fd, mask); if (!file) return EMPTY_FD; return CLONED_FD(file); } } struct fd fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(fdget); struct fd fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } /* * Try to avoid f_pos locking. We only need it if the * file is marked for FMODE_ATOMIC_POS, and it can be * accessed multiple ways. * * Always do it for directories, because pidfd_getfd() * can make a file accessible even if it otherwise would * not be, and for directories this is a correctness * issue, not a "POSIX requirement". */ static inline bool file_needs_f_pos_lock(struct file *file) { return (file->f_mode & FMODE_ATOMIC_POS) && (file_count(file) > 1 || file->f_op->iterate_shared); } struct fd fdget_pos(unsigned int fd) { struct fd f = fdget(fd); struct file *file = fd_file(f); if (file && file_needs_f_pos_lock(file)) { f.word |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } return f; } void __f_unlock_pos(struct file *f) { mutex_unlock(&f->f_pos_lock); } /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __set_close_on_exec(fd, files_fdtable(files), flag); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { bool res; rcu_read_lock(); res = close_on_exec(fd, current->files); rcu_read_unlock(); return res; } static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) __releases(&files->file_lock) { struct file *tofree; struct fdtable *fdt; /* * We need to detect attempts to do dup2() over allocated but still * not finished descriptor. NB: OpenBSD avoids that at the price of * extra work in their equivalent of fget() - they insert struct * file immediately after grabbing descriptor, mark it larval if * more work (e.g. actual opening) is needed and make sure that * fget() treats larval files as absent. Potentially interesting, * but while extra work in fget() is trivial, locking implications * and amount of surgery on open()-related paths in VFS are not. * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" * deadlocks in rather amusing ways, AFAICS. All of that is out of * scope of POSIX or SUS, since neither considers shared descriptor * tables and this condition does not arise without those. */ fdt = files_fdtable(files); fd = array_index_nospec(fd, fdt->max_fds); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt, flags & O_CLOEXEC); spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return close_fd(fd); if (fd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; return do_dup2(files, file, fd, flags); out_unlock: spin_unlock(&files->file_lock); return err; } /** * receive_fd() - Install received file into file descriptor table * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry * * Installs a received file into the file descriptor table, with appropriate * checks and count updates. Optionally writes the fd number to userspace, if * @ufd is non-NULL. * * This helper handles its own reference counting of the incoming * struct file. * * Returns newly install fd or -ve on error. */ int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags) { int new_fd; int error; error = security_file_receive(file); if (error) return error; new_fd = get_unused_fd_flags(o_flags); if (new_fd < 0) return new_fd; if (ufd) { error = put_user(new_fd, ufd); if (error) { put_unused_fd(new_fd); return error; } } fd_install(new_fd, get_file(file)); __receive_sock(file); return new_fd; } EXPORT_SYMBOL_GPL(receive_fd); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) { int error; error = security_file_receive(file); if (error) return error; error = replace_fd(new_fd, file, o_flags); if (error) return error; __receive_sock(file); return new_fd; } static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; if (unlikely(oldfd == newfd)) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); file = files_lookup_fd_locked(files, oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { return ksys_dup3(oldfd, newfd, flags); } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; struct file *f; int retval = oldfd; rcu_read_lock(); f = __fget_files_rcu(files, oldfd, 0); if (!f) retval = -EBADF; rcu_read_unlock(); if (f) fput(f); return retval; } return ksys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd_flags(0); if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { unsigned long nofile = rlimit(RLIMIT_NOFILE); int err; if (from >= nofile) return -EINVAL; err = alloc_fd(from, nofile, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; } spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd); |
| 2 2 2 4 3 4 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 | // 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/inet_dscp.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) { 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->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 unreachable * 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(const 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, }; ASSERT_RTNL(); /* Paired with READ_ONCE() in fib_rules_seq() */ WRITE_ONCE(ops->fib_rules_seq, ops->fib_rules_seq + 1); 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(const struct net *net, int family) { unsigned int fib_rules_seq; struct fib_rules_ops *ops; ops = lookup_rules_ops(net, family); if (!ops) return 0; /* Paired with WRITE_ONCE() in call_fib_rule_notifiers() */ fib_rules_seq = READ_ONCE(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 = nla_get_u8_default(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]); 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) }, [FRA_DSCP] = NLA_POLICY_MAX(NLA_U8, INET_DSCP_MASK >> 2), }; 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 err, idx = 0, family; if (cb->strict_check) { 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; return dump_rules(skb, cb, ops); } err = 0; 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; err = dump_rules(skb, cb, ops); if (err < 0) break; cb->args[1] = 0; skip: idx++; } rcu_read_unlock(); cb->args[0] = idx; return err; } 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: 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 const struct rtnl_msg_handler fib_rules_rtnl_msg_handlers[] __initconst = { {.msgtype = RTM_NEWRULE, .doit = fib_nl_newrule}, {.msgtype = RTM_DELRULE, .doit = fib_nl_delrule}, {.msgtype = RTM_GETRULE, .dumpit = fib_nl_dumprule, .flags = RTNL_FLAG_DUMP_UNLOCKED}, }; static int __init fib_rules_init(void) { int err; rtnl_register_many(fib_rules_rtnl_msg_handlers); 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_many(fib_rules_rtnl_msg_handlers); return err; } subsys_initcall(fib_rules_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 | #ifndef _LINUX_SCHED_ISOLATION_H #define _LINUX_SCHED_ISOLATION_H #include <linux/cpumask.h> #include <linux/cpuset.h> #include <linux/init.h> #include <linux/tick.h> enum hk_type { HK_TYPE_TIMER, HK_TYPE_RCU, HK_TYPE_MISC, HK_TYPE_SCHED, HK_TYPE_TICK, HK_TYPE_DOMAIN, HK_TYPE_WQ, HK_TYPE_MANAGED_IRQ, HK_TYPE_KTHREAD, HK_TYPE_MAX }; #ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE(housekeeping_overridden); extern int housekeeping_any_cpu(enum hk_type type); extern const struct cpumask *housekeeping_cpumask(enum hk_type type); extern bool housekeeping_enabled(enum hk_type type); extern void housekeeping_affine(struct task_struct *t, enum hk_type type); extern bool housekeeping_test_cpu(int cpu, enum hk_type type); extern void __init housekeeping_init(void); #else static inline int housekeeping_any_cpu(enum hk_type type) { return smp_processor_id(); } static inline const struct cpumask *housekeeping_cpumask(enum hk_type type) { return cpu_possible_mask; } static inline bool housekeeping_enabled(enum hk_type type) { return false; } static inline void housekeeping_affine(struct task_struct *t, enum hk_type type) { } static inline bool housekeeping_test_cpu(int cpu, enum hk_type type) { return true; } static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ static inline bool housekeeping_cpu(int cpu, enum hk_type type) { #ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely(&housekeeping_overridden)) return housekeeping_test_cpu(cpu, type); #endif return true; } static inline bool cpu_is_isolated(int cpu) { return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN) || !housekeeping_test_cpu(cpu, HK_TYPE_TICK) || cpuset_cpu_is_isolated(cpu); } #endif /* _LINUX_SCHED_ISOLATION_H */ |
| 117 63 71 2 190 190 53 135 135 37 109 35 1 135 133 78 78 35 11 135 135 128 68 106 45 1 2 297 207 172 1 1 2 1 2 142 48 16 1 2 2 2 2 2 2 2 1 1 2 133 1 76 74 133 132 2 130 10 133 22 133 131 2 133 133 1 1 1 1 1 1 1 1 1 1 1 1 1 1 36 36 36 6 6 36 1 5 32 2 1 16 25 298 298 208 173 170 1 109 134 48 48 33 27 52 29 33 13 52 52 52 139 140 135 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2017 Christoph Hellwig. */ #include "xfs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_bit.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trace.h" /* * In-core extent record layout: * * +-------+----------------------------+ * | 00:53 | all 54 bits of startoff | * | 54:63 | low 10 bits of startblock | * +-------+----------------------------+ * | 00:20 | all 21 bits of length | * | 21 | unwritten extent bit | * | 22:63 | high 42 bits of startblock | * +-------+----------------------------+ */ #define XFS_IEXT_STARTOFF_MASK xfs_mask64lo(BMBT_STARTOFF_BITLEN) #define XFS_IEXT_LENGTH_MASK xfs_mask64lo(BMBT_BLOCKCOUNT_BITLEN) #define XFS_IEXT_STARTBLOCK_MASK xfs_mask64lo(BMBT_STARTBLOCK_BITLEN) struct xfs_iext_rec { uint64_t lo; uint64_t hi; }; /* * Given that the length can't be a zero, only an empty hi value indicates an * unused record. */ static bool xfs_iext_rec_is_empty(struct xfs_iext_rec *rec) { return rec->hi == 0; } static inline void xfs_iext_rec_clear(struct xfs_iext_rec *rec) { rec->lo = 0; rec->hi = 0; } static void xfs_iext_set( struct xfs_iext_rec *rec, struct xfs_bmbt_irec *irec) { ASSERT((irec->br_startoff & ~XFS_IEXT_STARTOFF_MASK) == 0); ASSERT((irec->br_blockcount & ~XFS_IEXT_LENGTH_MASK) == 0); ASSERT((irec->br_startblock & ~XFS_IEXT_STARTBLOCK_MASK) == 0); rec->lo = irec->br_startoff & XFS_IEXT_STARTOFF_MASK; rec->hi = irec->br_blockcount & XFS_IEXT_LENGTH_MASK; rec->lo |= (irec->br_startblock << 54); rec->hi |= ((irec->br_startblock & ~xfs_mask64lo(10)) << (22 - 10)); if (irec->br_state == XFS_EXT_UNWRITTEN) rec->hi |= (1 << 21); } static void xfs_iext_get( struct xfs_bmbt_irec *irec, struct xfs_iext_rec *rec) { irec->br_startoff = rec->lo & XFS_IEXT_STARTOFF_MASK; irec->br_blockcount = rec->hi & XFS_IEXT_LENGTH_MASK; irec->br_startblock = rec->lo >> 54; irec->br_startblock |= (rec->hi & xfs_mask64hi(42)) >> (22 - 10); if (rec->hi & (1 << 21)) irec->br_state = XFS_EXT_UNWRITTEN; else irec->br_state = XFS_EXT_NORM; } enum { NODE_SIZE = 256, KEYS_PER_NODE = NODE_SIZE / (sizeof(uint64_t) + sizeof(void *)), RECS_PER_LEAF = (NODE_SIZE - (2 * sizeof(struct xfs_iext_leaf *))) / sizeof(struct xfs_iext_rec), }; /* * In-core extent btree block layout: * * There are two types of blocks in the btree: leaf and inner (non-leaf) blocks. * * The leaf blocks are made up by %KEYS_PER_NODE extent records, which each * contain the startoffset, blockcount, startblock and unwritten extent flag. * See above for the exact format, followed by pointers to the previous and next * leaf blocks (if there are any). * * The inner (non-leaf) blocks first contain KEYS_PER_NODE lookup keys, followed * by an equal number of pointers to the btree blocks at the next lower level. * * +-------+-------+-------+-------+-------+----------+----------+ * Leaf: | rec 1 | rec 2 | rec 3 | rec 4 | rec N | prev-ptr | next-ptr | * +-------+-------+-------+-------+-------+----------+----------+ * * +-------+-------+-------+-------+-------+-------+------+-------+ * Inner: | key 1 | key 2 | key 3 | key N | ptr 1 | ptr 2 | ptr3 | ptr N | * +-------+-------+-------+-------+-------+-------+------+-------+ */ struct xfs_iext_node { uint64_t keys[KEYS_PER_NODE]; #define XFS_IEXT_KEY_INVALID (1ULL << 63) void *ptrs[KEYS_PER_NODE]; }; struct xfs_iext_leaf { struct xfs_iext_rec recs[RECS_PER_LEAF]; struct xfs_iext_leaf *prev; struct xfs_iext_leaf *next; }; inline xfs_extnum_t xfs_iext_count(struct xfs_ifork *ifp) { return ifp->if_bytes / sizeof(struct xfs_iext_rec); } static inline int xfs_iext_max_recs(struct xfs_ifork *ifp) { if (ifp->if_height == 1) return xfs_iext_count(ifp); return RECS_PER_LEAF; } static inline struct xfs_iext_rec *cur_rec(struct xfs_iext_cursor *cur) { return &cur->leaf->recs[cur->pos]; } static inline bool xfs_iext_valid(struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { if (!cur->leaf) return false; if (cur->pos < 0 || cur->pos >= xfs_iext_max_recs(ifp)) return false; if (xfs_iext_rec_is_empty(cur_rec(cur))) return false; return true; } static void * xfs_iext_find_first_leaf( struct xfs_ifork *ifp) { struct xfs_iext_node *node = ifp->if_data; int height; if (!ifp->if_height) return NULL; for (height = ifp->if_height; height > 1; height--) { node = node->ptrs[0]; ASSERT(node); } return node; } static void * xfs_iext_find_last_leaf( struct xfs_ifork *ifp) { struct xfs_iext_node *node = ifp->if_data; int height, i; if (!ifp->if_height) return NULL; for (height = ifp->if_height; height > 1; height--) { for (i = 1; i < KEYS_PER_NODE; i++) if (!node->ptrs[i]) break; node = node->ptrs[i - 1]; ASSERT(node); } return node; } void xfs_iext_first( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { cur->pos = 0; cur->leaf = xfs_iext_find_first_leaf(ifp); } void xfs_iext_last( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { int i; cur->leaf = xfs_iext_find_last_leaf(ifp); if (!cur->leaf) { cur->pos = 0; return; } for (i = 1; i < xfs_iext_max_recs(ifp); i++) { if (xfs_iext_rec_is_empty(&cur->leaf->recs[i])) break; } cur->pos = i - 1; } void xfs_iext_next( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { if (!cur->leaf) { ASSERT(cur->pos <= 0 || cur->pos >= RECS_PER_LEAF); xfs_iext_first(ifp, cur); return; } ASSERT(cur->pos >= 0); ASSERT(cur->pos < xfs_iext_max_recs(ifp)); cur->pos++; if (ifp->if_height > 1 && !xfs_iext_valid(ifp, cur) && cur->leaf->next) { cur->leaf = cur->leaf->next; cur->pos = 0; } } void xfs_iext_prev( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { if (!cur->leaf) { ASSERT(cur->pos <= 0 || cur->pos >= RECS_PER_LEAF); xfs_iext_last(ifp, cur); return; } ASSERT(cur->pos >= 0); ASSERT(cur->pos <= RECS_PER_LEAF); recurse: do { cur->pos--; if (xfs_iext_valid(ifp, cur)) return; } while (cur->pos > 0); if (ifp->if_height > 1 && cur->leaf->prev) { cur->leaf = cur->leaf->prev; cur->pos = RECS_PER_LEAF; goto recurse; } } static inline int xfs_iext_key_cmp( struct xfs_iext_node *node, int n, xfs_fileoff_t offset) { if (node->keys[n] > offset) return 1; if (node->keys[n] < offset) return -1; return 0; } static inline int xfs_iext_rec_cmp( struct xfs_iext_rec *rec, xfs_fileoff_t offset) { uint64_t rec_offset = rec->lo & XFS_IEXT_STARTOFF_MASK; uint32_t rec_len = rec->hi & XFS_IEXT_LENGTH_MASK; if (rec_offset > offset) return 1; if (rec_offset + rec_len <= offset) return -1; return 0; } static void * xfs_iext_find_level( struct xfs_ifork *ifp, xfs_fileoff_t offset, int level) { struct xfs_iext_node *node = ifp->if_data; int height, i; if (!ifp->if_height) return NULL; for (height = ifp->if_height; height > level; height--) { for (i = 1; i < KEYS_PER_NODE; i++) if (xfs_iext_key_cmp(node, i, offset) > 0) break; node = node->ptrs[i - 1]; if (!node) break; } return node; } static int xfs_iext_node_pos( struct xfs_iext_node *node, xfs_fileoff_t offset) { int i; for (i = 1; i < KEYS_PER_NODE; i++) { if (xfs_iext_key_cmp(node, i, offset) > 0) break; } return i - 1; } static int xfs_iext_node_insert_pos( struct xfs_iext_node *node, xfs_fileoff_t offset) { int i; for (i = 0; i < KEYS_PER_NODE; i++) { if (xfs_iext_key_cmp(node, i, offset) > 0) return i; } return KEYS_PER_NODE; } static int xfs_iext_node_nr_entries( struct xfs_iext_node *node, int start) { int i; for (i = start; i < KEYS_PER_NODE; i++) { if (node->keys[i] == XFS_IEXT_KEY_INVALID) break; } return i; } static int xfs_iext_leaf_nr_entries( struct xfs_ifork *ifp, struct xfs_iext_leaf *leaf, int start) { int i; for (i = start; i < xfs_iext_max_recs(ifp); i++) { if (xfs_iext_rec_is_empty(&leaf->recs[i])) break; } return i; } static inline uint64_t xfs_iext_leaf_key( struct xfs_iext_leaf *leaf, int n) { return leaf->recs[n].lo & XFS_IEXT_STARTOFF_MASK; } static inline void * xfs_iext_alloc_node( int size) { return kzalloc(size, GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); } static void xfs_iext_grow( struct xfs_ifork *ifp) { struct xfs_iext_node *node = xfs_iext_alloc_node(NODE_SIZE); int i; if (ifp->if_height == 1) { struct xfs_iext_leaf *prev = ifp->if_data; node->keys[0] = xfs_iext_leaf_key(prev, 0); node->ptrs[0] = prev; } else { struct xfs_iext_node *prev = ifp->if_data; ASSERT(ifp->if_height > 1); node->keys[0] = prev->keys[0]; node->ptrs[0] = prev; } for (i = 1; i < KEYS_PER_NODE; i++) node->keys[i] = XFS_IEXT_KEY_INVALID; ifp->if_data = node; ifp->if_height++; } static void xfs_iext_update_node( struct xfs_ifork *ifp, xfs_fileoff_t old_offset, xfs_fileoff_t new_offset, int level, void *ptr) { struct xfs_iext_node *node = ifp->if_data; int height, i; for (height = ifp->if_height; height > level; height--) { for (i = 0; i < KEYS_PER_NODE; i++) { if (i > 0 && xfs_iext_key_cmp(node, i, old_offset) > 0) break; if (node->keys[i] == old_offset) node->keys[i] = new_offset; } node = node->ptrs[i - 1]; ASSERT(node); } ASSERT(node == ptr); } static struct xfs_iext_node * xfs_iext_split_node( struct xfs_iext_node **nodep, int *pos, int *nr_entries) { struct xfs_iext_node *node = *nodep; struct xfs_iext_node *new = xfs_iext_alloc_node(NODE_SIZE); const int nr_move = KEYS_PER_NODE / 2; int nr_keep = nr_move + (KEYS_PER_NODE & 1); int i = 0; /* for sequential append operations just spill over into the new node */ if (*pos == KEYS_PER_NODE) { *nodep = new; *pos = 0; *nr_entries = 0; goto done; } for (i = 0; i < nr_move; i++) { new->keys[i] = node->keys[nr_keep + i]; new->ptrs[i] = node->ptrs[nr_keep + i]; node->keys[nr_keep + i] = XFS_IEXT_KEY_INVALID; node->ptrs[nr_keep + i] = NULL; } if (*pos >= nr_keep) { *nodep = new; *pos -= nr_keep; *nr_entries = nr_move; } else { *nr_entries = nr_keep; } done: for (; i < KEYS_PER_NODE; i++) new->keys[i] = XFS_IEXT_KEY_INVALID; return new; } static void xfs_iext_insert_node( struct xfs_ifork *ifp, uint64_t offset, void *ptr, int level) { struct xfs_iext_node *node, *new; int i, pos, nr_entries; again: if (ifp->if_height < level) xfs_iext_grow(ifp); new = NULL; node = xfs_iext_find_level(ifp, offset, level); pos = xfs_iext_node_insert_pos(node, offset); nr_entries = xfs_iext_node_nr_entries(node, pos); ASSERT(pos >= nr_entries || xfs_iext_key_cmp(node, pos, offset) != 0); ASSERT(nr_entries <= KEYS_PER_NODE); if (nr_entries == KEYS_PER_NODE) new = xfs_iext_split_node(&node, &pos, &nr_entries); /* * Update the pointers in higher levels if the first entry changes * in an existing node. */ if (node != new && pos == 0 && nr_entries > 0) xfs_iext_update_node(ifp, node->keys[0], offset, level, node); for (i = nr_entries; i > pos; i--) { node->keys[i] = node->keys[i - 1]; node->ptrs[i] = node->ptrs[i - 1]; } node->keys[pos] = offset; node->ptrs[pos] = ptr; if (new) { offset = new->keys[0]; ptr = new; level++; goto again; } } static struct xfs_iext_leaf * xfs_iext_split_leaf( struct xfs_iext_cursor *cur, int *nr_entries) { struct xfs_iext_leaf *leaf = cur->leaf; struct xfs_iext_leaf *new = xfs_iext_alloc_node(NODE_SIZE); const int nr_move = RECS_PER_LEAF / 2; int nr_keep = nr_move + (RECS_PER_LEAF & 1); int i; /* for sequential append operations just spill over into the new node */ if (cur->pos == RECS_PER_LEAF) { cur->leaf = new; cur->pos = 0; *nr_entries = 0; goto done; } for (i = 0; i < nr_move; i++) { new->recs[i] = leaf->recs[nr_keep + i]; xfs_iext_rec_clear(&leaf->recs[nr_keep + i]); } if (cur->pos >= nr_keep) { cur->leaf = new; cur->pos -= nr_keep; *nr_entries = nr_move; } else { *nr_entries = nr_keep; } done: if (leaf->next) leaf->next->prev = new; new->next = leaf->next; new->prev = leaf; leaf->next = new; return new; } static void xfs_iext_alloc_root( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { ASSERT(ifp->if_bytes == 0); ifp->if_data = xfs_iext_alloc_node(sizeof(struct xfs_iext_rec)); ifp->if_height = 1; /* now that we have a node step into it */ cur->leaf = ifp->if_data; cur->pos = 0; } static void xfs_iext_realloc_root( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { int64_t new_size = ifp->if_bytes + sizeof(struct xfs_iext_rec); void *new; /* account for the prev/next pointers */ if (new_size / sizeof(struct xfs_iext_rec) == RECS_PER_LEAF) new_size = NODE_SIZE; new = krealloc(ifp->if_data, new_size, GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL); memset(new + ifp->if_bytes, 0, new_size - ifp->if_bytes); ifp->if_data = new; cur->leaf = new; } /* * Increment the sequence counter on extent tree changes. If we are on a COW * fork, this allows the writeback code to skip looking for a COW extent if the * COW fork hasn't changed. We use WRITE_ONCE here to ensure the update to the * sequence counter is seen before the modifications to the extent tree itself * take effect. */ static inline void xfs_iext_inc_seq(struct xfs_ifork *ifp) { WRITE_ONCE(ifp->if_seq, READ_ONCE(ifp->if_seq) + 1); } void xfs_iext_insert_raw( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *irec) { xfs_fileoff_t offset = irec->br_startoff; struct xfs_iext_leaf *new = NULL; int nr_entries, i; xfs_iext_inc_seq(ifp); if (ifp->if_height == 0) xfs_iext_alloc_root(ifp, cur); else if (ifp->if_height == 1) xfs_iext_realloc_root(ifp, cur); nr_entries = xfs_iext_leaf_nr_entries(ifp, cur->leaf, cur->pos); ASSERT(nr_entries <= RECS_PER_LEAF); ASSERT(cur->pos >= nr_entries || xfs_iext_rec_cmp(cur_rec(cur), irec->br_startoff) != 0); if (nr_entries == RECS_PER_LEAF) new = xfs_iext_split_leaf(cur, &nr_entries); /* * Update the pointers in higher levels if the first entry changes * in an existing node. */ if (cur->leaf != new && cur->pos == 0 && nr_entries > 0) { xfs_iext_update_node(ifp, xfs_iext_leaf_key(cur->leaf, 0), offset, 1, cur->leaf); } for (i = nr_entries; i > cur->pos; i--) cur->leaf->recs[i] = cur->leaf->recs[i - 1]; xfs_iext_set(cur_rec(cur), irec); ifp->if_bytes += sizeof(struct xfs_iext_rec); if (new) xfs_iext_insert_node(ifp, xfs_iext_leaf_key(new, 0), new, 2); } void xfs_iext_insert( struct xfs_inode *ip, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *irec, int state) { struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state); xfs_iext_insert_raw(ifp, cur, irec); trace_xfs_iext_insert(ip, cur, state, _RET_IP_); } static struct xfs_iext_node * xfs_iext_rebalance_node( struct xfs_iext_node *parent, int *pos, struct xfs_iext_node *node, int nr_entries) { /* * If the neighbouring nodes are completely full, or have different * parents, we might never be able to merge our node, and will only * delete it once the number of entries hits zero. */ if (nr_entries == 0) return node; if (*pos > 0) { struct xfs_iext_node *prev = parent->ptrs[*pos - 1]; int nr_prev = xfs_iext_node_nr_entries(prev, 0), i; if (nr_prev + nr_entries <= KEYS_PER_NODE) { for (i = 0; i < nr_entries; i++) { prev->keys[nr_prev + i] = node->keys[i]; prev->ptrs[nr_prev + i] = node->ptrs[i]; } return node; } } if (*pos + 1 < xfs_iext_node_nr_entries(parent, *pos)) { struct xfs_iext_node *next = parent->ptrs[*pos + 1]; int nr_next = xfs_iext_node_nr_entries(next, 0), i; if (nr_entries + nr_next <= KEYS_PER_NODE) { /* * Merge the next node into this node so that we don't * have to do an additional update of the keys in the * higher levels. */ for (i = 0; i < nr_next; i++) { node->keys[nr_entries + i] = next->keys[i]; node->ptrs[nr_entries + i] = next->ptrs[i]; } ++*pos; return next; } } return NULL; } static void xfs_iext_remove_node( struct xfs_ifork *ifp, xfs_fileoff_t offset, void *victim) { struct xfs_iext_node *node, *parent; int level = 2, pos, nr_entries, i; ASSERT(level <= ifp->if_height); node = xfs_iext_find_level(ifp, offset, level); pos = xfs_iext_node_pos(node, offset); again: ASSERT(node->ptrs[pos]); ASSERT(node->ptrs[pos] == victim); kfree(victim); nr_entries = xfs_iext_node_nr_entries(node, pos) - 1; offset = node->keys[0]; for (i = pos; i < nr_entries; i++) { node->keys[i] = node->keys[i + 1]; node->ptrs[i] = node->ptrs[i + 1]; } node->keys[nr_entries] = XFS_IEXT_KEY_INVALID; node->ptrs[nr_entries] = NULL; if (pos == 0 && nr_entries > 0) { xfs_iext_update_node(ifp, offset, node->keys[0], level, node); offset = node->keys[0]; } if (nr_entries >= KEYS_PER_NODE / 2) return; if (level < ifp->if_height) { /* * If we aren't at the root yet try to find a neighbour node to * merge with (or delete the node if it is empty), and then * recurse up to the next level. */ level++; parent = xfs_iext_find_level(ifp, offset, level); pos = xfs_iext_node_pos(parent, offset); ASSERT(pos != KEYS_PER_NODE); ASSERT(parent->ptrs[pos] == node); node = xfs_iext_rebalance_node(parent, &pos, node, nr_entries); if (node) { victim = node; node = parent; goto again; } } else if (nr_entries == 1) { /* * If we are at the root and only one entry is left we can just * free this node and update the root pointer. */ ASSERT(node == ifp->if_data); ifp->if_data = node->ptrs[0]; ifp->if_height--; kfree(node); } } static void xfs_iext_rebalance_leaf( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur, struct xfs_iext_leaf *leaf, xfs_fileoff_t offset, int nr_entries) { /* * If the neighbouring nodes are completely full we might never be able * to merge our node, and will only delete it once the number of * entries hits zero. */ if (nr_entries == 0) goto remove_node; if (leaf->prev) { int nr_prev = xfs_iext_leaf_nr_entries(ifp, leaf->prev, 0), i; if (nr_prev + nr_entries <= RECS_PER_LEAF) { for (i = 0; i < nr_entries; i++) leaf->prev->recs[nr_prev + i] = leaf->recs[i]; if (cur->leaf == leaf) { cur->leaf = leaf->prev; cur->pos += nr_prev; } goto remove_node; } } if (leaf->next) { int nr_next = xfs_iext_leaf_nr_entries(ifp, leaf->next, 0), i; if (nr_entries + nr_next <= RECS_PER_LEAF) { /* * Merge the next node into this node so that we don't * have to do an additional update of the keys in the * higher levels. */ for (i = 0; i < nr_next; i++) { leaf->recs[nr_entries + i] = leaf->next->recs[i]; } if (cur->leaf == leaf->next) { cur->leaf = leaf; cur->pos += nr_entries; } offset = xfs_iext_leaf_key(leaf->next, 0); leaf = leaf->next; goto remove_node; } } return; remove_node: if (leaf->prev) leaf->prev->next = leaf->next; if (leaf->next) leaf->next->prev = leaf->prev; xfs_iext_remove_node(ifp, offset, leaf); } static void xfs_iext_free_last_leaf( struct xfs_ifork *ifp) { ifp->if_height--; kfree(ifp->if_data); ifp->if_data = NULL; } void xfs_iext_remove( struct xfs_inode *ip, struct xfs_iext_cursor *cur, int state) { struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state); struct xfs_iext_leaf *leaf = cur->leaf; xfs_fileoff_t offset = xfs_iext_leaf_key(leaf, 0); int i, nr_entries; trace_xfs_iext_remove(ip, cur, state, _RET_IP_); ASSERT(ifp->if_height > 0); ASSERT(ifp->if_data != NULL); ASSERT(xfs_iext_valid(ifp, cur)); xfs_iext_inc_seq(ifp); nr_entries = xfs_iext_leaf_nr_entries(ifp, leaf, cur->pos) - 1; for (i = cur->pos; i < nr_entries; i++) leaf->recs[i] = leaf->recs[i + 1]; xfs_iext_rec_clear(&leaf->recs[nr_entries]); ifp->if_bytes -= sizeof(struct xfs_iext_rec); if (cur->pos == 0 && nr_entries > 0) { xfs_iext_update_node(ifp, offset, xfs_iext_leaf_key(leaf, 0), 1, leaf); offset = xfs_iext_leaf_key(leaf, 0); } else if (cur->pos == nr_entries) { if (ifp->if_height > 1 && leaf->next) cur->leaf = leaf->next; else cur->leaf = NULL; cur->pos = 0; } if (nr_entries >= RECS_PER_LEAF / 2) return; if (ifp->if_height > 1) xfs_iext_rebalance_leaf(ifp, cur, leaf, offset, nr_entries); else if (nr_entries == 0) xfs_iext_free_last_leaf(ifp); } /* * Lookup the extent covering bno. * * If there is an extent covering bno return the extent index, and store the * expanded extent structure in *gotp, and the extent cursor in *cur. * If there is no extent covering bno, but there is an extent after it (e.g. * it lies in a hole) return that extent in *gotp and its cursor in *cur * instead. * If bno is beyond the last extent return false, and return an invalid * cursor value. */ bool xfs_iext_lookup_extent( struct xfs_inode *ip, struct xfs_ifork *ifp, xfs_fileoff_t offset, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *gotp) { XFS_STATS_INC(ip->i_mount, xs_look_exlist); cur->leaf = xfs_iext_find_level(ifp, offset, 1); if (!cur->leaf) { cur->pos = 0; return false; } for (cur->pos = 0; cur->pos < xfs_iext_max_recs(ifp); cur->pos++) { struct xfs_iext_rec *rec = cur_rec(cur); if (xfs_iext_rec_is_empty(rec)) break; if (xfs_iext_rec_cmp(rec, offset) >= 0) goto found; } /* Try looking in the next node for an entry > offset */ if (ifp->if_height == 1 || !cur->leaf->next) return false; cur->leaf = cur->leaf->next; cur->pos = 0; if (!xfs_iext_valid(ifp, cur)) return false; found: xfs_iext_get(gotp, cur_rec(cur)); return true; } /* * Returns the last extent before end, and if this extent doesn't cover * end, update end to the end of the extent. */ bool xfs_iext_lookup_extent_before( struct xfs_inode *ip, struct xfs_ifork *ifp, xfs_fileoff_t *end, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *gotp) { /* could be optimized to not even look up the next on a match.. */ if (xfs_iext_lookup_extent(ip, ifp, *end - 1, cur, gotp) && gotp->br_startoff <= *end - 1) return true; if (!xfs_iext_prev_extent(ifp, cur, gotp)) return false; *end = gotp->br_startoff + gotp->br_blockcount; return true; } void xfs_iext_update_extent( struct xfs_inode *ip, int state, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *new) { struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state); xfs_iext_inc_seq(ifp); if (cur->pos == 0) { struct xfs_bmbt_irec old; xfs_iext_get(&old, cur_rec(cur)); if (new->br_startoff != old.br_startoff) { xfs_iext_update_node(ifp, old.br_startoff, new->br_startoff, 1, cur->leaf); } } trace_xfs_bmap_pre_update(ip, cur, state, _RET_IP_); xfs_iext_set(cur_rec(cur), new); trace_xfs_bmap_post_update(ip, cur, state, _RET_IP_); } /* * Return true if the cursor points at an extent and return the extent structure * in gotp. Else return false. */ bool xfs_iext_get_extent( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *gotp) { if (!xfs_iext_valid(ifp, cur)) return false; xfs_iext_get(gotp, cur_rec(cur)); return true; } /* * This is a recursive function, because of that we need to be extremely * careful with stack usage. */ static void xfs_iext_destroy_node( struct xfs_iext_node *node, int level) { int i; if (level > 1) { for (i = 0; i < KEYS_PER_NODE; i++) { if (node->keys[i] == XFS_IEXT_KEY_INVALID) break; xfs_iext_destroy_node(node->ptrs[i], level - 1); } } kfree(node); } void xfs_iext_destroy( struct xfs_ifork *ifp) { xfs_iext_destroy_node(ifp->if_data, ifp->if_height); ifp->if_bytes = 0; ifp->if_height = 0; ifp->if_data = NULL; } |
| 4 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 | // SPDX-License-Identifier: GPL-2.0 /* * Support for async notification of waitid */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/compat.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "cancel.h" #include "waitid.h" #include "../kernel/exit.h" static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts); #define IO_WAITID_CANCEL_FLAG BIT(31) #define IO_WAITID_REF_MASK GENMASK(30, 0) struct io_waitid { struct file *file; int which; pid_t upid; int options; atomic_t refs; struct wait_queue_head *head; struct siginfo __user *infop; struct waitid_info info; }; static void io_waitid_free(struct io_kiocb *req) { struct io_waitid_async *iwa = req->async_data; put_pid(iwa->wo.wo_pid); kfree(req->async_data); req->async_data = NULL; req->flags &= ~REQ_F_ASYNC_DATA; } #ifdef CONFIG_COMPAT static bool io_waitid_compat_copy_si(struct io_waitid *iw, int signo) { struct compat_siginfo __user *infop; bool ret; infop = (struct compat_siginfo __user *) iw->infop; if (!user_write_access_begin(infop, sizeof(*infop))) return false; unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(iw->info.cause, &infop->si_code, Efault); unsafe_put_user(iw->info.pid, &infop->si_pid, Efault); unsafe_put_user(iw->info.uid, &infop->si_uid, Efault); unsafe_put_user(iw->info.status, &infop->si_status, Efault); ret = true; done: user_write_access_end(); return ret; Efault: ret = false; goto done; } #endif static bool io_waitid_copy_si(struct io_kiocb *req, int signo) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); bool ret; if (!iw->infop) return true; #ifdef CONFIG_COMPAT if (req->ctx->compat) return io_waitid_compat_copy_si(iw, signo); #endif if (!user_write_access_begin(iw->infop, sizeof(*iw->infop))) return false; unsafe_put_user(signo, &iw->infop->si_signo, Efault); unsafe_put_user(0, &iw->infop->si_errno, Efault); unsafe_put_user(iw->info.cause, &iw->infop->si_code, Efault); unsafe_put_user(iw->info.pid, &iw->infop->si_pid, Efault); unsafe_put_user(iw->info.uid, &iw->infop->si_uid, Efault); unsafe_put_user(iw->info.status, &iw->infop->si_status, Efault); ret = true; done: user_write_access_end(); return ret; Efault: ret = false; goto done; } static int io_waitid_finish(struct io_kiocb *req, int ret) { int signo = 0; if (ret > 0) { signo = SIGCHLD; ret = 0; } if (!io_waitid_copy_si(req, signo)) ret = -EFAULT; io_waitid_free(req); return ret; } static void io_waitid_complete(struct io_kiocb *req, int ret) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); struct io_tw_state ts = {}; /* anyone completing better be holding a reference */ WARN_ON_ONCE(!(atomic_read(&iw->refs) & IO_WAITID_REF_MASK)); lockdep_assert_held(&req->ctx->uring_lock); hlist_del_init(&req->hash_node); ret = io_waitid_finish(req, ret); if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0); io_req_task_complete(req, &ts); } static bool __io_waitid_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); struct io_waitid_async *iwa = req->async_data; /* * Mark us canceled regardless of ownership. This will prevent a * potential retry from a spurious wakeup. */ atomic_or(IO_WAITID_CANCEL_FLAG, &iw->refs); /* claim ownership */ if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK) return false; spin_lock_irq(&iw->head->lock); list_del_init(&iwa->wo.child_wait.entry); spin_unlock_irq(&iw->head->lock); io_waitid_complete(req, -ECANCELED); return true; } int io_waitid_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd, unsigned int issue_flags) { struct hlist_node *tmp; struct io_kiocb *req; int nr = 0; if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_FD_FIXED)) return -ENOENT; io_ring_submit_lock(ctx, issue_flags); hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) { if (req->cqe.user_data != cd->data && !(cd->flags & IORING_ASYNC_CANCEL_ANY)) continue; if (__io_waitid_cancel(ctx, req)) nr++; if (!(cd->flags & IORING_ASYNC_CANCEL_ALL)) break; } io_ring_submit_unlock(ctx, issue_flags); if (nr) return nr; return -ENOENT; } bool io_waitid_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx, bool cancel_all) { struct hlist_node *tmp; struct io_kiocb *req; bool found = false; lockdep_assert_held(&ctx->uring_lock); hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) { if (!io_match_task_safe(req, tctx, cancel_all)) continue; hlist_del_init(&req->hash_node); __io_waitid_cancel(ctx, req); found = true; } return found; } static inline bool io_waitid_drop_issue_ref(struct io_kiocb *req) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); struct io_waitid_async *iwa = req->async_data; if (!atomic_sub_return(1, &iw->refs)) return false; /* * Wakeup triggered, racing with us. It was prevented from * completing because of that, queue up the tw to do that. */ req->io_task_work.func = io_waitid_cb; io_req_task_work_add(req); remove_wait_queue(iw->head, &iwa->wo.child_wait); return true; } static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts) { struct io_waitid_async *iwa = req->async_data; struct io_ring_ctx *ctx = req->ctx; int ret; io_tw_lock(ctx, ts); ret = __do_wait(&iwa->wo); /* * If we get -ERESTARTSYS here, we need to re-arm and check again * to ensure we get another callback. If the retry works, then we can * just remove ourselves from the waitqueue again and finish the * request. */ if (unlikely(ret == -ERESTARTSYS)) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); /* Don't retry if cancel found it meanwhile */ ret = -ECANCELED; if (!(atomic_read(&iw->refs) & IO_WAITID_CANCEL_FLAG)) { iw->head = ¤t->signal->wait_chldexit; add_wait_queue(iw->head, &iwa->wo.child_wait); ret = __do_wait(&iwa->wo); if (ret == -ERESTARTSYS) { /* retry armed, drop our ref */ io_waitid_drop_issue_ref(req); return; } remove_wait_queue(iw->head, &iwa->wo.child_wait); } } io_waitid_complete(req, ret); } static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode, int sync, void *key) { struct wait_opts *wo = container_of(wait, struct wait_opts, child_wait); struct io_waitid_async *iwa = container_of(wo, struct io_waitid_async, wo); struct io_kiocb *req = iwa->req; struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); struct task_struct *p = key; if (!pid_child_should_wake(wo, p)) return 0; /* cancel is in progress */ if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK) return 1; req->io_task_work.func = io_waitid_cb; io_req_task_work_add(req); list_del_init(&wait->entry); return 1; } int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); if (sqe->addr || sqe->buf_index || sqe->addr3 || sqe->waitid_flags) return -EINVAL; iw->which = READ_ONCE(sqe->len); iw->upid = READ_ONCE(sqe->fd); iw->options = READ_ONCE(sqe->file_index); iw->infop = u64_to_user_ptr(READ_ONCE(sqe->addr2)); return 0; } int io_waitid(struct io_kiocb *req, unsigned int issue_flags) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); struct io_ring_ctx *ctx = req->ctx; struct io_waitid_async *iwa; int ret; if (io_alloc_async_data(req)) return -ENOMEM; iwa = req->async_data; iwa->req = req; ret = kernel_waitid_prepare(&iwa->wo, iw->which, iw->upid, &iw->info, iw->options, NULL); if (ret) goto done; /* * Mark the request as busy upfront, in case we're racing with the * wakeup. If we are, then we'll notice when we drop this initial * reference again after arming. */ atomic_set(&iw->refs, 1); /* * Cancel must hold the ctx lock, so there's no risk of cancelation * finding us until a) we remain on the list, and b) the lock is * dropped. We only need to worry about racing with the wakeup * callback. */ io_ring_submit_lock(ctx, issue_flags); hlist_add_head(&req->hash_node, &ctx->waitid_list); init_waitqueue_func_entry(&iwa->wo.child_wait, io_waitid_wait); iwa->wo.child_wait.private = req->tctx->task; iw->head = ¤t->signal->wait_chldexit; add_wait_queue(iw->head, &iwa->wo.child_wait); ret = __do_wait(&iwa->wo); if (ret == -ERESTARTSYS) { /* * Nobody else grabbed a reference, it'll complete when we get * a waitqueue callback, or if someone cancels it. */ if (!io_waitid_drop_issue_ref(req)) { io_ring_submit_unlock(ctx, issue_flags); return IOU_ISSUE_SKIP_COMPLETE; } /* * Wakeup triggered, racing with us. It was prevented from * completing because of that, queue up the tw to do that. */ io_ring_submit_unlock(ctx, issue_flags); return IOU_ISSUE_SKIP_COMPLETE; } hlist_del_init(&req->hash_node); remove_wait_queue(iw->head, &iwa->wo.child_wait); ret = io_waitid_finish(req, ret); io_ring_submit_unlock(ctx, issue_flags); done: if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0); return IOU_OK; } |
| 38 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) 2002, 2004, 2005 Oracle. All rights reserved. */ #ifndef OCFS2_AOPS_H #define OCFS2_AOPS_H #include <linux/fs.h> handle_t *ocfs2_start_walk_page_trans(struct inode *inode, struct page *page, unsigned from, unsigned to); int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno, struct inode *inode, unsigned int from, unsigned int to, int new); void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages); int walk_page_buffers( handle_t *handle, struct buffer_head *head, unsigned from, unsigned to, int *partial, int (*fn)( handle_t *handle, struct buffer_head *bh)); int ocfs2_write_end_nolock(struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, void *fsdata); typedef enum { OCFS2_WRITE_BUFFER = 0, OCFS2_WRITE_DIRECT, OCFS2_WRITE_MMAP, } ocfs2_write_type_t; int ocfs2_write_begin_nolock(struct address_space *mapping, loff_t pos, unsigned len, ocfs2_write_type_t type, struct folio **foliop, void **fsdata, struct buffer_head *di_bh, struct page *mmap_page); int ocfs2_read_inline_data(struct inode *inode, struct page *page, struct buffer_head *di_bh); int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size); int ocfs2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); /* all ocfs2_dio_end_io()'s fault */ #define ocfs2_iocb_is_rw_locked(iocb) \ test_bit(0, (unsigned long *)&iocb->private) static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level) { set_bit(0, (unsigned long *)&iocb->private); if (level) set_bit(1, (unsigned long *)&iocb->private); else clear_bit(1, (unsigned long *)&iocb->private); } /* * Using a named enum representing lock types in terms of #N bit stored in * iocb->private, which is going to be used for communication between * ocfs2_dio_end_io() and ocfs2_file_write/read_iter(). */ enum ocfs2_iocb_lock_bits { OCFS2_IOCB_RW_LOCK = 0, OCFS2_IOCB_RW_LOCK_LEVEL, OCFS2_IOCB_NUM_LOCKS }; #define ocfs2_iocb_clear_rw_locked(iocb) \ clear_bit(OCFS2_IOCB_RW_LOCK, (unsigned long *)&iocb->private) #define ocfs2_iocb_rw_locked_level(iocb) \ test_bit(OCFS2_IOCB_RW_LOCK_LEVEL, (unsigned long *)&iocb->private) #endif /* OCFS2_FILE_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. */ /* * Quota change tags are associated with each transaction that allocates or * deallocates space. Those changes are accumulated locally to each node (in a * per-node file) and then are periodically synced to the quota file. This * avoids the bottleneck of constantly touching the quota file, but introduces * fuzziness in the current usage value of IDs that are being used on different * nodes in the cluster simultaneously. So, it is possible for a user on * multiple nodes to overrun their quota, but that overrun is controlable. * Since quota tags are part of transactions, there is no need for a quota check * program to be run on node crashes or anything like that. * * There are couple of knobs that let the administrator manage the quota * fuzziness. "quota_quantum" sets the maximum time a quota change can be * sitting on one node before being synced to the quota file. (The default is * 60 seconds.) Another knob, "quota_scale" controls how quickly the frequency * of quota file syncs increases as the user moves closer to their limit. The * more frequent the syncs, the more accurate the quota enforcement, but that * means that there is more contention between the nodes for the quota file. * The default value is one. This sets the maximum theoretical quota overrun * (with infinite node with infinite bandwidth) to twice the user's limit. (In * practice, the maximum overrun you see should be much less.) A "quota_scale" * number greater than one makes quota syncs more frequent and reduces the * maximum overrun. Numbers less than one (but greater than zero) make quota * syncs less frequent. * * GFS quotas also use per-ID Lock Value Blocks (LVBs) to cache the contents of * the quota file, so it is not being constantly read. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/sched.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/buffer_head.h> #include <linux/sort.h> #include <linux/fs.h> #include <linux/bio.h> #include <linux/gfs2_ondisk.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/quota.h> #include <linux/dqblk_xfs.h> #include <linux/lockref.h> #include <linux/list_lru.h> #include <linux/rcupdate.h> #include <linux/rculist_bl.h> #include <linux/bit_spinlock.h> #include <linux/jhash.h> #include <linux/vmalloc.h> #include "gfs2.h" #include "incore.h" #include "bmap.h" #include "glock.h" #include "glops.h" #include "log.h" #include "meta_io.h" #include "quota.h" #include "rgrp.h" #include "super.h" #include "trans.h" #include "inode.h" #include "util.h" #define GFS2_QD_HASH_SHIFT 12 #define GFS2_QD_HASH_SIZE BIT(GFS2_QD_HASH_SHIFT) #define GFS2_QD_HASH_MASK (GFS2_QD_HASH_SIZE - 1) /* Lock order: qd_lock -> bucket lock -> qd->lockref.lock -> lru lock */ /* -> sd_bitmap_lock */ static DEFINE_SPINLOCK(qd_lock); struct list_lru gfs2_qd_lru; static struct hlist_bl_head qd_hash_table[GFS2_QD_HASH_SIZE]; static unsigned int gfs2_qd_hash(const struct gfs2_sbd *sdp, const struct kqid qid) { unsigned int h; h = jhash(&sdp, sizeof(struct gfs2_sbd *), 0); h = jhash(&qid, sizeof(struct kqid), h); return h & GFS2_QD_HASH_MASK; } static inline void spin_lock_bucket(unsigned int hash) { hlist_bl_lock(&qd_hash_table[hash]); } static inline void spin_unlock_bucket(unsigned int hash) { hlist_bl_unlock(&qd_hash_table[hash]); } static void gfs2_qd_dealloc(struct rcu_head *rcu) { struct gfs2_quota_data *qd = container_of(rcu, struct gfs2_quota_data, qd_rcu); struct gfs2_sbd *sdp = qd->qd_sbd; kmem_cache_free(gfs2_quotad_cachep, qd); if (atomic_dec_and_test(&sdp->sd_quota_count)) wake_up(&sdp->sd_kill_wait); } static void gfs2_qd_dispose(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; spin_lock(&qd_lock); list_del(&qd->qd_list); spin_unlock(&qd_lock); spin_lock_bucket(qd->qd_hash); hlist_bl_del_rcu(&qd->qd_hlist); spin_unlock_bucket(qd->qd_hash); if (!gfs2_withdrawing_or_withdrawn(sdp)) { gfs2_assert_warn(sdp, !qd->qd_change); gfs2_assert_warn(sdp, !qd->qd_slot_ref); gfs2_assert_warn(sdp, !qd->qd_bh_count); } gfs2_glock_put(qd->qd_gl); call_rcu(&qd->qd_rcu, gfs2_qd_dealloc); } static void gfs2_qd_list_dispose(struct list_head *list) { struct gfs2_quota_data *qd; while (!list_empty(list)) { qd = list_first_entry(list, struct gfs2_quota_data, qd_lru); list_del(&qd->qd_lru); gfs2_qd_dispose(qd); } } static enum lru_status gfs2_qd_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *dispose = arg; struct gfs2_quota_data *qd = list_entry(item, struct gfs2_quota_data, qd_lru); enum lru_status status; if (!spin_trylock(&qd->qd_lockref.lock)) return LRU_SKIP; status = LRU_SKIP; if (qd->qd_lockref.count == 0) { lockref_mark_dead(&qd->qd_lockref); list_lru_isolate_move(lru, &qd->qd_lru, dispose); status = LRU_REMOVED; } spin_unlock(&qd->qd_lockref.lock); return status; } static unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { LIST_HEAD(dispose); unsigned long freed; if (!(sc->gfp_mask & __GFP_FS)) return SHRINK_STOP; freed = list_lru_shrink_walk(&gfs2_qd_lru, sc, gfs2_qd_isolate, &dispose); gfs2_qd_list_dispose(&dispose); return freed; } static unsigned long gfs2_qd_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { return vfs_pressure_ratio(list_lru_shrink_count(&gfs2_qd_lru, sc)); } static struct shrinker *gfs2_qd_shrinker; int __init gfs2_qd_shrinker_init(void) { gfs2_qd_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE, "gfs2-qd"); if (!gfs2_qd_shrinker) return -ENOMEM; gfs2_qd_shrinker->count_objects = gfs2_qd_shrink_count; gfs2_qd_shrinker->scan_objects = gfs2_qd_shrink_scan; shrinker_register(gfs2_qd_shrinker); return 0; } void gfs2_qd_shrinker_exit(void) { shrinker_free(gfs2_qd_shrinker); } static u64 qd2index(struct gfs2_quota_data *qd) { struct kqid qid = qd->qd_id; return (2 * (u64)from_kqid(&init_user_ns, qid)) + ((qid.type == USRQUOTA) ? 0 : 1); } static u64 qd2offset(struct gfs2_quota_data *qd) { return qd2index(qd) * sizeof(struct gfs2_quota); } static struct gfs2_quota_data *qd_alloc(unsigned hash, struct gfs2_sbd *sdp, struct kqid qid) { struct gfs2_quota_data *qd; int error; qd = kmem_cache_zalloc(gfs2_quotad_cachep, GFP_NOFS); if (!qd) return NULL; qd->qd_sbd = sdp; qd->qd_lockref.count = 0; spin_lock_init(&qd->qd_lockref.lock); qd->qd_id = qid; qd->qd_slot = -1; INIT_LIST_HEAD(&qd->qd_lru); qd->qd_hash = hash; error = gfs2_glock_get(sdp, qd2index(qd), &gfs2_quota_glops, CREATE, &qd->qd_gl); if (error) goto fail; return qd; fail: kmem_cache_free(gfs2_quotad_cachep, qd); return NULL; } static struct gfs2_quota_data *gfs2_qd_search_bucket(unsigned int hash, const struct gfs2_sbd *sdp, struct kqid qid) { struct gfs2_quota_data *qd; struct hlist_bl_node *h; hlist_bl_for_each_entry_rcu(qd, h, &qd_hash_table[hash], qd_hlist) { if (!qid_eq(qd->qd_id, qid)) continue; if (qd->qd_sbd != sdp) continue; if (lockref_get_not_dead(&qd->qd_lockref)) { list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru); return qd; } } return NULL; } static int qd_get(struct gfs2_sbd *sdp, struct kqid qid, struct gfs2_quota_data **qdp) { struct gfs2_quota_data *qd, *new_qd; unsigned int hash = gfs2_qd_hash(sdp, qid); rcu_read_lock(); *qdp = qd = gfs2_qd_search_bucket(hash, sdp, qid); rcu_read_unlock(); if (qd) return 0; new_qd = qd_alloc(hash, sdp, qid); if (!new_qd) return -ENOMEM; spin_lock(&qd_lock); spin_lock_bucket(hash); *qdp = qd = gfs2_qd_search_bucket(hash, sdp, qid); if (qd == NULL) { new_qd->qd_lockref.count++; *qdp = new_qd; list_add(&new_qd->qd_list, &sdp->sd_quota_list); hlist_bl_add_head_rcu(&new_qd->qd_hlist, &qd_hash_table[hash]); atomic_inc(&sdp->sd_quota_count); } spin_unlock_bucket(hash); spin_unlock(&qd_lock); if (qd) { gfs2_glock_put(new_qd->qd_gl); kmem_cache_free(gfs2_quotad_cachep, new_qd); } return 0; } static void __qd_hold(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; gfs2_assert(sdp, qd->qd_lockref.count > 0); qd->qd_lockref.count++; } static void qd_put(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp; if (lockref_put_or_lock(&qd->qd_lockref)) return; BUG_ON(__lockref_is_dead(&qd->qd_lockref)); sdp = qd->qd_sbd; if (unlikely(!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))) { lockref_mark_dead(&qd->qd_lockref); spin_unlock(&qd->qd_lockref.lock); gfs2_qd_dispose(qd); return; } qd->qd_lockref.count = 0; list_lru_add_obj(&gfs2_qd_lru, &qd->qd_lru); spin_unlock(&qd->qd_lockref.lock); } static int slot_get(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; unsigned int bit; int error = 0; spin_lock(&sdp->sd_bitmap_lock); if (qd->qd_slot_ref == 0) { bit = find_first_zero_bit(sdp->sd_quota_bitmap, sdp->sd_quota_slots); if (bit >= sdp->sd_quota_slots) { error = -ENOSPC; goto out; } set_bit(bit, sdp->sd_quota_bitmap); qd->qd_slot = bit; } qd->qd_slot_ref++; out: spin_unlock(&sdp->sd_bitmap_lock); return error; } static void slot_hold(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; spin_lock(&sdp->sd_bitmap_lock); gfs2_assert(sdp, qd->qd_slot_ref); qd->qd_slot_ref++; spin_unlock(&sdp->sd_bitmap_lock); } static void slot_put(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; spin_lock(&sdp->sd_bitmap_lock); gfs2_assert(sdp, qd->qd_slot_ref); if (!--qd->qd_slot_ref) { BUG_ON(!test_and_clear_bit(qd->qd_slot, sdp->sd_quota_bitmap)); qd->qd_slot = -1; } spin_unlock(&sdp->sd_bitmap_lock); } static int bh_get(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; struct inode *inode = sdp->sd_qc_inode; struct gfs2_inode *ip = GFS2_I(inode); unsigned int block, offset; struct buffer_head *bh = NULL; struct iomap iomap = { }; int error; spin_lock(&qd->qd_lockref.lock); if (qd->qd_bh_count) { qd->qd_bh_count++; spin_unlock(&qd->qd_lockref.lock); return 0; } spin_unlock(&qd->qd_lockref.lock); block = qd->qd_slot / sdp->sd_qc_per_block; offset = qd->qd_slot % sdp->sd_qc_per_block; error = gfs2_iomap_get(inode, (loff_t)block << inode->i_blkbits, i_blocksize(inode), &iomap); if (error) return error; error = -ENOENT; if (iomap.type != IOMAP_MAPPED) return error; error = gfs2_meta_read(ip->i_gl, iomap.addr >> inode->i_blkbits, DIO_WAIT, 0, &bh); if (error) return error; error = -EIO; if (gfs2_metatype_check(sdp, bh, GFS2_METATYPE_QC)) goto out; spin_lock(&qd->qd_lockref.lock); if (qd->qd_bh == NULL) { qd->qd_bh = bh; qd->qd_bh_qc = (struct gfs2_quota_change *) (bh->b_data + sizeof(struct gfs2_meta_header) + offset * sizeof(struct gfs2_quota_change)); bh = NULL; } qd->qd_bh_count++; spin_unlock(&qd->qd_lockref.lock); error = 0; out: brelse(bh); return error; } static void bh_put(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; struct buffer_head *bh = NULL; spin_lock(&qd->qd_lockref.lock); gfs2_assert(sdp, qd->qd_bh_count); if (!--qd->qd_bh_count) { bh = qd->qd_bh; qd->qd_bh = NULL; qd->qd_bh_qc = NULL; } spin_unlock(&qd->qd_lockref.lock); brelse(bh); } static bool qd_grab_sync(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd, u64 sync_gen) { bool ret = false; spin_lock(&qd->qd_lockref.lock); if (test_bit(QDF_LOCKED, &qd->qd_flags) || !test_bit(QDF_CHANGE, &qd->qd_flags) || qd->qd_sync_gen >= sync_gen) goto out; if (__lockref_is_dead(&qd->qd_lockref)) goto out; qd->qd_lockref.count++; list_move_tail(&qd->qd_list, &sdp->sd_quota_list); set_bit(QDF_LOCKED, &qd->qd_flags); qd->qd_change_sync = qd->qd_change; slot_hold(qd); ret = true; out: spin_unlock(&qd->qd_lockref.lock); return ret; } static void qd_ungrab_sync(struct gfs2_quota_data *qd) { clear_bit(QDF_LOCKED, &qd->qd_flags); slot_put(qd); qd_put(qd); } static void qdsb_put(struct gfs2_quota_data *qd) { bh_put(qd); slot_put(qd); qd_put(qd); } static void qd_unlock(struct gfs2_quota_data *qd) { spin_lock(&qd->qd_lockref.lock); gfs2_assert_warn(qd->qd_sbd, test_bit(QDF_LOCKED, &qd->qd_flags)); clear_bit(QDF_LOCKED, &qd->qd_flags); spin_unlock(&qd->qd_lockref.lock); qdsb_put(qd); } static int qdsb_get(struct gfs2_sbd *sdp, struct kqid qid, struct gfs2_quota_data **qdp) { int error; error = qd_get(sdp, qid, qdp); if (error) return error; error = slot_get(*qdp); if (error) goto fail; error = bh_get(*qdp); if (error) goto fail_slot; return 0; fail_slot: slot_put(*qdp); fail: qd_put(*qdp); return error; } /** * gfs2_qa_get - make sure we have a quota allocations data structure, * if necessary * @ip: the inode for this reservation */ int gfs2_qa_get(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct inode *inode = &ip->i_inode; if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return 0; spin_lock(&inode->i_lock); if (ip->i_qadata == NULL) { struct gfs2_qadata *tmp; spin_unlock(&inode->i_lock); tmp = kmem_cache_zalloc(gfs2_qadata_cachep, GFP_NOFS); if (!tmp) return -ENOMEM; spin_lock(&inode->i_lock); if (ip->i_qadata == NULL) ip->i_qadata = tmp; else kmem_cache_free(gfs2_qadata_cachep, tmp); } ip->i_qadata->qa_ref++; spin_unlock(&inode->i_lock); return 0; } void gfs2_qa_put(struct gfs2_inode *ip) { struct inode *inode = &ip->i_inode; spin_lock(&inode->i_lock); if (ip->i_qadata && --ip->i_qadata->qa_ref == 0) { kmem_cache_free(gfs2_qadata_cachep, ip->i_qadata); ip->i_qadata = NULL; } spin_unlock(&inode->i_lock); } int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data **qd; int error; if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return 0; error = gfs2_qa_get(ip); if (error) return error; qd = ip->i_qadata->qa_qd; if (gfs2_assert_warn(sdp, !ip->i_qadata->qa_qd_num) || gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags))) { error = -EIO; gfs2_qa_put(ip); goto out; } error = qdsb_get(sdp, make_kqid_uid(ip->i_inode.i_uid), qd); if (error) goto out_unhold; ip->i_qadata->qa_qd_num++; qd++; error = qdsb_get(sdp, make_kqid_gid(ip->i_inode.i_gid), qd); if (error) goto out_unhold; ip->i_qadata->qa_qd_num++; qd++; if (!uid_eq(uid, NO_UID_QUOTA_CHANGE) && !uid_eq(uid, ip->i_inode.i_uid)) { error = qdsb_get(sdp, make_kqid_uid(uid), qd); if (error) goto out_unhold; ip->i_qadata->qa_qd_num++; qd++; } if (!gid_eq(gid, NO_GID_QUOTA_CHANGE) && !gid_eq(gid, ip->i_inode.i_gid)) { error = qdsb_get(sdp, make_kqid_gid(gid), qd); if (error) goto out_unhold; ip->i_qadata->qa_qd_num++; qd++; } out_unhold: if (error) gfs2_quota_unhold(ip); out: return error; } void gfs2_quota_unhold(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); u32 x; if (ip->i_qadata == NULL) return; gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags)); for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qdsb_put(ip->i_qadata->qa_qd[x]); ip->i_qadata->qa_qd[x] = NULL; } ip->i_qadata->qa_qd_num = 0; gfs2_qa_put(ip); } static int sort_qd(const void *a, const void *b) { const struct gfs2_quota_data *qd_a = *(const struct gfs2_quota_data **)a; const struct gfs2_quota_data *qd_b = *(const struct gfs2_quota_data **)b; if (qid_lt(qd_a->qd_id, qd_b->qd_id)) return -1; if (qid_lt(qd_b->qd_id, qd_a->qd_id)) return 1; return 0; } static void do_qc(struct gfs2_quota_data *qd, s64 change) { struct gfs2_sbd *sdp = qd->qd_sbd; struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode); struct gfs2_quota_change *qc = qd->qd_bh_qc; bool needs_put = false; s64 x; gfs2_trans_add_meta(ip->i_gl, qd->qd_bh); /* * The QDF_CHANGE flag indicates that the slot in the quota change file * is used. Here, we use the value of qc->qc_change when the slot is * used, and we assume a value of 0 otherwise. */ spin_lock(&qd->qd_lockref.lock); x = 0; if (test_bit(QDF_CHANGE, &qd->qd_flags)) x = be64_to_cpu(qc->qc_change); x += change; qd->qd_change += change; if (!x && test_bit(QDF_CHANGE, &qd->qd_flags)) { /* The slot in the quota change file becomes unused. */ clear_bit(QDF_CHANGE, &qd->qd_flags); qc->qc_flags = 0; qc->qc_id = 0; needs_put = true; } else if (x && !test_bit(QDF_CHANGE, &qd->qd_flags)) { /* The slot in the quota change file becomes used. */ set_bit(QDF_CHANGE, &qd->qd_flags); __qd_hold(qd); slot_hold(qd); qc->qc_flags = 0; if (qd->qd_id.type == USRQUOTA) qc->qc_flags = cpu_to_be32(GFS2_QCF_USER); qc->qc_id = cpu_to_be32(from_kqid(&init_user_ns, qd->qd_id)); } qc->qc_change = cpu_to_be64(x); spin_unlock(&qd->qd_lockref.lock); if (needs_put) { slot_put(qd); qd_put(qd); } if (change < 0) /* Reset quiet flag if we freed some blocks */ clear_bit(QDF_QMSG_QUIET, &qd->qd_flags); } static int gfs2_write_buf_to_page(struct gfs2_sbd *sdp, unsigned long index, unsigned off, void *buf, unsigned bytes) { struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); struct inode *inode = &ip->i_inode; struct address_space *mapping = inode->i_mapping; struct folio *folio; struct buffer_head *bh; u64 blk; unsigned bsize = sdp->sd_sb.sb_bsize, bnum = 0, boff = 0; unsigned to_write = bytes, pg_off = off; blk = index << (PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift); boff = off % bsize; folio = filemap_grab_folio(mapping, index); if (IS_ERR(folio)) return PTR_ERR(folio); bh = folio_buffers(folio); if (!bh) bh = create_empty_buffers(folio, bsize, 0); for (;;) { /* Find the beginning block within the folio */ if (pg_off >= ((bnum * bsize) + bsize)) { bh = bh->b_this_page; bnum++; blk++; continue; } if (!buffer_mapped(bh)) { gfs2_block_map(inode, blk, bh, 1); if (!buffer_mapped(bh)) goto unlock_out; /* If it's a newly allocated disk block, zero it */ if (buffer_new(bh)) folio_zero_range(folio, bnum * bsize, bh->b_size); } if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); if (bh_read(bh, REQ_META | REQ_PRIO) < 0) goto unlock_out; gfs2_trans_add_data(ip->i_gl, bh); /* If we need to write to the next block as well */ if (to_write > (bsize - boff)) { pg_off += (bsize - boff); to_write -= (bsize - boff); boff = pg_off % bsize; continue; } break; } /* Write to the folio, now that we have setup the buffer(s) */ memcpy_to_folio(folio, off, buf, bytes); flush_dcache_folio(folio); folio_unlock(folio); folio_put(folio); return 0; unlock_out: folio_unlock(folio); folio_put(folio); return -EIO; } static int gfs2_write_disk_quota(struct gfs2_sbd *sdp, struct gfs2_quota *qp, loff_t loc) { unsigned long pg_beg; unsigned pg_off, nbytes, overflow = 0; int error; void *ptr; nbytes = sizeof(struct gfs2_quota); pg_beg = loc >> PAGE_SHIFT; pg_off = offset_in_page(loc); /* If the quota straddles a page boundary, split the write in two */ if ((pg_off + nbytes) > PAGE_SIZE) overflow = (pg_off + nbytes) - PAGE_SIZE; ptr = qp; error = gfs2_write_buf_to_page(sdp, pg_beg, pg_off, ptr, nbytes - overflow); /* If there's an overflow, write the remaining bytes to the next page */ if (!error && overflow) error = gfs2_write_buf_to_page(sdp, pg_beg + 1, 0, ptr + nbytes - overflow, overflow); return error; } /** * gfs2_adjust_quota - adjust record of current block usage * @sdp: The superblock * @loc: Offset of the entry in the quota file * @change: The amount of usage change to record * @qd: The quota data * @fdq: The updated limits to record * * This function was mostly borrowed from gfs2_block_truncate_page which was * in turn mostly borrowed from ext3 * * Returns: 0 or -ve on error */ static int gfs2_adjust_quota(struct gfs2_sbd *sdp, loff_t loc, s64 change, struct gfs2_quota_data *qd, struct qc_dqblk *fdq) { struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); struct inode *inode = &ip->i_inode; struct gfs2_quota q; int err; u64 size; if (gfs2_is_stuffed(ip)) { err = gfs2_unstuff_dinode(ip); if (err) return err; } memset(&q, 0, sizeof(struct gfs2_quota)); err = gfs2_internal_read(ip, (char *)&q, &loc, sizeof(q)); if (err < 0) return err; loc -= sizeof(q); /* gfs2_internal_read would've advanced the loc ptr */ be64_add_cpu(&q.qu_value, change); if (((s64)be64_to_cpu(q.qu_value)) < 0) q.qu_value = 0; /* Never go negative on quota usage */ spin_lock(&qd->qd_lockref.lock); qd->qd_qb.qb_value = q.qu_value; if (fdq) { if (fdq->d_fieldmask & QC_SPC_SOFT) { q.qu_warn = cpu_to_be64(fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_warn = q.qu_warn; } if (fdq->d_fieldmask & QC_SPC_HARD) { q.qu_limit = cpu_to_be64(fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_limit = q.qu_limit; } if (fdq->d_fieldmask & QC_SPACE) { q.qu_value = cpu_to_be64(fdq->d_space >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_value = q.qu_value; } } spin_unlock(&qd->qd_lockref.lock); err = gfs2_write_disk_quota(sdp, &q, loc); if (!err) { size = loc + sizeof(struct gfs2_quota); if (size > inode->i_size) i_size_write(inode, size); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); set_bit(QDF_REFRESH, &qd->qd_flags); } return err; } static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda, u64 sync_gen) { struct gfs2_sbd *sdp = (*qda)->qd_sbd; struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); struct gfs2_alloc_parms ap = {}; unsigned int data_blocks, ind_blocks; struct gfs2_holder *ghs, i_gh; unsigned int qx, x; struct gfs2_quota_data *qd; unsigned reserved; loff_t offset; unsigned int nalloc = 0, blocks; int error; gfs2_write_calc_reserv(ip, sizeof(struct gfs2_quota), &data_blocks, &ind_blocks); ghs = kmalloc_array(num_qd, sizeof(struct gfs2_holder), GFP_NOFS); if (!ghs) return -ENOMEM; sort(qda, num_qd, sizeof(struct gfs2_quota_data *), sort_qd, NULL); inode_lock(&ip->i_inode); for (qx = 0; qx < num_qd; qx++) { error = gfs2_glock_nq_init(qda[qx]->qd_gl, LM_ST_EXCLUSIVE, GL_NOCACHE, &ghs[qx]); if (error) goto out_dq; } error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh); if (error) goto out_dq; for (x = 0; x < num_qd; x++) { offset = qd2offset(qda[x]); if (gfs2_write_alloc_required(ip, offset, sizeof(struct gfs2_quota))) nalloc++; } /* * 1 blk for unstuffing inode if stuffed. We add this extra * block to the reservation unconditionally. If the inode * doesn't need unstuffing, the block will be released to the * rgrp since it won't be allocated during the transaction */ /* +3 in the end for unstuffing block, inode size update block * and another block in case quota straddles page boundary and * two blocks need to be updated instead of 1 */ blocks = num_qd * data_blocks + RES_DINODE + num_qd + 3; reserved = 1 + (nalloc * (data_blocks + ind_blocks)); ap.target = reserved; error = gfs2_inplace_reserve(ip, &ap); if (error) goto out_alloc; if (nalloc) blocks += gfs2_rg_blocks(ip, reserved) + nalloc * ind_blocks + RES_STATFS; error = gfs2_trans_begin(sdp, blocks, 0); if (error) goto out_ipres; for (x = 0; x < num_qd; x++) { qd = qda[x]; offset = qd2offset(qd); error = gfs2_adjust_quota(sdp, offset, qd->qd_change_sync, qd, NULL); if (error) goto out_end_trans; do_qc(qd, -qd->qd_change_sync); set_bit(QDF_REFRESH, &qd->qd_flags); } out_end_trans: gfs2_trans_end(sdp); out_ipres: gfs2_inplace_release(ip); out_alloc: gfs2_glock_dq_uninit(&i_gh); out_dq: while (qx--) gfs2_glock_dq_uninit(&ghs[qx]); inode_unlock(&ip->i_inode); kfree(ghs); gfs2_log_flush(ip->i_gl->gl_name.ln_sbd, ip->i_gl, GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_DO_SYNC); if (!error) { for (x = 0; x < num_qd; x++) { qd = qda[x]; spin_lock(&qd->qd_lockref.lock); if (qd->qd_sync_gen < sync_gen) qd->qd_sync_gen = sync_gen; spin_unlock(&qd->qd_lockref.lock); } } return error; } static int update_qd(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd) { struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); struct gfs2_quota q; struct gfs2_quota_lvb *qlvb; loff_t pos; int error; memset(&q, 0, sizeof(struct gfs2_quota)); pos = qd2offset(qd); error = gfs2_internal_read(ip, (char *)&q, &pos, sizeof(q)); if (error < 0) return error; qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr; qlvb->qb_magic = cpu_to_be32(GFS2_MAGIC); qlvb->__pad = 0; qlvb->qb_limit = q.qu_limit; qlvb->qb_warn = q.qu_warn; qlvb->qb_value = q.qu_value; spin_lock(&qd->qd_lockref.lock); qd->qd_qb = *qlvb; spin_unlock(&qd->qd_lockref.lock); return 0; } static int do_glock(struct gfs2_quota_data *qd, int force_refresh, struct gfs2_holder *q_gh) { struct gfs2_sbd *sdp = qd->qd_sbd; struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); struct gfs2_holder i_gh; int error; gfs2_assert_warn(sdp, sdp == qd->qd_gl->gl_name.ln_sbd); restart: error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_SHARED, 0, q_gh); if (error) return error; if (test_and_clear_bit(QDF_REFRESH, &qd->qd_flags)) force_refresh = FORCE; spin_lock(&qd->qd_lockref.lock); qd->qd_qb = *(struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr; spin_unlock(&qd->qd_lockref.lock); if (force_refresh || qd->qd_qb.qb_magic != cpu_to_be32(GFS2_MAGIC)) { gfs2_glock_dq_uninit(q_gh); error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_EXCLUSIVE, GL_NOCACHE, q_gh); if (error) return error; error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh); if (error) goto fail; error = update_qd(sdp, qd); if (error) goto fail_gunlock; gfs2_glock_dq_uninit(&i_gh); gfs2_glock_dq_uninit(q_gh); force_refresh = 0; goto restart; } return 0; fail_gunlock: gfs2_glock_dq_uninit(&i_gh); fail: gfs2_glock_dq_uninit(q_gh); return error; } int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qd; u32 x; int error; if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return 0; error = gfs2_quota_hold(ip, uid, gid); if (error) return error; sort(ip->i_qadata->qa_qd, ip->i_qadata->qa_qd_num, sizeof(struct gfs2_quota_data *), sort_qd, NULL); for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qd = ip->i_qadata->qa_qd[x]; error = do_glock(qd, NO_FORCE, &ip->i_qadata->qa_qd_ghs[x]); if (error) break; } if (!error) set_bit(GIF_QD_LOCKED, &ip->i_flags); else { while (x--) gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]); gfs2_quota_unhold(ip); } return error; } static bool need_sync(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; struct gfs2_tune *gt = &sdp->sd_tune; s64 value, change, limit; unsigned int num, den; int ret = false; spin_lock(&qd->qd_lockref.lock); if (!qd->qd_qb.qb_limit) goto out; change = qd->qd_change; if (change <= 0) goto out; value = (s64)be64_to_cpu(qd->qd_qb.qb_value); limit = (s64)be64_to_cpu(qd->qd_qb.qb_limit); if (value >= limit) goto out; spin_lock(>->gt_spin); num = gt->gt_quota_scale_num; den = gt->gt_quota_scale_den; spin_unlock(>->gt_spin); change *= gfs2_jindex_size(sdp) * num; change = div_s64(change, den); if (value + change < limit) goto out; ret = true; out: spin_unlock(&qd->qd_lockref.lock); return ret; } void gfs2_quota_unlock(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qda[2 * GFS2_MAXQUOTAS]; unsigned int count = 0; u32 x; if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags)) return; for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { struct gfs2_quota_data *qd; bool sync; int error; qd = ip->i_qadata->qa_qd[x]; sync = need_sync(qd); gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]); if (!sync) continue; spin_lock(&qd_lock); sync = qd_grab_sync(sdp, qd, U64_MAX); spin_unlock(&qd_lock); if (!sync) continue; gfs2_assert_warn(sdp, qd->qd_change_sync); error = bh_get(qd); if (error) { qd_ungrab_sync(qd); continue; } qda[count++] = qd; } if (count) { u64 sync_gen = READ_ONCE(sdp->sd_quota_sync_gen); do_sync(count, qda, sync_gen); for (x = 0; x < count; x++) qd_unlock(qda[x]); } gfs2_quota_unhold(ip); } #define MAX_LINE 256 static void print_message(struct gfs2_quota_data *qd, char *type) { struct gfs2_sbd *sdp = qd->qd_sbd; if (sdp->sd_args.ar_quota != GFS2_QUOTA_QUIET) { fs_info(sdp, "quota %s for %s %u\n", type, (qd->qd_id.type == USRQUOTA) ? "user" : "group", from_kqid(&init_user_ns, qd->qd_id)); } } /** * gfs2_quota_check - check if allocating new blocks will exceed quota * @ip: The inode for which this check is being performed * @uid: The uid to check against * @gid: The gid to check against * @ap: The allocation parameters. ap->target contains the requested * blocks. ap->min_target, if set, contains the minimum blks * requested. * * Returns: 0 on success. * min_req = ap->min_target ? ap->min_target : ap->target; * quota must allow at least min_req blks for success and * ap->allowed is set to the number of blocks allowed * * -EDQUOT otherwise, quota violation. ap->allowed is set to number * of blocks available. */ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid, struct gfs2_alloc_parms *ap) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qd; s64 value, warn, limit; u32 x; int error = 0; ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */ if (!test_bit(GIF_QD_LOCKED, &ip->i_flags)) return 0; for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qd = ip->i_qadata->qa_qd[x]; if (!(qid_eq(qd->qd_id, make_kqid_uid(uid)) || qid_eq(qd->qd_id, make_kqid_gid(gid)))) continue; spin_lock(&qd->qd_lockref.lock); warn = (s64)be64_to_cpu(qd->qd_qb.qb_warn); limit = (s64)be64_to_cpu(qd->qd_qb.qb_limit); value = (s64)be64_to_cpu(qd->qd_qb.qb_value); value += qd->qd_change; spin_unlock(&qd->qd_lockref.lock); if (limit > 0 && (limit - value) < ap->allowed) ap->allowed = limit - value; /* If we can't meet the target */ if (limit && limit < (value + (s64)ap->target)) { /* If no min_target specified or we don't meet * min_target, return -EDQUOT */ if (!ap->min_target || ap->min_target > ap->allowed) { if (!test_and_set_bit(QDF_QMSG_QUIET, &qd->qd_flags)) { print_message(qd, "exceeded"); quota_send_warning(qd->qd_id, sdp->sd_vfs->s_dev, QUOTA_NL_BHARDWARN); } error = -EDQUOT; break; } } else if (warn && warn < value && time_after_eq(jiffies, qd->qd_last_warn + gfs2_tune_get(sdp, gt_quota_warn_period) * HZ)) { quota_send_warning(qd->qd_id, sdp->sd_vfs->s_dev, QUOTA_NL_BSOFTWARN); print_message(qd, "warning"); error = 0; qd->qd_last_warn = jiffies; } } return error; } void gfs2_quota_change(struct gfs2_inode *ip, s64 change, kuid_t uid, kgid_t gid) { struct gfs2_quota_data *qd; u32 x; struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF || gfs2_assert_warn(sdp, change)) return; if (ip->i_diskflags & GFS2_DIF_SYSTEM) return; if (gfs2_assert_withdraw(sdp, ip->i_qadata && ip->i_qadata->qa_ref > 0)) return; for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qd = ip->i_qadata->qa_qd[x]; if (qid_eq(qd->qd_id, make_kqid_uid(uid)) || qid_eq(qd->qd_id, make_kqid_gid(gid))) { do_qc(qd, change); } } } int gfs2_quota_sync(struct super_block *sb, int type) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_quota_data **qda; unsigned int max_qd = PAGE_SIZE / sizeof(struct gfs2_holder); u64 sync_gen; int error = 0; if (sb_rdonly(sdp->sd_vfs)) return 0; qda = kcalloc(max_qd, sizeof(struct gfs2_quota_data *), GFP_KERNEL); if (!qda) return -ENOMEM; mutex_lock(&sdp->sd_quota_sync_mutex); sync_gen = sdp->sd_quota_sync_gen + 1; do { struct gfs2_quota_data *iter; unsigned int num_qd = 0; unsigned int x; spin_lock(&qd_lock); list_for_each_entry(iter, &sdp->sd_quota_list, qd_list) { if (qd_grab_sync(sdp, iter, sync_gen)) { qda[num_qd++] = iter; if (num_qd == max_qd) break; } } spin_unlock(&qd_lock); if (!num_qd) break; for (x = 0; x < num_qd; x++) { error = bh_get(qda[x]); if (!error) continue; while (x < num_qd) qd_ungrab_sync(qda[--num_qd]); break; } if (!error) { WRITE_ONCE(sdp->sd_quota_sync_gen, sync_gen); error = do_sync(num_qd, qda, sync_gen); } for (x = 0; x < num_qd; x++) qd_unlock(qda[x]); } while (!error); mutex_unlock(&sdp->sd_quota_sync_mutex); kfree(qda); return error; } int gfs2_quota_refresh(struct gfs2_sbd *sdp, struct kqid qid) { struct gfs2_quota_data *qd; struct gfs2_holder q_gh; int error; error = qd_get(sdp, qid, &qd); if (error) return error; error = do_glock(qd, FORCE, &q_gh); if (!error) gfs2_glock_dq_uninit(&q_gh); qd_put(qd); return error; } int gfs2_quota_init(struct gfs2_sbd *sdp) { struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode); u64 size = i_size_read(sdp->sd_qc_inode); unsigned int blocks = size >> sdp->sd_sb.sb_bsize_shift; unsigned int x, slot = 0; unsigned int found = 0; unsigned int hash; unsigned int bm_size; struct buffer_head *bh; u64 dblock; u32 extlen = 0; int error; if (gfs2_check_internal_file_size(sdp->sd_qc_inode, 1, 64 << 20)) return -EIO; sdp->sd_quota_slots = blocks * sdp->sd_qc_per_block; bm_size = DIV_ROUND_UP(sdp->sd_quota_slots, 8 * sizeof(unsigned long)); bm_size *= sizeof(unsigned long); error = -ENOMEM; sdp->sd_quota_bitmap = kzalloc(bm_size, GFP_NOFS | __GFP_NOWARN); if (sdp->sd_quota_bitmap == NULL) sdp->sd_quota_bitmap = __vmalloc(bm_size, GFP_NOFS | __GFP_ZERO); if (!sdp->sd_quota_bitmap) return error; for (x = 0; x < blocks; x++) { struct gfs2_quota_change *qc; unsigned int y; if (!extlen) { extlen = 32; error = gfs2_get_extent(&ip->i_inode, x, &dblock, &extlen); if (error) goto fail; } error = -EIO; bh = gfs2_meta_ra(ip->i_gl, dblock, extlen); if (!bh) goto fail; if (gfs2_metatype_check(sdp, bh, GFS2_METATYPE_QC)) goto fail_brelse; qc = (struct gfs2_quota_change *)(bh->b_data + sizeof(struct gfs2_meta_header)); for (y = 0; y < sdp->sd_qc_per_block && slot < sdp->sd_quota_slots; y++, slot++) { struct gfs2_quota_data *old_qd, *qd; s64 qc_change = be64_to_cpu(qc->qc_change); u32 qc_flags = be32_to_cpu(qc->qc_flags); enum quota_type qtype = (qc_flags & GFS2_QCF_USER) ? USRQUOTA : GRPQUOTA; struct kqid qc_id = make_kqid(&init_user_ns, qtype, be32_to_cpu(qc->qc_id)); qc++; if (!qc_change) continue; hash = gfs2_qd_hash(sdp, qc_id); qd = qd_alloc(hash, sdp, qc_id); if (qd == NULL) goto fail_brelse; set_bit(QDF_CHANGE, &qd->qd_flags); qd->qd_change = qc_change; qd->qd_slot = slot; qd->qd_slot_ref = 1; spin_lock(&qd_lock); spin_lock_bucket(hash); old_qd = gfs2_qd_search_bucket(hash, sdp, qc_id); if (old_qd) { fs_err(sdp, "Corruption found in quota_change%u" "file: duplicate identifier in " "slot %u\n", sdp->sd_jdesc->jd_jid, slot); spin_unlock_bucket(hash); spin_unlock(&qd_lock); qd_put(old_qd); gfs2_glock_put(qd->qd_gl); kmem_cache_free(gfs2_quotad_cachep, qd); /* zero out the duplicate slot */ lock_buffer(bh); memset(qc, 0, sizeof(*qc)); mark_buffer_dirty(bh); unlock_buffer(bh); continue; } BUG_ON(test_and_set_bit(slot, sdp->sd_quota_bitmap)); list_add(&qd->qd_list, &sdp->sd_quota_list); atomic_inc(&sdp->sd_quota_count); hlist_bl_add_head_rcu(&qd->qd_hlist, &qd_hash_table[hash]); spin_unlock_bucket(hash); spin_unlock(&qd_lock); found++; } if (buffer_dirty(bh)) sync_dirty_buffer(bh); brelse(bh); dblock++; extlen--; } if (found) fs_info(sdp, "found %u quota changes\n", found); return 0; fail_brelse: if (buffer_dirty(bh)) sync_dirty_buffer(bh); brelse(bh); fail: gfs2_quota_cleanup(sdp); return error; } void gfs2_quota_cleanup(struct gfs2_sbd *sdp) { struct gfs2_quota_data *qd; LIST_HEAD(dispose); int count; BUG_ON(!test_bit(SDF_NORECOVERY, &sdp->sd_flags) && test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)); spin_lock(&qd_lock); list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) { spin_lock(&qd->qd_lockref.lock); if (qd->qd_lockref.count != 0) { spin_unlock(&qd->qd_lockref.lock); continue; } lockref_mark_dead(&qd->qd_lockref); spin_unlock(&qd->qd_lockref.lock); list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru); list_add(&qd->qd_lru, &dispose); } spin_unlock(&qd_lock); gfs2_qd_list_dispose(&dispose); wait_event_timeout(sdp->sd_kill_wait, (count = atomic_read(&sdp->sd_quota_count)) == 0, HZ * 60); if (count != 0) fs_err(sdp, "%d left-over quota data objects\n", count); kvfree(sdp->sd_quota_bitmap); sdp->sd_quota_bitmap = NULL; } static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error) { if (error == 0 || error == -EROFS) return; if (!gfs2_withdrawing_or_withdrawn(sdp)) { if (!cmpxchg(&sdp->sd_log_error, 0, error)) fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error); wake_up(&sdp->sd_logd_waitq); } } static void quotad_check_timeo(struct gfs2_sbd *sdp, const char *msg, int (*fxn)(struct super_block *sb, int type), unsigned long t, unsigned long *timeo, unsigned int *new_timeo) { if (t >= *timeo) { int error = fxn(sdp->sd_vfs, 0); quotad_error(sdp, msg, error); *timeo = gfs2_tune_get_i(&sdp->sd_tune, new_timeo) * HZ; } else { *timeo -= t; } } void gfs2_wake_up_statfs(struct gfs2_sbd *sdp) { if (!sdp->sd_statfs_force_sync) { sdp->sd_statfs_force_sync = 1; wake_up(&sdp->sd_quota_wait); } } /** * gfs2_quotad - Write cached quota changes into the quota file * @data: Pointer to GFS2 superblock * */ int gfs2_quotad(void *data) { struct gfs2_sbd *sdp = data; struct gfs2_tune *tune = &sdp->sd_tune; unsigned long statfs_timeo = 0; unsigned long quotad_timeo = 0; unsigned long t = 0; set_freezable(); while (!kthread_should_stop()) { if (gfs2_withdrawing_or_withdrawn(sdp)) break; /* Update the master statfs file */ if (sdp->sd_statfs_force_sync) { int error = gfs2_statfs_sync(sdp->sd_vfs, 0); quotad_error(sdp, "statfs", error); statfs_timeo = gfs2_tune_get(sdp, gt_statfs_quantum) * HZ; } else quotad_check_timeo(sdp, "statfs", gfs2_statfs_sync, t, &statfs_timeo, &tune->gt_statfs_quantum); /* Update quota file */ quotad_check_timeo(sdp, "sync", gfs2_quota_sync, t, "ad_timeo, &tune->gt_quota_quantum); t = min(quotad_timeo, statfs_timeo); t = wait_event_freezable_timeout(sdp->sd_quota_wait, sdp->sd_statfs_force_sync || gfs2_withdrawing_or_withdrawn(sdp) || kthread_should_stop(), t); if (sdp->sd_statfs_force_sync) t = 0; } return 0; } static int gfs2_quota_get_state(struct super_block *sb, struct qc_state *state) { struct gfs2_sbd *sdp = sb->s_fs_info; memset(state, 0, sizeof(*state)); switch (sdp->sd_args.ar_quota) { case GFS2_QUOTA_QUIET: fallthrough; case GFS2_QUOTA_ON: state->s_state[USRQUOTA].flags |= QCI_LIMITS_ENFORCED; state->s_state[GRPQUOTA].flags |= QCI_LIMITS_ENFORCED; fallthrough; case GFS2_QUOTA_ACCOUNT: state->s_state[USRQUOTA].flags |= QCI_ACCT_ENABLED | QCI_SYSFILE; state->s_state[GRPQUOTA].flags |= QCI_ACCT_ENABLED | QCI_SYSFILE; break; case GFS2_QUOTA_OFF: break; } if (sdp->sd_quota_inode) { state->s_state[USRQUOTA].ino = GFS2_I(sdp->sd_quota_inode)->i_no_addr; state->s_state[USRQUOTA].blocks = sdp->sd_quota_inode->i_blocks; } state->s_state[USRQUOTA].nextents = 1; /* unsupported */ state->s_state[GRPQUOTA] = state->s_state[USRQUOTA]; state->s_incoredqs = list_lru_count(&gfs2_qd_lru); return 0; } static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid, struct qc_dqblk *fdq) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_quota_lvb *qlvb; struct gfs2_quota_data *qd; struct gfs2_holder q_gh; int error; memset(fdq, 0, sizeof(*fdq)); if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return -ESRCH; /* Crazy XFS error code */ if ((qid.type != USRQUOTA) && (qid.type != GRPQUOTA)) return -EINVAL; error = qd_get(sdp, qid, &qd); if (error) return error; error = do_glock(qd, FORCE, &q_gh); if (error) goto out; qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr; fdq->d_spc_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_sb.sb_bsize_shift; fdq->d_spc_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_sb.sb_bsize_shift; fdq->d_space = be64_to_cpu(qlvb->qb_value) << sdp->sd_sb.sb_bsize_shift; gfs2_glock_dq_uninit(&q_gh); out: qd_put(qd); return error; } /* GFS2 only supports a subset of the XFS fields */ #define GFS2_FIELDMASK (QC_SPC_SOFT|QC_SPC_HARD|QC_SPACE) static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid, struct qc_dqblk *fdq) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); struct gfs2_quota_data *qd; struct gfs2_holder q_gh, i_gh; unsigned int data_blocks, ind_blocks; unsigned int blocks = 0; int alloc_required; loff_t offset; int error; if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return -ESRCH; /* Crazy XFS error code */ if ((qid.type != USRQUOTA) && (qid.type != GRPQUOTA)) return -EINVAL; if (fdq->d_fieldmask & ~GFS2_FIELDMASK) return -EINVAL; error = qd_get(sdp, qid, &qd); if (error) return error; error = gfs2_qa_get(ip); if (error) goto out_put; inode_lock(&ip->i_inode); error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_EXCLUSIVE, 0, &q_gh); if (error) goto out_unlockput; error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh); if (error) goto out_q; /* Check for existing entry, if none then alloc new blocks */ error = update_qd(sdp, qd); if (error) goto out_i; /* If nothing has changed, this is a no-op */ if ((fdq->d_fieldmask & QC_SPC_SOFT) && ((fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_warn))) fdq->d_fieldmask ^= QC_SPC_SOFT; if ((fdq->d_fieldmask & QC_SPC_HARD) && ((fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_limit))) fdq->d_fieldmask ^= QC_SPC_HARD; if ((fdq->d_fieldmask & QC_SPACE) && ((fdq->d_space >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_value))) fdq->d_fieldmask ^= QC_SPACE; if (fdq->d_fieldmask == 0) goto out_i; offset = qd2offset(qd); alloc_required = gfs2_write_alloc_required(ip, offset, sizeof(struct gfs2_quota)); if (gfs2_is_stuffed(ip)) alloc_required = 1; if (alloc_required) { struct gfs2_alloc_parms ap = {}; gfs2_write_calc_reserv(ip, sizeof(struct gfs2_quota), &data_blocks, &ind_blocks); blocks = 1 + data_blocks + ind_blocks; ap.target = blocks; error = gfs2_inplace_reserve(ip, &ap); if (error) goto out_i; blocks += gfs2_rg_blocks(ip, blocks); } /* Some quotas span block boundaries and can update two blocks, adding an extra block to the transaction to handle such quotas */ error = gfs2_trans_begin(sdp, blocks + RES_DINODE + 2, 0); if (error) goto out_release; /* Apply changes */ error = gfs2_adjust_quota(sdp, offset, 0, qd, fdq); if (!error) clear_bit(QDF_QMSG_QUIET, &qd->qd_flags); gfs2_trans_end(sdp); out_release: if (alloc_required) gfs2_inplace_release(ip); out_i: gfs2_glock_dq_uninit(&i_gh); out_q: gfs2_glock_dq_uninit(&q_gh); out_unlockput: gfs2_qa_put(ip); inode_unlock(&ip->i_inode); out_put: qd_put(qd); return error; } const struct quotactl_ops gfs2_quotactl_ops = { .quota_sync = gfs2_quota_sync, .get_state = gfs2_quota_get_state, .get_dqblk = gfs2_get_dqblk, .set_dqblk = gfs2_set_dqblk, }; void __init gfs2_quota_hash_init(void) { unsigned i; for(i = 0; i < GFS2_QD_HASH_SIZE; i++) INIT_HLIST_BL_HEAD(&qd_hash_table[i]); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_XATTR_H #define _BCACHEFS_XATTR_H #include "str_hash.h" extern const struct bch_hash_desc bch2_xattr_hash_desc; int bch2_xattr_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); void bch2_xattr_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); #define bch2_bkey_ops_xattr ((struct bkey_ops) { \ .key_validate = bch2_xattr_validate, \ .val_to_text = bch2_xattr_to_text, \ .min_val_size = 8, \ }) static inline unsigned xattr_val_u64s(unsigned name_len, unsigned val_len) { return DIV_ROUND_UP(offsetof(struct bch_xattr, x_name) + name_len + val_len, sizeof(u64)); } #define xattr_val(_xattr) \ ((void *) (_xattr)->x_name + (_xattr)->x_name_len) struct xattr_search_key { u8 type; struct qstr name; }; #define X_SEARCH(_type, _name, _len) ((struct xattr_search_key) \ { .type = _type, .name = QSTR_INIT(_name, _len) }) struct dentry; struct xattr_handler; struct bch_hash_info; struct bch_inode_info; /* Exported for cmd_migrate.c in tools: */ int bch2_xattr_set(struct btree_trans *, subvol_inum, struct bch_inode_unpacked *, const struct bch_hash_info *, const char *, const void *, size_t, int, int); ssize_t bch2_xattr_list(struct dentry *, char *, size_t); extern const struct xattr_handler *bch2_xattr_handlers[]; #endif /* _BCACHEFS_XATTR_H */ |
| 103 61 104 4733 1398 1357 47 546 499 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | // SPDX-License-Identifier: GPL-2.0 #include <linux/err.h> #include <linux/bug.h> #include <linux/atomic.h> #include <linux/errseq.h> #include <linux/log2.h> /* * An errseq_t is a way of recording errors in one place, and allowing any * number of "subscribers" to tell whether it has changed since a previous * point where it was sampled. * * It's implemented as an unsigned 32-bit value. The low order bits are * designated to hold an error code (between 0 and -MAX_ERRNO). The upper bits * are used as a counter. This is done with atomics instead of locking so that * these functions can be called from any context. * * The general idea is for consumers to sample an errseq_t value. That value * can later be used to tell whether any new errors have occurred since that * sampling was done. * * Note that there is a risk of collisions if new errors are being recorded * frequently, since we have so few bits to use as a counter. * * To mitigate this, one bit is used as a flag to tell whether the value has * been sampled since a new value was recorded. That allows us to avoid bumping * the counter if no one has sampled it since the last time an error was * recorded. * * A new errseq_t should always be zeroed out. A errseq_t value of all zeroes * is the special (but common) case where there has never been an error. An all * zero value thus serves as the "epoch" if one wishes to know whether there * has ever been an error set since it was first initialized. */ /* The low bits are designated for error code (max of MAX_ERRNO) */ #define ERRSEQ_SHIFT ilog2(MAX_ERRNO + 1) /* This bit is used as a flag to indicate whether the value has been seen */ #define ERRSEQ_SEEN (1 << ERRSEQ_SHIFT) /* The lowest bit of the counter */ #define ERRSEQ_CTR_INC (1 << (ERRSEQ_SHIFT + 1)) /** * errseq_set - set a errseq_t for later reporting * @eseq: errseq_t field that should be set * @err: error to set (must be between -1 and -MAX_ERRNO) * * This function sets the error in @eseq, and increments the sequence counter * if the last sequence was sampled at some point in the past. * * Any error set will always overwrite an existing error. * * Return: The previous value, primarily for debugging purposes. The * return value should not be used as a previously sampled value in later * calls as it will not have the SEEN flag set. */ errseq_t errseq_set(errseq_t *eseq, int err) { errseq_t cur, old; /* MAX_ERRNO must be able to serve as a mask */ BUILD_BUG_ON_NOT_POWER_OF_2(MAX_ERRNO + 1); /* * Ensure the error code actually fits where we want it to go. If it * doesn't then just throw a warning and don't record anything. We * also don't accept zero here as that would effectively clear a * previous error. */ old = READ_ONCE(*eseq); if (WARN(unlikely(err == 0 || (unsigned int)-err > MAX_ERRNO), "err = %d\n", err)) return old; for (;;) { errseq_t new; /* Clear out error bits and set new error */ new = (old & ~(MAX_ERRNO|ERRSEQ_SEEN)) | -err; /* Only increment if someone has looked at it */ if (old & ERRSEQ_SEEN) new += ERRSEQ_CTR_INC; /* If there would be no change, then call it done */ if (new == old) { cur = new; break; } /* Try to swap the new value into place */ cur = cmpxchg(eseq, old, new); /* * Call it success if we did the swap or someone else beat us * to it for the same value. */ if (likely(cur == old || cur == new)) break; /* Raced with an update, try again */ old = cur; } return cur; } EXPORT_SYMBOL(errseq_set); /** * errseq_sample() - Grab current errseq_t value. * @eseq: Pointer to errseq_t to be sampled. * * This function allows callers to initialise their errseq_t variable. * If the error has been "seen", new callers will not see an old error. * If there is an unseen error in @eseq, the caller of this function will * see it the next time it checks for an error. * * Context: Any context. * Return: The current errseq value. */ errseq_t errseq_sample(errseq_t *eseq) { errseq_t old = READ_ONCE(*eseq); /* If nobody has seen this error yet, then we can be the first. */ if (!(old & ERRSEQ_SEEN)) old = 0; return old; } EXPORT_SYMBOL(errseq_sample); /** * errseq_check() - Has an error occurred since a particular sample point? * @eseq: Pointer to errseq_t value to be checked. * @since: Previously-sampled errseq_t from which to check. * * Grab the value that eseq points to, and see if it has changed @since * the given value was sampled. The @since value is not advanced, so there * is no need to mark the value as seen. * * Return: The latest error set in the errseq_t or 0 if it hasn't changed. */ int errseq_check(errseq_t *eseq, errseq_t since) { errseq_t cur = READ_ONCE(*eseq); if (likely(cur == since)) return 0; return -(cur & MAX_ERRNO); } EXPORT_SYMBOL(errseq_check); /** * errseq_check_and_advance() - Check an errseq_t and advance to current value. * @eseq: Pointer to value being checked and reported. * @since: Pointer to previously-sampled errseq_t to check against and advance. * * Grab the eseq value, and see whether it matches the value that @since * points to. If it does, then just return 0. * * If it doesn't, then the value has changed. Set the "seen" flag, and try to * swap it into place as the new eseq value. Then, set that value as the new * "since" value, and return whatever the error portion is set to. * * Note that no locking is provided here for concurrent updates to the "since" * value. The caller must provide that if necessary. Because of this, callers * may want to do a lockless errseq_check before taking the lock and calling * this. * * Return: Negative errno if one has been stored, or 0 if no new error has * occurred. */ int errseq_check_and_advance(errseq_t *eseq, errseq_t *since) { int err = 0; errseq_t old, new; /* * Most callers will want to use the inline wrapper to check this, * so that the common case of no error is handled without needing * to take the lock that protects the "since" value. */ old = READ_ONCE(*eseq); if (old != *since) { /* * Set the flag and try to swap it into place if it has * changed. * * We don't care about the outcome of the swap here. If the * swap doesn't occur, then it has either been updated by a * writer who is altering the value in some way (updating * counter or resetting the error), or another reader who is * just setting the "seen" flag. Either outcome is OK, and we * can advance "since" and return an error based on what we * have. */ new = old | ERRSEQ_SEEN; if (new != old) cmpxchg(eseq, old, new); *since = new; err = -(new & MAX_ERRNO); } return err; } EXPORT_SYMBOL(errseq_check_and_advance); |
| 2 2 100 56 100 8 101 101 22 69 56 65 103 20 69 38 94 96 31 73 93 10 73 41 103 103 6 6 22 68 90 29 75 10 103 87 88 87 1 86 103 88 90 6 2 101 99 101 11 90 94 8 90 90 90 89 90 4 65 78 89 90 89 90 48 48 55 90 90 4 4 89 29 71 90 42 46 38 89 59 59 89 90 90 104 93 22 13 12 12 90 102 100 100 63 38 101 10 28 29 89 90 52 56 65 26 24 11 1 13 14 17 89 26 90 89 40 87 90 86 135 135 106 44 10 79 60 61 61 85 105 39 84 103 105 105 79 27 105 8 45 37 25 88 26 88 103 83 35 103 103 102 30 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/direct-io.c * * Copyright (C) 2002, Linus Torvalds. * * O_DIRECT * * 04Jul2002 Andrew Morton * Initial version * 11Sep2002 janetinc@us.ibm.com * added readv/writev support. * 29Oct2002 Andrew Morton * rewrote bio_add_page() support. * 30Oct2002 pbadari@us.ibm.com * added support for non-aligned IO. * 06Nov2002 pbadari@us.ibm.com * added asynchronous IO support. * 21Jul2003 nathans@sgi.com * added IO completion notifier. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/task_io_accounting_ops.h> #include <linux/bio.h> #include <linux/wait.h> #include <linux/err.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> #include <linux/rwsem.h> #include <linux/uio.h> #include <linux/atomic.h> #include "internal.h" /* * How many user pages to map in one call to iov_iter_extract_pages(). This * determines the size of a structure in the slab cache */ #define DIO_PAGES 64 /* * Flags for dio_complete() */ #define DIO_COMPLETE_ASYNC 0x01 /* This is async IO */ #define DIO_COMPLETE_INVALIDATE 0x02 /* Can invalidate pages */ /* * This code generally works in units of "dio_blocks". A dio_block is * somewhere between the hard sector size and the filesystem block size. it * is determined on a per-invocation basis. When talking to the filesystem * we need to convert dio_blocks to fs_blocks by scaling the dio_block quantity * down by dio->blkfactor. Similarly, fs-blocksize quantities are converted * to bio_block quantities by shifting left by blkfactor. * * If blkfactor is zero then the user's request was aligned to the filesystem's * blocksize. */ /* dio_state only used in the submission path */ struct dio_submit { struct bio *bio; /* bio under assembly */ unsigned blkbits; /* doesn't change */ unsigned blkfactor; /* When we're using an alignment which is finer than the filesystem's soft blocksize, this specifies how much finer. blkfactor=2 means 1/4-block alignment. Does not change */ unsigned start_zero_done; /* flag: sub-blocksize zeroing has been performed at the start of a write */ int pages_in_io; /* approximate total IO pages */ sector_t block_in_file; /* Current offset into the underlying file in dio_block units. */ unsigned blocks_available; /* At block_in_file. changes */ int reap_counter; /* rate limit reaping */ sector_t final_block_in_request;/* doesn't change */ int boundary; /* prev block is at a boundary */ get_block_t *get_block; /* block mapping function */ loff_t logical_offset_in_bio; /* current first logical block in bio */ sector_t final_block_in_bio; /* current final block in bio + 1 */ sector_t next_block_for_io; /* next block to be put under IO, in dio_blocks units */ /* * Deferred addition of a page to the dio. These variables are * private to dio_send_cur_page(), submit_page_section() and * dio_bio_add_page(). */ struct page *cur_page; /* The page */ unsigned cur_page_offset; /* Offset into it, in bytes */ unsigned cur_page_len; /* Nr of bytes at cur_page_offset */ sector_t cur_page_block; /* Where it starts */ loff_t cur_page_fs_offset; /* Offset in file */ struct iov_iter *iter; /* * Page queue. These variables belong to dio_refill_pages() and * dio_get_page(). */ unsigned head; /* next page to process */ unsigned tail; /* last valid page + 1 */ size_t from, to; }; /* dio_state communicated between submission path and end_io */ struct dio { int flags; /* doesn't change */ blk_opf_t opf; /* request operation type and flags */ struct gendisk *bio_disk; struct inode *inode; loff_t i_size; /* i_size when submitted */ dio_iodone_t *end_io; /* IO completion function */ bool is_pinned; /* T if we have pins on the pages */ void *private; /* copy from map_bh.b_private */ /* BIO completion state */ spinlock_t bio_lock; /* protects BIO fields below */ int page_errors; /* err from iov_iter_extract_pages() */ int is_async; /* is IO async ? */ bool defer_completion; /* defer AIO completion to workqueue? */ bool should_dirty; /* if pages should be dirtied */ int io_error; /* IO error in completion path */ unsigned long refcount; /* direct_io_worker() and bios */ struct bio *bio_list; /* singly linked via bi_private */ struct task_struct *waiter; /* waiting task (NULL if none) */ /* AIO related stuff */ struct kiocb *iocb; /* kiocb */ ssize_t result; /* IO result */ /* * pages[] (and any fields placed after it) are not zeroed out at * allocation time. Don't add new fields after pages[] unless you * wish that they not be zeroed. */ union { struct page *pages[DIO_PAGES]; /* page buffer */ struct work_struct complete_work;/* deferred AIO completion */ }; } ____cacheline_aligned_in_smp; static struct kmem_cache *dio_cache __ro_after_init; /* * How many pages are in the queue? */ static inline unsigned dio_pages_present(struct dio_submit *sdio) { return sdio->tail - sdio->head; } /* * Go grab and pin some userspace pages. Typically we'll get 64 at a time. */ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) { struct page **pages = dio->pages; const enum req_op dio_op = dio->opf & REQ_OP_MASK; ssize_t ret; ret = iov_iter_extract_pages(sdio->iter, &pages, LONG_MAX, DIO_PAGES, 0, &sdio->from); if (ret < 0 && sdio->blocks_available && dio_op == REQ_OP_WRITE) { /* * A memory fault, but the filesystem has some outstanding * mapped blocks. We need to use those blocks up to avoid * leaking stale data in the file. */ if (dio->page_errors == 0) dio->page_errors = ret; dio->pages[0] = ZERO_PAGE(0); sdio->head = 0; sdio->tail = 1; sdio->from = 0; sdio->to = PAGE_SIZE; return 0; } if (ret >= 0) { ret += sdio->from; sdio->head = 0; sdio->tail = (ret + PAGE_SIZE - 1) / PAGE_SIZE; sdio->to = ((ret - 1) & (PAGE_SIZE - 1)) + 1; return 0; } return ret; } /* * Get another userspace page. Returns an ERR_PTR on error. Pages are * buffered inside the dio so that we can call iov_iter_extract_pages() * against a decent number of pages, less frequently. To provide nicer use of * the L1 cache. */ static inline struct page *dio_get_page(struct dio *dio, struct dio_submit *sdio) { if (dio_pages_present(sdio) == 0) { int ret; ret = dio_refill_pages(dio, sdio); if (ret) return ERR_PTR(ret); BUG_ON(dio_pages_present(sdio) == 0); } return dio->pages[sdio->head]; } static void dio_pin_page(struct dio *dio, struct page *page) { if (dio->is_pinned) folio_add_pin(page_folio(page)); } static void dio_unpin_page(struct dio *dio, struct page *page) { if (dio->is_pinned) unpin_user_page(page); } /* * dio_complete() - called when all DIO BIO I/O has been completed * * This drops i_dio_count, lets interested parties know that a DIO operation * has completed, and calculates the resulting return code for the operation. * * It lets the filesystem know if it registered an interest earlier via * get_block. Pass the private field of the map buffer_head so that * filesystems can use it to hold additional state between get_block calls and * dio_complete. */ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags) { const enum req_op dio_op = dio->opf & REQ_OP_MASK; loff_t offset = dio->iocb->ki_pos; ssize_t transferred = 0; int err; /* * AIO submission can race with bio completion to get here while * expecting to have the last io completed by bio completion. * In that case -EIOCBQUEUED is in fact not an error we want * to preserve through this call. */ if (ret == -EIOCBQUEUED) ret = 0; if (dio->result) { transferred = dio->result; /* Check for short read case */ if (dio_op == REQ_OP_READ && ((offset + transferred) > dio->i_size)) transferred = dio->i_size - offset; /* ignore EFAULT if some IO has been done */ if (unlikely(ret == -EFAULT) && transferred) ret = 0; } if (ret == 0) ret = dio->page_errors; if (ret == 0) ret = dio->io_error; if (ret == 0) ret = transferred; if (dio->end_io) { // XXX: ki_pos?? err = dio->end_io(dio->iocb, offset, ret, dio->private); if (err) ret = err; } /* * Try again to invalidate clean pages which might have been cached by * non-direct readahead, or faulted in by get_user_pages() if the source * of the write was an mmap'ed region of the file we're writing. Either * one is a pretty crazy thing to do, so we don't support it 100%. If * this invalidation fails, tough, the write still worked... * * And this page cache invalidation has to be after dio->end_io(), as * some filesystems convert unwritten extents to real allocations in * end_io() when necessary, otherwise a racing buffer read would cache * zeros from unwritten extents. */ if (flags & DIO_COMPLETE_INVALIDATE && ret > 0 && dio_op == REQ_OP_WRITE) kiocb_invalidate_post_direct_write(dio->iocb, ret); inode_dio_end(dio->inode); if (flags & DIO_COMPLETE_ASYNC) { /* * generic_write_sync expects ki_pos to have been updated * already, but the submission path only does this for * synchronous I/O. */ dio->iocb->ki_pos += transferred; if (ret > 0 && dio_op == REQ_OP_WRITE) ret = generic_write_sync(dio->iocb, ret); dio->iocb->ki_complete(dio->iocb, ret); } kmem_cache_free(dio_cache, dio); return ret; } static void dio_aio_complete_work(struct work_struct *work) { struct dio *dio = container_of(work, struct dio, complete_work); dio_complete(dio, 0, DIO_COMPLETE_ASYNC | DIO_COMPLETE_INVALIDATE); } static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio); /* * Asynchronous IO callback. */ static void dio_bio_end_aio(struct bio *bio) { struct dio *dio = bio->bi_private; const enum req_op dio_op = dio->opf & REQ_OP_MASK; unsigned long remaining; unsigned long flags; bool defer_completion = false; /* cleanup the bio */ dio_bio_complete(dio, bio); spin_lock_irqsave(&dio->bio_lock, flags); remaining = --dio->refcount; if (remaining == 1 && dio->waiter) wake_up_process(dio->waiter); spin_unlock_irqrestore(&dio->bio_lock, flags); if (remaining == 0) { /* * Defer completion when defer_completion is set or * when the inode has pages mapped and this is AIO write. * We need to invalidate those pages because there is a * chance they contain stale data in the case buffered IO * went in between AIO submission and completion into the * same region. */ if (dio->result) defer_completion = dio->defer_completion || (dio_op == REQ_OP_WRITE && dio->inode->i_mapping->nrpages); if (defer_completion) { INIT_WORK(&dio->complete_work, dio_aio_complete_work); queue_work(dio->inode->i_sb->s_dio_done_wq, &dio->complete_work); } else { dio_complete(dio, 0, DIO_COMPLETE_ASYNC); } } } /* * The BIO completion handler simply queues the BIO up for the process-context * handler. * * During I/O bi_private points at the dio. After I/O, bi_private is used to * implement a singly-linked list of completed BIOs, at dio->bio_list. */ static void dio_bio_end_io(struct bio *bio) { struct dio *dio = bio->bi_private; unsigned long flags; spin_lock_irqsave(&dio->bio_lock, flags); bio->bi_private = dio->bio_list; dio->bio_list = bio; if (--dio->refcount == 1 && dio->waiter) wake_up_process(dio->waiter); spin_unlock_irqrestore(&dio->bio_lock, flags); } static inline void dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, struct block_device *bdev, sector_t first_sector, int nr_vecs) { struct bio *bio; /* * bio_alloc() is guaranteed to return a bio when allowed to sleep and * we request a valid number of vectors. */ bio = bio_alloc(bdev, nr_vecs, dio->opf, GFP_KERNEL); bio->bi_iter.bi_sector = first_sector; if (dio->is_async) bio->bi_end_io = dio_bio_end_aio; else bio->bi_end_io = dio_bio_end_io; if (dio->is_pinned) bio_set_flag(bio, BIO_PAGE_PINNED); bio->bi_write_hint = file_inode(dio->iocb->ki_filp)->i_write_hint; sdio->bio = bio; sdio->logical_offset_in_bio = sdio->cur_page_fs_offset; } /* * In the AIO read case we speculatively dirty the pages before starting IO. * During IO completion, any of these pages which happen to have been written * back will be redirtied by bio_check_pages_dirty(). * * bios hold a dio reference between submit_bio and ->end_io. */ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) { const enum req_op dio_op = dio->opf & REQ_OP_MASK; struct bio *bio = sdio->bio; unsigned long flags; bio->bi_private = dio; spin_lock_irqsave(&dio->bio_lock, flags); dio->refcount++; spin_unlock_irqrestore(&dio->bio_lock, flags); if (dio->is_async && dio_op == REQ_OP_READ && dio->should_dirty) bio_set_pages_dirty(bio); dio->bio_disk = bio->bi_bdev->bd_disk; submit_bio(bio); sdio->bio = NULL; sdio->boundary = 0; sdio->logical_offset_in_bio = 0; } /* * Release any resources in case of a failure */ static inline void dio_cleanup(struct dio *dio, struct dio_submit *sdio) { if (dio->is_pinned) unpin_user_pages(dio->pages + sdio->head, sdio->tail - sdio->head); sdio->head = sdio->tail; } /* * Wait for the next BIO to complete. Remove it and return it. NULL is * returned once all BIOs have been completed. This must only be called once * all bios have been issued so that dio->refcount can only decrease. This * requires that the caller hold a reference on the dio. */ static struct bio *dio_await_one(struct dio *dio) { unsigned long flags; struct bio *bio = NULL; spin_lock_irqsave(&dio->bio_lock, flags); /* * Wait as long as the list is empty and there are bios in flight. bio * completion drops the count, maybe adds to the list, and wakes while * holding the bio_lock so we don't need set_current_state()'s barrier * and can call it after testing our condition. */ while (dio->refcount > 1 && dio->bio_list == NULL) { __set_current_state(TASK_UNINTERRUPTIBLE); dio->waiter = current; spin_unlock_irqrestore(&dio->bio_lock, flags); blk_io_schedule(); /* wake up sets us TASK_RUNNING */ spin_lock_irqsave(&dio->bio_lock, flags); dio->waiter = NULL; } if (dio->bio_list) { bio = dio->bio_list; dio->bio_list = bio->bi_private; } spin_unlock_irqrestore(&dio->bio_lock, flags); return bio; } /* * Process one completed BIO. No locks are held. */ static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio) { blk_status_t err = bio->bi_status; const enum req_op dio_op = dio->opf & REQ_OP_MASK; bool should_dirty = dio_op == REQ_OP_READ && dio->should_dirty; if (err) { if (err == BLK_STS_AGAIN && (bio->bi_opf & REQ_NOWAIT)) dio->io_error = -EAGAIN; else dio->io_error = -EIO; } if (dio->is_async && should_dirty) { bio_check_pages_dirty(bio); /* transfers ownership */ } else { bio_release_pages(bio, should_dirty); bio_put(bio); } return err; } /* * Wait on and process all in-flight BIOs. This must only be called once * all bios have been issued so that the refcount can only decrease. * This just waits for all bios to make it through dio_bio_complete. IO * errors are propagated through dio->io_error and should be propagated via * dio_complete(). */ static void dio_await_completion(struct dio *dio) { struct bio *bio; do { bio = dio_await_one(dio); if (bio) dio_bio_complete(dio, bio); } while (bio); } /* * A really large O_DIRECT read or write can generate a lot of BIOs. So * to keep the memory consumption sane we periodically reap any completed BIOs * during the BIO generation phase. * * This also helps to limit the peak amount of pinned userspace memory. */ static inline int dio_bio_reap(struct dio *dio, struct dio_submit *sdio) { int ret = 0; if (sdio->reap_counter++ >= 64) { while (dio->bio_list) { unsigned long flags; struct bio *bio; int ret2; spin_lock_irqsave(&dio->bio_lock, flags); bio = dio->bio_list; dio->bio_list = bio->bi_private; spin_unlock_irqrestore(&dio->bio_lock, flags); ret2 = blk_status_to_errno(dio_bio_complete(dio, bio)); if (ret == 0) ret = ret2; } sdio->reap_counter = 0; } return ret; } static int dio_set_defer_completion(struct dio *dio) { struct super_block *sb = dio->inode->i_sb; if (dio->defer_completion) return 0; dio->defer_completion = true; if (!sb->s_dio_done_wq) return sb_init_dio_done_wq(sb); return 0; } /* * Call into the fs to map some more disk blocks. We record the current number * of available blocks at sdio->blocks_available. These are in units of the * fs blocksize, i_blocksize(inode). * * The fs is allowed to map lots of blocks at once. If it wants to do that, * it uses the passed inode-relative block number as the file offset, as usual. * * get_block() is passed the number of i_blkbits-sized blocks which direct_io * has remaining to do. The fs should not map more than this number of blocks. * * If the fs has mapped a lot of blocks, it should populate bh->b_size to * indicate how much contiguous disk space has been made available at * bh->b_blocknr. * * If *any* of the mapped blocks are new, then the fs must set buffer_new(). * This isn't very efficient... * * In the case of filesystem holes: the fs may return an arbitrarily-large * hole by returning an appropriate value in b_size and by clearing * buffer_mapped(). However the direct-io code will only process holes one * block at a time - it will repeatedly call get_block() as it walks the hole. */ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio, struct buffer_head *map_bh) { const enum req_op dio_op = dio->opf & REQ_OP_MASK; int ret; sector_t fs_startblk; /* Into file, in filesystem-sized blocks */ sector_t fs_endblk; /* Into file, in filesystem-sized blocks */ unsigned long fs_count; /* Number of filesystem-sized blocks */ int create; unsigned int i_blkbits = sdio->blkbits + sdio->blkfactor; loff_t i_size; /* * If there was a memory error and we've overwritten all the * mapped blocks then we can now return that memory error */ ret = dio->page_errors; if (ret == 0) { BUG_ON(sdio->block_in_file >= sdio->final_block_in_request); fs_startblk = sdio->block_in_file >> sdio->blkfactor; fs_endblk = (sdio->final_block_in_request - 1) >> sdio->blkfactor; fs_count = fs_endblk - fs_startblk + 1; map_bh->b_state = 0; map_bh->b_size = fs_count << i_blkbits; /* * For writes that could fill holes inside i_size on a * DIO_SKIP_HOLES filesystem we forbid block creations: only * overwrites are permitted. We will return early to the caller * once we see an unmapped buffer head returned, and the caller * will fall back to buffered I/O. * * Otherwise the decision is left to the get_blocks method, * which may decide to handle it or also return an unmapped * buffer head. */ create = dio_op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { i_size = i_size_read(dio->inode); if (i_size && fs_startblk <= (i_size - 1) >> i_blkbits) create = 0; } ret = (*sdio->get_block)(dio->inode, fs_startblk, map_bh, create); /* Store for completion */ dio->private = map_bh->b_private; if (ret == 0 && buffer_defer_completion(map_bh)) ret = dio_set_defer_completion(dio); } return ret; } /* * There is no bio. Make one now. */ static inline int dio_new_bio(struct dio *dio, struct dio_submit *sdio, sector_t start_sector, struct buffer_head *map_bh) { sector_t sector; int ret, nr_pages; ret = dio_bio_reap(dio, sdio); if (ret) goto out; sector = start_sector << (sdio->blkbits - 9); nr_pages = bio_max_segs(sdio->pages_in_io); BUG_ON(nr_pages <= 0); dio_bio_alloc(dio, sdio, map_bh->b_bdev, sector, nr_pages); sdio->boundary = 0; out: return ret; } /* * Attempt to put the current chunk of 'cur_page' into the current BIO. If * that was successful then update final_block_in_bio and take a ref against * the just-added page. * * Return zero on success. Non-zero means the caller needs to start a new BIO. */ static inline int dio_bio_add_page(struct dio *dio, struct dio_submit *sdio) { int ret; ret = bio_add_page(sdio->bio, sdio->cur_page, sdio->cur_page_len, sdio->cur_page_offset); if (ret == sdio->cur_page_len) { /* * Decrement count only, if we are done with this page */ if ((sdio->cur_page_len + sdio->cur_page_offset) == PAGE_SIZE) sdio->pages_in_io--; dio_pin_page(dio, sdio->cur_page); sdio->final_block_in_bio = sdio->cur_page_block + (sdio->cur_page_len >> sdio->blkbits); ret = 0; } else { ret = 1; } return ret; } /* * Put cur_page under IO. The section of cur_page which is described by * cur_page_offset,cur_page_len is put into a BIO. The section of cur_page * starts on-disk at cur_page_block. * * We take a ref against the page here (on behalf of its presence in the bio). * * The caller of this function is responsible for removing cur_page from the * dio, and for dropping the refcount which came from that presence. */ static inline int dio_send_cur_page(struct dio *dio, struct dio_submit *sdio, struct buffer_head *map_bh) { int ret = 0; if (sdio->bio) { loff_t cur_offset = sdio->cur_page_fs_offset; loff_t bio_next_offset = sdio->logical_offset_in_bio + sdio->bio->bi_iter.bi_size; /* * See whether this new request is contiguous with the old. * * Btrfs cannot handle having logically non-contiguous requests * submitted. For example if you have * * Logical: [0-4095][HOLE][8192-12287] * Physical: [0-4095] [4096-8191] * * We cannot submit those pages together as one BIO. So if our * current logical offset in the file does not equal what would * be the next logical offset in the bio, submit the bio we * have. */ if (sdio->final_block_in_bio != sdio->cur_page_block || cur_offset != bio_next_offset) dio_bio_submit(dio, sdio); } if (sdio->bio == NULL) { ret = dio_new_bio(dio, sdio, sdio->cur_page_block, map_bh); if (ret) goto out; } if (dio_bio_add_page(dio, sdio) != 0) { dio_bio_submit(dio, sdio); ret = dio_new_bio(dio, sdio, sdio->cur_page_block, map_bh); if (ret == 0) { ret = dio_bio_add_page(dio, sdio); BUG_ON(ret != 0); } } out: return ret; } /* * An autonomous function to put a chunk of a page under deferred IO. * * The caller doesn't actually know (or care) whether this piece of page is in * a BIO, or is under IO or whatever. We just take care of all possible * situations here. The separation between the logic of do_direct_IO() and * that of submit_page_section() is important for clarity. Please don't break. * * The chunk of page starts on-disk at blocknr. * * We perform deferred IO, by recording the last-submitted page inside our * private part of the dio structure. If possible, we just expand the IO * across that page here. * * If that doesn't work out then we put the old page into the bio and add this * page to the dio instead. */ static inline int submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page, unsigned offset, unsigned len, sector_t blocknr, struct buffer_head *map_bh) { const enum req_op dio_op = dio->opf & REQ_OP_MASK; int ret = 0; int boundary = sdio->boundary; /* dio_send_cur_page may clear it */ if (dio_op == REQ_OP_WRITE) { /* * Read accounting is performed in submit_bio() */ task_io_account_write(len); } /* * Can we just grow the current page's presence in the dio? */ if (sdio->cur_page == page && sdio->cur_page_offset + sdio->cur_page_len == offset && sdio->cur_page_block + (sdio->cur_page_len >> sdio->blkbits) == blocknr) { sdio->cur_page_len += len; goto out; } /* * If there's a deferred page already there then send it. */ if (sdio->cur_page) { ret = dio_send_cur_page(dio, sdio, map_bh); dio_unpin_page(dio, sdio->cur_page); sdio->cur_page = NULL; if (ret) return ret; } dio_pin_page(dio, page); /* It is in dio */ sdio->cur_page = page; sdio->cur_page_offset = offset; sdio->cur_page_len = len; sdio->cur_page_block = blocknr; sdio->cur_page_fs_offset = sdio->block_in_file << sdio->blkbits; out: /* * If boundary then we want to schedule the IO now to * avoid metadata seeks. */ if (boundary) { ret = dio_send_cur_page(dio, sdio, map_bh); if (sdio->bio) dio_bio_submit(dio, sdio); dio_unpin_page(dio, sdio->cur_page); sdio->cur_page = NULL; } return ret; } /* * If we are not writing the entire block and get_block() allocated * the block for us, we need to fill-in the unused portion of the * block with zeros. This happens only if user-buffer, fileoffset or * io length is not filesystem block-size multiple. * * `end' is zero if we're doing the start of the IO, 1 at the end of the * IO. */ static inline void dio_zero_block(struct dio *dio, struct dio_submit *sdio, int end, struct buffer_head *map_bh) { unsigned dio_blocks_per_fs_block; unsigned this_chunk_blocks; /* In dio_blocks */ unsigned this_chunk_bytes; struct page *page; sdio->start_zero_done = 1; if (!sdio->blkfactor || !buffer_new(map_bh)) return; dio_blocks_per_fs_block = 1 << sdio->blkfactor; this_chunk_blocks = sdio->block_in_file & (dio_blocks_per_fs_block - 1); if (!this_chunk_blocks) return; /* * We need to zero out part of an fs block. It is either at the * beginning or the end of the fs block. */ if (end) this_chunk_blocks = dio_blocks_per_fs_block - this_chunk_blocks; this_chunk_bytes = this_chunk_blocks << sdio->blkbits; page = ZERO_PAGE(0); if (submit_page_section(dio, sdio, page, 0, this_chunk_bytes, sdio->next_block_for_io, map_bh)) return; sdio->next_block_for_io += this_chunk_blocks; } /* * Walk the user pages, and the file, mapping blocks to disk and generating * a sequence of (page,offset,len,block) mappings. These mappings are injected * into submit_page_section(), which takes care of the next stage of submission * * Direct IO against a blockdev is different from a file. Because we can * happily perform page-sized but 512-byte aligned IOs. It is important that * blockdev IO be able to have fine alignment and large sizes. * * So what we do is to permit the ->get_block function to populate bh.b_size * with the size of IO which is permitted at this offset and this i_blkbits. * * For best results, the blockdev should be set up with 512-byte i_blkbits and * it should set b_size to PAGE_SIZE or more inside get_block(). This gives * fine alignment but still allows this function to work in PAGE_SIZE units. */ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio, struct buffer_head *map_bh) { const enum req_op dio_op = dio->opf & REQ_OP_MASK; const unsigned blkbits = sdio->blkbits; const unsigned i_blkbits = blkbits + sdio->blkfactor; int ret = 0; while (sdio->block_in_file < sdio->final_block_in_request) { struct page *page; size_t from, to; page = dio_get_page(dio, sdio); if (IS_ERR(page)) { ret = PTR_ERR(page); goto out; } from = sdio->head ? 0 : sdio->from; to = (sdio->head == sdio->tail - 1) ? sdio->to : PAGE_SIZE; sdio->head++; while (from < to) { unsigned this_chunk_bytes; /* # of bytes mapped */ unsigned this_chunk_blocks; /* # of blocks */ unsigned u; if (sdio->blocks_available == 0) { /* * Need to go and map some more disk */ unsigned long blkmask; unsigned long dio_remainder; ret = get_more_blocks(dio, sdio, map_bh); if (ret) { dio_unpin_page(dio, page); goto out; } if (!buffer_mapped(map_bh)) goto do_holes; sdio->blocks_available = map_bh->b_size >> blkbits; sdio->next_block_for_io = map_bh->b_blocknr << sdio->blkfactor; if (buffer_new(map_bh)) { clean_bdev_aliases( map_bh->b_bdev, map_bh->b_blocknr, map_bh->b_size >> i_blkbits); } if (!sdio->blkfactor) goto do_holes; blkmask = (1 << sdio->blkfactor) - 1; dio_remainder = (sdio->block_in_file & blkmask); /* * If we are at the start of IO and that IO * starts partway into a fs-block, * dio_remainder will be non-zero. If the IO * is a read then we can simply advance the IO * cursor to the first block which is to be * read. But if the IO is a write and the * block was newly allocated we cannot do that; * the start of the fs block must be zeroed out * on-disk */ if (!buffer_new(map_bh)) sdio->next_block_for_io += dio_remainder; sdio->blocks_available -= dio_remainder; } do_holes: /* Handle holes */ if (!buffer_mapped(map_bh)) { loff_t i_size_aligned; /* AKPM: eargh, -ENOTBLK is a hack */ if (dio_op == REQ_OP_WRITE) { dio_unpin_page(dio, page); return -ENOTBLK; } /* * Be sure to account for a partial block as the * last block in the file */ i_size_aligned = ALIGN(i_size_read(dio->inode), 1 << blkbits); if (sdio->block_in_file >= i_size_aligned >> blkbits) { /* We hit eof */ dio_unpin_page(dio, page); goto out; } zero_user(page, from, 1 << blkbits); sdio->block_in_file++; from += 1 << blkbits; dio->result += 1 << blkbits; goto next_block; } /* * If we're performing IO which has an alignment which * is finer than the underlying fs, go check to see if * we must zero out the start of this block. */ if (unlikely(sdio->blkfactor && !sdio->start_zero_done)) dio_zero_block(dio, sdio, 0, map_bh); /* * Work out, in this_chunk_blocks, how much disk we * can add to this page */ this_chunk_blocks = sdio->blocks_available; u = (to - from) >> blkbits; if (this_chunk_blocks > u) this_chunk_blocks = u; u = sdio->final_block_in_request - sdio->block_in_file; if (this_chunk_blocks > u) this_chunk_blocks = u; this_chunk_bytes = this_chunk_blocks << blkbits; BUG_ON(this_chunk_bytes == 0); if (this_chunk_blocks == sdio->blocks_available) sdio->boundary = buffer_boundary(map_bh); ret = submit_page_section(dio, sdio, page, from, this_chunk_bytes, sdio->next_block_for_io, map_bh); if (ret) { dio_unpin_page(dio, page); goto out; } sdio->next_block_for_io += this_chunk_blocks; sdio->block_in_file += this_chunk_blocks; from += this_chunk_bytes; dio->result += this_chunk_bytes; sdio->blocks_available -= this_chunk_blocks; next_block: BUG_ON(sdio->block_in_file > sdio->final_block_in_request); if (sdio->block_in_file == sdio->final_block_in_request) break; } /* Drop the pin which was taken in get_user_pages() */ dio_unpin_page(dio, page); } out: return ret; } static inline int drop_refcount(struct dio *dio) { int ret2; unsigned long flags; /* * Sync will always be dropping the final ref and completing the * operation. AIO can if it was a broken operation described above or * in fact if all the bios race to complete before we get here. In * that case dio_complete() translates the EIOCBQUEUED into the proper * return code that the caller will hand to ->complete(). * * This is managed by the bio_lock instead of being an atomic_t so that * completion paths can drop their ref and use the remaining count to * decide to wake the submission path atomically. */ spin_lock_irqsave(&dio->bio_lock, flags); ret2 = --dio->refcount; spin_unlock_irqrestore(&dio->bio_lock, flags); return ret2; } /* * This is a library function for use by filesystem drivers. * * The locking rules are governed by the flags parameter: * - if the flags value contains DIO_LOCKING we use a fancy locking * scheme for dumb filesystems. * For writes this function is called under i_mutex and returns with * i_mutex held, for reads, i_mutex is not held on entry, but it is * taken and dropped again before returning. * - if the flags value does NOT contain DIO_LOCKING we don't use any * internal locking but rather rely on the filesystem to synchronize * direct I/O reads/writes versus each other and truncate. * * To help with locking against truncate we incremented the i_dio_count * counter before starting direct I/O, and decrement it once we are done. * Truncate can wait for it to reach zero to provide exclusion. It is * expected that filesystem provide exclusion between new direct I/O * and truncates. For DIO_LOCKING filesystems this is done by i_mutex, * but other filesystems need to take care of this on their own. * * NOTE: if you pass "sdio" to anything by pointer make sure that function * is always inlined. Otherwise gcc is unable to split the structure into * individual fields and will generate much worse code. This is important * for the whole file. */ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, int flags) { unsigned i_blkbits = READ_ONCE(inode->i_blkbits); unsigned blkbits = i_blkbits; unsigned blocksize_mask = (1 << blkbits) - 1; ssize_t retval = -EINVAL; const size_t count = iov_iter_count(iter); loff_t offset = iocb->ki_pos; const loff_t end = offset + count; struct dio *dio; struct dio_submit sdio = { NULL, }; struct buffer_head map_bh = { 0, }; struct blk_plug plug; unsigned long align = offset | iov_iter_alignment(iter); /* watch out for a 0 len io from a tricksy fs */ if (iov_iter_rw(iter) == READ && !count) return 0; dio = kmem_cache_alloc(dio_cache, GFP_KERNEL); if (!dio) return -ENOMEM; /* * Believe it or not, zeroing out the page array caused a .5% * performance regression in a database benchmark. So, we take * care to only zero out what's needed. */ memset(dio, 0, offsetof(struct dio, pages)); dio->flags = flags; if (dio->flags & DIO_LOCKING && iov_iter_rw(iter) == READ) { /* will be released by direct_io_worker */ inode_lock(inode); } dio->is_pinned = iov_iter_extract_will_pin(iter); /* Once we sampled i_size check for reads beyond EOF */ dio->i_size = i_size_read(inode); if (iov_iter_rw(iter) == READ && offset >= dio->i_size) { retval = 0; goto fail_dio; } if (align & blocksize_mask) { if (bdev) blkbits = blksize_bits(bdev_logical_block_size(bdev)); blocksize_mask = (1 << blkbits) - 1; if (align & blocksize_mask) goto fail_dio; } if (dio->flags & DIO_LOCKING && iov_iter_rw(iter) == READ) { struct address_space *mapping = iocb->ki_filp->f_mapping; retval = filemap_write_and_wait_range(mapping, offset, end - 1); if (retval) goto fail_dio; } /* * For file extending writes updating i_size before data writeouts * complete can expose uninitialized blocks in dumb filesystems. * In that case we need to wait for I/O completion even if asked * for an asynchronous write. */ if (is_sync_kiocb(iocb)) dio->is_async = false; else if (iov_iter_rw(iter) == WRITE && end > i_size_read(inode)) dio->is_async = false; else dio->is_async = true; dio->inode = inode; if (iov_iter_rw(iter) == WRITE) { dio->opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; if (iocb->ki_flags & IOCB_NOWAIT) dio->opf |= REQ_NOWAIT; } else { dio->opf = REQ_OP_READ; } /* * For AIO O_(D)SYNC writes we need to defer completions to a workqueue * so that we can call ->fsync. */ if (dio->is_async && iov_iter_rw(iter) == WRITE) { retval = 0; if (iocb_is_dsync(iocb)) retval = dio_set_defer_completion(dio); else if (!dio->inode->i_sb->s_dio_done_wq) { /* * In case of AIO write racing with buffered read we * need to defer completion. We can't decide this now, * however the workqueue needs to be initialized here. */ retval = sb_init_dio_done_wq(dio->inode->i_sb); } if (retval) goto fail_dio; } /* * Will be decremented at I/O completion time. */ inode_dio_begin(inode); sdio.blkbits = blkbits; sdio.blkfactor = i_blkbits - blkbits; sdio.block_in_file = offset >> blkbits; sdio.get_block = get_block; dio->end_io = end_io; sdio.final_block_in_bio = -1; sdio.next_block_for_io = -1; dio->iocb = iocb; spin_lock_init(&dio->bio_lock); dio->refcount = 1; dio->should_dirty = user_backed_iter(iter) && iov_iter_rw(iter) == READ; sdio.iter = iter; sdio.final_block_in_request = end >> blkbits; /* * In case of non-aligned buffers, we may need 2 more * pages since we need to zero out first and last block. */ if (unlikely(sdio.blkfactor)) sdio.pages_in_io = 2; sdio.pages_in_io += iov_iter_npages(iter, INT_MAX); blk_start_plug(&plug); retval = do_direct_IO(dio, &sdio, &map_bh); if (retval) dio_cleanup(dio, &sdio); if (retval == -ENOTBLK) { /* * The remaining part of the request will be * handled by buffered I/O when we return */ retval = 0; } /* * There may be some unwritten disk at the end of a part-written * fs-block-sized block. Go zero that now. */ dio_zero_block(dio, &sdio, 1, &map_bh); if (sdio.cur_page) { ssize_t ret2; ret2 = dio_send_cur_page(dio, &sdio, &map_bh); if (retval == 0) retval = ret2; dio_unpin_page(dio, sdio.cur_page); sdio.cur_page = NULL; } if (sdio.bio) dio_bio_submit(dio, &sdio); blk_finish_plug(&plug); /* * It is possible that, we return short IO due to end of file. * In that case, we need to release all the pages we got hold on. */ dio_cleanup(dio, &sdio); /* * All block lookups have been performed. For READ requests * we can let i_mutex go now that its achieved its purpose * of protecting us from looking up uninitialized blocks. */ if (iov_iter_rw(iter) == READ && (dio->flags & DIO_LOCKING)) inode_unlock(dio->inode); /* * The only time we want to leave bios in flight is when a successful * partial aio read or full aio write have been setup. In that case * bio completion will call aio_complete. The only time it's safe to * call aio_complete is when we return -EIOCBQUEUED, so we key on that. * This had *better* be the only place that raises -EIOCBQUEUED. */ BUG_ON(retval == -EIOCBQUEUED); if (dio->is_async && retval == 0 && dio->result && (iov_iter_rw(iter) == READ || dio->result == count)) retval = -EIOCBQUEUED; else dio_await_completion(dio); if (drop_refcount(dio) == 0) { retval = dio_complete(dio, retval, DIO_COMPLETE_INVALIDATE); } else BUG_ON(retval != -EIOCBQUEUED); return retval; fail_dio: if (dio->flags & DIO_LOCKING && iov_iter_rw(iter) == READ) inode_unlock(inode); kmem_cache_free(dio_cache, dio); return retval; } EXPORT_SYMBOL(__blockdev_direct_IO); static __init int dio_init(void) { dio_cache = KMEM_CACHE(dio, SLAB_PANIC); return 0; } module_init(dio_init) |
| 4 4 4 183 30 13 13 2 11 4 29 4 22 22 20 13 1 4 22 22 15 12 20 21 11 187 187 182 2 1 29 34 183 1 20 9 11 184 184 30 182 41 41 25 29 29 29 15 14 2 11 2 16 24 24 49 1 47 12 12 4 43 11 35 13 13 16 41 3 4 13 1 70 2 3 30 44 9 27 27 9 2 1 3 2 44 44 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hfsplus/extents.c * * Copyright (C) 2001 * Brad Boyer (flar@allandria.com) * (C) 2003 Ardis Technologies <roman@ardistech.com> * * Handling of Extents both in catalog and extents overflow trees */ #include <linux/errno.h> #include <linux/fs.h> #include <linux/pagemap.h> #include "hfsplus_fs.h" #include "hfsplus_raw.h" /* Compare two extents keys, returns 0 on same, pos/neg for difference */ int hfsplus_ext_cmp_key(const hfsplus_btree_key *k1, const hfsplus_btree_key *k2) { __be32 k1id, k2id; __be32 k1s, k2s; k1id = k1->ext.cnid; k2id = k2->ext.cnid; if (k1id != k2id) return be32_to_cpu(k1id) < be32_to_cpu(k2id) ? -1 : 1; if (k1->ext.fork_type != k2->ext.fork_type) return k1->ext.fork_type < k2->ext.fork_type ? -1 : 1; k1s = k1->ext.start_block; k2s = k2->ext.start_block; if (k1s == k2s) return 0; return be32_to_cpu(k1s) < be32_to_cpu(k2s) ? -1 : 1; } static void hfsplus_ext_build_key(hfsplus_btree_key *key, u32 cnid, u32 block, u8 type) { key->key_len = cpu_to_be16(HFSPLUS_EXT_KEYLEN - 2); key->ext.cnid = cpu_to_be32(cnid); key->ext.start_block = cpu_to_be32(block); key->ext.fork_type = type; key->ext.pad = 0; } static u32 hfsplus_ext_find_block(struct hfsplus_extent *ext, u32 off) { int i; u32 count; for (i = 0; i < 8; ext++, i++) { count = be32_to_cpu(ext->block_count); if (off < count) return be32_to_cpu(ext->start_block) + off; off -= count; } /* panic? */ return 0; } static int hfsplus_ext_block_count(struct hfsplus_extent *ext) { int i; u32 count = 0; for (i = 0; i < 8; ext++, i++) count += be32_to_cpu(ext->block_count); return count; } static u32 hfsplus_ext_lastblock(struct hfsplus_extent *ext) { int i; ext += 7; for (i = 0; i < 7; ext--, i++) if (ext->block_count) break; return be32_to_cpu(ext->start_block) + be32_to_cpu(ext->block_count); } static int __hfsplus_ext_write_extent(struct inode *inode, struct hfs_find_data *fd) { struct hfsplus_inode_info *hip = HFSPLUS_I(inode); int res; WARN_ON(!mutex_is_locked(&hip->extents_lock)); hfsplus_ext_build_key(fd->search_key, inode->i_ino, hip->cached_start, HFSPLUS_IS_RSRC(inode) ? HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA); res = hfs_brec_find(fd, hfs_find_rec_by_key); if (hip->extent_state & HFSPLUS_EXT_NEW) { if (res != -ENOENT) return res; /* Fail early and avoid ENOSPC during the btree operation */ res = hfs_bmap_reserve(fd->tree, fd->tree->depth + 1); if (res) return res; hfs_brec_insert(fd, hip->cached_extents, sizeof(hfsplus_extent_rec)); hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); } else { if (res) return res; hfs_bnode_write(fd->bnode, hip->cached_extents, fd->entryoffset, fd->entrylength); hip->extent_state &= ~HFSPLUS_EXT_DIRTY; } /* * We can't just use hfsplus_mark_inode_dirty here, because we * also get called from hfsplus_write_inode, which should not * redirty the inode. Instead the callers have to be careful * to explicily mark the inode dirty, too. */ set_bit(HFSPLUS_I_EXT_DIRTY, &hip->flags); return 0; } static int hfsplus_ext_write_extent_locked(struct inode *inode) { int res = 0; if (HFSPLUS_I(inode)->extent_state & HFSPLUS_EXT_DIRTY) { struct hfs_find_data fd; res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd); if (res) return res; res = __hfsplus_ext_write_extent(inode, &fd); hfs_find_exit(&fd); } return res; } int hfsplus_ext_write_extent(struct inode *inode) { int res; mutex_lock(&HFSPLUS_I(inode)->extents_lock); res = hfsplus_ext_write_extent_locked(inode); mutex_unlock(&HFSPLUS_I(inode)->extents_lock); return res; } static inline int __hfsplus_ext_read_extent(struct hfs_find_data *fd, struct hfsplus_extent *extent, u32 cnid, u32 block, u8 type) { int res; hfsplus_ext_build_key(fd->search_key, cnid, block, type); fd->key->ext.cnid = 0; res = hfs_brec_find(fd, hfs_find_rec_by_key); if (res && res != -ENOENT) return res; if (fd->key->ext.cnid != fd->search_key->ext.cnid || fd->key->ext.fork_type != fd->search_key->ext.fork_type) return -ENOENT; if (fd->entrylength != sizeof(hfsplus_extent_rec)) return -EIO; hfs_bnode_read(fd->bnode, extent, fd->entryoffset, sizeof(hfsplus_extent_rec)); return 0; } static inline int __hfsplus_ext_cache_extent(struct hfs_find_data *fd, struct inode *inode, u32 block) { struct hfsplus_inode_info *hip = HFSPLUS_I(inode); int res; WARN_ON(!mutex_is_locked(&hip->extents_lock)); if (hip->extent_state & HFSPLUS_EXT_DIRTY) { res = __hfsplus_ext_write_extent(inode, fd); if (res) return res; } res = __hfsplus_ext_read_extent(fd, hip->cached_extents, inode->i_ino, block, HFSPLUS_IS_RSRC(inode) ? HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA); if (!res) { hip->cached_start = be32_to_cpu(fd->key->ext.start_block); hip->cached_blocks = hfsplus_ext_block_count(hip->cached_extents); } else { hip->cached_start = hip->cached_blocks = 0; hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); } return res; } static int hfsplus_ext_read_extent(struct inode *inode, u32 block) { struct hfsplus_inode_info *hip = HFSPLUS_I(inode); struct hfs_find_data fd; int res; if (block >= hip->cached_start && block < hip->cached_start + hip->cached_blocks) return 0; res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd); if (!res) { res = __hfsplus_ext_cache_extent(&fd, inode, block); hfs_find_exit(&fd); } return res; } /* Get a block at iblock for inode, possibly allocating if create */ int hfsplus_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct super_block *sb = inode->i_sb; struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); struct hfsplus_inode_info *hip = HFSPLUS_I(inode); int res = -EIO; u32 ablock, dblock, mask; sector_t sector; int was_dirty = 0; /* Convert inode block to disk allocation block */ ablock = iblock >> sbi->fs_shift; if (iblock >= hip->fs_blocks) { if (!create) return 0; if (iblock > hip->fs_blocks) return -EIO; if (ablock >= hip->alloc_blocks) { res = hfsplus_file_extend(inode, false); if (res) return res; } } else create = 0; if (ablock < hip->first_blocks) { dblock = hfsplus_ext_find_block(hip->first_extents, ablock); goto done; } if (inode->i_ino == HFSPLUS_EXT_CNID) return -EIO; mutex_lock(&hip->extents_lock); /* * hfsplus_ext_read_extent will write out a cached extent into * the extents btree. In that case we may have to mark the inode * dirty even for a pure read of an extent here. */ was_dirty = (hip->extent_state & HFSPLUS_EXT_DIRTY); res = hfsplus_ext_read_extent(inode, ablock); if (res) { mutex_unlock(&hip->extents_lock); return -EIO; } dblock = hfsplus_ext_find_block(hip->cached_extents, ablock - hip->cached_start); mutex_unlock(&hip->extents_lock); done: hfs_dbg(EXTENT, "get_block(%lu): %llu - %u\n", inode->i_ino, (long long)iblock, dblock); mask = (1 << sbi->fs_shift) - 1; sector = ((sector_t)dblock << sbi->fs_shift) + sbi->blockoffset + (iblock & mask); map_bh(bh_result, sb, sector); if (create) { set_buffer_new(bh_result); hip->phys_size += sb->s_blocksize; hip->fs_blocks++; inode_add_bytes(inode, sb->s_blocksize); } if (create || was_dirty) mark_inode_dirty(inode); return 0; } static void hfsplus_dump_extent(struct hfsplus_extent *extent) { int i; hfs_dbg(EXTENT, " "); for (i = 0; i < 8; i++) hfs_dbg_cont(EXTENT, " %u:%u", be32_to_cpu(extent[i].start_block), be32_to_cpu(extent[i].block_count)); hfs_dbg_cont(EXTENT, "\n"); } static int hfsplus_add_extent(struct hfsplus_extent *extent, u32 offset, u32 alloc_block, u32 block_count) { u32 count, start; int i; hfsplus_dump_extent(extent); for (i = 0; i < 8; extent++, i++) { count = be32_to_cpu(extent->block_count); if (offset == count) { start = be32_to_cpu(extent->start_block); if (alloc_block != start + count) { if (++i >= 8) return -ENOSPC; extent++; extent->start_block = cpu_to_be32(alloc_block); } else block_count += count; extent->block_count = cpu_to_be32(block_count); return 0; } else if (offset < count) break; offset -= count; } /* panic? */ return -EIO; } static int hfsplus_free_extents(struct super_block *sb, struct hfsplus_extent *extent, u32 offset, u32 block_nr) { u32 count, start; int i; int err = 0; /* Mapping the allocation file may lock the extent tree */ WARN_ON(mutex_is_locked(&HFSPLUS_SB(sb)->ext_tree->tree_lock)); hfsplus_dump_extent(extent); for (i = 0; i < 8; extent++, i++) { count = be32_to_cpu(extent->block_count); if (offset == count) goto found; else if (offset < count) break; offset -= count; } /* panic? */ return -EIO; found: for (;;) { start = be32_to_cpu(extent->start_block); if (count <= block_nr) { err = hfsplus_block_free(sb, start, count); if (err) { pr_err("can't free extent\n"); hfs_dbg(EXTENT, " start: %u count: %u\n", start, count); } extent->block_count = 0; extent->start_block = 0; block_nr -= count; } else { count -= block_nr; err = hfsplus_block_free(sb, start + count, block_nr); if (err) { pr_err("can't free extent\n"); hfs_dbg(EXTENT, " start: %u count: %u\n", start, count); } extent->block_count = cpu_to_be32(count); block_nr = 0; } if (!block_nr || !i) { /* * Try to free all extents and * return only last error */ return err; } i--; extent--; count = be32_to_cpu(extent->block_count); } } int hfsplus_free_fork(struct super_block *sb, u32 cnid, struct hfsplus_fork_raw *fork, int type) { struct hfs_find_data fd; hfsplus_extent_rec ext_entry; u32 total_blocks, blocks, start; int res, i; total_blocks = be32_to_cpu(fork->total_blocks); if (!total_blocks) return 0; blocks = 0; for (i = 0; i < 8; i++) blocks += be32_to_cpu(fork->extents[i].block_count); res = hfsplus_free_extents(sb, fork->extents, blocks, blocks); if (res) return res; if (total_blocks == blocks) return 0; res = hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd); if (res) return res; do { res = __hfsplus_ext_read_extent(&fd, ext_entry, cnid, total_blocks, type); if (res) break; start = be32_to_cpu(fd.key->ext.start_block); hfs_brec_remove(&fd); mutex_unlock(&fd.tree->tree_lock); hfsplus_free_extents(sb, ext_entry, total_blocks - start, total_blocks); total_blocks = start; mutex_lock_nested(&fd.tree->tree_lock, hfsplus_btree_lock_class(fd.tree)); } while (total_blocks > blocks); hfs_find_exit(&fd); return res; } int hfsplus_file_extend(struct inode *inode, bool zeroout) { struct super_block *sb = inode->i_sb; struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); struct hfsplus_inode_info *hip = HFSPLUS_I(inode); u32 start, len, goal; int res; if (sbi->alloc_file->i_size * 8 < sbi->total_blocks - sbi->free_blocks + 8) { /* extend alloc file */ pr_err_ratelimited("extend alloc file! (%llu,%u,%u)\n", sbi->alloc_file->i_size * 8, sbi->total_blocks, sbi->free_blocks); return -ENOSPC; } mutex_lock(&hip->extents_lock); if (hip->alloc_blocks == hip->first_blocks) goal = hfsplus_ext_lastblock(hip->first_extents); else { res = hfsplus_ext_read_extent(inode, hip->alloc_blocks); if (res) goto out; goal = hfsplus_ext_lastblock(hip->cached_extents); } len = hip->clump_blocks; start = hfsplus_block_allocate(sb, sbi->total_blocks, goal, &len); if (start >= sbi->total_blocks) { start = hfsplus_block_allocate(sb, goal, 0, &len); if (start >= goal) { res = -ENOSPC; goto out; } } if (zeroout) { res = sb_issue_zeroout(sb, start, len, GFP_NOFS); if (res) goto out; } hfs_dbg(EXTENT, "extend %lu: %u,%u\n", inode->i_ino, start, len); if (hip->alloc_blocks <= hip->first_blocks) { if (!hip->first_blocks) { hfs_dbg(EXTENT, "first extents\n"); /* no extents yet */ hip->first_extents[0].start_block = cpu_to_be32(start); hip->first_extents[0].block_count = cpu_to_be32(len); res = 0; } else { /* try to append to extents in inode */ res = hfsplus_add_extent(hip->first_extents, hip->alloc_blocks, start, len); if (res == -ENOSPC) goto insert_extent; } if (!res) { hfsplus_dump_extent(hip->first_extents); hip->first_blocks += len; } } else { res = hfsplus_add_extent(hip->cached_extents, hip->alloc_blocks - hip->cached_start, start, len); if (!res) { hfsplus_dump_extent(hip->cached_extents); hip->extent_state |= HFSPLUS_EXT_DIRTY; hip->cached_blocks += len; } else if (res == -ENOSPC) goto insert_extent; } out: if (!res) { hip->alloc_blocks += len; mutex_unlock(&hip->extents_lock); hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ALLOC_DIRTY); return 0; } mutex_unlock(&hip->extents_lock); return res; insert_extent: hfs_dbg(EXTENT, "insert new extent\n"); res = hfsplus_ext_write_extent_locked(inode); if (res) goto out; memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec)); hip->cached_extents[0].start_block = cpu_to_be32(start); hip->cached_extents[0].block_count = cpu_to_be32(len); hfsplus_dump_extent(hip->cached_extents); hip->extent_state |= HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW; hip->cached_start = hip->alloc_blocks; hip->cached_blocks = len; res = 0; goto out; } void hfsplus_file_truncate(struct inode *inode) { struct super_block *sb = inode->i_sb; struct hfsplus_inode_info *hip = HFSPLUS_I(inode); struct hfs_find_data fd; u32 alloc_cnt, blk_cnt, start; int res; hfs_dbg(INODE, "truncate: %lu, %llu -> %llu\n", inode->i_ino, (long long)hip->phys_size, inode->i_size); if (inode->i_size > hip->phys_size) { struct address_space *mapping = inode->i_mapping; struct folio *folio; void *fsdata = NULL; loff_t size = inode->i_size; res = hfsplus_write_begin(NULL, mapping, size, 0, &folio, &fsdata); if (res) return; res = generic_write_end(NULL, mapping, size, 0, 0, folio, fsdata); if (res < 0) return; mark_inode_dirty(inode); return; } else if (inode->i_size == hip->phys_size) return; blk_cnt = (inode->i_size + HFSPLUS_SB(sb)->alloc_blksz - 1) >> HFSPLUS_SB(sb)->alloc_blksz_shift; mutex_lock(&hip->extents_lock); alloc_cnt = hip->alloc_blocks; if (blk_cnt == alloc_cnt) goto out_unlock; res = hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd); if (res) { mutex_unlock(&hip->extents_lock); /* XXX: We lack error handling of hfsplus_file_truncate() */ return; } while (1) { if (alloc_cnt == hip->first_blocks) { mutex_unlock(&fd.tree->tree_lock); hfsplus_free_extents(sb, hip->first_extents, alloc_cnt, alloc_cnt - blk_cnt); hfsplus_dump_extent(hip->first_extents); hip->first_blocks = blk_cnt; mutex_lock_nested(&fd.tree->tree_lock, hfsplus_btree_lock_class(fd.tree)); break; } res = __hfsplus_ext_cache_extent(&fd, inode, alloc_cnt); if (res) break; start = hip->cached_start; if (blk_cnt <= start) hfs_brec_remove(&fd); mutex_unlock(&fd.tree->tree_lock); hfsplus_free_extents(sb, hip->cached_extents, alloc_cnt - start, alloc_cnt - blk_cnt); hfsplus_dump_extent(hip->cached_extents); mutex_lock_nested(&fd.tree->tree_lock, hfsplus_btree_lock_class(fd.tree)); if (blk_cnt > start) { hip->extent_state |= HFSPLUS_EXT_DIRTY; break; } alloc_cnt = start; hip->cached_start = hip->cached_blocks = 0; hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); } hfs_find_exit(&fd); hip->alloc_blocks = blk_cnt; out_unlock: mutex_unlock(&hip->extents_lock); hip->phys_size = inode->i_size; hip->fs_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; inode_set_bytes(inode, hip->fs_blocks << sb->s_blocksize_bits); hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ALLOC_DIRTY); } |
| 4672 3149 180 124 3375 7898 592 64 18 3712 4294 4283 4290 102 241 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 // Generated by scripts/atomic/gen-atomic-instrumented.sh // DO NOT MODIFY THIS FILE DIRECTLY /* * This file provoides atomic operations with explicit instrumentation (e.g. * KASAN, KCSAN), which should be used unless it is necessary to avoid * instrumentation. Where it is necessary to aovid instrumenation, the * raw_atomic*() operations should be used. */ #ifndef _LINUX_ATOMIC_INSTRUMENTED_H #define _LINUX_ATOMIC_INSTRUMENTED_H #include <linux/build_bug.h> #include <linux/compiler.h> #include <linux/instrumented.h> /** * atomic_read() - atomic load with relaxed ordering * @v: pointer to atomic_t * * Atomically loads the value of @v with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_read() there. * * Return: The value loaded from @v. */ static __always_inline int atomic_read(const atomic_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic_read(v); } /** * atomic_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic_t * * Atomically loads the value of @v with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_read_acquire() there. * * Return: The value loaded from @v. */ static __always_inline int atomic_read_acquire(const atomic_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic_read_acquire(v); } /** * atomic_set() - atomic set with relaxed ordering * @v: pointer to atomic_t * @i: int value to assign * * Atomically sets @v to @i with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_set() there. * * Return: Nothing. */ static __always_inline void atomic_set(atomic_t *v, int i) { instrument_atomic_write(v, sizeof(*v)); raw_atomic_set(v, i); } /** * atomic_set_release() - atomic set with release ordering * @v: pointer to atomic_t * @i: int value to assign * * Atomically sets @v to @i with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_set_release() there. * * Return: Nothing. */ static __always_inline void atomic_set_release(atomic_t *v, int i) { kcsan_release(); instrument_atomic_write(v, sizeof(*v)); raw_atomic_set_release(v, i); } /** * atomic_add() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_add() there. * * Return: Nothing. */ static __always_inline void atomic_add(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_add(i, v); } /** * atomic_add_return() - atomic add with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_return() there. * * Return: The updated value of @v. */ static __always_inline int atomic_add_return(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_return(i, v); } /** * atomic_add_return_acquire() - atomic add with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline int atomic_add_return_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_return_acquire(i, v); } /** * atomic_add_return_release() - atomic add with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_return_release() there. * * Return: The updated value of @v. */ static __always_inline int atomic_add_return_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_return_release(i, v); } /** * atomic_add_return_relaxed() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline int atomic_add_return_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_return_relaxed(i, v); } /** * atomic_fetch_add() - atomic add with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add(i, v); } /** * atomic_fetch_add_acquire() - atomic add with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add_acquire(i, v); } /** * atomic_fetch_add_release() - atomic add with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add_release(i, v); } /** * atomic_fetch_add_relaxed() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add_relaxed(i, v); } /** * atomic_sub() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub() there. * * Return: Nothing. */ static __always_inline void atomic_sub(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_sub(i, v); } /** * atomic_sub_return() - atomic subtract with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_return() there. * * Return: The updated value of @v. */ static __always_inline int atomic_sub_return(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_return(i, v); } /** * atomic_sub_return_acquire() - atomic subtract with acquire ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline int atomic_sub_return_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_return_acquire(i, v); } /** * atomic_sub_return_release() - atomic subtract with release ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_return_release() there. * * Return: The updated value of @v. */ static __always_inline int atomic_sub_return_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_return_release(i, v); } /** * atomic_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline int atomic_sub_return_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_return_relaxed(i, v); } /** * atomic_fetch_sub() - atomic subtract with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_sub() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_sub(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_sub(i, v); } /** * atomic_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_sub_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_sub_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_sub_acquire(i, v); } /** * atomic_fetch_sub_release() - atomic subtract with release ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_sub_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_sub_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_sub_release(i, v); } /** * atomic_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_sub_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_sub_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_sub_relaxed(i, v); } /** * atomic_inc() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc() there. * * Return: Nothing. */ static __always_inline void atomic_inc(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_inc(v); } /** * atomic_inc_return() - atomic increment with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_return() there. * * Return: The updated value of @v. */ static __always_inline int atomic_inc_return(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_return(v); } /** * atomic_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline int atomic_inc_return_acquire(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_return_acquire(v); } /** * atomic_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_return_release() there. * * Return: The updated value of @v. */ static __always_inline int atomic_inc_return_release(atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_return_release(v); } /** * atomic_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline int atomic_inc_return_relaxed(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_return_relaxed(v); } /** * atomic_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_inc() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_inc(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_inc(v); } /** * atomic_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_inc_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_inc_acquire(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_inc_acquire(v); } /** * atomic_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_inc_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_inc_release(atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_inc_release(v); } /** * atomic_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_inc_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_inc_relaxed(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_inc_relaxed(v); } /** * atomic_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec() there. * * Return: Nothing. */ static __always_inline void atomic_dec(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_dec(v); } /** * atomic_dec_return() - atomic decrement with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_return() there. * * Return: The updated value of @v. */ static __always_inline int atomic_dec_return(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_return(v); } /** * atomic_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline int atomic_dec_return_acquire(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_return_acquire(v); } /** * atomic_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_return_release() there. * * Return: The updated value of @v. */ static __always_inline int atomic_dec_return_release(atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_return_release(v); } /** * atomic_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline int atomic_dec_return_relaxed(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_return_relaxed(v); } /** * atomic_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_dec() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_dec(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_dec(v); } /** * atomic_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_dec_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_dec_acquire(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_dec_acquire(v); } /** * atomic_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_dec_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_dec_release(atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_dec_release(v); } /** * atomic_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_dec_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_dec_relaxed(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_dec_relaxed(v); } /** * atomic_and() - atomic bitwise AND with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_and() there. * * Return: Nothing. */ static __always_inline void atomic_and(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_and(i, v); } /** * atomic_fetch_and() - atomic bitwise AND with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_and() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_and(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_and(i, v); } /** * atomic_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_and_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_and_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_and_acquire(i, v); } /** * atomic_fetch_and_release() - atomic bitwise AND with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_and_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_and_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_and_release(i, v); } /** * atomic_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_and_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_and_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_and_relaxed(i, v); } /** * atomic_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_andnot() there. * * Return: Nothing. */ static __always_inline void atomic_andnot(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_andnot(i, v); } /** * atomic_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_andnot(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_andnot(i, v); } /** * atomic_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_andnot_acquire(i, v); } /** * atomic_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_andnot_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_andnot_release(i, v); } /** * atomic_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_andnot_relaxed(i, v); } /** * atomic_or() - atomic bitwise OR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_or() there. * * Return: Nothing. */ static __always_inline void atomic_or(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_or(i, v); } /** * atomic_fetch_or() - atomic bitwise OR with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_or() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_or(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_or(i, v); } /** * atomic_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_or_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_or_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_or_acquire(i, v); } /** * atomic_fetch_or_release() - atomic bitwise OR with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_or_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_or_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_or_release(i, v); } /** * atomic_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_or_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_or_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_or_relaxed(i, v); } /** * atomic_xor() - atomic bitwise XOR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_xor() there. * * Return: Nothing. */ static __always_inline void atomic_xor(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_xor(i, v); } /** * atomic_fetch_xor() - atomic bitwise XOR with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_xor() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_xor(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_xor(i, v); } /** * atomic_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_xor_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_xor_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_xor_acquire(i, v); } /** * atomic_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_xor_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_xor_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_xor_release(i, v); } /** * atomic_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_xor_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_xor_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_xor_relaxed(i, v); } /** * atomic_xchg() - atomic exchange with full ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_xchg() there. * * Return: The original value of @v. */ static __always_inline int atomic_xchg(atomic_t *v, int new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_xchg(v, new); } /** * atomic_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_xchg_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_xchg_acquire(atomic_t *v, int new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_xchg_acquire(v, new); } /** * atomic_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_xchg_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_xchg_release(atomic_t *v, int new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_xchg_release(v, new); } /** * atomic_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_xchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_xchg_relaxed(atomic_t *v, int new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_xchg_relaxed(v, new); } /** * atomic_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg() there. * * Return: The original value of @v. */ static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_cmpxchg(v, old, new); } /** * atomic_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_cmpxchg_acquire(atomic_t *v, int old, int new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_cmpxchg_acquire(v, old, new); } /** * atomic_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_cmpxchg_release(atomic_t *v, int old, int new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_cmpxchg_release(v, old, new); } /** * atomic_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_cmpxchg_relaxed(v, old, new); } /** * atomic_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg() there. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg(v, old, new); } /** * atomic_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_acquire() there. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_acquire(v, old, new); } /** * atomic_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_release() there. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_release(v, old, new); } /** * atomic_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_relaxed() there. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_relaxed(v, old, new); } /** * atomic_sub_and_test() - atomic subtract and test if zero with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_and_test(i, v); } /** * atomic_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_dec_and_test(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_and_test(v); } /** * atomic_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_inc_and_test(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_and_test(v); } /** * atomic_add_negative() - atomic add and test if negative with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_negative() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_add_negative(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_negative(i, v); } /** * atomic_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_negative_acquire() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_add_negative_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_negative_acquire(i, v); } /** * atomic_add_negative_release() - atomic add and test if negative with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_negative_release() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_add_negative_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_negative_release(i, v); } /** * atomic_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_negative_relaxed() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_add_negative_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_negative_relaxed(i, v); } /** * atomic_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_t * @a: int value to add * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_unless() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add_unless(v, a, u); } /** * atomic_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_t * @a: int value to add * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_add_unless() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_add_unless(atomic_t *v, int a, int u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_unless(v, a, u); } /** * atomic_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_inc_not_zero() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_inc_not_zero(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_not_zero(v); } /** * atomic_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_inc_unless_negative() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_inc_unless_negative(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_unless_negative(v); } /** * atomic_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_dec_unless_positive() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_dec_unless_positive(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_unless_positive(v); } /** * atomic_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_dec_if_positive() there. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline int atomic_dec_if_positive(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_if_positive(v); } /** * atomic64_read() - atomic load with relaxed ordering * @v: pointer to atomic64_t * * Atomically loads the value of @v with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_read() there. * * Return: The value loaded from @v. */ static __always_inline s64 atomic64_read(const atomic64_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic64_read(v); } /** * atomic64_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic64_t * * Atomically loads the value of @v with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_read_acquire() there. * * Return: The value loaded from @v. */ static __always_inline s64 atomic64_read_acquire(const atomic64_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic64_read_acquire(v); } /** * atomic64_set() - atomic set with relaxed ordering * @v: pointer to atomic64_t * @i: s64 value to assign * * Atomically sets @v to @i with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_set() there. * * Return: Nothing. */ static __always_inline void atomic64_set(atomic64_t *v, s64 i) { instrument_atomic_write(v, sizeof(*v)); raw_atomic64_set(v, i); } /** * atomic64_set_release() - atomic set with release ordering * @v: pointer to atomic64_t * @i: s64 value to assign * * Atomically sets @v to @i with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_set_release() there. * * Return: Nothing. */ static __always_inline void atomic64_set_release(atomic64_t *v, s64 i) { kcsan_release(); instrument_atomic_write(v, sizeof(*v)); raw_atomic64_set_release(v, i); } /** * atomic64_add() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add() there. * * Return: Nothing. */ static __always_inline void atomic64_add(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_add(i, v); } /** * atomic64_add_return() - atomic add with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_return() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_add_return(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_return(i, v); } /** * atomic64_add_return_acquire() - atomic add with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_add_return_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_return_acquire(i, v); } /** * atomic64_add_return_release() - atomic add with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_return_release() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_add_return_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_return_release(i, v); } /** * atomic64_add_return_relaxed() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_add_return_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_return_relaxed(i, v); } /** * atomic64_fetch_add() - atomic add with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add(i, v); } /** * atomic64_fetch_add_acquire() - atomic add with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add_acquire(i, v); } /** * atomic64_fetch_add_release() - atomic add with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add_release(i, v); } /** * atomic64_fetch_add_relaxed() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add_relaxed(i, v); } /** * atomic64_sub() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub() there. * * Return: Nothing. */ static __always_inline void atomic64_sub(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_sub(i, v); } /** * atomic64_sub_return() - atomic subtract with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_return() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_sub_return(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_return(i, v); } /** * atomic64_sub_return_acquire() - atomic subtract with acquire ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_sub_return_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_return_acquire(i, v); } /** * atomic64_sub_return_release() - atomic subtract with release ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_return_release() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_sub_return_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_return_release(i, v); } /** * atomic64_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_sub_return_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_return_relaxed(i, v); } /** * atomic64_fetch_sub() - atomic subtract with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_sub(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_sub(i, v); } /** * atomic64_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_sub_acquire(i, v); } /** * atomic64_fetch_sub_release() - atomic subtract with release ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_sub_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_sub_release(i, v); } /** * atomic64_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_sub_relaxed(i, v); } /** * atomic64_inc() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc() there. * * Return: Nothing. */ static __always_inline void atomic64_inc(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_inc(v); } /** * atomic64_inc_return() - atomic increment with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_return() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_inc_return(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_return(v); } /** * atomic64_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_inc_return_acquire(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_return_acquire(v); } /** * atomic64_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_return_release() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_inc_return_release(atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_return_release(v); } /** * atomic64_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_inc_return_relaxed(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_return_relaxed(v); } /** * atomic64_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_inc(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_inc(v); } /** * atomic64_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_inc_acquire(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_inc_acquire(v); } /** * atomic64_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_inc_release(atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_inc_release(v); } /** * atomic64_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_inc_relaxed(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_inc_relaxed(v); } /** * atomic64_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec() there. * * Return: Nothing. */ static __always_inline void atomic64_dec(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_dec(v); } /** * atomic64_dec_return() - atomic decrement with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_return() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_dec_return(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_return(v); } /** * atomic64_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_dec_return_acquire(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_return_acquire(v); } /** * atomic64_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_return_release() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_dec_return_release(atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_return_release(v); } /** * atomic64_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_dec_return_relaxed(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_return_relaxed(v); } /** * atomic64_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_dec(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_dec(v); } /** * atomic64_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_dec_acquire(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_dec_acquire(v); } /** * atomic64_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_dec_release(atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_dec_release(v); } /** * atomic64_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_dec_relaxed(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_dec_relaxed(v); } /** * atomic64_and() - atomic bitwise AND with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_and() there. * * Return: Nothing. */ static __always_inline void atomic64_and(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_and(i, v); } /** * atomic64_fetch_and() - atomic bitwise AND with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_and() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_and(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_and(i, v); } /** * atomic64_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_and_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_and_acquire(i, v); } /** * atomic64_fetch_and_release() - atomic bitwise AND with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_and_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_and_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_and_release(i, v); } /** * atomic64_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_and_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_and_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_and_relaxed(i, v); } /** * atomic64_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_andnot() there. * * Return: Nothing. */ static __always_inline void atomic64_andnot(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_andnot(i, v); } /** * atomic64_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_andnot(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_andnot(i, v); } /** * atomic64_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_andnot_acquire(i, v); } /** * atomic64_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_andnot_release(i, v); } /** * atomic64_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_andnot_relaxed(i, v); } /** * atomic64_or() - atomic bitwise OR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_or() there. * * Return: Nothing. */ static __always_inline void atomic64_or(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_or(i, v); } /** * atomic64_fetch_or() - atomic bitwise OR with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_or() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_or(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_or(i, v); } /** * atomic64_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_or_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_or_acquire(i, v); } /** * atomic64_fetch_or_release() - atomic bitwise OR with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_or_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_or_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_or_release(i, v); } /** * atomic64_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_or_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_or_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_or_relaxed(i, v); } /** * atomic64_xor() - atomic bitwise XOR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xor() there. * * Return: Nothing. */ static __always_inline void atomic64_xor(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_xor(i, v); } /** * atomic64_fetch_xor() - atomic bitwise XOR with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_xor(i, v); } /** * atomic64_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_xor_acquire(i, v); } /** * atomic64_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_xor_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_xor_release(i, v); } /** * atomic64_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_xor_relaxed(i, v); } /** * atomic64_xchg() - atomic exchange with full ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xchg() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_xchg(atomic64_t *v, s64 new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_xchg(v, new); } /** * atomic64_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xchg_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_xchg_acquire(atomic64_t *v, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_xchg_acquire(v, new); } /** * atomic64_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xchg_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_xchg_release(atomic64_t *v, s64 new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_xchg_release(v, new); } /** * atomic64_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_xchg_relaxed(atomic64_t *v, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_xchg_relaxed(v, new); } /** * atomic64_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_cmpxchg(v, old, new); } /** * atomic64_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_cmpxchg_acquire(v, old, new); } /** * atomic64_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_cmpxchg_release(v, old, new); } /** * atomic64_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_cmpxchg_relaxed(v, old, new); } /** * atomic64_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg() there. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg(v, old, new); } /** * atomic64_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_acquire() there. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_acquire(v, old, new); } /** * atomic64_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_release() there. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_release(v, old, new); } /** * atomic64_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_relaxed() there. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_relaxed(v, old, new); } /** * atomic64_sub_and_test() - atomic subtract and test if zero with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_and_test(i, v); } /** * atomic64_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic64_dec_and_test(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_and_test(v); } /** * atomic64_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic64_inc_and_test(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_and_test(v); } /** * atomic64_add_negative() - atomic add and test if negative with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_negative() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_negative(i, v); } /** * atomic64_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_negative_acquire() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic64_add_negative_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_negative_acquire(i, v); } /** * atomic64_add_negative_release() - atomic add and test if negative with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_negative_release() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic64_add_negative_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_negative_release(i, v); } /** * atomic64_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_negative_relaxed() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic64_add_negative_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_negative_relaxed(i, v); } /** * atomic64_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic64_t * @a: s64 value to add * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_unless() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add_unless(v, a, u); } /** * atomic64_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic64_t * @a: s64 value to add * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_add_unless() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_unless(v, a, u); } /** * atomic64_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic64_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_inc_not_zero() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_not_zero(v); } /** * atomic64_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic64_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_inc_unless_negative() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic64_inc_unless_negative(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_unless_negative(v); } /** * atomic64_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic64_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_dec_unless_positive() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic64_dec_unless_positive(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_unless_positive(v); } /** * atomic64_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic64_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_dec_if_positive() there. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_if_positive(v); } /** * atomic_long_read() - atomic load with relaxed ordering * @v: pointer to atomic_long_t * * Atomically loads the value of @v with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_read() there. * * Return: The value loaded from @v. */ static __always_inline long atomic_long_read(const atomic_long_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic_long_read(v); } /** * atomic_long_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic_long_t * * Atomically loads the value of @v with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_read_acquire() there. * * Return: The value loaded from @v. */ static __always_inline long atomic_long_read_acquire(const atomic_long_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic_long_read_acquire(v); } /** * atomic_long_set() - atomic set with relaxed ordering * @v: pointer to atomic_long_t * @i: long value to assign * * Atomically sets @v to @i with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_set() there. * * Return: Nothing. */ static __always_inline void atomic_long_set(atomic_long_t *v, long i) { instrument_atomic_write(v, sizeof(*v)); raw_atomic_long_set(v, i); } /** * atomic_long_set_release() - atomic set with release ordering * @v: pointer to atomic_long_t * @i: long value to assign * * Atomically sets @v to @i with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_set_release() there. * * Return: Nothing. */ static __always_inline void atomic_long_set_release(atomic_long_t *v, long i) { kcsan_release(); instrument_atomic_write(v, sizeof(*v)); raw_atomic_long_set_release(v, i); } /** * atomic_long_add() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add() there. * * Return: Nothing. */ static __always_inline void atomic_long_add(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_add(i, v); } /** * atomic_long_add_return() - atomic add with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_return() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_add_return(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_return(i, v); } /** * atomic_long_add_return_acquire() - atomic add with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_add_return_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_return_acquire(i, v); } /** * atomic_long_add_return_release() - atomic add with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_return_release() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_add_return_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_return_release(i, v); } /** * atomic_long_add_return_relaxed() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_add_return_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_return_relaxed(i, v); } /** * atomic_long_fetch_add() - atomic add with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add(i, v); } /** * atomic_long_fetch_add_acquire() - atomic add with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add_acquire(i, v); } /** * atomic_long_fetch_add_release() - atomic add with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add_release(i, v); } /** * atomic_long_fetch_add_relaxed() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add_relaxed(i, v); } /** * atomic_long_sub() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub() there. * * Return: Nothing. */ static __always_inline void atomic_long_sub(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_sub(i, v); } /** * atomic_long_sub_return() - atomic subtract with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_return() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_sub_return(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_return(i, v); } /** * atomic_long_sub_return_acquire() - atomic subtract with acquire ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_sub_return_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_return_acquire(i, v); } /** * atomic_long_sub_return_release() - atomic subtract with release ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_return_release() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_sub_return_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_return_release(i, v); } /** * atomic_long_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_sub_return_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_return_relaxed(i, v); } /** * atomic_long_fetch_sub() - atomic subtract with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_sub(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_sub(i, v); } /** * atomic_long_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_sub_acquire(i, v); } /** * atomic_long_fetch_sub_release() - atomic subtract with release ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_sub_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_sub_release(i, v); } /** * atomic_long_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_sub_relaxed(i, v); } /** * atomic_long_inc() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc() there. * * Return: Nothing. */ static __always_inline void atomic_long_inc(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_inc(v); } /** * atomic_long_inc_return() - atomic increment with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_return() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_inc_return(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_return(v); } /** * atomic_long_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_inc_return_acquire(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_return_acquire(v); } /** * atomic_long_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_return_release() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_inc_return_release(atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_return_release(v); } /** * atomic_long_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_inc_return_relaxed(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_return_relaxed(v); } /** * atomic_long_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_inc(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_inc(v); } /** * atomic_long_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_inc_acquire(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_inc_acquire(v); } /** * atomic_long_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_inc_release(atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_inc_release(v); } /** * atomic_long_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_inc_relaxed(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_inc_relaxed(v); } /** * atomic_long_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec() there. * * Return: Nothing. */ static __always_inline void atomic_long_dec(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_dec(v); } /** * atomic_long_dec_return() - atomic decrement with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_return() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_dec_return(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_return(v); } /** * atomic_long_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_dec_return_acquire(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_return_acquire(v); } /** * atomic_long_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_return_release() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_dec_return_release(atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_return_release(v); } /** * atomic_long_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_dec_return_relaxed(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_return_relaxed(v); } /** * atomic_long_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_dec(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_dec(v); } /** * atomic_long_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_dec_acquire(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_dec_acquire(v); } /** * atomic_long_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_dec_release(atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_dec_release(v); } /** * atomic_long_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_dec_relaxed(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_dec_relaxed(v); } /** * atomic_long_and() - atomic bitwise AND with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_and() there. * * Return: Nothing. */ static __always_inline void atomic_long_and(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_and(i, v); } /** * atomic_long_fetch_and() - atomic bitwise AND with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_and(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_and(i, v); } /** * atomic_long_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_and_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_and_acquire(i, v); } /** * atomic_long_fetch_and_release() - atomic bitwise AND with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_and_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_and_release(i, v); } /** * atomic_long_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_and_relaxed(i, v); } /** * atomic_long_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_andnot() there. * * Return: Nothing. */ static __always_inline void atomic_long_andnot(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_andnot(i, v); } /** * atomic_long_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_andnot(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_andnot(i, v); } /** * atomic_long_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_andnot_acquire(i, v); } /** * atomic_long_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_andnot_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_andnot_release(i, v); } /** * atomic_long_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_andnot_relaxed(i, v); } /** * atomic_long_or() - atomic bitwise OR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_or() there. * * Return: Nothing. */ static __always_inline void atomic_long_or(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_or(i, v); } /** * atomic_long_fetch_or() - atomic bitwise OR with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_or(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_or(i, v); } /** * atomic_long_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_or_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_or_acquire(i, v); } /** * atomic_long_fetch_or_release() - atomic bitwise OR with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_or_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_or_release(i, v); } /** * atomic_long_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_or_relaxed(i, v); } /** * atomic_long_xor() - atomic bitwise XOR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xor() there. * * Return: Nothing. */ static __always_inline void atomic_long_xor(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_xor(i, v); } /** * atomic_long_fetch_xor() - atomic bitwise XOR with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_xor(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_xor(i, v); } /** * atomic_long_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_xor_acquire(i, v); } /** * atomic_long_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_xor_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_xor_release(i, v); } /** * atomic_long_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_xor_relaxed(i, v); } /** * atomic_long_xchg() - atomic exchange with full ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xchg() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_xchg(atomic_long_t *v, long new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_xchg(v, new); } /** * atomic_long_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xchg_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_xchg_acquire(atomic_long_t *v, long new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_xchg_acquire(v, new); } /** * atomic_long_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xchg_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_xchg_release(atomic_long_t *v, long new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_xchg_release(v, new); } /** * atomic_long_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_xchg_relaxed(atomic_long_t *v, long new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_xchg_relaxed(v, new); } /** * atomic_long_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_cmpxchg(atomic_long_t *v, long old, long new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_cmpxchg(v, old, new); } /** * atomic_long_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_cmpxchg_acquire(v, old, new); } /** * atomic_long_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_cmpxchg_release(v, old, new); } /** * atomic_long_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_cmpxchg_relaxed(v, old, new); } /** * atomic_long_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg() there. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg(v, old, new); } /** * atomic_long_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_acquire() there. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_acquire(v, old, new); } /** * atomic_long_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_release() there. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_release(v, old, new); } /** * atomic_long_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_relaxed() there. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_relaxed(v, old, new); } /** * atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_long_sub_and_test(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_and_test(i, v); } /** * atomic_long_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_long_dec_and_test(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_and_test(v); } /** * atomic_long_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_long_inc_and_test(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_and_test(v); } /** * atomic_long_add_negative() - atomic add and test if negative with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_negative() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_long_add_negative(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_negative(i, v); } /** * atomic_long_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_negative_acquire() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_long_add_negative_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_negative_acquire(i, v); } /** * atomic_long_add_negative_release() - atomic add and test if negative with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_negative_release() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_long_add_negative_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_negative_release(i, v); } /** * atomic_long_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_negative_relaxed() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_long_add_negative_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_negative_relaxed(i, v); } /** * atomic_long_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_long_t * @a: long value to add * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_unless() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add_unless(v, a, u); } /** * atomic_long_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_long_t * @a: long value to add * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_add_unless() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_long_add_unless(atomic_long_t *v, long a, long u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_unless(v, a, u); } /** * atomic_long_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic_long_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_not_zero() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_long_inc_not_zero(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_not_zero(v); } /** * atomic_long_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic_long_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_unless_negative() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_long_inc_unless_negative(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_unless_negative(v); } /** * atomic_long_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic_long_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_unless_positive() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_long_dec_unless_positive(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_unless_positive(v); } /** * atomic_long_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic_long_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_if_positive() there. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline long atomic_long_dec_if_positive(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_if_positive(v); } #define xchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_xchg(__ai_ptr, __VA_ARGS__); \ }) #define xchg_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_xchg_acquire(__ai_ptr, __VA_ARGS__); \ }) #define xchg_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_xchg_release(__ai_ptr, __VA_ARGS__); \ }) #define xchg_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_xchg_relaxed(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128_acquire(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128_relaxed(__ai_ptr, __VA_ARGS__); \ }) #define try_cmpxchg(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg_acquire(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg_release(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg_relaxed(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64_acquire(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64_release(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64_relaxed(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128_acquire(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128_release(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128_relaxed(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define cmpxchg_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg_local(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128_local(__ai_ptr, __VA_ARGS__); \ }) #define sync_cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) #define try_cmpxchg_local(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64_local(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128_local(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define sync_try_cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_sync_try_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ // 8829b337928e9508259079d32581775ececd415b |
| 6 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM notifier #if !defined(_TRACE_NOTIFIERS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NOTIFIERS_H #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(notifier_info, TP_PROTO(void *cb), TP_ARGS(cb), TP_STRUCT__entry( __field(void *, cb) ), TP_fast_assign( __entry->cb = cb; ), TP_printk("%ps", __entry->cb) ); /* * notifier_register - called upon notifier callback registration * * @cb: callback pointer * */ DEFINE_EVENT(notifier_info, notifier_register, TP_PROTO(void *cb), TP_ARGS(cb) ); /* * notifier_unregister - called upon notifier callback unregistration * * @cb: callback pointer * */ DEFINE_EVENT(notifier_info, notifier_unregister, TP_PROTO(void *cb), TP_ARGS(cb) ); /* * notifier_run - called upon notifier callback execution * * @cb: callback pointer * */ DEFINE_EVENT(notifier_info, notifier_run, TP_PROTO(void *cb), TP_ARGS(cb) ); #endif /* _TRACE_NOTIFIERS_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2 2 58 58 18 18 18 18 18 18 18 18 62 4 58 58 40 18 18 58 5 5 5 5 5 5 2 3 1 1 7 2 1 5 2 2 4 2 40 1 3 33 21 7 5 29 12 41 33 10 41 35 2 32 4 1 20 14 33 33 26 33 1 8 15 5 17 16 3 5 2 3 4 4 6 1 1 4 2 1 1 7 9 9 1 2 1 1 24 23 23 15 6 2 19 1 1 17 16 49 38 13 45 1 44 43 41 22 24 1 13 1 1 1 1 1 1 3 1 1 1 5 1 2 2 9 29 5 1 1 1 2 1 1 1 1 4 1 1 2 21 24 1 19 1 4 1 2 1 12 1 2 1 3 3 18 1 4 12 1 33 7 1 3 1 4 1 8 1 2 1 5 5 1 5 3 14 7 1 19 1 1 1 1 4 1 5 2 5 275 275 54 367 64 302 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/ioctl.c * * Copyright (C) 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) */ #include <linux/fs.h> #include <linux/capability.h> #include <linux/time.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/file.h> #include <linux/quotaops.h> #include <linux/random.h> #include <linux/uaccess.h> #include <linux/delay.h> #include <linux/iversion.h> #include <linux/fileattr.h> #include <linux/uuid.h> #include "ext4_jbd2.h" #include "ext4.h" #include <linux/fsmap.h> #include "fsmap.h" #include <trace/events/ext4.h> typedef void ext4_update_sb_callback(struct ext4_super_block *es, const void *arg); /* * Superblock modification callback function for changing file system * label */ static void ext4_sb_setlabel(struct ext4_super_block *es, const void *arg) { /* Sanity check, this should never happen */ BUILD_BUG_ON(sizeof(es->s_volume_name) < EXT4_LABEL_MAX); memcpy(es->s_volume_name, (char *)arg, EXT4_LABEL_MAX); } /* * Superblock modification callback function for changing file system * UUID. */ static void ext4_sb_setuuid(struct ext4_super_block *es, const void *arg) { memcpy(es->s_uuid, (__u8 *)arg, UUID_SIZE); } static int ext4_update_primary_sb(struct super_block *sb, handle_t *handle, ext4_update_sb_callback func, const void *arg) { int err = 0; struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bh = sbi->s_sbh; struct ext4_super_block *es = sbi->s_es; trace_ext4_update_sb(sb, bh->b_blocknr, 1); BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE); if (err) goto out_err; lock_buffer(bh); func(es, arg); ext4_superblock_csum_set(sb); unlock_buffer(bh); if (buffer_write_io_error(bh) || !buffer_uptodate(bh)) { ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to " "superblock detected"); clear_buffer_write_io_error(bh); set_buffer_uptodate(bh); } err = ext4_handle_dirty_metadata(handle, NULL, bh); if (err) goto out_err; err = sync_dirty_buffer(bh); out_err: ext4_std_error(sb, err); return err; } /* * Update one backup superblock in the group 'grp' using the callback * function 'func' and argument 'arg'. If the handle is NULL the * modification is not journalled. * * Returns: 0 when no modification was done (no superblock in the group) * 1 when the modification was successful * <0 on error */ static int ext4_update_backup_sb(struct super_block *sb, handle_t *handle, ext4_group_t grp, ext4_update_sb_callback func, const void *arg) { int err = 0; ext4_fsblk_t sb_block; struct buffer_head *bh; unsigned long offset = 0; struct ext4_super_block *es; if (!ext4_bg_has_super(sb, grp)) return 0; /* * For the group 0 there is always 1k padding, so we have * either adjust offset, or sb_block depending on blocksize */ if (grp == 0) { sb_block = 1 * EXT4_MIN_BLOCK_SIZE; offset = do_div(sb_block, sb->s_blocksize); } else { sb_block = ext4_group_first_block_no(sb, grp); offset = 0; } trace_ext4_update_sb(sb, sb_block, handle ? 1 : 0); bh = ext4_sb_bread(sb, sb_block, 0); if (IS_ERR(bh)) return PTR_ERR(bh); if (handle) { BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE); if (err) goto out_bh; } es = (struct ext4_super_block *) (bh->b_data + offset); lock_buffer(bh); if (ext4_has_metadata_csum(sb) && es->s_checksum != ext4_superblock_csum(sb, es)) { ext4_msg(sb, KERN_ERR, "Invalid checksum for backup " "superblock %llu", sb_block); unlock_buffer(bh); goto out_bh; } func(es, arg); if (ext4_has_metadata_csum(sb)) es->s_checksum = ext4_superblock_csum(sb, es); set_buffer_uptodate(bh); unlock_buffer(bh); if (handle) { err = ext4_handle_dirty_metadata(handle, NULL, bh); if (err) goto out_bh; } else { BUFFER_TRACE(bh, "marking dirty"); mark_buffer_dirty(bh); } err = sync_dirty_buffer(bh); out_bh: brelse(bh); ext4_std_error(sb, err); return (err) ? err : 1; } /* * Update primary and backup superblocks using the provided function * func and argument arg. * * Only the primary superblock and at most two backup superblock * modifications are journalled; the rest is modified without journal. * This is safe because e2fsck will re-write them if there is a problem, * and we're very unlikely to ever need more than two backups. */ static int ext4_update_superblocks_fn(struct super_block *sb, ext4_update_sb_callback func, const void *arg) { handle_t *handle; ext4_group_t ngroups; unsigned int three = 1; unsigned int five = 5; unsigned int seven = 7; int err = 0, ret, i; ext4_group_t grp, primary_grp; struct ext4_sb_info *sbi = EXT4_SB(sb); /* * We can't update superblocks while the online resize is running */ if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING, &sbi->s_ext4_flags)) { ext4_msg(sb, KERN_ERR, "Can't modify superblock while" "performing online resize"); return -EBUSY; } /* * We're only going to update primary superblock and two * backup superblocks in this transaction. */ handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 3); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto out; } /* Update primary superblock */ err = ext4_update_primary_sb(sb, handle, func, arg); if (err) { ext4_msg(sb, KERN_ERR, "Failed to update primary " "superblock"); goto out_journal; } primary_grp = ext4_get_group_number(sb, sbi->s_sbh->b_blocknr); ngroups = ext4_get_groups_count(sb); /* * Update backup superblocks. We have to start from group 0 * because it might not be where the primary superblock is * if the fs is mounted with -o sb=<backup_sb_block> */ i = 0; grp = 0; while (grp < ngroups) { /* Skip primary superblock */ if (grp == primary_grp) goto next_grp; ret = ext4_update_backup_sb(sb, handle, grp, func, arg); if (ret < 0) { /* Ignore bad checksum; try to update next sb */ if (ret == -EFSBADCRC) goto next_grp; err = ret; goto out_journal; } i += ret; if (handle && i > 1) { /* * We're only journalling primary superblock and * two backup superblocks; the rest is not * journalled. */ err = ext4_journal_stop(handle); if (err) goto out; handle = NULL; } next_grp: grp = ext4_list_backups(sb, &three, &five, &seven); } out_journal: if (handle) { ret = ext4_journal_stop(handle); if (ret && !err) err = ret; } out: clear_bit_unlock(EXT4_FLAGS_RESIZING, &sbi->s_ext4_flags); smp_mb__after_atomic(); return err ? err : 0; } /* * Swap memory between @a and @b for @len bytes. * * @a: pointer to first memory area * @b: pointer to second memory area * @len: number of bytes to swap * */ static void memswap(void *a, void *b, size_t len) { unsigned char *ap, *bp; ap = (unsigned char *)a; bp = (unsigned char *)b; while (len-- > 0) { swap(*ap, *bp); ap++; bp++; } } /* * Swap i_data and associated attributes between @inode1 and @inode2. * This function is used for the primary swap between inode1 and inode2 * and also to revert this primary swap in case of errors. * * Therefore you have to make sure, that calling this method twice * will revert all changes. * * @inode1: pointer to first inode * @inode2: pointer to second inode */ static void swap_inode_data(struct inode *inode1, struct inode *inode2) { loff_t isize; struct ext4_inode_info *ei1; struct ext4_inode_info *ei2; unsigned long tmp; struct timespec64 ts1, ts2; ei1 = EXT4_I(inode1); ei2 = EXT4_I(inode2); swap(inode1->i_version, inode2->i_version); ts1 = inode_get_atime(inode1); ts2 = inode_get_atime(inode2); inode_set_atime_to_ts(inode1, ts2); inode_set_atime_to_ts(inode2, ts1); ts1 = inode_get_mtime(inode1); ts2 = inode_get_mtime(inode2); inode_set_mtime_to_ts(inode1, ts2); inode_set_mtime_to_ts(inode2, ts1); memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data)); tmp = ei1->i_flags & EXT4_FL_SHOULD_SWAP; ei1->i_flags = (ei2->i_flags & EXT4_FL_SHOULD_SWAP) | (ei1->i_flags & ~EXT4_FL_SHOULD_SWAP); ei2->i_flags = tmp | (ei2->i_flags & ~EXT4_FL_SHOULD_SWAP); swap(ei1->i_disksize, ei2->i_disksize); ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS); ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS); isize = i_size_read(inode1); i_size_write(inode1, i_size_read(inode2)); i_size_write(inode2, isize); } void ext4_reset_inode_seed(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = cpu_to_le32(inode->i_generation); __u32 csum; if (!ext4_has_metadata_csum(inode->i_sb)) return; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum, sizeof(inum)); ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, sizeof(gen)); } /* * Swap the information from the given @inode and the inode * EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other * important fields of the inodes. * * @sb: the super block of the filesystem * @idmap: idmap of the mount the inode was found from * @inode: the inode to swap with EXT4_BOOT_LOADER_INO * */ static long swap_inode_boot_loader(struct super_block *sb, struct mnt_idmap *idmap, struct inode *inode) { handle_t *handle; int err; struct inode *inode_bl; struct ext4_inode_info *ei_bl; qsize_t size, size_bl, diff; blkcnt_t blocks; unsigned short bytes; inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL | EXT4_IGET_BAD); if (IS_ERR(inode_bl)) return PTR_ERR(inode_bl); ei_bl = EXT4_I(inode_bl); /* Protect orig inodes against a truncate and make sure, * that only 1 swap_inode_boot_loader is running. */ lock_two_nondirectories(inode, inode_bl); if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) || IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) || (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) || ext4_has_inline_data(inode)) { err = -EINVAL; goto journal_err_out; } if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || !inode_owner_or_capable(idmap, inode) || !capable(CAP_SYS_ADMIN)) { err = -EPERM; goto journal_err_out; } filemap_invalidate_lock(inode->i_mapping); err = filemap_write_and_wait(inode->i_mapping); if (err) goto err_out; err = filemap_write_and_wait(inode_bl->i_mapping); if (err) goto err_out; /* Wait for all existing dio workers */ inode_dio_wait(inode); inode_dio_wait(inode_bl); truncate_inode_pages(&inode->i_data, 0); truncate_inode_pages(&inode_bl->i_data, 0); handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2); if (IS_ERR(handle)) { err = -EINVAL; goto err_out; } ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT, handle); /* Protect extent tree against block allocations via delalloc */ ext4_double_down_write_data_sem(inode, inode_bl); if (is_bad_inode(inode_bl) || !S_ISREG(inode_bl->i_mode)) { /* this inode has never been used as a BOOT_LOADER */ set_nlink(inode_bl, 1); i_uid_write(inode_bl, 0); i_gid_write(inode_bl, 0); inode_bl->i_flags = 0; ei_bl->i_flags = 0; inode_set_iversion(inode_bl, 1); i_size_write(inode_bl, 0); EXT4_I(inode_bl)->i_disksize = inode_bl->i_size; inode_bl->i_mode = S_IFREG; if (ext4_has_feature_extents(sb)) { ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS); ext4_ext_tree_init(handle, inode_bl); } else memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data)); } err = dquot_initialize(inode); if (err) goto err_out1; size = (qsize_t)(inode->i_blocks) * (1 << 9) + inode->i_bytes; size_bl = (qsize_t)(inode_bl->i_blocks) * (1 << 9) + inode_bl->i_bytes; diff = size - size_bl; swap_inode_data(inode, inode_bl); inode_set_ctime_current(inode); inode_set_ctime_current(inode_bl); inode_inc_iversion(inode); inode->i_generation = get_random_u32(); inode_bl->i_generation = get_random_u32(); ext4_reset_inode_seed(inode); ext4_reset_inode_seed(inode_bl); ext4_discard_preallocations(inode); err = ext4_mark_inode_dirty(handle, inode); if (err < 0) { /* No need to update quota information. */ ext4_warning(inode->i_sb, "couldn't mark inode #%lu dirty (err %d)", inode->i_ino, err); /* Revert all changes: */ swap_inode_data(inode, inode_bl); ext4_mark_inode_dirty(handle, inode); goto err_out1; } blocks = inode_bl->i_blocks; bytes = inode_bl->i_bytes; inode_bl->i_blocks = inode->i_blocks; inode_bl->i_bytes = inode->i_bytes; err = ext4_mark_inode_dirty(handle, inode_bl); if (err < 0) { /* No need to update quota information. */ ext4_warning(inode_bl->i_sb, "couldn't mark inode #%lu dirty (err %d)", inode_bl->i_ino, err); goto revert; } /* Bootloader inode should not be counted into quota information. */ if (diff > 0) dquot_free_space(inode, diff); else err = dquot_alloc_space(inode, -1 * diff); if (err < 0) { revert: /* Revert all changes: */ inode_bl->i_blocks = blocks; inode_bl->i_bytes = bytes; swap_inode_data(inode, inode_bl); ext4_mark_inode_dirty(handle, inode); ext4_mark_inode_dirty(handle, inode_bl); } err_out1: ext4_journal_stop(handle); ext4_double_up_write_data_sem(inode, inode_bl); err_out: filemap_invalidate_unlock(inode->i_mapping); journal_err_out: unlock_two_nondirectories(inode, inode_bl); iput(inode_bl); return err; } /* * If immutable is set and we are not clearing it, we're not allowed to change * anything else in the inode. Don't error out if we're only trying to set * immutable on an immutable file. */ static int ext4_ioctl_check_immutable(struct inode *inode, __u32 new_projid, unsigned int flags) { struct ext4_inode_info *ei = EXT4_I(inode); unsigned int oldflags = ei->i_flags; if (!(oldflags & EXT4_IMMUTABLE_FL) || !(flags & EXT4_IMMUTABLE_FL)) return 0; if ((oldflags & ~EXT4_IMMUTABLE_FL) != (flags & ~EXT4_IMMUTABLE_FL)) return -EPERM; if (ext4_has_feature_project(inode->i_sb) && __kprojid_val(ei->i_projid) != new_projid) return -EPERM; return 0; } static void ext4_dax_dontcache(struct inode *inode, unsigned int flags) { struct ext4_inode_info *ei = EXT4_I(inode); if (S_ISDIR(inode->i_mode)) return; if (test_opt2(inode->i_sb, DAX_NEVER) || test_opt(inode->i_sb, DAX_ALWAYS)) return; if ((ei->i_flags ^ flags) & EXT4_DAX_FL) d_mark_dontcache(inode); } static bool dax_compatible(struct inode *inode, unsigned int oldflags, unsigned int flags) { /* Allow the DAX flag to be changed on inline directories */ if (S_ISDIR(inode->i_mode)) { flags &= ~EXT4_INLINE_DATA_FL; oldflags &= ~EXT4_INLINE_DATA_FL; } if (flags & EXT4_DAX_FL) { if ((oldflags & EXT4_DAX_MUT_EXCL) || ext4_test_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS)) { return false; } } if ((flags & EXT4_DAX_MUT_EXCL) && (oldflags & EXT4_DAX_FL)) return false; return true; } static int ext4_ioctl_setflags(struct inode *inode, unsigned int flags) { struct ext4_inode_info *ei = EXT4_I(inode); handle_t *handle = NULL; int err = -EPERM, migrate = 0; struct ext4_iloc iloc; unsigned int oldflags, mask, i; struct super_block *sb = inode->i_sb; /* Is it quota file? Do not allow user to mess with it */ if (ext4_is_quota_file(inode)) goto flags_out; oldflags = ei->i_flags; /* * The JOURNAL_DATA flag can only be changed by * the relevant capability. */ if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { if (!capable(CAP_SYS_RESOURCE)) goto flags_out; } if (!dax_compatible(inode, oldflags, flags)) { err = -EOPNOTSUPP; goto flags_out; } if ((flags ^ oldflags) & EXT4_EXTENTS_FL) migrate = 1; if ((flags ^ oldflags) & EXT4_CASEFOLD_FL) { if (!ext4_has_feature_casefold(sb)) { err = -EOPNOTSUPP; goto flags_out; } if (!S_ISDIR(inode->i_mode)) { err = -ENOTDIR; goto flags_out; } if (!ext4_empty_dir(inode)) { err = -ENOTEMPTY; goto flags_out; } } /* * Wait for all pending directio and then flush all the dirty pages * for this file. The flush marks all the pages readonly, so any * subsequent attempt to write to the file (particularly mmap pages) * will come through the filesystem and fail. */ if (S_ISREG(inode->i_mode) && !IS_IMMUTABLE(inode) && (flags & EXT4_IMMUTABLE_FL)) { inode_dio_wait(inode); err = filemap_write_and_wait(inode->i_mapping); if (err) goto flags_out; } handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto flags_out; } if (IS_SYNC(inode)) ext4_handle_sync(handle); err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) goto flags_err; ext4_dax_dontcache(inode, flags); for (i = 0, mask = 1; i < 32; i++, mask <<= 1) { if (!(mask & EXT4_FL_USER_MODIFIABLE)) continue; /* These flags get special treatment later */ if (mask == EXT4_JOURNAL_DATA_FL || mask == EXT4_EXTENTS_FL) continue; if (mask & flags) ext4_set_inode_flag(inode, i); else ext4_clear_inode_flag(inode, i); } ext4_set_inode_flags(inode, false); inode_set_ctime_current(inode); inode_inc_iversion(inode); err = ext4_mark_iloc_dirty(handle, inode, &iloc); flags_err: ext4_journal_stop(handle); if (err) goto flags_out; if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { /* * Changes to the journaling mode can cause unsafe changes to * S_DAX if the inode is DAX */ if (IS_DAX(inode)) { err = -EBUSY; goto flags_out; } err = ext4_change_inode_journal_flag(inode, flags & EXT4_JOURNAL_DATA_FL); if (err) goto flags_out; } if (migrate) { if (flags & EXT4_EXTENTS_FL) err = ext4_ext_migrate(inode); else err = ext4_ind_migrate(inode); } flags_out: return err; } #ifdef CONFIG_QUOTA static int ext4_ioctl_setproject(struct inode *inode, __u32 projid) { struct super_block *sb = inode->i_sb; struct ext4_inode_info *ei = EXT4_I(inode); int err, rc; handle_t *handle; kprojid_t kprojid; struct ext4_iloc iloc; struct ext4_inode *raw_inode; struct dquot *transfer_to[MAXQUOTAS] = { }; if (!ext4_has_feature_project(sb)) { if (projid != EXT4_DEF_PROJID) return -EOPNOTSUPP; else return 0; } if (EXT4_INODE_SIZE(sb) <= EXT4_GOOD_OLD_INODE_SIZE) return -EOPNOTSUPP; kprojid = make_kprojid(&init_user_ns, (projid_t)projid); if (projid_eq(kprojid, EXT4_I(inode)->i_projid)) return 0; err = -EPERM; /* Is it quota file? Do not allow user to mess with it */ if (ext4_is_quota_file(inode)) return err; err = dquot_initialize(inode); if (err) return err; err = ext4_get_inode_loc(inode, &iloc); if (err) return err; raw_inode = ext4_raw_inode(&iloc); if (!EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) { err = ext4_expand_extra_isize(inode, EXT4_SB(sb)->s_want_extra_isize, &iloc); if (err) return err; } else { brelse(iloc.bh); } handle = ext4_journal_start(inode, EXT4_HT_QUOTA, EXT4_QUOTA_INIT_BLOCKS(sb) + EXT4_QUOTA_DEL_BLOCKS(sb) + 3); if (IS_ERR(handle)) return PTR_ERR(handle); err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) goto out_stop; transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); if (!IS_ERR(transfer_to[PRJQUOTA])) { /* __dquot_transfer() calls back ext4_get_inode_usage() which * counts xattr inode references. */ down_read(&EXT4_I(inode)->xattr_sem); err = __dquot_transfer(inode, transfer_to); up_read(&EXT4_I(inode)->xattr_sem); dqput(transfer_to[PRJQUOTA]); if (err) goto out_dirty; } EXT4_I(inode)->i_projid = kprojid; inode_set_ctime_current(inode); inode_inc_iversion(inode); out_dirty: rc = ext4_mark_iloc_dirty(handle, inode, &iloc); if (!err) err = rc; out_stop: ext4_journal_stop(handle); return err; } #else static int ext4_ioctl_setproject(struct inode *inode, __u32 projid) { if (projid != EXT4_DEF_PROJID) return -EOPNOTSUPP; return 0; } #endif int ext4_force_shutdown(struct super_block *sb, u32 flags) { struct ext4_sb_info *sbi = EXT4_SB(sb); int ret; if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH) return -EINVAL; if (ext4_forced_shutdown(sb)) return 0; ext4_msg(sb, KERN_ALERT, "shut down requested (%d)", flags); trace_ext4_shutdown(sb, flags); switch (flags) { case EXT4_GOING_FLAGS_DEFAULT: ret = bdev_freeze(sb->s_bdev); if (ret) return ret; set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); bdev_thaw(sb->s_bdev); break; case EXT4_GOING_FLAGS_LOGFLUSH: set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) { (void) ext4_force_commit(sb); jbd2_journal_abort(sbi->s_journal, -ESHUTDOWN); } break; case EXT4_GOING_FLAGS_NOLOGFLUSH: set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) jbd2_journal_abort(sbi->s_journal, -ESHUTDOWN); break; default: return -EINVAL; } clear_opt(sb, DISCARD); return 0; } static int ext4_ioctl_shutdown(struct super_block *sb, unsigned long arg) { u32 flags; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(flags, (__u32 __user *)arg)) return -EFAULT; return ext4_force_shutdown(sb, flags); } struct getfsmap_info { struct super_block *gi_sb; struct fsmap_head __user *gi_data; unsigned int gi_idx; __u32 gi_last_flags; }; static int ext4_getfsmap_format(struct ext4_fsmap *xfm, void *priv) { struct getfsmap_info *info = priv; struct fsmap fm; trace_ext4_getfsmap_mapping(info->gi_sb, xfm); info->gi_last_flags = xfm->fmr_flags; ext4_fsmap_from_internal(info->gi_sb, &fm, xfm); if (copy_to_user(&info->gi_data->fmh_recs[info->gi_idx++], &fm, sizeof(struct fsmap))) return -EFAULT; return 0; } static int ext4_ioc_getfsmap(struct super_block *sb, struct fsmap_head __user *arg) { struct getfsmap_info info = { NULL }; struct ext4_fsmap_head xhead = {0}; struct fsmap_head head; bool aborted = false; int error; if (copy_from_user(&head, arg, sizeof(struct fsmap_head))) return -EFAULT; if (memchr_inv(head.fmh_reserved, 0, sizeof(head.fmh_reserved)) || memchr_inv(head.fmh_keys[0].fmr_reserved, 0, sizeof(head.fmh_keys[0].fmr_reserved)) || memchr_inv(head.fmh_keys[1].fmr_reserved, 0, sizeof(head.fmh_keys[1].fmr_reserved))) return -EINVAL; /* * ext4 doesn't report file extents at all, so the only valid * file offsets are the magic ones (all zeroes or all ones). */ if (head.fmh_keys[0].fmr_offset || (head.fmh_keys[1].fmr_offset != 0 && head.fmh_keys[1].fmr_offset != -1ULL)) return -EINVAL; xhead.fmh_iflags = head.fmh_iflags; xhead.fmh_count = head.fmh_count; ext4_fsmap_to_internal(sb, &xhead.fmh_keys[0], &head.fmh_keys[0]); ext4_fsmap_to_internal(sb, &xhead.fmh_keys[1], &head.fmh_keys[1]); trace_ext4_getfsmap_low_key(sb, &xhead.fmh_keys[0]); trace_ext4_getfsmap_high_key(sb, &xhead.fmh_keys[1]); info.gi_sb = sb; info.gi_data = arg; error = ext4_getfsmap(sb, &xhead, ext4_getfsmap_format, &info); if (error == EXT4_QUERY_RANGE_ABORT) aborted = true; else if (error) return error; /* If we didn't abort, set the "last" flag in the last fmx */ if (!aborted && info.gi_idx) { info.gi_last_flags |= FMR_OF_LAST; if (copy_to_user(&info.gi_data->fmh_recs[info.gi_idx - 1].fmr_flags, &info.gi_last_flags, sizeof(info.gi_last_flags))) return -EFAULT; } /* copy back header */ head.fmh_entries = xhead.fmh_entries; head.fmh_oflags = xhead.fmh_oflags; if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) return -EFAULT; return 0; } static long ext4_ioctl_group_add(struct file *file, struct ext4_new_group_data *input) { struct super_block *sb = file_inode(file)->i_sb; int err, err2=0; err = ext4_resize_begin(sb); if (err) return err; if (ext4_has_feature_bigalloc(sb)) { ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc"); err = -EOPNOTSUPP; goto group_add_out; } err = mnt_want_write_file(file); if (err) goto group_add_out; err = ext4_group_add(sb, input); if (EXT4_SB(sb)->s_journal) { jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) err = err2; mnt_drop_write_file(file); if (!err && ext4_has_group_desc_csum(sb) && test_opt(sb, INIT_INODE_TABLE)) err = ext4_register_li_request(sb, input->group); group_add_out: err2 = ext4_resize_end(sb, false); if (err == 0) err = err2; return err; } int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); struct ext4_inode_info *ei = EXT4_I(inode); u32 flags = ei->i_flags & EXT4_FL_USER_VISIBLE; if (S_ISREG(inode->i_mode)) flags &= ~FS_PROJINHERIT_FL; fileattr_fill_flags(fa, flags); if (ext4_has_feature_project(inode->i_sb)) fa->fsx_projid = from_kprojid(&init_user_ns, ei->i_projid); return 0; } int ext4_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); u32 flags = fa->flags; int err = -EOPNOTSUPP; if (flags & ~EXT4_FL_USER_VISIBLE) goto out; /* * chattr(1) grabs flags via GETFLAGS, modifies the result and * passes that to SETFLAGS. So we cannot easily make SETFLAGS * more restrictive than just silently masking off visible but * not settable flags as we always did. */ flags &= EXT4_FL_USER_MODIFIABLE; if (ext4_mask_flags(inode->i_mode, flags) != flags) goto out; err = ext4_ioctl_check_immutable(inode, fa->fsx_projid, flags); if (err) goto out; err = ext4_ioctl_setflags(inode, flags); if (err) goto out; err = ext4_ioctl_setproject(inode, fa->fsx_projid); out: return err; } /* So that the fiemap access checks can't overflow on 32 bit machines. */ #define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) static int ext4_ioctl_get_es_cache(struct file *filp, unsigned long arg) { struct fiemap fiemap; struct fiemap __user *ufiemap = (struct fiemap __user *) arg; struct fiemap_extent_info fieinfo = { 0, }; struct inode *inode = file_inode(filp); int error; if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap))) return -EFAULT; if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) return -EINVAL; fieinfo.fi_flags = fiemap.fm_flags; fieinfo.fi_extents_max = fiemap.fm_extent_count; fieinfo.fi_extents_start = ufiemap->fm_extents; error = ext4_get_es_cache(inode, &fieinfo, fiemap.fm_start, fiemap.fm_length); fiemap.fm_flags = fieinfo.fi_flags; fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap))) error = -EFAULT; return error; } static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg) { int err = 0; __u32 flags = 0; unsigned int flush_flags = 0; struct super_block *sb = file_inode(filp)->i_sb; if (copy_from_user(&flags, (__u32 __user *)arg, sizeof(__u32))) return -EFAULT; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* check for invalid bits set */ if ((flags & ~EXT4_IOC_CHECKPOINT_FLAG_VALID) || ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && (flags & JBD2_JOURNAL_FLUSH_ZEROOUT))) return -EINVAL; if (!EXT4_SB(sb)->s_journal) return -ENODEV; if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !bdev_max_discard_sectors(EXT4_SB(sb)->s_journal->j_dev)) return -EOPNOTSUPP; if (flags & EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN) return 0; if (flags & EXT4_IOC_CHECKPOINT_FLAG_DISCARD) flush_flags |= JBD2_JOURNAL_FLUSH_DISCARD; if (flags & EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT) { flush_flags |= JBD2_JOURNAL_FLUSH_ZEROOUT; pr_info_ratelimited("warning: checkpointing journal with EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT can be slow"); } jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err = jbd2_journal_flush(EXT4_SB(sb)->s_journal, flush_flags); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); return err; } static int ext4_ioctl_setlabel(struct file *filp, const char __user *user_label) { size_t len; int ret = 0; char new_label[EXT4_LABEL_MAX + 1]; struct super_block *sb = file_inode(filp)->i_sb; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* * Copy the maximum length allowed for ext4 label with one more to * find the required terminating null byte in order to test the * label length. The on disk label doesn't need to be null terminated. */ if (copy_from_user(new_label, user_label, EXT4_LABEL_MAX + 1)) return -EFAULT; len = strnlen(new_label, EXT4_LABEL_MAX + 1); if (len > EXT4_LABEL_MAX) return -EINVAL; /* * Clear the buffer after the new label */ memset(new_label + len, 0, EXT4_LABEL_MAX - len); ret = mnt_want_write_file(filp); if (ret) return ret; ret = ext4_update_superblocks_fn(sb, ext4_sb_setlabel, new_label); mnt_drop_write_file(filp); return ret; } static int ext4_ioctl_getlabel(struct ext4_sb_info *sbi, char __user *user_label) { char label[EXT4_LABEL_MAX + 1]; /* * EXT4_LABEL_MAX must always be smaller than FSLABEL_MAX because * FSLABEL_MAX must include terminating null byte, while s_volume_name * does not have to. */ BUILD_BUG_ON(EXT4_LABEL_MAX >= FSLABEL_MAX); lock_buffer(sbi->s_sbh); memtostr_pad(label, sbi->s_es->s_volume_name); unlock_buffer(sbi->s_sbh); if (copy_to_user(user_label, label, sizeof(label))) return -EFAULT; return 0; } static int ext4_ioctl_getuuid(struct ext4_sb_info *sbi, struct fsuuid __user *ufsuuid) { struct fsuuid fsuuid; __u8 uuid[UUID_SIZE]; if (copy_from_user(&fsuuid, ufsuuid, sizeof(fsuuid))) return -EFAULT; if (fsuuid.fsu_len == 0) { fsuuid.fsu_len = UUID_SIZE; if (copy_to_user(&ufsuuid->fsu_len, &fsuuid.fsu_len, sizeof(fsuuid.fsu_len))) return -EFAULT; return 0; } if (fsuuid.fsu_len < UUID_SIZE || fsuuid.fsu_flags != 0) return -EINVAL; lock_buffer(sbi->s_sbh); memcpy(uuid, sbi->s_es->s_uuid, UUID_SIZE); unlock_buffer(sbi->s_sbh); fsuuid.fsu_len = UUID_SIZE; if (copy_to_user(ufsuuid, &fsuuid, sizeof(fsuuid)) || copy_to_user(&ufsuuid->fsu_uuid[0], uuid, UUID_SIZE)) return -EFAULT; return 0; } static int ext4_ioctl_setuuid(struct file *filp, const struct fsuuid __user *ufsuuid) { int ret = 0; struct super_block *sb = file_inode(filp)->i_sb; struct fsuuid fsuuid; __u8 uuid[UUID_SIZE]; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* * If any checksums (group descriptors or metadata) are being used * then the checksum seed feature is required to change the UUID. */ if (((ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb)) && !ext4_has_feature_csum_seed(sb)) || ext4_has_feature_stable_inodes(sb)) return -EOPNOTSUPP; if (copy_from_user(&fsuuid, ufsuuid, sizeof(fsuuid))) return -EFAULT; if (fsuuid.fsu_len != UUID_SIZE || fsuuid.fsu_flags != 0) return -EINVAL; if (copy_from_user(uuid, &ufsuuid->fsu_uuid[0], UUID_SIZE)) return -EFAULT; ret = mnt_want_write_file(filp); if (ret) return ret; ret = ext4_update_superblocks_fn(sb, ext4_sb_setuuid, &uuid); mnt_drop_write_file(filp); return ret; } static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; struct mnt_idmap *idmap = file_mnt_idmap(filp); ext4_debug("cmd = %u, arg = %lu\n", cmd, arg); switch (cmd) { case FS_IOC_GETFSMAP: return ext4_ioc_getfsmap(sb, (void __user *)arg); case EXT4_IOC_GETVERSION: case EXT4_IOC_GETVERSION_OLD: return put_user(inode->i_generation, (int __user *) arg); case EXT4_IOC_SETVERSION: case EXT4_IOC_SETVERSION_OLD: { handle_t *handle; struct ext4_iloc iloc; __u32 generation; int err; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (ext4_has_metadata_csum(inode->i_sb)) { ext4_warning(sb, "Setting inode version is not " "supported with metadata_csum enabled."); return -ENOTTY; } err = mnt_want_write_file(filp); if (err) return err; if (get_user(generation, (int __user *) arg)) { err = -EFAULT; goto setversion_out; } inode_lock(inode); handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto unlock_out; } err = ext4_reserve_inode_write(handle, inode, &iloc); if (err == 0) { inode_set_ctime_current(inode); inode_inc_iversion(inode); inode->i_generation = generation; err = ext4_mark_iloc_dirty(handle, inode, &iloc); } ext4_journal_stop(handle); unlock_out: inode_unlock(inode); setversion_out: mnt_drop_write_file(filp); return err; } case EXT4_IOC_GROUP_EXTEND: { ext4_fsblk_t n_blocks_count; int err, err2=0; err = ext4_resize_begin(sb); if (err) return err; if (get_user(n_blocks_count, (__u32 __user *)arg)) { err = -EFAULT; goto group_extend_out; } if (ext4_has_feature_bigalloc(sb)) { ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc"); err = -EOPNOTSUPP; goto group_extend_out; } err = mnt_want_write_file(filp); if (err) goto group_extend_out; err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count); if (EXT4_SB(sb)->s_journal) { jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) err = err2; mnt_drop_write_file(filp); group_extend_out: err2 = ext4_resize_end(sb, false); if (err == 0) err = err2; return err; } case EXT4_IOC_MOVE_EXT: { struct move_extent me; int err; if (!(filp->f_mode & FMODE_READ) || !(filp->f_mode & FMODE_WRITE)) return -EBADF; if (copy_from_user(&me, (struct move_extent __user *)arg, sizeof(me))) return -EFAULT; me.moved_len = 0; CLASS(fd, donor)(me.donor_fd); if (fd_empty(donor)) return -EBADF; if (!(fd_file(donor)->f_mode & FMODE_WRITE)) return -EBADF; if (ext4_has_feature_bigalloc(sb)) { ext4_msg(sb, KERN_ERR, "Online defrag not supported with bigalloc"); return -EOPNOTSUPP; } else if (IS_DAX(inode)) { ext4_msg(sb, KERN_ERR, "Online defrag not supported with DAX"); return -EOPNOTSUPP; } err = mnt_want_write_file(filp); if (err) return err; err = ext4_move_extents(filp, fd_file(donor), me.orig_start, me.donor_start, me.len, &me.moved_len); mnt_drop_write_file(filp); if (copy_to_user((struct move_extent __user *)arg, &me, sizeof(me))) err = -EFAULT; return err; } case EXT4_IOC_GROUP_ADD: { struct ext4_new_group_data input; if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg, sizeof(input))) return -EFAULT; return ext4_ioctl_group_add(filp, &input); } case EXT4_IOC_MIGRATE: { int err; if (!inode_owner_or_capable(idmap, inode)) return -EACCES; err = mnt_want_write_file(filp); if (err) return err; /* * inode_mutex prevent write and truncate on the file. * Read still goes through. We take i_data_sem in * ext4_ext_swap_inode_data before we switch the * inode format to prevent read. */ inode_lock((inode)); err = ext4_ext_migrate(inode); inode_unlock((inode)); mnt_drop_write_file(filp); return err; } case EXT4_IOC_ALLOC_DA_BLKS: { int err; if (!inode_owner_or_capable(idmap, inode)) return -EACCES; err = mnt_want_write_file(filp); if (err) return err; err = ext4_alloc_da_blocks(inode); mnt_drop_write_file(filp); return err; } case EXT4_IOC_SWAP_BOOT: { int err; if (!(filp->f_mode & FMODE_WRITE)) return -EBADF; err = mnt_want_write_file(filp); if (err) return err; err = swap_inode_boot_loader(sb, idmap, inode); mnt_drop_write_file(filp); return err; } case EXT4_IOC_RESIZE_FS: { ext4_fsblk_t n_blocks_count; int err = 0, err2 = 0; ext4_group_t o_group = EXT4_SB(sb)->s_groups_count; if (copy_from_user(&n_blocks_count, (__u64 __user *)arg, sizeof(__u64))) { return -EFAULT; } err = ext4_resize_begin(sb); if (err) return err; err = mnt_want_write_file(filp); if (err) goto resizefs_out; err = ext4_resize_fs(sb, n_blocks_count); if (EXT4_SB(sb)->s_journal) { ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE, NULL); jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) err = err2; mnt_drop_write_file(filp); if (!err && (o_group < EXT4_SB(sb)->s_groups_count) && ext4_has_group_desc_csum(sb) && test_opt(sb, INIT_INODE_TABLE)) err = ext4_register_li_request(sb, o_group); resizefs_out: err2 = ext4_resize_end(sb, true); if (err == 0) err = err2; return err; } case FITRIM: { struct fstrim_range range; int ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!bdev_max_discard_sectors(sb->s_bdev)) return -EOPNOTSUPP; /* * We haven't replayed the journal, so we cannot use our * block-bitmap-guided storage zapping commands. */ if (test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) return -EROFS; if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; ret = ext4_trim_fs(sb, &range); if (ret < 0) return ret; if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range))) return -EFAULT; return 0; } case EXT4_IOC_PRECACHE_EXTENTS: return ext4_ext_precache(inode); case FS_IOC_SET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_set_policy(filp, (const void __user *)arg); case FS_IOC_GET_ENCRYPTION_PWSALT: return ext4_ioctl_get_encryption_pwsalt(filp, (void __user *)arg); case FS_IOC_GET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_policy(filp, (void __user *)arg); case FS_IOC_GET_ENCRYPTION_POLICY_EX: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_policy_ex(filp, (void __user *)arg); case FS_IOC_ADD_ENCRYPTION_KEY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_add_key(filp, (void __user *)arg); case FS_IOC_REMOVE_ENCRYPTION_KEY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_remove_key(filp, (void __user *)arg); case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_remove_key_all_users(filp, (void __user *)arg); case FS_IOC_GET_ENCRYPTION_KEY_STATUS: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_key_status(filp, (void __user *)arg); case FS_IOC_GET_ENCRYPTION_NONCE: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_nonce(filp, (void __user *)arg); case EXT4_IOC_CLEAR_ES_CACHE: { if (!inode_owner_or_capable(idmap, inode)) return -EACCES; ext4_clear_inode_es(inode); return 0; } case EXT4_IOC_GETSTATE: { __u32 state = 0; if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED)) state |= EXT4_STATE_FLAG_EXT_PRECACHED; if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) state |= EXT4_STATE_FLAG_NEW; if (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) state |= EXT4_STATE_FLAG_NEWENTRY; if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) state |= EXT4_STATE_FLAG_DA_ALLOC_CLOSE; return put_user(state, (__u32 __user *) arg); } case EXT4_IOC_GET_ES_CACHE: return ext4_ioctl_get_es_cache(filp, arg); case EXT4_IOC_SHUTDOWN: return ext4_ioctl_shutdown(sb, arg); case FS_IOC_ENABLE_VERITY: if (!ext4_has_feature_verity(sb)) return -EOPNOTSUPP; return fsverity_ioctl_enable(filp, (const void __user *)arg); case FS_IOC_MEASURE_VERITY: if (!ext4_has_feature_verity(sb)) return -EOPNOTSUPP; return fsverity_ioctl_measure(filp, (void __user *)arg); case FS_IOC_READ_VERITY_METADATA: if (!ext4_has_feature_verity(sb)) return -EOPNOTSUPP; return fsverity_ioctl_read_metadata(filp, (const void __user *)arg); case EXT4_IOC_CHECKPOINT: return ext4_ioctl_checkpoint(filp, arg); case FS_IOC_GETFSLABEL: return ext4_ioctl_getlabel(EXT4_SB(sb), (void __user *)arg); case FS_IOC_SETFSLABEL: return ext4_ioctl_setlabel(filp, (const void __user *)arg); case EXT4_IOC_GETFSUUID: return ext4_ioctl_getuuid(EXT4_SB(sb), (void __user *)arg); case EXT4_IOC_SETFSUUID: return ext4_ioctl_setuuid(filp, (const void __user *)arg); default: return -ENOTTY; } } long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { return __ext4_ioctl(filp, cmd, arg); } #ifdef CONFIG_COMPAT long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { /* These are just misnamed, they actually get/put from/to user an int */ switch (cmd) { case EXT4_IOC32_GETVERSION: cmd = EXT4_IOC_GETVERSION; break; case EXT4_IOC32_SETVERSION: cmd = EXT4_IOC_SETVERSION; break; case EXT4_IOC32_GROUP_EXTEND: cmd = EXT4_IOC_GROUP_EXTEND; break; case EXT4_IOC32_GETVERSION_OLD: cmd = EXT4_IOC_GETVERSION_OLD; break; case EXT4_IOC32_SETVERSION_OLD: cmd = EXT4_IOC_SETVERSION_OLD; break; case EXT4_IOC32_GETRSVSZ: cmd = EXT4_IOC_GETRSVSZ; break; case EXT4_IOC32_SETRSVSZ: cmd = EXT4_IOC_SETRSVSZ; break; case EXT4_IOC32_GROUP_ADD: { struct compat_ext4_new_group_input __user *uinput; struct ext4_new_group_data input; int err; uinput = compat_ptr(arg); err = get_user(input.group, &uinput->group); err |= get_user(input.block_bitmap, &uinput->block_bitmap); err |= get_user(input.inode_bitmap, &uinput->inode_bitmap); err |= get_user(input.inode_table, &uinput->inode_table); err |= get_user(input.blocks_count, &uinput->blocks_count); err |= get_user(input.reserved_blocks, &uinput->reserved_blocks); if (err) return -EFAULT; return ext4_ioctl_group_add(file, &input); } case EXT4_IOC_MOVE_EXT: case EXT4_IOC_RESIZE_FS: case FITRIM: case EXT4_IOC_PRECACHE_EXTENTS: case FS_IOC_SET_ENCRYPTION_POLICY: case FS_IOC_GET_ENCRYPTION_PWSALT: case FS_IOC_GET_ENCRYPTION_POLICY: case FS_IOC_GET_ENCRYPTION_POLICY_EX: case FS_IOC_ADD_ENCRYPTION_KEY: case FS_IOC_REMOVE_ENCRYPTION_KEY: case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS: case FS_IOC_GET_ENCRYPTION_KEY_STATUS: case FS_IOC_GET_ENCRYPTION_NONCE: case EXT4_IOC_SHUTDOWN: case FS_IOC_GETFSMAP: case FS_IOC_ENABLE_VERITY: case FS_IOC_MEASURE_VERITY: case FS_IOC_READ_VERITY_METADATA: case EXT4_IOC_CLEAR_ES_CACHE: case EXT4_IOC_GETSTATE: case EXT4_IOC_GET_ES_CACHE: case EXT4_IOC_CHECKPOINT: case FS_IOC_GETFSLABEL: case FS_IOC_SETFSLABEL: case EXT4_IOC_GETFSUUID: case EXT4_IOC_SETFSUUID: break; default: return -ENOIOCTLCMD; } return ext4_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif static void set_overhead(struct ext4_super_block *es, const void *arg) { es->s_overhead_clusters = cpu_to_le32(*((unsigned long *) arg)); } int ext4_update_overhead(struct super_block *sb, bool force) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (sb_rdonly(sb)) return 0; if (!force && (sbi->s_overhead == 0 || sbi->s_overhead == le32_to_cpu(sbi->s_es->s_overhead_clusters))) return 0; return ext4_update_superblocks_fn(sb, set_overhead, &sbi->s_overhead); } |
| 2 2 346 347 16 64 26 347 346 26 347 347 76 347 345 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_log_format.h" #include "xfs_bit.h" /* * XFS bit manipulation routines, used in non-realtime code. */ /* * Return whether bitmap is empty. * Size is number of words in the bitmap, which is padded to word boundary * Returns 1 for empty, 0 for non-empty. */ int xfs_bitmap_empty(uint *map, uint size) { uint i; for (i = 0; i < size; i++) { if (map[i] != 0) return 0; } return 1; } /* * Count the number of contiguous bits set in the bitmap starting with bit * start_bit. Size is the size of the bitmap in words. */ int xfs_contig_bits(uint *map, uint size, uint start_bit) { uint * p = ((unsigned int *) map) + (start_bit >> BIT_TO_WORD_SHIFT); uint result = 0; uint tmp; size <<= BIT_TO_WORD_SHIFT; ASSERT(start_bit < size); size -= start_bit & ~(NBWORD - 1); start_bit &= (NBWORD - 1); if (start_bit) { tmp = *p++; /* set to one first offset bits prior to start */ tmp |= (~0U >> (NBWORD-start_bit)); if (tmp != ~0U) goto found; result += NBWORD; size -= NBWORD; } while (size) { if ((tmp = *p++) != ~0U) goto found; result += NBWORD; size -= NBWORD; } return result - start_bit; found: return result + ffz(tmp) - start_bit; } /* * This takes the bit number to start looking from and * returns the next set bit from there. It returns -1 * if there are no more bits set or the start bit is * beyond the end of the bitmap. * * Size is the number of words, not bytes, in the bitmap. */ int xfs_next_bit(uint *map, uint size, uint start_bit) { uint * p = ((unsigned int *) map) + (start_bit >> BIT_TO_WORD_SHIFT); uint result = start_bit & ~(NBWORD - 1); uint tmp; size <<= BIT_TO_WORD_SHIFT; if (start_bit >= size) return -1; size -= result; start_bit &= (NBWORD - 1); if (start_bit) { tmp = *p++; /* set to zero first offset bits prior to start */ tmp &= (~0U << start_bit); if (tmp != 0U) goto found; result += NBWORD; size -= NBWORD; } while (size) { if ((tmp = *p++) != 0U) goto found; result += NBWORD; size -= NBWORD; } return -1; found: return result + ffs(tmp) - 1; } |
| 16 16 16 4 16 16 4 12 16 2 16 16 13 6 16 2 16 16 16 13 16 2 2 2 2 2 2 2 13 13 16 16 16 16 16 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 | // SPDX-License-Identifier: GPL-2.0 /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> #include "debug.h" #include "ntfs_fs.h" // clang-format off /* Src buffer is zero. */ #define LZNT_ERROR_ALL_ZEROS 1 #define LZNT_CHUNK_SIZE 0x1000 // clang-format on struct lznt_hash { const u8 *p1; const u8 *p2; }; struct lznt { const u8 *unc; const u8 *unc_end; const u8 *best_match; size_t max_len; bool std; struct lznt_hash hash[LZNT_CHUNK_SIZE]; }; static inline size_t get_match_len(const u8 *ptr, const u8 *end, const u8 *prev, size_t max_len) { size_t len = 0; while (ptr + len < end && ptr[len] == prev[len] && ++len < max_len) ; return len; } static size_t longest_match_std(const u8 *src, struct lznt *ctx) { size_t hash_index; size_t len1 = 0, len2 = 0; const u8 **hash; hash_index = ((40543U * ((((src[0] << 4) ^ src[1]) << 4) ^ src[2])) >> 4) & (LZNT_CHUNK_SIZE - 1); hash = &(ctx->hash[hash_index].p1); if (hash[0] >= ctx->unc && hash[0] < src && hash[0][0] == src[0] && hash[0][1] == src[1] && hash[0][2] == src[2]) { len1 = 3; if (ctx->max_len > 3) len1 += get_match_len(src + 3, ctx->unc_end, hash[0] + 3, ctx->max_len - 3); } if (hash[1] >= ctx->unc && hash[1] < src && hash[1][0] == src[0] && hash[1][1] == src[1] && hash[1][2] == src[2]) { len2 = 3; if (ctx->max_len > 3) len2 += get_match_len(src + 3, ctx->unc_end, hash[1] + 3, ctx->max_len - 3); } /* Compare two matches and select the best one. */ if (len1 < len2) { ctx->best_match = hash[1]; len1 = len2; } else { ctx->best_match = hash[0]; } hash[1] = hash[0]; hash[0] = src; return len1; } static size_t longest_match_best(const u8 *src, struct lznt *ctx) { size_t max_len; const u8 *ptr; if (ctx->unc >= src || !ctx->max_len) return 0; max_len = 0; for (ptr = ctx->unc; ptr < src; ++ptr) { size_t len = get_match_len(src, ctx->unc_end, ptr, ctx->max_len); if (len >= max_len) { max_len = len; ctx->best_match = ptr; } } return max_len >= 3 ? max_len : 0; } static const size_t s_max_len[] = { 0x1002, 0x802, 0x402, 0x202, 0x102, 0x82, 0x42, 0x22, 0x12, }; static const size_t s_max_off[] = { 0x10, 0x20, 0x40, 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, }; static inline u16 make_pair(size_t offset, size_t len, size_t index) { return ((offset - 1) << (12 - index)) | ((len - 3) & (((1 << (12 - index)) - 1))); } static inline size_t parse_pair(u16 pair, size_t *offset, size_t index) { *offset = 1 + (pair >> (12 - index)); return 3 + (pair & ((1 << (12 - index)) - 1)); } /* * compress_chunk * * Return: * * 0 - Ok, @cmpr contains @cmpr_chunk_size bytes of compressed data. * * 1 - Input buffer is full zero. * * -2 - The compressed buffer is too small to hold the compressed data. */ static inline int compress_chunk(size_t (*match)(const u8 *, struct lznt *), const u8 *unc, const u8 *unc_end, u8 *cmpr, u8 *cmpr_end, size_t *cmpr_chunk_size, struct lznt *ctx) { size_t cnt = 0; size_t idx = 0; const u8 *up = unc; u8 *cp = cmpr + 3; u8 *cp2 = cmpr + 2; u8 not_zero = 0; /* Control byte of 8-bit values: ( 0 - means byte as is, 1 - short pair ). */ u8 ohdr = 0; u8 *last; u16 t16; if (unc + LZNT_CHUNK_SIZE < unc_end) unc_end = unc + LZNT_CHUNK_SIZE; last = min(cmpr + LZNT_CHUNK_SIZE + sizeof(short), cmpr_end); ctx->unc = unc; ctx->unc_end = unc_end; ctx->max_len = s_max_len[0]; while (up < unc_end) { size_t max_len; while (unc + s_max_off[idx] < up) ctx->max_len = s_max_len[++idx]; /* Find match. */ max_len = up + 3 <= unc_end ? (*match)(up, ctx) : 0; if (!max_len) { if (cp >= last) goto NotCompressed; not_zero |= *cp++ = *up++; } else if (cp + 1 >= last) { goto NotCompressed; } else { t16 = make_pair(up - ctx->best_match, max_len, idx); *cp++ = t16; *cp++ = t16 >> 8; ohdr |= 1 << cnt; up += max_len; } cnt = (cnt + 1) & 7; if (!cnt) { *cp2 = ohdr; ohdr = 0; cp2 = cp; cp += 1; } } if (cp2 < last) *cp2 = ohdr; else cp -= 1; *cmpr_chunk_size = cp - cmpr; t16 = (*cmpr_chunk_size - 3) | 0xB000; cmpr[0] = t16; cmpr[1] = t16 >> 8; return not_zero ? 0 : LZNT_ERROR_ALL_ZEROS; NotCompressed: if ((cmpr + LZNT_CHUNK_SIZE + sizeof(short)) > last) return -2; /* * Copy non cmpr data. * 0x3FFF == ((LZNT_CHUNK_SIZE + 2 - 3) | 0x3000) */ cmpr[0] = 0xff; cmpr[1] = 0x3f; memcpy(cmpr + sizeof(short), unc, LZNT_CHUNK_SIZE); *cmpr_chunk_size = LZNT_CHUNK_SIZE + sizeof(short); return 0; } static inline ssize_t decompress_chunk(u8 *unc, u8 *unc_end, const u8 *cmpr, const u8 *cmpr_end) { u8 *up = unc; u8 ch = *cmpr++; size_t bit = 0; size_t index = 0; u16 pair; size_t offset, length; /* Do decompression until pointers are inside range. */ while (up < unc_end && cmpr < cmpr_end) { // return err if more than LZNT_CHUNK_SIZE bytes are written if (up - unc > LZNT_CHUNK_SIZE) return -EINVAL; /* Correct index */ while (unc + s_max_off[index] < up) index += 1; /* Check the current flag for zero. */ if (!(ch & (1 << bit))) { /* Just copy byte. */ *up++ = *cmpr++; goto next; } /* Check for boundary. */ if (cmpr + 1 >= cmpr_end) return -EINVAL; /* Read a short from little endian stream. */ pair = cmpr[1]; pair <<= 8; pair |= cmpr[0]; cmpr += 2; /* Translate packed information into offset and length. */ length = parse_pair(pair, &offset, index); /* Check offset for boundary. */ if (unc + offset > up) return -EINVAL; /* Truncate the length if necessary. */ if (up + length >= unc_end) length = unc_end - up; /* Now we copy bytes. This is the heart of LZ algorithm. */ for (; length > 0; length--, up++) *up = *(up - offset); next: /* Advance flag bit value. */ bit = (bit + 1) & 7; if (!bit) { if (cmpr >= cmpr_end) break; ch = *cmpr++; } } /* Return the size of uncompressed data. */ return up - unc; } /* * get_lznt_ctx * @level: 0 - Standard compression. * !0 - Best compression, requires a lot of cpu. */ struct lznt *get_lznt_ctx(int level) { struct lznt *r = kzalloc(level ? offsetof(struct lznt, hash) : sizeof(struct lznt), GFP_NOFS); if (r) r->std = !level; return r; } /* * compress_lznt - Compresses @unc into @cmpr * * Return: * * +x - Ok, @cmpr contains 'final_compressed_size' bytes of compressed data. * * 0 - Input buffer is full zero. */ size_t compress_lznt(const void *unc, size_t unc_size, void *cmpr, size_t cmpr_size, struct lznt *ctx) { int err; size_t (*match)(const u8 *src, struct lznt *ctx); u8 *p = cmpr; u8 *end = p + cmpr_size; const u8 *unc_chunk = unc; const u8 *unc_end = unc_chunk + unc_size; bool is_zero = true; if (ctx->std) { match = &longest_match_std; memset(ctx->hash, 0, sizeof(ctx->hash)); } else { match = &longest_match_best; } /* Compression cycle. */ for (; unc_chunk < unc_end; unc_chunk += LZNT_CHUNK_SIZE) { cmpr_size = 0; err = compress_chunk(match, unc_chunk, unc_end, p, end, &cmpr_size, ctx); if (err < 0) return unc_size; if (is_zero && err != LZNT_ERROR_ALL_ZEROS) is_zero = false; p += cmpr_size; } if (p <= end - 2) p[0] = p[1] = 0; return is_zero ? 0 : PtrOffset(cmpr, p); } /* * decompress_lznt - Decompress @cmpr into @unc. */ ssize_t decompress_lznt(const void *cmpr, size_t cmpr_size, void *unc, size_t unc_size) { const u8 *cmpr_chunk = cmpr; const u8 *cmpr_end = cmpr_chunk + cmpr_size; u8 *unc_chunk = unc; u8 *unc_end = unc_chunk + unc_size; u16 chunk_hdr; if (cmpr_size < sizeof(short)) return -EINVAL; /* Read chunk header. */ chunk_hdr = cmpr_chunk[1]; chunk_hdr <<= 8; chunk_hdr |= cmpr_chunk[0]; /* Loop through decompressing chunks. */ for (;;) { size_t chunk_size_saved; size_t unc_use; size_t cmpr_use = 3 + (chunk_hdr & (LZNT_CHUNK_SIZE - 1)); /* Check that the chunk actually fits the supplied buffer. */ if (cmpr_chunk + cmpr_use > cmpr_end) return -EINVAL; /* First make sure the chunk contains compressed data. */ if (chunk_hdr & 0x8000) { /* Decompress a chunk and return if we get an error. */ ssize_t err = decompress_chunk(unc_chunk, unc_end, cmpr_chunk + sizeof(chunk_hdr), cmpr_chunk + cmpr_use); if (err < 0) return err; unc_use = err; } else { /* This chunk does not contain compressed data. */ unc_use = unc_chunk + LZNT_CHUNK_SIZE > unc_end ? unc_end - unc_chunk : LZNT_CHUNK_SIZE; if (cmpr_chunk + sizeof(chunk_hdr) + unc_use > cmpr_end) { return -EINVAL; } memcpy(unc_chunk, cmpr_chunk + sizeof(chunk_hdr), unc_use); } /* Advance pointers. */ cmpr_chunk += cmpr_use; unc_chunk += unc_use; /* Check for the end of unc buffer. */ if (unc_chunk >= unc_end) break; /* Proceed the next chunk. */ if (cmpr_chunk > cmpr_end - 2) break; chunk_size_saved = LZNT_CHUNK_SIZE; /* Read chunk header. */ chunk_hdr = cmpr_chunk[1]; chunk_hdr <<= 8; chunk_hdr |= cmpr_chunk[0]; if (!chunk_hdr) break; /* Check the size of unc buffer. */ if (unc_use < chunk_size_saved) { size_t t1 = chunk_size_saved - unc_use; u8 *t2 = unc_chunk + t1; /* 'Zero' memory. */ if (t2 >= unc_end) break; memset(unc_chunk, 0, t1); unc_chunk = t2; } } /* Check compression boundary. */ if (cmpr_chunk > cmpr_end) return -EINVAL; /* * The unc size is just a difference between current * pointer and original one. */ return PtrOffset(unc, unc_chunk); } |
| 72 71 35 35 33 2 33 33 8 1 1 7 7 54 55 53 1 44 45 43 1487 3 1483 1485 1485 744 745 232 232 232 238 10 10 29 29 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/file.c - sysfs regular (text) file implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * * Please see Documentation/filesystems/sysfs.rst for more information. */ #include <linux/module.h> #include <linux/kobject.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/seq_file.h> #include <linux/mm.h> #include "sysfs.h" /* * Determine ktype->sysfs_ops for the given kernfs_node. This function * must be called while holding an active reference. */ static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn) { struct kobject *kobj = kn->parent->priv; if (kn->flags & KERNFS_LOCKDEP) lockdep_assert_held(kn); return kobj->ktype ? kobj->ktype->sysfs_ops : NULL; } /* * Reads on sysfs are handled through seq_file, which takes care of hairy * details like buffering and seeking. The following function pipes * sysfs_ops->show() result through seq_file. */ static int sysfs_kf_seq_show(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; struct kobject *kobj = of->kn->parent->priv; const struct sysfs_ops *ops = sysfs_file_ops(of->kn); ssize_t count; char *buf; if (WARN_ON_ONCE(!ops->show)) return -EINVAL; /* acquire buffer and ensure that it's >= PAGE_SIZE and clear */ count = seq_get_buf(sf, &buf); if (count < PAGE_SIZE) { seq_commit(sf, -1); return 0; } memset(buf, 0, PAGE_SIZE); count = ops->show(kobj, of->kn->priv, buf); if (count < 0) return count; /* * The code works fine with PAGE_SIZE return but it's likely to * indicate truncated result or overflow in normal use cases. */ if (count >= (ssize_t)PAGE_SIZE) { printk("fill_read_buffer: %pS returned bad count\n", ops->show); /* Try to struggle along */ count = PAGE_SIZE - 1; } seq_commit(sf, count); return 0; } static ssize_t sysfs_kf_bin_read(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { struct bin_attribute *battr = of->kn->priv; struct kobject *kobj = of->kn->parent->priv; loff_t size = file_inode(of->file)->i_size; if (!count) return 0; if (size) { if (pos >= size) return 0; if (pos + count > size) count = size - pos; } if (!battr->read) return -EIO; return battr->read(of->file, kobj, battr, buf, pos, count); } /* kernfs read callback for regular sysfs files with pre-alloc */ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); struct kobject *kobj = of->kn->parent->priv; ssize_t len; /* * If buf != of->prealloc_buf, we don't know how * large it is, so cannot safely pass it to ->show */ if (WARN_ON_ONCE(buf != of->prealloc_buf)) return 0; len = ops->show(kobj, of->kn->priv, buf); if (len < 0) return len; if (pos) { if (len <= pos) return 0; len -= pos; memmove(buf, buf + pos, len); } return min_t(ssize_t, count, len); } /* kernfs write callback for regular sysfs files */ static ssize_t sysfs_kf_write(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); struct kobject *kobj = of->kn->parent->priv; if (!count) return 0; return ops->store(kobj, of->kn->priv, buf, count); } /* kernfs write callback for bin sysfs files */ static ssize_t sysfs_kf_bin_write(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { struct bin_attribute *battr = of->kn->priv; struct kobject *kobj = of->kn->parent->priv; loff_t size = file_inode(of->file)->i_size; if (size) { if (size <= pos) return -EFBIG; count = min_t(ssize_t, count, size - pos); } if (!count) return 0; if (!battr->write) return -EIO; return battr->write(of->file, kobj, battr, buf, pos, count); } static int sysfs_kf_bin_mmap(struct kernfs_open_file *of, struct vm_area_struct *vma) { struct bin_attribute *battr = of->kn->priv; struct kobject *kobj = of->kn->parent->priv; return battr->mmap(of->file, kobj, battr, vma); } static loff_t sysfs_kf_bin_llseek(struct kernfs_open_file *of, loff_t offset, int whence) { struct bin_attribute *battr = of->kn->priv; struct kobject *kobj = of->kn->parent->priv; if (battr->llseek) return battr->llseek(of->file, kobj, battr, offset, whence); else return generic_file_llseek(of->file, offset, whence); } static int sysfs_kf_bin_open(struct kernfs_open_file *of) { struct bin_attribute *battr = of->kn->priv; if (battr->f_mapping) of->file->f_mapping = battr->f_mapping(); return 0; } void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr) { struct kernfs_node *kn = kobj->sd, *tmp; if (kn && dir) kn = kernfs_find_and_get(kn, dir); else kernfs_get(kn); if (kn && attr) { tmp = kernfs_find_and_get(kn, attr); kernfs_put(kn); kn = tmp; } if (kn) { kernfs_notify(kn); kernfs_put(kn); } } EXPORT_SYMBOL_GPL(sysfs_notify); static const struct kernfs_ops sysfs_file_kfops_empty = { }; static const struct kernfs_ops sysfs_file_kfops_ro = { .seq_show = sysfs_kf_seq_show, }; static const struct kernfs_ops sysfs_file_kfops_wo = { .write = sysfs_kf_write, }; static const struct kernfs_ops sysfs_file_kfops_rw = { .seq_show = sysfs_kf_seq_show, .write = sysfs_kf_write, }; static const struct kernfs_ops sysfs_prealloc_kfops_ro = { .read = sysfs_kf_read, .prealloc = true, }; static const struct kernfs_ops sysfs_prealloc_kfops_wo = { .write = sysfs_kf_write, .prealloc = true, }; static const struct kernfs_ops sysfs_prealloc_kfops_rw = { .read = sysfs_kf_read, .write = sysfs_kf_write, .prealloc = true, }; static const struct kernfs_ops sysfs_bin_kfops_ro = { .read = sysfs_kf_bin_read, }; static const struct kernfs_ops sysfs_bin_kfops_wo = { .write = sysfs_kf_bin_write, }; static const struct kernfs_ops sysfs_bin_kfops_rw = { .read = sysfs_kf_bin_read, .write = sysfs_kf_bin_write, }; static const struct kernfs_ops sysfs_bin_kfops_mmap = { .read = sysfs_kf_bin_read, .write = sysfs_kf_bin_write, .mmap = sysfs_kf_bin_mmap, .open = sysfs_kf_bin_open, .llseek = sysfs_kf_bin_llseek, }; int sysfs_add_file_mode_ns(struct kernfs_node *parent, const struct attribute *attr, umode_t mode, kuid_t uid, kgid_t gid, const void *ns) { struct kobject *kobj = parent->priv; const struct sysfs_ops *sysfs_ops = kobj->ktype->sysfs_ops; struct lock_class_key *key = NULL; const struct kernfs_ops *ops = NULL; struct kernfs_node *kn; /* every kobject with an attribute needs a ktype assigned */ if (WARN(!sysfs_ops, KERN_ERR "missing sysfs attribute operations for kobject: %s\n", kobject_name(kobj))) return -EINVAL; if (mode & SYSFS_PREALLOC) { if (sysfs_ops->show && sysfs_ops->store) ops = &sysfs_prealloc_kfops_rw; else if (sysfs_ops->show) ops = &sysfs_prealloc_kfops_ro; else if (sysfs_ops->store) ops = &sysfs_prealloc_kfops_wo; } else { if (sysfs_ops->show && sysfs_ops->store) ops = &sysfs_file_kfops_rw; else if (sysfs_ops->show) ops = &sysfs_file_kfops_ro; else if (sysfs_ops->store) ops = &sysfs_file_kfops_wo; } if (!ops) ops = &sysfs_file_kfops_empty; #ifdef CONFIG_DEBUG_LOCK_ALLOC if (!attr->ignore_lockdep) key = attr->key ?: (struct lock_class_key *)&attr->skey; #endif kn = __kernfs_create_file(parent, attr->name, mode & 0777, uid, gid, PAGE_SIZE, ops, (void *)attr, ns, key); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, attr->name); return PTR_ERR(kn); } return 0; } int sysfs_add_bin_file_mode_ns(struct kernfs_node *parent, const struct bin_attribute *battr, umode_t mode, kuid_t uid, kgid_t gid, const void *ns) { const struct attribute *attr = &battr->attr; struct lock_class_key *key = NULL; const struct kernfs_ops *ops; struct kernfs_node *kn; if (battr->mmap) ops = &sysfs_bin_kfops_mmap; else if (battr->read && battr->write) ops = &sysfs_bin_kfops_rw; else if (battr->read) ops = &sysfs_bin_kfops_ro; else if (battr->write) ops = &sysfs_bin_kfops_wo; else ops = &sysfs_file_kfops_empty; #ifdef CONFIG_DEBUG_LOCK_ALLOC if (!attr->ignore_lockdep) key = attr->key ?: (struct lock_class_key *)&attr->skey; #endif kn = __kernfs_create_file(parent, attr->name, mode & 0777, uid, gid, battr->size, ops, (void *)attr, ns, key); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, attr->name); return PTR_ERR(kn); } return 0; } /** * sysfs_create_file_ns - create an attribute file for an object with custom ns * @kobj: object we're creating for * @attr: attribute descriptor * @ns: namespace the new file should belong to */ int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns) { kuid_t uid; kgid_t gid; if (WARN_ON(!kobj || !kobj->sd || !attr)) return -EINVAL; kobject_get_ownership(kobj, &uid, &gid); return sysfs_add_file_mode_ns(kobj->sd, attr, attr->mode, uid, gid, ns); } EXPORT_SYMBOL_GPL(sysfs_create_file_ns); int sysfs_create_files(struct kobject *kobj, const struct attribute * const *ptr) { int err = 0; int i; for (i = 0; ptr[i] && !err; i++) err = sysfs_create_file(kobj, ptr[i]); if (err) while (--i >= 0) sysfs_remove_file(kobj, ptr[i]); return err; } EXPORT_SYMBOL_GPL(sysfs_create_files); /** * sysfs_add_file_to_group - add an attribute file to a pre-existing group. * @kobj: object we're acting for. * @attr: attribute descriptor. * @group: group name. */ int sysfs_add_file_to_group(struct kobject *kobj, const struct attribute *attr, const char *group) { struct kernfs_node *parent; kuid_t uid; kgid_t gid; int error; if (group) { parent = kernfs_find_and_get(kobj->sd, group); } else { parent = kobj->sd; kernfs_get(parent); } if (!parent) return -ENOENT; kobject_get_ownership(kobj, &uid, &gid); error = sysfs_add_file_mode_ns(parent, attr, attr->mode, uid, gid, NULL); kernfs_put(parent); return error; } EXPORT_SYMBOL_GPL(sysfs_add_file_to_group); /** * sysfs_chmod_file - update the modified mode value on an object attribute. * @kobj: object we're acting for. * @attr: attribute descriptor. * @mode: file permissions. * */ int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr, umode_t mode) { struct kernfs_node *kn; struct iattr newattrs; int rc; kn = kernfs_find_and_get(kobj->sd, attr->name); if (!kn) return -ENOENT; newattrs.ia_mode = (mode & S_IALLUGO) | (kn->mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE; rc = kernfs_setattr(kn, &newattrs); kernfs_put(kn); return rc; } EXPORT_SYMBOL_GPL(sysfs_chmod_file); /** * sysfs_break_active_protection - break "active" protection * @kobj: The kernel object @attr is associated with. * @attr: The attribute to break the "active" protection for. * * With sysfs, just like kernfs, deletion of an attribute is postponed until * all active .show() and .store() callbacks have finished unless this function * is called. Hence this function is useful in methods that implement self * deletion. */ struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, const struct attribute *attr) { struct kernfs_node *kn; kobject_get(kobj); kn = kernfs_find_and_get(kobj->sd, attr->name); if (kn) kernfs_break_active_protection(kn); else kobject_put(kobj); return kn; } EXPORT_SYMBOL_GPL(sysfs_break_active_protection); /** * sysfs_unbreak_active_protection - restore "active" protection * @kn: Pointer returned by sysfs_break_active_protection(). * * Undo the effects of sysfs_break_active_protection(). Since this function * calls kernfs_put() on the kernfs node that corresponds to the 'attr' * argument passed to sysfs_break_active_protection() that attribute may have * been removed between the sysfs_break_active_protection() and * sysfs_unbreak_active_protection() calls, it is not safe to access @kn after * this function has returned. */ void sysfs_unbreak_active_protection(struct kernfs_node *kn) { struct kobject *kobj = kn->parent->priv; kernfs_unbreak_active_protection(kn); kernfs_put(kn); kobject_put(kobj); } EXPORT_SYMBOL_GPL(sysfs_unbreak_active_protection); /** * sysfs_remove_file_ns - remove an object attribute with a custom ns tag * @kobj: object we're acting for * @attr: attribute descriptor * @ns: namespace tag of the file to remove * * Hash the attribute name and namespace tag and kill the victim. */ void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns) { struct kernfs_node *parent = kobj->sd; kernfs_remove_by_name_ns(parent, attr->name, ns); } EXPORT_SYMBOL_GPL(sysfs_remove_file_ns); /** * sysfs_remove_file_self - remove an object attribute from its own method * @kobj: object we're acting for * @attr: attribute descriptor * * See kernfs_remove_self() for details. */ bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr) { struct kernfs_node *parent = kobj->sd; struct kernfs_node *kn; bool ret; kn = kernfs_find_and_get(parent, attr->name); if (WARN_ON_ONCE(!kn)) return false; ret = kernfs_remove_self(kn); kernfs_put(kn); return ret; } EXPORT_SYMBOL_GPL(sysfs_remove_file_self); void sysfs_remove_files(struct kobject *kobj, const struct attribute * const *ptr) { int i; for (i = 0; ptr[i]; i++) sysfs_remove_file(kobj, ptr[i]); } EXPORT_SYMBOL_GPL(sysfs_remove_files); /** * sysfs_remove_file_from_group - remove an attribute file from a group. * @kobj: object we're acting for. * @attr: attribute descriptor. * @group: group name. */ void sysfs_remove_file_from_group(struct kobject *kobj, const struct attribute *attr, const char *group) { struct kernfs_node *parent; if (group) { parent = kernfs_find_and_get(kobj->sd, group); } else { parent = kobj->sd; kernfs_get(parent); } if (parent) { kernfs_remove_by_name(parent, attr->name); kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group); /** * sysfs_create_bin_file - create binary file for object. * @kobj: object. * @attr: attribute descriptor. */ int sysfs_create_bin_file(struct kobject *kobj, const struct bin_attribute *attr) { kuid_t uid; kgid_t gid; if (WARN_ON(!kobj || !kobj->sd || !attr)) return -EINVAL; kobject_get_ownership(kobj, &uid, &gid); return sysfs_add_bin_file_mode_ns(kobj->sd, attr, attr->attr.mode, uid, gid, NULL); } EXPORT_SYMBOL_GPL(sysfs_create_bin_file); /** * sysfs_remove_bin_file - remove binary file for object. * @kobj: object. * @attr: attribute descriptor. */ void sysfs_remove_bin_file(struct kobject *kobj, const struct bin_attribute *attr) { kernfs_remove_by_name(kobj->sd, attr->attr.name); } EXPORT_SYMBOL_GPL(sysfs_remove_bin_file); static int internal_change_owner(struct kernfs_node *kn, kuid_t kuid, kgid_t kgid) { struct iattr newattrs = { .ia_valid = ATTR_UID | ATTR_GID, .ia_uid = kuid, .ia_gid = kgid, }; return kernfs_setattr(kn, &newattrs); } /** * sysfs_link_change_owner - change owner of a sysfs file. * @kobj: object of the kernfs_node the symlink is located in. * @targ: object of the kernfs_node the symlink points to. * @name: name of the link. * @kuid: new owner's kuid * @kgid: new owner's kgid * * This function looks up the sysfs symlink entry @name under @kobj and changes * the ownership to @kuid/@kgid. The symlink is looked up in the namespace of * @targ. * * Returns 0 on success or error code on failure. */ int sysfs_link_change_owner(struct kobject *kobj, struct kobject *targ, const char *name, kuid_t kuid, kgid_t kgid) { struct kernfs_node *kn = NULL; int error; if (!name || !kobj->state_in_sysfs || !targ->state_in_sysfs) return -EINVAL; error = -ENOENT; kn = kernfs_find_and_get_ns(kobj->sd, name, targ->sd->ns); if (!kn) goto out; error = -EINVAL; if (kernfs_type(kn) != KERNFS_LINK) goto out; if (kn->symlink.target_kn->priv != targ) goto out; error = internal_change_owner(kn, kuid, kgid); out: kernfs_put(kn); return error; } /** * sysfs_file_change_owner - change owner of a sysfs file. * @kobj: object. * @name: name of the file to change. * @kuid: new owner's kuid * @kgid: new owner's kgid * * This function looks up the sysfs entry @name under @kobj and changes the * ownership to @kuid/@kgid. * * Returns 0 on success or error code on failure. */ int sysfs_file_change_owner(struct kobject *kobj, const char *name, kuid_t kuid, kgid_t kgid) { struct kernfs_node *kn; int error; if (!name) return -EINVAL; if (!kobj->state_in_sysfs) return -EINVAL; kn = kernfs_find_and_get(kobj->sd, name); if (!kn) return -ENOENT; error = internal_change_owner(kn, kuid, kgid); kernfs_put(kn); return error; } EXPORT_SYMBOL_GPL(sysfs_file_change_owner); /** * sysfs_change_owner - change owner of the given object. * @kobj: object. * @kuid: new owner's kuid * @kgid: new owner's kgid * * Change the owner of the default directory, files, groups, and attributes of * @kobj to @kuid/@kgid. Note that sysfs_change_owner mirrors how the sysfs * entries for a kobject are added by driver core. In summary, * sysfs_change_owner() takes care of the default directory entry for @kobj, * the default attributes associated with the ktype of @kobj and the default * attributes associated with the ktype of @kobj. * Additional properties not added by driver core have to be changed by the * driver or subsystem which created them. This is similar to how * driver/subsystem specific entries are removed. * * Returns 0 on success or error code on failure. */ int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid) { int error; const struct kobj_type *ktype; if (!kobj->state_in_sysfs) return -EINVAL; /* Change the owner of the kobject itself. */ error = internal_change_owner(kobj->sd, kuid, kgid); if (error) return error; ktype = get_ktype(kobj); if (ktype) { /* * Change owner of the default groups associated with the * ktype of @kobj. */ error = sysfs_groups_change_owner(kobj, ktype->default_groups, kuid, kgid); if (error) return error; } return 0; } EXPORT_SYMBOL_GPL(sysfs_change_owner); /** * sysfs_emit - scnprintf equivalent, aware of PAGE_SIZE buffer. * @buf: start of PAGE_SIZE buffer. * @fmt: format * @...: optional arguments to @format * * * Returns number of characters written to @buf. */ int sysfs_emit(char *buf, const char *fmt, ...) { va_list args; int len; if (WARN(!buf || offset_in_page(buf), "invalid sysfs_emit: buf:%p\n", buf)) return 0; va_start(args, fmt); len = vscnprintf(buf, PAGE_SIZE, fmt, args); va_end(args); return len; } EXPORT_SYMBOL_GPL(sysfs_emit); /** * sysfs_emit_at - scnprintf equivalent, aware of PAGE_SIZE buffer. * @buf: start of PAGE_SIZE buffer. * @at: offset in @buf to start write in bytes * @at must be >= 0 && < PAGE_SIZE * @fmt: format * @...: optional arguments to @fmt * * * Returns number of characters written starting at &@buf[@at]. */ int sysfs_emit_at(char *buf, int at, const char *fmt, ...) { va_list args; int len; if (WARN(!buf || offset_in_page(buf) || at < 0 || at >= PAGE_SIZE, "invalid sysfs_emit_at: buf:%p at:%d\n", buf, at)) return 0; va_start(args, fmt); len = vscnprintf(buf + at, PAGE_SIZE - at, fmt, args); va_end(args); return len; } EXPORT_SYMBOL_GPL(sysfs_emit_at); /** * sysfs_bin_attr_simple_read - read callback to simply copy from memory. * @file: attribute file which is being read. * @kobj: object to which the attribute belongs. * @attr: attribute descriptor. * @buf: destination buffer. * @off: offset in bytes from which to read. * @count: maximum number of bytes to read. * * Simple ->read() callback for bin_attributes backed by a buffer in memory. * The @private and @size members in struct bin_attribute must be set to the * buffer's location and size before the bin_attribute is created in sysfs. * * Bounds check for @off and @count is done in sysfs_kf_bin_read(). * Negative value check for @off is done in vfs_setpos() and default_llseek(). * * Returns number of bytes written to @buf. */ ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { memcpy(buf, attr->private + off, count); return count; } EXPORT_SYMBOL_GPL(sysfs_bin_attr_simple_read); |
| 78 78 210 213 1 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2008 Christoph Hellwig. * Portions Copyright (C) 2000-2008 Silicon Graphics, Inc. */ #include "xfs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_da_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_da_btree.h" #include "xfs_attr.h" #include "xfs_acl.h" #include "xfs_log.h" #include "xfs_xattr.h" #include "xfs_quota.h" #include <linux/posix_acl_xattr.h> /* * Get permission to use log-assisted atomic exchange of file extents. * Callers must not be running any transactions or hold any ILOCKs. */ static inline int xfs_attr_grab_log_assist( struct xfs_mount *mp) { int error = 0; /* xattr update log intent items are already enabled */ if (xfs_is_using_logged_xattrs(mp)) return 0; /* * Check if the filesystem featureset is new enough to set this log * incompat feature bit. Strictly speaking, the minimum requirement is * a V5 filesystem for the superblock field, but we'll require rmap * or reflink to avoid having to deal with really old kernels. */ if (!xfs_has_reflink(mp) && !xfs_has_rmapbt(mp)) return -EOPNOTSUPP; /* Enable log-assisted xattrs. */ error = xfs_add_incompat_log_feature(mp, XFS_SB_FEAT_INCOMPAT_LOG_XATTRS); if (error) return error; xfs_set_using_logged_xattrs(mp); xfs_warn_experimental(mp, XFS_EXPERIMENTAL_LARP); return 0; } static inline bool xfs_attr_want_log_assist( struct xfs_mount *mp) { #ifdef DEBUG /* Logged xattrs require a V5 super for log_incompat */ return xfs_has_crc(mp) && xfs_globals.larp; #else return false; #endif } /* * Set or remove an xattr, having grabbed the appropriate logging resources * prior to calling libxfs. Callers of this function are only required to * initialize the inode, attr_filter, name, namelen, value, and valuelen fields * of @args. */ int xfs_attr_change( struct xfs_da_args *args, enum xfs_attr_update op) { struct xfs_mount *mp = args->dp->i_mount; int error; if (xfs_is_shutdown(mp)) return -EIO; error = xfs_qm_dqattach(args->dp); if (error) return error; /* * We have no control over the attribute names that userspace passes us * to remove, so we have to allow the name lookup prior to attribute * removal to fail as well. */ args->op_flags = XFS_DA_OP_OKNOENT; if (xfs_attr_want_log_assist(mp)) { error = xfs_attr_grab_log_assist(mp); if (error) return error; args->op_flags |= XFS_DA_OP_LOGGED; } args->owner = args->dp->i_ino; args->geo = mp->m_attr_geo; args->whichfork = XFS_ATTR_FORK; xfs_attr_sethash(args); /* * Some xattrs must be resistant to allocation failure at ENOSPC, e.g. * creating an inode with ACLs or security attributes requires the * allocation of the xattr holding that information to succeed. Hence * we allow xattrs in the VFS TRUSTED, SYSTEM, POSIX_ACL and SECURITY * (LSM xattr) namespaces to dip into the reserve block pool to allow * manipulation of these xattrs when at ENOSPC. These VFS xattr * namespaces translate to the XFS_ATTR_ROOT and XFS_ATTR_SECURE on-disk * namespaces. * * For most of these cases, these special xattrs will fit in the inode * itself and so consume no extra space or only require temporary extra * space while an overwrite is being made. Hence the use of the reserved * pool is largely to avoid the worst case reservation from preventing * the xattr from being created at ENOSPC. */ return xfs_attr_set(args, op, args->attr_filter & (XFS_ATTR_ROOT | XFS_ATTR_SECURE)); } static int xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *value, size_t size) { struct xfs_da_args args = { .dp = XFS_I(inode), .attr_filter = handler->flags, .name = name, .namelen = strlen(name), .value = value, .valuelen = size, }; int error; if (xfs_ifork_zapped(XFS_I(inode), XFS_ATTR_FORK)) return -EIO; error = xfs_attr_get(&args); if (error) return error; return args.valuelen; } static inline enum xfs_attr_update xfs_xattr_flags_to_op( int flags, const void *value) { if (!value) return XFS_ATTRUPDATE_REMOVE; if (flags & XATTR_CREATE) return XFS_ATTRUPDATE_CREATE; if (flags & XATTR_REPLACE) return XFS_ATTRUPDATE_REPLACE; return XFS_ATTRUPDATE_UPSERT; } static int xfs_xattr_set(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct xfs_da_args args = { .dp = XFS_I(inode), .attr_filter = handler->flags, .name = name, .namelen = strlen(name), .value = (void *)value, .valuelen = size, }; int error; error = xfs_attr_change(&args, xfs_xattr_flags_to_op(flags, value)); if (!error && (handler->flags & XFS_ATTR_ROOT)) xfs_forget_acl(inode, name); return error; } static const struct xattr_handler xfs_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, .flags = 0, /* no flags implies user namespace */ .get = xfs_xattr_get, .set = xfs_xattr_set, }; static const struct xattr_handler xfs_xattr_trusted_handler = { .prefix = XATTR_TRUSTED_PREFIX, .flags = XFS_ATTR_ROOT, .get = xfs_xattr_get, .set = xfs_xattr_set, }; static const struct xattr_handler xfs_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .flags = XFS_ATTR_SECURE, .get = xfs_xattr_get, .set = xfs_xattr_set, }; const struct xattr_handler * const xfs_xattr_handlers[] = { &xfs_xattr_user_handler, &xfs_xattr_trusted_handler, &xfs_xattr_security_handler, NULL }; static void __xfs_xattr_put_listent( struct xfs_attr_list_context *context, char *prefix, int prefix_len, unsigned char *name, int namelen) { char *offset; int arraytop; if (context->count < 0 || context->seen_enough) return; if (!context->buffer) goto compute_size; arraytop = context->count + prefix_len + namelen + 1; if (arraytop > context->firstu) { context->count = -1; /* insufficient space */ context->seen_enough = 1; return; } offset = context->buffer + context->count; memcpy(offset, prefix, prefix_len); offset += prefix_len; strncpy(offset, (char *)name, namelen); /* real name */ offset += namelen; *offset = '\0'; compute_size: context->count += prefix_len + namelen + 1; return; } static void xfs_xattr_put_listent( struct xfs_attr_list_context *context, int flags, unsigned char *name, int namelen, void *value, int valuelen) { char *prefix; int prefix_len; ASSERT(context->count >= 0); /* Don't expose private xattr namespaces. */ if (flags & XFS_ATTR_PRIVATE_NSP_MASK) return; if (flags & XFS_ATTR_ROOT) { #ifdef CONFIG_XFS_POSIX_ACL if (namelen == SGI_ACL_FILE_SIZE && strncmp(name, SGI_ACL_FILE, SGI_ACL_FILE_SIZE) == 0) { __xfs_xattr_put_listent( context, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN, XATTR_POSIX_ACL_ACCESS, strlen(XATTR_POSIX_ACL_ACCESS)); } else if (namelen == SGI_ACL_DEFAULT_SIZE && strncmp(name, SGI_ACL_DEFAULT, SGI_ACL_DEFAULT_SIZE) == 0) { __xfs_xattr_put_listent( context, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN, XATTR_POSIX_ACL_DEFAULT, strlen(XATTR_POSIX_ACL_DEFAULT)); } #endif /* * Only show root namespace entries if we are actually allowed to * see them. */ if (!capable(CAP_SYS_ADMIN)) return; prefix = XATTR_TRUSTED_PREFIX; prefix_len = XATTR_TRUSTED_PREFIX_LEN; } else if (flags & XFS_ATTR_SECURE) { prefix = XATTR_SECURITY_PREFIX; prefix_len = XATTR_SECURITY_PREFIX_LEN; } else { prefix = XATTR_USER_PREFIX; prefix_len = XATTR_USER_PREFIX_LEN; } __xfs_xattr_put_listent(context, prefix, prefix_len, name, namelen); return; } ssize_t xfs_vn_listxattr( struct dentry *dentry, char *data, size_t size) { struct xfs_attr_list_context context; struct inode *inode = d_inode(dentry); int error; if (xfs_ifork_zapped(XFS_I(inode), XFS_ATTR_FORK)) return -EIO; /* * First read the regular on-disk attributes. */ memset(&context, 0, sizeof(context)); context.dp = XFS_I(inode); context.resynch = 1; context.buffer = size ? data : NULL; context.bufsize = size; context.firstu = context.bufsize; context.put_listent = xfs_xattr_put_listent; error = xfs_attr_list(&context); if (error) return error; if (context.count < 0) return -ERANGE; return context.count; } |
| 3 3 3 3 3 3 2 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Initialization routines * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/init.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/device.h> #include <linux/file.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/ctype.h> #include <linux/pm.h> #include <linux/debugfs.h> #include <linux/completion.h> #include <linux/interrupt.h> #include <sound/core.h> #include <sound/control.h> #include <sound/info.h> /* monitor files for graceful shutdown (hotplug) */ struct snd_monitor_file { struct file *file; const struct file_operations *disconnected_f_op; struct list_head shutdown_list; /* still need to shutdown */ struct list_head list; /* link of monitor files */ }; static DEFINE_SPINLOCK(shutdown_lock); static LIST_HEAD(shutdown_files); static const struct file_operations snd_shutdown_f_ops; /* locked for registering/using */ static DECLARE_BITMAP(snd_cards_lock, SNDRV_CARDS); static struct snd_card *snd_cards[SNDRV_CARDS]; static DEFINE_MUTEX(snd_card_mutex); static char *slots[SNDRV_CARDS]; module_param_array(slots, charp, NULL, 0444); MODULE_PARM_DESC(slots, "Module names assigned to the slots."); /* return non-zero if the given index is reserved for the given * module via slots option */ static int module_slot_match(struct module *module, int idx) { int match = 1; #ifdef CONFIG_MODULES const char *s1, *s2; if (!module || !*module->name || !slots[idx]) return 0; s1 = module->name; s2 = slots[idx]; if (*s2 == '!') { match = 0; /* negative match */ s2++; } /* compare module name strings * hyphens are handled as equivalent with underscore */ for (;;) { char c1 = *s1++; char c2 = *s2++; if (c1 == '-') c1 = '_'; if (c2 == '-') c2 = '_'; if (c1 != c2) return !match; if (!c1) break; } #endif /* CONFIG_MODULES */ return match; } #if IS_ENABLED(CONFIG_SND_MIXER_OSS) int (*snd_mixer_oss_notify_callback)(struct snd_card *card, int free_flag); EXPORT_SYMBOL(snd_mixer_oss_notify_callback); #endif static int check_empty_slot(struct module *module, int slot) { return !slots[slot] || !*slots[slot]; } /* return an empty slot number (>= 0) found in the given bitmask @mask. * @mask == -1 == 0xffffffff means: take any free slot up to 32 * when no slot is available, return the original @mask as is. */ static int get_slot_from_bitmask(int mask, int (*check)(struct module *, int), struct module *module) { int slot; for (slot = 0; slot < SNDRV_CARDS; slot++) { if (slot < 32 && !(mask & (1U << slot))) continue; if (!test_bit(slot, snd_cards_lock)) { if (check(module, slot)) return slot; /* found */ } } return mask; /* unchanged */ } /* the default release callback set in snd_device_alloc() */ static void default_release_alloc(struct device *dev) { kfree(dev); } /** * snd_device_alloc - Allocate and initialize struct device for sound devices * @dev_p: pointer to store the allocated device * @card: card to assign, optional * * For releasing the allocated device, call put_device(). */ int snd_device_alloc(struct device **dev_p, struct snd_card *card) { struct device *dev; *dev_p = NULL; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return -ENOMEM; device_initialize(dev); if (card) dev->parent = &card->card_dev; dev->class = &sound_class; dev->release = default_release_alloc; *dev_p = dev; return 0; } EXPORT_SYMBOL_GPL(snd_device_alloc); static int snd_card_init(struct snd_card *card, struct device *parent, int idx, const char *xid, struct module *module, size_t extra_size); static int snd_card_do_free(struct snd_card *card); static const struct attribute_group card_dev_attr_group; static void release_card_device(struct device *dev) { snd_card_do_free(dev_to_snd_card(dev)); } /** * snd_card_new - create and initialize a soundcard structure * @parent: the parent device object * @idx: card index (address) [0 ... (SNDRV_CARDS-1)] * @xid: card identification (ASCII string) * @module: top level module for locking * @extra_size: allocate this extra size after the main soundcard structure * @card_ret: the pointer to store the created card instance * * The function allocates snd_card instance via kzalloc with the given * space for the driver to use freely. The allocated struct is stored * in the given card_ret pointer. * * Return: Zero if successful or a negative error code. */ int snd_card_new(struct device *parent, int idx, const char *xid, struct module *module, int extra_size, struct snd_card **card_ret) { struct snd_card *card; int err; if (snd_BUG_ON(!card_ret)) return -EINVAL; *card_ret = NULL; if (extra_size < 0) extra_size = 0; card = kzalloc(sizeof(*card) + extra_size, GFP_KERNEL); if (!card) return -ENOMEM; err = snd_card_init(card, parent, idx, xid, module, extra_size); if (err < 0) return err; /* card is freed by error handler */ *card_ret = card; return 0; } EXPORT_SYMBOL(snd_card_new); static void __snd_card_release(struct device *dev, void *data) { snd_card_free(data); } /** * snd_devm_card_new - managed snd_card object creation * @parent: the parent device object * @idx: card index (address) [0 ... (SNDRV_CARDS-1)] * @xid: card identification (ASCII string) * @module: top level module for locking * @extra_size: allocate this extra size after the main soundcard structure * @card_ret: the pointer to store the created card instance * * This function works like snd_card_new() but manages the allocated resource * via devres, i.e. you don't need to free explicitly. * * When a snd_card object is created with this function and registered via * snd_card_register(), the very first devres action to call snd_card_free() * is added automatically. In that way, the resource disconnection is assured * at first, then released in the expected order. * * If an error happens at the probe before snd_card_register() is called and * there have been other devres resources, you'd need to free the card manually * via snd_card_free() call in the error; otherwise it may lead to UAF due to * devres call orders. You can use snd_card_free_on_error() helper for * handling it more easily. * * Return: zero if successful, or a negative error code */ int snd_devm_card_new(struct device *parent, int idx, const char *xid, struct module *module, size_t extra_size, struct snd_card **card_ret) { struct snd_card *card; int err; *card_ret = NULL; card = devres_alloc(__snd_card_release, sizeof(*card) + extra_size, GFP_KERNEL); if (!card) return -ENOMEM; card->managed = true; err = snd_card_init(card, parent, idx, xid, module, extra_size); if (err < 0) { devres_free(card); /* in managed mode, we need to free manually */ return err; } devres_add(parent, card); *card_ret = card; return 0; } EXPORT_SYMBOL_GPL(snd_devm_card_new); /** * snd_card_free_on_error - a small helper for handling devm probe errors * @dev: the managed device object * @ret: the return code from the probe callback * * This function handles the explicit snd_card_free() call at the error from * the probe callback. It's just a small helper for simplifying the error * handling with the managed devices. * * Return: zero if successful, or a negative error code */ int snd_card_free_on_error(struct device *dev, int ret) { struct snd_card *card; if (!ret) return 0; card = devres_find(dev, __snd_card_release, NULL, NULL); if (card) snd_card_free(card); return ret; } EXPORT_SYMBOL_GPL(snd_card_free_on_error); static int snd_card_init(struct snd_card *card, struct device *parent, int idx, const char *xid, struct module *module, size_t extra_size) { int err; if (extra_size > 0) card->private_data = (char *)card + sizeof(struct snd_card); if (xid) strscpy(card->id, xid, sizeof(card->id)); err = 0; scoped_guard(mutex, &snd_card_mutex) { if (idx < 0) /* first check the matching module-name slot */ idx = get_slot_from_bitmask(idx, module_slot_match, module); if (idx < 0) /* if not matched, assign an empty slot */ idx = get_slot_from_bitmask(idx, check_empty_slot, module); if (idx < 0) err = -ENODEV; else if (idx < snd_ecards_limit) { if (test_bit(idx, snd_cards_lock)) err = -EBUSY; /* invalid */ } else if (idx >= SNDRV_CARDS) err = -ENODEV; if (!err) { set_bit(idx, snd_cards_lock); /* lock it */ if (idx >= snd_ecards_limit) snd_ecards_limit = idx + 1; /* increase the limit */ } } if (err < 0) { dev_err(parent, "cannot find the slot for index %d (range 0-%i), error: %d\n", idx, snd_ecards_limit - 1, err); if (!card->managed) kfree(card); /* manually free here, as no destructor called */ return err; } card->dev = parent; card->number = idx; WARN_ON(IS_MODULE(CONFIG_SND) && !module); card->module = module; INIT_LIST_HEAD(&card->devices); init_rwsem(&card->controls_rwsem); rwlock_init(&card->controls_rwlock); INIT_LIST_HEAD(&card->controls); INIT_LIST_HEAD(&card->ctl_files); #ifdef CONFIG_SND_CTL_FAST_LOOKUP xa_init(&card->ctl_numids); xa_init(&card->ctl_hash); #endif spin_lock_init(&card->files_lock); INIT_LIST_HEAD(&card->files_list); mutex_init(&card->memory_mutex); #ifdef CONFIG_PM init_waitqueue_head(&card->power_sleep); init_waitqueue_head(&card->power_ref_sleep); atomic_set(&card->power_ref, 0); #endif init_waitqueue_head(&card->remove_sleep); card->sync_irq = -1; device_initialize(&card->card_dev); card->card_dev.parent = parent; card->card_dev.class = &sound_class; card->card_dev.release = release_card_device; card->card_dev.groups = card->dev_groups; card->dev_groups[0] = &card_dev_attr_group; err = kobject_set_name(&card->card_dev.kobj, "card%d", idx); if (err < 0) goto __error; snprintf(card->irq_descr, sizeof(card->irq_descr), "%s:%s", dev_driver_string(card->dev), dev_name(&card->card_dev)); /* the control interface cannot be accessed from the user space until */ /* snd_cards_bitmask and snd_cards are set with snd_card_register */ err = snd_ctl_create(card); if (err < 0) { dev_err(parent, "unable to register control minors\n"); goto __error; } err = snd_info_card_create(card); if (err < 0) { dev_err(parent, "unable to create card info\n"); goto __error_ctl; } #ifdef CONFIG_SND_DEBUG card->debugfs_root = debugfs_create_dir(dev_name(&card->card_dev), sound_debugfs_root); #endif return 0; __error_ctl: snd_device_free_all(card); __error: put_device(&card->card_dev); return err; } /** * snd_card_ref - Get the card object from the index * @idx: the card index * * Returns a card object corresponding to the given index or NULL if not found. * Release the object via snd_card_unref(). * * Return: a card object or NULL */ struct snd_card *snd_card_ref(int idx) { struct snd_card *card; guard(mutex)(&snd_card_mutex); card = snd_cards[idx]; if (card) get_device(&card->card_dev); return card; } EXPORT_SYMBOL_GPL(snd_card_ref); /* return non-zero if a card is already locked */ int snd_card_locked(int card) { guard(mutex)(&snd_card_mutex); return test_bit(card, snd_cards_lock); } static loff_t snd_disconnect_llseek(struct file *file, loff_t offset, int orig) { return -ENODEV; } static ssize_t snd_disconnect_read(struct file *file, char __user *buf, size_t count, loff_t *offset) { return -ENODEV; } static ssize_t snd_disconnect_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { return -ENODEV; } static int snd_disconnect_release(struct inode *inode, struct file *file) { struct snd_monitor_file *df = NULL, *_df; scoped_guard(spinlock, &shutdown_lock) { list_for_each_entry(_df, &shutdown_files, shutdown_list) { if (_df->file == file) { df = _df; list_del_init(&df->shutdown_list); break; } } } if (likely(df)) { if ((file->f_flags & FASYNC) && df->disconnected_f_op->fasync) df->disconnected_f_op->fasync(-1, file, 0); return df->disconnected_f_op->release(inode, file); } panic("%s(%p, %p) failed!", __func__, inode, file); } static __poll_t snd_disconnect_poll(struct file * file, poll_table * wait) { return EPOLLERR | EPOLLNVAL; } static long snd_disconnect_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return -ENODEV; } static int snd_disconnect_mmap(struct file *file, struct vm_area_struct *vma) { return -ENODEV; } static int snd_disconnect_fasync(int fd, struct file *file, int on) { return -ENODEV; } static const struct file_operations snd_shutdown_f_ops = { .owner = THIS_MODULE, .llseek = snd_disconnect_llseek, .read = snd_disconnect_read, .write = snd_disconnect_write, .release = snd_disconnect_release, .poll = snd_disconnect_poll, .unlocked_ioctl = snd_disconnect_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = snd_disconnect_ioctl, #endif .mmap = snd_disconnect_mmap, .fasync = snd_disconnect_fasync }; /** * snd_card_disconnect - disconnect all APIs from the file-operations (user space) * @card: soundcard structure * * Disconnects all APIs from the file-operations (user space). * * Return: Zero, otherwise a negative error code. * * Note: The current implementation replaces all active file->f_op with special * dummy file operations (they do nothing except release). */ void snd_card_disconnect(struct snd_card *card) { struct snd_monitor_file *mfile; if (!card) return; scoped_guard(spinlock, &card->files_lock) { if (card->shutdown) return; card->shutdown = 1; /* replace file->f_op with special dummy operations */ list_for_each_entry(mfile, &card->files_list, list) { /* it's critical part, use endless loop */ /* we have no room to fail */ mfile->disconnected_f_op = mfile->file->f_op; scoped_guard(spinlock, &shutdown_lock) list_add(&mfile->shutdown_list, &shutdown_files); mfile->file->f_op = &snd_shutdown_f_ops; fops_get(mfile->file->f_op); } } #ifdef CONFIG_PM /* wake up sleepers here before other callbacks for avoiding potential * deadlocks with other locks (e.g. in kctls); * then this notifies the shutdown and sleepers would abort immediately */ wake_up_all(&card->power_sleep); #endif /* notify all connected devices about disconnection */ /* at this point, they cannot respond to any calls except release() */ #if IS_ENABLED(CONFIG_SND_MIXER_OSS) if (snd_mixer_oss_notify_callback) snd_mixer_oss_notify_callback(card, SND_MIXER_OSS_NOTIFY_DISCONNECT); #endif /* notify all devices that we are disconnected */ snd_device_disconnect_all(card); if (card->sync_irq > 0) synchronize_irq(card->sync_irq); snd_info_card_disconnect(card); #ifdef CONFIG_SND_DEBUG debugfs_remove(card->debugfs_root); card->debugfs_root = NULL; #endif if (card->registered) { device_del(&card->card_dev); card->registered = false; } /* disable fops (user space) operations for ALSA API */ scoped_guard(mutex, &snd_card_mutex) { snd_cards[card->number] = NULL; clear_bit(card->number, snd_cards_lock); } snd_power_sync_ref(card); } EXPORT_SYMBOL(snd_card_disconnect); /** * snd_card_disconnect_sync - disconnect card and wait until files get closed * @card: card object to disconnect * * This calls snd_card_disconnect() for disconnecting all belonging components * and waits until all pending files get closed. * It assures that all accesses from user-space finished so that the driver * can release its resources gracefully. */ void snd_card_disconnect_sync(struct snd_card *card) { snd_card_disconnect(card); guard(spinlock_irq)(&card->files_lock); wait_event_lock_irq(card->remove_sleep, list_empty(&card->files_list), card->files_lock); } EXPORT_SYMBOL_GPL(snd_card_disconnect_sync); static int snd_card_do_free(struct snd_card *card) { card->releasing = true; #if IS_ENABLED(CONFIG_SND_MIXER_OSS) if (snd_mixer_oss_notify_callback) snd_mixer_oss_notify_callback(card, SND_MIXER_OSS_NOTIFY_FREE); #endif snd_device_free_all(card); if (card->private_free) card->private_free(card); if (snd_info_card_free(card) < 0) { dev_warn(card->dev, "unable to free card info\n"); /* Not fatal error */ } if (card->release_completion) complete(card->release_completion); if (!card->managed) kfree(card); return 0; } /** * snd_card_free_when_closed - Disconnect the card, free it later eventually * @card: soundcard structure * * Unlike snd_card_free(), this function doesn't try to release the card * resource immediately, but tries to disconnect at first. When the card * is still in use, the function returns before freeing the resources. * The card resources will be freed when the refcount gets to zero. * * Return: zero if successful, or a negative error code */ void snd_card_free_when_closed(struct snd_card *card) { if (!card) return; snd_card_disconnect(card); put_device(&card->card_dev); return; } EXPORT_SYMBOL(snd_card_free_when_closed); /** * snd_card_free - frees given soundcard structure * @card: soundcard structure * * This function releases the soundcard structure and the all assigned * devices automatically. That is, you don't have to release the devices * by yourself. * * This function waits until the all resources are properly released. * * Return: Zero. Frees all associated devices and frees the control * interface associated to given soundcard. */ void snd_card_free(struct snd_card *card) { DECLARE_COMPLETION_ONSTACK(released); /* The call of snd_card_free() is allowed from various code paths; * a manual call from the driver and the call via devres_free, and * we need to avoid double-free. Moreover, the release via devres * may call snd_card_free() twice due to its nature, we need to have * the check here at the beginning. */ if (card->releasing) return; card->release_completion = &released; snd_card_free_when_closed(card); /* wait, until all devices are ready for the free operation */ wait_for_completion(&released); } EXPORT_SYMBOL(snd_card_free); /* check, if the character is in the valid ASCII range */ static inline bool safe_ascii_char(char c) { return isascii(c) && isalnum(c); } /* retrieve the last word of shortname or longname */ static const char *retrieve_id_from_card_name(const char *name) { const char *spos = name; while (*name) { if (isspace(*name) && safe_ascii_char(name[1])) spos = name + 1; name++; } return spos; } /* return true if the given id string doesn't conflict any other card ids */ static bool card_id_ok(struct snd_card *card, const char *id) { int i; if (!snd_info_check_reserved_words(id)) return false; for (i = 0; i < snd_ecards_limit; i++) { if (snd_cards[i] && snd_cards[i] != card && !strcmp(snd_cards[i]->id, id)) return false; } return true; } /* copy to card->id only with valid letters from nid */ static void copy_valid_id_string(struct snd_card *card, const char *src, const char *nid) { char *id = card->id; while (*nid && !safe_ascii_char(*nid)) nid++; if (isdigit(*nid)) *id++ = isalpha(*src) ? *src : 'D'; while (*nid && (size_t)(id - card->id) < sizeof(card->id) - 1) { if (safe_ascii_char(*nid)) *id++ = *nid; nid++; } *id = 0; } /* Set card->id from the given string * If the string conflicts with other ids, add a suffix to make it unique. */ static void snd_card_set_id_no_lock(struct snd_card *card, const char *src, const char *nid) { int len, loops; bool is_default = false; char *id; copy_valid_id_string(card, src, nid); id = card->id; again: /* use "Default" for obviously invalid strings * ("card" conflicts with proc directories) */ if (!*id || !strncmp(id, "card", 4)) { strcpy(id, "Default"); is_default = true; } len = strlen(id); for (loops = 0; loops < SNDRV_CARDS; loops++) { char *spos; char sfxstr[5]; /* "_012" */ int sfxlen; if (card_id_ok(card, id)) return; /* OK */ /* Add _XYZ suffix */ sprintf(sfxstr, "_%X", loops + 1); sfxlen = strlen(sfxstr); if (len + sfxlen >= sizeof(card->id)) spos = id + sizeof(card->id) - sfxlen - 1; else spos = id + len; strcpy(spos, sfxstr); } /* fallback to the default id */ if (!is_default) { *id = 0; goto again; } /* last resort... */ dev_err(card->dev, "unable to set card id (%s)\n", id); if (card->proc_root->name) strscpy(card->id, card->proc_root->name, sizeof(card->id)); } /** * snd_card_set_id - set card identification name * @card: soundcard structure * @nid: new identification string * * This function sets the card identification and checks for name * collisions. */ void snd_card_set_id(struct snd_card *card, const char *nid) { /* check if user specified own card->id */ if (card->id[0] != '\0') return; guard(mutex)(&snd_card_mutex); snd_card_set_id_no_lock(card, nid, nid); } EXPORT_SYMBOL(snd_card_set_id); static ssize_t id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct snd_card *card = container_of(dev, struct snd_card, card_dev); return sysfs_emit(buf, "%s\n", card->id); } static ssize_t id_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct snd_card *card = container_of(dev, struct snd_card, card_dev); char buf1[sizeof(card->id)]; size_t copy = count > sizeof(card->id) - 1 ? sizeof(card->id) - 1 : count; size_t idx; int c; for (idx = 0; idx < copy; idx++) { c = buf[idx]; if (!safe_ascii_char(c) && c != '_' && c != '-') return -EINVAL; } memcpy(buf1, buf, copy); buf1[copy] = '\0'; guard(mutex)(&snd_card_mutex); if (!card_id_ok(NULL, buf1)) return -EEXIST; strcpy(card->id, buf1); snd_info_card_id_change(card); return count; } static DEVICE_ATTR_RW(id); static ssize_t number_show(struct device *dev, struct device_attribute *attr, char *buf) { struct snd_card *card = container_of(dev, struct snd_card, card_dev); return sysfs_emit(buf, "%i\n", card->number); } static DEVICE_ATTR_RO(number); static struct attribute *card_dev_attrs[] = { &dev_attr_id.attr, &dev_attr_number.attr, NULL }; static const struct attribute_group card_dev_attr_group = { .attrs = card_dev_attrs, }; /** * snd_card_add_dev_attr - Append a new sysfs attribute group to card * @card: card instance * @group: attribute group to append * * Return: zero if successful, or a negative error code */ int snd_card_add_dev_attr(struct snd_card *card, const struct attribute_group *group) { int i; /* loop for (arraysize-1) here to keep NULL at the last entry */ for (i = 0; i < ARRAY_SIZE(card->dev_groups) - 1; i++) { if (!card->dev_groups[i]) { card->dev_groups[i] = group; return 0; } } dev_err(card->dev, "Too many groups assigned\n"); return -ENOSPC; } EXPORT_SYMBOL_GPL(snd_card_add_dev_attr); static void trigger_card_free(void *data) { snd_card_free(data); } /** * snd_card_register - register the soundcard * @card: soundcard structure * * This function registers all the devices assigned to the soundcard. * Until calling this, the ALSA control interface is blocked from the * external accesses. Thus, you should call this function at the end * of the initialization of the card. * * Return: Zero otherwise a negative error code if the registration failed. */ int snd_card_register(struct snd_card *card) { int err; if (snd_BUG_ON(!card)) return -EINVAL; if (!card->registered) { err = device_add(&card->card_dev); if (err < 0) return err; card->registered = true; } else { if (card->managed) devm_remove_action(card->dev, trigger_card_free, card); } if (card->managed) { err = devm_add_action(card->dev, trigger_card_free, card); if (err < 0) return err; } err = snd_device_register_all(card); if (err < 0) return err; scoped_guard(mutex, &snd_card_mutex) { if (snd_cards[card->number]) { /* already registered */ return snd_info_card_register(card); /* register pending info */ } if (*card->id) { /* make a unique id name from the given string */ char tmpid[sizeof(card->id)]; memcpy(tmpid, card->id, sizeof(card->id)); snd_card_set_id_no_lock(card, tmpid, tmpid); } else { /* create an id from either shortname or longname */ const char *src; src = *card->shortname ? card->shortname : card->longname; snd_card_set_id_no_lock(card, src, retrieve_id_from_card_name(src)); } snd_cards[card->number] = card; } err = snd_info_card_register(card); if (err < 0) return err; #if IS_ENABLED(CONFIG_SND_MIXER_OSS) if (snd_mixer_oss_notify_callback) snd_mixer_oss_notify_callback(card, SND_MIXER_OSS_NOTIFY_REGISTER); #endif return 0; } EXPORT_SYMBOL(snd_card_register); #ifdef CONFIG_SND_PROC_FS static void snd_card_info_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { int idx, count; struct snd_card *card; for (idx = count = 0; idx < SNDRV_CARDS; idx++) { guard(mutex)(&snd_card_mutex); card = snd_cards[idx]; if (card) { count++; snd_iprintf(buffer, "%2i [%-15s]: %s - %s\n", idx, card->id, card->driver, card->shortname); snd_iprintf(buffer, " %s\n", card->longname); } } if (!count) snd_iprintf(buffer, "--- no soundcards ---\n"); } #ifdef CONFIG_SND_OSSEMUL void snd_card_info_read_oss(struct snd_info_buffer *buffer) { int idx, count; struct snd_card *card; for (idx = count = 0; idx < SNDRV_CARDS; idx++) { guard(mutex)(&snd_card_mutex); card = snd_cards[idx]; if (card) { count++; snd_iprintf(buffer, "%s\n", card->longname); } } if (!count) { snd_iprintf(buffer, "--- no soundcards ---\n"); } } #endif #ifdef CONFIG_MODULES static void snd_card_module_info_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { int idx; struct snd_card *card; for (idx = 0; idx < SNDRV_CARDS; idx++) { guard(mutex)(&snd_card_mutex); card = snd_cards[idx]; if (card) snd_iprintf(buffer, "%2i %s\n", idx, card->module->name); } } #endif int __init snd_card_info_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "cards", NULL); if (! entry) return -ENOMEM; entry->c.text.read = snd_card_info_read; if (snd_info_register(entry) < 0) return -ENOMEM; /* freed in error path */ #ifdef CONFIG_MODULES entry = snd_info_create_module_entry(THIS_MODULE, "modules", NULL); if (!entry) return -ENOMEM; entry->c.text.read = snd_card_module_info_read; if (snd_info_register(entry) < 0) return -ENOMEM; /* freed in error path */ #endif return 0; } #endif /* CONFIG_SND_PROC_FS */ /** * snd_component_add - add a component string * @card: soundcard structure * @component: the component id string * * This function adds the component id string to the supported list. * The component can be referred from the alsa-lib. * * Return: Zero otherwise a negative error code. */ int snd_component_add(struct snd_card *card, const char *component) { char *ptr; int len = strlen(component); ptr = strstr(card->components, component); if (ptr != NULL) { if (ptr[len] == '\0' || ptr[len] == ' ') /* already there */ return 1; } if (strlen(card->components) + 1 + len + 1 > sizeof(card->components)) { snd_BUG(); return -ENOMEM; } if (card->components[0] != '\0') strcat(card->components, " "); strcat(card->components, component); return 0; } EXPORT_SYMBOL(snd_component_add); /** * snd_card_file_add - add the file to the file list of the card * @card: soundcard structure * @file: file pointer * * This function adds the file to the file linked-list of the card. * This linked-list is used to keep tracking the connection state, * and to avoid the release of busy resources by hotplug. * * Return: zero or a negative error code. */ int snd_card_file_add(struct snd_card *card, struct file *file) { struct snd_monitor_file *mfile; mfile = kmalloc(sizeof(*mfile), GFP_KERNEL); if (mfile == NULL) return -ENOMEM; mfile->file = file; mfile->disconnected_f_op = NULL; INIT_LIST_HEAD(&mfile->shutdown_list); guard(spinlock)(&card->files_lock); if (card->shutdown) { kfree(mfile); return -ENODEV; } list_add(&mfile->list, &card->files_list); get_device(&card->card_dev); return 0; } EXPORT_SYMBOL(snd_card_file_add); /** * snd_card_file_remove - remove the file from the file list * @card: soundcard structure * @file: file pointer * * This function removes the file formerly added to the card via * snd_card_file_add() function. * If all files are removed and snd_card_free_when_closed() was * called beforehand, it processes the pending release of * resources. * * Return: Zero or a negative error code. */ int snd_card_file_remove(struct snd_card *card, struct file *file) { struct snd_monitor_file *mfile, *found = NULL; scoped_guard(spinlock, &card->files_lock) { list_for_each_entry(mfile, &card->files_list, list) { if (mfile->file == file) { list_del(&mfile->list); scoped_guard(spinlock, &shutdown_lock) list_del(&mfile->shutdown_list); if (mfile->disconnected_f_op) fops_put(mfile->disconnected_f_op); found = mfile; break; } } if (list_empty(&card->files_list)) wake_up_all(&card->remove_sleep); } if (!found) { dev_err(card->dev, "card file remove problem (%p)\n", file); return -ENOENT; } kfree(found); put_device(&card->card_dev); return 0; } EXPORT_SYMBOL(snd_card_file_remove); #ifdef CONFIG_PM /** * snd_power_ref_and_wait - wait until the card gets powered up * @card: soundcard structure * * Take the power_ref reference count of the given card, and * wait until the card gets powered up to SNDRV_CTL_POWER_D0 state. * The refcount is down again while sleeping until power-up, hence this * function can be used for syncing the floating control ops accesses, * typically around calling control ops. * * The caller needs to pull down the refcount via snd_power_unref() later * no matter whether the error is returned from this function or not. * * Return: Zero if successful, or a negative error code. */ int snd_power_ref_and_wait(struct snd_card *card) { snd_power_ref(card); if (snd_power_get_state(card) == SNDRV_CTL_POWER_D0) return 0; wait_event_cmd(card->power_sleep, card->shutdown || snd_power_get_state(card) == SNDRV_CTL_POWER_D0, snd_power_unref(card), snd_power_ref(card)); return card->shutdown ? -ENODEV : 0; } EXPORT_SYMBOL_GPL(snd_power_ref_and_wait); /** * snd_power_wait - wait until the card gets powered up (old form) * @card: soundcard structure * * Wait until the card gets powered up to SNDRV_CTL_POWER_D0 state. * * Return: Zero if successful, or a negative error code. */ int snd_power_wait(struct snd_card *card) { int ret; ret = snd_power_ref_and_wait(card); snd_power_unref(card); return ret; } EXPORT_SYMBOL(snd_power_wait); #endif /* CONFIG_PM */ |
| 158 40 124 29 1 28 96 95 12 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 | // SPDX-License-Identifier: GPL-2.0 /* * Out-of-line refcount functions. */ #include <linux/mutex.h> #include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/bug.h> #define REFCOUNT_WARN(str) WARN_ONCE(1, "refcount_t: " str ".\n") void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t) { refcount_set(r, REFCOUNT_SATURATED); switch (t) { case REFCOUNT_ADD_NOT_ZERO_OVF: REFCOUNT_WARN("saturated; leaking memory"); break; case REFCOUNT_ADD_OVF: REFCOUNT_WARN("saturated; leaking memory"); break; case REFCOUNT_ADD_UAF: REFCOUNT_WARN("addition on 0; use-after-free"); break; case REFCOUNT_SUB_UAF: REFCOUNT_WARN("underflow; use-after-free"); break; case REFCOUNT_DEC_LEAK: REFCOUNT_WARN("decrement hit 0; leaking memory"); break; default: REFCOUNT_WARN("unknown saturation event!?"); } } EXPORT_SYMBOL(refcount_warn_saturate); /** * refcount_dec_if_one - decrement a refcount if it is 1 * @r: the refcount * * No atomic_t counterpart, it attempts a 1 -> 0 transition and returns the * success thereof. * * Like all decrement operations, it provides release memory order and provides * a control dependency. * * It can be used like a try-delete operator; this explicit case is provided * and not cmpxchg in generic, because that would allow implementing unsafe * operations. * * Return: true if the resulting refcount is 0, false otherwise */ bool refcount_dec_if_one(refcount_t *r) { int val = 1; return atomic_try_cmpxchg_release(&r->refs, &val, 0); } EXPORT_SYMBOL(refcount_dec_if_one); /** * refcount_dec_not_one - decrement a refcount if it is not 1 * @r: the refcount * * No atomic_t counterpart, it decrements unless the value is 1, in which case * it will return false. * * Was often done like: atomic_add_unless(&var, -1, 1) * * Return: true if the decrement operation was successful, false otherwise */ bool refcount_dec_not_one(refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); do { if (unlikely(val == REFCOUNT_SATURATED)) return true; if (val == 1) return false; new = val - 1; if (new > val) { WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n"); return true; } } while (!atomic_try_cmpxchg_release(&r->refs, &val, new)); return true; } EXPORT_SYMBOL(refcount_dec_not_one); /** * refcount_dec_and_mutex_lock - return holding mutex if able to decrement * refcount to 0 * @r: the refcount * @lock: the mutex to be locked * * Similar to atomic_dec_and_mutex_lock(), it will WARN on underflow and fail * to decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides a control dependency such that free() must come after. * See the comment on top. * * Return: true and hold mutex if able to decrement refcount to 0, false * otherwise */ bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock) { if (refcount_dec_not_one(r)) return false; mutex_lock(lock); if (!refcount_dec_and_test(r)) { mutex_unlock(lock); return false; } return true; } EXPORT_SYMBOL(refcount_dec_and_mutex_lock); /** * refcount_dec_and_lock - return holding spinlock if able to decrement * refcount to 0 * @r: the refcount * @lock: the spinlock to be locked * * Similar to atomic_dec_and_lock(), it will WARN on underflow and fail to * decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides a control dependency such that free() must come after. * See the comment on top. * * Return: true and hold spinlock if able to decrement refcount to 0, false * otherwise */ bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock) { if (refcount_dec_not_one(r)) return false; spin_lock(lock); if (!refcount_dec_and_test(r)) { spin_unlock(lock); return false; } return true; } EXPORT_SYMBOL(refcount_dec_and_lock); /** * refcount_dec_and_lock_irqsave - return holding spinlock with disabled * interrupts if able to decrement refcount to 0 * @r: the refcount * @lock: the spinlock to be locked * @flags: saved IRQ-flags if the is acquired * * Same as refcount_dec_and_lock() above except that the spinlock is acquired * with disabled interrupts. * * Return: true and hold spinlock if able to decrement refcount to 0, false * otherwise */ bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, unsigned long *flags) { if (refcount_dec_not_one(r)) return false; spin_lock_irqsave(lock, *flags); if (!refcount_dec_and_test(r)) { spin_unlock_irqrestore(lock, *flags); return false; } return true; } EXPORT_SYMBOL(refcount_dec_and_lock_irqsave); |
| 25 24 24 25 24 13 25 24 25 23 24 13 12 12 12 23 23 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * lib/plist.c * * Descending-priority-sorted double-linked list * * (C) 2002-2003 Intel Corp * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>. * * 2001-2005 (c) MontaVista Software, Inc. * Daniel Walker <dwalker@mvista.com> * * (C) 2005 Thomas Gleixner <tglx@linutronix.de> * * Simplifications of the original code by * Oleg Nesterov <oleg@tv-sign.ru> * * Based on simple lists (include/linux/list.h). * * This file contains the add / del functions which are considered to * be too large to inline. See include/linux/plist.h for further * information. */ #include <linux/bug.h> #include <linux/plist.h> #ifdef CONFIG_DEBUG_PLIST static struct plist_head test_head; static void plist_check_prev_next(struct list_head *t, struct list_head *p, struct list_head *n) { WARN(n->prev != p || p->next != n, "top: %p, n: %p, p: %p\n" "prev: %p, n: %p, p: %p\n" "next: %p, n: %p, p: %p\n", t, t->next, t->prev, p, p->next, p->prev, n, n->next, n->prev); } static void plist_check_list(struct list_head *top) { struct list_head *prev = top, *next = top->next; plist_check_prev_next(top, prev, next); while (next != top) { WRITE_ONCE(prev, next); WRITE_ONCE(next, prev->next); plist_check_prev_next(top, prev, next); } } static void plist_check_head(struct plist_head *head) { if (!plist_head_empty(head)) plist_check_list(&plist_first(head)->prio_list); plist_check_list(&head->node_list); } #else # define plist_check_head(h) do { } while (0) #endif /** * plist_add - add @node to @head * * @node: &struct plist_node pointer * @head: &struct plist_head pointer */ void plist_add(struct plist_node *node, struct plist_head *head) { struct plist_node *first, *iter, *prev = NULL, *last, *reverse_iter; struct list_head *node_next = &head->node_list; plist_check_head(head); WARN_ON(!plist_node_empty(node)); WARN_ON(!list_empty(&node->prio_list)); if (plist_head_empty(head)) goto ins_node; first = iter = plist_first(head); last = reverse_iter = list_entry(first->prio_list.prev, struct plist_node, prio_list); do { if (node->prio < iter->prio) { node_next = &iter->node_list; break; } else if (node->prio >= reverse_iter->prio) { prev = reverse_iter; iter = list_entry(reverse_iter->prio_list.next, struct plist_node, prio_list); if (likely(reverse_iter != last)) node_next = &iter->node_list; break; } prev = iter; iter = list_entry(iter->prio_list.next, struct plist_node, prio_list); reverse_iter = list_entry(reverse_iter->prio_list.prev, struct plist_node, prio_list); } while (iter != first); if (!prev || prev->prio != node->prio) list_add_tail(&node->prio_list, &iter->prio_list); ins_node: list_add_tail(&node->node_list, node_next); plist_check_head(head); } /** * plist_del - Remove a @node from plist. * * @node: &struct plist_node pointer - entry to be removed * @head: &struct plist_head pointer - list head */ void plist_del(struct plist_node *node, struct plist_head *head) { plist_check_head(head); if (!list_empty(&node->prio_list)) { if (node->node_list.next != &head->node_list) { struct plist_node *next; next = list_entry(node->node_list.next, struct plist_node, node_list); /* add the next plist_node into prio_list */ if (list_empty(&next->prio_list)) list_add(&next->prio_list, &node->prio_list); } list_del_init(&node->prio_list); } list_del_init(&node->node_list); plist_check_head(head); } /** * plist_requeue - Requeue @node at end of same-prio entries. * * This is essentially an optimized plist_del() followed by * plist_add(). It moves an entry already in the plist to * after any other same-priority entries. * * @node: &struct plist_node pointer - entry to be moved * @head: &struct plist_head pointer - list head */ void plist_requeue(struct plist_node *node, struct plist_head *head) { struct plist_node *iter; struct list_head *node_next = &head->node_list; plist_check_head(head); BUG_ON(plist_head_empty(head)); BUG_ON(plist_node_empty(node)); if (node == plist_last(head)) return; iter = plist_next(node); if (node->prio != iter->prio) return; plist_del(node, head); plist_for_each_continue(iter, head) { if (node->prio != iter->prio) { node_next = &iter->node_list; break; } } list_add_tail(&node->node_list, node_next); plist_check_head(head); } #ifdef CONFIG_DEBUG_PLIST #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/module.h> #include <linux/init.h> static struct plist_node __initdata test_node[241]; static void __init plist_test_check(int nr_expect) { struct plist_node *first, *prio_pos, *node_pos; if (plist_head_empty(&test_head)) { BUG_ON(nr_expect != 0); return; } prio_pos = first = plist_first(&test_head); plist_for_each(node_pos, &test_head) { if (nr_expect-- < 0) break; if (node_pos == first) continue; if (node_pos->prio == prio_pos->prio) { BUG_ON(!list_empty(&node_pos->prio_list)); continue; } BUG_ON(prio_pos->prio > node_pos->prio); BUG_ON(prio_pos->prio_list.next != &node_pos->prio_list); prio_pos = node_pos; } BUG_ON(nr_expect != 0); BUG_ON(prio_pos->prio_list.next != &first->prio_list); } static void __init plist_test_requeue(struct plist_node *node) { plist_requeue(node, &test_head); if (node != plist_last(&test_head)) BUG_ON(node->prio == plist_next(node)->prio); } static int __init plist_test(void) { int nr_expect = 0, i, loop; unsigned int r = local_clock(); printk(KERN_DEBUG "start plist test\n"); plist_head_init(&test_head); for (i = 0; i < ARRAY_SIZE(test_node); i++) plist_node_init(test_node + i, 0); for (loop = 0; loop < 1000; loop++) { r = r * 193939 % 47629; i = r % ARRAY_SIZE(test_node); if (plist_node_empty(test_node + i)) { r = r * 193939 % 47629; test_node[i].prio = r % 99; plist_add(test_node + i, &test_head); nr_expect++; } else { plist_del(test_node + i, &test_head); nr_expect--; } plist_test_check(nr_expect); if (!plist_node_empty(test_node + i)) { plist_test_requeue(test_node + i); plist_test_check(nr_expect); } } for (i = 0; i < ARRAY_SIZE(test_node); i++) { if (plist_node_empty(test_node + i)) continue; plist_del(test_node + i, &test_head); nr_expect--; plist_test_check(nr_expect); } printk(KERN_DEBUG "end plist test\n"); /* Worst case test for plist_add() */ unsigned int test_data[241]; for (i = 0; i < ARRAY_SIZE(test_data); i++) test_data[i] = i; ktime_t start, end, time_elapsed = 0; plist_head_init(&test_head); for (i = 0; i < ARRAY_SIZE(test_node); i++) { plist_node_init(test_node + i, 0); test_node[i].prio = test_data[i]; } for (i = 0; i < ARRAY_SIZE(test_node); i++) { if (plist_node_empty(test_node + i)) { start = ktime_get(); plist_add(test_node + i, &test_head); end = ktime_get(); time_elapsed += (end - start); } } pr_debug("plist_add worst case test time elapsed %lld\n", time_elapsed); return 0; } module_init(plist_test); #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2023 Isovalent */ #ifndef __NET_TCX_H #define __NET_TCX_H #include <linux/bpf.h> #include <linux/bpf_mprog.h> #include <net/sch_generic.h> struct mini_Qdisc; struct tcx_entry { struct mini_Qdisc __rcu *miniq; struct bpf_mprog_bundle bundle; u32 miniq_active; struct rcu_head rcu; }; struct tcx_link { struct bpf_link link; struct net_device *dev; u32 location; }; static inline void tcx_set_ingress(struct sk_buff *skb, bool ingress) { #ifdef CONFIG_NET_XGRESS skb->tc_at_ingress = ingress; #endif } #ifdef CONFIG_NET_XGRESS static inline struct tcx_entry *tcx_entry(struct bpf_mprog_entry *entry) { struct bpf_mprog_bundle *bundle = entry->parent; return container_of(bundle, struct tcx_entry, bundle); } static inline struct tcx_link *tcx_link(const struct bpf_link *link) { return container_of(link, struct tcx_link, link); } void tcx_inc(void); void tcx_dec(void); static inline void tcx_entry_sync(void) { /* bpf_mprog_entry got a/b swapped, therefore ensure that * there are no inflight users on the old one anymore. */ synchronize_rcu(); } static inline void tcx_entry_update(struct net_device *dev, struct bpf_mprog_entry *entry, bool ingress) { ASSERT_RTNL(); if (ingress) rcu_assign_pointer(dev->tcx_ingress, entry); else rcu_assign_pointer(dev->tcx_egress, entry); } static inline struct bpf_mprog_entry * tcx_entry_fetch(struct net_device *dev, bool ingress) { ASSERT_RTNL(); if (ingress) return rcu_dereference_rtnl(dev->tcx_ingress); else return rcu_dereference_rtnl(dev->tcx_egress); } static inline struct bpf_mprog_entry *tcx_entry_create_noprof(void) { struct tcx_entry *tcx = kzalloc_noprof(sizeof(*tcx), GFP_KERNEL); if (tcx) { bpf_mprog_bundle_init(&tcx->bundle); return &tcx->bundle.a; } return NULL; } #define tcx_entry_create(...) alloc_hooks(tcx_entry_create_noprof(__VA_ARGS__)) static inline void tcx_entry_free(struct bpf_mprog_entry *entry) { kfree_rcu(tcx_entry(entry), rcu); } static inline struct bpf_mprog_entry * tcx_entry_fetch_or_create(struct net_device *dev, bool ingress, bool *created) { struct bpf_mprog_entry *entry = tcx_entry_fetch(dev, ingress); *created = false; if (!entry) { entry = tcx_entry_create(); if (!entry) return NULL; *created = true; } return entry; } static inline void tcx_skeys_inc(bool ingress) { tcx_inc(); if (ingress) net_inc_ingress_queue(); else net_inc_egress_queue(); } static inline void tcx_skeys_dec(bool ingress) { if (ingress) net_dec_ingress_queue(); else net_dec_egress_queue(); tcx_dec(); } static inline void tcx_miniq_inc(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active++; } static inline void tcx_miniq_dec(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active--; } static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); return bpf_mprog_total(entry) || tcx_entry(entry)->miniq_active; } static inline enum tcx_action_base tcx_action_code(struct sk_buff *skb, int code) { switch (code) { case TCX_PASS: skb->tc_index = qdisc_skb_cb(skb)->tc_classid; fallthrough; case TCX_DROP: case TCX_REDIRECT: return code; case TCX_NEXT: default: return TCX_NEXT; } } #endif /* CONFIG_NET_XGRESS */ #if defined(CONFIG_NET_XGRESS) && defined(CONFIG_BPF_SYSCALL) int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog); void tcx_uninstall(struct net_device *dev, bool ingress); int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); static inline void dev_tcx_uninstall(struct net_device *dev) { ASSERT_RTNL(); tcx_uninstall(dev, true); tcx_uninstall(dev, false); } #else static inline int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EINVAL; } static inline void dev_tcx_uninstall(struct net_device *dev) { } #endif /* CONFIG_NET_XGRESS && CONFIG_BPF_SYSCALL */ #endif /* __NET_TCX_H */ |
| 72 151 89 5 122 264 264 262 263 111 111 111 93 44 106 111 112 16 111 111 111 9 4 3 3 258 119 256 3 255 252 254 253 186 7 255 1 32 113 158 158 156 1 37 37 168 4 141 27 162 12 11 11 11 1 1 166 165 166 165 4 1 163 160 14 14 3 14 14 166 3 166 13 13 13 1 9 9 1 13 9 14 14 263 14 127 166 126 185 1 1 29 27 29 3 26 4 15 15 13 5 2 7 7 7 7 6 1 7 7 24 29 7 24 6 122 14 1 14 14 1 89 14 14 9 72 86 89 89 89 89 72 9 14 71 81 13 89 80 14 20 18 19 2 29 1 23 31 3 6 5 5 5 1 5 2 5 2 4 1 2 2 38 31 7 28 28 25 3 28 253 255 126 181 250 251 114 114 114 114 10 1 10 10 10 10 10 10 10 13 1 11 11 11 11 10 10 11 11 11 11 15 15 20 20 20 22 22 7 15 15 15 15 20 20 2 18 20 20 7 13 20 7 1 11 18 7 11 19 2 19 9 12 21 21 21 7 7 7 7 7 25 22 2 1 18 7 7 2 5 7 7 7 18 7 21 24 24 24 106 15 118 121 118 118 1 7 2 2 2 7 7 7 7 6 5 1 2 5 6 5 5 1 7 7 5 5 127 127 17 110 8 1 121 8 6 2 1 19 20 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * dir.c * * Creates, reads, walks and deletes directory-nodes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. * * Portions of this code from linux/fs/ext3/dir.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/dir.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/fs.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/highmem.h> #include <linux/quotaops.h> #include <linux/sort.h> #include <linux/iversion.h> #include <cluster/masklog.h> #include "ocfs2.h" #include "alloc.h" #include "blockcheck.h" #include "dir.h" #include "dlmglue.h" #include "extent_map.h" #include "file.h" #include "inode.h" #include "journal.h" #include "namei.h" #include "suballoc.h" #include "super.h" #include "sysfile.h" #include "uptodate.h" #include "ocfs2_trace.h" #include "buffer_head_io.h" #define NAMEI_RA_CHUNKS 2 #define NAMEI_RA_BLOCKS 4 #define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS) static int ocfs2_do_extend_dir(struct super_block *sb, handle_t *handle, struct inode *dir, struct buffer_head *parent_fe_bh, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac, struct buffer_head **new_bh); static int ocfs2_dir_indexed(struct inode *inode); /* * These are distinct checks because future versions of the file system will * want to have a trailing dirent structure independent of indexing. */ static int ocfs2_supports_dir_trailer(struct inode *dir) { struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) return 0; return ocfs2_meta_ecc(osb) || ocfs2_dir_indexed(dir); } /* * "new' here refers to the point at which we're creating a new * directory via "mkdir()", but also when we're expanding an inline * directory. In either case, we don't yet have the indexing bit set * on the directory, so the standard checks will fail in when metaecc * is turned off. Only directory-initialization type functions should * use this then. Everything else wants ocfs2_supports_dir_trailer() */ static int ocfs2_new_dir_wants_trailer(struct inode *dir) { struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); return ocfs2_meta_ecc(osb) || ocfs2_supports_indexed_dirs(osb); } static inline unsigned int ocfs2_dir_trailer_blk_off(struct super_block *sb) { return sb->s_blocksize - sizeof(struct ocfs2_dir_block_trailer); } #define ocfs2_trailer_from_bh(_bh, _sb) ((struct ocfs2_dir_block_trailer *) ((_bh)->b_data + ocfs2_dir_trailer_blk_off((_sb)))) /* XXX ocfs2_block_dqtrailer() is similar but not quite - can we make * them more consistent? */ struct ocfs2_dir_block_trailer *ocfs2_dir_trailer_from_size(int blocksize, void *data) { char *p = data; p += blocksize - sizeof(struct ocfs2_dir_block_trailer); return (struct ocfs2_dir_block_trailer *)p; } /* * XXX: This is executed once on every dirent. We should consider optimizing * it. */ static int ocfs2_skip_dir_trailer(struct inode *dir, struct ocfs2_dir_entry *de, unsigned long offset, unsigned long blklen) { unsigned long toff = blklen - sizeof(struct ocfs2_dir_block_trailer); if (!ocfs2_supports_dir_trailer(dir)) return 0; if (offset != toff) return 0; return 1; } static void ocfs2_init_dir_trailer(struct inode *inode, struct buffer_head *bh, u16 rec_len) { struct ocfs2_dir_block_trailer *trailer; trailer = ocfs2_trailer_from_bh(bh, inode->i_sb); strcpy(trailer->db_signature, OCFS2_DIR_TRAILER_SIGNATURE); trailer->db_compat_rec_len = cpu_to_le16(sizeof(struct ocfs2_dir_block_trailer)); trailer->db_parent_dinode = cpu_to_le64(OCFS2_I(inode)->ip_blkno); trailer->db_blkno = cpu_to_le64(bh->b_blocknr); trailer->db_free_rec_len = cpu_to_le16(rec_len); } /* * Link an unindexed block with a dir trailer structure into the index free * list. This function will modify dirdata_bh, but assumes you've already * passed it to the journal. */ static int ocfs2_dx_dir_link_trailer(struct inode *dir, handle_t *handle, struct buffer_head *dx_root_bh, struct buffer_head *dirdata_bh) { int ret; struct ocfs2_dx_root_block *dx_root; struct ocfs2_dir_block_trailer *trailer; ret = ocfs2_journal_access_dr(handle, INODE_CACHE(dir), dx_root_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } trailer = ocfs2_trailer_from_bh(dirdata_bh, dir->i_sb); dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; trailer->db_free_next = dx_root->dr_free_blk; dx_root->dr_free_blk = cpu_to_le64(dirdata_bh->b_blocknr); ocfs2_journal_dirty(handle, dx_root_bh); out: return ret; } static int ocfs2_free_list_at_root(struct ocfs2_dir_lookup_result *res) { return res->dl_prev_leaf_bh == NULL; } void ocfs2_free_dir_lookup_result(struct ocfs2_dir_lookup_result *res) { brelse(res->dl_dx_root_bh); brelse(res->dl_leaf_bh); brelse(res->dl_dx_leaf_bh); brelse(res->dl_prev_leaf_bh); } static int ocfs2_dir_indexed(struct inode *inode) { if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INDEXED_DIR_FL) return 1; return 0; } static inline int ocfs2_dx_root_inline(struct ocfs2_dx_root_block *dx_root) { return dx_root->dr_flags & OCFS2_DX_FLAG_INLINE; } /* * Hashing code adapted from ext3 */ #define DELTA 0x9E3779B9 static void TEA_transform(__u32 buf[4], __u32 const in[]) { __u32 sum = 0; __u32 b0 = buf[0], b1 = buf[1]; __u32 a = in[0], b = in[1], c = in[2], d = in[3]; int n = 16; do { sum += DELTA; b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b); b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d); } while (--n); buf[0] += b0; buf[1] += b1; } static void str2hashbuf(const char *msg, int len, __u32 *buf, int num) { __u32 pad, val; int i; pad = (__u32)len | ((__u32)len << 8); pad |= pad << 16; val = pad; if (len > num*4) len = num * 4; for (i = 0; i < len; i++) { if ((i % 4) == 0) val = pad; val = msg[i] + (val << 8); if ((i % 4) == 3) { *buf++ = val; val = pad; num--; } } if (--num >= 0) *buf++ = val; while (--num >= 0) *buf++ = pad; } static void ocfs2_dx_dir_name_hash(struct inode *dir, const char *name, int len, struct ocfs2_dx_hinfo *hinfo) { struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); const char *p; __u32 in[8], buf[4]; /* * XXX: Is this really necessary, if the index is never looked * at by readdir? Is a hash value of '0' a bad idea? */ if ((len == 1 && !strncmp(".", name, 1)) || (len == 2 && !strncmp("..", name, 2))) { buf[0] = buf[1] = 0; goto out; } #ifdef OCFS2_DEBUG_DX_DIRS /* * This makes it very easy to debug indexing problems. We * should never allow this to be selected without hand editing * this file though. */ buf[0] = buf[1] = len; goto out; #endif memcpy(buf, osb->osb_dx_seed, sizeof(buf)); p = name; while (len > 0) { str2hashbuf(p, len, in, 4); TEA_transform(buf, in); len -= 16; p += 16; } out: hinfo->major_hash = buf[0]; hinfo->minor_hash = buf[1]; } /* * bh passed here can be an inode block or a dir data block, depending * on the inode inline data flag. */ static int ocfs2_check_dir_entry(struct inode *dir, struct ocfs2_dir_entry *de, struct buffer_head *bh, char *buf, unsigned int size, unsigned long offset) { const char *error_msg = NULL; const int rlen = le16_to_cpu(de->rec_len); const unsigned long next_offset = ((char *) de - buf) + rlen; if (unlikely(rlen < OCFS2_DIR_REC_LEN(1))) error_msg = "rec_len is smaller than minimal"; else if (unlikely(rlen % 4 != 0)) error_msg = "rec_len % 4 != 0"; else if (unlikely(rlen < OCFS2_DIR_REC_LEN(de->name_len))) error_msg = "rec_len is too small for name_len"; else if (unlikely(next_offset > size)) error_msg = "directory entry overrun"; else if (unlikely(next_offset > size - OCFS2_DIR_REC_LEN(1)) && next_offset != size) error_msg = "directory entry too close to end"; if (unlikely(error_msg != NULL)) mlog(ML_ERROR, "bad entry in directory #%llu: %s - " "offset=%lu, inode=%llu, rec_len=%d, name_len=%d\n", (unsigned long long)OCFS2_I(dir)->ip_blkno, error_msg, offset, (unsigned long long)le64_to_cpu(de->inode), rlen, de->name_len); return error_msg == NULL ? 1 : 0; } static inline int ocfs2_match(int len, const char * const name, struct ocfs2_dir_entry *de) { if (len != de->name_len) return 0; if (!de->inode) return 0; return !memcmp(name, de->name, len); } /* * Returns 0 if not found, -1 on failure, and 1 on success */ static inline int ocfs2_search_dirblock(struct buffer_head *bh, struct inode *dir, const char *name, int namelen, unsigned long offset, char *first_de, unsigned int bytes, struct ocfs2_dir_entry **res_dir) { struct ocfs2_dir_entry *de; char *dlimit, *de_buf; int de_len; int ret = 0; de_buf = first_de; dlimit = de_buf + bytes; while (de_buf < dlimit - OCFS2_DIR_MEMBER_LEN) { /* this code is executed quadratically often */ /* do minimal checking `by hand' */ de = (struct ocfs2_dir_entry *) de_buf; if (de->name + namelen <= dlimit && ocfs2_match(namelen, name, de)) { /* found a match - just to be sure, do a full check */ if (!ocfs2_check_dir_entry(dir, de, bh, first_de, bytes, offset)) { ret = -1; goto bail; } *res_dir = de; ret = 1; goto bail; } /* prevent looping on a bad block */ de_len = le16_to_cpu(de->rec_len); if (de_len <= 0) { ret = -1; goto bail; } de_buf += de_len; offset += de_len; } bail: trace_ocfs2_search_dirblock(ret); return ret; } static struct buffer_head *ocfs2_find_entry_id(const char *name, int namelen, struct inode *dir, struct ocfs2_dir_entry **res_dir) { int ret, found; struct buffer_head *di_bh = NULL; struct ocfs2_dinode *di; struct ocfs2_inline_data *data; ret = ocfs2_read_inode_block(dir, &di_bh); if (ret) { mlog_errno(ret); goto out; } di = (struct ocfs2_dinode *)di_bh->b_data; data = &di->id2.i_data; found = ocfs2_search_dirblock(di_bh, dir, name, namelen, 0, data->id_data, i_size_read(dir), res_dir); if (found == 1) return di_bh; brelse(di_bh); out: return NULL; } static int ocfs2_validate_dir_block(struct super_block *sb, struct buffer_head *bh) { int rc; struct ocfs2_dir_block_trailer *trailer = ocfs2_trailer_from_bh(bh, sb); /* * We don't validate dirents here, that's handled * in-place when the code walks them. */ trace_ocfs2_validate_dir_block((unsigned long long)bh->b_blocknr); BUG_ON(!buffer_uptodate(bh)); /* * If the ecc fails, we return the error but otherwise * leave the filesystem running. We know any error is * local to this block. * * Note that we are safe to call this even if the directory * doesn't have a trailer. Filesystems without metaecc will do * nothing, and filesystems with it will have one. */ rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &trailer->db_check); if (rc) mlog(ML_ERROR, "Checksum failed for dinode %llu\n", (unsigned long long)bh->b_blocknr); return rc; } /* * Validate a directory trailer. * * We check the trailer here rather than in ocfs2_validate_dir_block() * because that function doesn't have the inode to test. */ static int ocfs2_check_dir_trailer(struct inode *dir, struct buffer_head *bh) { int rc = 0; struct ocfs2_dir_block_trailer *trailer; trailer = ocfs2_trailer_from_bh(bh, dir->i_sb); if (!OCFS2_IS_VALID_DIR_TRAILER(trailer)) { rc = ocfs2_error(dir->i_sb, "Invalid dirblock #%llu: signature = %.*s\n", (unsigned long long)bh->b_blocknr, 7, trailer->db_signature); goto out; } if (le64_to_cpu(trailer->db_blkno) != bh->b_blocknr) { rc = ocfs2_error(dir->i_sb, "Directory block #%llu has an invalid db_blkno of %llu\n", (unsigned long long)bh->b_blocknr, (unsigned long long)le64_to_cpu(trailer->db_blkno)); goto out; } if (le64_to_cpu(trailer->db_parent_dinode) != OCFS2_I(dir)->ip_blkno) { rc = ocfs2_error(dir->i_sb, "Directory block #%llu on dinode #%llu has an invalid parent_dinode of %llu\n", (unsigned long long)bh->b_blocknr, (unsigned long long)OCFS2_I(dir)->ip_blkno, (unsigned long long)le64_to_cpu(trailer->db_blkno)); goto out; } out: return rc; } /* * This function forces all errors to -EIO for consistency with its * predecessor, ocfs2_bread(). We haven't audited what returning the * real error codes would do to callers. We log the real codes with * mlog_errno() before we squash them. */ static int ocfs2_read_dir_block(struct inode *inode, u64 v_block, struct buffer_head **bh, int flags) { int rc = 0; struct buffer_head *tmp = *bh; rc = ocfs2_read_virt_blocks(inode, v_block, 1, &tmp, flags, ocfs2_validate_dir_block); if (rc) { mlog_errno(rc); goto out; } if (!(flags & OCFS2_BH_READAHEAD) && ocfs2_supports_dir_trailer(inode)) { rc = ocfs2_check_dir_trailer(inode, tmp); if (rc) { if (!*bh) brelse(tmp); mlog_errno(rc); goto out; } } /* If ocfs2_read_virt_blocks() got us a new bh, pass it up. */ if (!*bh) *bh = tmp; out: return rc ? -EIO : 0; } /* * Read the block at 'phys' which belongs to this directory * inode. This function does no virtual->physical block translation - * what's passed in is assumed to be a valid directory block. */ static int ocfs2_read_dir_block_direct(struct inode *dir, u64 phys, struct buffer_head **bh) { int ret; struct buffer_head *tmp = *bh; ret = ocfs2_read_block(INODE_CACHE(dir), phys, &tmp, ocfs2_validate_dir_block); if (ret) { mlog_errno(ret); goto out; } if (ocfs2_supports_dir_trailer(dir)) { ret = ocfs2_check_dir_trailer(dir, tmp); if (ret) { if (!*bh) brelse(tmp); mlog_errno(ret); goto out; } } if (!ret && !*bh) *bh = tmp; out: return ret; } static int ocfs2_validate_dx_root(struct super_block *sb, struct buffer_head *bh) { int ret; struct ocfs2_dx_root_block *dx_root; BUG_ON(!buffer_uptodate(bh)); dx_root = (struct ocfs2_dx_root_block *) bh->b_data; ret = ocfs2_validate_meta_ecc(sb, bh->b_data, &dx_root->dr_check); if (ret) { mlog(ML_ERROR, "Checksum failed for dir index root block %llu\n", (unsigned long long)bh->b_blocknr); return ret; } if (!OCFS2_IS_VALID_DX_ROOT(dx_root)) { ret = ocfs2_error(sb, "Dir Index Root # %llu has bad signature %.*s\n", (unsigned long long)le64_to_cpu(dx_root->dr_blkno), 7, dx_root->dr_signature); } return ret; } static int ocfs2_read_dx_root(struct inode *dir, struct ocfs2_dinode *di, struct buffer_head **dx_root_bh) { int ret; u64 blkno = le64_to_cpu(di->i_dx_root); struct buffer_head *tmp = *dx_root_bh; ret = ocfs2_read_block(INODE_CACHE(dir), blkno, &tmp, ocfs2_validate_dx_root); /* If ocfs2_read_block() got us a new bh, pass it up. */ if (!ret && !*dx_root_bh) *dx_root_bh = tmp; return ret; } static int ocfs2_validate_dx_leaf(struct super_block *sb, struct buffer_head *bh) { int ret; struct ocfs2_dx_leaf *dx_leaf = (struct ocfs2_dx_leaf *)bh->b_data; BUG_ON(!buffer_uptodate(bh)); ret = ocfs2_validate_meta_ecc(sb, bh->b_data, &dx_leaf->dl_check); if (ret) { mlog(ML_ERROR, "Checksum failed for dir index leaf block %llu\n", (unsigned long long)bh->b_blocknr); return ret; } if (!OCFS2_IS_VALID_DX_LEAF(dx_leaf)) { ret = ocfs2_error(sb, "Dir Index Leaf has bad signature %.*s\n", 7, dx_leaf->dl_signature); } return ret; } static int ocfs2_read_dx_leaf(struct inode *dir, u64 blkno, struct buffer_head **dx_leaf_bh) { int ret; struct buffer_head *tmp = *dx_leaf_bh; ret = ocfs2_read_block(INODE_CACHE(dir), blkno, &tmp, ocfs2_validate_dx_leaf); /* If ocfs2_read_block() got us a new bh, pass it up. */ if (!ret && !*dx_leaf_bh) *dx_leaf_bh = tmp; return ret; } /* * Read a series of dx_leaf blocks. This expects all buffer_head * pointers to be NULL on function entry. */ static int ocfs2_read_dx_leaves(struct inode *dir, u64 start, int num, struct buffer_head **dx_leaf_bhs) { int ret; ret = ocfs2_read_blocks(INODE_CACHE(dir), start, num, dx_leaf_bhs, 0, ocfs2_validate_dx_leaf); if (ret) mlog_errno(ret); return ret; } static struct buffer_head *ocfs2_find_entry_el(const char *name, int namelen, struct inode *dir, struct ocfs2_dir_entry **res_dir) { struct super_block *sb; struct buffer_head *bh_use[NAMEI_RA_SIZE]; struct buffer_head *bh, *ret = NULL; unsigned long start, block, b; int ra_max = 0; /* Number of bh's in the readahead buffer, bh_use[] */ int ra_ptr = 0; /* Current index into readahead buffer */ int num = 0; int nblocks, i; sb = dir->i_sb; nblocks = i_size_read(dir) >> sb->s_blocksize_bits; start = OCFS2_I(dir)->ip_dir_start_lookup; if (start >= nblocks) start = 0; block = start; restart: do { /* * We deal with the read-ahead logic here. */ if (ra_ptr >= ra_max) { /* Refill the readahead buffer */ ra_ptr = 0; b = block; for (ra_max = 0; ra_max < NAMEI_RA_SIZE; ra_max++) { /* * Terminate if we reach the end of the * directory and must wrap, or if our * search has finished at this block. */ if (b >= nblocks || (num && block == start)) { bh_use[ra_max] = NULL; break; } num++; bh = NULL; ocfs2_read_dir_block(dir, b++, &bh, OCFS2_BH_READAHEAD); bh_use[ra_max] = bh; } } if ((bh = bh_use[ra_ptr++]) == NULL) goto next; if (ocfs2_read_dir_block(dir, block, &bh, 0)) { /* read error, skip block & hope for the best. * ocfs2_read_dir_block() has released the bh. */ mlog(ML_ERROR, "reading directory %llu, " "offset %lu\n", (unsigned long long)OCFS2_I(dir)->ip_blkno, block); goto next; } i = ocfs2_search_dirblock(bh, dir, name, namelen, block << sb->s_blocksize_bits, bh->b_data, sb->s_blocksize, res_dir); if (i == 1) { OCFS2_I(dir)->ip_dir_start_lookup = block; ret = bh; goto cleanup_and_exit; } else { brelse(bh); if (i < 0) goto cleanup_and_exit; } next: if (++block >= nblocks) block = 0; } while (block != start); /* * If the directory has grown while we were searching, then * search the last part of the directory before giving up. */ block = nblocks; nblocks = i_size_read(dir) >> sb->s_blocksize_bits; if (block < nblocks) { start = 0; goto restart; } cleanup_and_exit: /* Clean up the read-ahead blocks */ for (; ra_ptr < ra_max; ra_ptr++) brelse(bh_use[ra_ptr]); trace_ocfs2_find_entry_el(ret); return ret; } static int ocfs2_dx_dir_lookup_rec(struct inode *inode, struct ocfs2_extent_list *el, u32 major_hash, u32 *ret_cpos, u64 *ret_phys_blkno, unsigned int *ret_clen) { int ret = 0, i, found; struct buffer_head *eb_bh = NULL; struct ocfs2_extent_block *eb; struct ocfs2_extent_rec *rec = NULL; if (el->l_tree_depth) { ret = ocfs2_find_leaf(INODE_CACHE(inode), el, major_hash, &eb_bh); if (ret) { mlog_errno(ret); goto out; } eb = (struct ocfs2_extent_block *) eb_bh->b_data; el = &eb->h_list; if (el->l_tree_depth) { ret = ocfs2_error(inode->i_sb, "Inode %lu has non zero tree depth in btree tree block %llu\n", inode->i_ino, (unsigned long long)eb_bh->b_blocknr); goto out; } } found = 0; for (i = le16_to_cpu(el->l_next_free_rec) - 1; i >= 0; i--) { rec = &el->l_recs[i]; if (le32_to_cpu(rec->e_cpos) <= major_hash) { found = 1; break; } } if (!found) { ret = ocfs2_error(inode->i_sb, "Inode %lu has bad extent record (%u, %u, 0) in btree\n", inode->i_ino, le32_to_cpu(rec->e_cpos), ocfs2_rec_clusters(el, rec)); goto out; } if (ret_phys_blkno) *ret_phys_blkno = le64_to_cpu(rec->e_blkno); if (ret_cpos) *ret_cpos = le32_to_cpu(rec->e_cpos); if (ret_clen) *ret_clen = le16_to_cpu(rec->e_leaf_clusters); out: brelse(eb_bh); return ret; } /* * Returns the block index, from the start of the cluster which this * hash belongs too. */ static inline unsigned int __ocfs2_dx_dir_hash_idx(struct ocfs2_super *osb, u32 minor_hash) { return minor_hash & osb->osb_dx_mask; } static inline unsigned int ocfs2_dx_dir_hash_idx(struct ocfs2_super *osb, struct ocfs2_dx_hinfo *hinfo) { return __ocfs2_dx_dir_hash_idx(osb, hinfo->minor_hash); } static int ocfs2_dx_dir_lookup(struct inode *inode, struct ocfs2_extent_list *el, struct ocfs2_dx_hinfo *hinfo, u32 *ret_cpos, u64 *ret_phys_blkno) { int ret = 0; unsigned int cend, clen; u32 cpos; u64 blkno; u32 name_hash = hinfo->major_hash; ret = ocfs2_dx_dir_lookup_rec(inode, el, name_hash, &cpos, &blkno, &clen); if (ret) { mlog_errno(ret); goto out; } cend = cpos + clen; if (name_hash >= cend) { /* We want the last cluster */ blkno += ocfs2_clusters_to_blocks(inode->i_sb, clen - 1); cpos += clen - 1; } else { blkno += ocfs2_clusters_to_blocks(inode->i_sb, name_hash - cpos); cpos = name_hash; } /* * We now have the cluster which should hold our entry. To * find the exact block from the start of the cluster to * search, we take the lower bits of the hash. */ blkno += ocfs2_dx_dir_hash_idx(OCFS2_SB(inode->i_sb), hinfo); if (ret_phys_blkno) *ret_phys_blkno = blkno; if (ret_cpos) *ret_cpos = cpos; out: return ret; } static int ocfs2_dx_dir_search(const char *name, int namelen, struct inode *dir, struct ocfs2_dx_root_block *dx_root, struct ocfs2_dir_lookup_result *res) { int ret, i, found; u64 phys; struct buffer_head *dx_leaf_bh = NULL; struct ocfs2_dx_leaf *dx_leaf; struct ocfs2_dx_entry *dx_entry = NULL; struct buffer_head *dir_ent_bh = NULL; struct ocfs2_dir_entry *dir_ent = NULL; struct ocfs2_dx_hinfo *hinfo = &res->dl_hinfo; struct ocfs2_extent_list *dr_el; struct ocfs2_dx_entry_list *entry_list; ocfs2_dx_dir_name_hash(dir, name, namelen, &res->dl_hinfo); if (ocfs2_dx_root_inline(dx_root)) { entry_list = &dx_root->dr_entries; goto search; } dr_el = &dx_root->dr_list; ret = ocfs2_dx_dir_lookup(dir, dr_el, hinfo, NULL, &phys); if (ret) { mlog_errno(ret); goto out; } trace_ocfs2_dx_dir_search((unsigned long long)OCFS2_I(dir)->ip_blkno, namelen, name, hinfo->major_hash, hinfo->minor_hash, (unsigned long long)phys); ret = ocfs2_read_dx_leaf(dir, phys, &dx_leaf_bh); if (ret) { mlog_errno(ret); goto out; } dx_leaf = (struct ocfs2_dx_leaf *) dx_leaf_bh->b_data; trace_ocfs2_dx_dir_search_leaf_info( le16_to_cpu(dx_leaf->dl_list.de_num_used), le16_to_cpu(dx_leaf->dl_list.de_count)); entry_list = &dx_leaf->dl_list; search: /* * Empty leaf is legal, so no need to check for that. */ found = 0; for (i = 0; i < le16_to_cpu(entry_list->de_num_used); i++) { dx_entry = &entry_list->de_entries[i]; if (hinfo->major_hash != le32_to_cpu(dx_entry->dx_major_hash) || hinfo->minor_hash != le32_to_cpu(dx_entry->dx_minor_hash)) continue; /* * Search unindexed leaf block now. We're not * guaranteed to find anything. */ ret = ocfs2_read_dir_block_direct(dir, le64_to_cpu(dx_entry->dx_dirent_blk), &dir_ent_bh); if (ret) { mlog_errno(ret); goto out; } /* * XXX: We should check the unindexed block here, * before using it. */ found = ocfs2_search_dirblock(dir_ent_bh, dir, name, namelen, 0, dir_ent_bh->b_data, dir->i_sb->s_blocksize, &dir_ent); if (found == 1) break; if (found == -1) { /* This means we found a bad directory entry. */ ret = -EIO; mlog_errno(ret); goto out; } brelse(dir_ent_bh); dir_ent_bh = NULL; } if (found <= 0) { ret = -ENOENT; goto out; } res->dl_leaf_bh = dir_ent_bh; res->dl_entry = dir_ent; res->dl_dx_leaf_bh = dx_leaf_bh; res->dl_dx_entry = dx_entry; ret = 0; out: if (ret) { brelse(dx_leaf_bh); brelse(dir_ent_bh); } return ret; } static int ocfs2_find_entry_dx(const char *name, int namelen, struct inode *dir, struct ocfs2_dir_lookup_result *lookup) { int ret; struct buffer_head *di_bh = NULL; struct ocfs2_dinode *di; struct buffer_head *dx_root_bh = NULL; struct ocfs2_dx_root_block *dx_root; ret = ocfs2_read_inode_block(dir, &di_bh); if (ret) { mlog_errno(ret); goto out; } di = (struct ocfs2_dinode *)di_bh->b_data; ret = ocfs2_read_dx_root(dir, di, &dx_root_bh); if (ret) { mlog_errno(ret); goto out; } dx_root = (struct ocfs2_dx_root_block *) dx_root_bh->b_data; ret = ocfs2_dx_dir_search(name, namelen, dir, dx_root, lookup); if (ret) { if (ret != -ENOENT) mlog_errno(ret); goto out; } lookup->dl_dx_root_bh = dx_root_bh; dx_root_bh = NULL; out: brelse(di_bh); brelse(dx_root_bh); return ret; } /* * Try to find an entry of the provided name within 'dir'. * * If nothing was found, -ENOENT is returned. Otherwise, zero is * returned and the struct 'res' will contain information useful to * other directory manipulation functions. * * Caller can NOT assume anything about the contents of the * buffer_heads - they are passed back only so that it can be passed * into any one of the manipulation functions (add entry, delete * entry, etc). As an example, bh in the extent directory case is a * data block, in the inline-data case it actually points to an inode, * in the indexed directory case, multiple buffers are involved. */ int ocfs2_find_entry(const char *name, int namelen, struct inode *dir, struct ocfs2_dir_lookup_result *lookup) { struct buffer_head *bh; struct ocfs2_dir_entry *res_dir = NULL; if (ocfs2_dir_indexed(dir)) return ocfs2_find_entry_dx(name, namelen, dir, lookup); /* * The unindexed dir code only uses part of the lookup * structure, so there's no reason to push it down further * than this. */ if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) bh = ocfs2_find_entry_id(name, namelen, dir, &res_dir); else bh = ocfs2_find_entry_el(name, namelen, dir, &res_dir); if (bh == NULL) return -ENOENT; lookup->dl_leaf_bh = bh; lookup->dl_entry = res_dir; return 0; } /* * Update inode number and type of a previously found directory entry. */ int ocfs2_update_entry(struct inode *dir, handle_t *handle, struct ocfs2_dir_lookup_result *res, struct inode *new_entry_inode) { int ret; ocfs2_journal_access_func access = ocfs2_journal_access_db; struct ocfs2_dir_entry *de = res->dl_entry; struct buffer_head *de_bh = res->dl_leaf_bh; /* * The same code works fine for both inline-data and extent * based directories, so no need to split this up. The only * difference is the journal_access function. */ if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) access = ocfs2_journal_access_di; ret = access(handle, INODE_CACHE(dir), de_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } de->inode = cpu_to_le64(OCFS2_I(new_entry_inode)->ip_blkno); ocfs2_set_de_type(de, new_entry_inode->i_mode); ocfs2_journal_dirty(handle, de_bh); out: return ret; } /* * __ocfs2_delete_entry deletes a directory entry by merging it with the * previous entry */ static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir, struct ocfs2_dir_entry *de_del, struct buffer_head *bh, char *first_de, unsigned int bytes) { struct ocfs2_dir_entry *de, *pde; int i, status = -ENOENT; ocfs2_journal_access_func access = ocfs2_journal_access_db; if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) access = ocfs2_journal_access_di; i = 0; pde = NULL; de = (struct ocfs2_dir_entry *) first_de; while (i < bytes) { if (!ocfs2_check_dir_entry(dir, de, bh, first_de, bytes, i)) { status = -EIO; mlog_errno(status); goto bail; } if (de == de_del) { status = access(handle, INODE_CACHE(dir), bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { status = -EIO; mlog_errno(status); goto bail; } if (pde) le16_add_cpu(&pde->rec_len, le16_to_cpu(de->rec_len)); de->inode = 0; inode_inc_iversion(dir); ocfs2_journal_dirty(handle, bh); goto bail; } i += le16_to_cpu(de->rec_len); pde = de; de = (struct ocfs2_dir_entry *)((char *)de + le16_to_cpu(de->rec_len)); } bail: return status; } static unsigned int ocfs2_figure_dirent_hole(struct ocfs2_dir_entry *de) { unsigned int hole; if (le64_to_cpu(de->inode) == 0) hole = le16_to_cpu(de->rec_len); else hole = le16_to_cpu(de->rec_len) - OCFS2_DIR_REC_LEN(de->name_len); return hole; } static int ocfs2_find_max_rec_len(struct super_block *sb, struct buffer_head *dirblock_bh) { int size, this_hole, largest_hole = 0; char *trailer, *de_buf, *limit, *start = dirblock_bh->b_data; struct ocfs2_dir_entry *de; trailer = (char *)ocfs2_trailer_from_bh(dirblock_bh, sb); size = ocfs2_dir_trailer_blk_off(sb); limit = start + size; de_buf = start; de = (struct ocfs2_dir_entry *)de_buf; do { if (de_buf != trailer) { this_hole = ocfs2_figure_dirent_hole(de); if (this_hole > largest_hole) largest_hole = this_hole; } de_buf += le16_to_cpu(de->rec_len); de = (struct ocfs2_dir_entry *)de_buf; } while (de_buf < limit); if (largest_hole >= OCFS2_DIR_MIN_REC_LEN) return largest_hole; return 0; } static void ocfs2_dx_list_remove_entry(struct ocfs2_dx_entry_list *entry_list, int index) { int num_used = le16_to_cpu(entry_list->de_num_used); if (num_used == 1 || index == (num_used - 1)) goto clear; memmove(&entry_list->de_entries[index], &entry_list->de_entries[index + 1], (num_used - index - 1)*sizeof(struct ocfs2_dx_entry)); clear: num_used--; memset(&entry_list->de_entries[num_used], 0, sizeof(struct ocfs2_dx_entry)); entry_list->de_num_used = cpu_to_le16(num_used); } static int ocfs2_delete_entry_dx(handle_t *handle, struct inode *dir, struct ocfs2_dir_lookup_result *lookup) { int ret, index, max_rec_len, add_to_free_list = 0; struct buffer_head *dx_root_bh = lookup->dl_dx_root_bh; struct buffer_head *leaf_bh = lookup->dl_leaf_bh; struct ocfs2_dx_leaf *dx_leaf; struct ocfs2_dx_entry *dx_entry = lookup->dl_dx_entry; struct ocfs2_dir_block_trailer *trailer; struct ocfs2_dx_root_block *dx_root; struct ocfs2_dx_entry_list *entry_list; /* * This function gets a bit messy because we might have to * modify the root block, regardless of whether the indexed * entries are stored inline. */ /* * *Only* set 'entry_list' here, based on where we're looking * for the indexed entries. Later, we might still want to * journal both blocks, based on free list state. */ dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; if (ocfs2_dx_root_inline(dx_root)) { entry_list = &dx_root->dr_entries; } else { dx_leaf = (struct ocfs2_dx_leaf *) lookup->dl_dx_leaf_bh->b_data; entry_list = &dx_leaf->dl_list; } /* Neither of these are a disk corruption - that should have * been caught by lookup, before we got here. */ BUG_ON(le16_to_cpu(entry_list->de_count) <= 0); BUG_ON(le16_to_cpu(entry_list->de_num_used) <= 0); index = (char *)dx_entry - (char *)entry_list->de_entries; index /= sizeof(*dx_entry); if (index >= le16_to_cpu(entry_list->de_num_used)) { mlog(ML_ERROR, "Dir %llu: Bad dx_entry ptr idx %d, (%p, %p)\n", (unsigned long long)OCFS2_I(dir)->ip_blkno, index, entry_list, dx_entry); return -EIO; } /* * We know that removal of this dirent will leave enough room * for a new one, so add this block to the free list if it * isn't already there. */ trailer = ocfs2_trailer_from_bh(leaf_bh, dir->i_sb); if (trailer->db_free_rec_len == 0) add_to_free_list = 1; /* * Add the block holding our index into the journal before * removing the unindexed entry. If we get an error return * from __ocfs2_delete_entry(), then it hasn't removed the * entry yet. Likewise, successful return means we *must* * remove the indexed entry. * * We're also careful to journal the root tree block here as * the entry count needs to be updated. Also, we might be * adding to the start of the free list. */ ret = ocfs2_journal_access_dr(handle, INODE_CACHE(dir), dx_root_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } if (!ocfs2_dx_root_inline(dx_root)) { ret = ocfs2_journal_access_dl(handle, INODE_CACHE(dir), lookup->dl_dx_leaf_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } } trace_ocfs2_delete_entry_dx((unsigned long long)OCFS2_I(dir)->ip_blkno, index); ret = __ocfs2_delete_entry(handle, dir, lookup->dl_entry, leaf_bh, leaf_bh->b_data, leaf_bh->b_size); if (ret) { mlog_errno(ret); goto out; } max_rec_len = ocfs2_find_max_rec_len(dir->i_sb, leaf_bh); trailer->db_free_rec_len = cpu_to_le16(max_rec_len); if (add_to_free_list) { trailer->db_free_next = dx_root->dr_free_blk; dx_root->dr_free_blk = cpu_to_le64(leaf_bh->b_blocknr); ocfs2_journal_dirty(handle, dx_root_bh); } /* leaf_bh was journal_accessed for us in __ocfs2_delete_entry */ ocfs2_journal_dirty(handle, leaf_bh); le32_add_cpu(&dx_root->dr_num_entries, -1); ocfs2_journal_dirty(handle, dx_root_bh); ocfs2_dx_list_remove_entry(entry_list, index); if (!ocfs2_dx_root_inline(dx_root)) ocfs2_journal_dirty(handle, lookup->dl_dx_leaf_bh); out: return ret; } static inline int ocfs2_delete_entry_id(handle_t *handle, struct inode *dir, struct ocfs2_dir_entry *de_del, struct buffer_head *bh) { int ret; struct buffer_head *di_bh = NULL; struct ocfs2_dinode *di; struct ocfs2_inline_data *data; ret = ocfs2_read_inode_block(dir, &di_bh); if (ret) { mlog_errno(ret); goto out; } di = (struct ocfs2_dinode *)di_bh->b_data; data = &di->id2.i_data; ret = __ocfs2_delete_entry(handle, dir, de_del, bh, data->id_data, i_size_read(dir)); brelse(di_bh); out: return ret; } static inline int ocfs2_delete_entry_el(handle_t *handle, struct inode *dir, struct ocfs2_dir_entry *de_del, struct buffer_head *bh) { return __ocfs2_delete_entry(handle, dir, de_del, bh, bh->b_data, bh->b_size); } /* * Delete a directory entry. Hide the details of directory * implementation from the caller. */ int ocfs2_delete_entry(handle_t *handle, struct inode *dir, struct ocfs2_dir_lookup_result *res) { if (ocfs2_dir_indexed(dir)) return ocfs2_delete_entry_dx(handle, dir, res); if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) return ocfs2_delete_entry_id(handle, dir, res->dl_entry, res->dl_leaf_bh); return ocfs2_delete_entry_el(handle, dir, res->dl_entry, res->dl_leaf_bh); } /* * Check whether 'de' has enough room to hold an entry of * 'new_rec_len' bytes. */ static inline int ocfs2_dirent_would_fit(struct ocfs2_dir_entry *de, unsigned int new_rec_len) { unsigned int de_really_used; /* Check whether this is an empty record with enough space */ if (le64_to_cpu(de->inode) == 0 && le16_to_cpu(de->rec_len) >= new_rec_len) return 1; /* * Record might have free space at the end which we can * use. */ de_really_used = OCFS2_DIR_REC_LEN(de->name_len); if (le16_to_cpu(de->rec_len) >= (de_really_used + new_rec_len)) return 1; return 0; } static void ocfs2_dx_dir_leaf_insert_tail(struct ocfs2_dx_leaf *dx_leaf, struct ocfs2_dx_entry *dx_new_entry) { int i; i = le16_to_cpu(dx_leaf->dl_list.de_num_used); dx_leaf->dl_list.de_entries[i] = *dx_new_entry; le16_add_cpu(&dx_leaf->dl_list.de_num_used, 1); } static void ocfs2_dx_entry_list_insert(struct ocfs2_dx_entry_list *entry_list, struct ocfs2_dx_hinfo *hinfo, u64 dirent_blk) { int i; struct ocfs2_dx_entry *dx_entry; i = le16_to_cpu(entry_list->de_num_used); dx_entry = &entry_list->de_entries[i]; memset(dx_entry, 0, sizeof(*dx_entry)); dx_entry->dx_major_hash = cpu_to_le32(hinfo->major_hash); dx_entry->dx_minor_hash = cpu_to_le32(hinfo->minor_hash); dx_entry->dx_dirent_blk = cpu_to_le64(dirent_blk); le16_add_cpu(&entry_list->de_num_used, 1); } static int __ocfs2_dx_dir_leaf_insert(struct inode *dir, handle_t *handle, struct ocfs2_dx_hinfo *hinfo, u64 dirent_blk, struct buffer_head *dx_leaf_bh) { int ret; struct ocfs2_dx_leaf *dx_leaf; ret = ocfs2_journal_access_dl(handle, INODE_CACHE(dir), dx_leaf_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } dx_leaf = (struct ocfs2_dx_leaf *)dx_leaf_bh->b_data; ocfs2_dx_entry_list_insert(&dx_leaf->dl_list, hinfo, dirent_blk); ocfs2_journal_dirty(handle, dx_leaf_bh); out: return ret; } static void ocfs2_dx_inline_root_insert(struct inode *dir, handle_t *handle, struct ocfs2_dx_hinfo *hinfo, u64 dirent_blk, struct ocfs2_dx_root_block *dx_root) { ocfs2_dx_entry_list_insert(&dx_root->dr_entries, hinfo, dirent_blk); } static int ocfs2_dx_dir_insert(struct inode *dir, handle_t *handle, struct ocfs2_dir_lookup_result *lookup) { int ret = 0; struct ocfs2_dx_root_block *dx_root; struct buffer_head *dx_root_bh = lookup->dl_dx_root_bh; ret = ocfs2_journal_access_dr(handle, INODE_CACHE(dir), dx_root_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } dx_root = (struct ocfs2_dx_root_block *)lookup->dl_dx_root_bh->b_data; if (ocfs2_dx_root_inline(dx_root)) { ocfs2_dx_inline_root_insert(dir, handle, &lookup->dl_hinfo, lookup->dl_leaf_bh->b_blocknr, dx_root); } else { ret = __ocfs2_dx_dir_leaf_insert(dir, handle, &lookup->dl_hinfo, lookup->dl_leaf_bh->b_blocknr, lookup->dl_dx_leaf_bh); if (ret) goto out; } le32_add_cpu(&dx_root->dr_num_entries, 1); ocfs2_journal_dirty(handle, dx_root_bh); out: return ret; } static void ocfs2_remove_block_from_free_list(struct inode *dir, handle_t *handle, struct ocfs2_dir_lookup_result *lookup) { struct ocfs2_dir_block_trailer *trailer, *prev; struct ocfs2_dx_root_block *dx_root; struct buffer_head *bh; trailer = ocfs2_trailer_from_bh(lookup->dl_leaf_bh, dir->i_sb); if (ocfs2_free_list_at_root(lookup)) { bh = lookup->dl_dx_root_bh; dx_root = (struct ocfs2_dx_root_block *)bh->b_data; dx_root->dr_free_blk = trailer->db_free_next; } else { bh = lookup->dl_prev_leaf_bh; prev = ocfs2_trailer_from_bh(bh, dir->i_sb); prev->db_free_next = trailer->db_free_next; } trailer->db_free_rec_len = cpu_to_le16(0); trailer->db_free_next = cpu_to_le64(0); ocfs2_journal_dirty(handle, bh); ocfs2_journal_dirty(handle, lookup->dl_leaf_bh); } /* * This expects that a journal write has been reserved on * lookup->dl_prev_leaf_bh or lookup->dl_dx_root_bh */ static void ocfs2_recalc_free_list(struct inode *dir, handle_t *handle, struct ocfs2_dir_lookup_result *lookup) { int max_rec_len; struct ocfs2_dir_block_trailer *trailer; /* Walk dl_leaf_bh to figure out what the new free rec_len is. */ max_rec_len = ocfs2_find_max_rec_len(dir->i_sb, lookup->dl_leaf_bh); if (max_rec_len) { /* * There's still room in this block, so no need to remove it * from the free list. In this case, we just want to update * the rec len accounting. */ trailer = ocfs2_trailer_from_bh(lookup->dl_leaf_bh, dir->i_sb); trailer->db_free_rec_len = cpu_to_le16(max_rec_len); ocfs2_journal_dirty(handle, lookup->dl_leaf_bh); } else { ocfs2_remove_block_from_free_list(dir, handle, lookup); } } /* we don't always have a dentry for what we want to add, so people * like orphan dir can call this instead. * * The lookup context must have been filled from * ocfs2_prepare_dir_for_insert. */ int __ocfs2_add_entry(handle_t *handle, struct inode *dir, const char *name, int namelen, struct inode *inode, u64 blkno, struct buffer_head *parent_fe_bh, struct ocfs2_dir_lookup_result *lookup) { unsigned long offset; unsigned short rec_len; struct ocfs2_dir_entry *de, *de1; struct ocfs2_dinode *di = (struct ocfs2_dinode *)parent_fe_bh->b_data; struct super_block *sb = dir->i_sb; int retval; unsigned int size = sb->s_blocksize; struct buffer_head *insert_bh = lookup->dl_leaf_bh; char *data_start = insert_bh->b_data; if (ocfs2_dir_indexed(dir)) { struct buffer_head *bh; /* * An indexed dir may require that we update the free space * list. Reserve a write to the previous node in the list so * that we don't fail later. * * XXX: This can be either a dx_root_block, or an unindexed * directory tree leaf block. */ if (ocfs2_free_list_at_root(lookup)) { bh = lookup->dl_dx_root_bh; retval = ocfs2_journal_access_dr(handle, INODE_CACHE(dir), bh, OCFS2_JOURNAL_ACCESS_WRITE); } else { bh = lookup->dl_prev_leaf_bh; retval = ocfs2_journal_access_db(handle, INODE_CACHE(dir), bh, OCFS2_JOURNAL_ACCESS_WRITE); } if (retval) { mlog_errno(retval); return retval; } } else if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { data_start = di->id2.i_data.id_data; size = i_size_read(dir); BUG_ON(insert_bh != parent_fe_bh); } rec_len = OCFS2_DIR_REC_LEN(namelen); offset = 0; de = (struct ocfs2_dir_entry *) data_start; while (1) { BUG_ON((char *)de >= (size + data_start)); /* These checks should've already been passed by the * prepare function, but I guess we can leave them * here anyway. */ if (!ocfs2_check_dir_entry(dir, de, insert_bh, data_start, size, offset)) { retval = -ENOENT; goto bail; } if (ocfs2_match(namelen, name, de)) { retval = -EEXIST; goto bail; } /* We're guaranteed that we should have space, so we * can't possibly have hit the trailer...right? */ mlog_bug_on_msg(ocfs2_skip_dir_trailer(dir, de, offset, size), "Hit dir trailer trying to insert %.*s " "(namelen %d) into directory %llu. " "offset is %lu, trailer offset is %d\n", namelen, name, namelen, (unsigned long long)parent_fe_bh->b_blocknr, offset, ocfs2_dir_trailer_blk_off(dir->i_sb)); if (ocfs2_dirent_would_fit(de, rec_len)) { inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); retval = ocfs2_mark_inode_dirty(handle, dir, parent_fe_bh); if (retval < 0) { mlog_errno(retval); goto bail; } if (insert_bh == parent_fe_bh) retval = ocfs2_journal_access_di(handle, INODE_CACHE(dir), insert_bh, OCFS2_JOURNAL_ACCESS_WRITE); else { retval = ocfs2_journal_access_db(handle, INODE_CACHE(dir), insert_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (!retval && ocfs2_dir_indexed(dir)) retval = ocfs2_dx_dir_insert(dir, handle, lookup); } if (retval) { mlog_errno(retval); goto bail; } /* By now the buffer is marked for journaling */ offset += le16_to_cpu(de->rec_len); if (le64_to_cpu(de->inode)) { de1 = (struct ocfs2_dir_entry *)((char *) de + OCFS2_DIR_REC_LEN(de->name_len)); de1->rec_len = cpu_to_le16(le16_to_cpu(de->rec_len) - OCFS2_DIR_REC_LEN(de->name_len)); de->rec_len = cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len)); de = de1; } de->file_type = FT_UNKNOWN; if (blkno) { de->inode = cpu_to_le64(blkno); ocfs2_set_de_type(de, inode->i_mode); } else de->inode = 0; de->name_len = namelen; memcpy(de->name, name, namelen); if (ocfs2_dir_indexed(dir)) ocfs2_recalc_free_list(dir, handle, lookup); inode_inc_iversion(dir); ocfs2_journal_dirty(handle, insert_bh); retval = 0; goto bail; } offset += le16_to_cpu(de->rec_len); de = (struct ocfs2_dir_entry *) ((char *) de + le16_to_cpu(de->rec_len)); } /* when you think about it, the assert above should prevent us * from ever getting here. */ retval = -ENOSPC; bail: if (retval) mlog_errno(retval); return retval; } static int ocfs2_dir_foreach_blk_id(struct inode *inode, u64 *f_version, struct dir_context *ctx) { int ret, i; unsigned long offset = ctx->pos; struct buffer_head *di_bh = NULL; struct ocfs2_dinode *di; struct ocfs2_inline_data *data; struct ocfs2_dir_entry *de; ret = ocfs2_read_inode_block(inode, &di_bh); if (ret) { mlog(ML_ERROR, "Unable to read inode block for dir %llu\n", (unsigned long long)OCFS2_I(inode)->ip_blkno); goto out; } di = (struct ocfs2_dinode *)di_bh->b_data; data = &di->id2.i_data; while (ctx->pos < i_size_read(inode)) { /* If the dir block has changed since the last call to * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the block * to make sure. */ if (!inode_eq_iversion(inode, *f_version)) { for (i = 0; i < i_size_read(inode) && i < offset; ) { de = (struct ocfs2_dir_entry *) (data->id_data + i); /* It's too expensive to do a full * dirent test each time round this * loop, but we do have to test at * least that it is non-zero. A * failure will be detected in the * dirent test below. */ if (le16_to_cpu(de->rec_len) < OCFS2_DIR_REC_LEN(1)) break; i += le16_to_cpu(de->rec_len); } ctx->pos = offset = i; *f_version = inode_query_iversion(inode); } de = (struct ocfs2_dir_entry *) (data->id_data + ctx->pos); if (!ocfs2_check_dir_entry(inode, de, di_bh, (char *)data->id_data, i_size_read(inode), ctx->pos)) { /* On error, skip the f_pos to the end. */ ctx->pos = i_size_read(inode); break; } offset += le16_to_cpu(de->rec_len); if (le64_to_cpu(de->inode)) { if (!dir_emit(ctx, de->name, de->name_len, le64_to_cpu(de->inode), fs_ftype_to_dtype(de->file_type))) goto out; } ctx->pos += le16_to_cpu(de->rec_len); } out: brelse(di_bh); return 0; } /* * NOTE: This function can be called against unindexed directories, * and indexed ones. */ static int ocfs2_dir_foreach_blk_el(struct inode *inode, u64 *f_version, struct dir_context *ctx, bool persist) { unsigned long offset, blk, last_ra_blk = 0; int i; struct buffer_head * bh, * tmp; struct ocfs2_dir_entry * de; struct super_block * sb = inode->i_sb; unsigned int ra_sectors = 16; int stored = 0; bh = NULL; offset = ctx->pos & (sb->s_blocksize - 1); while (ctx->pos < i_size_read(inode)) { blk = ctx->pos >> sb->s_blocksize_bits; if (ocfs2_read_dir_block(inode, blk, &bh, 0)) { /* Skip the corrupt dirblock and keep trying */ ctx->pos += sb->s_blocksize - offset; continue; } /* The idea here is to begin with 8k read-ahead and to stay * 4k ahead of our current position. * * TODO: Use the pagecache for this. We just need to * make sure it's cluster-safe... */ if (!last_ra_blk || (((last_ra_blk - blk) << 9) <= (ra_sectors / 2))) { for (i = ra_sectors >> (sb->s_blocksize_bits - 9); i > 0; i--) { tmp = NULL; if (!ocfs2_read_dir_block(inode, ++blk, &tmp, OCFS2_BH_READAHEAD)) brelse(tmp); } last_ra_blk = blk; ra_sectors = 8; } /* If the dir block has changed since the last call to * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the block * to make sure. */ if (!inode_eq_iversion(inode, *f_version)) { for (i = 0; i < sb->s_blocksize && i < offset; ) { de = (struct ocfs2_dir_entry *) (bh->b_data + i); /* It's too expensive to do a full * dirent test each time round this * loop, but we do have to test at * least that it is non-zero. A * failure will be detected in the * dirent test below. */ if (le16_to_cpu(de->rec_len) < OCFS2_DIR_REC_LEN(1)) break; i += le16_to_cpu(de->rec_len); } offset = i; ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1)) | offset; *f_version = inode_query_iversion(inode); } while (ctx->pos < i_size_read(inode) && offset < sb->s_blocksize) { de = (struct ocfs2_dir_entry *) (bh->b_data + offset); if (!ocfs2_check_dir_entry(inode, de, bh, bh->b_data, sb->s_blocksize, offset)) { /* On error, skip the f_pos to the next block. */ ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1; break; } if (le64_to_cpu(de->inode)) { if (!dir_emit(ctx, de->name, de->name_len, le64_to_cpu(de->inode), fs_ftype_to_dtype(de->file_type))) { brelse(bh); return 0; } stored++; } offset += le16_to_cpu(de->rec_len); ctx->pos += le16_to_cpu(de->rec_len); } offset = 0; brelse(bh); bh = NULL; if (!persist && stored) break; } return 0; } static int ocfs2_dir_foreach_blk(struct inode *inode, u64 *f_version, struct dir_context *ctx, bool persist) { if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) return ocfs2_dir_foreach_blk_id(inode, f_version, ctx); return ocfs2_dir_foreach_blk_el(inode, f_version, ctx, persist); } /* * This is intended to be called from inside other kernel functions, * so we fake some arguments. */ int ocfs2_dir_foreach(struct inode *inode, struct dir_context *ctx) { u64 version = inode_query_iversion(inode); ocfs2_dir_foreach_blk(inode, &version, ctx, true); return 0; } /* * ocfs2_readdir() * */ int ocfs2_readdir(struct file *file, struct dir_context *ctx) { int error = 0; struct inode *inode = file_inode(file); struct ocfs2_file_private *fp = file->private_data; int lock_level = 0; trace_ocfs2_readdir((unsigned long long)OCFS2_I(inode)->ip_blkno); error = ocfs2_inode_lock_atime(inode, file->f_path.mnt, &lock_level, 1); if (lock_level && error >= 0) { /* We release EX lock which used to update atime * and get PR lock again to reduce contention * on commonly accessed directories. */ ocfs2_inode_unlock(inode, 1); lock_level = 0; error = ocfs2_inode_lock(inode, NULL, 0); } if (error < 0) { if (error != -ENOENT) mlog_errno(error); /* we haven't got any yet, so propagate the error. */ goto bail_nolock; } error = ocfs2_dir_foreach_blk(inode, &fp->cookie, ctx, false); ocfs2_inode_unlock(inode, lock_level); if (error) mlog_errno(error); bail_nolock: return error; } /* * NOTE: this should always be called with parent dir i_rwsem taken. */ int ocfs2_find_files_on_disk(const char *name, int namelen, u64 *blkno, struct inode *inode, struct ocfs2_dir_lookup_result *lookup) { int status = -ENOENT; trace_ocfs2_find_files_on_disk(namelen, name, blkno, (unsigned long long)OCFS2_I(inode)->ip_blkno); status = ocfs2_find_entry(name, namelen, inode, lookup); if (status) goto leave; *blkno = le64_to_cpu(lookup->dl_entry->inode); status = 0; leave: return status; } /* * Convenience function for callers which just want the block number * mapped to a name and don't require the full dirent info, etc. */ int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name, int namelen, u64 *blkno) { int ret; struct ocfs2_dir_lookup_result lookup = { NULL, }; ret = ocfs2_find_files_on_disk(name, namelen, blkno, dir, &lookup); ocfs2_free_dir_lookup_result(&lookup); return ret; } /* Check for a name within a directory. * * Return 0 if the name does not exist * Return -EEXIST if the directory contains the name * * Callers should have i_rwsem + a cluster lock on dir */ int ocfs2_check_dir_for_entry(struct inode *dir, const char *name, int namelen) { int ret = 0; struct ocfs2_dir_lookup_result lookup = { NULL, }; trace_ocfs2_check_dir_for_entry( (unsigned long long)OCFS2_I(dir)->ip_blkno, namelen, name); if (ocfs2_find_entry(name, namelen, dir, &lookup) == 0) { ret = -EEXIST; mlog_errno(ret); } ocfs2_free_dir_lookup_result(&lookup); return ret; } struct ocfs2_empty_dir_priv { struct dir_context ctx; unsigned seen_dot; unsigned seen_dot_dot; unsigned seen_other; unsigned dx_dir; }; static bool ocfs2_empty_dir_filldir(struct dir_context *ctx, const char *name, int name_len, loff_t pos, u64 ino, unsigned type) { struct ocfs2_empty_dir_priv *p = container_of(ctx, struct ocfs2_empty_dir_priv, ctx); /* * Check the positions of "." and ".." records to be sure * they're in the correct place. * * Indexed directories don't need to proceed past the first * two entries, so we end the scan after seeing '..'. Despite * that, we allow the scan to proceed In the event that we * have a corrupted indexed directory (no dot or dot dot * entries). This allows us to double check for existing * entries which might not have been found in the index. */ if (name_len == 1 && !strncmp(".", name, 1) && pos == 0) { p->seen_dot = 1; return true; } if (name_len == 2 && !strncmp("..", name, 2) && pos == OCFS2_DIR_REC_LEN(1)) { p->seen_dot_dot = 1; if (p->dx_dir && p->seen_dot) return false; return true; } p->seen_other = 1; return false; } static int ocfs2_empty_dir_dx(struct inode *inode, struct ocfs2_empty_dir_priv *priv) { int ret; struct buffer_head *di_bh = NULL; struct buffer_head *dx_root_bh = NULL; struct ocfs2_dinode *di; struct ocfs2_dx_root_block *dx_root; priv->dx_dir = 1; ret = ocfs2_read_inode_block(inode, &di_bh); if (ret) { mlog_errno(ret); goto out; } di = (struct ocfs2_dinode *)di_bh->b_data; ret = ocfs2_read_dx_root(inode, di, &dx_root_bh); if (ret) { mlog_errno(ret); goto out; } dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; if (le32_to_cpu(dx_root->dr_num_entries) != 2) priv->seen_other = 1; out: brelse(di_bh); brelse(dx_root_bh); return ret; } /* * routine to check that the specified directory is empty (for rmdir) * * Returns 1 if dir is empty, zero otherwise. * * XXX: This is a performance problem for unindexed directories. */ int ocfs2_empty_dir(struct inode *inode) { int ret; struct ocfs2_empty_dir_priv priv = { .ctx.actor = ocfs2_empty_dir_filldir, }; if (ocfs2_dir_indexed(inode)) { ret = ocfs2_empty_dir_dx(inode, &priv); if (ret) mlog_errno(ret); /* * We still run ocfs2_dir_foreach to get the checks * for "." and "..". */ } ret = ocfs2_dir_foreach(inode, &priv.ctx); if (ret) mlog_errno(ret); if (!priv.seen_dot || !priv.seen_dot_dot) { mlog(ML_ERROR, "bad directory (dir #%llu) - no `.' or `..'\n", (unsigned long long)OCFS2_I(inode)->ip_blkno); /* * XXX: Is it really safe to allow an unlink to continue? */ return 1; } return !priv.seen_other; } /* * Fills "." and ".." dirents in a new directory block. Returns dirent for * "..", which might be used during creation of a directory with a trailing * header. It is otherwise safe to ignore the return code. */ static struct ocfs2_dir_entry *ocfs2_fill_initial_dirents(struct inode *inode, struct inode *parent, char *start, unsigned int size) { struct ocfs2_dir_entry *de = (struct ocfs2_dir_entry *)start; de->inode = cpu_to_le64(OCFS2_I(inode)->ip_blkno); de->name_len = 1; de->rec_len = cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len)); strcpy(de->name, "."); ocfs2_set_de_type(de, S_IFDIR); de = (struct ocfs2_dir_entry *) ((char *)de + le16_to_cpu(de->rec_len)); de->inode = cpu_to_le64(OCFS2_I(parent)->ip_blkno); de->rec_len = cpu_to_le16(size - OCFS2_DIR_REC_LEN(1)); de->name_len = 2; strcpy(de->name, ".."); ocfs2_set_de_type(de, S_IFDIR); return de; } /* * This works together with code in ocfs2_mknod_locked() which sets * the inline-data flag and initializes the inline-data section. */ static int ocfs2_fill_new_dir_id(struct ocfs2_super *osb, handle_t *handle, struct inode *parent, struct inode *inode, struct buffer_head *di_bh) { int ret; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_inline_data *data = &di->id2.i_data; unsigned int size = le16_to_cpu(data->id_count); ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } ocfs2_fill_initial_dirents(inode, parent, data->id_data, size); ocfs2_journal_dirty(handle, di_bh); i_size_write(inode, size); set_nlink(inode, 2); inode->i_blocks = ocfs2_inode_sector_count(inode); ret = ocfs2_mark_inode_dirty(handle, inode, di_bh); if (ret < 0) mlog_errno(ret); out: return ret; } static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb, handle_t *handle, struct inode *parent, struct inode *inode, struct buffer_head *fe_bh, struct ocfs2_alloc_context *data_ac, struct buffer_head **ret_new_bh) { int status; unsigned int size = osb->sb->s_blocksize; struct buffer_head *new_bh = NULL; struct ocfs2_dir_entry *de; if (ocfs2_new_dir_wants_trailer(inode)) size = ocfs2_dir_trailer_blk_off(parent->i_sb); status = ocfs2_do_extend_dir(osb->sb, handle, inode, fe_bh, data_ac, NULL, &new_bh); if (status < 0) { mlog_errno(status); goto bail; } ocfs2_set_new_buffer_uptodate(INODE_CACHE(inode), new_bh); status = ocfs2_journal_access_db(handle, INODE_CACHE(inode), new_bh, OCFS2_JOURNAL_ACCESS_CREATE); if (status < 0) { mlog_errno(status); goto bail; } memset(new_bh->b_data, 0, osb->sb->s_blocksize); de = ocfs2_fill_initial_dirents(inode, parent, new_bh->b_data, size); if (ocfs2_new_dir_wants_trailer(inode)) { int size = le16_to_cpu(de->rec_len); /* * Figure out the size of the hole left over after * insertion of '.' and '..'. The trailer wants this * information. */ size -= OCFS2_DIR_REC_LEN(2); size -= sizeof(struct ocfs2_dir_block_trailer); ocfs2_init_dir_trailer(inode, new_bh, size); } ocfs2_journal_dirty(handle, new_bh); i_size_write(inode, inode->i_sb->s_blocksize); set_nlink(inode, 2); inode->i_blocks = ocfs2_inode_sector_count(inode); status = ocfs2_mark_inode_dirty(handle, inode, fe_bh); if (status < 0) { mlog_errno(status); goto bail; } status = 0; if (ret_new_bh) { *ret_new_bh = new_bh; new_bh = NULL; } bail: brelse(new_bh); return status; } static int ocfs2_dx_dir_attach_index(struct ocfs2_super *osb, handle_t *handle, struct inode *dir, struct buffer_head *di_bh, struct buffer_head *dirdata_bh, struct ocfs2_alloc_context *meta_ac, int dx_inline, u32 num_entries, struct buffer_head **ret_dx_root_bh) { int ret; struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data; u16 dr_suballoc_bit; u64 suballoc_loc, dr_blkno; unsigned int num_bits; struct buffer_head *dx_root_bh = NULL; struct ocfs2_dx_root_block *dx_root; struct ocfs2_dir_block_trailer *trailer = ocfs2_trailer_from_bh(dirdata_bh, dir->i_sb); ret = ocfs2_claim_metadata(handle, meta_ac, 1, &suballoc_loc, &dr_suballoc_bit, &num_bits, &dr_blkno); if (ret) { mlog_errno(ret); goto out; } trace_ocfs2_dx_dir_attach_index( (unsigned long long)OCFS2_I(dir)->ip_blkno, (unsigned long long)dr_blkno); dx_root_bh = sb_getblk(osb->sb, dr_blkno); if (dx_root_bh == NULL) { ret = -ENOMEM; goto out; } ocfs2_set_new_buffer_uptodate(INODE_CACHE(dir), dx_root_bh); ret = ocfs2_journal_access_dr(handle, INODE_CACHE(dir), dx_root_bh, OCFS2_JOURNAL_ACCESS_CREATE); if (ret < 0) { mlog_errno(ret); goto out; } dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; memset(dx_root, 0, osb->sb->s_blocksize); strcpy(dx_root->dr_signature, OCFS2_DX_ROOT_SIGNATURE); dx_root->dr_suballoc_slot = cpu_to_le16(meta_ac->ac_alloc_slot); dx_root->dr_suballoc_loc = cpu_to_le64(suballoc_loc); dx_root->dr_suballoc_bit = cpu_to_le16(dr_suballoc_bit); dx_root->dr_fs_generation = cpu_to_le32(osb->fs_generation); dx_root->dr_blkno = cpu_to_le64(dr_blkno); dx_root->dr_dir_blkno = cpu_to_le64(OCFS2_I(dir)->ip_blkno); dx_root->dr_num_entries = cpu_to_le32(num_entries); if (le16_to_cpu(trailer->db_free_rec_len)) dx_root->dr_free_blk = cpu_to_le64(dirdata_bh->b_blocknr); else dx_root->dr_free_blk = cpu_to_le64(0); if (dx_inline) { dx_root->dr_flags |= OCFS2_DX_FLAG_INLINE; dx_root->dr_entries.de_count = cpu_to_le16(ocfs2_dx_entries_per_root(osb->sb)); } else { dx_root->dr_list.l_count = cpu_to_le16(ocfs2_extent_recs_per_dx_root(osb->sb)); } ocfs2_journal_dirty(handle, dx_root_bh); ret = ocfs2_journal_access_di(handle, INODE_CACHE(dir), di_bh, OCFS2_JOURNAL_ACCESS_CREATE); if (ret) { mlog_errno(ret); goto out; } di->i_dx_root = cpu_to_le64(dr_blkno); spin_lock(&OCFS2_I(dir)->ip_lock); OCFS2_I(dir)->ip_dyn_features |= OCFS2_INDEXED_DIR_FL; di->i_dyn_features = cpu_to_le16(OCFS2_I(dir)->ip_dyn_features); spin_unlock(&OCFS2_I(dir)->ip_lock); ocfs2_journal_dirty(handle, di_bh); *ret_dx_root_bh = dx_root_bh; dx_root_bh = NULL; out: brelse(dx_root_bh); return ret; } static int ocfs2_dx_dir_format_cluster(struct ocfs2_super *osb, handle_t *handle, struct inode *dir, struct buffer_head **dx_leaves, int num_dx_leaves, u64 start_blk) { int ret, i; struct ocfs2_dx_leaf *dx_leaf; struct buffer_head *bh; for (i = 0; i < num_dx_leaves; i++) { bh = sb_getblk(osb->sb, start_blk + i); if (bh == NULL) { ret = -ENOMEM; goto out; } dx_leaves[i] = bh; ocfs2_set_new_buffer_uptodate(INODE_CACHE(dir), bh); ret = ocfs2_journal_access_dl(handle, INODE_CACHE(dir), bh, OCFS2_JOURNAL_ACCESS_CREATE); if (ret < 0) { mlog_errno(ret); goto out; } dx_leaf = (struct ocfs2_dx_leaf *) bh->b_data; memset(dx_leaf, 0, osb->sb->s_blocksize); strcpy(dx_leaf->dl_signature, OCFS2_DX_LEAF_SIGNATURE); dx_leaf->dl_fs_generation = cpu_to_le32(osb->fs_generation); dx_leaf->dl_blkno = cpu_to_le64(bh->b_blocknr); dx_leaf->dl_list.de_count = cpu_to_le16(ocfs2_dx_entries_per_leaf(osb->sb)); trace_ocfs2_dx_dir_format_cluster( (unsigned long long)OCFS2_I(dir)->ip_blkno, (unsigned long long)bh->b_blocknr, le16_to_cpu(dx_leaf->dl_list.de_count)); ocfs2_journal_dirty(handle, bh); } ret = 0; out: return ret; } /* * Allocates and formats a new cluster for use in an indexed dir * leaf. This version will not do the extent insert, so that it can be * used by operations which need careful ordering. */ static int __ocfs2_dx_dir_new_cluster(struct inode *dir, u32 cpos, handle_t *handle, struct ocfs2_alloc_context *data_ac, struct buffer_head **dx_leaves, int num_dx_leaves, u64 *ret_phys_blkno) { int ret; u32 phys, num; u64 phys_blkno; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); /* * XXX: For create, this should claim cluster for the index * *before* the unindexed insert so that we have a better * chance of contiguousness as the directory grows in number * of entries. */ ret = __ocfs2_claim_clusters(handle, data_ac, 1, 1, &phys, &num); if (ret) { mlog_errno(ret); goto out; } /* * Format the new cluster first. That way, we're inserting * valid data. */ phys_blkno = ocfs2_clusters_to_blocks(osb->sb, phys); ret = ocfs2_dx_dir_format_cluster(osb, handle, dir, dx_leaves, num_dx_leaves, phys_blkno); if (ret) { mlog_errno(ret); goto out; } *ret_phys_blkno = phys_blkno; out: return ret; } static int ocfs2_dx_dir_new_cluster(struct inode *dir, struct ocfs2_extent_tree *et, u32 cpos, handle_t *handle, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac, struct buffer_head **dx_leaves, int num_dx_leaves) { int ret; u64 phys_blkno; ret = __ocfs2_dx_dir_new_cluster(dir, cpos, handle, data_ac, dx_leaves, num_dx_leaves, &phys_blkno); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_insert_extent(handle, et, cpos, phys_blkno, 1, 0, meta_ac); if (ret) mlog_errno(ret); out: return ret; } static struct buffer_head **ocfs2_dx_dir_kmalloc_leaves(struct super_block *sb, int *ret_num_leaves) { int num_dx_leaves = ocfs2_clusters_to_blocks(sb, 1); struct buffer_head **dx_leaves; dx_leaves = kcalloc(num_dx_leaves, sizeof(struct buffer_head *), GFP_NOFS); if (dx_leaves && ret_num_leaves) *ret_num_leaves = num_dx_leaves; return dx_leaves; } static int ocfs2_fill_new_dir_dx(struct ocfs2_super *osb, handle_t *handle, struct inode *parent, struct inode *inode, struct buffer_head *di_bh, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac) { int ret; struct buffer_head *leaf_bh = NULL; struct buffer_head *dx_root_bh = NULL; struct ocfs2_dx_hinfo hinfo; struct ocfs2_dx_root_block *dx_root; struct ocfs2_dx_entry_list *entry_list; /* * Our strategy is to create the directory as though it were * unindexed, then add the index block. This works with very * little complication since the state of a new directory is a * very well known quantity. * * Essentially, we have two dirents ("." and ".."), in the 1st * block which need indexing. These are easily inserted into * the index block. */ ret = ocfs2_fill_new_dir_el(osb, handle, parent, inode, di_bh, data_ac, &leaf_bh); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_dx_dir_attach_index(osb, handle, inode, di_bh, leaf_bh, meta_ac, 1, 2, &dx_root_bh); if (ret) { mlog_errno(ret); goto out; } dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; entry_list = &dx_root->dr_entries; /* Buffer has been journaled for us by ocfs2_dx_dir_attach_index */ ocfs2_dx_dir_name_hash(inode, ".", 1, &hinfo); ocfs2_dx_entry_list_insert(entry_list, &hinfo, leaf_bh->b_blocknr); ocfs2_dx_dir_name_hash(inode, "..", 2, &hinfo); ocfs2_dx_entry_list_insert(entry_list, &hinfo, leaf_bh->b_blocknr); out: brelse(dx_root_bh); brelse(leaf_bh); return ret; } int ocfs2_fill_new_dir(struct ocfs2_super *osb, handle_t *handle, struct inode *parent, struct inode *inode, struct buffer_head *fe_bh, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac) { BUG_ON(!ocfs2_supports_inline_data(osb) && data_ac == NULL); if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) return ocfs2_fill_new_dir_id(osb, handle, parent, inode, fe_bh); if (ocfs2_supports_indexed_dirs(osb)) return ocfs2_fill_new_dir_dx(osb, handle, parent, inode, fe_bh, data_ac, meta_ac); return ocfs2_fill_new_dir_el(osb, handle, parent, inode, fe_bh, data_ac, NULL); } static int ocfs2_dx_dir_index_block(struct inode *dir, handle_t *handle, struct buffer_head **dx_leaves, int num_dx_leaves, u32 *num_dx_entries, struct buffer_head *dirent_bh) { int ret = 0, namelen, i; char *de_buf, *limit; struct ocfs2_dir_entry *de; struct buffer_head *dx_leaf_bh; struct ocfs2_dx_hinfo hinfo; u64 dirent_blk = dirent_bh->b_blocknr; de_buf = dirent_bh->b_data; limit = de_buf + dir->i_sb->s_blocksize; while (de_buf < limit) { de = (struct ocfs2_dir_entry *)de_buf; namelen = de->name_len; if (!namelen || !de->inode) goto inc; ocfs2_dx_dir_name_hash(dir, de->name, namelen, &hinfo); i = ocfs2_dx_dir_hash_idx(OCFS2_SB(dir->i_sb), &hinfo); dx_leaf_bh = dx_leaves[i]; ret = __ocfs2_dx_dir_leaf_insert(dir, handle, &hinfo, dirent_blk, dx_leaf_bh); if (ret) { mlog_errno(ret); goto out; } *num_dx_entries = *num_dx_entries + 1; inc: de_buf += le16_to_cpu(de->rec_len); } out: return ret; } /* * XXX: This expects dx_root_bh to already be part of the transaction. */ static void ocfs2_dx_dir_index_root_block(struct inode *dir, struct buffer_head *dx_root_bh, struct buffer_head *dirent_bh) { char *de_buf, *limit; struct ocfs2_dx_root_block *dx_root; struct ocfs2_dir_entry *de; struct ocfs2_dx_hinfo hinfo; u64 dirent_blk = dirent_bh->b_blocknr; dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; de_buf = dirent_bh->b_data; limit = de_buf + dir->i_sb->s_blocksize; while (de_buf < limit) { de = (struct ocfs2_dir_entry *)de_buf; if (!de->name_len || !de->inode) goto inc; ocfs2_dx_dir_name_hash(dir, de->name, de->name_len, &hinfo); trace_ocfs2_dx_dir_index_root_block( (unsigned long long)dir->i_ino, hinfo.major_hash, hinfo.minor_hash, de->name_len, de->name, le16_to_cpu(dx_root->dr_entries.de_num_used)); ocfs2_dx_entry_list_insert(&dx_root->dr_entries, &hinfo, dirent_blk); le32_add_cpu(&dx_root->dr_num_entries, 1); inc: de_buf += le16_to_cpu(de->rec_len); } } /* * Count the number of inline directory entries in di_bh and compare * them against the number of entries we can hold in an inline dx root * block. */ static int ocfs2_new_dx_should_be_inline(struct inode *dir, struct buffer_head *di_bh) { int dirent_count = 0; char *de_buf, *limit; struct ocfs2_dir_entry *de; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; de_buf = di->id2.i_data.id_data; limit = de_buf + i_size_read(dir); while (de_buf < limit) { de = (struct ocfs2_dir_entry *)de_buf; if (de->name_len && de->inode) dirent_count++; de_buf += le16_to_cpu(de->rec_len); } /* We are careful to leave room for one extra record. */ return dirent_count < ocfs2_dx_entries_per_root(dir->i_sb); } /* * Expand rec_len of the rightmost dirent in a directory block so that it * contains the end of our valid space for dirents. We do this during * expansion from an inline directory to one with extents. The first dir block * in that case is taken from the inline data portion of the inode block. * * This will also return the largest amount of contiguous space for a dirent * in the block. That value is *not* necessarily the last dirent, even after * expansion. The directory indexing code wants this value for free space * accounting. We do this here since we're already walking the entire dir * block. * * We add the dir trailer if this filesystem wants it. */ static unsigned int ocfs2_expand_last_dirent(char *start, unsigned int old_size, struct inode *dir) { struct super_block *sb = dir->i_sb; struct ocfs2_dir_entry *de; struct ocfs2_dir_entry *prev_de; char *de_buf, *limit; unsigned int new_size = sb->s_blocksize; unsigned int bytes, this_hole; unsigned int largest_hole = 0; if (ocfs2_new_dir_wants_trailer(dir)) new_size = ocfs2_dir_trailer_blk_off(sb); bytes = new_size - old_size; limit = start + old_size; de_buf = start; de = (struct ocfs2_dir_entry *)de_buf; do { this_hole = ocfs2_figure_dirent_hole(de); if (this_hole > largest_hole) largest_hole = this_hole; prev_de = de; de_buf += le16_to_cpu(de->rec_len); de = (struct ocfs2_dir_entry *)de_buf; } while (de_buf < limit); le16_add_cpu(&prev_de->rec_len, bytes); /* We need to double check this after modification of the final * dirent. */ this_hole = ocfs2_figure_dirent_hole(prev_de); if (this_hole > largest_hole) largest_hole = this_hole; if (largest_hole >= OCFS2_DIR_MIN_REC_LEN) return largest_hole; return 0; } /* * We allocate enough clusters to fulfill "blocks_wanted", but set * i_size to exactly one block. Ocfs2_extend_dir() will handle the * rest automatically for us. * * *first_block_bh is a pointer to the 1st data block allocated to the * directory. */ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, unsigned int blocks_wanted, struct ocfs2_dir_lookup_result *lookup, struct buffer_head **first_block_bh) { u32 alloc, dx_alloc, bit_off, len, num_dx_entries = 0; struct super_block *sb = dir->i_sb; int ret, i, num_dx_leaves = 0, dx_inline = 0, credits = ocfs2_inline_to_extents_credits(sb); u64 dx_insert_blkno, blkno, bytes = blocks_wanted << sb->s_blocksize_bits; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct ocfs2_inode_info *oi = OCFS2_I(dir); struct ocfs2_alloc_context *data_ac = NULL; struct ocfs2_alloc_context *meta_ac = NULL; struct buffer_head *dirdata_bh = NULL; struct buffer_head *dx_root_bh = NULL; struct buffer_head **dx_leaves = NULL; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; handle_t *handle; struct ocfs2_extent_tree et; struct ocfs2_extent_tree dx_et; int did_quota = 0, bytes_allocated = 0; ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(dir), di_bh); alloc = ocfs2_clusters_for_bytes(sb, bytes); dx_alloc = 0; down_write(&oi->ip_alloc_sem); if (ocfs2_supports_indexed_dirs(osb)) { credits += ocfs2_add_dir_index_credits(sb); dx_inline = ocfs2_new_dx_should_be_inline(dir, di_bh); if (!dx_inline) { /* Add one more cluster for an index leaf */ dx_alloc++; dx_leaves = ocfs2_dx_dir_kmalloc_leaves(sb, &num_dx_leaves); if (!dx_leaves) { ret = -ENOMEM; mlog_errno(ret); goto out; } } /* This gets us the dx_root */ ret = ocfs2_reserve_new_metadata_blocks(osb, 1, &meta_ac); if (ret) { mlog_errno(ret); goto out; } } /* * We should never need more than 2 clusters for the unindexed * tree - maximum dirent size is far less than one block. In * fact, the only time we'd need more than one cluster is if * blocksize == clustersize and the dirent won't fit in the * extra space that the expansion to a single block gives. As * of today, that only happens on 4k/4k file systems. */ BUG_ON(alloc > 2); ret = ocfs2_reserve_clusters(osb, alloc + dx_alloc, &data_ac); if (ret) { mlog_errno(ret); goto out; } /* * Prepare for worst case allocation scenario of two separate * extents in the unindexed tree. */ if (alloc == 2) credits += OCFS2_SUBALLOC_ALLOC; handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out; } ret = dquot_alloc_space_nodirty(dir, ocfs2_clusters_to_bytes(osb->sb, alloc + dx_alloc)); if (ret) goto out_commit; did_quota = 1; if (ocfs2_supports_indexed_dirs(osb) && !dx_inline) { /* * Allocate our index cluster first, to maximize the * possibility that unindexed leaves grow * contiguously. */ ret = __ocfs2_dx_dir_new_cluster(dir, 0, handle, data_ac, dx_leaves, num_dx_leaves, &dx_insert_blkno); if (ret) { mlog_errno(ret); goto out_commit; } bytes_allocated += ocfs2_clusters_to_bytes(dir->i_sb, 1); } /* * Try to claim as many clusters as the bitmap can give though * if we only get one now, that's enough to continue. The rest * will be claimed after the conversion to extents. */ if (ocfs2_dir_resv_allowed(osb)) data_ac->ac_resv = &oi->ip_la_data_resv; ret = ocfs2_claim_clusters(handle, data_ac, 1, &bit_off, &len); if (ret) { mlog_errno(ret); goto out_commit; } bytes_allocated += ocfs2_clusters_to_bytes(dir->i_sb, 1); /* * Operations are carefully ordered so that we set up the new * data block first. The conversion from inline data to * extents follows. */ blkno = ocfs2_clusters_to_blocks(dir->i_sb, bit_off); dirdata_bh = sb_getblk(sb, blkno); if (!dirdata_bh) { ret = -ENOMEM; mlog_errno(ret); goto out_commit; } ocfs2_set_new_buffer_uptodate(INODE_CACHE(dir), dirdata_bh); ret = ocfs2_journal_access_db(handle, INODE_CACHE(dir), dirdata_bh, OCFS2_JOURNAL_ACCESS_CREATE); if (ret) { mlog_errno(ret); goto out_commit; } memcpy(dirdata_bh->b_data, di->id2.i_data.id_data, i_size_read(dir)); memset(dirdata_bh->b_data + i_size_read(dir), 0, sb->s_blocksize - i_size_read(dir)); i = ocfs2_expand_last_dirent(dirdata_bh->b_data, i_size_read(dir), dir); if (ocfs2_new_dir_wants_trailer(dir)) { /* * Prepare the dir trailer up front. It will otherwise look * like a valid dirent. Even if inserting the index fails * (unlikely), then all we'll have done is given first dir * block a small amount of fragmentation. */ ocfs2_init_dir_trailer(dir, dirdata_bh, i); } ocfs2_update_inode_fsync_trans(handle, dir, 1); ocfs2_journal_dirty(handle, dirdata_bh); if (ocfs2_supports_indexed_dirs(osb) && !dx_inline) { /* * Dx dirs with an external cluster need to do this up * front. Inline dx root's get handled later, after * we've allocated our root block. We get passed back * a total number of items so that dr_num_entries can * be correctly set once the dx_root has been * allocated. */ ret = ocfs2_dx_dir_index_block(dir, handle, dx_leaves, num_dx_leaves, &num_dx_entries, dirdata_bh); if (ret) { mlog_errno(ret); goto out_commit; } } /* * Set extent, i_size, etc on the directory. After this, the * inode should contain the same exact dirents as before and * be fully accessible from system calls. * * We let the later dirent insert modify c/mtime - to the user * the data hasn't changed. */ ret = ocfs2_journal_access_di(handle, INODE_CACHE(dir), di_bh, OCFS2_JOURNAL_ACCESS_CREATE); if (ret) { mlog_errno(ret); goto out_commit; } spin_lock(&oi->ip_lock); oi->ip_dyn_features &= ~OCFS2_INLINE_DATA_FL; di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features); spin_unlock(&oi->ip_lock); ocfs2_dinode_new_extent_list(dir, di); i_size_write(dir, sb->s_blocksize); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); di->i_size = cpu_to_le64(sb->s_blocksize); di->i_ctime = di->i_mtime = cpu_to_le64(inode_get_ctime_sec(dir)); di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode_get_ctime_nsec(dir)); ocfs2_update_inode_fsync_trans(handle, dir, 1); /* * This should never fail as our extent list is empty and all * related blocks have been journaled already. */ ret = ocfs2_insert_extent(handle, &et, 0, blkno, len, 0, NULL); if (ret) { mlog_errno(ret); goto out_commit; } /* * Set i_blocks after the extent insert for the most up to * date ip_clusters value. */ dir->i_blocks = ocfs2_inode_sector_count(dir); ocfs2_journal_dirty(handle, di_bh); if (ocfs2_supports_indexed_dirs(osb)) { ret = ocfs2_dx_dir_attach_index(osb, handle, dir, di_bh, dirdata_bh, meta_ac, dx_inline, num_dx_entries, &dx_root_bh); if (ret) { mlog_errno(ret); goto out_commit; } if (dx_inline) { ocfs2_dx_dir_index_root_block(dir, dx_root_bh, dirdata_bh); } else { ocfs2_init_dx_root_extent_tree(&dx_et, INODE_CACHE(dir), dx_root_bh); ret = ocfs2_insert_extent(handle, &dx_et, 0, dx_insert_blkno, 1, 0, NULL); if (ret) mlog_errno(ret); } } /* * We asked for two clusters, but only got one in the 1st * pass. Claim the 2nd cluster as a separate extent. */ if (alloc > len) { ret = ocfs2_claim_clusters(handle, data_ac, 1, &bit_off, &len); if (ret) { mlog_errno(ret); goto out_commit; } blkno = ocfs2_clusters_to_blocks(dir->i_sb, bit_off); ret = ocfs2_insert_extent(handle, &et, 1, blkno, len, 0, NULL); if (ret) { mlog_errno(ret); goto out_commit; } bytes_allocated += ocfs2_clusters_to_bytes(dir->i_sb, 1); } *first_block_bh = dirdata_bh; dirdata_bh = NULL; if (ocfs2_supports_indexed_dirs(osb)) { unsigned int off; if (!dx_inline) { /* * We need to return the correct block within the * cluster which should hold our entry. */ off = ocfs2_dx_dir_hash_idx(osb, &lookup->dl_hinfo); get_bh(dx_leaves[off]); lookup->dl_dx_leaf_bh = dx_leaves[off]; } lookup->dl_dx_root_bh = dx_root_bh; dx_root_bh = NULL; } out_commit: if (ret < 0 && did_quota) dquot_free_space_nodirty(dir, bytes_allocated); ocfs2_commit_trans(osb, handle); out: up_write(&oi->ip_alloc_sem); if (data_ac) ocfs2_free_alloc_context(data_ac); if (meta_ac) ocfs2_free_alloc_context(meta_ac); if (dx_leaves) { for (i = 0; i < num_dx_leaves; i++) brelse(dx_leaves[i]); kfree(dx_leaves); } brelse(dirdata_bh); brelse(dx_root_bh); return ret; } /* returns a bh of the 1st new block in the allocation. */ static int ocfs2_do_extend_dir(struct super_block *sb, handle_t *handle, struct inode *dir, struct buffer_head *parent_fe_bh, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac, struct buffer_head **new_bh) { int status; int extend, did_quota = 0; u64 p_blkno, v_blkno; spin_lock(&OCFS2_I(dir)->ip_lock); extend = (i_size_read(dir) == ocfs2_clusters_to_bytes(sb, OCFS2_I(dir)->ip_clusters)); spin_unlock(&OCFS2_I(dir)->ip_lock); if (extend) { u32 offset = OCFS2_I(dir)->ip_clusters; status = dquot_alloc_space_nodirty(dir, ocfs2_clusters_to_bytes(sb, 1)); if (status) goto bail; did_quota = 1; status = ocfs2_add_inode_data(OCFS2_SB(sb), dir, &offset, 1, 0, parent_fe_bh, handle, data_ac, meta_ac, NULL); BUG_ON(status == -EAGAIN); if (status < 0) { mlog_errno(status); goto bail; } } v_blkno = ocfs2_blocks_for_bytes(sb, i_size_read(dir)); status = ocfs2_extent_map_get_blocks(dir, v_blkno, &p_blkno, NULL, NULL); if (status < 0) { mlog_errno(status); goto bail; } *new_bh = sb_getblk(sb, p_blkno); if (!*new_bh) { status = -ENOMEM; mlog_errno(status); goto bail; } status = 0; bail: if (did_quota && status < 0) dquot_free_space_nodirty(dir, ocfs2_clusters_to_bytes(sb, 1)); return status; } /* * Assumes you already have a cluster lock on the directory. * * 'blocks_wanted' is only used if we have an inline directory which * is to be turned into an extent based one. The size of the dirent to * insert might be larger than the space gained by growing to just one * block, so we may have to grow the inode by two blocks in that case. * * If the directory is already indexed, dx_root_bh must be provided. */ static int ocfs2_extend_dir(struct ocfs2_super *osb, struct inode *dir, struct buffer_head *parent_fe_bh, unsigned int blocks_wanted, struct ocfs2_dir_lookup_result *lookup, struct buffer_head **new_de_bh) { int status = 0; int credits, num_free_extents, drop_alloc_sem = 0; loff_t dir_i_size; struct ocfs2_dinode *fe = (struct ocfs2_dinode *) parent_fe_bh->b_data; struct ocfs2_extent_list *el = &fe->id2.i_list; struct ocfs2_alloc_context *data_ac = NULL; struct ocfs2_alloc_context *meta_ac = NULL; handle_t *handle = NULL; struct buffer_head *new_bh = NULL; struct ocfs2_dir_entry * de; struct super_block *sb = osb->sb; struct ocfs2_extent_tree et; struct buffer_head *dx_root_bh = lookup->dl_dx_root_bh; if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { /* * This would be a code error as an inline directory should * never have an index root. */ BUG_ON(dx_root_bh); status = ocfs2_expand_inline_dir(dir, parent_fe_bh, blocks_wanted, lookup, &new_bh); if (status) { mlog_errno(status); goto bail; } /* Expansion from inline to an indexed directory will * have given us this. */ dx_root_bh = lookup->dl_dx_root_bh; if (blocks_wanted == 1) { /* * If the new dirent will fit inside the space * created by pushing out to one block, then * we can complete the operation * here. Otherwise we have to expand i_size * and format the 2nd block below. */ BUG_ON(new_bh == NULL); goto bail_bh; } /* * Get rid of 'new_bh' - we want to format the 2nd * data block and return that instead. */ brelse(new_bh); new_bh = NULL; down_write(&OCFS2_I(dir)->ip_alloc_sem); drop_alloc_sem = 1; dir_i_size = i_size_read(dir); credits = OCFS2_SIMPLE_DIR_EXTEND_CREDITS; goto do_extend; } down_write(&OCFS2_I(dir)->ip_alloc_sem); drop_alloc_sem = 1; dir_i_size = i_size_read(dir); trace_ocfs2_extend_dir((unsigned long long)OCFS2_I(dir)->ip_blkno, dir_i_size); /* dir->i_size is always block aligned. */ spin_lock(&OCFS2_I(dir)->ip_lock); if (dir_i_size == ocfs2_clusters_to_bytes(sb, OCFS2_I(dir)->ip_clusters)) { spin_unlock(&OCFS2_I(dir)->ip_lock); ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(dir), parent_fe_bh); num_free_extents = ocfs2_num_free_extents(&et); if (num_free_extents < 0) { status = num_free_extents; mlog_errno(status); goto bail; } if (!num_free_extents) { status = ocfs2_reserve_new_metadata(osb, el, &meta_ac); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto bail; } } status = ocfs2_reserve_clusters(osb, 1, &data_ac); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); goto bail; } if (ocfs2_dir_resv_allowed(osb)) data_ac->ac_resv = &OCFS2_I(dir)->ip_la_data_resv; credits = ocfs2_calc_extend_credits(sb, el); } else { spin_unlock(&OCFS2_I(dir)->ip_lock); credits = OCFS2_SIMPLE_DIR_EXTEND_CREDITS; } do_extend: if (ocfs2_dir_indexed(dir)) credits++; /* For attaching the new dirent block to the * dx_root */ handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; mlog_errno(status); goto bail; } status = ocfs2_do_extend_dir(osb->sb, handle, dir, parent_fe_bh, data_ac, meta_ac, &new_bh); if (status < 0) { mlog_errno(status); goto bail; } ocfs2_set_new_buffer_uptodate(INODE_CACHE(dir), new_bh); status = ocfs2_journal_access_db(handle, INODE_CACHE(dir), new_bh, OCFS2_JOURNAL_ACCESS_CREATE); if (status < 0) { mlog_errno(status); goto bail; } memset(new_bh->b_data, 0, sb->s_blocksize); de = (struct ocfs2_dir_entry *) new_bh->b_data; de->inode = 0; if (ocfs2_supports_dir_trailer(dir)) { de->rec_len = cpu_to_le16(ocfs2_dir_trailer_blk_off(sb)); ocfs2_init_dir_trailer(dir, new_bh, le16_to_cpu(de->rec_len)); if (ocfs2_dir_indexed(dir)) { status = ocfs2_dx_dir_link_trailer(dir, handle, dx_root_bh, new_bh); if (status) { mlog_errno(status); goto bail; } } } else { de->rec_len = cpu_to_le16(sb->s_blocksize); } ocfs2_update_inode_fsync_trans(handle, dir, 1); ocfs2_journal_dirty(handle, new_bh); dir_i_size += dir->i_sb->s_blocksize; i_size_write(dir, dir_i_size); dir->i_blocks = ocfs2_inode_sector_count(dir); status = ocfs2_mark_inode_dirty(handle, dir, parent_fe_bh); if (status < 0) { mlog_errno(status); goto bail; } bail_bh: *new_de_bh = new_bh; get_bh(*new_de_bh); bail: if (handle) ocfs2_commit_trans(osb, handle); if (drop_alloc_sem) up_write(&OCFS2_I(dir)->ip_alloc_sem); if (data_ac) ocfs2_free_alloc_context(data_ac); if (meta_ac) ocfs2_free_alloc_context(meta_ac); brelse(new_bh); return status; } static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh, const char *name, int namelen, struct buffer_head **ret_de_bh, unsigned int *blocks_wanted) { int ret; struct super_block *sb = dir->i_sb; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_dir_entry *de, *last_de = NULL; char *first_de, *de_buf, *limit; unsigned long offset = 0; unsigned int rec_len, new_rec_len, free_space; /* * This calculates how many free bytes we'd have in block zero, should * this function force expansion to an extent tree. */ if (ocfs2_new_dir_wants_trailer(dir)) free_space = ocfs2_dir_trailer_blk_off(sb) - i_size_read(dir); else free_space = dir->i_sb->s_blocksize - i_size_read(dir); first_de = di->id2.i_data.id_data; de_buf = first_de; limit = de_buf + i_size_read(dir); rec_len = OCFS2_DIR_REC_LEN(namelen); while (de_buf < limit) { de = (struct ocfs2_dir_entry *)de_buf; if (!ocfs2_check_dir_entry(dir, de, di_bh, first_de, i_size_read(dir), offset)) { ret = -ENOENT; goto out; } if (ocfs2_match(namelen, name, de)) { ret = -EEXIST; goto out; } /* * No need to check for a trailing dirent record here as * they're not used for inline dirs. */ if (ocfs2_dirent_would_fit(de, rec_len)) { /* Ok, we found a spot. Return this bh and let * the caller actually fill it in. */ *ret_de_bh = di_bh; get_bh(*ret_de_bh); ret = 0; goto out; } last_de = de; de_buf += le16_to_cpu(de->rec_len); offset += le16_to_cpu(de->rec_len); } /* * We're going to require expansion of the directory - figure * out how many blocks we'll need so that a place for the * dirent can be found. */ *blocks_wanted = 1; new_rec_len = le16_to_cpu(last_de->rec_len) + free_space; if (new_rec_len < (rec_len + OCFS2_DIR_REC_LEN(last_de->name_len))) *blocks_wanted = 2; ret = -ENOSPC; out: return ret; } static int ocfs2_find_dir_space_el(struct inode *dir, const char *name, int namelen, struct buffer_head **ret_de_bh) { unsigned long offset; struct buffer_head *bh = NULL; unsigned short rec_len; struct ocfs2_dir_entry *de; struct super_block *sb = dir->i_sb; int status; int blocksize = dir->i_sb->s_blocksize; status = ocfs2_read_dir_block(dir, 0, &bh, 0); if (status) goto bail; rec_len = OCFS2_DIR_REC_LEN(namelen); offset = 0; de = (struct ocfs2_dir_entry *) bh->b_data; while (1) { if ((char *)de >= sb->s_blocksize + bh->b_data) { brelse(bh); bh = NULL; if (i_size_read(dir) <= offset) { /* * Caller will have to expand this * directory. */ status = -ENOSPC; goto bail; } status = ocfs2_read_dir_block(dir, offset >> sb->s_blocksize_bits, &bh, 0); if (status) goto bail; /* move to next block */ de = (struct ocfs2_dir_entry *) bh->b_data; } if (!ocfs2_check_dir_entry(dir, de, bh, bh->b_data, blocksize, offset)) { status = -ENOENT; goto bail; } if (ocfs2_match(namelen, name, de)) { status = -EEXIST; goto bail; } if (ocfs2_skip_dir_trailer(dir, de, offset % blocksize, blocksize)) goto next; if (ocfs2_dirent_would_fit(de, rec_len)) { /* Ok, we found a spot. Return this bh and let * the caller actually fill it in. */ *ret_de_bh = bh; get_bh(*ret_de_bh); status = 0; goto bail; } next: offset += le16_to_cpu(de->rec_len); de = (struct ocfs2_dir_entry *)((char *) de + le16_to_cpu(de->rec_len)); } bail: brelse(bh); if (status) mlog_errno(status); return status; } static int dx_leaf_sort_cmp(const void *a, const void *b) { const struct ocfs2_dx_entry *entry1 = a; const struct ocfs2_dx_entry *entry2 = b; u32 major_hash1 = le32_to_cpu(entry1->dx_major_hash); u32 major_hash2 = le32_to_cpu(entry2->dx_major_hash); u32 minor_hash1 = le32_to_cpu(entry1->dx_minor_hash); u32 minor_hash2 = le32_to_cpu(entry2->dx_minor_hash); if (major_hash1 > major_hash2) return 1; if (major_hash1 < major_hash2) return -1; /* * It is not strictly necessary to sort by minor */ if (minor_hash1 > minor_hash2) return 1; if (minor_hash1 < minor_hash2) return -1; return 0; } static int ocfs2_dx_leaf_same_major(struct ocfs2_dx_leaf *dx_leaf) { struct ocfs2_dx_entry_list *dl_list = &dx_leaf->dl_list; int i, num = le16_to_cpu(dl_list->de_num_used); for (i = 0; i < (num - 1); i++) { if (le32_to_cpu(dl_list->de_entries[i].dx_major_hash) != le32_to_cpu(dl_list->de_entries[i + 1].dx_major_hash)) return 0; } return 1; } /* * Find the optimal value to split this leaf on. This expects the leaf * entries to be in sorted order. * * leaf_cpos is the cpos of the leaf we're splitting. insert_hash is * the hash we want to insert. * * This function is only concerned with the major hash - that which * determines which cluster an item belongs to. */ static int ocfs2_dx_dir_find_leaf_split(struct ocfs2_dx_leaf *dx_leaf, u32 leaf_cpos, u32 insert_hash, u32 *split_hash) { struct ocfs2_dx_entry_list *dl_list = &dx_leaf->dl_list; int i, num_used = le16_to_cpu(dl_list->de_num_used); int allsame; /* * There's a couple rare, but nasty corner cases we have to * check for here. All of them involve a leaf where all value * have the same hash, which is what we look for first. * * Most of the time, all of the above is false, and we simply * pick the median value for a split. */ allsame = ocfs2_dx_leaf_same_major(dx_leaf); if (allsame) { u32 val = le32_to_cpu(dl_list->de_entries[0].dx_major_hash); if (val == insert_hash) { /* * No matter where we would choose to split, * the new entry would want to occupy the same * block as these. Since there's no space left * in their existing block, we know there * won't be space after the split. */ return -ENOSPC; } if (val == leaf_cpos) { /* * Because val is the same as leaf_cpos (which * is the smallest value this leaf can have), * yet is not equal to insert_hash, then we * know that insert_hash *must* be larger than * val (and leaf_cpos). At least cpos+1 in value. * * We also know then, that there cannot be an * adjacent extent (otherwise we'd be looking * at it). Choosing this value gives us a * chance to get some contiguousness. */ *split_hash = leaf_cpos + 1; return 0; } if (val > insert_hash) { /* * val can not be the same as insert hash, and * also must be larger than leaf_cpos. Also, * we know that there can't be a leaf between * cpos and val, otherwise the entries with * hash 'val' would be there. */ *split_hash = val; return 0; } *split_hash = insert_hash; return 0; } /* * Since the records are sorted and the checks above * guaranteed that not all records in this block are the same, * we simple travel forward, from the median, and pick the 1st * record whose value is larger than leaf_cpos. */ for (i = (num_used / 2); i < num_used; i++) if (le32_to_cpu(dl_list->de_entries[i].dx_major_hash) > leaf_cpos) break; BUG_ON(i == num_used); /* Should be impossible */ *split_hash = le32_to_cpu(dl_list->de_entries[i].dx_major_hash); return 0; } /* * Transfer all entries in orig_dx_leaves whose major hash is equal to or * larger than split_hash into new_dx_leaves. We use a temporary * buffer (tmp_dx_leaf) to make the changes to the original leaf blocks. * * Since the block offset inside a leaf (cluster) is a constant mask * of minor_hash, we can optimize - an item at block offset X within * the original cluster, will be at offset X within the new cluster. */ static void ocfs2_dx_dir_transfer_leaf(struct inode *dir, u32 split_hash, handle_t *handle, struct ocfs2_dx_leaf *tmp_dx_leaf, struct buffer_head **orig_dx_leaves, struct buffer_head **new_dx_leaves, int num_dx_leaves) { int i, j, num_used; u32 major_hash; struct ocfs2_dx_leaf *orig_dx_leaf, *new_dx_leaf; struct ocfs2_dx_entry_list *orig_list, *tmp_list; struct ocfs2_dx_entry *dx_entry; tmp_list = &tmp_dx_leaf->dl_list; for (i = 0; i < num_dx_leaves; i++) { orig_dx_leaf = (struct ocfs2_dx_leaf *) orig_dx_leaves[i]->b_data; orig_list = &orig_dx_leaf->dl_list; new_dx_leaf = (struct ocfs2_dx_leaf *) new_dx_leaves[i]->b_data; num_used = le16_to_cpu(orig_list->de_num_used); memcpy(tmp_dx_leaf, orig_dx_leaf, dir->i_sb->s_blocksize); tmp_list->de_num_used = cpu_to_le16(0); memset(&tmp_list->de_entries, 0, sizeof(*dx_entry)*num_used); for (j = 0; j < num_used; j++) { dx_entry = &orig_list->de_entries[j]; major_hash = le32_to_cpu(dx_entry->dx_major_hash); if (major_hash >= split_hash) ocfs2_dx_dir_leaf_insert_tail(new_dx_leaf, dx_entry); else ocfs2_dx_dir_leaf_insert_tail(tmp_dx_leaf, dx_entry); } memcpy(orig_dx_leaf, tmp_dx_leaf, dir->i_sb->s_blocksize); ocfs2_journal_dirty(handle, orig_dx_leaves[i]); ocfs2_journal_dirty(handle, new_dx_leaves[i]); } } static int ocfs2_dx_dir_rebalance_credits(struct ocfs2_super *osb, struct ocfs2_dx_root_block *dx_root) { int credits = ocfs2_clusters_to_blocks(osb->sb, 3); credits += ocfs2_calc_extend_credits(osb->sb, &dx_root->dr_list); credits += ocfs2_quota_trans_credits(osb->sb); return credits; } /* * Find the median value in dx_leaf_bh and allocate a new leaf to move * half our entries into. */ static int ocfs2_dx_dir_rebalance(struct ocfs2_super *osb, struct inode *dir, struct buffer_head *dx_root_bh, struct buffer_head *dx_leaf_bh, struct ocfs2_dx_hinfo *hinfo, u32 leaf_cpos, u64 leaf_blkno) { struct ocfs2_dx_leaf *dx_leaf = (struct ocfs2_dx_leaf *)dx_leaf_bh->b_data; int credits, ret, i, num_used, did_quota = 0; u32 cpos, split_hash, insert_hash = hinfo->major_hash; u64 orig_leaves_start; int num_dx_leaves; struct buffer_head **orig_dx_leaves = NULL; struct buffer_head **new_dx_leaves = NULL; struct ocfs2_alloc_context *data_ac = NULL, *meta_ac = NULL; struct ocfs2_extent_tree et; handle_t *handle = NULL; struct ocfs2_dx_root_block *dx_root; struct ocfs2_dx_leaf *tmp_dx_leaf = NULL; trace_ocfs2_dx_dir_rebalance((unsigned long long)OCFS2_I(dir)->ip_blkno, (unsigned long long)leaf_blkno, insert_hash); ocfs2_init_dx_root_extent_tree(&et, INODE_CACHE(dir), dx_root_bh); dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; /* * XXX: This is a rather large limit. We should use a more * realistic value. */ if (le32_to_cpu(dx_root->dr_clusters) == UINT_MAX) return -ENOSPC; num_used = le16_to_cpu(dx_leaf->dl_list.de_num_used); if (num_used < le16_to_cpu(dx_leaf->dl_list.de_count)) { mlog(ML_ERROR, "DX Dir: %llu, Asked to rebalance empty leaf: " "%llu, %d\n", (unsigned long long)OCFS2_I(dir)->ip_blkno, (unsigned long long)leaf_blkno, num_used); ret = -EIO; goto out; } orig_dx_leaves = ocfs2_dx_dir_kmalloc_leaves(osb->sb, &num_dx_leaves); if (!orig_dx_leaves) { ret = -ENOMEM; mlog_errno(ret); goto out; } new_dx_leaves = ocfs2_dx_dir_kmalloc_leaves(osb->sb, NULL); if (!new_dx_leaves) { ret = -ENOMEM; mlog_errno(ret); goto out; } ret = ocfs2_lock_allocators(dir, &et, 1, 0, &data_ac, &meta_ac); if (ret) { if (ret != -ENOSPC) mlog_errno(ret); goto out; } credits = ocfs2_dx_dir_rebalance_credits(osb, dx_root); handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); handle = NULL; mlog_errno(ret); goto out; } ret = dquot_alloc_space_nodirty(dir, ocfs2_clusters_to_bytes(dir->i_sb, 1)); if (ret) goto out_commit; did_quota = 1; ret = ocfs2_journal_access_dl(handle, INODE_CACHE(dir), dx_leaf_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; } /* * This block is changing anyway, so we can sort it in place. */ sort(dx_leaf->dl_list.de_entries, num_used, sizeof(struct ocfs2_dx_entry), dx_leaf_sort_cmp, NULL); ocfs2_journal_dirty(handle, dx_leaf_bh); ret = ocfs2_dx_dir_find_leaf_split(dx_leaf, leaf_cpos, insert_hash, &split_hash); if (ret) { mlog_errno(ret); goto out_commit; } trace_ocfs2_dx_dir_rebalance_split(leaf_cpos, split_hash, insert_hash); /* * We have to carefully order operations here. There are items * which want to be in the new cluster before insert, but in * order to put those items in the new cluster, we alter the * old cluster. A failure to insert gets nasty. * * So, start by reserving writes to the old * cluster. ocfs2_dx_dir_new_cluster will reserve writes on * the new cluster for us, before inserting it. The insert * won't happen if there's an error before that. Once the * insert is done then, we can transfer from one leaf into the * other without fear of hitting any error. */ /* * The leaf transfer wants some scratch space so that we don't * wind up doing a bunch of expensive memmove(). */ tmp_dx_leaf = kmalloc(osb->sb->s_blocksize, GFP_NOFS); if (!tmp_dx_leaf) { ret = -ENOMEM; mlog_errno(ret); goto out_commit; } orig_leaves_start = ocfs2_block_to_cluster_start(dir->i_sb, leaf_blkno); ret = ocfs2_read_dx_leaves(dir, orig_leaves_start, num_dx_leaves, orig_dx_leaves); if (ret) { mlog_errno(ret); goto out_commit; } cpos = split_hash; ret = ocfs2_dx_dir_new_cluster(dir, &et, cpos, handle, data_ac, meta_ac, new_dx_leaves, num_dx_leaves); if (ret) { mlog_errno(ret); goto out_commit; } for (i = 0; i < num_dx_leaves; i++) { ret = ocfs2_journal_access_dl(handle, INODE_CACHE(dir), orig_dx_leaves[i], OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; } ret = ocfs2_journal_access_dl(handle, INODE_CACHE(dir), new_dx_leaves[i], OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; } } ocfs2_dx_dir_transfer_leaf(dir, split_hash, handle, tmp_dx_leaf, orig_dx_leaves, new_dx_leaves, num_dx_leaves); out_commit: if (ret < 0 && did_quota) dquot_free_space_nodirty(dir, ocfs2_clusters_to_bytes(dir->i_sb, 1)); ocfs2_update_inode_fsync_trans(handle, dir, 1); ocfs2_commit_trans(osb, handle); out: if (orig_dx_leaves || new_dx_leaves) { for (i = 0; i < num_dx_leaves; i++) { if (orig_dx_leaves) brelse(orig_dx_leaves[i]); if (new_dx_leaves) brelse(new_dx_leaves[i]); } kfree(orig_dx_leaves); kfree(new_dx_leaves); } if (meta_ac) ocfs2_free_alloc_context(meta_ac); if (data_ac) ocfs2_free_alloc_context(data_ac); kfree(tmp_dx_leaf); return ret; } static int ocfs2_find_dir_space_dx(struct ocfs2_super *osb, struct inode *dir, struct buffer_head *di_bh, struct buffer_head *dx_root_bh, const char *name, int namelen, struct ocfs2_dir_lookup_result *lookup) { int ret, rebalanced = 0; struct ocfs2_dx_root_block *dx_root; struct buffer_head *dx_leaf_bh = NULL; struct ocfs2_dx_leaf *dx_leaf; u64 blkno; u32 leaf_cpos; dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; restart_search: ret = ocfs2_dx_dir_lookup(dir, &dx_root->dr_list, &lookup->dl_hinfo, &leaf_cpos, &blkno); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_read_dx_leaf(dir, blkno, &dx_leaf_bh); if (ret) { mlog_errno(ret); goto out; } dx_leaf = (struct ocfs2_dx_leaf *)dx_leaf_bh->b_data; if (le16_to_cpu(dx_leaf->dl_list.de_num_used) >= le16_to_cpu(dx_leaf->dl_list.de_count)) { if (rebalanced) { /* * Rebalancing should have provided us with * space in an appropriate leaf. * * XXX: Is this an abnormal condition then? * Should we print a message here? */ ret = -ENOSPC; goto out; } ret = ocfs2_dx_dir_rebalance(osb, dir, dx_root_bh, dx_leaf_bh, &lookup->dl_hinfo, leaf_cpos, blkno); if (ret) { if (ret != -ENOSPC) mlog_errno(ret); goto out; } /* * Restart the lookup. The rebalance might have * changed which block our item fits into. Mark our * progress, so we only execute this once. */ brelse(dx_leaf_bh); dx_leaf_bh = NULL; rebalanced = 1; goto restart_search; } lookup->dl_dx_leaf_bh = dx_leaf_bh; dx_leaf_bh = NULL; out: brelse(dx_leaf_bh); return ret; } static int ocfs2_search_dx_free_list(struct inode *dir, struct buffer_head *dx_root_bh, int namelen, struct ocfs2_dir_lookup_result *lookup) { int ret = -ENOSPC; struct buffer_head *leaf_bh = NULL, *prev_leaf_bh = NULL; struct ocfs2_dir_block_trailer *db; u64 next_block; int rec_len = OCFS2_DIR_REC_LEN(namelen); struct ocfs2_dx_root_block *dx_root; dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; next_block = le64_to_cpu(dx_root->dr_free_blk); while (next_block) { brelse(prev_leaf_bh); prev_leaf_bh = leaf_bh; leaf_bh = NULL; ret = ocfs2_read_dir_block_direct(dir, next_block, &leaf_bh); if (ret) { mlog_errno(ret); goto out; } db = ocfs2_trailer_from_bh(leaf_bh, dir->i_sb); if (rec_len <= le16_to_cpu(db->db_free_rec_len)) { lookup->dl_leaf_bh = leaf_bh; lookup->dl_prev_leaf_bh = prev_leaf_bh; leaf_bh = NULL; prev_leaf_bh = NULL; break; } next_block = le64_to_cpu(db->db_free_next); } if (!next_block) ret = -ENOSPC; out: brelse(leaf_bh); brelse(prev_leaf_bh); return ret; } static int ocfs2_expand_inline_dx_root(struct inode *dir, struct buffer_head *dx_root_bh) { int ret, num_dx_leaves, i, j, did_quota = 0; struct buffer_head **dx_leaves = NULL; struct ocfs2_extent_tree et; u64 insert_blkno; struct ocfs2_alloc_context *data_ac = NULL; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); handle_t *handle = NULL; struct ocfs2_dx_root_block *dx_root; struct ocfs2_dx_entry_list *entry_list; struct ocfs2_dx_entry *dx_entry; struct ocfs2_dx_leaf *target_leaf; ret = ocfs2_reserve_clusters(osb, 1, &data_ac); if (ret) { mlog_errno(ret); goto out; } dx_leaves = ocfs2_dx_dir_kmalloc_leaves(osb->sb, &num_dx_leaves); if (!dx_leaves) { ret = -ENOMEM; mlog_errno(ret); goto out; } handle = ocfs2_start_trans(osb, ocfs2_calc_dxi_expand_credits(osb->sb)); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out; } ret = dquot_alloc_space_nodirty(dir, ocfs2_clusters_to_bytes(osb->sb, 1)); if (ret) goto out_commit; did_quota = 1; /* * We do this up front, before the allocation, so that a * failure to add the dx_root_bh to the journal won't result * us losing clusters. */ ret = ocfs2_journal_access_dr(handle, INODE_CACHE(dir), dx_root_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; } ret = __ocfs2_dx_dir_new_cluster(dir, 0, handle, data_ac, dx_leaves, num_dx_leaves, &insert_blkno); if (ret) { mlog_errno(ret); goto out_commit; } /* * Transfer the entries from our dx_root into the appropriate * block */ dx_root = (struct ocfs2_dx_root_block *) dx_root_bh->b_data; entry_list = &dx_root->dr_entries; for (i = 0; i < le16_to_cpu(entry_list->de_num_used); i++) { dx_entry = &entry_list->de_entries[i]; j = __ocfs2_dx_dir_hash_idx(osb, le32_to_cpu(dx_entry->dx_minor_hash)); target_leaf = (struct ocfs2_dx_leaf *)dx_leaves[j]->b_data; ocfs2_dx_dir_leaf_insert_tail(target_leaf, dx_entry); /* Each leaf has been passed to the journal already * via __ocfs2_dx_dir_new_cluster() */ } dx_root->dr_flags &= ~OCFS2_DX_FLAG_INLINE; memset(&dx_root->dr_list, 0, osb->sb->s_blocksize - offsetof(struct ocfs2_dx_root_block, dr_list)); dx_root->dr_list.l_count = cpu_to_le16(ocfs2_extent_recs_per_dx_root(osb->sb)); /* This should never fail considering we start with an empty * dx_root. */ ocfs2_init_dx_root_extent_tree(&et, INODE_CACHE(dir), dx_root_bh); ret = ocfs2_insert_extent(handle, &et, 0, insert_blkno, 1, 0, NULL); if (ret) mlog_errno(ret); did_quota = 0; ocfs2_update_inode_fsync_trans(handle, dir, 1); ocfs2_journal_dirty(handle, dx_root_bh); out_commit: if (ret < 0 && did_quota) dquot_free_space_nodirty(dir, ocfs2_clusters_to_bytes(dir->i_sb, 1)); ocfs2_commit_trans(osb, handle); out: if (data_ac) ocfs2_free_alloc_context(data_ac); if (dx_leaves) { for (i = 0; i < num_dx_leaves; i++) brelse(dx_leaves[i]); kfree(dx_leaves); } return ret; } static int ocfs2_inline_dx_has_space(struct buffer_head *dx_root_bh) { struct ocfs2_dx_root_block *dx_root; struct ocfs2_dx_entry_list *entry_list; dx_root = (struct ocfs2_dx_root_block *) dx_root_bh->b_data; entry_list = &dx_root->dr_entries; if (le16_to_cpu(entry_list->de_num_used) >= le16_to_cpu(entry_list->de_count)) return -ENOSPC; return 0; } static int ocfs2_prepare_dx_dir_for_insert(struct inode *dir, struct buffer_head *di_bh, const char *name, int namelen, struct ocfs2_dir_lookup_result *lookup) { int ret, free_dx_root = 1; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct buffer_head *dx_root_bh = NULL; struct buffer_head *leaf_bh = NULL; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_dx_root_block *dx_root; ret = ocfs2_read_dx_root(dir, di, &dx_root_bh); if (ret) { mlog_errno(ret); goto out; } dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; if (le32_to_cpu(dx_root->dr_num_entries) == OCFS2_DX_ENTRIES_MAX) { ret = -ENOSPC; mlog_errno(ret); goto out; } if (ocfs2_dx_root_inline(dx_root)) { ret = ocfs2_inline_dx_has_space(dx_root_bh); if (ret == 0) goto search_el; /* * We ran out of room in the root block. Expand it to * an extent, then allow ocfs2_find_dir_space_dx to do * the rest. */ ret = ocfs2_expand_inline_dx_root(dir, dx_root_bh); if (ret) { mlog_errno(ret); goto out; } } /* * Insert preparation for an indexed directory is split into two * steps. The call to find_dir_space_dx reserves room in the index for * an additional item. If we run out of space there, it's a real error * we can't continue on. */ ret = ocfs2_find_dir_space_dx(osb, dir, di_bh, dx_root_bh, name, namelen, lookup); if (ret) { mlog_errno(ret); goto out; } search_el: /* * Next, we need to find space in the unindexed tree. This call * searches using the free space linked list. If the unindexed tree * lacks sufficient space, we'll expand it below. The expansion code * is smart enough to add any new blocks to the free space list. */ ret = ocfs2_search_dx_free_list(dir, dx_root_bh, namelen, lookup); if (ret && ret != -ENOSPC) { mlog_errno(ret); goto out; } /* Do this up here - ocfs2_extend_dir might need the dx_root */ lookup->dl_dx_root_bh = dx_root_bh; free_dx_root = 0; if (ret == -ENOSPC) { ret = ocfs2_extend_dir(osb, dir, di_bh, 1, lookup, &leaf_bh); if (ret) { mlog_errno(ret); goto out; } /* * We make the assumption here that new leaf blocks are added * to the front of our free list. */ lookup->dl_prev_leaf_bh = NULL; lookup->dl_leaf_bh = leaf_bh; } out: if (free_dx_root) brelse(dx_root_bh); return ret; } /* * Get a directory ready for insert. Any directory allocation required * happens here. Success returns zero, and enough context in the dir * lookup result that ocfs2_add_entry() will be able complete the task * with minimal performance impact. */ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb, struct inode *dir, struct buffer_head *parent_fe_bh, const char *name, int namelen, struct ocfs2_dir_lookup_result *lookup) { int ret; unsigned int blocks_wanted = 1; struct buffer_head *bh = NULL; trace_ocfs2_prepare_dir_for_insert( (unsigned long long)OCFS2_I(dir)->ip_blkno, namelen); /* * Do this up front to reduce confusion. * * The directory might start inline, then be turned into an * indexed one, in which case we'd need to hash deep inside * ocfs2_find_dir_space_id(). Since * ocfs2_prepare_dx_dir_for_insert() also needs this hash * done, there seems no point in spreading out the calls. We * can optimize away the case where the file system doesn't * support indexing. */ if (ocfs2_supports_indexed_dirs(osb)) ocfs2_dx_dir_name_hash(dir, name, namelen, &lookup->dl_hinfo); if (ocfs2_dir_indexed(dir)) { ret = ocfs2_prepare_dx_dir_for_insert(dir, parent_fe_bh, name, namelen, lookup); if (ret) mlog_errno(ret); goto out; } if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { ret = ocfs2_find_dir_space_id(dir, parent_fe_bh, name, namelen, &bh, &blocks_wanted); } else ret = ocfs2_find_dir_space_el(dir, name, namelen, &bh); if (ret && ret != -ENOSPC) { mlog_errno(ret); goto out; } if (ret == -ENOSPC) { /* * We have to expand the directory to add this name. */ BUG_ON(bh); ret = ocfs2_extend_dir(osb, dir, parent_fe_bh, blocks_wanted, lookup, &bh); if (ret) { if (ret != -ENOSPC) mlog_errno(ret); goto out; } BUG_ON(!bh); } lookup->dl_leaf_bh = bh; bh = NULL; out: brelse(bh); return ret; } static int ocfs2_dx_dir_remove_index(struct inode *dir, struct buffer_head *di_bh, struct buffer_head *dx_root_bh) { int ret; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_dx_root_block *dx_root; struct inode *dx_alloc_inode = NULL; struct buffer_head *dx_alloc_bh = NULL; handle_t *handle; u64 blk; u16 bit; u64 bg_blkno; dx_root = (struct ocfs2_dx_root_block *) dx_root_bh->b_data; dx_alloc_inode = ocfs2_get_system_file_inode(osb, EXTENT_ALLOC_SYSTEM_INODE, le16_to_cpu(dx_root->dr_suballoc_slot)); if (!dx_alloc_inode) { ret = -ENOMEM; mlog_errno(ret); goto out; } inode_lock(dx_alloc_inode); ret = ocfs2_inode_lock(dx_alloc_inode, &dx_alloc_bh, 1); if (ret) { mlog_errno(ret); goto out_mutex; } handle = ocfs2_start_trans(osb, OCFS2_DX_ROOT_REMOVE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out_unlock; } ret = ocfs2_journal_access_di(handle, INODE_CACHE(dir), di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; } spin_lock(&OCFS2_I(dir)->ip_lock); OCFS2_I(dir)->ip_dyn_features &= ~OCFS2_INDEXED_DIR_FL; di->i_dyn_features = cpu_to_le16(OCFS2_I(dir)->ip_dyn_features); spin_unlock(&OCFS2_I(dir)->ip_lock); di->i_dx_root = cpu_to_le64(0ULL); ocfs2_update_inode_fsync_trans(handle, dir, 1); ocfs2_journal_dirty(handle, di_bh); blk = le64_to_cpu(dx_root->dr_blkno); bit = le16_to_cpu(dx_root->dr_suballoc_bit); if (dx_root->dr_suballoc_loc) bg_blkno = le64_to_cpu(dx_root->dr_suballoc_loc); else bg_blkno = ocfs2_which_suballoc_group(blk, bit); ret = ocfs2_free_suballoc_bits(handle, dx_alloc_inode, dx_alloc_bh, bit, bg_blkno, 1); if (ret) mlog_errno(ret); out_commit: ocfs2_commit_trans(osb, handle); out_unlock: ocfs2_inode_unlock(dx_alloc_inode, 1); out_mutex: inode_unlock(dx_alloc_inode); brelse(dx_alloc_bh); out: iput(dx_alloc_inode); return ret; } int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh) { int ret; unsigned int clen; u32 major_hash = UINT_MAX, p_cpos, cpos; u64 blkno; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct buffer_head *dx_root_bh = NULL; struct ocfs2_dx_root_block *dx_root; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_cached_dealloc_ctxt dealloc; struct ocfs2_extent_tree et; ocfs2_init_dealloc_ctxt(&dealloc); if (!ocfs2_dir_indexed(dir)) return 0; ret = ocfs2_read_dx_root(dir, di, &dx_root_bh); if (ret) { mlog_errno(ret); goto out; } dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; if (ocfs2_dx_root_inline(dx_root)) goto remove_index; ocfs2_init_dx_root_extent_tree(&et, INODE_CACHE(dir), dx_root_bh); /* XXX: What if dr_clusters is too large? */ while (le32_to_cpu(dx_root->dr_clusters)) { ret = ocfs2_dx_dir_lookup_rec(dir, &dx_root->dr_list, major_hash, &cpos, &blkno, &clen); if (ret) { mlog_errno(ret); goto out; } p_cpos = ocfs2_blocks_to_clusters(dir->i_sb, blkno); ret = ocfs2_remove_btree_range(dir, &et, cpos, p_cpos, clen, 0, &dealloc, 0, false); if (ret) { mlog_errno(ret); goto out; } if (cpos == 0) break; major_hash = cpos - 1; } remove_index: ret = ocfs2_dx_dir_remove_index(dir, di_bh, dx_root_bh); if (ret) { mlog_errno(ret); goto out; } ocfs2_remove_from_cache(INODE_CACHE(dir), dx_root_bh); out: ocfs2_schedule_truncate_log_flush(osb, 1); ocfs2_run_deallocs(osb, &dealloc); brelse(dx_root_bh); return ret; } |
| 6 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 | /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/cgroup-defs.h - basic definitions for cgroup * * This file provides basic type and interface. Include this file directly * only if necessary to avoid cyclic dependencies. */ #ifndef _LINUX_CGROUP_DEFS_H #define _LINUX_CGROUP_DEFS_H #include <linux/limits.h> #include <linux/list.h> #include <linux/idr.h> #include <linux/wait.h> #include <linux/mutex.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <linux/percpu-refcount.h> #include <linux/percpu-rwsem.h> #include <linux/u64_stats_sync.h> #include <linux/workqueue.h> #include <linux/bpf-cgroup-defs.h> #include <linux/psi_types.h> #ifdef CONFIG_CGROUPS struct cgroup; struct cgroup_root; struct cgroup_subsys; struct cgroup_taskset; struct kernfs_node; struct kernfs_ops; struct kernfs_open_file; struct seq_file; struct poll_table_struct; #define MAX_CGROUP_TYPE_NAMELEN 32 #define MAX_CGROUP_ROOT_NAMELEN 64 #define MAX_CFTYPE_NAME 64 /* define the enumeration of all cgroup subsystems */ #define SUBSYS(_x) _x ## _cgrp_id, enum cgroup_subsys_id { #include <linux/cgroup_subsys.h> CGROUP_SUBSYS_COUNT, }; #undef SUBSYS /* bits in struct cgroup_subsys_state flags field */ enum { CSS_NO_REF = (1 << 0), /* no reference counting for this css */ CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */ CSS_VISIBLE = (1 << 3), /* css is visible to userland */ CSS_DYING = (1 << 4), /* css is dying */ }; /* bits in struct cgroup flags field */ enum { /* Control Group requires release notifications to userspace */ CGRP_NOTIFY_ON_RELEASE, /* * Clone the parent's configuration when creating a new child * cpuset cgroup. For historical reasons, this option can be * specified at mount time and thus is implemented here. */ CGRP_CPUSET_CLONE_CHILDREN, /* Control group has to be frozen. */ CGRP_FREEZE, /* Cgroup is frozen. */ CGRP_FROZEN, /* Control group has to be killed. */ CGRP_KILL, }; /* cgroup_root->flags */ enum { CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ /* * Consider namespaces as delegation boundaries. If this flag is * set, controller specific interface files in a namespace root * aren't writeable from inside the namespace. */ CGRP_ROOT_NS_DELEGATE = (1 << 3), /* * Reduce latencies on dynamic cgroup modifications such as task * migrations and controller on/offs by disabling percpu operation on * cgroup_threadgroup_rwsem. This makes hot path operations such as * forks and exits into the slow path and more expensive. * * The static usage pattern of creating a cgroup, enabling controllers, * and then seeding it with CLONE_INTO_CGROUP doesn't require write * locking cgroup_threadgroup_rwsem and thus doesn't benefit from * favordynmod. */ CGRP_ROOT_FAVOR_DYNMODS = (1 << 4), /* * Enable cpuset controller in v1 cgroup to use v2 behavior. */ CGRP_ROOT_CPUSET_V2_MODE = (1 << 16), /* * Enable legacy local memory.events. */ CGRP_ROOT_MEMORY_LOCAL_EVENTS = (1 << 17), /* * Enable recursive subtree protection */ CGRP_ROOT_MEMORY_RECURSIVE_PROT = (1 << 18), /* * Enable hugetlb accounting for the memory controller. */ CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING = (1 << 19), /* * Enable legacy local pids.events. */ CGRP_ROOT_PIDS_LOCAL_EVENTS = (1 << 20), }; /* cftype->flags */ enum { CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ CFTYPE_NS_DELEGATABLE = (1 << 2), /* writeable beyond delegation boundaries */ CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ CFTYPE_WORLD_WRITABLE = (1 << 4), /* (DON'T USE FOR NEW FILES) S_IWUGO */ CFTYPE_DEBUG = (1 << 5), /* create when cgroup_debug */ /* internal flags, do not use outside cgroup core proper */ __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ __CFTYPE_ADDED = (1 << 18), }; /* * cgroup_file is the handle for a file instance created in a cgroup which * is used, for example, to generate file changed notifications. This can * be obtained by setting cftype->file_offset. */ struct cgroup_file { /* do not access any fields from outside cgroup core */ struct kernfs_node *kn; unsigned long notified_at; struct timer_list notify_timer; }; /* * Per-subsystem/per-cgroup state maintained by the system. This is the * fundamental structural building block that controllers deal with. * * Fields marked with "PI:" are public and immutable and may be accessed * directly without synchronization. */ struct cgroup_subsys_state { /* PI: the cgroup that this css is attached to */ struct cgroup *cgroup; /* PI: the cgroup subsystem that this css is attached to */ struct cgroup_subsys *ss; /* reference count - access via css_[try]get() and css_put() */ struct percpu_ref refcnt; /* * siblings list anchored at the parent's ->children * * linkage is protected by cgroup_mutex or RCU */ struct list_head sibling; struct list_head children; /* flush target list anchored at cgrp->rstat_css_list */ struct list_head rstat_css_node; /* * PI: Subsys-unique ID. 0 is unused and root is always 1. The * matching css can be looked up using css_from_id(). */ int id; unsigned int flags; /* * Monotonically increasing unique serial number which defines a * uniform order among all csses. It's guaranteed that all * ->children lists are in the ascending order of ->serial_nr and * used to allow interrupting and resuming iterations. */ u64 serial_nr; /* * Incremented by online self and children. Used to guarantee that * parents are not offlined before their children. */ atomic_t online_cnt; /* percpu_ref killing and RCU release */ struct work_struct destroy_work; struct rcu_work destroy_rwork; /* * PI: the parent css. Placed here for cache proximity to following * fields of the containing structure. */ struct cgroup_subsys_state *parent; /* * Keep track of total numbers of visible descendant CSSes. * The total number of dying CSSes is tracked in * css->cgroup->nr_dying_subsys[ssid]. * Protected by cgroup_mutex. */ int nr_descendants; }; /* * A css_set is a structure holding pointers to a set of * cgroup_subsys_state objects. This saves space in the task struct * object and speeds up fork()/exit(), since a single inc/dec and a * list_add()/del() can bump the reference count on the entire cgroup * set for a task. */ struct css_set { /* * Set of subsystem states, one for each subsystem. This array is * immutable after creation apart from the init_css_set during * subsystem registration (at boot time). */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; /* reference count */ refcount_t refcount; /* * For a domain cgroup, the following points to self. If threaded, * to the matching cset of the nearest domain ancestor. The * dom_cset provides access to the domain cgroup and its csses to * which domain level resource consumptions should be charged. */ struct css_set *dom_cset; /* the default cgroup associated with this css_set */ struct cgroup *dfl_cgrp; /* internal task count, protected by css_set_lock */ int nr_tasks; /* * Lists running through all tasks using this cgroup group. * mg_tasks lists tasks which belong to this cset but are in the * process of being migrated out or in. Protected by * css_set_lock, but, during migration, once tasks are moved to * mg_tasks, it can be read safely while holding cgroup_mutex. */ struct list_head tasks; struct list_head mg_tasks; struct list_head dying_tasks; /* all css_task_iters currently walking this cset */ struct list_head task_iters; /* * On the default hierarchy, ->subsys[ssid] may point to a css * attached to an ancestor instead of the cgroup this css_set is * associated with. The following node is anchored at * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to * iterate through all css's attached to a given cgroup. */ struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; /* all threaded csets whose ->dom_cset points to this cset */ struct list_head threaded_csets; struct list_head threaded_csets_node; /* * List running through all cgroup groups in the same hash * slot. Protected by css_set_lock */ struct hlist_node hlist; /* * List of cgrp_cset_links pointing at cgroups referenced from this * css_set. Protected by css_set_lock. */ struct list_head cgrp_links; /* * List of csets participating in the on-going migration either as * source or destination. Protected by cgroup_mutex. */ struct list_head mg_src_preload_node; struct list_head mg_dst_preload_node; struct list_head mg_node; /* * If this cset is acting as the source of migration the following * two fields are set. mg_src_cgrp and mg_dst_cgrp are * respectively the source and destination cgroups of the on-going * migration. mg_dst_cset is the destination cset the target tasks * on this cset should be migrated to. Protected by cgroup_mutex. */ struct cgroup *mg_src_cgrp; struct cgroup *mg_dst_cgrp; struct css_set *mg_dst_cset; /* dead and being drained, ignore for migration */ bool dead; /* For RCU-protected deletion */ struct rcu_head rcu_head; }; struct cgroup_base_stat { struct task_cputime cputime; #ifdef CONFIG_SCHED_CORE u64 forceidle_sum; #endif u64 ntime; }; /* * rstat - cgroup scalable recursive statistics. Accounting is done * per-cpu in cgroup_rstat_cpu which is then lazily propagated up the * hierarchy on reads. * * When a stat gets updated, the cgroup_rstat_cpu and its ancestors are * linked into the updated tree. On the following read, propagation only * considers and consumes the updated tree. This makes reading O(the * number of descendants which have been active since last read) instead of * O(the total number of descendants). * * This is important because there can be a lot of (draining) cgroups which * aren't active and stat may be read frequently. The combination can * become very expensive. By propagating selectively, increasing reading * frequency decreases the cost of each read. * * This struct hosts both the fields which implement the above - * updated_children and updated_next - and the fields which track basic * resource statistics on top of it - bsync, bstat and last_bstat. */ struct cgroup_rstat_cpu { /* * ->bsync protects ->bstat. These are the only fields which get * updated in the hot path. */ struct u64_stats_sync bsync; struct cgroup_base_stat bstat; /* * Snapshots at the last reading. These are used to calculate the * deltas to propagate to the global counters. */ struct cgroup_base_stat last_bstat; /* * This field is used to record the cumulative per-cpu time of * the cgroup and its descendants. Currently it can be read via * eBPF/drgn etc, and we are still trying to determine how to * expose it in the cgroupfs interface. */ struct cgroup_base_stat subtree_bstat; /* * Snapshots at the last reading. These are used to calculate the * deltas to propagate to the per-cpu subtree_bstat. */ struct cgroup_base_stat last_subtree_bstat; /* * Child cgroups with stat updates on this cpu since the last read * are linked on the parent's ->updated_children through * ->updated_next. * * In addition to being more compact, singly-linked list pointing * to the cgroup makes it unnecessary for each per-cpu struct to * point back to the associated cgroup. * * Protected by per-cpu cgroup_rstat_cpu_lock. */ struct cgroup *updated_children; /* terminated by self cgroup */ struct cgroup *updated_next; /* NULL iff not on the list */ }; struct cgroup_freezer_state { /* Should the cgroup and its descendants be frozen. */ bool freeze; /* Should the cgroup actually be frozen? */ bool e_freeze; /* Fields below are protected by css_set_lock */ /* Number of frozen descendant cgroups */ int nr_frozen_descendants; /* * Number of tasks, which are counted as frozen: * frozen, SIGSTOPped, and PTRACEd. */ int nr_frozen_tasks; }; struct cgroup { /* self css with NULL ->ss, points back to this cgroup */ struct cgroup_subsys_state self; unsigned long flags; /* "unsigned long" so bitops work */ /* * The depth this cgroup is at. The root is at depth zero and each * step down the hierarchy increments the level. This along with * ancestors[] can determine whether a given cgroup is a * descendant of another without traversing the hierarchy. */ int level; /* Maximum allowed descent tree depth */ int max_depth; /* * Keep track of total numbers of visible and dying descent cgroups. * Dying cgroups are cgroups which were deleted by a user, * but are still existing because someone else is holding a reference. * max_descendants is a maximum allowed number of descent cgroups. * * nr_descendants and nr_dying_descendants are protected * by cgroup_mutex and css_set_lock. It's fine to read them holding * any of cgroup_mutex and css_set_lock; for writing both locks * should be held. */ int nr_descendants; int nr_dying_descendants; int max_descendants; /* * Each non-empty css_set associated with this cgroup contributes * one to nr_populated_csets. The counter is zero iff this cgroup * doesn't have any tasks. * * All children which have non-zero nr_populated_csets and/or * nr_populated_children of their own contribute one to either * nr_populated_domain_children or nr_populated_threaded_children * depending on their type. Each counter is zero iff all cgroups * of the type in the subtree proper don't have any tasks. */ int nr_populated_csets; int nr_populated_domain_children; int nr_populated_threaded_children; int nr_threaded_children; /* # of live threaded child cgroups */ struct kernfs_node *kn; /* cgroup kernfs entry */ struct cgroup_file procs_file; /* handle for "cgroup.procs" */ struct cgroup_file events_file; /* handle for "cgroup.events" */ /* handles for "{cpu,memory,io,irq}.pressure" */ struct cgroup_file psi_files[NR_PSI_RESOURCES]; /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through * "cgroup.subtree_control" while ->subtree_ss_mask is the effective * one which may have more subsystems enabled. Controller knobs * are made available iff it's enabled in ->subtree_control. */ u16 subtree_control; u16 subtree_ss_mask; u16 old_subtree_control; u16 old_subtree_ss_mask; /* Private pointers for each registered subsystem */ struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; /* * Keep track of total number of dying CSSes at and below this cgroup. * Protected by cgroup_mutex. */ int nr_dying_subsys[CGROUP_SUBSYS_COUNT]; struct cgroup_root *root; /* * List of cgrp_cset_links pointing at css_sets with tasks in this * cgroup. Protected by css_set_lock. */ struct list_head cset_links; /* * On the default hierarchy, a css_set for a cgroup with some * susbsys disabled will point to css's which are associated with * the closest ancestor which has the subsys enabled. The * following lists all css_sets which point to this cgroup's css * for the given subsystem. */ struct list_head e_csets[CGROUP_SUBSYS_COUNT]; /* * If !threaded, self. If threaded, it points to the nearest * domain ancestor. Inside a threaded subtree, cgroups are exempt * from process granularity and no-internal-task constraint. * Domain level resource consumptions which aren't tied to a * specific task are charged to the dom_cgrp. */ struct cgroup *dom_cgrp; struct cgroup *old_dom_cgrp; /* used while enabling threaded */ /* per-cpu recursive resource statistics */ struct cgroup_rstat_cpu __percpu *rstat_cpu; struct list_head rstat_css_list; /* * Add padding to separate the read mostly rstat_cpu and * rstat_css_list into a different cacheline from the following * rstat_flush_next and *bstat fields which can have frequent updates. */ CACHELINE_PADDING(_pad_); /* * A singly-linked list of cgroup structures to be rstat flushed. * This is a scratch field to be used exclusively by * cgroup_rstat_flush_locked() and protected by cgroup_rstat_lock. */ struct cgroup *rstat_flush_next; /* cgroup basic resource statistics */ struct cgroup_base_stat last_bstat; struct cgroup_base_stat bstat; struct prev_cputime prev_cputime; /* for printing out cputime */ /* * list of pidlists, up to two for each namespace (one for procs, one * for tasks); created on demand. */ struct list_head pidlists; struct mutex pidlist_mutex; /* used to wait for offlining of csses */ wait_queue_head_t offline_waitq; /* used to schedule release agent */ struct work_struct release_agent_work; /* used to track pressure stalls */ struct psi_group *psi; /* used to store eBPF programs */ struct cgroup_bpf bpf; /* Used to store internal freezer state */ struct cgroup_freezer_state freezer; #ifdef CONFIG_BPF_SYSCALL struct bpf_local_storage __rcu *bpf_cgrp_storage; #endif /* All ancestors including self */ struct cgroup *ancestors[]; }; /* * A cgroup_root represents the root of a cgroup hierarchy, and may be * associated with a kernfs_root to form an active hierarchy. This is * internal to cgroup core. Don't access directly from controllers. */ struct cgroup_root { struct kernfs_root *kf_root; /* The bitmask of subsystems attached to this hierarchy */ unsigned int subsys_mask; /* Unique id for this hierarchy. */ int hierarchy_id; /* A list running through the active hierarchies */ struct list_head root_list; struct rcu_head rcu; /* Must be near the top */ /* * The root cgroup. The containing cgroup_root will be destroyed on its * release. cgrp->ancestors[0] will be used overflowing into the * following field. cgrp_ancestor_storage must immediately follow. */ struct cgroup cgrp; /* must follow cgrp for cgrp->ancestors[0], see above */ struct cgroup *cgrp_ancestor_storage; /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ atomic_t nr_cgrps; /* Hierarchy-specific flags */ unsigned int flags; /* The path to use for release notifications. */ char release_agent_path[PATH_MAX]; /* The name for this hierarchy - may be empty */ char name[MAX_CGROUP_ROOT_NAMELEN]; }; /* * struct cftype: handler definitions for cgroup control files * * When reading/writing to a file: * - the cgroup to use is file->f_path.dentry->d_parent->d_fsdata * - the 'cftype' of the file is file->f_path.dentry->d_fsdata */ struct cftype { /* * By convention, the name should begin with the name of the * subsystem, followed by a period. Zero length string indicates * end of cftype array. */ char name[MAX_CFTYPE_NAME]; unsigned long private; /* * The maximum length of string, excluding trailing nul, that can * be passed to write. If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed. */ size_t max_write_len; /* CFTYPE_* flags */ unsigned int flags; /* * If non-zero, should contain the offset from the start of css to * a struct cgroup_file field. cgroup will record the handle of * the created file into it. The recorded handle can be used as * long as the containing css remains accessible. */ unsigned int file_offset; /* * Fields used for internal bookkeeping. Initialized automatically * during registration. */ struct cgroup_subsys *ss; /* NULL for cgroup core files */ struct list_head node; /* anchored at ss->cfts */ struct kernfs_ops *kf_ops; int (*open)(struct kernfs_open_file *of); void (*release)(struct kernfs_open_file *of); /* * read_u64() is a shortcut for the common case of returning a * single integer. Use it in place of read() */ u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); /* * read_s64() is a signed version of read_u64() */ s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft); /* generic seq_file read interface */ int (*seq_show)(struct seq_file *sf, void *v); /* optional ops, implement all or none */ void *(*seq_start)(struct seq_file *sf, loff_t *ppos); void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); void (*seq_stop)(struct seq_file *sf, void *v); /* * write_u64() is a shortcut for the common case of accepting * a single integer (as parsed by simple_strtoull) from * userspace. Use in place of write(); return 0 or error. */ int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft, u64 val); /* * write_s64() is a signed version of write_u64() */ int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, s64 val); /* * write() is the generic write callback which maps directly to * kernfs write operation and overrides all other operations. * Maximum write size is determined by ->max_write_len. Use * of_css/cft() to access the associated css and cft. */ ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); __poll_t (*poll)(struct kernfs_open_file *of, struct poll_table_struct *pt); struct lock_class_key lockdep_key; }; /* * Control Group subsystem type. * See Documentation/admin-guide/cgroup-v1/cgroups.rst for details */ struct cgroup_subsys { struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); int (*css_online)(struct cgroup_subsys_state *css); void (*css_offline)(struct cgroup_subsys_state *css); void (*css_released)(struct cgroup_subsys_state *css); void (*css_free)(struct cgroup_subsys_state *css); void (*css_reset)(struct cgroup_subsys_state *css); void (*css_rstat_flush)(struct cgroup_subsys_state *css, int cpu); int (*css_extra_stat_show)(struct seq_file *seq, struct cgroup_subsys_state *css); int (*css_local_stat_show)(struct seq_file *seq, struct cgroup_subsys_state *css); int (*can_attach)(struct cgroup_taskset *tset); void (*cancel_attach)(struct cgroup_taskset *tset); void (*attach)(struct cgroup_taskset *tset); void (*post_attach)(void); int (*can_fork)(struct task_struct *task, struct css_set *cset); void (*cancel_fork)(struct task_struct *task, struct css_set *cset); void (*fork)(struct task_struct *task); void (*exit)(struct task_struct *task); void (*release)(struct task_struct *task); void (*bind)(struct cgroup_subsys_state *root_css); bool early_init:1; /* * If %true, the controller, on the default hierarchy, doesn't show * up in "cgroup.controllers" or "cgroup.subtree_control", is * implicitly enabled on all cgroups on the default hierarchy, and * bypasses the "no internal process" constraint. This is for * utility type controllers which is transparent to userland. * * An implicit controller can be stolen from the default hierarchy * anytime and thus must be okay with offline csses from previous * hierarchies coexisting with csses for the current one. */ bool implicit_on_dfl:1; /* * If %true, the controller, supports threaded mode on the default * hierarchy. In a threaded subtree, both process granularity and * no-internal-process constraint are ignored and a threaded * controllers should be able to handle that. * * Note that as an implicit controller is automatically enabled on * all cgroups on the default hierarchy, it should also be * threaded. implicit && !threaded is not supported. */ bool threaded:1; /* the following two fields are initialized automatically during boot */ int id; const char *name; /* optional, initialized automatically during boot if not set */ const char *legacy_name; /* link to parent, protected by cgroup_lock() */ struct cgroup_root *root; /* idr for css->id */ struct idr css_idr; /* * List of cftypes. Each entry is the first entry of an array * terminated by zero length name. */ struct list_head cfts; /* * Base cftypes which are automatically registered. The two can * point to the same array. */ struct cftype *dfl_cftypes; /* for the default hierarchy */ struct cftype *legacy_cftypes; /* for the legacy hierarchies */ /* * A subsystem may depend on other subsystems. When such subsystem * is enabled on a cgroup, the depended-upon subsystems are enabled * together if available. Subsystems enabled due to dependency are * not visible to userland until explicitly enabled. The following * specifies the mask of subsystems that this one depends on. */ unsigned int depends_on; }; extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; struct cgroup_of_peak { unsigned long value; struct list_head list; }; /** * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups * @tsk: target task * * Allows cgroup operations to synchronize against threadgroup changes * using a percpu_rw_semaphore. */ static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) { percpu_down_read(&cgroup_threadgroup_rwsem); } /** * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups * @tsk: target task * * Counterpart of cgroup_threadcgroup_change_begin(). */ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) { percpu_up_read(&cgroup_threadgroup_rwsem); } #else /* CONFIG_CGROUPS */ #define CGROUP_SUBSYS_COUNT 0 static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) { might_sleep(); } static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} #endif /* CONFIG_CGROUPS */ #ifdef CONFIG_SOCK_CGROUP_DATA /* * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains * per-socket cgroup information except for memcg association. * * On legacy hierarchies, net_prio and net_cls controllers directly * set attributes on each sock which can then be tested by the network * layer. On the default hierarchy, each sock is associated with the * cgroup it was created in and the networking layer can match the * cgroup directly. */ struct sock_cgroup_data { struct cgroup *cgroup; /* v2 */ #ifdef CONFIG_CGROUP_NET_CLASSID u32 classid; /* v1 */ #endif #ifdef CONFIG_CGROUP_NET_PRIO u16 prioidx; /* v1 */ #endif }; static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd) { #ifdef CONFIG_CGROUP_NET_PRIO return READ_ONCE(skcd->prioidx); #else return 1; #endif } static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd) { #ifdef CONFIG_CGROUP_NET_CLASSID return READ_ONCE(skcd->classid); #else return 0; #endif } static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, u16 prioidx) { #ifdef CONFIG_CGROUP_NET_PRIO WRITE_ONCE(skcd->prioidx, prioidx); #endif } static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd, u32 classid) { #ifdef CONFIG_CGROUP_NET_CLASSID WRITE_ONCE(skcd->classid, classid); #endif } #else /* CONFIG_SOCK_CGROUP_DATA */ struct sock_cgroup_data { }; #endif /* CONFIG_SOCK_CGROUP_DATA */ #endif /* _LINUX_CGROUP_DEFS_H */ |
| 2 2 113 44 2 37 10 2 39 43 15 19 30 86 86 86 2 16 24 61 24 59 24 77 10 83 1 16 58 58 16 41 1 8 3 2 56 3 10 47 4 13 114 15 114 220 139 125 41 40 73 40 110 5 102 13 18 2 20 12 8 2 18 15 33 60 11 20 9 10 20 15 5 9 72 41 176 31 99 118 19 23 73 40 250 224 42 241 21 250 21 24 7 32 4 30 1 24 14 24 7 4 1 22 2 2 24 9 19 18 1 17 2 2 2 61 61 61 6 21 11 4 15 12 6 6 8 46 27 19 19 1 17 5 3 3 3 16 16 2 6 5 13 13 15 15 10 11 14 1 5 2 2 3 6 6 5 1 1 4 6 6 6 5 3 3 7 6 5 4 4 4 2 2 4 2 2 2 4 3 2 2 2 1 1 15 15 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 | // SPDX-License-Identifier: GPL-2.0 /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * * TODO: Merge attr_set_size/attr_data_get_block/attr_allocate_frame? */ #include <linux/fs.h> #include <linux/slab.h> #include <linux/kernel.h> #include "debug.h" #include "ntfs.h" #include "ntfs_fs.h" /* * You can set external NTFS_MIN_LOG2_OF_CLUMP/NTFS_MAX_LOG2_OF_CLUMP to manage * preallocate algorithm. */ #ifndef NTFS_MIN_LOG2_OF_CLUMP #define NTFS_MIN_LOG2_OF_CLUMP 16 #endif #ifndef NTFS_MAX_LOG2_OF_CLUMP #define NTFS_MAX_LOG2_OF_CLUMP 26 #endif // 16M #define NTFS_CLUMP_MIN (1 << (NTFS_MIN_LOG2_OF_CLUMP + 8)) // 16G #define NTFS_CLUMP_MAX (1ull << (NTFS_MAX_LOG2_OF_CLUMP + 8)) static inline u64 get_pre_allocated(u64 size) { u32 clump; u8 align_shift; u64 ret; if (size <= NTFS_CLUMP_MIN) { clump = 1 << NTFS_MIN_LOG2_OF_CLUMP; align_shift = NTFS_MIN_LOG2_OF_CLUMP; } else if (size >= NTFS_CLUMP_MAX) { clump = 1 << NTFS_MAX_LOG2_OF_CLUMP; align_shift = NTFS_MAX_LOG2_OF_CLUMP; } else { align_shift = NTFS_MIN_LOG2_OF_CLUMP - 1 + __ffs(size >> (8 + NTFS_MIN_LOG2_OF_CLUMP)); clump = 1u << align_shift; } ret = (((size + clump - 1) >> align_shift)) << align_shift; return ret; } /* * attr_load_runs - Load all runs stored in @attr. */ static int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni, struct runs_tree *run, const CLST *vcn) { int err; CLST svcn = le64_to_cpu(attr->nres.svcn); CLST evcn = le64_to_cpu(attr->nres.evcn); u32 asize; u16 run_off; if (svcn >= evcn + 1 || run_is_mapped_full(run, svcn, evcn)) return 0; if (vcn && (evcn < *vcn || *vcn < svcn)) return -EINVAL; asize = le32_to_cpu(attr->size); run_off = le16_to_cpu(attr->nres.run_off); if (run_off > asize) return -EINVAL; err = run_unpack_ex(run, ni->mi.sbi, ni->mi.rno, svcn, evcn, vcn ? *vcn : svcn, Add2Ptr(attr, run_off), asize - run_off); if (err < 0) return err; return 0; } /* * run_deallocate_ex - Deallocate clusters. */ static int run_deallocate_ex(struct ntfs_sb_info *sbi, struct runs_tree *run, CLST vcn, CLST len, CLST *done, bool trim) { int err = 0; CLST vcn_next, vcn0 = vcn, lcn, clen, dn = 0; size_t idx; if (!len) goto out; if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) { failed: run_truncate(run, vcn0); err = -EINVAL; goto out; } for (;;) { if (clen > len) clen = len; if (!clen) { err = -EINVAL; goto out; } if (lcn != SPARSE_LCN) { if (sbi) { /* mark bitmap range [lcn + clen) as free and trim clusters. */ mark_as_free_ex(sbi, lcn, clen, trim); } dn += clen; } len -= clen; if (!len) break; vcn_next = vcn + clen; if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) || vcn != vcn_next) { /* Save memory - don't load entire run. */ goto failed; } } out: if (done) *done += dn; return err; } /* * attr_allocate_clusters - Find free space, mark it as used and store in @run. */ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, CLST vcn, CLST lcn, CLST len, CLST *pre_alloc, enum ALLOCATE_OPT opt, CLST *alen, const size_t fr, CLST *new_lcn, CLST *new_len) { int err; CLST flen, vcn0 = vcn, pre = pre_alloc ? *pre_alloc : 0; size_t cnt = run->count; for (;;) { err = ntfs_look_for_free_space(sbi, lcn, len + pre, &lcn, &flen, opt); if (err == -ENOSPC && pre) { pre = 0; if (*pre_alloc) *pre_alloc = 0; continue; } if (err) goto out; if (vcn == vcn0) { /* Return the first fragment. */ if (new_lcn) *new_lcn = lcn; if (new_len) *new_len = flen; } /* Add new fragment into run storage. */ if (!run_add_entry(run, vcn, lcn, flen, opt & ALLOCATE_MFT)) { /* Undo last 'ntfs_look_for_free_space' */ mark_as_free_ex(sbi, lcn, len, false); err = -ENOMEM; goto out; } if (opt & ALLOCATE_ZERO) { u8 shift = sbi->cluster_bits - SECTOR_SHIFT; err = blkdev_issue_zeroout(sbi->sb->s_bdev, (sector_t)lcn << shift, (sector_t)flen << shift, GFP_NOFS, 0); if (err) goto out; } vcn += flen; if (flen >= len || (opt & ALLOCATE_MFT) || (fr && run->count - cnt >= fr)) { *alen = vcn - vcn0; return 0; } len -= flen; } out: /* Undo 'ntfs_look_for_free_space' */ if (vcn - vcn0) { run_deallocate_ex(sbi, run, vcn0, vcn - vcn0, NULL, false); run_truncate(run, vcn0); } return err; } /* * attr_make_nonresident * * If page is not NULL - it is already contains resident data * and locked (called from ni_write_frame()). */ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr, struct ATTR_LIST_ENTRY *le, struct mft_inode *mi, u64 new_size, struct runs_tree *run, struct ATTRIB **ins_attr, struct page *page) { struct ntfs_sb_info *sbi; struct ATTRIB *attr_s; struct MFT_REC *rec; u32 used, asize, rsize, aoff; bool is_data; CLST len, alen; char *next; int err; if (attr->non_res) { *ins_attr = attr; return 0; } sbi = mi->sbi; rec = mi->mrec; attr_s = NULL; used = le32_to_cpu(rec->used); asize = le32_to_cpu(attr->size); next = Add2Ptr(attr, asize); aoff = PtrOffset(rec, attr); rsize = le32_to_cpu(attr->res.data_size); is_data = attr->type == ATTR_DATA && !attr->name_len; /* len - how many clusters required to store 'rsize' bytes */ if (is_attr_compressed(attr)) { u8 shift = sbi->cluster_bits + NTFS_LZNT_CUNIT; len = ((rsize + (1u << shift) - 1) >> shift) << NTFS_LZNT_CUNIT; } else { len = bytes_to_cluster(sbi, rsize); } run_init(run); /* Make a copy of original attribute. */ attr_s = kmemdup(attr, asize, GFP_NOFS); if (!attr_s) { err = -ENOMEM; goto out; } if (!len) { /* Empty resident -> Empty nonresident. */ alen = 0; } else { const char *data = resident_data(attr); err = attr_allocate_clusters(sbi, run, 0, 0, len, NULL, ALLOCATE_DEF, &alen, 0, NULL, NULL); if (err) goto out1; if (!rsize) { /* Empty resident -> Non empty nonresident. */ } else if (!is_data) { err = ntfs_sb_write_run(sbi, run, 0, data, rsize, 0); if (err) goto out2; } else if (!page) { struct address_space *mapping = ni->vfs_inode.i_mapping; struct folio *folio; folio = __filemap_get_folio( mapping, 0, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) { err = PTR_ERR(folio); goto out2; } folio_fill_tail(folio, 0, data, rsize); folio_mark_uptodate(folio); folio_mark_dirty(folio); folio_unlock(folio); folio_put(folio); } } /* Remove original attribute. */ used -= asize; memmove(attr, Add2Ptr(attr, asize), used - aoff); rec->used = cpu_to_le32(used); mi->dirty = true; if (le) al_remove_le(ni, le); err = ni_insert_nonresident(ni, attr_s->type, attr_name(attr_s), attr_s->name_len, run, 0, alen, attr_s->flags, &attr, NULL, NULL); if (err) goto out3; kfree(attr_s); attr->nres.data_size = cpu_to_le64(rsize); attr->nres.valid_size = attr->nres.data_size; *ins_attr = attr; if (is_data) ni->ni_flags &= ~NI_FLAG_RESIDENT; /* Resident attribute becomes non resident. */ return 0; out3: attr = Add2Ptr(rec, aoff); memmove(next, attr, used - aoff); memcpy(attr, attr_s, asize); rec->used = cpu_to_le32(used + asize); mi->dirty = true; out2: /* Undo: do not trim new allocated clusters. */ run_deallocate(sbi, run, false); run_close(run); out1: kfree(attr_s); out: return err; } /* * attr_set_size_res - Helper for attr_set_size(). */ static int attr_set_size_res(struct ntfs_inode *ni, struct ATTRIB *attr, struct ATTR_LIST_ENTRY *le, struct mft_inode *mi, u64 new_size, struct runs_tree *run, struct ATTRIB **ins_attr) { struct ntfs_sb_info *sbi = mi->sbi; struct MFT_REC *rec = mi->mrec; u32 used = le32_to_cpu(rec->used); u32 asize = le32_to_cpu(attr->size); u32 aoff = PtrOffset(rec, attr); u32 rsize = le32_to_cpu(attr->res.data_size); u32 tail = used - aoff - asize; char *next = Add2Ptr(attr, asize); s64 dsize = ALIGN(new_size, 8) - ALIGN(rsize, 8); if (dsize < 0) { memmove(next + dsize, next, tail); } else if (dsize > 0) { if (used + dsize > sbi->max_bytes_per_attr) return attr_make_nonresident(ni, attr, le, mi, new_size, run, ins_attr, NULL); memmove(next + dsize, next, tail); memset(next, 0, dsize); } if (new_size > rsize) memset(Add2Ptr(resident_data(attr), rsize), 0, new_size - rsize); rec->used = cpu_to_le32(used + dsize); attr->size = cpu_to_le32(asize + dsize); attr->res.data_size = cpu_to_le32(new_size); mi->dirty = true; *ins_attr = attr; return 0; } /* * attr_set_size - Change the size of attribute. * * Extend: * - Sparse/compressed: No allocated clusters. * - Normal: Append allocated and preallocated new clusters. * Shrink: * - No deallocate if @keep_prealloc is set. */ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, struct runs_tree *run, u64 new_size, const u64 *new_valid, bool keep_prealloc, struct ATTRIB **ret) { int err = 0; struct ntfs_sb_info *sbi = ni->mi.sbi; u8 cluster_bits = sbi->cluster_bits; bool is_mft = ni->mi.rno == MFT_REC_MFT && type == ATTR_DATA && !name_len; u64 old_valid, old_size, old_alloc, new_alloc, new_alloc_tmp; struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; CLST alen, vcn, lcn, new_alen, old_alen, svcn, evcn; CLST next_svcn, pre_alloc = -1, done = 0; bool is_ext, is_bad = false; bool dirty = false; u32 align; struct MFT_REC *rec; again: alen = 0; le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len, NULL, &mi_b); if (!attr_b) { err = -ENOENT; goto bad_inode; } if (!attr_b->non_res) { err = attr_set_size_res(ni, attr_b, le_b, mi_b, new_size, run, &attr_b); if (err) return err; /* Return if file is still resident. */ if (!attr_b->non_res) { dirty = true; goto ok1; } /* Layout of records may be changed, so do a full search. */ goto again; } is_ext = is_attr_ext(attr_b); align = sbi->cluster_size; if (is_ext) align <<= attr_b->nres.c_unit; old_valid = le64_to_cpu(attr_b->nres.valid_size); old_size = le64_to_cpu(attr_b->nres.data_size); old_alloc = le64_to_cpu(attr_b->nres.alloc_size); again_1: old_alen = old_alloc >> cluster_bits; new_alloc = (new_size + align - 1) & ~(u64)(align - 1); new_alen = new_alloc >> cluster_bits; if (keep_prealloc && new_size < old_size) { attr_b->nres.data_size = cpu_to_le64(new_size); mi_b->dirty = dirty = true; goto ok; } vcn = old_alen - 1; svcn = le64_to_cpu(attr_b->nres.svcn); evcn = le64_to_cpu(attr_b->nres.evcn); if (svcn <= vcn && vcn <= evcn) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { err = -EINVAL; goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, type, name, name_len, &vcn, &mi); if (!attr) { err = -EINVAL; goto bad_inode; } next_le_1: svcn = le64_to_cpu(attr->nres.svcn); evcn = le64_to_cpu(attr->nres.evcn); } /* * Here we have: * attr,mi,le - last attribute segment (containing 'vcn'). * attr_b,mi_b,le_b - base (primary) attribute segment. */ next_le: rec = mi->mrec; err = attr_load_runs(attr, ni, run, NULL); if (err) goto out; if (new_size > old_size) { CLST to_allocate; size_t free; if (new_alloc <= old_alloc) { attr_b->nres.data_size = cpu_to_le64(new_size); mi_b->dirty = dirty = true; goto ok; } /* * Add clusters. In simple case we have to: * - allocate space (vcn, lcn, len) * - update packed run in 'mi' * - update attr->nres.evcn * - update attr_b->nres.data_size/attr_b->nres.alloc_size */ to_allocate = new_alen - old_alen; add_alloc_in_same_attr_seg: lcn = 0; if (is_mft) { /* MFT allocates clusters from MFT zone. */ pre_alloc = 0; } else if (is_ext) { /* No preallocate for sparse/compress. */ pre_alloc = 0; } else if (pre_alloc == -1) { pre_alloc = 0; if (type == ATTR_DATA && !name_len && sbi->options->prealloc) { pre_alloc = bytes_to_cluster( sbi, get_pre_allocated( new_size)) - new_alen; } /* Get the last LCN to allocate from. */ if (old_alen && !run_lookup_entry(run, vcn, &lcn, NULL, NULL)) { lcn = SPARSE_LCN; } if (lcn == SPARSE_LCN) lcn = 0; else if (lcn) lcn += 1; free = wnd_zeroes(&sbi->used.bitmap); if (to_allocate > free) { err = -ENOSPC; goto out; } if (pre_alloc && to_allocate + pre_alloc > free) pre_alloc = 0; } vcn = old_alen; if (is_ext) { if (!run_add_entry(run, vcn, SPARSE_LCN, to_allocate, false)) { err = -ENOMEM; goto out; } alen = to_allocate; } else { /* ~3 bytes per fragment. */ err = attr_allocate_clusters( sbi, run, vcn, lcn, to_allocate, &pre_alloc, is_mft ? ALLOCATE_MFT : ALLOCATE_DEF, &alen, is_mft ? 0 : (sbi->record_size - le32_to_cpu(rec->used) + 8) / 3 + 1, NULL, NULL); if (err) goto out; } done += alen; vcn += alen; if (to_allocate > alen) to_allocate -= alen; else to_allocate = 0; pack_runs: err = mi_pack_runs(mi, attr, run, vcn - svcn); if (err) goto undo_1; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; new_alloc_tmp = (u64)next_svcn << cluster_bits; attr_b->nres.alloc_size = cpu_to_le64(new_alloc_tmp); mi_b->dirty = dirty = true; if (next_svcn >= vcn && !to_allocate) { /* Normal way. Update attribute and exit. */ attr_b->nres.data_size = cpu_to_le64(new_size); goto ok; } /* At least two MFT to avoid recursive loop. */ if (is_mft && next_svcn == vcn && ((u64)done << sbi->cluster_bits) >= 2 * sbi->record_size) { new_size = new_alloc_tmp; attr_b->nres.data_size = attr_b->nres.alloc_size; goto ok; } if (le32_to_cpu(rec->used) < sbi->record_size) { old_alen = next_svcn; evcn = old_alen - 1; goto add_alloc_in_same_attr_seg; } attr_b->nres.data_size = attr_b->nres.alloc_size; if (new_alloc_tmp < old_valid) attr_b->nres.valid_size = attr_b->nres.data_size; if (type == ATTR_LIST) { err = ni_expand_list(ni); if (err) goto undo_2; if (next_svcn < vcn) goto pack_runs; /* Layout of records is changed. */ goto again; } if (!ni->attr_list.size) { err = ni_create_attr_list(ni); /* In case of error layout of records is not changed. */ if (err) goto undo_2; /* Layout of records is changed. */ } if (next_svcn >= vcn) { /* This is MFT data, repeat. */ goto again; } /* Insert new attribute segment. */ err = ni_insert_nonresident(ni, type, name, name_len, run, next_svcn, vcn - next_svcn, attr_b->flags, &attr, &mi, NULL); /* * Layout of records maybe changed. * Find base attribute to update. */ le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len, NULL, &mi_b); if (!attr_b) { err = -EINVAL; goto bad_inode; } if (err) { /* ni_insert_nonresident failed. */ attr = NULL; goto undo_2; } /* keep runs for $MFT::$ATTR_DATA and $MFT::$ATTR_BITMAP. */ if (ni->mi.rno != MFT_REC_MFT) run_truncate_head(run, evcn + 1); svcn = le64_to_cpu(attr->nres.svcn); evcn = le64_to_cpu(attr->nres.evcn); /* * Attribute is in consistency state. * Save this point to restore to if next steps fail. */ old_valid = old_size = old_alloc = (u64)vcn << cluster_bits; attr_b->nres.valid_size = attr_b->nres.data_size = attr_b->nres.alloc_size = cpu_to_le64(old_size); mi_b->dirty = dirty = true; goto again_1; } if (new_size != old_size || (new_alloc != old_alloc && !keep_prealloc)) { /* * Truncate clusters. In simple case we have to: * - update packed run in 'mi' * - update attr->nres.evcn * - update attr_b->nres.data_size/attr_b->nres.alloc_size * - mark and trim clusters as free (vcn, lcn, len) */ CLST dlen = 0; vcn = max(svcn, new_alen); new_alloc_tmp = (u64)vcn << cluster_bits; if (vcn > svcn) { err = mi_pack_runs(mi, attr, run, vcn - svcn); if (err) goto out; } else if (le && le->vcn) { u16 le_sz = le16_to_cpu(le->size); /* * NOTE: List entries for one attribute are always * the same size. We deal with last entry (vcn==0) * and it is not first in entries array * (list entry for std attribute always first). * So it is safe to step back. */ mi_remove_attr(NULL, mi, attr); if (!al_remove_le(ni, le)) { err = -EINVAL; goto bad_inode; } le = (struct ATTR_LIST_ENTRY *)((u8 *)le - le_sz); } else { attr->nres.evcn = cpu_to_le64((u64)vcn - 1); mi->dirty = true; } attr_b->nres.alloc_size = cpu_to_le64(new_alloc_tmp); if (vcn == new_alen) { attr_b->nres.data_size = cpu_to_le64(new_size); if (new_size < old_valid) attr_b->nres.valid_size = attr_b->nres.data_size; } else { if (new_alloc_tmp <= le64_to_cpu(attr_b->nres.data_size)) attr_b->nres.data_size = attr_b->nres.alloc_size; if (new_alloc_tmp < le64_to_cpu(attr_b->nres.valid_size)) attr_b->nres.valid_size = attr_b->nres.alloc_size; } mi_b->dirty = dirty = true; err = run_deallocate_ex(sbi, run, vcn, evcn - vcn + 1, &dlen, true); if (err) goto out; if (is_ext) { /* dlen - really deallocated clusters. */ le64_sub_cpu(&attr_b->nres.total_size, ((u64)dlen << cluster_bits)); } run_truncate(run, vcn); if (new_alloc_tmp <= new_alloc) goto ok; old_size = new_alloc_tmp; vcn = svcn - 1; if (le == le_b) { attr = attr_b; mi = mi_b; evcn = svcn - 1; svcn = 0; goto next_le; } if (le->type != type || le->name_len != name_len || memcmp(le_name(le), name, name_len * sizeof(short))) { err = -EINVAL; goto bad_inode; } err = ni_load_mi(ni, le, &mi); if (err) goto out; attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id); if (!attr) { err = -EINVAL; goto bad_inode; } goto next_le_1; } ok: if (new_valid) { __le64 valid = cpu_to_le64(min(*new_valid, new_size)); if (attr_b->nres.valid_size != valid) { attr_b->nres.valid_size = valid; mi_b->dirty = true; } } ok1: if (ret) *ret = attr_b; if (((type == ATTR_DATA && !name_len) || (type == ATTR_ALLOC && name == I30_NAME))) { /* Update inode_set_bytes. */ if (attr_b->non_res) { new_alloc = le64_to_cpu(attr_b->nres.alloc_size); if (inode_get_bytes(&ni->vfs_inode) != new_alloc) { inode_set_bytes(&ni->vfs_inode, new_alloc); dirty = true; } } /* Don't forget to update duplicate information in parent. */ if (dirty) { ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mark_inode_dirty(&ni->vfs_inode); } } return 0; undo_2: vcn -= alen; attr_b->nres.data_size = cpu_to_le64(old_size); attr_b->nres.valid_size = cpu_to_le64(old_valid); attr_b->nres.alloc_size = cpu_to_le64(old_alloc); /* Restore 'attr' and 'mi'. */ if (attr) goto restore_run; if (le64_to_cpu(attr_b->nres.svcn) <= svcn && svcn <= le64_to_cpu(attr_b->nres.evcn)) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { err = -EINVAL; goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, type, name, name_len, &svcn, &mi); if (!attr) goto bad_inode; } restore_run: if (mi_pack_runs(mi, attr, run, evcn - svcn + 1)) is_bad = true; undo_1: run_deallocate_ex(sbi, run, vcn, alen, NULL, false); run_truncate(run, vcn); out: if (is_bad) { bad_inode: _ntfs_bad_inode(&ni->vfs_inode); } return err; } /* * attr_data_get_block - Returns 'lcn' and 'len' for given 'vcn'. * * @new == NULL means just to get current mapping for 'vcn' * @new != NULL means allocate real cluster if 'vcn' maps to hole * @zero - zeroout new allocated clusters * * NOTE: * - @new != NULL is called only for sparsed or compressed attributes. * - new allocated clusters are zeroed via blkdev_issue_zeroout. */ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, CLST *len, bool *new, bool zero) { int err = 0; struct runs_tree *run = &ni->file.run; struct ntfs_sb_info *sbi; u8 cluster_bits; struct ATTRIB *attr, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; CLST hint, svcn, to_alloc, evcn1, next_svcn, asize, end, vcn0, alen; CLST alloc, evcn; unsigned fr; u64 total_size, total_size0; int step = 0; if (new) *new = false; /* Try to find in cache. */ down_read(&ni->file.run_lock); if (!run_lookup_entry(run, vcn, lcn, len, NULL)) *len = 0; up_read(&ni->file.run_lock); if (*len && (*lcn != SPARSE_LCN || !new)) return 0; /* Fast normal way without allocation. */ /* No cluster in cache or we need to allocate cluster in hole. */ sbi = ni->mi.sbi; cluster_bits = sbi->cluster_bits; ni_lock(ni); down_write(&ni->file.run_lock); /* Repeat the code above (under write lock). */ if (!run_lookup_entry(run, vcn, lcn, len, NULL)) *len = 0; if (*len) { if (*lcn != SPARSE_LCN || !new) goto out; /* normal way without allocation. */ if (clen > *len) clen = *len; } le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -ENOENT; goto out; } if (!attr_b->non_res) { *lcn = RESIDENT_LCN; *len = 1; goto out; } asize = le64_to_cpu(attr_b->nres.alloc_size) >> cluster_bits; if (vcn >= asize) { if (new) { err = -EINVAL; } else { *len = 1; *lcn = SPARSE_LCN; } goto out; } svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; attr = attr_b; le = le_b; mi = mi_b; if (le_b && (vcn < svcn || evcn1 <= vcn)) { attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { err = -EINVAL; goto out; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } /* Load in cache actual information. */ err = attr_load_runs(attr, ni, run, NULL); if (err) goto out; /* Check for compressed frame. */ err = attr_is_frame_compressed(ni, attr_b, vcn >> NTFS_LZNT_CUNIT, &hint); if (err) goto out; if (hint) { /* if frame is compressed - don't touch it. */ *lcn = COMPRESSED_LCN; /* length to the end of frame. */ *len = NTFS_LZNT_CLUSTERS - (vcn & (NTFS_LZNT_CLUSTERS - 1)); err = 0; goto out; } if (!*len) { if (run_lookup_entry(run, vcn, lcn, len, NULL)) { if (*lcn != SPARSE_LCN || !new) goto ok; /* Slow normal way without allocation. */ if (clen > *len) clen = *len; } else if (!new) { /* Here we may return -ENOENT. * In any case caller gets zero length. */ goto ok; } } if (!is_attr_ext(attr_b)) { /* The code below only for sparsed or compressed attributes. */ err = -EINVAL; goto out; } vcn0 = vcn; to_alloc = clen; fr = (sbi->record_size - le32_to_cpu(mi->mrec->used) + 8) / 3 + 1; /* Allocate frame aligned clusters. * ntfs.sys usually uses 16 clusters per frame for sparsed or compressed. * ntfs3 uses 1 cluster per frame for new created sparsed files. */ if (attr_b->nres.c_unit) { CLST clst_per_frame = 1u << attr_b->nres.c_unit; CLST cmask = ~(clst_per_frame - 1); /* Get frame aligned vcn and to_alloc. */ vcn = vcn0 & cmask; to_alloc = ((vcn0 + clen + clst_per_frame - 1) & cmask) - vcn; if (fr < clst_per_frame) fr = clst_per_frame; zero = true; /* Check if 'vcn' and 'vcn0' in different attribute segments. */ if (vcn < svcn || evcn1 <= vcn) { struct ATTRIB *attr2; /* Load runs for truncated vcn. */ attr2 = ni_find_attr(ni, attr_b, &le_b, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr2) { err = -EINVAL; goto out; } evcn1 = le64_to_cpu(attr2->nres.evcn) + 1; err = attr_load_runs(attr2, ni, run, NULL); if (err) goto out; } } if (vcn + to_alloc > asize) to_alloc = asize - vcn; /* Get the last LCN to allocate from. */ hint = 0; if (vcn > evcn1) { if (!run_add_entry(run, evcn1, SPARSE_LCN, vcn - evcn1, false)) { err = -ENOMEM; goto out; } } else if (vcn && !run_lookup_entry(run, vcn - 1, &hint, NULL, NULL)) { hint = -1; } /* Allocate and zeroout new clusters. */ err = attr_allocate_clusters(sbi, run, vcn, hint + 1, to_alloc, NULL, zero ? ALLOCATE_ZERO : ALLOCATE_DEF, &alen, fr, lcn, len); if (err) goto out; *new = true; step = 1; end = vcn + alen; /* Save 'total_size0' to restore if error. */ total_size0 = le64_to_cpu(attr_b->nres.total_size); total_size = total_size0 + ((u64)alen << cluster_bits); if (vcn != vcn0) { if (!run_lookup_entry(run, vcn0, lcn, len, NULL)) { err = -EINVAL; goto out; } if (*lcn == SPARSE_LCN) { /* Internal error. Should not happened. */ WARN_ON(1); err = -EINVAL; goto out; } /* Check case when vcn0 + len overlaps new allocated clusters. */ if (vcn0 + *len > end) *len = end - vcn0; } repack: err = mi_pack_runs(mi, attr, run, max(end, evcn1) - svcn); if (err) goto out; attr_b->nres.total_size = cpu_to_le64(total_size); inode_set_bytes(&ni->vfs_inode, total_size); ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mi_b->dirty = true; mark_inode_dirty(&ni->vfs_inode); /* Stored [vcn : next_svcn) from [vcn : end). */ next_svcn = le64_to_cpu(attr->nres.evcn) + 1; if (end <= evcn1) { if (next_svcn == evcn1) { /* Normal way. Update attribute and exit. */ goto ok; } /* Add new segment [next_svcn : evcn1 - next_svcn). */ if (!ni->attr_list.size) { err = ni_create_attr_list(ni); if (err) goto undo1; /* Layout of records is changed. */ le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -ENOENT; goto out; } attr = attr_b; le = le_b; mi = mi_b; goto repack; } } /* * The code below may require additional cluster (to extend attribute list) * and / or one MFT record * It is too complex to undo operations if -ENOSPC occurs deep inside * in 'ni_insert_nonresident'. * Return in advance -ENOSPC here if there are no free cluster and no free MFT. */ if (!ntfs_check_for_free_space(sbi, 1, 1)) { /* Undo step 1. */ err = -ENOSPC; goto undo1; } step = 2; svcn = evcn1; /* Estimate next attribute. */ attr = ni_find_attr(ni, attr, &le, ATTR_DATA, NULL, 0, &svcn, &mi); if (!attr) { /* Insert new attribute segment. */ goto ins_ext; } /* Try to update existed attribute segment. */ alloc = bytes_to_cluster(sbi, le64_to_cpu(attr_b->nres.alloc_size)); evcn = le64_to_cpu(attr->nres.evcn); if (end < next_svcn) end = next_svcn; while (end > evcn) { /* Remove segment [svcn : evcn). */ mi_remove_attr(NULL, mi, attr); if (!al_remove_le(ni, le)) { err = -EINVAL; goto out; } if (evcn + 1 >= alloc) { /* Last attribute segment. */ evcn1 = evcn + 1; goto ins_ext; } if (ni_load_mi(ni, le, &mi)) { attr = NULL; goto out; } attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, &le->id); if (!attr) { err = -EINVAL; goto out; } svcn = le64_to_cpu(attr->nres.svcn); evcn = le64_to_cpu(attr->nres.evcn); } if (end < svcn) end = svcn; err = attr_load_runs(attr, ni, run, &end); if (err) goto out; evcn1 = evcn + 1; attr->nres.svcn = cpu_to_le64(next_svcn); err = mi_pack_runs(mi, attr, run, evcn1 - next_svcn); if (err) goto out; le->vcn = cpu_to_le64(next_svcn); ni->attr_list.dirty = true; mi->dirty = true; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; ins_ext: if (evcn1 > next_svcn) { err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - next_svcn, attr_b->flags, &attr, &mi, NULL); if (err) goto out; } ok: run_truncate_around(run, vcn); out: if (err && step > 1) { /* Too complex to restore. */ _ntfs_bad_inode(&ni->vfs_inode); } up_write(&ni->file.run_lock); ni_unlock(ni); return err; undo1: /* Undo step1. */ attr_b->nres.total_size = cpu_to_le64(total_size0); inode_set_bytes(&ni->vfs_inode, total_size0); if (run_deallocate_ex(sbi, run, vcn, alen, NULL, false) || !run_add_entry(run, vcn, SPARSE_LCN, alen, false) || mi_pack_runs(mi, attr, run, max(end, evcn1) - svcn)) { _ntfs_bad_inode(&ni->vfs_inode); } goto out; } int attr_data_read_resident(struct ntfs_inode *ni, struct folio *folio) { u64 vbo; struct ATTRIB *attr; u32 data_size; size_t len; attr = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, NULL); if (!attr) return -EINVAL; if (attr->non_res) return E_NTFS_NONRESIDENT; vbo = folio->index << PAGE_SHIFT; data_size = le32_to_cpu(attr->res.data_size); if (vbo > data_size) len = 0; else len = min(data_size - vbo, folio_size(folio)); folio_fill_tail(folio, 0, resident_data(attr) + vbo, len); folio_mark_uptodate(folio); return 0; } int attr_data_write_resident(struct ntfs_inode *ni, struct folio *folio) { u64 vbo; struct mft_inode *mi; struct ATTRIB *attr; u32 data_size; attr = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, &mi); if (!attr) return -EINVAL; if (attr->non_res) { /* Return special error code to check this case. */ return E_NTFS_NONRESIDENT; } vbo = folio->index << PAGE_SHIFT; data_size = le32_to_cpu(attr->res.data_size); if (vbo < data_size) { char *data = resident_data(attr); size_t len = min(data_size - vbo, folio_size(folio)); memcpy_from_folio(data + vbo, folio, 0, len); mi->dirty = true; } ni->i_valid = data_size; return 0; } /* * attr_load_runs_vcn - Load runs with VCN. */ int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, struct runs_tree *run, CLST vcn) { struct ATTRIB *attr; int err; CLST svcn, evcn; u16 ro; if (!ni) { /* Is record corrupted? */ return -ENOENT; } attr = ni_find_attr(ni, NULL, NULL, type, name, name_len, &vcn, NULL); if (!attr) { /* Is record corrupted? */ return -ENOENT; } svcn = le64_to_cpu(attr->nres.svcn); evcn = le64_to_cpu(attr->nres.evcn); if (evcn < vcn || vcn < svcn) { /* Is record corrupted? */ return -EINVAL; } ro = le16_to_cpu(attr->nres.run_off); if (ro > le32_to_cpu(attr->size)) return -EINVAL; err = run_unpack_ex(run, ni->mi.sbi, ni->mi.rno, svcn, evcn, svcn, Add2Ptr(attr, ro), le32_to_cpu(attr->size) - ro); if (err < 0) return err; return 0; } /* * attr_load_runs_range - Load runs for given range [from to). */ int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, struct runs_tree *run, u64 from, u64 to) { struct ntfs_sb_info *sbi = ni->mi.sbi; u8 cluster_bits = sbi->cluster_bits; CLST vcn; CLST vcn_last = (to - 1) >> cluster_bits; CLST lcn, clen; int err; for (vcn = from >> cluster_bits; vcn <= vcn_last; vcn += clen) { if (!run_lookup_entry(run, vcn, &lcn, &clen, NULL)) { err = attr_load_runs_vcn(ni, type, name, name_len, run, vcn); if (err) return err; clen = 0; /* Next run_lookup_entry(vcn) must be success. */ } } return 0; } #ifdef CONFIG_NTFS3_LZX_XPRESS /* * attr_wof_frame_info * * Read header of Xpress/LZX file to get info about frame. */ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr, struct runs_tree *run, u64 frame, u64 frames, u8 frame_bits, u32 *ondisk_size, u64 *vbo_data) { struct ntfs_sb_info *sbi = ni->mi.sbi; u64 vbo[2], off[2], wof_size; u32 voff; u8 bytes_per_off; char *addr; struct folio *folio; int i, err; __le32 *off32; __le64 *off64; if (ni->vfs_inode.i_size < 0x100000000ull) { /* File starts with array of 32 bit offsets. */ bytes_per_off = sizeof(__le32); vbo[1] = frame << 2; *vbo_data = frames << 2; } else { /* File starts with array of 64 bit offsets. */ bytes_per_off = sizeof(__le64); vbo[1] = frame << 3; *vbo_data = frames << 3; } /* * Read 4/8 bytes at [vbo - 4(8)] == offset where compressed frame starts. * Read 4/8 bytes at [vbo] == offset where compressed frame ends. */ if (!attr->non_res) { if (vbo[1] + bytes_per_off > le32_to_cpu(attr->res.data_size)) { ntfs_inode_err(&ni->vfs_inode, "is corrupted"); return -EINVAL; } addr = resident_data(attr); if (bytes_per_off == sizeof(__le32)) { off32 = Add2Ptr(addr, vbo[1]); off[0] = vbo[1] ? le32_to_cpu(off32[-1]) : 0; off[1] = le32_to_cpu(off32[0]); } else { off64 = Add2Ptr(addr, vbo[1]); off[0] = vbo[1] ? le64_to_cpu(off64[-1]) : 0; off[1] = le64_to_cpu(off64[0]); } *vbo_data += off[0]; *ondisk_size = off[1] - off[0]; return 0; } wof_size = le64_to_cpu(attr->nres.data_size); down_write(&ni->file.run_lock); folio = ni->file.offs_folio; if (!folio) { folio = folio_alloc(GFP_KERNEL, 0); if (!folio) { err = -ENOMEM; goto out; } folio->index = -1; ni->file.offs_folio = folio; } folio_lock(folio); addr = folio_address(folio); if (vbo[1]) { voff = vbo[1] & (PAGE_SIZE - 1); vbo[0] = vbo[1] - bytes_per_off; i = 0; } else { voff = 0; vbo[0] = 0; off[0] = 0; i = 1; } do { pgoff_t index = vbo[i] >> PAGE_SHIFT; if (index != folio->index) { struct page *page = &folio->page; u64 from = vbo[i] & ~(u64)(PAGE_SIZE - 1); u64 to = min(from + PAGE_SIZE, wof_size); err = attr_load_runs_range(ni, ATTR_DATA, WOF_NAME, ARRAY_SIZE(WOF_NAME), run, from, to); if (err) goto out1; err = ntfs_bio_pages(sbi, run, &page, 1, from, to - from, REQ_OP_READ); if (err) { folio->index = -1; goto out1; } folio->index = index; } if (i) { if (bytes_per_off == sizeof(__le32)) { off32 = Add2Ptr(addr, voff); off[1] = le32_to_cpu(*off32); } else { off64 = Add2Ptr(addr, voff); off[1] = le64_to_cpu(*off64); } } else if (!voff) { if (bytes_per_off == sizeof(__le32)) { off32 = Add2Ptr(addr, PAGE_SIZE - sizeof(u32)); off[0] = le32_to_cpu(*off32); } else { off64 = Add2Ptr(addr, PAGE_SIZE - sizeof(u64)); off[0] = le64_to_cpu(*off64); } } else { /* Two values in one page. */ if (bytes_per_off == sizeof(__le32)) { off32 = Add2Ptr(addr, voff); off[0] = le32_to_cpu(off32[-1]); off[1] = le32_to_cpu(off32[0]); } else { off64 = Add2Ptr(addr, voff); off[0] = le64_to_cpu(off64[-1]); off[1] = le64_to_cpu(off64[0]); } break; } } while (++i < 2); *vbo_data += off[0]; *ondisk_size = off[1] - off[0]; out1: folio_unlock(folio); out: up_write(&ni->file.run_lock); return err; } #endif /* * attr_is_frame_compressed - Used to detect compressed frame. * * attr - base (primary) attribute segment. * Only base segments contains valid 'attr->nres.c_unit' */ int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr, CLST frame, CLST *clst_data) { int err; u32 clst_frame; CLST clen, lcn, vcn, alen, slen, vcn_next; size_t idx; struct runs_tree *run; *clst_data = 0; if (!is_attr_compressed(attr)) return 0; if (!attr->non_res) return 0; clst_frame = 1u << attr->nres.c_unit; vcn = frame * clst_frame; run = &ni->file.run; if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) { err = attr_load_runs_vcn(ni, attr->type, attr_name(attr), attr->name_len, run, vcn); if (err) return err; if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) return -EINVAL; } if (lcn == SPARSE_LCN) { /* Sparsed frame. */ return 0; } if (clen >= clst_frame) { /* * The frame is not compressed 'cause * it does not contain any sparse clusters. */ *clst_data = clst_frame; return 0; } alen = bytes_to_cluster(ni->mi.sbi, le64_to_cpu(attr->nres.alloc_size)); slen = 0; *clst_data = clen; /* * The frame is compressed if *clst_data + slen >= clst_frame. * Check next fragments. */ while ((vcn += clen) < alen) { vcn_next = vcn; if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) || vcn_next != vcn) { err = attr_load_runs_vcn(ni, attr->type, attr_name(attr), attr->name_len, run, vcn_next); if (err) return err; vcn = vcn_next; if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) return -EINVAL; } if (lcn == SPARSE_LCN) { slen += clen; } else { if (slen) { /* * Data_clusters + sparse_clusters = * not enough for frame. */ return -EINVAL; } *clst_data += clen; } if (*clst_data + slen >= clst_frame) { if (!slen) { /* * There is no sparsed clusters in this frame * so it is not compressed. */ *clst_data = clst_frame; } else { /* Frame is compressed. */ } break; } } return 0; } /* * attr_allocate_frame - Allocate/free clusters for @frame. * * Assumed: down_write(&ni->file.run_lock); */ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size, u64 new_valid) { int err = 0; struct runs_tree *run = &ni->file.run; struct ntfs_sb_info *sbi = ni->mi.sbi; struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; CLST svcn, evcn1, next_svcn, len; CLST vcn, end, clst_data; u64 total_size, valid_size, data_size; le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) return -ENOENT; if (!is_attr_ext(attr_b)) return -EINVAL; vcn = frame << NTFS_LZNT_CUNIT; total_size = le64_to_cpu(attr_b->nres.total_size); svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; data_size = le64_to_cpu(attr_b->nres.data_size); if (svcn <= vcn && vcn < evcn1) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { err = -EINVAL; goto out; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { err = -EINVAL; goto out; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } err = attr_load_runs(attr, ni, run, NULL); if (err) goto out; err = attr_is_frame_compressed(ni, attr_b, frame, &clst_data); if (err) goto out; total_size -= (u64)clst_data << sbi->cluster_bits; len = bytes_to_cluster(sbi, compr_size); if (len == clst_data) goto out; if (len < clst_data) { err = run_deallocate_ex(sbi, run, vcn + len, clst_data - len, NULL, true); if (err) goto out; if (!run_add_entry(run, vcn + len, SPARSE_LCN, clst_data - len, false)) { err = -ENOMEM; goto out; } end = vcn + clst_data; /* Run contains updated range [vcn + len : end). */ } else { CLST alen, hint = 0; /* Get the last LCN to allocate from. */ if (vcn + clst_data && !run_lookup_entry(run, vcn + clst_data - 1, &hint, NULL, NULL)) { hint = -1; } err = attr_allocate_clusters(sbi, run, vcn + clst_data, hint + 1, len - clst_data, NULL, ALLOCATE_DEF, &alen, 0, NULL, NULL); if (err) goto out; end = vcn + len; /* Run contains updated range [vcn + clst_data : end). */ } total_size += (u64)len << sbi->cluster_bits; repack: err = mi_pack_runs(mi, attr, run, max(end, evcn1) - svcn); if (err) goto out; attr_b->nres.total_size = cpu_to_le64(total_size); inode_set_bytes(&ni->vfs_inode, total_size); ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mi_b->dirty = true; mark_inode_dirty(&ni->vfs_inode); /* Stored [vcn : next_svcn) from [vcn : end). */ next_svcn = le64_to_cpu(attr->nres.evcn) + 1; if (end <= evcn1) { if (next_svcn == evcn1) { /* Normal way. Update attribute and exit. */ goto ok; } /* Add new segment [next_svcn : evcn1 - next_svcn). */ if (!ni->attr_list.size) { err = ni_create_attr_list(ni); if (err) goto out; /* Layout of records is changed. */ le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -ENOENT; goto out; } attr = attr_b; le = le_b; mi = mi_b; goto repack; } } svcn = evcn1; /* Estimate next attribute. */ attr = ni_find_attr(ni, attr, &le, ATTR_DATA, NULL, 0, &svcn, &mi); if (attr) { CLST alloc = bytes_to_cluster( sbi, le64_to_cpu(attr_b->nres.alloc_size)); CLST evcn = le64_to_cpu(attr->nres.evcn); if (end < next_svcn) end = next_svcn; while (end > evcn) { /* Remove segment [svcn : evcn). */ mi_remove_attr(NULL, mi, attr); if (!al_remove_le(ni, le)) { err = -EINVAL; goto out; } if (evcn + 1 >= alloc) { /* Last attribute segment. */ evcn1 = evcn + 1; goto ins_ext; } if (ni_load_mi(ni, le, &mi)) { attr = NULL; goto out; } attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, &le->id); if (!attr) { err = -EINVAL; goto out; } svcn = le64_to_cpu(attr->nres.svcn); evcn = le64_to_cpu(attr->nres.evcn); } if (end < svcn) end = svcn; err = attr_load_runs(attr, ni, run, &end); if (err) goto out; evcn1 = evcn + 1; attr->nres.svcn = cpu_to_le64(next_svcn); err = mi_pack_runs(mi, attr, run, evcn1 - next_svcn); if (err) goto out; le->vcn = cpu_to_le64(next_svcn); ni->attr_list.dirty = true; mi->dirty = true; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; } ins_ext: if (evcn1 > next_svcn) { err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - next_svcn, attr_b->flags, &attr, &mi, NULL); if (err) goto out; } ok: run_truncate_around(run, vcn); out: if (attr_b) { if (new_valid > data_size) new_valid = data_size; valid_size = le64_to_cpu(attr_b->nres.valid_size); if (new_valid != valid_size) { attr_b->nres.valid_size = cpu_to_le64(valid_size); mi_b->dirty = true; } } return err; } /* * attr_collapse_range - Collapse range in file. */ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes) { int err = 0; struct runs_tree *run = &ni->file.run; struct ntfs_sb_info *sbi = ni->mi.sbi; struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; CLST svcn, evcn1, len, dealloc, alen; CLST vcn, end; u64 valid_size, data_size, alloc_size, total_size; u32 mask; __le16 a_flags; if (!bytes) return 0; le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) return -ENOENT; if (!attr_b->non_res) { /* Attribute is resident. Nothing to do? */ return 0; } data_size = le64_to_cpu(attr_b->nres.data_size); alloc_size = le64_to_cpu(attr_b->nres.alloc_size); a_flags = attr_b->flags; if (is_attr_ext(attr_b)) { total_size = le64_to_cpu(attr_b->nres.total_size); mask = (sbi->cluster_size << attr_b->nres.c_unit) - 1; } else { total_size = alloc_size; mask = sbi->cluster_mask; } if ((vbo & mask) || (bytes & mask)) { /* Allow to collapse only cluster aligned ranges. */ return -EINVAL; } if (vbo > data_size) return -EINVAL; down_write(&ni->file.run_lock); if (vbo + bytes >= data_size) { u64 new_valid = min(ni->i_valid, vbo); /* Simple truncate file at 'vbo'. */ truncate_setsize(&ni->vfs_inode, vbo); err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, vbo, &new_valid, true, NULL); if (!err && new_valid < ni->i_valid) ni->i_valid = new_valid; goto out; } /* * Enumerate all attribute segments and collapse. */ alen = alloc_size >> sbi->cluster_bits; vcn = vbo >> sbi->cluster_bits; len = bytes >> sbi->cluster_bits; end = vcn + len; dealloc = 0; svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; if (svcn <= vcn && vcn < evcn1) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { err = -EINVAL; goto out; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { err = -EINVAL; goto out; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } for (;;) { if (svcn >= end) { /* Shift VCN- */ attr->nres.svcn = cpu_to_le64(svcn - len); attr->nres.evcn = cpu_to_le64(evcn1 - 1 - len); if (le) { le->vcn = attr->nres.svcn; ni->attr_list.dirty = true; } mi->dirty = true; } else if (svcn < vcn || end < evcn1) { CLST vcn1, eat, next_svcn; /* Collapse a part of this attribute segment. */ err = attr_load_runs(attr, ni, run, &svcn); if (err) goto out; vcn1 = max(vcn, svcn); eat = min(end, evcn1) - vcn1; err = run_deallocate_ex(sbi, run, vcn1, eat, &dealloc, true); if (err) goto out; if (!run_collapse_range(run, vcn1, eat)) { err = -ENOMEM; goto out; } if (svcn >= vcn) { /* Shift VCN */ attr->nres.svcn = cpu_to_le64(vcn); if (le) { le->vcn = attr->nres.svcn; ni->attr_list.dirty = true; } } err = mi_pack_runs(mi, attr, run, evcn1 - svcn - eat); if (err) goto out; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; if (next_svcn + eat < evcn1) { err = ni_insert_nonresident( ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - eat - next_svcn, a_flags, &attr, &mi, &le); if (err) goto out; /* Layout of records maybe changed. */ attr_b = NULL; } /* Free all allocated memory. */ run_truncate(run, 0); } else { u16 le_sz; u16 roff = le16_to_cpu(attr->nres.run_off); if (roff > le32_to_cpu(attr->size)) { err = -EINVAL; goto out; } run_unpack_ex(RUN_DEALLOCATE, sbi, ni->mi.rno, svcn, evcn1 - 1, svcn, Add2Ptr(attr, roff), le32_to_cpu(attr->size) - roff); /* Delete this attribute segment. */ mi_remove_attr(NULL, mi, attr); if (!le) break; le_sz = le16_to_cpu(le->size); if (!al_remove_le(ni, le)) { err = -EINVAL; goto out; } if (evcn1 >= alen) break; if (!svcn) { /* Load next record that contains this attribute. */ if (ni_load_mi(ni, le, &mi)) { err = -EINVAL; goto out; } /* Look for required attribute. */ attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, &le->id); if (!attr) { err = -EINVAL; goto out; } goto next_attr; } le = (struct ATTR_LIST_ENTRY *)((u8 *)le - le_sz); } if (evcn1 >= alen) break; attr = ni_enum_attr_ex(ni, attr, &le, &mi); if (!attr) { err = -EINVAL; goto out; } next_attr: svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } if (!attr_b) { le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -ENOENT; goto out; } } data_size -= bytes; valid_size = ni->i_valid; if (vbo + bytes <= valid_size) valid_size -= bytes; else if (vbo < valid_size) valid_size = vbo; attr_b->nres.alloc_size = cpu_to_le64(alloc_size - bytes); attr_b->nres.data_size = cpu_to_le64(data_size); attr_b->nres.valid_size = cpu_to_le64(min(valid_size, data_size)); total_size -= (u64)dealloc << sbi->cluster_bits; if (is_attr_ext(attr_b)) attr_b->nres.total_size = cpu_to_le64(total_size); mi_b->dirty = true; /* Update inode size. */ ni->i_valid = valid_size; i_size_write(&ni->vfs_inode, data_size); inode_set_bytes(&ni->vfs_inode, total_size); ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mark_inode_dirty(&ni->vfs_inode); out: up_write(&ni->file.run_lock); if (err) _ntfs_bad_inode(&ni->vfs_inode); return err; } /* * attr_punch_hole * * Not for normal files. */ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) { int err = 0; struct runs_tree *run = &ni->file.run; struct ntfs_sb_info *sbi = ni->mi.sbi; struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; CLST svcn, evcn1, vcn, len, end, alen, hole, next_svcn; u64 total_size, alloc_size; u32 mask; __le16 a_flags; struct runs_tree run2; if (!bytes) return 0; le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) return -ENOENT; if (!attr_b->non_res) { u32 data_size = le32_to_cpu(attr_b->res.data_size); u32 from, to; if (vbo > data_size) return 0; from = vbo; to = min_t(u64, vbo + bytes, data_size); memset(Add2Ptr(resident_data(attr_b), from), 0, to - from); return 0; } if (!is_attr_ext(attr_b)) return -EOPNOTSUPP; alloc_size = le64_to_cpu(attr_b->nres.alloc_size); total_size = le64_to_cpu(attr_b->nres.total_size); if (vbo >= alloc_size) { /* NOTE: It is allowed. */ return 0; } mask = (sbi->cluster_size << attr_b->nres.c_unit) - 1; bytes += vbo; if (bytes > alloc_size) bytes = alloc_size; bytes -= vbo; if ((vbo & mask) || (bytes & mask)) { /* We have to zero a range(s). */ if (frame_size == NULL) { /* Caller insists range is aligned. */ return -EINVAL; } *frame_size = mask + 1; return E_NTFS_NOTALIGNED; } down_write(&ni->file.run_lock); run_init(&run2); run_truncate(run, 0); /* * Enumerate all attribute segments and punch hole where necessary. */ alen = alloc_size >> sbi->cluster_bits; vcn = vbo >> sbi->cluster_bits; len = bytes >> sbi->cluster_bits; end = vcn + len; hole = 0; svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; a_flags = attr_b->flags; if (svcn <= vcn && vcn < evcn1) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { err = -EINVAL; goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { err = -EINVAL; goto bad_inode; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } while (svcn < end) { CLST vcn1, zero, hole2 = hole; err = attr_load_runs(attr, ni, run, &svcn); if (err) goto done; vcn1 = max(vcn, svcn); zero = min(end, evcn1) - vcn1; /* * Check range [vcn1 + zero). * Calculate how many clusters there are. * Don't do any destructive actions. */ err = run_deallocate_ex(NULL, run, vcn1, zero, &hole2, false); if (err) goto done; /* Check if required range is already hole. */ if (hole2 == hole) goto next_attr; /* Make a clone of run to undo. */ err = run_clone(run, &run2); if (err) goto done; /* Make a hole range (sparse) [vcn1 + zero). */ if (!run_add_entry(run, vcn1, SPARSE_LCN, zero, false)) { err = -ENOMEM; goto done; } /* Update run in attribute segment. */ err = mi_pack_runs(mi, attr, run, evcn1 - svcn); if (err) goto done; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; if (next_svcn < evcn1) { /* Insert new attribute segment. */ err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - next_svcn, a_flags, &attr, &mi, &le); if (err) goto undo_punch; /* Layout of records maybe changed. */ attr_b = NULL; } /* Real deallocate. Should not fail. */ run_deallocate_ex(sbi, &run2, vcn1, zero, &hole, true); next_attr: /* Free all allocated memory. */ run_truncate(run, 0); if (evcn1 >= alen) break; /* Get next attribute segment. */ attr = ni_enum_attr_ex(ni, attr, &le, &mi); if (!attr) { err = -EINVAL; goto bad_inode; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } done: if (!hole) goto out; if (!attr_b) { attr_b = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -EINVAL; goto bad_inode; } } total_size -= (u64)hole << sbi->cluster_bits; attr_b->nres.total_size = cpu_to_le64(total_size); mi_b->dirty = true; /* Update inode size. */ inode_set_bytes(&ni->vfs_inode, total_size); ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mark_inode_dirty(&ni->vfs_inode); out: run_close(&run2); up_write(&ni->file.run_lock); return err; bad_inode: _ntfs_bad_inode(&ni->vfs_inode); goto out; undo_punch: /* * Restore packed runs. * 'mi_pack_runs' should not fail, cause we restore original. */ if (mi_pack_runs(mi, attr, &run2, evcn1 - svcn)) goto bad_inode; goto done; } /* * attr_insert_range - Insert range (hole) in file. * Not for normal files. */ int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes) { int err = 0; struct runs_tree *run = &ni->file.run; struct ntfs_sb_info *sbi = ni->mi.sbi; struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; CLST vcn, svcn, evcn1, len, next_svcn; u64 data_size, alloc_size; u32 mask; __le16 a_flags; if (!bytes) return 0; le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) return -ENOENT; if (!is_attr_ext(attr_b)) { /* It was checked above. See fallocate. */ return -EOPNOTSUPP; } if (!attr_b->non_res) { data_size = le32_to_cpu(attr_b->res.data_size); alloc_size = data_size; mask = sbi->cluster_mask; /* cluster_size - 1 */ } else { data_size = le64_to_cpu(attr_b->nres.data_size); alloc_size = le64_to_cpu(attr_b->nres.alloc_size); mask = (sbi->cluster_size << attr_b->nres.c_unit) - 1; } if (vbo >= data_size) { /* * Insert range after the file size is not allowed. * If the offset is equal to or greater than the end of * file, an error is returned. For such operations (i.e., inserting * a hole at the end of file), ftruncate(2) should be used. */ return -EINVAL; } if ((vbo & mask) || (bytes & mask)) { /* Allow to insert only frame aligned ranges. */ return -EINVAL; } /* * valid_size <= data_size <= alloc_size * Check alloc_size for maximum possible. */ if (bytes > sbi->maxbytes_sparse - alloc_size) return -EFBIG; vcn = vbo >> sbi->cluster_bits; len = bytes >> sbi->cluster_bits; down_write(&ni->file.run_lock); if (!attr_b->non_res) { err = attr_set_size(ni, ATTR_DATA, NULL, 0, run, data_size + bytes, NULL, false, NULL); le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -EINVAL; goto bad_inode; } if (err) goto out; if (!attr_b->non_res) { /* Still resident. */ char *data = Add2Ptr(attr_b, le16_to_cpu(attr_b->res.data_off)); memmove(data + bytes, data, bytes); memset(data, 0, bytes); goto done; } /* Resident files becomes nonresident. */ data_size = le64_to_cpu(attr_b->nres.data_size); alloc_size = le64_to_cpu(attr_b->nres.alloc_size); } /* * Enumerate all attribute segments and shift start vcn. */ a_flags = attr_b->flags; svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; if (svcn <= vcn && vcn < evcn1) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { err = -EINVAL; goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { err = -EINVAL; goto bad_inode; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } run_truncate(run, 0); /* clear cached values. */ err = attr_load_runs(attr, ni, run, NULL); if (err) goto out; if (!run_insert_range(run, vcn, len)) { err = -ENOMEM; goto out; } /* Try to pack in current record as much as possible. */ err = mi_pack_runs(mi, attr, run, evcn1 + len - svcn); if (err) goto out; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; while ((attr = ni_enum_attr_ex(ni, attr, &le, &mi)) && attr->type == ATTR_DATA && !attr->name_len) { le64_add_cpu(&attr->nres.svcn, len); le64_add_cpu(&attr->nres.evcn, len); if (le) { le->vcn = attr->nres.svcn; ni->attr_list.dirty = true; } mi->dirty = true; } if (next_svcn < evcn1 + len) { err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 + len - next_svcn, a_flags, NULL, NULL, NULL); le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -EINVAL; goto bad_inode; } if (err) { /* ni_insert_nonresident failed. Try to undo. */ goto undo_insert_range; } } /* * Update primary attribute segment. */ if (vbo <= ni->i_valid) ni->i_valid += bytes; attr_b->nres.data_size = cpu_to_le64(data_size + bytes); attr_b->nres.alloc_size = cpu_to_le64(alloc_size + bytes); /* ni->valid may be not equal valid_size (temporary). */ if (ni->i_valid > data_size + bytes) attr_b->nres.valid_size = attr_b->nres.data_size; else attr_b->nres.valid_size = cpu_to_le64(ni->i_valid); mi_b->dirty = true; done: i_size_write(&ni->vfs_inode, ni->vfs_inode.i_size + bytes); ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mark_inode_dirty(&ni->vfs_inode); out: run_truncate(run, 0); /* clear cached values. */ up_write(&ni->file.run_lock); return err; bad_inode: _ntfs_bad_inode(&ni->vfs_inode); goto out; undo_insert_range: svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; if (svcn <= vcn && vcn < evcn1) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { goto bad_inode; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } if (attr_load_runs(attr, ni, run, NULL)) goto bad_inode; if (!run_collapse_range(run, vcn, len)) goto bad_inode; if (mi_pack_runs(mi, attr, run, evcn1 + len - svcn)) goto bad_inode; while ((attr = ni_enum_attr_ex(ni, attr, &le, &mi)) && attr->type == ATTR_DATA && !attr->name_len) { le64_sub_cpu(&attr->nres.svcn, len); le64_sub_cpu(&attr->nres.evcn, len); if (le) { le->vcn = attr->nres.svcn; ni->attr_list.dirty = true; } mi->dirty = true; } goto out; } /* * attr_force_nonresident * * Convert default data attribute into non resident form. */ int attr_force_nonresident(struct ntfs_inode *ni) { int err; struct ATTRIB *attr; struct ATTR_LIST_ENTRY *le = NULL; struct mft_inode *mi; attr = ni_find_attr(ni, NULL, &le, ATTR_DATA, NULL, 0, NULL, &mi); if (!attr) { ntfs_bad_inode(&ni->vfs_inode, "no data attribute"); return -ENOENT; } if (attr->non_res) { /* Already non resident. */ return 0; } down_write(&ni->file.run_lock); err = attr_make_nonresident(ni, attr, le, mi, le32_to_cpu(attr->res.data_size), &ni->file.run, &attr, NULL); up_write(&ni->file.run_lock); return err; } /* * Change the compression of data attribute */ int attr_set_compress(struct ntfs_inode *ni, bool compr) { struct ATTRIB *attr; struct mft_inode *mi; attr = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, &mi); if (!attr) return -ENOENT; if (is_attr_compressed(attr) == !!compr) { /* Already required compressed state. */ return 0; } if (attr->non_res) { u16 run_off; u32 run_size; char *run; if (attr->nres.data_size) { /* * There are rare cases when it possible to change * compress state without big changes. * TODO: Process these cases. */ return -EOPNOTSUPP; } run_off = le16_to_cpu(attr->nres.run_off); run_size = le32_to_cpu(attr->size) - run_off; run = Add2Ptr(attr, run_off); if (!compr) { /* remove field 'attr->nres.total_size'. */ memmove(run - 8, run, run_size); run_off -= 8; } if (!mi_resize_attr(mi, attr, compr ? +8 : -8)) { /* * Ignore rare case when there are no 8 bytes in record with attr. * TODO: split attribute. */ return -EOPNOTSUPP; } if (compr) { /* Make a gap for 'attr->nres.total_size'. */ memmove(run + 8, run, run_size); run_off += 8; attr->nres.total_size = attr->nres.alloc_size; } attr->nres.run_off = cpu_to_le16(run_off); } /* Update data attribute flags. */ if (compr) { attr->flags |= ATTR_FLAG_COMPRESSED; attr->nres.c_unit = NTFS_LZNT_CUNIT; } else { attr->flags &= ~ATTR_FLAG_COMPRESSED; attr->nres.c_unit = 0; } mi->dirty = true; return 0; } |
| 13 13 13 13 13 13 13 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Fast Userspace Mutexes (which I call "Futexes!"). * (C) Rusty Russell, IBM 2002 * * Generalized futexes, futex requeueing, misc fixes by Ingo Molnar * (C) Copyright 2003 Red Hat Inc, All Rights Reserved * * Removed page pinning, fix privately mapped COW pages and other cleanups * (C) Copyright 2003, 2004 Jamie Lokier * * Robust futex support started by Ingo Molnar * (C) Copyright 2006 Red Hat Inc, All Rights Reserved * Thanks to Thomas Gleixner for suggestions, analysis and fixes. * * PI-futex support started by Ingo Molnar and Thomas Gleixner * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com> * * PRIVATE futexes by Eric Dumazet * Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com> * * Requeue-PI support by Darren Hart <dvhltc@us.ibm.com> * Copyright (C) IBM Corporation, 2009 * Thanks to Thomas Gleixner for conceptual design and careful reviews. * * Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly * enough at me, Linus for the original (flawed) idea, Matthew * Kirkwood for proof-of-concept implementation. * * "The futexes are also cursed." * "But they come in a choice of three flavours!" */ #include <linux/compat.h> #include <linux/jhash.h> #include <linux/pagemap.h> #include <linux/debugfs.h> #include <linux/plist.h> #include <linux/memblock.h> #include <linux/fault-inject.h> #include <linux/slab.h> #include "futex.h" #include "../locking/rtmutex_common.h" /* * The base of the bucket array and its size are always used together * (after initialization only in futex_hash()), so ensure that they * reside in the same cacheline. */ static struct { struct futex_hash_bucket *queues; unsigned long hashsize; } __futex_data __read_mostly __aligned(2*sizeof(long)); #define futex_queues (__futex_data.queues) #define futex_hashsize (__futex_data.hashsize) /* * Fault injections for futexes. */ #ifdef CONFIG_FAIL_FUTEX static struct { struct fault_attr attr; bool ignore_private; } fail_futex = { .attr = FAULT_ATTR_INITIALIZER, .ignore_private = false, }; static int __init setup_fail_futex(char *str) { return setup_fault_attr(&fail_futex.attr, str); } __setup("fail_futex=", setup_fail_futex); bool should_fail_futex(bool fshared) { if (fail_futex.ignore_private && !fshared) return false; return should_fail(&fail_futex.attr, 1); } #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_futex_debugfs(void) { umode_t mode = S_IFREG | S_IRUSR | S_IWUSR; struct dentry *dir; dir = fault_create_debugfs_attr("fail_futex", NULL, &fail_futex.attr); if (IS_ERR(dir)) return PTR_ERR(dir); debugfs_create_bool("ignore-private", mode, dir, &fail_futex.ignore_private); return 0; } late_initcall(fail_futex_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ #endif /* CONFIG_FAIL_FUTEX */ /** * futex_hash - Return the hash bucket in the global hash * @key: Pointer to the futex key for which the hash is calculated * * We hash on the keys returned from get_futex_key (see below) and return the * corresponding hash bucket in the global hash. */ struct futex_hash_bucket *futex_hash(union futex_key *key) { u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4, key->both.offset); return &futex_queues[hash & (futex_hashsize - 1)]; } /** * futex_setup_timer - set up the sleeping hrtimer. * @time: ptr to the given timeout value * @timeout: the hrtimer_sleeper structure to be set up * @flags: futex flags * @range_ns: optional range in ns * * Return: Initialized hrtimer_sleeper structure or NULL if no timeout * value given */ struct hrtimer_sleeper * futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns) { if (!time) return NULL; hrtimer_setup_sleeper_on_stack(timeout, (flags & FLAGS_CLOCKRT) ? CLOCK_REALTIME : CLOCK_MONOTONIC, HRTIMER_MODE_ABS); /* * If range_ns is 0, calling hrtimer_set_expires_range_ns() is * effectively the same as calling hrtimer_set_expires(). */ hrtimer_set_expires_range_ns(&timeout->timer, *time, range_ns); return timeout; } /* * Generate a machine wide unique identifier for this inode. * * This relies on u64 not wrapping in the life-time of the machine; which with * 1ns resolution means almost 585 years. * * This further relies on the fact that a well formed program will not unmap * the file while it has a (shared) futex waiting on it. This mapping will have * a file reference which pins the mount and inode. * * If for some reason an inode gets evicted and read back in again, it will get * a new sequence number and will _NOT_ match, even though it is the exact same * file. * * It is important that futex_match() will never have a false-positive, esp. * for PI futexes that can mess up the state. The above argues that false-negatives * are only possible for malformed programs. */ static u64 get_inode_sequence_number(struct inode *inode) { static atomic64_t i_seq; u64 old; /* Does the inode already have a sequence number? */ old = atomic64_read(&inode->i_sequence); if (likely(old)) return old; for (;;) { u64 new = atomic64_inc_return(&i_seq); if (WARN_ON_ONCE(!new)) continue; old = 0; if (!atomic64_try_cmpxchg_relaxed(&inode->i_sequence, &old, new)) return old; return new; } } /** * get_futex_key() - Get parameters which are the keys for a futex * @uaddr: virtual address of the futex * @flags: FLAGS_* * @key: address where result is stored. * @rw: mapping needs to be read/write (values: FUTEX_READ, * FUTEX_WRITE) * * Return: a negative error code or 0 * * The key words are stored in @key on success. * * For shared mappings (when @fshared), the key is: * * ( inode->i_sequence, page->index, offset_within_page ) * * [ also see get_inode_sequence_number() ] * * For private mappings (or when !@fshared), the key is: * * ( current->mm, address, 0 ) * * This allows (cross process, where applicable) identification of the futex * without keeping the page pinned for the duration of the FUTEX_WAIT. * * lock_page() might sleep, the caller should not hold a spinlock. */ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, enum futex_access rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; struct page *page; struct folio *folio; struct address_space *mapping; int err, ro = 0; bool fshared; fshared = flags & FLAGS_SHARED; /* * The futex address must be "naturally" aligned. */ key->both.offset = address % PAGE_SIZE; if (unlikely((address % sizeof(u32)) != 0)) return -EINVAL; address -= key->both.offset; if (unlikely(!access_ok(uaddr, sizeof(u32)))) return -EFAULT; if (unlikely(should_fail_futex(fshared))) return -EFAULT; /* * PROCESS_PRIVATE futexes are fast. * As the mm cannot disappear under us and the 'key' only needs * virtual address, we dont even have to find the underlying vma. * Note : We do have to check 'uaddr' is a valid user address, * but access_ok() should be faster than find_vma() */ if (!fshared) { /* * On no-MMU, shared futexes are treated as private, therefore * we must not include the current process in the key. Since * there is only one address space, the address is a unique key * on its own. */ if (IS_ENABLED(CONFIG_MMU)) key->private.mm = mm; else key->private.mm = NULL; key->private.address = address; return 0; } again: /* Ignore any VERIFY_READ mapping (futex common case) */ if (unlikely(should_fail_futex(true))) return -EFAULT; err = get_user_pages_fast(address, 1, FOLL_WRITE, &page); /* * If write access is not required (eg. FUTEX_WAIT), try * and get read-only access. */ if (err == -EFAULT && rw == FUTEX_READ) { err = get_user_pages_fast(address, 1, 0, &page); ro = 1; } if (err < 0) return err; else err = 0; /* * The treatment of mapping from this point on is critical. The folio * lock protects many things but in this context the folio lock * stabilizes mapping, prevents inode freeing in the shared * file-backed region case and guards against movement to swap cache. * * Strictly speaking the folio lock is not needed in all cases being * considered here and folio lock forces unnecessarily serialization. * From this point on, mapping will be re-verified if necessary and * folio lock will be acquired only if it is unavoidable * * Mapping checks require the folio so it is looked up now. For * anonymous pages, it does not matter if the folio is split * in the future as the key is based on the address. For * filesystem-backed pages, the precise page is required as the * index of the page determines the key. */ folio = page_folio(page); mapping = READ_ONCE(folio->mapping); /* * If folio->mapping is NULL, then it cannot be an anonymous * page; but it might be the ZERO_PAGE or in the gate area or * in a special mapping (all cases which we are happy to fail); * or it may have been a good file page when get_user_pages_fast * found it, but truncated or holepunched or subjected to * invalidate_complete_page2 before we got the folio lock (also * cases which we are happy to fail). And we hold a reference, * so refcount care in invalidate_inode_page's remove_mapping * prevents drop_caches from setting mapping to NULL beneath us. * * The case we do have to guard against is when memory pressure made * shmem_writepage move it from filecache to swapcache beneath us: * an unlikely race, but we do need to retry for folio->mapping. */ if (unlikely(!mapping)) { int shmem_swizzled; /* * Folio lock is required to identify which special case above * applies. If this is really a shmem page then the folio lock * will prevent unexpected transitions. */ folio_lock(folio); shmem_swizzled = folio_test_swapcache(folio) || folio->mapping; folio_unlock(folio); folio_put(folio); if (shmem_swizzled) goto again; return -EFAULT; } /* * Private mappings are handled in a simple way. * * If the futex key is stored in anonymous memory, then the associated * object is the mm which is implicitly pinned by the calling process. * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. */ if (folio_test_anon(folio)) { /* * A RO anonymous page will never change and thus doesn't make * sense for futex operations. */ if (unlikely(should_fail_futex(true)) || ro) { err = -EFAULT; goto out; } key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ key->private.mm = mm; key->private.address = address; } else { struct inode *inode; /* * The associated futex object in this case is the inode and * the folio->mapping must be traversed. Ordinarily this should * be stabilised under folio lock but it's not strictly * necessary in this case as we just want to pin the inode, not * update i_pages or anything like that. * * The RCU read lock is taken as the inode is finally freed * under RCU. If the mapping still matches expectations then the * mapping->host can be safely accessed as being a valid inode. */ rcu_read_lock(); if (READ_ONCE(folio->mapping) != mapping) { rcu_read_unlock(); folio_put(folio); goto again; } inode = READ_ONCE(mapping->host); if (!inode) { rcu_read_unlock(); folio_put(folio); goto again; } key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); key->shared.pgoff = folio->index + folio_page_idx(folio, page); rcu_read_unlock(); } out: folio_put(folio); return err; } /** * fault_in_user_writeable() - Fault in user address and verify RW access * @uaddr: pointer to faulting user space address * * Slow path to fixup the fault we just took in the atomic write * access to @uaddr. * * We have no generic implementation of a non-destructive write to the * user address. We know that we faulted in the atomic pagefault * disabled section so we can as well avoid the #PF overhead by * calling get_user_pages() right away. */ int fault_in_user_writeable(u32 __user *uaddr) { struct mm_struct *mm = current->mm; int ret; mmap_read_lock(mm); ret = fixup_user_fault(mm, (unsigned long)uaddr, FAULT_FLAG_WRITE, NULL); mmap_read_unlock(mm); return ret < 0 ? ret : 0; } /** * futex_top_waiter() - Return the highest priority waiter on a futex * @hb: the hash bucket the futex_q's reside in * @key: the futex key (to distinguish it from other futex futex_q's) * * Must be called with the hb lock held. */ struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key) { struct futex_q *this; plist_for_each_entry(this, &hb->chain, list) { if (futex_match(&this->key, key)) return this; } return NULL; } int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval) { int ret; pagefault_disable(); ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval); pagefault_enable(); return ret; } int futex_get_value_locked(u32 *dest, u32 __user *from) { int ret; pagefault_disable(); ret = __get_user(*dest, from); pagefault_enable(); return ret ? -EFAULT : 0; } /** * wait_for_owner_exiting - Block until the owner has exited * @ret: owner's current futex lock status * @exiting: Pointer to the exiting task * * Caller must hold a refcount on @exiting. */ void wait_for_owner_exiting(int ret, struct task_struct *exiting) { if (ret != -EBUSY) { WARN_ON_ONCE(exiting); return; } if (WARN_ON_ONCE(ret == -EBUSY && !exiting)) return; mutex_lock(&exiting->futex_exit_mutex); /* * No point in doing state checking here. If the waiter got here * while the task was in exec()->exec_futex_release() then it can * have any FUTEX_STATE_* value when the waiter has acquired the * mutex. OK, if running, EXITING or DEAD if it reached exit() * already. Highly unlikely and not a problem. Just one more round * through the futex maze. */ mutex_unlock(&exiting->futex_exit_mutex); put_task_struct(exiting); } /** * __futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be NULL and must be held by the caller. */ void __futex_unqueue(struct futex_q *q) { struct futex_hash_bucket *hb; if (WARN_ON_SMP(!q->lock_ptr) || WARN_ON(plist_node_empty(&q->list))) return; lockdep_assert_held(q->lock_ptr); hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock); plist_del(&q->list, &hb->chain); futex_hb_waiters_dec(hb); } /* The key must be already stored in q->key. */ struct futex_hash_bucket *futex_q_lock(struct futex_q *q) __acquires(&hb->lock) { struct futex_hash_bucket *hb; hb = futex_hash(&q->key); /* * Increment the counter before taking the lock so that * a potential waker won't miss a to-be-slept task that is * waiting for the spinlock. This is safe as all futex_q_lock() * users end up calling futex_queue(). Similarly, for housekeeping, * decrement the counter at futex_q_unlock() when some error has * occurred and we don't end up adding the task to the list. */ futex_hb_waiters_inc(hb); /* implies smp_mb(); (A) */ q->lock_ptr = &hb->lock; spin_lock(&hb->lock); return hb; } void futex_q_unlock(struct futex_hash_bucket *hb) __releases(&hb->lock) { spin_unlock(&hb->lock); futex_hb_waiters_dec(hb); } void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) { int prio; /* * The priority used to register this element is * - either the real thread-priority for the real-time threads * (i.e. threads with a priority lower than MAX_RT_PRIO) * - or MAX_RT_PRIO for non-RT threads. * Thus, all RT-threads are woken first in priority order, and * the others are woken last, in FIFO order. */ prio = min(current->normal_prio, MAX_RT_PRIO); plist_node_init(&q->list, prio); plist_add(&q->list, &hb->chain); q->task = current; } /** * futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be held by the caller. A call to futex_unqueue() must * be paired with exactly one earlier call to futex_queue(). * * Return: * - 1 - if the futex_q was still queued (and we removed unqueued it); * - 0 - if the futex_q was already removed by the waking thread */ int futex_unqueue(struct futex_q *q) { spinlock_t *lock_ptr; int ret = 0; /* In the common case we don't take the spinlock, which is nice. */ retry: /* * q->lock_ptr can change between this read and the following spin_lock. * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and * optimizing lock_ptr out of the logic below. */ lock_ptr = READ_ONCE(q->lock_ptr); if (lock_ptr != NULL) { spin_lock(lock_ptr); /* * q->lock_ptr can change between reading it and * spin_lock(), causing us to take the wrong lock. This * corrects the race condition. * * Reasoning goes like this: if we have the wrong lock, * q->lock_ptr must have changed (maybe several times) * between reading it and the spin_lock(). It can * change again after the spin_lock() but only if it was * already changed before the spin_lock(). It cannot, * however, change back to the original value. Therefore * we can detect whether we acquired the correct lock. */ if (unlikely(lock_ptr != q->lock_ptr)) { spin_unlock(lock_ptr); goto retry; } __futex_unqueue(q); BUG_ON(q->pi_state); spin_unlock(lock_ptr); ret = 1; } return ret; } /* * PI futexes can not be requeued and must remove themselves from the hash * bucket. The hash bucket lock (i.e. lock_ptr) is held. */ void futex_unqueue_pi(struct futex_q *q) { /* * If the lock was not acquired (due to timeout or signal) then the * rt_waiter is removed before futex_q is. If this is observed by * an unlocker after dropping the rtmutex wait lock and before * acquiring the hash bucket lock, then the unlocker dequeues the * futex_q from the hash bucket list to guarantee consistent state * vs. userspace. Therefore the dequeue here must be conditional. */ if (!plist_node_empty(&q->list)) __futex_unqueue(q); BUG_ON(!q->pi_state); put_pi_state(q->pi_state); q->pi_state = NULL; } /* Constants for the pending_op argument of handle_futex_death */ #define HANDLE_DEATH_PENDING true #define HANDLE_DEATH_LIST false /* * Process a futex-list entry, check whether it's owned by the * dying task, and do notification if so: */ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, bool pi, bool pending_op) { u32 uval, nval, mval; pid_t owner; int err; /* Futex address must be 32bit aligned */ if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0) return -1; retry: if (get_user(uval, uaddr)) return -1; /* * Special case for regular (non PI) futexes. The unlock path in * user space has two race scenarios: * * 1. The unlock path releases the user space futex value and * before it can execute the futex() syscall to wake up * waiters it is killed. * * 2. A woken up waiter is killed before it can acquire the * futex in user space. * * In the second case, the wake up notification could be generated * by the unlock path in user space after setting the futex value * to zero or by the kernel after setting the OWNER_DIED bit below. * * In both cases the TID validation below prevents a wakeup of * potential waiters which can cause these waiters to block * forever. * * In both cases the following conditions are met: * * 1) task->robust_list->list_op_pending != NULL * @pending_op == true * 2) The owner part of user space futex value == 0 * 3) Regular futex: @pi == false * * If these conditions are met, it is safe to attempt waking up a * potential waiter without touching the user space futex value and * trying to set the OWNER_DIED bit. If the futex value is zero, * the rest of the user space mutex state is consistent, so a woken * waiter will just take over the uncontended futex. Setting the * OWNER_DIED bit would create inconsistent state and malfunction * of the user space owner died handling. Otherwise, the OWNER_DIED * bit is already set, and the woken waiter is expected to deal with * this. */ owner = uval & FUTEX_TID_MASK; if (pending_op && !pi && !owner) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); return 0; } if (owner != task_pid_vnr(curr)) return 0; /* * Ok, this dying thread is truly holding a futex * of interest. Set the OWNER_DIED bit atomically * via cmpxchg, and if the value had FUTEX_WAITERS * set, wake up a waiter (if any). (We have to do a * futex_wake() even if OWNER_DIED is already set - * to handle the rare but possible case of recursive * thread-death.) The rest of the cleanup is done in * userspace. */ mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; /* * We are not holding a lock here, but we want to have * the pagefault_disable/enable() protection because * we want to handle the fault gracefully. If the * access fails we try to fault in the futex with R/W * verification via get_user_pages. get_user() above * does not guarantee R/W access. If that fails we * give up and leave the futex locked. */ if ((err = futex_cmpxchg_value_locked(&nval, uaddr, uval, mval))) { switch (err) { case -EFAULT: if (fault_in_user_writeable(uaddr)) return -1; goto retry; case -EAGAIN: cond_resched(); goto retry; default: WARN_ON_ONCE(1); return err; } } if (nval != uval) goto retry; /* * Wake robust non-PI futexes here. The wakeup of * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); } return 0; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int fetch_robust_entry(struct robust_list __user **entry, struct robust_list __user * __user *head, unsigned int *pi) { unsigned long uentry; if (get_user(uentry, (unsigned long __user *)head)) return -EFAULT; *entry = (void __user *)(uentry & ~1UL); *pi = uentry & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void exit_robust_list(struct task_struct *curr) { struct robust_list_head __user *head = curr->robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; unsigned long futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (fetch_robust_entry(&entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (fetch_robust_entry(&pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi); /* * A pending lock might already be on the list, so * don't process it twice: */ if (entry != pending) { if (handle_futex_death((void __user *)entry + futex_offset, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { handle_futex_death((void __user *)pending + futex_offset, curr, pip, HANDLE_DEATH_PENDING); } } #ifdef CONFIG_COMPAT static void __user *futex_uaddr(struct robust_list __user *entry, compat_long_t futex_offset) { compat_uptr_t base = ptr_to_compat(entry); void __user *uaddr = compat_ptr(base + futex_offset); return uaddr; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, compat_uptr_t __user *head, unsigned int *pi) { if (get_user(*uentry, head)) return -EFAULT; *entry = compat_ptr((*uentry) & ~1); *pi = (unsigned int)(*uentry) & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void compat_exit_robust_list(struct task_struct *curr) { struct compat_robust_list_head __user *head = curr->compat_robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; compat_uptr_t uentry, next_uentry, upending; compat_long_t futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (compat_fetch_robust_entry(&upending, &pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != (struct robust_list __user *) &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = compat_fetch_robust_entry(&next_uentry, &next_entry, (compat_uptr_t __user *)&entry->next, &next_pi); /* * A pending lock might already be on the list, so * dont process it twice: */ if (entry != pending) { void __user *uaddr = futex_uaddr(entry, futex_offset); if (handle_futex_death(uaddr, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; uentry = next_uentry; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { void __user *uaddr = futex_uaddr(pending, futex_offset); handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING); } } #endif #ifdef CONFIG_FUTEX_PI /* * This task is holding PI mutexes at exit time => bad. * Kernel cleans up PI-state, but userspace is likely hosed. * (Robust-futex cleanup is separate and might save the day for userspace.) */ static void exit_pi_state_list(struct task_struct *curr) { struct list_head *next, *head = &curr->pi_state_list; struct futex_pi_state *pi_state; struct futex_hash_bucket *hb; union futex_key key = FUTEX_KEY_INIT; /* * We are a ZOMBIE and nobody can enqueue itself on * pi_state_list anymore, but we have to be careful * versus waiters unqueueing themselves: */ raw_spin_lock_irq(&curr->pi_lock); while (!list_empty(head)) { next = head->next; pi_state = list_entry(next, struct futex_pi_state, list); key = pi_state->key; hb = futex_hash(&key); /* * We can race against put_pi_state() removing itself from the * list (a waiter going away). put_pi_state() will first * decrement the reference count and then modify the list, so * its possible to see the list entry but fail this reference * acquire. * * In that case; drop the locks to let put_pi_state() make * progress and retry the loop. */ if (!refcount_inc_not_zero(&pi_state->refcount)) { raw_spin_unlock_irq(&curr->pi_lock); cpu_relax(); raw_spin_lock_irq(&curr->pi_lock); continue; } raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { /* retain curr->pi_lock for the loop invariant */ raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); put_pi_state(pi_state); continue; } WARN_ON(pi_state->owner != curr); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; raw_spin_unlock(&curr->pi_lock); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); put_pi_state(pi_state); raw_spin_lock_irq(&curr->pi_lock); } raw_spin_unlock_irq(&curr->pi_lock); } #else static inline void exit_pi_state_list(struct task_struct *curr) { } #endif static void futex_cleanup(struct task_struct *tsk) { if (unlikely(tsk->robust_list)) { exit_robust_list(tsk); tsk->robust_list = NULL; } #ifdef CONFIG_COMPAT if (unlikely(tsk->compat_robust_list)) { compat_exit_robust_list(tsk); tsk->compat_robust_list = NULL; } #endif if (unlikely(!list_empty(&tsk->pi_state_list))) exit_pi_state_list(tsk); } /** * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD * @tsk: task to set the state on * * Set the futex exit state of the task lockless. The futex waiter code * observes that state when a task is exiting and loops until the task has * actually finished the futex cleanup. The worst case for this is that the * waiter runs through the wait loop until the state becomes visible. * * This is called from the recursive fault handling path in make_task_dead(). * * This is best effort. Either the futex exit code has run already or * not. If the OWNER_DIED bit has been set on the futex then the waiter can * take it over. If not, the problem is pushed back to user space. If the * futex exit code did not run yet, then an already queued waiter might * block forever, but there is nothing which can be done about that. */ void futex_exit_recursive(struct task_struct *tsk) { /* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */ if (tsk->futex_state == FUTEX_STATE_EXITING) mutex_unlock(&tsk->futex_exit_mutex); tsk->futex_state = FUTEX_STATE_DEAD; } static void futex_cleanup_begin(struct task_struct *tsk) { /* * Prevent various race issues against a concurrent incoming waiter * including live locks by forcing the waiter to block on * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in * attach_to_pi_owner(). */ mutex_lock(&tsk->futex_exit_mutex); /* * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock. * * This ensures that all subsequent checks of tsk->futex_state in * attach_to_pi_owner() must observe FUTEX_STATE_EXITING with * tsk->pi_lock held. * * It guarantees also that a pi_state which was queued right before * the state change under tsk->pi_lock by a concurrent waiter must * be observed in exit_pi_state_list(). */ raw_spin_lock_irq(&tsk->pi_lock); tsk->futex_state = FUTEX_STATE_EXITING; raw_spin_unlock_irq(&tsk->pi_lock); } static void futex_cleanup_end(struct task_struct *tsk, int state) { /* * Lockless store. The only side effect is that an observer might * take another loop until it becomes visible. */ tsk->futex_state = state; /* * Drop the exit protection. This unblocks waiters which observed * FUTEX_STATE_EXITING to reevaluate the state. */ mutex_unlock(&tsk->futex_exit_mutex); } void futex_exec_release(struct task_struct *tsk) { /* * The state handling is done for consistency, but in the case of * exec() there is no way to prevent further damage as the PID stays * the same. But for the unlikely and arguably buggy case that a * futex is held on exec(), this provides at least as much state * consistency protection which is possible. */ futex_cleanup_begin(tsk); futex_cleanup(tsk); /* * Reset the state to FUTEX_STATE_OK. The task is alive and about * exec a new binary. */ futex_cleanup_end(tsk, FUTEX_STATE_OK); } void futex_exit_release(struct task_struct *tsk) { futex_cleanup_begin(tsk); futex_cleanup(tsk); futex_cleanup_end(tsk, FUTEX_STATE_DEAD); } static int __init futex_init(void) { unsigned int futex_shift; unsigned long i; #ifdef CONFIG_BASE_SMALL futex_hashsize = 16; #else futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus()); #endif futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues), futex_hashsize, 0, 0, &futex_shift, NULL, futex_hashsize, futex_hashsize); futex_hashsize = 1UL << futex_shift; for (i = 0; i < futex_hashsize; i++) { atomic_set(&futex_queues[i].waiters, 0); plist_head_init(&futex_queues[i].chain); spin_lock_init(&futex_queues[i].lock); } return 0; } core_initcall(futex_init); |
| 5 3 33 5 5 5 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 | // 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, const 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, 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_sz("net", empty, 0); 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, size_t table_size) { struct ctl_table *ent; pr_debug("Registering net sysctl (net %p): %s\n", net, path); ent = table; for (size_t i = 0; i < table_size; ent++, i++) { 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_sz(struct net *net, const char *path, struct ctl_table *table, size_t table_size) { if (!net_eq(net, &init_net)) ensure_safe_net_sysctl(net, path, table, table_size); return __register_sysctl_table(&net->sysctls, path, table, table_size); } EXPORT_SYMBOL_GPL(register_ne |