| 201 329 19 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Routines to manage notifier chains for passing status changes to any * interested routines. We need this instead of hard coded call lists so * that modules can poke their nose into the innards. The network devices * needed them so here they are for the rest of you. * * Alan Cox <Alan.Cox@linux.org> */ #ifndef _LINUX_NOTIFIER_H #define _LINUX_NOTIFIER_H #include <linux/errno.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/srcu.h> /* * Notifier chains are of four types: * * Atomic notifier chains: Chain callbacks run in interrupt/atomic * context. Callouts are not allowed to block. * Blocking notifier chains: Chain callbacks run in process context. * Callouts are allowed to block. * Raw notifier chains: There are no restrictions on callbacks, * registration, or unregistration. All locking and protection * must be provided by the caller. * SRCU notifier chains: A variant of blocking notifier chains, with * the same restrictions. * * atomic_notifier_chain_register() may be called from an atomic context, * but blocking_notifier_chain_register() and srcu_notifier_chain_register() * must be called from a process context. Ditto for the corresponding * _unregister() routines. * * atomic_notifier_chain_unregister(), blocking_notifier_chain_unregister(), * and srcu_notifier_chain_unregister() _must not_ be called from within * the call chain. * * SRCU notifier chains are an alternative form of blocking notifier chains. * They use SRCU (Sleepable Read-Copy Update) instead of rw-semaphores for * protection of the chain links. This means there is _very_ low overhead * in srcu_notifier_call_chain(): no cache bounces and no memory barriers. * As compensation, srcu_notifier_chain_unregister() is rather expensive. * SRCU notifier chains should be used when the chain will be called very * often but notifier_blocks will seldom be removed. */ struct notifier_block; typedef int (*notifier_fn_t)(struct notifier_block *nb, unsigned long action, void *data); struct notifier_block { notifier_fn_t notifier_call; struct notifier_block __rcu *next; int priority; }; struct atomic_notifier_head { spinlock_t lock; struct notifier_block __rcu *head; }; struct blocking_notifier_head { struct rw_semaphore rwsem; struct notifier_block __rcu *head; }; struct raw_notifier_head { struct notifier_block __rcu *head; }; struct srcu_notifier_head { struct mutex mutex; struct srcu_struct srcu; struct notifier_block __rcu *head; }; #define ATOMIC_INIT_NOTIFIER_HEAD(name) do { \ spin_lock_init(&(name)->lock); \ (name)->head = NULL; \ } while (0) #define BLOCKING_INIT_NOTIFIER_HEAD(name) do { \ init_rwsem(&(name)->rwsem); \ (name)->head = NULL; \ } while (0) #define RAW_INIT_NOTIFIER_HEAD(name) do { \ (name)->head = NULL; \ } while (0) /* srcu_notifier_heads must be cleaned up dynamically */ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #define srcu_cleanup_notifier_head(name) \ cleanup_srcu_struct(&(name)->srcu); #define ATOMIC_NOTIFIER_INIT(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .head = NULL } #define BLOCKING_NOTIFIER_INIT(name) { \ .rwsem = __RWSEM_INITIALIZER((name).rwsem), \ .head = NULL } #define RAW_NOTIFIER_INIT(name) { \ .head = NULL } #define SRCU_NOTIFIER_INIT(name, pcpu) \ { \ .mutex = __MUTEX_INITIALIZER(name.mutex), \ .head = NULL, \ .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \ } #define ATOMIC_NOTIFIER_HEAD(name) \ struct atomic_notifier_head name = \ ATOMIC_NOTIFIER_INIT(name) #define BLOCKING_NOTIFIER_HEAD(name) \ struct blocking_notifier_head name = \ BLOCKING_NOTIFIER_INIT(name) #define RAW_NOTIFIER_HEAD(name) \ struct raw_notifier_head name = \ RAW_NOTIFIER_INIT(name) #ifdef CONFIG_TREE_SRCU #define _SRCU_NOTIFIER_HEAD(name, mod) \ static DEFINE_PER_CPU(struct srcu_data, name##_head_srcu_data); \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name##_head_srcu_data) #else #define _SRCU_NOTIFIER_HEAD(name, mod) \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name) #endif #define SRCU_NOTIFIER_HEAD(name) \ _SRCU_NOTIFIER_HEAD(name, /* not static */) #define SRCU_NOTIFIER_HEAD_STATIC(name) \ _SRCU_NOTIFIER_HEAD(name, static) #ifdef __KERNEL__ extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *nb); extern int raw_notifier_chain_register(struct raw_notifier_head *nh, struct notifier_block *nb); extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_chain_register_unique_prio( struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_register_unique_prio( struct blocking_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, struct notifier_block *nb); extern int raw_notifier_chain_unregister(struct raw_notifier_head *nh, struct notifier_block *nb); extern int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_call_chain(struct atomic_notifier_head *nh, unsigned long val, void *v); extern int blocking_notifier_call_chain(struct blocking_notifier_head *nh, unsigned long val, void *v); extern int raw_notifier_call_chain(struct raw_notifier_head *nh, unsigned long val, void *v); extern int srcu_notifier_call_chain(struct srcu_notifier_head *nh, unsigned long val, void *v); extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); extern bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh); #define NOTIFY_DONE 0x0000 /* Don't care */ #define NOTIFY_OK 0x0001 /* Suits me */ #define NOTIFY_STOP_MASK 0x8000 /* Don't call further */ #define NOTIFY_BAD (NOTIFY_STOP_MASK|0x0002) /* Bad/Veto action */ /* * Clean way to return from the notifier and stop further calls. */ #define NOTIFY_STOP (NOTIFY_OK|NOTIFY_STOP_MASK) /* Encapsulate (negative) errno value (in particular, NOTIFY_BAD <=> EPERM). */ static inline int notifier_from_errno(int err) { if (err) return NOTIFY_STOP_MASK | (NOTIFY_OK - err); return NOTIFY_OK; } /* Restore (negative) errno value from notify return value. */ static inline int notifier_to_errno(int ret) { ret &= ~NOTIFY_STOP_MASK; return ret > NOTIFY_OK ? NOTIFY_OK - ret : 0; } /* * Declared notifiers so far. I can imagine quite a few more chains * over time (eg laptop power reset chains, reboot chain (to clean * device units up), device [un]mount chain, module load/unload chain, * low memory chain, screenblank chain (for plug in modular screenblankers) * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... */ /* CPU notfiers are defined in include/linux/cpu.h. */ /* netdevice notifiers are defined in include/linux/netdevice.h */ /* reboot notifiers are defined in include/linux/reboot.h. */ /* Hibernation and suspend events are defined in include/linux/suspend.h. */ /* Virtual Terminal events are defined in include/linux/vt.h. */ #define NETLINK_URELEASE 0x0001 /* Unicast netlink socket released */ /* Console keyboard events. * Note: KBD_KEYCODE is always sent before KBD_UNBOUND_KEYCODE, KBD_UNICODE and * KBD_KEYSYM. */ #define KBD_KEYCODE 0x0001 /* Keyboard keycode, called before any other */ #define KBD_UNBOUND_KEYCODE 0x0002 /* Keyboard keycode which is not bound to any other */ #define KBD_UNICODE 0x0003 /* Keyboard unicode */ #define KBD_KEYSYM 0x0004 /* Keyboard keysym */ #define KBD_POST_KEYSYM 0x0005 /* Called after keyboard keysym interpretation */ extern struct blocking_notifier_head reboot_notifier_list; #endif /* __KERNEL__ */ #endif /* _LINUX_NOTIFIER_H */ |
| 981 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/linux/eventpoll.h ( Efficient event polling implementation ) * Copyright (C) 2001,...,2006 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #ifndef _LINUX_EVENTPOLL_H #define _LINUX_EVENTPOLL_H #include <uapi/linux/eventpoll.h> #include <uapi/linux/kcmp.h> /* Forward declarations to avoid compiler errors */ struct file; #ifdef CONFIG_EPOLL #ifdef CONFIG_KCMP struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); #endif /* Used to release the epoll bits inside the "struct file" */ void eventpoll_release_file(struct file *file); /* * This is called from inside fs/file_table.c:__fput() to unlink files * from the eventpoll interface. We need to have this facility to cleanup * correctly files that are closed without being removed from the eventpoll * interface. */ static inline void eventpoll_release(struct file *file) { /* * Fast check to avoid the get/release of the semaphore. Since * we're doing this outside the semaphore lock, it might return * false negatives, but we don't care. It'll help in 99.99% of cases * to avoid the semaphore lock. False positives simply cannot happen * because the file in on the way to be removed and nobody ( but * eventpoll ) has still a reference to this file. */ if (likely(!file->f_ep)) return; /* * The file is being closed while it is still linked to an epoll * descriptor. We need to handle this by correctly unlinking it * from its containers. */ eventpoll_release_file(file); } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock); /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ static inline int ep_op_has_event(int op) { return op != EPOLL_CTL_DEL; } #else static inline void eventpoll_release(struct file *file) {} #endif #if defined(CONFIG_ARM) && defined(CONFIG_OABI_COMPAT) /* ARM OABI has an incompatible struct layout and needs a special handler */ extern struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent); #else static inline struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent) { if (__put_user(revents, &uevent->events) || __put_user(data, &uevent->data)) return NULL; return uevent+1; } #endif #endif /* #ifndef _LINUX_EVENTPOLL_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_PKT_CLS_H #define __NET_PKT_CLS_H #include <linux/pkt_cls.h> #include <linux/workqueue.h> #include <net/sch_generic.h> #include <net/act_api.h> #include <net/net_namespace.h> /* TC action not accessible from user space */ #define TC_ACT_CONSUMED (TC_ACT_VALUE_MAX + 1) /* Basic packet classifier frontend definitions. */ struct tcf_walker { int stop; int skip; int count; bool nonempty; unsigned long cookie; int (*fn)(struct tcf_proto *, void *node, struct tcf_walker *); }; int register_tcf_proto_ops(struct tcf_proto_ops *ops); void unregister_tcf_proto_ops(struct tcf_proto_ops *ops); struct tcf_block_ext_info { enum flow_block_binder_type binder_type; tcf_chain_head_change_t *chain_head_change; void *chain_head_change_priv; u32 block_index; }; struct tcf_qevent { struct tcf_block *block; struct tcf_block_ext_info info; struct tcf_proto __rcu *filter_chain; }; struct tcf_block_cb; bool tcf_queue_work(struct rcu_work *rwork, work_func_t func); #ifdef CONFIG_NET_CLS struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index); void tcf_chain_put_by_act(struct tcf_chain *chain); struct tcf_chain *tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain); struct tcf_proto *tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp); void tcf_block_netif_keep_dst(struct tcf_block *block); int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, struct netlink_ext_ack *extack); int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, struct tcf_block_ext_info *ei, struct netlink_ext_ack *extack); void tcf_block_put(struct tcf_block *block); void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei); static inline bool tcf_block_shared(struct tcf_block *block) { return block->index; } static inline bool tcf_block_non_null_shared(struct tcf_block *block) { return block && block->index; } static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { WARN_ON(tcf_block_shared(block)); return block->q; } int tcf_classify(struct sk_buff *skb, const struct tcf_block *block, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); static inline bool tc_cls_stats_dump(struct tcf_proto *tp, struct tcf_walker *arg, void *filter) { if (arg->count >= arg->skip && arg->fn(tp, filter, arg) < 0) { arg->stop = 1; return false; } arg->count++; return true; } #else static inline bool tcf_block_shared(struct tcf_block *block) { return false; } static inline bool tcf_block_non_null_shared(struct tcf_block *block) { return false; } static inline int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, struct netlink_ext_ack *extack) { return 0; } static inline int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, struct tcf_block_ext_info *ei, struct netlink_ext_ack *extack) { return 0; } static inline void tcf_block_put(struct tcf_block *block) { } static inline void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei) { } static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { return NULL; } static inline int tc_setup_cb_block_register(struct tcf_block *block, flow_setup_cb_t *cb, void *cb_priv) { return 0; } static inline void tc_setup_cb_block_unregister(struct tcf_block *block, flow_setup_cb_t *cb, void *cb_priv) { } static inline int tcf_classify(struct sk_buff *skb, const struct tcf_block *block, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { return TC_ACT_UNSPEC; } #endif static inline unsigned long __cls_set_class(unsigned long *clp, unsigned long cl) { return xchg(clp, cl); } static inline void __tcf_bind_filter(struct Qdisc *q, struct tcf_result *r, unsigned long base) { unsigned long cl; cl = q->ops->cl_ops->bind_tcf(q, base, r->classid); cl = __cls_set_class(&r->class, cl); if (cl) q->ops->cl_ops->unbind_tcf(q, cl); } static inline void tcf_bind_filter(struct tcf_proto *tp, struct tcf_result *r, unsigned long base) { struct Qdisc *q = tp->chain->block->q; /* Check q as it is not set for shared blocks. In that case, * setting class is not supported. */ if (!q) return; sch_tree_lock(q); __tcf_bind_filter(q, r, base); sch_tree_unlock(q); } static inline void __tcf_unbind_filter(struct Qdisc *q, struct tcf_result *r) { unsigned long cl; if ((cl = __cls_set_class(&r->class, 0)) != 0) q->ops->cl_ops->unbind_tcf(q, cl); } static inline void tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r) { struct Qdisc *q = tp->chain->block->q; if (!q) return; __tcf_unbind_filter(q, r); } static inline void tc_cls_bind_class(u32 classid, unsigned long cl, void *q, struct tcf_result *res, unsigned long base) { if (res->classid == classid) { if (cl) __tcf_bind_filter(q, res, base); else __tcf_unbind_filter(q, res); } } struct tcf_exts { #ifdef CONFIG_NET_CLS_ACT __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ int nr_actions; struct tc_action **actions; struct net *net; netns_tracker ns_tracker; #endif /* Map to export classifier specific extension TLV types to the * generic extensions API. Unsupported extensions must be set to 0. */ int action; int police; }; static inline int tcf_exts_init(struct tcf_exts *exts, struct net *net, int action, int police) { #ifdef CONFIG_NET_CLS_ACT exts->type = 0; exts->nr_actions = 0; /* Note: we do not own yet a reference on net. * This reference might be taken later from tcf_exts_get_net(). */ exts->net = net; exts->actions = kcalloc(TCA_ACT_MAX_PRIO, sizeof(struct tc_action *), GFP_KERNEL); if (!exts->actions) return -ENOMEM; #endif exts->action = action; exts->police = police; return 0; } /* Return false if the netns is being destroyed in cleanup_net(). Callers * need to do cleanup synchronously in this case, otherwise may race with * tc_action_net_exit(). Return true for other cases. */ static inline bool tcf_exts_get_net(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT exts->net = maybe_get_net(exts->net); if (exts->net) netns_tracker_alloc(exts->net, &exts->ns_tracker, GFP_KERNEL); return exts->net != NULL; #else return true; #endif } static inline void tcf_exts_put_net(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT if (exts->net) put_net_track(exts->net, &exts->ns_tracker); #endif } #ifdef CONFIG_NET_CLS_ACT #define tcf_exts_for_each_action(i, a, exts) \ for (i = 0; i < TCA_ACT_MAX_PRIO && ((a) = (exts)->actions[i]); i++) #else #define tcf_exts_for_each_action(i, a, exts) \ for (; 0; (void)(i), (void)(a), (void)(exts)) #endif #define tcf_act_for_each_action(i, a, actions) \ for (i = 0; i < TCA_ACT_MAX_PRIO && ((a) = actions[i]); i++) static inline void tcf_exts_hw_stats_update(const struct tcf_exts *exts, u64 bytes, u64 packets, u64 drops, u64 lastuse, u8 used_hw_stats, bool used_hw_stats_valid) { #ifdef CONFIG_NET_CLS_ACT int i; for (i = 0; i < exts->nr_actions; i++) { struct tc_action *a = exts->actions[i]; /* if stats from hw, just skip */ if (tcf_action_update_hw_stats(a)) { preempt_disable(); tcf_action_stats_update(a, bytes, packets, drops, lastuse, true); preempt_enable(); a->used_hw_stats = used_hw_stats; a->used_hw_stats_valid = used_hw_stats_valid; } } #endif } /** * tcf_exts_has_actions - check if at least one action is present * @exts: tc filter extensions handle * * Returns true if at least one action is present. */ static inline bool tcf_exts_has_actions(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT return exts->nr_actions; #else return false; #endif } /** * tcf_exts_exec - execute tc filter extensions * @skb: socket buffer * @exts: tc filter extensions handle * @res: desired result * * Executes all configured extensions. Returns TC_ACT_OK on a normal execution, * a negative number if the filter must be considered unmatched or * a positive action code (TC_ACT_*) which must be returned to the * underlying layer. */ static inline int tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts, struct tcf_result *res) { #ifdef CONFIG_NET_CLS_ACT return tcf_action_exec(skb, exts->actions, exts->nr_actions, res); #endif return TC_ACT_OK; } int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, u32 flags, struct netlink_ext_ack *extack); int tcf_exts_validate_ex(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack); void tcf_exts_destroy(struct tcf_exts *exts); void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src); int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_terse_dump(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts); /** * struct tcf_pkt_info - packet information * * @ptr: start of the pkt data * @nexthdr: offset of the next header */ struct tcf_pkt_info { unsigned char * ptr; int nexthdr; }; #ifdef CONFIG_NET_EMATCH struct tcf_ematch_ops; /** * struct tcf_ematch - extended match (ematch) * * @matchid: identifier to allow userspace to reidentify a match * @flags: flags specifying attributes and the relation to other matches * @ops: the operations lookup table of the corresponding ematch module * @datalen: length of the ematch specific configuration data * @data: ematch specific data * @net: the network namespace */ struct tcf_ematch { struct tcf_ematch_ops * ops; unsigned long data; unsigned int datalen; u16 matchid; u16 flags; struct net *net; }; static inline int tcf_em_is_container(struct tcf_ematch *em) { return !em->ops; } static inline int tcf_em_is_simple(struct tcf_ematch *em) { return em->flags & TCF_EM_SIMPLE; } static inline int tcf_em_is_inverted(struct tcf_ematch *em) { return em->flags & TCF_EM_INVERT; } static inline int tcf_em_last_match(struct tcf_ematch *em) { return (em->flags & TCF_EM_REL_MASK) == TCF_EM_REL_END; } static inline int tcf_em_early_end(struct tcf_ematch *em, int result) { if (tcf_em_last_match(em)) return 1; if (result == 0 && em->flags & TCF_EM_REL_AND) return 1; if (result != 0 && em->flags & TCF_EM_REL_OR) return 1; return 0; } /** * struct tcf_ematch_tree - ematch tree handle * * @hdr: ematch tree header supplied by userspace * @matches: array of ematches */ struct tcf_ematch_tree { struct tcf_ematch_tree_hdr hdr; struct tcf_ematch * matches; }; /** * struct tcf_ematch_ops - ematch module operations * * @kind: identifier (kind) of this ematch module * @datalen: length of expected configuration data (optional) * @change: called during validation (optional) * @match: called during ematch tree evaluation, must return 1/0 * @destroy: called during destroyage (optional) * @dump: called during dumping process (optional) * @owner: owner, must be set to THIS_MODULE * @link: link to previous/next ematch module (internal use) */ struct tcf_ematch_ops { int kind; int datalen; int (*change)(struct net *net, void *, int, struct tcf_ematch *); int (*match)(struct sk_buff *, struct tcf_ematch *, struct tcf_pkt_info *); void (*destroy)(struct tcf_ematch *); int (*dump)(struct sk_buff *, struct tcf_ematch *); struct module *owner; struct list_head link; }; int tcf_em_register(struct tcf_ematch_ops *); void tcf_em_unregister(struct tcf_ematch_ops *); int tcf_em_tree_validate(struct tcf_proto *, struct nlattr *, struct tcf_ematch_tree *); void tcf_em_tree_destroy(struct tcf_ematch_tree *); int tcf_em_tree_dump(struct sk_buff *, struct tcf_ematch_tree *, int); int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *, struct tcf_pkt_info *); /** * tcf_em_tree_match - evaulate an ematch tree * * @skb: socket buffer of the packet in question * @tree: ematch tree to be used for evaluation * @info: packet information examined by classifier * * This function matches @skb against the ematch tree in @tree by going * through all ematches respecting their logic relations returning * as soon as the result is obvious. * * Returns 1 if the ematch tree as-one matches, no ematches are configured * or ematch is not enabled in the kernel, otherwise 0 is returned. */ static inline int tcf_em_tree_match(struct sk_buff *skb, struct tcf_ematch_tree *tree, struct tcf_pkt_info *info) { if (tree->hdr.nmatches) return __tcf_em_tree_match(skb, tree, info); else return 1; } #define MODULE_ALIAS_TCF_EMATCH(kind) MODULE_ALIAS("ematch-kind-" __stringify(kind)) #else /* CONFIG_NET_EMATCH */ struct tcf_ematch_tree { }; #define tcf_em_tree_validate(tp, tb, t) ((void)(t), 0) #define tcf_em_tree_destroy(t) do { (void)(t); } while(0) #define tcf_em_tree_dump(skb, t, tlv) (0) #define tcf_em_tree_match(skb, t, info) ((void)(info), 1) #endif /* CONFIG_NET_EMATCH */ static inline unsigned char * tcf_get_base_ptr(struct sk_buff *skb, int layer) { switch (layer) { case TCF_LAYER_LINK: return skb_mac_header(skb); case TCF_LAYER_NETWORK: return skb_network_header(skb); case TCF_LAYER_TRANSPORT: return skb_transport_header(skb); } return NULL; } static inline int tcf_valid_offset(const struct sk_buff *skb, const unsigned char *ptr, const int len) { return likely((ptr + len) <= skb_tail_pointer(skb) && ptr >= skb->head && (ptr <= (ptr + len))); } static inline int tcf_change_indev(struct net *net, struct nlattr *indev_tlv, struct netlink_ext_ack *extack) { char indev[IFNAMSIZ]; struct net_device *dev; if (nla_strscpy(indev, indev_tlv, IFNAMSIZ) < 0) { NL_SET_ERR_MSG_ATTR(extack, indev_tlv, "Interface name too long"); return -EINVAL; } dev = __dev_get_by_name(net, indev); if (!dev) { NL_SET_ERR_MSG_ATTR(extack, indev_tlv, "Network device not found"); return -ENODEV; } return dev->ifindex; } static inline bool tcf_match_indev(struct sk_buff *skb, int ifindex) { if (!ifindex) return true; if (!skb->skb_iif) return false; return ifindex == skb->skb_iif; } int tc_setup_offload_action(struct flow_action *flow_action, const struct tcf_exts *exts, struct netlink_ext_ack *extack); void tc_cleanup_offload_action(struct flow_action *flow_action); int tc_setup_action(struct flow_action *flow_action, struct tc_action *actions[], struct netlink_ext_ack *extack); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop, bool rtnl_held); int tc_setup_cb_add(struct tcf_block *block, struct tcf_proto *tp, enum tc_setup_type type, void *type_data, bool err_stop, u32 *flags, unsigned int *in_hw_count, bool rtnl_held); int tc_setup_cb_replace(struct tcf_block *block, struct tcf_proto *tp, enum tc_setup_type type, void *type_data, bool err_stop, u32 *old_flags, unsigned int *old_in_hw_count, u32 *new_flags, unsigned int *new_in_hw_count, bool rtnl_held); int tc_setup_cb_destroy(struct tcf_block *block, struct tcf_proto *tp, enum tc_setup_type type, void *type_data, bool err_stop, u32 *flags, unsigned int *in_hw_count, bool rtnl_held); int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, enum tc_setup_type type, void *type_data, void *cb_priv, u32 *flags, unsigned int *in_hw_count); unsigned int tcf_exts_num_actions(struct tcf_exts *exts); #ifdef CONFIG_NET_CLS_ACT int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch, enum flow_block_binder_type binder_type, struct nlattr *block_index_attr, struct netlink_ext_ack *extack); void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch); int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr, struct netlink_ext_ack *extack); struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb, struct sk_buff **to_free, int *ret); int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe); #else static inline int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch, enum flow_block_binder_type binder_type, struct nlattr *block_index_attr, struct netlink_ext_ack *extack) { return 0; } static inline void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch) { } static inline int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr, struct netlink_ext_ack *extack) { return 0; } static inline struct sk_buff * tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb, struct sk_buff **to_free, int *ret) { return skb; } static inline int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe) { return 0; } #endif struct tc_cls_u32_knode { struct tcf_exts *exts; struct tcf_result *res; struct tc_u32_sel *sel; u32 handle; u32 val; u32 mask; u32 link_handle; u8 fshift; }; struct tc_cls_u32_hnode { u32 handle; u32 prio; unsigned int divisor; }; enum tc_clsu32_command { TC_CLSU32_NEW_KNODE, TC_CLSU32_REPLACE_KNODE, TC_CLSU32_DELETE_KNODE, TC_CLSU32_NEW_HNODE, TC_CLSU32_REPLACE_HNODE, TC_CLSU32_DELETE_HNODE, }; struct tc_cls_u32_offload { struct flow_cls_common_offload common; /* knode values */ enum tc_clsu32_command command; union { struct tc_cls_u32_knode knode; struct tc_cls_u32_hnode hnode; }; }; static inline bool tc_can_offload(const struct net_device *dev) { return dev->features & NETIF_F_HW_TC; } static inline bool tc_can_offload_extack(const struct net_device *dev, struct netlink_ext_ack *extack) { bool can = tc_can_offload(dev); if (!can) NL_SET_ERR_MSG(extack, "TC offload is disabled on net device"); return can; } static inline bool tc_cls_can_offload_and_chain0(const struct net_device *dev, struct flow_cls_common_offload *common) { if (!tc_can_offload_extack(dev, common->extack)) return false; if (common->chain_index) { NL_SET_ERR_MSG(common->extack, "Driver supports only offload of chain 0"); return false; } return true; } static inline bool tc_skip_hw(u32 flags) { return (flags & TCA_CLS_FLAGS_SKIP_HW) ? true : false; } static inline bool tc_skip_sw(u32 flags) { return (flags & TCA_CLS_FLAGS_SKIP_SW) ? true : false; } /* SKIP_HW and SKIP_SW are mutually exclusive flags. */ static inline bool tc_flags_valid(u32 flags) { if (flags & ~(TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW | TCA_CLS_FLAGS_VERBOSE)) return false; flags &= TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW; if (!(flags ^ (TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW))) return false; return true; } static inline bool tc_in_hw(u32 flags) { return (flags & TCA_CLS_FLAGS_IN_HW) ? true : false; } static inline void tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common, const struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { cls_common->chain_index = tp->chain->index; cls_common->protocol = tp->protocol; cls_common->prio = tp->prio >> 16; if (tc_skip_sw(flags) || flags & TCA_CLS_FLAGS_VERBOSE) cls_common->extack = extack; } #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb) { struct tc_skb_ext *tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); if (tc_skb_ext) memset(tc_skb_ext, 0, sizeof(*tc_skb_ext)); return tc_skb_ext; } #endif enum tc_matchall_command { TC_CLSMATCHALL_REPLACE, TC_CLSMATCHALL_DESTROY, TC_CLSMATCHALL_STATS, }; struct tc_cls_matchall_offload { struct flow_cls_common_offload common; enum tc_matchall_command command; struct flow_rule *rule; struct flow_stats stats; unsigned long cookie; }; enum tc_clsbpf_command { TC_CLSBPF_OFFLOAD, TC_CLSBPF_STATS, }; struct tc_cls_bpf_offload { struct flow_cls_common_offload common; enum tc_clsbpf_command command; struct tcf_exts *exts; struct bpf_prog *prog; struct bpf_prog *oldprog; const char *name; bool exts_integrated; }; struct tc_mqprio_qopt_offload { /* struct tc_mqprio_qopt must always be the first element */ struct tc_mqprio_qopt qopt; u16 mode; u16 shaper; u32 flags; u64 min_rate[TC_QOPT_MAX_QUEUE]; u64 max_rate[TC_QOPT_MAX_QUEUE]; }; /* This structure holds cookie structure that is passed from user * to the kernel for actions and classifiers */ struct tc_cookie { u8 *data; u32 len; struct rcu_head rcu; }; struct tc_qopt_offload_stats { struct gnet_stats_basic_sync *bstats; struct gnet_stats_queue *qstats; }; enum tc_mq_command { TC_MQ_CREATE, TC_MQ_DESTROY, TC_MQ_STATS, TC_MQ_GRAFT, }; struct tc_mq_opt_offload_graft_params { unsigned long queue; u32 child_handle; }; struct tc_mq_qopt_offload { enum tc_mq_command command; u32 handle; union { struct tc_qopt_offload_stats stats; struct tc_mq_opt_offload_graft_params graft_params; }; }; enum tc_htb_command { /* Root */ TC_HTB_CREATE, /* Initialize HTB offload. */ TC_HTB_DESTROY, /* Destroy HTB offload. */ /* Classes */ /* Allocate qid and create leaf. */ TC_HTB_LEAF_ALLOC_QUEUE, /* Convert leaf to inner, preserve and return qid, create new leaf. */ TC_HTB_LEAF_TO_INNER, /* Delete leaf, while siblings remain. */ TC_HTB_LEAF_DEL, /* Delete leaf, convert parent to leaf, preserving qid. */ TC_HTB_LEAF_DEL_LAST, /* TC_HTB_LEAF_DEL_LAST, but delete driver data on hardware errors. */ TC_HTB_LEAF_DEL_LAST_FORCE, /* Modify parameters of a node. */ TC_HTB_NODE_MODIFY, /* Class qdisc */ TC_HTB_LEAF_QUERY_QUEUE, /* Query qid by classid. */ }; struct tc_htb_qopt_offload { struct netlink_ext_ack *extack; enum tc_htb_command command; u32 parent_classid; u16 classid; u16 qid; u64 rate; u64 ceil; }; #define TC_HTB_CLASSID_ROOT U32_MAX enum tc_red_command { TC_RED_REPLACE, TC_RED_DESTROY, TC_RED_STATS, TC_RED_XSTATS, TC_RED_GRAFT, }; struct tc_red_qopt_offload_params { u32 min; u32 max; u32 probability; u32 limit; bool is_ecn; bool is_harddrop; bool is_nodrop; struct gnet_stats_queue *qstats; }; struct tc_red_qopt_offload { enum tc_red_command command; u32 handle; u32 parent; union { struct tc_red_qopt_offload_params set; struct tc_qopt_offload_stats stats; struct red_stats *xstats; u32 child_handle; }; }; enum tc_gred_command { TC_GRED_REPLACE, TC_GRED_DESTROY, TC_GRED_STATS, }; struct tc_gred_vq_qopt_offload_params { bool present; u32 limit; u32 prio; u32 min; u32 max; bool is_ecn; bool is_harddrop; u32 probability; /* Only need backlog, see struct tc_prio_qopt_offload_params */ u32 *backlog; }; struct tc_gred_qopt_offload_params { bool grio_on; bool wred_on; unsigned int dp_cnt; unsigned int dp_def; struct gnet_stats_queue *qstats; struct tc_gred_vq_qopt_offload_params tab[MAX_DPs]; }; struct tc_gred_qopt_offload_stats { struct gnet_stats_basic_sync bstats[MAX_DPs]; struct gnet_stats_queue qstats[MAX_DPs]; struct red_stats *xstats[MAX_DPs]; }; struct tc_gred_qopt_offload { enum tc_gred_command command; u32 handle; u32 parent; union { struct tc_gred_qopt_offload_params set; struct tc_gred_qopt_offload_stats stats; }; }; enum tc_prio_command { TC_PRIO_REPLACE, TC_PRIO_DESTROY, TC_PRIO_STATS, TC_PRIO_GRAFT, }; struct tc_prio_qopt_offload_params { int bands; u8 priomap[TC_PRIO_MAX + 1]; /* At the point of un-offloading the Qdisc, the reported backlog and * qlen need to be reduced by the portion that is in HW. */ struct gnet_stats_queue *qstats; }; struct tc_prio_qopt_offload_graft_params { u8 band; u32 child_handle; }; struct tc_prio_qopt_offload { enum tc_prio_command command; u32 handle; u32 parent; union { struct tc_prio_qopt_offload_params replace_params; struct tc_qopt_offload_stats stats; struct tc_prio_qopt_offload_graft_params graft_params; }; }; enum tc_root_command { TC_ROOT_GRAFT, }; struct tc_root_qopt_offload { enum tc_root_command command; u32 handle; bool ingress; }; enum tc_ets_command { TC_ETS_REPLACE, TC_ETS_DESTROY, TC_ETS_STATS, TC_ETS_GRAFT, }; struct tc_ets_qopt_offload_replace_params { unsigned int bands; u8 priomap[TC_PRIO_MAX + 1]; unsigned int quanta[TCQ_ETS_MAX_BANDS]; /* 0 for strict bands. */ unsigned int weights[TCQ_ETS_MAX_BANDS]; struct gnet_stats_queue *qstats; }; struct tc_ets_qopt_offload_graft_params { u8 band; u32 child_handle; }; struct tc_ets_qopt_offload { enum tc_ets_command command; u32 handle; u32 parent; union { struct tc_ets_qopt_offload_replace_params replace_params; struct tc_qopt_offload_stats stats; struct tc_ets_qopt_offload_graft_params graft_params; }; }; enum tc_tbf_command { TC_TBF_REPLACE, TC_TBF_DESTROY, TC_TBF_STATS, TC_TBF_GRAFT, }; struct tc_tbf_qopt_offload_replace_params { struct psched_ratecfg rate; u32 max_size; struct gnet_stats_queue *qstats; }; struct tc_tbf_qopt_offload { enum tc_tbf_command command; u32 handle; u32 parent; union { struct tc_tbf_qopt_offload_replace_params replace_params; struct tc_qopt_offload_stats stats; u32 child_handle; }; }; enum tc_fifo_command { TC_FIFO_REPLACE, TC_FIFO_DESTROY, TC_FIFO_STATS, }; struct tc_fifo_qopt_offload { enum tc_fifo_command command; u32 handle; u32 parent; union { struct tc_qopt_offload_stats stats; }; }; #ifdef CONFIG_NET_CLS_ACT DECLARE_STATIC_KEY_FALSE(tc_skb_ext_tc); void tc_skb_ext_tc_enable(void); void tc_skb_ext_tc_disable(void); #define tc_skb_ext_tc_enabled() static_branch_unlikely(&tc_skb_ext_tc) #else /* CONFIG_NET_CLS_ACT */ static inline void tc_skb_ext_tc_enable(void) { } static inline void tc_skb_ext_tc_disable(void) { } #define tc_skb_ext_tc_enabled() false #endif #endif |
| 1416 1416 1416 1412 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2002, 2004 * Copyright (c) 2002 Intel Corp. * * This file is part of the SCTP kernel implementation * * Sysctl related interfaces for SCTP. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * Mingqin Liu <liuming@us.ibm.com> * Jon Grimm <jgrimm@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> * Ryan Layer <rmlayer@us.ibm.com> * Sridhar Samudrala <sri@us.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <net/sctp/structs.h> #include <net/sctp/sctp.h> #include <linux/sysctl.h> static int timer_max = 86400000; /* ms in one day */ static int sack_timer_min = 1; static int sack_timer_max = 500; static int addr_scope_max = SCTP_SCOPE_POLICY_MAX; static int rwnd_scale_max = 16; static int rto_alpha_min = 0; static int rto_beta_min = 0; static int rto_alpha_max = 1000; static int rto_beta_max = 1000; static int pf_expose_max = SCTP_PF_EXPOSE_MAX; static int ps_retrans_max = SCTP_PS_RETRANS_MAX; static int udp_port_max = 65535; static unsigned long max_autoclose_min = 0; static unsigned long max_autoclose_max = (MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX) ? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ; static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static int proc_sctp_do_auth(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static struct ctl_table sctp_table[] = { { .procname = "sctp_mem", .data = &sysctl_sctp_mem, .maxlen = sizeof(sysctl_sctp_mem), .mode = 0644, .proc_handler = proc_doulongvec_minmax }, { .procname = "sctp_rmem", .data = &sysctl_sctp_rmem, .maxlen = sizeof(sysctl_sctp_rmem), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "sctp_wmem", .data = &sysctl_sctp_wmem, .maxlen = sizeof(sysctl_sctp_wmem), .mode = 0644, .proc_handler = proc_dointvec, }, { /* sentinel */ } }; static struct ctl_table sctp_net_table[] = { { .procname = "rto_initial", .data = &init_net.sctp.rto_initial, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = &timer_max }, { .procname = "rto_min", .data = &init_net.sctp.rto_min, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_sctp_do_rto_min, .extra1 = SYSCTL_ONE, .extra2 = &init_net.sctp.rto_max }, { .procname = "rto_max", .data = &init_net.sctp.rto_max, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_sctp_do_rto_max, .extra1 = &init_net.sctp.rto_min, .extra2 = &timer_max }, { .procname = "rto_alpha_exp_divisor", .data = &init_net.sctp.rto_alpha, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_sctp_do_alpha_beta, .extra1 = &rto_alpha_min, .extra2 = &rto_alpha_max, }, { .procname = "rto_beta_exp_divisor", .data = &init_net.sctp.rto_beta, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_sctp_do_alpha_beta, .extra1 = &rto_beta_min, .extra2 = &rto_beta_max, }, { .procname = "max_burst", .data = &init_net.sctp.max_burst, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, }, { .procname = "cookie_preserve_enable", .data = &init_net.sctp.cookie_preserve_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "cookie_hmac_alg", .data = &init_net.sctp.sctp_hmac_alg, .maxlen = 8, .mode = 0644, .proc_handler = proc_sctp_do_hmac_alg, }, { .procname = "valid_cookie_life", .data = &init_net.sctp.valid_cookie_life, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = &timer_max }, { .procname = "sack_timeout", .data = &init_net.sctp.sack_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &sack_timer_min, .extra2 = &sack_timer_max, }, { .procname = "hb_interval", .data = &init_net.sctp.hb_interval, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = &timer_max }, { .procname = "association_max_retrans", .data = &init_net.sctp.max_retrans_association, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_INT_MAX, }, { .procname = "path_max_retrans", .data = &init_net.sctp.max_retrans_path, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_INT_MAX, }, { .procname = "max_init_retransmits", .data = &init_net.sctp.max_retrans_init, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_INT_MAX, }, { .procname = "pf_retrans", .data = &init_net.sctp.pf_retrans, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &init_net.sctp.ps_retrans, }, { .procname = "ps_retrans", .data = &init_net.sctp.ps_retrans, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &init_net.sctp.pf_retrans, .extra2 = &ps_retrans_max, }, { .procname = "sndbuf_policy", .data = &init_net.sctp.sndbuf_policy, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "rcvbuf_policy", .data = &init_net.sctp.rcvbuf_policy, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "default_auto_asconf", .data = &init_net.sctp.default_auto_asconf, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "addip_enable", .data = &init_net.sctp.addip_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "addip_noauth_enable", .data = &init_net.sctp.addip_noauth, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "prsctp_enable", .data = &init_net.sctp.prsctp_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "reconf_enable", .data = &init_net.sctp.reconf_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "auth_enable", .data = &init_net.sctp.auth_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_sctp_do_auth, }, { .procname = "intl_enable", .data = &init_net.sctp.intl_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "ecn_enable", .data = &init_net.sctp.ecn_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "plpmtud_probe_interval", .data = &init_net.sctp.probe_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_sctp_do_probe_interval, }, { .procname = "udp_port", .data = &init_net.sctp.udp_port, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_sctp_do_udp_port, .extra1 = SYSCTL_ZERO, .extra2 = &udp_port_max, }, { .procname = "encap_port", .data = &init_net.sctp.encap_port, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &udp_port_max, }, { .procname = "addr_scope_policy", .data = &init_net.sctp.scope_policy, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &addr_scope_max, }, { .procname = "rwnd_update_shift", .data = &init_net.sctp.rwnd_upd_shift, .maxlen = sizeof(int), .mode = 0644, .proc_handler = &proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = &rwnd_scale_max, }, { .procname = "max_autoclose", .data = &init_net.sctp.max_autoclose, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = &proc_doulongvec_minmax, .extra1 = &max_autoclose_min, .extra2 = &max_autoclose_max, }, { .procname = "pf_enable", .data = &init_net.sctp.pf_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "pf_expose", .data = &init_net.sctp.pf_expose, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &pf_expose_max, }, { /* sentinel */ } }; static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; struct ctl_table tbl; bool changed = false; char *none = "none"; char tmp[8] = {0}; int ret; memset(&tbl, 0, sizeof(struct ctl_table)); if (write) { tbl.data = tmp; tbl.maxlen = sizeof(tmp); } else { tbl.data = net->sctp.sctp_hmac_alg ? : none; tbl.maxlen = strlen(tbl.data); } ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) { #ifdef CONFIG_CRYPTO_MD5 if (!strncmp(tmp, "md5", 3)) { net->sctp.sctp_hmac_alg = "md5"; changed = true; } #endif #ifdef CONFIG_CRYPTO_SHA1 if (!strncmp(tmp, "sha1", 4)) { net->sctp.sctp_hmac_alg = "sha1"; changed = true; } #endif if (!strncmp(tmp, "none", 4)) { net->sctp.sctp_hmac_alg = NULL; changed = true; } if (!changed) ret = -EINVAL; } return ret; } static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; unsigned int min = *(unsigned int *) ctl->extra1; unsigned int max = *(unsigned int *) ctl->extra2; struct ctl_table tbl; int ret, new_value; memset(&tbl, 0, sizeof(struct ctl_table)); tbl.maxlen = sizeof(unsigned int); if (write) tbl.data = &new_value; else tbl.data = &net->sctp.rto_min; ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) { if (new_value > max || new_value < min) return -EINVAL; net->sctp.rto_min = new_value; } return ret; } static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; unsigned int min = *(unsigned int *) ctl->extra1; unsigned int max = *(unsigned int *) ctl->extra2; struct ctl_table tbl; int ret, new_value; memset(&tbl, 0, sizeof(struct ctl_table)); tbl.maxlen = sizeof(unsigned int); if (write) tbl.data = &new_value; else tbl.data = &net->sctp.rto_max; ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) { if (new_value > max || new_value < min) return -EINVAL; net->sctp.rto_max = new_value; } return ret; } static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (write) pr_warn_once("Changing rto_alpha or rto_beta may lead to " "suboptimal rtt/srtt estimations!\n"); return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); } static int proc_sctp_do_auth(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; struct ctl_table tbl; int new_value, ret; memset(&tbl, 0, sizeof(struct ctl_table)); tbl.maxlen = sizeof(unsigned int); if (write) tbl.data = &new_value; else tbl.data = &net->sctp.auth_enable; ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) { struct sock *sk = net->sctp.ctl_sock; net->sctp.auth_enable = new_value; /* Update the value in the control socket */ lock_sock(sk); sctp_sk(sk)->ep->auth_enable = new_value; release_sock(sk); } return ret; } static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; unsigned int min = *(unsigned int *)ctl->extra1; unsigned int max = *(unsigned int *)ctl->extra2; struct ctl_table tbl; int ret, new_value; memset(&tbl, 0, sizeof(struct ctl_table)); tbl.maxlen = sizeof(unsigned int); if (write) tbl.data = &new_value; else tbl.data = &net->sctp.udp_port; ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) { struct sock *sk = net->sctp.ctl_sock; if (new_value > max || new_value < min) return -EINVAL; net->sctp.udp_port = new_value; sctp_udp_sock_stop(net); if (new_value) { ret = sctp_udp_sock_start(net); if (ret) net->sctp.udp_port = 0; } /* Update the value in the control socket */ lock_sock(sk); sctp_sk(sk)->udp_port = htons(net->sctp.udp_port); release_sock(sk); } return ret; } static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; struct ctl_table tbl; int ret, new_value; memset(&tbl, 0, sizeof(struct ctl_table)); tbl.maxlen = sizeof(unsigned int); if (write) tbl.data = &new_value; else tbl.data = &net->sctp.probe_interval; ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) { if (new_value && new_value < SCTP_PROBE_TIMER_MIN) return -EINVAL; net->sctp.probe_interval = new_value; } return ret; } int sctp_sysctl_net_register(struct net *net) { struct ctl_table *table; int i; table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL); if (!table) return -ENOMEM; for (i = 0; table[i].data; i++) table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp; net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table); if (net->sctp.sysctl_header == NULL) { kfree(table); return -ENOMEM; } return 0; } void sctp_sysctl_net_unregister(struct net *net) { struct ctl_table *table; table = net->sctp.sysctl_header->ctl_table_arg; unregister_net_sysctl_table(net->sctp.sysctl_header); kfree(table); } static struct ctl_table_header *sctp_sysctl_header; /* Sysctl registration. */ void sctp_sysctl_register(void) { sctp_sysctl_header = register_net_sysctl(&init_net, "net/sctp", sctp_table); } /* Sysctl deregistration. */ void sctp_sysctl_unregister(void) { unregister_net_sysctl_table(sctp_sysctl_header); } |
| 619 619 620 620 620 620 567 3284 620 620 618 620 619 620 10 620 620 568 3283 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 | // SPDX-License-Identifier: GPL-2.0 /* * A fast, small, non-recursive O(n log n) sort for the Linux kernel * * This performs n*log2(n) + 0.37*n + o(n) comparisons on average, * and 1.5*n*log2(n) + O(n) in the (very contrived) worst case. * * Glibc qsort() manages n*log2(n) - 1.26*n for random inputs (1.63*n * better) at the expense of stack usage and much larger code to avoid * quicksort's O(n^2) worst case. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/export.h> #include <linux/sort.h> /** * is_aligned - is this pointer & size okay for word-wide copying? * @base: pointer to data * @size: size of each element * @align: required alignment (typically 4 or 8) * * Returns true if elements can be copied using word loads and stores. * The size must be a multiple of the alignment, and the base address must * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS. * * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)" * to "if ((a | b) & mask)", so we do that by hand. */ __attribute_const__ __always_inline static bool is_aligned(const void *base, size_t size, unsigned char align) { unsigned char lsbits = (unsigned char)size; (void)base; #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS lsbits |= (unsigned char)(uintptr_t)base; #endif return (lsbits & (align - 1)) == 0; } /** * swap_words_32 - swap two elements in 32-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 4) * * Exchange the two objects in memory. This exploits base+index addressing, * which basically all CPUs have, to minimize loop overhead computations. * * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the * bottom of the loop, even though the zero flag is still valid from the * subtract (since the intervening mov instructions don't alter the flags). * Gcc 8.1.0 doesn't have that problem. */ static void swap_words_32(void *a, void *b, size_t n) { do { u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; } while (n); } /** * swap_words_64 - swap two elements in 64-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 8) * * Exchange the two objects in memory. This exploits base+index * addressing, which basically all CPUs have, to minimize loop overhead * computations. * * We'd like to use 64-bit loads if possible. If they're not, emulating * one requires base+index+4 addressing which x86 has but most other * processors do not. If CONFIG_64BIT, we definitely have 64-bit loads, * but it's possible to have 64-bit loads without 64-bit pointers (e.g. * x32 ABI). Are there any cases the kernel needs to worry about? */ static void swap_words_64(void *a, void *b, size_t n) { do { #ifdef CONFIG_64BIT u64 t = *(u64 *)(a + (n -= 8)); *(u64 *)(a + n) = *(u64 *)(b + n); *(u64 *)(b + n) = t; #else /* Use two 32-bit transfers to avoid base+index+4 addressing */ u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; #endif } while (n); } /** * swap_bytes - swap two elements a byte at a time * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size * * This is the fallback if alignment doesn't allow using larger chunks. */ static void swap_bytes(void *a, void *b, size_t n) { do { char t = ((char *)a)[--n]; ((char *)a)[n] = ((char *)b)[n]; ((char *)b)[n] = t; } while (n); } /* * The values are arbitrary as long as they can't be confused with * a pointer, but small integers make for the smallest compare * instructions. */ #define SWAP_WORDS_64 (swap_r_func_t)0 #define SWAP_WORDS_32 (swap_r_func_t)1 #define SWAP_BYTES (swap_r_func_t)2 #define SWAP_WRAPPER (swap_r_func_t)3 struct wrapper { cmp_func_t cmp; swap_func_t swap; }; /* * The function pointer is last to make tail calls most efficient if the * compiler decides not to inline this function. */ static void do_swap(void *a, void *b, size_t size, swap_r_func_t swap_func, const void *priv) { if (swap_func == SWAP_WRAPPER) { ((const struct wrapper *)priv)->swap(a, b, (int)size); return; } if (swap_func == SWAP_WORDS_64) swap_words_64(a, b, size); else if (swap_func == SWAP_WORDS_32) swap_words_32(a, b, size); else if (swap_func == SWAP_BYTES) swap_bytes(a, b, size); else swap_func(a, b, (int)size, priv); } #define _CMP_WRAPPER ((cmp_r_func_t)0L) static int do_cmp(const void *a, const void *b, cmp_r_func_t cmp, const void *priv) { if (cmp == _CMP_WRAPPER) return ((const struct wrapper *)priv)->cmp(a, b); return cmp(a, b, priv); } /** * parent - given the offset of the child, find the offset of the parent. * @i: the offset of the heap element whose parent is sought. Non-zero. * @lsbit: a precomputed 1-bit mask, equal to "size & -size" * @size: size of each element * * In terms of array indexes, the parent of element j = @i/@size is simply * (j-1)/2. But when working in byte offsets, we can't use implicit * truncation of integer divides. * * Fortunately, we only need one bit of the quotient, not the full divide. * @size has a least significant bit. That bit will be clear if @i is * an even multiple of @size, and set if it's an odd multiple. * * Logically, we're doing "if (i & lsbit) i -= size;", but since the * branch is unpredictable, it's done with a bit of clever branch-free * code instead. */ __attribute_const__ __always_inline static size_t parent(size_t i, unsigned int lsbit, size_t size) { i -= size; i -= size & -(i & lsbit); return i / 2; } /** * sort_r - sort an array of elements * @base: pointer to data to sort * @num: number of elements * @size: size of each element * @cmp_func: pointer to comparison function * @swap_func: pointer to swap function or NULL * @priv: third argument passed to comparison function * * This function does a heapsort on the given array. You may provide * a swap_func function if you need to do something more than a memory * copy (e.g. fix up pointers or auxiliary data), but the built-in swap * avoids a slow retpoline and so is significantly faster. * * Sorting time is O(n log n) both on average and worst-case. While * quicksort is slightly faster on average, it suffers from exploitable * O(n*n) worst-case behavior and extra memory requirements that make * it less suitable for kernel use. */ void sort_r(void *base, size_t num, size_t size, cmp_r_func_t cmp_func, swap_r_func_t swap_func, const void *priv) { /* pre-scale counters for performance */ size_t n = num * size, a = (num/2) * size; const unsigned int lsbit = size & -size; /* Used to find parent */ if (!a) /* num < 2 || size == 0 */ return; /* called from 'sort' without swap function, let's pick the default */ if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap) swap_func = NULL; if (!swap_func) { if (is_aligned(base, size, 8)) swap_func = SWAP_WORDS_64; else if (is_aligned(base, size, 4)) swap_func = SWAP_WORDS_32; else swap_func = SWAP_BYTES; } /* * Loop invariants: * 1. elements [a,n) satisfy the heap property (compare greater than * all of their children), * 2. elements [n,num*size) are sorted, and * 3. a <= b <= c <= d <= n (whenever they are valid). */ for (;;) { size_t b, c, d; if (a) /* Building heap: sift down --a */ a -= size; else if (n -= size) /* Sorting: Extract root to --n */ do_swap(base, base + n, size, swap_func, priv); else /* Sort complete */ break; /* * Sift element at "a" down into heap. This is the * "bottom-up" variant, which significantly reduces * calls to cmp_func(): we find the sift-down path all * the way to the leaves (one compare per level), then * backtrack to find where to insert the target element. * * Because elements tend to sift down close to the leaves, * this uses fewer compares than doing two per level * on the way down. (A bit more than half as many on * average, 3/4 worst-case.) */ for (b = a; c = 2*b + size, (d = c + size) < n;) b = do_cmp(base + c, base + d, cmp_func, priv) >= 0 ? c : d; if (d == n) /* Special case last leaf with no sibling */ b = c; /* Now backtrack from "b" to the correct location for "a" */ while (b != a && do_cmp(base + a, base + b, cmp_func, priv) >= 0) b = parent(b, lsbit, size); c = b; /* Where "a" belongs */ while (b != a) { /* Shift it into place */ b = parent(b, lsbit, size); do_swap(base + b, base + c, size, swap_func, priv); } } } EXPORT_SYMBOL(sort_r); void sort(void *base, size_t num, size_t size, cmp_func_t cmp_func, swap_func_t swap_func) { struct wrapper w = { .cmp = cmp_func, .swap = swap_func, }; return sort_r(base, num, size, _CMP_WRAPPER, SWAP_WRAPPER, &w); } EXPORT_SYMBOL(sort); |
| 13281 2061 1800 1503 13265 13268 105 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Latched RB-trees * * Copyright (C) 2015 Intel Corp., Peter Zijlstra <peterz@infradead.org> * * Since RB-trees have non-atomic modifications they're not immediately suited * for RCU/lockless queries. Even though we made RB-tree lookups non-fatal for * lockless lookups; we cannot guarantee they return a correct result. * * The simplest solution is a seqlock + RB-tree, this will allow lockless * lookups; but has the constraint (inherent to the seqlock) that read sides * cannot nest in write sides. * * If we need to allow unconditional lookups (say as required for NMI context * usage) we need a more complex setup; this data structure provides this by * employing the latch technique -- see @raw_write_seqcount_latch -- to * implement a latched RB-tree which does allow for unconditional lookups by * virtue of always having (at least) one stable copy of the tree. * * However, while we have the guarantee that there is at all times one stable * copy, this does not guarantee an iteration will not observe modifications. * What might have been a stable copy at the start of the iteration, need not * remain so for the duration of the iteration. * * Therefore, this does require a lockless RB-tree iteration to be non-fatal; * see the comment in lib/rbtree.c. Note however that we only require the first * condition -- not seeing partial stores -- because the latch thing isolates * us from loops. If we were to interrupt a modification the lookup would be * pointed at the stable tree and complete while the modification was halted. */ #ifndef RB_TREE_LATCH_H #define RB_TREE_LATCH_H #include <linux/rbtree.h> #include <linux/seqlock.h> #include <linux/rcupdate.h> struct latch_tree_node { struct rb_node node[2]; }; struct latch_tree_root { seqcount_latch_t seq; struct rb_root tree[2]; }; /** * latch_tree_ops - operators to define the tree order * @less: used for insertion; provides the (partial) order between two elements. * @comp: used for lookups; provides the order between the search key and an element. * * The operators are related like: * * comp(a->key,b) < 0 := less(a,b) * comp(a->key,b) > 0 := less(b,a) * comp(a->key,b) == 0 := !less(a,b) && !less(b,a) * * If these operators define a partial order on the elements we make no * guarantee on which of the elements matching the key is found. See * latch_tree_find(). */ struct latch_tree_ops { bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b); int (*comp)(void *key, struct latch_tree_node *b); }; static __always_inline struct latch_tree_node * __lt_from_rb(struct rb_node *node, int idx) { return container_of(node, struct latch_tree_node, node[idx]); } static __always_inline void __lt_insert(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx, bool (*less)(struct latch_tree_node *a, struct latch_tree_node *b)) { struct rb_root *root = <r->tree[idx]; struct rb_node **link = &root->rb_node; struct rb_node *node = <n->node[idx]; struct rb_node *parent = NULL; struct latch_tree_node *ltp; while (*link) { parent = *link; ltp = __lt_from_rb(parent, idx); if (less(ltn, ltp)) link = &parent->rb_left; else link = &parent->rb_right; } rb_link_node_rcu(node, parent, link); rb_insert_color(node, root); } static __always_inline void __lt_erase(struct latch_tree_node *ltn, struct latch_tree_root *ltr, int idx) { rb_erase(<n->node[idx], <r->tree[idx]); } static __always_inline struct latch_tree_node * __lt_find(void *key, struct latch_tree_root *ltr, int idx, int (*comp)(void *key, struct latch_tree_node *node)) { struct rb_node *node = rcu_dereference_raw(ltr->tree[idx].rb_node); struct latch_tree_node *ltn; int c; while (node) { ltn = __lt_from_rb(node, idx); c = comp(key, ltn); if (c < 0) node = rcu_dereference_raw(node->rb_left); else if (c > 0) node = rcu_dereference_raw(node->rb_right); else return ltn; } return NULL; } /** * latch_tree_insert() - insert @node into the trees @root * @node: nodes to insert * @root: trees to insert @node into * @ops: operators defining the node order * * It inserts @node into @root in an ordered fashion such that we can always * observe one complete tree. See the comment for raw_write_seqcount_latch(). * * The inserts use rcu_assign_pointer() to publish the element such that the * tree structure is stored before we can observe the new @node. * * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be * serialized. */ static __always_inline void latch_tree_insert(struct latch_tree_node *node, struct latch_tree_root *root, const struct latch_tree_ops *ops) { raw_write_seqcount_latch(&root->seq); __lt_insert(node, root, 0, ops->less); raw_write_seqcount_latch(&root->seq); __lt_insert(node, root, 1, ops->less); } /** * latch_tree_erase() - removes @node from the trees @root * @node: nodes to remote * @root: trees to remove @node from * @ops: operators defining the node order * * Removes @node from the trees @root in an ordered fashion such that we can * always observe one complete tree. See the comment for * raw_write_seqcount_latch(). * * It is assumed that @node will observe one RCU quiescent state before being * reused of freed. * * All modifications (latch_tree_insert, latch_tree_remove) are assumed to be * serialized. */ static __always_inline void latch_tree_erase(struct latch_tree_node *node, struct latch_tree_root *root, const struct latch_tree_ops *ops) { raw_write_seqcount_latch(&root->seq); __lt_erase(node, root, 0); raw_write_seqcount_latch(&root->seq); __lt_erase(node, root, 1); } /** * latch_tree_find() - find the node matching @key in the trees @root * @key: search key * @root: trees to search for @key * @ops: operators defining the node order * * Does a lockless lookup in the trees @root for the node matching @key. * * It is assumed that this is called while holding the appropriate RCU read * side lock. * * If the operators define a partial order on the elements (there are multiple * elements which have the same key value) it is undefined which of these * elements will be found. Nor is it possible to iterate the tree to find * further elements with the same key value. * * Returns: a pointer to the node matching @key or NULL. */ static __always_inline struct latch_tree_node * latch_tree_find(void *key, struct latch_tree_root *root, const struct latch_tree_ops *ops) { struct latch_tree_node *node; unsigned int seq; do { seq = raw_read_seqcount_latch(&root->seq); node = __lt_find(key, root, seq & 1, ops->comp); } while (read_seqcount_latch_retry(&root->seq, seq)); return node; } #endif /* RB_TREE_LATCH_H */ |
| 1232 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/dsa.h - Driver for Distributed Switch Architecture switch chips * Copyright (c) 2008-2009 Marvell Semiconductor */ #ifndef __LINUX_NET_DSA_H #define __LINUX_NET_DSA_H #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/of.h> #include <linux/ethtool.h> #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/platform_data/dsa.h> #include <linux/phylink.h> #include <net/devlink.h> #include <net/switchdev.h> struct tc_action; struct phy_device; struct fixed_phy_status; struct phylink_link_state; #define DSA_TAG_PROTO_NONE_VALUE 0 #define DSA_TAG_PROTO_BRCM_VALUE 1 #define DSA_TAG_PROTO_BRCM_PREPEND_VALUE 2 #define DSA_TAG_PROTO_DSA_VALUE 3 #define DSA_TAG_PROTO_EDSA_VALUE 4 #define DSA_TAG_PROTO_GSWIP_VALUE 5 #define DSA_TAG_PROTO_KSZ9477_VALUE 6 #define DSA_TAG_PROTO_KSZ9893_VALUE 7 #define DSA_TAG_PROTO_LAN9303_VALUE 8 #define DSA_TAG_PROTO_MTK_VALUE 9 #define DSA_TAG_PROTO_QCA_VALUE 10 #define DSA_TAG_PROTO_TRAILER_VALUE 11 #define DSA_TAG_PROTO_8021Q_VALUE 12 #define DSA_TAG_PROTO_SJA1105_VALUE 13 #define DSA_TAG_PROTO_KSZ8795_VALUE 14 #define DSA_TAG_PROTO_OCELOT_VALUE 15 #define DSA_TAG_PROTO_AR9331_VALUE 16 #define DSA_TAG_PROTO_RTL4_A_VALUE 17 #define DSA_TAG_PROTO_HELLCREEK_VALUE 18 #define DSA_TAG_PROTO_XRS700X_VALUE 19 #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 #define DSA_TAG_PROTO_SJA1110_VALUE 23 #define DSA_TAG_PROTO_RTL8_4_VALUE 24 #define DSA_TAG_PROTO_RTL8_4T_VALUE 25 #define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 #define DSA_TAG_PROTO_LAN937X_VALUE 27 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, DSA_TAG_PROTO_BRCM = DSA_TAG_PROTO_BRCM_VALUE, DSA_TAG_PROTO_BRCM_LEGACY = DSA_TAG_PROTO_BRCM_LEGACY_VALUE, DSA_TAG_PROTO_BRCM_PREPEND = DSA_TAG_PROTO_BRCM_PREPEND_VALUE, DSA_TAG_PROTO_DSA = DSA_TAG_PROTO_DSA_VALUE, DSA_TAG_PROTO_EDSA = DSA_TAG_PROTO_EDSA_VALUE, DSA_TAG_PROTO_GSWIP = DSA_TAG_PROTO_GSWIP_VALUE, DSA_TAG_PROTO_KSZ9477 = DSA_TAG_PROTO_KSZ9477_VALUE, DSA_TAG_PROTO_KSZ9893 = DSA_TAG_PROTO_KSZ9893_VALUE, DSA_TAG_PROTO_LAN9303 = DSA_TAG_PROTO_LAN9303_VALUE, DSA_TAG_PROTO_MTK = DSA_TAG_PROTO_MTK_VALUE, DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE, DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE, DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE, DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE, DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE, }; struct dsa_switch; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); int (*connect)(struct dsa_switch *ds); void (*disconnect)(struct dsa_switch *ds); unsigned int needed_headroom; unsigned int needed_tailroom; const char *name; enum dsa_tag_protocol proto; /* Some tagging protocols either mangle or shift the destination MAC * address, in which case the DSA master would drop packets on ingress * if what it understands out of the destination MAC address is not in * its RX filter. */ bool promisc_on_master; }; /* This structure defines the control interfaces that are overlayed by the * DSA layer on top of the DSA CPU/management net_device instance. This is * used by the core net_device layer while calling various net_device_ops * function pointers. */ struct dsa_netdevice_ops { int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); }; #define DSA_TAG_DRIVER_ALIAS "dsa_tag-" #define MODULE_ALIAS_DSA_TAG_DRIVER(__proto) \ MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS __stringify(__proto##_VALUE)) struct dsa_lag { struct net_device *dev; unsigned int id; struct mutex fdb_lock; struct list_head fdbs; refcount_t refcount; }; struct dsa_switch_tree { struct list_head list; /* List of switch ports */ struct list_head ports; /* Notifier chain for switch-wide events */ struct raw_notifier_head nh; /* Tree identifier */ unsigned int index; /* Number of switches attached to this tree */ struct kref refcount; /* Maps offloaded LAG netdevs to a zero-based linear ID for * drivers that need it. */ struct dsa_lag **lags; /* Tagging protocol operations */ const struct dsa_device_ops *tag_ops; /* Default tagging protocol preferred by the switches in this * tree. */ enum dsa_tag_protocol default_proto; /* Has this tree been applied to the hardware? */ bool setup; /* * Configuration data for the platform device that owns * this dsa switch tree instance. */ struct dsa_platform_data *pd; /* List of DSA links composing the routing table */ struct list_head rtable; /* Length of "lags" array */ unsigned int lags_len; /* Track the largest switch index within a tree */ unsigned int last_switch; }; /* LAG IDs are one-based, the dst->lags array is zero-based */ #define dsa_lags_foreach_id(_id, _dst) \ for ((_id) = 1; (_id) <= (_dst)->lags_len; (_id)++) \ if ((_dst)->lags[(_id) - 1]) #define dsa_lag_foreach_port(_dp, _dst, _lag) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_offloads_lag((_dp), (_lag))) #define dsa_hsr_foreach_port(_dp, _ds, _hsr) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds) && (_dp)->hsr_dev == (_hsr)) static inline struct dsa_lag *dsa_lag_by_id(struct dsa_switch_tree *dst, unsigned int id) { /* DSA LAG IDs are one-based, dst->lags is zero-based */ return dst->lags[id - 1]; } static inline int dsa_lag_id(struct dsa_switch_tree *dst, struct net_device *lag_dev) { unsigned int id; dsa_lags_foreach_id(id, dst) { struct dsa_lag *lag = dsa_lag_by_id(dst, id); if (lag->dev == lag_dev) return lag->id; } return -ENODEV; } /* TC matchall action types */ enum dsa_port_mall_action_type { DSA_PORT_MALL_MIRROR, DSA_PORT_MALL_POLICER, }; /* TC mirroring entry */ struct dsa_mall_mirror_tc_entry { u8 to_local_port; bool ingress; }; /* TC port policer entry */ struct dsa_mall_policer_tc_entry { u32 burst; u64 rate_bytes_per_sec; }; /* TC matchall entry */ struct dsa_mall_tc_entry { struct list_head list; unsigned long cookie; enum dsa_port_mall_action_type type; union { struct dsa_mall_mirror_tc_entry mirror; struct dsa_mall_policer_tc_entry policer; }; }; struct dsa_bridge { struct net_device *dev; unsigned int num; bool tx_fwd_offload; refcount_t refcount; }; struct dsa_port { /* A CPU port is physically connected to a master device. * A user port exposed to userspace has a slave device. */ union { struct net_device *master; struct net_device *slave; }; /* Copy of the tagging protocol operations, for quicker access * in the data path. Valid only for the CPU ports. */ const struct dsa_device_ops *tag_ops; /* Copies for faster access in master receive hot path */ struct dsa_switch_tree *dst; struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); struct dsa_switch *ds; unsigned int index; enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU, DSA_PORT_TYPE_DSA, DSA_PORT_TYPE_USER, } type; const char *name; struct dsa_port *cpu_dp; u8 mac[ETH_ALEN]; u8 stp_state; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u8 vlan_filtering:1; /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ u8 learning:1; u8 lag_tx_enabled:1; /* Master state bits, valid only on CPU ports */ u8 master_admin_up:1; u8 master_oper_up:1; /* Valid only on user ports */ u8 cpu_port_in_lag:1; u8 setup:1; struct device_node *dn; unsigned int ageing_time; struct dsa_bridge *bridge; struct devlink_port devlink_port; struct phylink *pl; struct phylink_config pl_config; struct dsa_lag *lag; struct net_device *hsr_dev; struct list_head list; /* * Original copy of the master netdev ethtool_ops */ const struct ethtool_ops *orig_ethtool_ops; /* * Original copy of the master netdev net_device_ops */ const struct dsa_netdevice_ops *netdev_ops; /* List of MAC addresses that must be forwarded on this port. * These are only valid on CPU ports and DSA links. */ struct mutex addr_lists_lock; struct list_head fdbs; struct list_head mdbs; /* List of VLANs that CPU and DSA ports are members of. */ struct mutex vlans_lock; struct list_head vlans; }; /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, * so keep it stupid at the moment and list them all. */ struct dsa_link { struct dsa_port *dp; struct dsa_port *link_dp; struct list_head list; }; enum dsa_db_type { DSA_DB_PORT, DSA_DB_LAG, DSA_DB_BRIDGE, }; struct dsa_db { enum dsa_db_type type; union { const struct dsa_port *dp; struct dsa_lag lag; struct dsa_bridge bridge; }; }; struct dsa_mac_addr { unsigned char addr[ETH_ALEN]; u16 vid; refcount_t refcount; struct list_head list; struct dsa_db db; }; struct dsa_vlan { u16 vid; refcount_t refcount; struct list_head list; }; struct dsa_switch { struct device *dev; /* * Parent switch tree, and switch index. */ struct dsa_switch_tree *dst; unsigned int index; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u32 setup:1; /* Disallow bridge core from requesting different VLAN awareness * settings on ports if not hardware-supported */ u32 vlan_filtering_is_global:1; /* Keep VLAN filtering enabled on ports not offloading any upper */ u32 needs_standalone_vlan_filtering:1; /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges * that have vlan_filtering=0. All drivers should ideally set this (and * then the option would get removed), but it is unknown whether this * would break things or not. */ u32 configure_vlan_while_not_filtering:1; /* If the switch driver always programs the CPU port as egress tagged * despite the VLAN configuration indicating otherwise, then setting * @untag_bridge_pvid will force the DSA receive path to pop the * bridge's default_pvid VLAN tagged frames to offer a consistent * behavior between a vlan_filtering=0 and vlan_filtering=1 bridge * device. */ u32 untag_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. */ u32 assisted_learning_on_cpu_port:1; /* In case vlan_filtering_is_global is set, the VLAN awareness state * should be retrieved from here and not from the per-port settings. */ u32 vlan_filtering:1; /* For switches that only have the MRU configurable. To ensure the * configured MTU is not exceeded, normalization of MRU on all bridged * interfaces is needed. */ u32 mtu_enforcement_ingress:1; /* Drivers that isolate the FDBs of multiple bridges must set this * to true to receive the bridge as an argument in .port_fdb_{add,del} * and .port_mdb_{add,del}. Otherwise, the bridge.num will always be * passed as zero. */ u32 fdb_isolation:1; /* Listener for switch fabric events */ struct notifier_block nb; /* * Give the switch driver somewhere to hang its private data * structure. */ void *priv; void *tagger_data; /* * Configuration data for this switch. */ struct dsa_chip_data *cd; /* * The switch operations. */ const struct dsa_switch_ops *ops; /* * Slave mii_bus and devices for the individual ports. */ u32 phys_mii_mask; struct mii_bus *slave_mii_bus; /* Ageing Time limits in msecs */ unsigned int ageing_time_min; unsigned int ageing_time_max; /* Storage for drivers using tag_8021q */ struct dsa_8021q_context *tag_8021q_ctx; /* devlink used to represent this switch device */ struct devlink *devlink; /* Number of switch port queues */ unsigned int num_tx_queues; /* Drivers that benefit from having an ID associated with each * offloaded LAG should set this to the maximum number of * supported IDs. DSA will then maintain a mapping of _at * least_ these many IDs, accessible to drivers via * dsa_lag_id(). */ unsigned int num_lag_ids; /* Drivers that support bridge forwarding offload or FDB isolation * should set this to the maximum number of bridges spanning the same * switch tree (or all trees, in the case of cross-tree bridging * support) that can be offloaded. */ unsigned int max_num_bridges; unsigned int num_ports; }; static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) { struct dsa_switch_tree *dst = ds->dst; struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dp->ds == ds && dp->index == p) return dp; return NULL; } static inline bool dsa_port_is_dsa(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_port_is_cpu(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_port_is_user(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_USER; } static inline bool dsa_port_is_unused(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_port_master_is_operational(struct dsa_port *dp) { return dsa_port_is_cpu(dp) && dp->master_admin_up && dp->master_oper_up; } static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER; } #define dsa_tree_for_each_user_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_user_port_continue_reverse(_dp, _dst) \ list_for_each_entry_continue_reverse((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_cpu_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_port(_dp, _ds) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_safe(_dp, _next, _ds) \ list_for_each_entry_safe((_dp), (_next), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_continue_reverse(_dp, _ds) \ list_for_each_entry_continue_reverse((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_available_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (!dsa_port_is_unused((_dp))) #define dsa_switch_for_each_user_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_cpu_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) static inline u32 dsa_user_ports(struct dsa_switch *ds) { struct dsa_port *dp; u32 mask = 0; dsa_switch_for_each_user_port(dp, ds) mask |= BIT(dp->index); return mask; } static inline u32 dsa_cpu_ports(struct dsa_switch *ds) { struct dsa_port *cpu_dp; u32 mask = 0; dsa_switch_for_each_cpu_port(cpu_dp, ds) mask |= BIT(cpu_dp->index); return mask; } /* Return the local port used to reach an arbitrary switch device */ static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device) { struct dsa_switch_tree *dst = ds->dst; struct dsa_link *dl; list_for_each_entry(dl, &dst->rtable, list) if (dl->dp->ds == ds && dl->link_dp->ds->index == device) return dl->dp->index; return ds->num_ports; } /* Return the local port used to reach an arbitrary switch port */ static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device, int port) { if (device == ds->index) return port; else return dsa_routing_port(ds, device); } /* Return the local port used to reach the dedicated CPU port */ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port) { const struct dsa_port *dp = dsa_to_port(ds, port); const struct dsa_port *cpu_dp = dp->cpu_dp; if (!cpu_dp) return port; return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index); } /* Return true if this is the local port used to reach the CPU port */ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) { if (dsa_is_unused_port(ds, port)) return false; return port == dsa_upstream_port(ds, port); } /* Return true if this is a DSA port leading away from the CPU */ static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port) { return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port); } /* Return the local port used to reach the CPU port */ static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) { struct dsa_port *dp; dsa_switch_for_each_available_port(dp, ds) { return dsa_upstream_port(ds, dp->index); } return ds->num_ports; } /* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning * that the routing port from @downstream_ds to @upstream_ds is also the port * which @downstream_ds uses to reach its dedicated CPU. */ static inline bool dsa_switch_is_upstream_of(struct dsa_switch *upstream_ds, struct dsa_switch *downstream_ds) { int routing_port; if (upstream_ds == downstream_ds) return true; routing_port = dsa_routing_port(downstream_ds, upstream_ds->index); return dsa_is_upstream_port(downstream_ds, routing_port); } static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) { const struct dsa_switch *ds = dp->ds; if (ds->vlan_filtering_is_global) return ds->vlan_filtering; else return dp->vlan_filtering; } static inline unsigned int dsa_port_lag_id_get(struct dsa_port *dp) { return dp->lag ? dp->lag->id : 0; } static inline struct net_device *dsa_port_lag_dev_get(struct dsa_port *dp) { return dp->lag ? dp->lag->dev : NULL; } static inline bool dsa_port_offloads_lag(struct dsa_port *dp, const struct dsa_lag *lag) { return dsa_port_lag_dev_get(dp) == lag->dev; } static inline struct net_device *dsa_port_to_master(const struct dsa_port *dp) { if (dp->cpu_port_in_lag) return dsa_port_lag_dev_get(dp->cpu_dp); return dp->cpu_dp->master; } static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { if (!dp->bridge) return NULL; if (dp->lag) return dp->lag->dev; else if (dp->hsr_dev) return dp->hsr_dev; return dp->slave; } static inline struct net_device * dsa_port_bridge_dev_get(const struct dsa_port *dp) { return dp->bridge ? dp->bridge->dev : NULL; } static inline unsigned int dsa_port_bridge_num_get(struct dsa_port *dp) { return dp->bridge ? dp->bridge->num : 0; } static inline bool dsa_port_bridge_same(const struct dsa_port *a, const struct dsa_port *b) { struct net_device *br_a = dsa_port_bridge_dev_get(a); struct net_device *br_b = dsa_port_bridge_dev_get(b); /* Standalone ports are not in the same bridge with one another */ return (!br_a || !br_b) ? false : (br_a == br_b); } static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, const struct net_device *dev) { return dsa_port_to_bridge_port(dp) == dev; } static inline bool dsa_port_offloads_bridge_dev(struct dsa_port *dp, const struct net_device *bridge_dev) { /* DSA ports connected to a bridge, and event was emitted * for the bridge. */ return dsa_port_bridge_dev_get(dp) == bridge_dev; } static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, const struct dsa_bridge *bridge) { return dsa_port_bridge_dev_get(dp) == bridge->dev; } /* Returns true if any port of this tree offloads the given net_device */ static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, const struct net_device *dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_port(dp, dev)) return true; return false; } /* Returns true if any port of this tree offloads the given bridge */ static inline bool dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst, const struct net_device *bridge_dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_dev(dp, bridge_dev)) return true; return false; } static inline bool dsa_port_tree_same(const struct dsa_port *a, const struct dsa_port *b) { return a->ds->dst == b->ds->dst; } typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { /* * Tagging protocol helpers called for the CPU ports and DSA links. * @get_tag_protocol retrieves the initial tagging protocol and is * mandatory. Switches which can operate using multiple tagging * protocols should implement @change_tag_protocol and report in * @get_tag_protocol the tagger in current use. */ enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); int (*change_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); /* * Method for switch drivers to connect to the tagging protocol driver * in current use. The switch driver can provide handlers for certain * types of packets for switch management. */ int (*connect_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); int (*port_change_master)(struct dsa_switch *ds, int port, struct net_device *master, struct netlink_ext_ack *extack); /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); /* Per-port initialization and destruction methods. Mandatory if the * driver registers devlink port regions, optional otherwise. */ int (*port_setup)(struct dsa_switch *ds, int port); void (*port_teardown)(struct dsa_switch *ds, int port); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* * Access to the switch's PHY registers. */ int (*phy_read)(struct dsa_switch *ds, int port, int regnum); int (*phy_write)(struct dsa_switch *ds, int port, int regnum, u16 val); /* * Link state adjustment (called from libphy) */ void (*adjust_link)(struct dsa_switch *ds, int port, struct phy_device *phydev); void (*fixed_link_update)(struct dsa_switch *ds, int port, struct fixed_phy_status *st); /* * PHYLINK integration */ void (*phylink_get_caps)(struct dsa_switch *ds, int port, struct phylink_config *config); void (*phylink_validate)(struct dsa_switch *ds, int port, unsigned long *supported, struct phylink_link_state *state); struct phylink_pcs *(*phylink_mac_select_pcs)(struct dsa_switch *ds, int port, phy_interface_t iface); int (*phylink_mac_link_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); void (*phylink_mac_config)(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state); void (*phylink_mac_an_restart)(struct dsa_switch *ds, int port); void (*phylink_mac_link_down)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface); void (*phylink_mac_link_up)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, struct phy_device *phydev, int speed, int duplex, bool tx_pause, bool rx_pause); void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* * Port statistics counters. */ void (*get_strings)(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data); void (*get_ethtool_stats)(struct dsa_switch *ds, int port, uint64_t *data); int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); void (*get_ethtool_phy_stats)(struct dsa_switch *ds, int port, uint64_t *data); void (*get_eth_phy_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_phy_stats *phy_stats); void (*get_eth_mac_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_mac_stats *mac_stats); void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats); void (*get_rmon_stats)(struct dsa_switch *ds, int port, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*get_pause_stats)(struct dsa_switch *ds, int port, struct ethtool_pause_stats *pause_stats); void (*self_test)(struct dsa_switch *ds, int port, struct ethtool_test *etest, u64 *data); /* * ethtool Wake-on-LAN */ void (*get_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); int (*set_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); /* * ethtool timestamp info */ int (*get_ts_info)(struct dsa_switch *ds, int port, struct ethtool_ts_info *ts); /* * DCB ops */ int (*port_get_default_prio)(struct dsa_switch *ds, int port); int (*port_set_default_prio)(struct dsa_switch *ds, int port, u8 prio); int (*port_get_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp); int (*port_add_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_del_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); /* * Suspend and resume */ int (*suspend)(struct dsa_switch *ds); int (*resume)(struct dsa_switch *ds); /* * Port enable/disable */ int (*port_enable)(struct dsa_switch *ds, int port, struct phy_device *phy); void (*port_disable)(struct dsa_switch *ds, int port); /* * Port's MAC EEE settings */ int (*set_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_eee *e); int (*get_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_eee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); int (*get_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); int (*set_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); /* * Register access. */ int (*get_regs_len)(struct dsa_switch *ds, int port); void (*get_regs)(struct dsa_switch *ds, int port, struct ethtool_regs *regs, void *p); /* * Upper device tracking. */ int (*port_prechangeupper)(struct dsa_switch *ds, int port, struct netdev_notifier_changeupper_info *info); /* * Bridge integration */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, struct netlink_ext_ack *extack); void (*port_bridge_leave)(struct dsa_switch *ds, int port, struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); int (*port_mst_state_set)(struct dsa_switch *ds, int port, const struct switchdev_mst_state *state); void (*port_fast_age)(struct dsa_switch *ds, int port); int (*port_vlan_fast_age)(struct dsa_switch *ds, int port, u16 vid); int (*port_pre_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); void (*port_set_host_flood)(struct dsa_switch *ds, int port, bool uc, bool mc); /* * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack); int (*port_vlan_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); int (*vlan_msti_set)(struct dsa_switch *ds, struct dsa_bridge bridge, const struct switchdev_vlan_msti *msti); /* * Forwarding database */ int (*port_fdb_add)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_del)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_dump)(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); int (*lag_fdb_add)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); int (*lag_fdb_del)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); /* * Multicast database */ int (*port_mdb_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); int (*port_mdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* * RXNFC */ int (*get_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc, u32 *rule_locs); int (*set_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc); /* * TC integration */ int (*cls_flower_add)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_del)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_stats)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*port_mirror_add)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, bool ingress, struct netlink_ext_ack *extack); void (*port_mirror_del)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); int (*port_policer_add)(struct dsa_switch *ds, int port, struct dsa_mall_policer_tc_entry *policer); void (*port_policer_del)(struct dsa_switch *ds, int port); int (*port_setup_tc)(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data); /* * Cross-chip operations */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge, struct netlink_ext_ack *extack); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge); int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag); /* * PTP functionality */ int (*port_hwtstamp_get)(struct dsa_switch *ds, int port, struct ifreq *ifr); int (*port_hwtstamp_set)(struct dsa_switch *ds, int port, struct ifreq *ifr); void (*port_txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); /* Devlink parameters, etc */ int (*devlink_param_get)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_param_set)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_info_get)(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack); int (*devlink_sb_pool_get)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info *pool_info); int (*devlink_sb_pool_set)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, u32 size, enum devlink_sb_threshold_type threshold_type, struct netlink_ext_ack *extack); int (*devlink_sb_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_threshold); int (*devlink_sb_port_pool_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_tc_pool_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 *p_pool_index, u32 *p_threshold); int (*devlink_sb_tc_pool_bind_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_occ_snapshot)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_max_clear)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_cur, u32 *p_max); int (*devlink_sb_occ_tc_port_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u32 *p_cur, u32 *p_max); /* * MTU change functionality. Switches can also adjust their MRU through * this method. By MTU, one understands the SDU (L2 payload) length. * If the switch needs to account for the DSA tag on the CPU port, this * method needs to do so privately. */ int (*port_change_mtu)(struct dsa_switch *ds, int port, int new_mtu); int (*port_max_mtu)(struct dsa_switch *ds, int port); /* * LAG integration */ int (*port_lag_change)(struct dsa_switch *ds, int port); int (*port_lag_join)(struct dsa_switch *ds, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*port_lag_leave)(struct dsa_switch *ds, int port, struct dsa_lag lag); /* * HSR integration */ int (*port_hsr_join)(struct dsa_switch *ds, int port, struct net_device *hsr); int (*port_hsr_leave)(struct dsa_switch *ds, int port, struct net_device *hsr); /* * MRP integration */ int (*port_mrp_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_add_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); /* * tag_8021q operations */ int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); /* * DSA master tracking operations */ void (*master_state_change)(struct dsa_switch *ds, const struct net_device *master, bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, \ dsa_devlink_param_get, dsa_devlink_param_set, NULL) int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx); int dsa_devlink_param_set(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx); int dsa_devlink_params_register(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); void dsa_devlink_params_unregister(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); int dsa_devlink_resource_register(struct dsa_switch *ds, const char *resource_name, u64 resource_size, u64 resource_id, u64 parent_resource_id, const struct devlink_resource_size_params *size_params); void dsa_devlink_resources_unregister(struct dsa_switch *ds); void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, u64 resource_id, devlink_resource_occ_get_t *occ_get, void *occ_get_priv); void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, u64 resource_id); struct devlink_region * dsa_devlink_region_create(struct dsa_switch *ds, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size); struct devlink_region * dsa_devlink_port_region_create(struct dsa_switch *ds, int port, const struct devlink_port_region_ops *ops, u32 region_max_snapshots, u64 region_size); void dsa_devlink_region_destroy(struct devlink_region *region); struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); struct dsa_devlink_priv { struct dsa_switch *ds; }; static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl) { struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port) { struct devlink *dl = port->devlink; struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline int dsa_devlink_port_to_port(struct devlink_port *port) { return port->index; } struct dsa_switch_driver { struct list_head list; const struct dsa_switch_ops *ops; }; struct net_device *dsa_dev_to_net_device(struct device *dev); bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* Keep inline for faster access in hot path */ static inline bool netdev_uses_dsa(const struct net_device *dev) { #if IS_ENABLED(CONFIG_NET_DSA) return dev->dsa_ptr && dev->dsa_ptr->rcv; #endif return false; } /* All DSA tags that push the EtherType to the right (basically all except tail * tags, which don't break dissection) can be treated the same from the * perspective of the flow dissector. * * We need to return: * - offset: the (B - A) difference between: * A. the position of the real EtherType and * B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes * after the normal EtherType was supposed to be) * The offset in bytes is exactly equal to the tagger overhead (and half of * that, in __be16 shorts). * * - proto: the value of the real EtherType. */ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, __be16 *proto, int *offset) { #if IS_ENABLED(CONFIG_NET_DSA) const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; int tag_len = ops->needed_headroom; *offset = tag_len; *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; #endif } #if IS_ENABLED(CONFIG_NET_DSA) static inline int __dsa_netdevice_ops_check(struct net_device *dev) { int err = -EOPNOTSUPP; if (!dev->dsa_ptr) return err; if (!dev->dsa_ptr->netdev_ops) return err; return 0; } static inline int dsa_ndo_eth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { const struct dsa_netdevice_ops *ops; int err; err = __dsa_netdevice_ops_check(dev); if (err) return err; ops = dev->dsa_ptr->netdev_ops; return ops->ndo_eth_ioctl(dev, ifr, cmd); } #else static inline int dsa_ndo_eth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { return -EOPNOTSUPP; } #endif void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); void dsa_flush_workqueue(void); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); #else static inline int dsa_switch_suspend(struct dsa_switch *ds) { return 0; } static inline int dsa_switch_resume(struct dsa_switch *ds) { return 0; } #endif /* CONFIG_PM_SLEEP */ #if IS_ENABLED(CONFIG_NET_DSA) bool dsa_slave_dev_check(const struct net_device *dev); #else static inline bool dsa_slave_dev_check(const struct net_device *dev) { return false; } #endif netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); struct dsa_tag_driver { const struct dsa_device_ops *ops; struct list_head list; struct module *owner; }; void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[], unsigned int count, struct module *owner); void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[], unsigned int count); #define dsa_tag_driver_module_drivers(__dsa_tag_drivers_array, __count) \ static int __init dsa_tag_driver_module_init(void) \ { \ dsa_tag_drivers_register(__dsa_tag_drivers_array, __count, \ THIS_MODULE); \ return 0; \ } \ module_init(dsa_tag_driver_module_init); \ \ static void __exit dsa_tag_driver_module_exit(void) \ { \ dsa_tag_drivers_unregister(__dsa_tag_drivers_array, __count); \ } \ module_exit(dsa_tag_driver_module_exit) /** * module_dsa_tag_drivers() - Helper macro for registering DSA tag * drivers * @__ops_array: Array of tag driver structures * * Helper macro for DSA tag drivers which do not do anything special * in module init/exit. Each module may only use this macro once, and * calling it replaces module_init() and module_exit(). */ #define module_dsa_tag_drivers(__ops_array) \ dsa_tag_driver_module_drivers(__ops_array, ARRAY_SIZE(__ops_array)) #define DSA_TAG_DRIVER_NAME(__ops) dsa_tag_driver ## _ ## __ops /* Create a static structure we can build a linked list of dsa_tag * drivers */ #define DSA_TAG_DRIVER(__ops) \ static struct dsa_tag_driver DSA_TAG_DRIVER_NAME(__ops) = { \ .ops = &__ops, \ } /** * module_dsa_tag_driver() - Helper macro for registering a single DSA tag * driver * @__ops: Single tag driver structures * * Helper macro for DSA tag drivers which do not do anything special * in module init/exit. Each module may only use this macro once, and * calling it replaces module_init() and module_exit(). */ #define module_dsa_tag_driver(__ops) \ DSA_TAG_DRIVER(__ops); \ \ static struct dsa_tag_driver *dsa_tag_driver_array[] = { \ &DSA_TAG_DRIVER_NAME(__ops) \ }; \ module_dsa_tag_drivers(dsa_tag_driver_array) #endif |
| 1514 1513 1513 1513 1513 1512 1501 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * sysctl_net_ipv4.c: sysctl interface to net IPV4 subsystem. * * Begun April 1, 1996, Mike Shaver. * Added /proc/sys/net/ipv4 directory entry (empty =) ). [MS] */ #include <linux/sysctl.h> #include <linux/seqlock.h> #include <linux/init.h> #include <linux/slab.h> #include <net/icmp.h> #include <net/ip.h> #include <net/ip_fib.h> #include <net/tcp.h> #include <net/udp.h> #include <net/cipso_ipv4.h> #include <net/ping.h> #include <net/protocol.h> #include <net/netevent.h> static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS; static int tcp_min_snd_mss_max = 65535; static int ip_privileged_port_min; static int ip_privileged_port_max = 65535; static int ip_ttl_min = 1; static int ip_ttl_max = 255; static int tcp_syn_retries_min = 1; static int tcp_syn_retries_max = MAX_TCP_SYNCNT; static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static u32 u32_max_div_HZ = UINT_MAX / HZ; static int one_day_secs = 24 * 3600; static u32 fib_multipath_hash_fields_all_mask __maybe_unused = FIB_MULTIPATH_HASH_FIELD_ALL_MASK; static unsigned int tcp_child_ehash_entries_max = 16 * 1024 * 1024; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; /* Update system visible IP port range */ static void set_local_port_range(struct net *net, int range[2]) { bool same_parity = !((range[0] ^ range[1]) & 1); write_seqlock_bh(&net->ipv4.ip_local_ports.lock); if (same_parity && !net->ipv4.ip_local_ports.warned) { net->ipv4.ip_local_ports.warned = true; pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n"); } net->ipv4.ip_local_ports.range[0] = range[0]; net->ipv4.ip_local_ports.range[1] = range[1]; write_sequnlock_bh(&net->ipv4.ip_local_ports.lock); } /* Validate changes from /proc interface. */ static int ipv4_local_port_range(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.ip_local_ports.range); int ret; int range[2]; struct ctl_table tmp = { .data = &range, .maxlen = sizeof(range), .mode = table->mode, .extra1 = &ip_local_port_range_min, .extra2 = &ip_local_port_range_max, }; inet_get_local_port_range(net, &range[0], &range[1]); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { /* Ensure that the upper limit is not smaller than the lower, * and that the lower does not encroach upon the privileged * port limit. */ if ((range[1] < range[0]) || (range[0] < READ_ONCE(net->ipv4.sysctl_ip_prot_sock))) ret = -EINVAL; else set_local_port_range(net, range); } return ret; } /* Validate changes from /proc interface. */ static int ipv4_privileged_ports(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_ip_prot_sock); int ret; int pports; int range[2]; struct ctl_table tmp = { .data = &pports, .maxlen = sizeof(pports), .mode = table->mode, .extra1 = &ip_privileged_port_min, .extra2 = &ip_privileged_port_max, }; pports = READ_ONCE(net->ipv4.sysctl_ip_prot_sock); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { inet_get_local_port_range(net, &range[0], &range[1]); /* Ensure that the local port range doesn't overlap with the * privileged port range. */ if (range[0] < pports) ret = -EINVAL; else WRITE_ONCE(net->ipv4.sysctl_ip_prot_sock, pports); } return ret; } static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low, kgid_t *high) { kgid_t *data = table->data; struct net *net = container_of(table->data, struct net, ipv4.ping_group_range.range); unsigned int seq; do { seq = read_seqbegin(&net->ipv4.ping_group_range.lock); *low = data[0]; *high = data[1]; } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq)); } /* Update system visible IP port range */ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t high) { kgid_t *data = table->data; struct net *net = container_of(table->data, struct net, ipv4.ping_group_range.range); write_seqlock(&net->ipv4.ping_group_range.lock); data[0] = low; data[1] = high; write_sequnlock(&net->ipv4.ping_group_range.lock); } /* Validate changes from /proc interface. */ static int ipv4_ping_group_range(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct user_namespace *user_ns = current_user_ns(); int ret; gid_t urange[2]; kgid_t low, high; struct ctl_table tmp = { .data = &urange, .maxlen = sizeof(urange), .mode = table->mode, .extra1 = &ip_ping_group_range_min, .extra2 = &ip_ping_group_range_max, }; inet_get_ping_group_range_table(table, &low, &high); urange[0] = from_kgid_munged(user_ns, low); urange[1] = from_kgid_munged(user_ns, high); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { low = make_kgid(user_ns, urange[0]); high = make_kgid(user_ns, urange[1]); if (!gid_valid(low) || !gid_valid(high)) return -EINVAL; if (urange[1] < urange[0] || gid_lt(high, low)) { low = make_kgid(&init_user_ns, 1); high = make_kgid(&init_user_ns, 0); } set_ping_group_range(table, low, high); } return ret; } static int ipv4_fwd_update_priority(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; net = container_of(table->data, struct net, ipv4.sysctl_ip_fwd_update_priority); ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE, net); return ret; } static int proc_tcp_congestion_control(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(ctl->data, struct net, ipv4.tcp_congestion_control); char val[TCP_CA_NAME_MAX]; struct ctl_table tbl = { .data = val, .maxlen = TCP_CA_NAME_MAX, }; int ret; tcp_get_default_congestion_control(net, val); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) ret = tcp_set_default_congestion_control(net, val); return ret; } static int proc_tcp_available_congestion_control(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX, }; int ret; tbl.data = kmalloc(tbl.maxlen, GFP_USER); if (!tbl.data) return -ENOMEM; tcp_get_available_congestion_control(tbl.data, TCP_CA_BUF_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); kfree(tbl.data); return ret; } static int proc_allowed_congestion_control(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX }; int ret; tbl.data = kmalloc(tbl.maxlen, GFP_USER); if (!tbl.data) return -ENOMEM; tcp_get_allowed_congestion_control(tbl.data, tbl.maxlen); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) ret = tcp_set_allowed_congestion_control(tbl.data); kfree(tbl.data); return ret; } static int sscanf_key(char *buf, __le32 *key) { u32 user_key[4]; int i, ret = 0; if (sscanf(buf, "%x-%x-%x-%x", user_key, user_key + 1, user_key + 2, user_key + 3) != 4) { ret = -EINVAL; } else { for (i = 0; i < ARRAY_SIZE(user_key); i++) key[i] = cpu_to_le32(user_key[i]); } pr_debug("proc TFO key set 0x%x-%x-%x-%x <- 0x%s: %u\n", user_key[0], user_key[1], user_key[2], user_key[3], buf, ret); return ret; } static int proc_tcp_fastopen_key(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_tcp_fastopen); /* maxlen to print the list of keys in hex (*2), with dashes * separating doublewords and a comma in between keys. */ struct ctl_table tbl = { .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2 * TCP_FASTOPEN_KEY_MAX) + (TCP_FASTOPEN_KEY_MAX * 5)) }; u32 user_key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u32)]; __le32 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(__le32)]; char *backup_data; int ret, i = 0, off = 0, n_keys; tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL); if (!tbl.data) return -ENOMEM; n_keys = tcp_fastopen_get_cipher(net, NULL, (u64 *)key); if (!n_keys) { memset(&key[0], 0, TCP_FASTOPEN_KEY_LENGTH); n_keys = 1; } for (i = 0; i < n_keys * 4; i++) user_key[i] = le32_to_cpu(key[i]); for (i = 0; i < n_keys; i++) { off += snprintf(tbl.data + off, tbl.maxlen - off, "%08x-%08x-%08x-%08x", user_key[i * 4], user_key[i * 4 + 1], user_key[i * 4 + 2], user_key[i * 4 + 3]); if (WARN_ON_ONCE(off >= tbl.maxlen - 1)) break; if (i + 1 < n_keys) off += snprintf(tbl.data + off, tbl.maxlen - off, ","); } ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) { backup_data = strchr(tbl.data, ','); if (backup_data) { *backup_data = '\0'; backup_data++; } if (sscanf_key(tbl.data, key)) { ret = -EINVAL; goto bad_key; } if (backup_data) { if (sscanf_key(backup_data, key + 4)) { ret = -EINVAL; goto bad_key; } } tcp_fastopen_reset_cipher(net, NULL, key, backup_data ? key + 4 : NULL); } bad_key: kfree(tbl.data); return ret; } static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_tcp_fastopen_blackhole_timeout); int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) atomic_set(&net->ipv4.tfo_active_disable_times, 0); return ret; } static int proc_tcp_available_ulp(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tbl = { .maxlen = TCP_ULP_BUF_MAX, }; int ret; tbl.data = kmalloc(tbl.maxlen, GFP_USER); if (!tbl.data) return -ENOMEM; tcp_get_available_ulp(tbl.data, TCP_ULP_BUF_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); kfree(tbl.data); return ret; } static int proc_tcp_ehash_entries(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_tcp_child_ehash_entries); struct inet_hashinfo *hinfo = net->ipv4.tcp_death_row.hashinfo; int tcp_ehash_entries; struct ctl_table tbl; tcp_ehash_entries = hinfo->ehash_mask + 1; /* A negative number indicates that the child netns * shares the global ehash. */ if (!net_eq(net, &init_net) && !hinfo->pernet) tcp_ehash_entries *= -1; tbl.data = &tcp_ehash_entries; tbl.maxlen = sizeof(int); return proc_dointvec(&tbl, write, buffer, lenp, ppos); } #ifdef CONFIG_IP_ROUTE_MULTIPATH static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_fib_multipath_hash_policy); int ret; ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net); return ret; } static int proc_fib_multipath_hash_fields(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; net = container_of(table->data, struct net, ipv4.sysctl_fib_multipath_hash_fields); ret = proc_douintvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net); return ret; } #endif static struct ctl_table ipv4_table[] = { { .procname = "tcp_max_orphans", .data = &sysctl_tcp_max_orphans, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "inet_peer_threshold", .data = &inet_peer_threshold, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "inet_peer_minttl", .data = &inet_peer_minttl, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "inet_peer_maxttl", .data = &inet_peer_maxttl, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "tcp_mem", .maxlen = sizeof(sysctl_tcp_mem), .data = &sysctl_tcp_mem, .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "tcp_low_latency", .data = &sysctl_tcp_low_latency, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, #ifdef CONFIG_NETLABEL { .procname = "cipso_cache_enable", .data = &cipso_v4_cache_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "cipso_cache_bucket_size", .data = &cipso_v4_cache_bucketsize, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "cipso_rbm_optfmt", .data = &cipso_v4_rbm_optfmt, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "cipso_rbm_strictvalid", .data = &cipso_v4_rbm_strictvalid, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif /* CONFIG_NETLABEL */ { .procname = "tcp_available_ulp", .maxlen = TCP_ULP_BUF_MAX, .mode = 0444, .proc_handler = proc_tcp_available_ulp, }, { .procname = "icmp_msgs_per_sec", .data = &sysctl_icmp_msgs_per_sec, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { .procname = "icmp_msgs_burst", .data = &sysctl_icmp_msgs_burst, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { .procname = "udp_mem", .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "fib_sync_mem", .data = &sysctl_fib_sync_mem, .maxlen = sizeof(sysctl_fib_sync_mem), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = &sysctl_fib_sync_mem_min, .extra2 = &sysctl_fib_sync_mem_max, }, { } }; static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_max_tw_buckets", .data = &init_net.ipv4.tcp_death_row.sysctl_max_tw_buckets, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "icmp_echo_ignore_all", .data = &init_net.ipv4.sysctl_icmp_echo_ignore_all, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "icmp_echo_enable_probe", .data = &init_net.ipv4.sysctl_icmp_echo_enable_probe, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "icmp_echo_ignore_broadcasts", .data = &init_net.ipv4.sysctl_icmp_echo_ignore_broadcasts, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "icmp_ignore_bogus_error_responses", .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "icmp_errors_use_inbound_ifaddr", .data = &init_net.ipv4.sysctl_icmp_errors_use_inbound_ifaddr, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "icmp_ratelimit", .data = &init_net.ipv4.sysctl_icmp_ratelimit, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "icmp_ratemask", .data = &init_net.ipv4.sysctl_icmp_ratemask, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "ping_group_range", .data = &init_net.ipv4.ping_group_range.range, .maxlen = sizeof(gid_t)*2, .mode = 0644, .proc_handler = ipv4_ping_group_range, }, #ifdef CONFIG_NET_L3_MASTER_DEV { .procname = "raw_l3mdev_accept", .data = &init_net.ipv4.sysctl_raw_l3mdev_accept, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "tcp_ecn", .data = &init_net.ipv4.sysctl_tcp_ecn, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "tcp_ecn_fallback", .data = &init_net.ipv4.sysctl_tcp_ecn_fallback, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "ip_dynaddr", .data = &init_net.ipv4.sysctl_ip_dynaddr, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_early_demux", .data = &init_net.ipv4.sysctl_ip_early_demux, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "udp_early_demux", .data = &init_net.ipv4.sysctl_udp_early_demux, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_early_demux", .data = &init_net.ipv4.sysctl_tcp_early_demux, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "nexthop_compat_mode", .data = &init_net.ipv4.sysctl_nexthop_compat_mode, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "ip_default_ttl", .data = &init_net.ipv4.sysctl_ip_default_ttl, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = &ip_ttl_min, .extra2 = &ip_ttl_max, }, { .procname = "ip_local_port_range", .maxlen = sizeof(init_net.ipv4.ip_local_ports.range), .data = &init_net.ipv4.ip_local_ports.range, .mode = 0644, .proc_handler = ipv4_local_port_range, }, { .procname = "ip_local_reserved_ports", .data = &init_net.ipv4.sysctl_local_reserved_ports, .maxlen = 65536, .mode = 0644, .proc_handler = proc_do_large_bitmap, }, { .procname = "ip_no_pmtu_disc", .data = &init_net.ipv4.sysctl_ip_no_pmtu_disc, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_forward_use_pmtu", .data = &init_net.ipv4.sysctl_ip_fwd_use_pmtu, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_forward_update_priority", .data = &init_net.ipv4.sysctl_ip_fwd_update_priority, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = ipv4_fwd_update_priority, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "ip_nonlocal_bind", .data = &init_net.ipv4.sysctl_ip_nonlocal_bind, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_autobind_reuse", .data = &init_net.ipv4.sysctl_ip_autobind_reuse, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "fwmark_reflect", .data = &init_net.ipv4.sysctl_fwmark_reflect, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_fwmark_accept", .data = &init_net.ipv4.sysctl_tcp_fwmark_accept, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, #ifdef CONFIG_NET_L3_MASTER_DEV { .procname = "tcp_l3mdev_accept", .data = &init_net.ipv4.sysctl_tcp_l3mdev_accept, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "tcp_mtu_probing", .data = &init_net.ipv4.sysctl_tcp_mtu_probing, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_base_mss", .data = &init_net.ipv4.sysctl_tcp_base_mss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "tcp_min_snd_mss", .data = &init_net.ipv4.sysctl_tcp_min_snd_mss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &tcp_min_snd_mss_min, .extra2 = &tcp_min_snd_mss_max, }, { .procname = "tcp_mtu_probe_floor", .data = &init_net.ipv4.sysctl_tcp_mtu_probe_floor, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &tcp_min_snd_mss_min, .extra2 = &tcp_min_snd_mss_max, }, { .procname = "tcp_probe_threshold", .data = &init_net.ipv4.sysctl_tcp_probe_threshold, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "tcp_probe_interval", .data = &init_net.ipv4.sysctl_tcp_probe_interval, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra2 = &u32_max_div_HZ, }, { .procname = "igmp_link_local_mcast_reports", .data = &init_net.ipv4.sysctl_igmp_llm_reports, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "igmp_max_memberships", .data = &init_net.ipv4.sysctl_igmp_max_memberships, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "igmp_max_msf", .data = &init_net.ipv4.sysctl_igmp_max_msf, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, #ifdef CONFIG_IP_MULTICAST { .procname = "igmp_qrv", .data = &init_net.ipv4.sysctl_igmp_qrv, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE }, #endif { .procname = "tcp_congestion_control", .data = &init_net.ipv4.tcp_congestion_control, .mode = 0644, .maxlen = TCP_CA_NAME_MAX, .proc_handler = proc_tcp_congestion_control, }, { .procname = "tcp_available_congestion_control", .maxlen = TCP_CA_BUF_MAX, .mode = 0444, .proc_handler = proc_tcp_available_congestion_control, }, { .procname = "tcp_allowed_congestion_control", .maxlen = TCP_CA_BUF_MAX, .mode = 0644, .proc_handler = proc_allowed_congestion_control, }, { .procname = "tcp_keepalive_time", .data = &init_net.ipv4.sysctl_tcp_keepalive_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "tcp_keepalive_probes", .data = &init_net.ipv4.sysctl_tcp_keepalive_probes, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_keepalive_intvl", .data = &init_net.ipv4.sysctl_tcp_keepalive_intvl, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "tcp_syn_retries", .data = &init_net.ipv4.sysctl_tcp_syn_retries, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = &tcp_syn_retries_min, .extra2 = &tcp_syn_retries_max }, { .procname = "tcp_synack_retries", .data = &init_net.ipv4.sysctl_tcp_synack_retries, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, #ifdef CONFIG_SYN_COOKIES { .procname = "tcp_syncookies", .data = &init_net.ipv4.sysctl_tcp_syncookies, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, #endif { .procname = "tcp_migrate_req", .data = &init_net.ipv4.sysctl_tcp_migrate_req, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "tcp_reordering", .data = &init_net.ipv4.sysctl_tcp_reordering, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "tcp_retries1", .data = &init_net.ipv4.sysctl_tcp_retries1, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra2 = &tcp_retr1_max }, { .procname = "tcp_retries2", .data = &init_net.ipv4.sysctl_tcp_retries2, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_orphan_retries", .data = &init_net.ipv4.sysctl_tcp_orphan_retries, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_fin_timeout", .data = &init_net.ipv4.sysctl_tcp_fin_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "tcp_notsent_lowat", .data = &init_net.ipv4.sysctl_tcp_notsent_lowat, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec, }, { .procname = "tcp_tw_reuse", .data = &init_net.ipv4.sysctl_tcp_tw_reuse, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "tcp_max_syn_backlog", .data = &init_net.ipv4.sysctl_max_syn_backlog, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "tcp_fastopen", .data = &init_net.ipv4.sysctl_tcp_fastopen, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "tcp_fastopen_key", .mode = 0600, .data = &init_net.ipv4.sysctl_tcp_fastopen, /* maxlen to print the list of keys in hex (*2), with dashes * separating doublewords and a comma in between keys. */ .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2 * TCP_FASTOPEN_KEY_MAX) + (TCP_FASTOPEN_KEY_MAX * 5)), .proc_handler = proc_tcp_fastopen_key, }, { .procname = "tcp_fastopen_blackhole_timeout_sec", .data = &init_net.ipv4.sysctl_tcp_fastopen_blackhole_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_tfo_blackhole_detect_timeout, .extra1 = SYSCTL_ZERO, }, #ifdef CONFIG_IP_ROUTE_MULTIPATH { .procname = "fib_multipath_use_neigh", .data = &init_net.ipv4.sysctl_fib_multipath_use_neigh, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "fib_multipath_hash_policy", .data = &init_net.ipv4.sysctl_fib_multipath_hash_policy, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_fib_multipath_hash_policy, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_THREE, }, { .procname = "fib_multipath_hash_fields", .data = &init_net.ipv4.sysctl_fib_multipath_hash_fields, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_fib_multipath_hash_fields, .extra1 = SYSCTL_ONE, .extra2 = &fib_multipath_hash_fields_all_mask, }, #endif { .procname = "ip_unprivileged_port_start", .maxlen = sizeof(int), .data = &init_net.ipv4.sysctl_ip_prot_sock, .mode = 0644, .proc_handler = ipv4_privileged_ports, }, #ifdef CONFIG_NET_L3_MASTER_DEV { .procname = "udp_l3mdev_accept", .data = &init_net.ipv4.sysctl_udp_l3mdev_accept, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "tcp_sack", .data = &init_net.ipv4.sysctl_tcp_sack, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_window_scaling", .data = &init_net.ipv4.sysctl_tcp_window_scaling, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_timestamps", .data = &init_net.ipv4.sysctl_tcp_timestamps, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_early_retrans", .data = &init_net.ipv4.sysctl_tcp_early_retrans, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_FOUR, }, { .procname = "tcp_recovery", .data = &init_net.ipv4.sysctl_tcp_recovery, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_thin_linear_timeouts", .data = &init_net.ipv4.sysctl_tcp_thin_linear_timeouts, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_slow_start_after_idle", .data = &init_net.ipv4.sysctl_tcp_slow_start_after_idle, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_retrans_collapse", .data = &init_net.ipv4.sysctl_tcp_retrans_collapse, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_stdurg", .data = &init_net.ipv4.sysctl_tcp_stdurg, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_rfc1337", .data = &init_net.ipv4.sysctl_tcp_rfc1337, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_abort_on_overflow", .data = &init_net.ipv4.sysctl_tcp_abort_on_overflow, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_fack", .data = &init_net.ipv4.sysctl_tcp_fack, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_max_reordering", .data = &init_net.ipv4.sysctl_tcp_max_reordering, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "tcp_dsack", .data = &init_net.ipv4.sysctl_tcp_dsack, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_app_win", .data = &init_net.ipv4.sysctl_tcp_app_win, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_adv_win_scale", .data = &init_net.ipv4.sysctl_tcp_adv_win_scale, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &tcp_adv_win_scale_min, .extra2 = &tcp_adv_win_scale_max, }, { .procname = "tcp_frto", .data = &init_net.ipv4.sysctl_tcp_frto, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_no_metrics_save", .data = &init_net.ipv4.sysctl_tcp_nometrics_save, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_no_ssthresh_metrics_save", .data = &init_net.ipv4.sysctl_tcp_no_ssthresh_metrics_save, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "tcp_moderate_rcvbuf", .data = &init_net.ipv4.sysctl_tcp_moderate_rcvbuf, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_tso_win_divisor", .data = &init_net.ipv4.sysctl_tcp_tso_win_divisor, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_workaround_signed_windows", .data = &init_net.ipv4.sysctl_tcp_workaround_signed_windows, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_limit_output_bytes", .data = &init_net.ipv4.sysctl_tcp_limit_output_bytes, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "tcp_challenge_ack_limit", .data = &init_net.ipv4.sysctl_tcp_challenge_ack_limit, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "tcp_min_tso_segs", .data = &init_net.ipv4.sysctl_tcp_min_tso_segs, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ONE, }, { .procname = "tcp_tso_rtt_log", .data = &init_net.ipv4.sysctl_tcp_tso_rtt_log, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_min_rtt_wlen", .data = &init_net.ipv4.sysctl_tcp_min_rtt_wlen, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &one_day_secs }, { .procname = "tcp_autocorking", .data = &init_net.ipv4.sysctl_tcp_autocorking, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "tcp_invalid_ratelimit", .data = &init_net.ipv4.sysctl_tcp_invalid_ratelimit, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "tcp_pacing_ss_ratio", .data = &init_net.ipv4.sysctl_tcp_pacing_ss_ratio, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_THOUSAND, }, { .procname = "tcp_pacing_ca_ratio", .data = &init_net.ipv4.sysctl_tcp_pacing_ca_ratio, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_THOUSAND, }, { .procname = "tcp_wmem", .data = &init_net.ipv4.sysctl_tcp_wmem, .maxlen = sizeof(init_net.ipv4.sysctl_tcp_wmem), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, { .procname = "tcp_rmem", .data = &init_net.ipv4.sysctl_tcp_rmem, .maxlen = sizeof(init_net.ipv4.sysctl_tcp_rmem), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, { .procname = "tcp_comp_sack_delay_ns", .data = &init_net.ipv4.sysctl_tcp_comp_sack_delay_ns, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "tcp_comp_sack_slack_ns", .data = &init_net.ipv4.sysctl_tcp_comp_sack_slack_ns, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "tcp_comp_sack_nr", .data = &init_net.ipv4.sysctl_tcp_comp_sack_nr, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, }, { .procname = "tcp_reflect_tos", .data = &init_net.ipv4.sysctl_tcp_reflect_tos, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "tcp_ehash_entries", .data = &init_net.ipv4.sysctl_tcp_child_ehash_entries, .mode = 0444, .proc_handler = proc_tcp_ehash_entries, }, { .procname = "tcp_child_ehash_entries", .data = &init_net.ipv4.sysctl_tcp_child_ehash_entries, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &tcp_child_ehash_entries_max, }, { .procname = "udp_rmem_min", .data = &init_net.ipv4.sysctl_udp_rmem_min, .maxlen = sizeof(init_net.ipv4.sysctl_udp_rmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE }, { .procname = "udp_wmem_min", .data = &init_net.ipv4.sysctl_udp_wmem_min, .maxlen = sizeof(init_net.ipv4.sysctl_udp_wmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE }, { .procname = "fib_notify_on_flag_change", .data = &init_net.ipv4.sysctl_fib_notify_on_flag_change, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { } }; static __net_init int ipv4_sysctl_init_net(struct net *net) { struct ctl_table *table; table = ipv4_net_table; if (!net_eq(net, &init_net)) { int i; table = kmemdup(table, sizeof(ipv4_net_table), GFP_KERNEL); if (!table) goto err_alloc; for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) { if (table[i].data) { /* Update the variables to point into * the current struct net */ table[i].data += (void *)net - (void *)&init_net; } else { /* Entries without data pointer are global; * Make them read-only in non-init_net ns */ table[i].mode &= ~0222; } } } net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); if (!net->ipv4.ipv4_hdr) goto err_reg; net->ipv4.sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL); if (!net->ipv4.sysctl_local_reserved_ports) goto err_ports; return 0; err_ports: unregister_net_sysctl_table(net->ipv4.ipv4_hdr); err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static __net_exit void ipv4_sysctl_exit_net(struct net *net) { struct ctl_table *table; kfree(net->ipv4.sysctl_local_reserved_ports); table = net->ipv4.ipv4_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.ipv4_hdr); kfree(table); } static __net_initdata struct pernet_operations ipv4_sysctl_ops = { .init = ipv4_sysctl_init_net, .exit = ipv4_sysctl_exit_net, }; static __init int sysctl_ipv4_init(void) { struct ctl_table_header *hdr; hdr = register_net_sysctl(&init_net, "net/ipv4", ipv4_table); if (!hdr) return -ENOMEM; if (register_pernet_subsys(&ipv4_sysctl_ops)) { unregister_net_sysctl_table(hdr); return -ENOMEM; } return 0; } __initcall(sysctl_ipv4_init); |
| 5 5 5 5 5 5 5 59 59 58 59 58 59 59 59 59 58 58 59 58 59 59 59 59 59 58 59 59 2680 2680 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include <net/sock.h> #include <linux/ethtool_netlink.h> #include <linux/pm_runtime.h> #include "netlink.h" static struct genl_family ethtool_genl_family; static bool ethnl_ok __read_mostly; static u32 ethnl_bcast_seq; #define ETHTOOL_FLAGS_BASIC (ETHTOOL_FLAG_COMPACT_BITSETS | \ ETHTOOL_FLAG_OMIT_REPLY) #define ETHTOOL_FLAGS_STATS (ETHTOOL_FLAGS_BASIC | ETHTOOL_FLAG_STATS) const struct nla_policy ethnl_header_policy[] = { [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_BASIC), }; const struct nla_policy ethnl_header_policy_stats[] = { [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_STATS), }; int ethnl_ops_begin(struct net_device *dev) { int ret; if (!dev) return -ENODEV; if (dev->dev.parent) pm_runtime_get_sync(dev->dev.parent); if (!netif_device_present(dev) || dev->reg_state == NETREG_UNREGISTERING) { ret = -ENODEV; goto err; } if (dev->ethtool_ops->begin) { ret = dev->ethtool_ops->begin(dev); if (ret) goto err; } return 0; err: if (dev->dev.parent) pm_runtime_put(dev->dev.parent); return ret; } void ethnl_ops_complete(struct net_device *dev) { if (dev->ethtool_ops->complete) dev->ethtool_ops->complete(dev); if (dev->dev.parent) pm_runtime_put(dev->dev.parent); } /** * ethnl_parse_header_dev_get() - parse request header * @req_info: structure to put results into * @header: nest attribute with request header * @net: request netns * @extack: netlink extack for error reporting * @require_dev: fail if no device identified in header * * Parse request header in nested attribute @nest and puts results into * the structure pointed to by @req_info. Extack from @info is used for error * reporting. If req_info->dev is not null on return, reference to it has * been taken. If error is returned, *req_info is null initialized and no * reference is held. * * Return: 0 on success or negative error code */ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, const struct nlattr *header, struct net *net, struct netlink_ext_ack *extack, bool require_dev) { struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy)]; const struct nlattr *devname_attr; struct net_device *dev = NULL; u32 flags = 0; int ret; if (!header) { NL_SET_ERR_MSG(extack, "request header missing"); return -EINVAL; } /* No validation here, command policy should have a nested policy set * for the header, therefore validation should have already been done. */ ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy) - 1, header, NULL, extack); if (ret < 0) return ret; if (tb[ETHTOOL_A_HEADER_FLAGS]) flags = nla_get_u32(tb[ETHTOOL_A_HEADER_FLAGS]); devname_attr = tb[ETHTOOL_A_HEADER_DEV_NAME]; if (tb[ETHTOOL_A_HEADER_DEV_INDEX]) { u32 ifindex = nla_get_u32(tb[ETHTOOL_A_HEADER_DEV_INDEX]); dev = dev_get_by_index(net, ifindex); if (!dev) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_HEADER_DEV_INDEX], "no device matches ifindex"); return -ENODEV; } /* if both ifindex and ifname are passed, they must match */ if (devname_attr && strncmp(dev->name, nla_data(devname_attr), IFNAMSIZ)) { dev_put(dev); NL_SET_ERR_MSG_ATTR(extack, header, "ifindex and name do not match"); return -ENODEV; } } else if (devname_attr) { dev = dev_get_by_name(net, nla_data(devname_attr)); if (!dev) { NL_SET_ERR_MSG_ATTR(extack, devname_attr, "no device matches name"); return -ENODEV; } } else if (require_dev) { NL_SET_ERR_MSG_ATTR(extack, header, "neither ifindex nor name specified"); return -EINVAL; } req_info->dev = dev; if (dev) netdev_tracker_alloc(dev, &req_info->dev_tracker, GFP_KERNEL); req_info->flags = flags; return 0; } /** * ethnl_fill_reply_header() - Put common header into a reply message * @skb: skb with the message * @dev: network device to describe in header * @attrtype: attribute type to use for the nest * * Create a nested attribute with attributes describing given network device. * * Return: 0 on success, error value (-EMSGSIZE only) on error */ int ethnl_fill_reply_header(struct sk_buff *skb, struct net_device *dev, u16 attrtype) { struct nlattr *nest; if (!dev) return 0; nest = nla_nest_start(skb, attrtype); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_HEADER_DEV_INDEX, (u32)dev->ifindex) || nla_put_string(skb, ETHTOOL_A_HEADER_DEV_NAME, dev->name)) goto nla_put_failure; /* If more attributes are put into reply header, ethnl_header_size() * must be updated to account for them. */ nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } /** * ethnl_reply_init() - Create skb for a reply and fill device identification * @payload: payload length (without netlink and genetlink header) * @dev: device the reply is about (may be null) * @cmd: ETHTOOL_MSG_* message type for reply * @hdr_attrtype: attribute type for common header * @info: genetlink info of the received packet we respond to * @ehdrp: place to store payload pointer returned by genlmsg_new() * * Return: pointer to allocated skb on success, NULL on error */ struct sk_buff *ethnl_reply_init(size_t payload, struct net_device *dev, u8 cmd, u16 hdr_attrtype, struct genl_info *info, void **ehdrp) { struct sk_buff *skb; skb = genlmsg_new(payload, GFP_KERNEL); if (!skb) goto err; *ehdrp = genlmsg_put_reply(skb, info, ðtool_genl_family, 0, cmd); if (!*ehdrp) goto err_free; if (dev) { int ret; ret = ethnl_fill_reply_header(skb, dev, hdr_attrtype); if (ret < 0) goto err_free; } return skb; err_free: nlmsg_free(skb); err: if (info) GENL_SET_ERR_MSG(info, "failed to setup reply message"); return NULL; } void *ethnl_dump_put(struct sk_buff *skb, struct netlink_callback *cb, u8 cmd) { return genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, ðtool_genl_family, 0, cmd); } void *ethnl_bcastmsg_put(struct sk_buff *skb, u8 cmd) { return genlmsg_put(skb, 0, ++ethnl_bcast_seq, ðtool_genl_family, 0, cmd); } int ethnl_multicast(struct sk_buff *skb, struct net_device *dev) { return genlmsg_multicast_netns(ðtool_genl_family, dev_net(dev), skb, 0, ETHNL_MCGRP_MONITOR, GFP_KERNEL); } /* GET request helpers */ /** * struct ethnl_dump_ctx - context structure for generic dumpit() callback * @ops: request ops of currently processed message type * @req_info: parsed request header of processed request * @reply_data: data needed to compose the reply * @pos_hash: saved iteration position - hashbucket * @pos_idx: saved iteration position - index * * These parameters are kept in struct netlink_callback as context preserved * between iterations. They are initialized by ethnl_default_start() and used * in ethnl_default_dumpit() and ethnl_default_done(). */ struct ethnl_dump_ctx { const struct ethnl_request_ops *ops; struct ethnl_req_info *req_info; struct ethnl_reply_data *reply_data; int pos_hash; int pos_idx; }; static const struct ethnl_request_ops * ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_STRSET_GET] = ðnl_strset_request_ops, [ETHTOOL_MSG_LINKINFO_GET] = ðnl_linkinfo_request_ops, [ETHTOOL_MSG_LINKMODES_GET] = ðnl_linkmodes_request_ops, [ETHTOOL_MSG_LINKSTATE_GET] = ðnl_linkstate_request_ops, [ETHTOOL_MSG_DEBUG_GET] = ðnl_debug_request_ops, [ETHTOOL_MSG_WOL_GET] = ðnl_wol_request_ops, [ETHTOOL_MSG_FEATURES_GET] = ðnl_features_request_ops, [ETHTOOL_MSG_PRIVFLAGS_GET] = ðnl_privflags_request_ops, [ETHTOOL_MSG_RINGS_GET] = ðnl_rings_request_ops, [ETHTOOL_MSG_CHANNELS_GET] = ðnl_channels_request_ops, [ETHTOOL_MSG_COALESCE_GET] = ðnl_coalesce_request_ops, [ETHTOOL_MSG_PAUSE_GET] = ðnl_pause_request_ops, [ETHTOOL_MSG_EEE_GET] = ðnl_eee_request_ops, [ETHTOOL_MSG_FEC_GET] = ðnl_fec_request_ops, [ETHTOOL_MSG_TSINFO_GET] = ðnl_tsinfo_request_ops, [ETHTOOL_MSG_MODULE_EEPROM_GET] = ðnl_module_eeprom_request_ops, [ETHTOOL_MSG_STATS_GET] = ðnl_stats_request_ops, [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops, [ETHTOOL_MSG_MODULE_GET] = ðnl_module_request_ops, [ETHTOOL_MSG_PSE_GET] = ðnl_pse_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) { return (struct ethnl_dump_ctx *)cb->ctx; } /** * ethnl_default_parse() - Parse request message * @req_info: pointer to structure to put data into * @tb: parsed attributes * @net: request netns * @request_ops: struct request_ops for request type * @extack: netlink extack for error reporting * @require_dev: fail if no device identified in header * * Parse universal request header and call request specific ->parse_request() * callback (if defined) to parse the rest of the message. * * Return: 0 on success or negative error code */ static int ethnl_default_parse(struct ethnl_req_info *req_info, struct nlattr **tb, struct net *net, const struct ethnl_request_ops *request_ops, struct netlink_ext_ack *extack, bool require_dev) { int ret; ret = ethnl_parse_header_dev_get(req_info, tb[request_ops->hdr_attr], net, extack, require_dev); if (ret < 0) return ret; if (request_ops->parse_request) { ret = request_ops->parse_request(req_info, tb, extack); if (ret < 0) return ret; } return 0; } /** * ethnl_init_reply_data() - Initialize reply data for GET request * @reply_data: pointer to embedded struct ethnl_reply_data * @ops: instance of struct ethnl_request_ops describing the layout * @dev: network device to initialize the reply for * * Fills the reply data part with zeros and sets the dev member. Must be called * before calling the ->fill_reply() callback (for each iteration when handling * dump requests). */ static void ethnl_init_reply_data(struct ethnl_reply_data *reply_data, const struct ethnl_request_ops *ops, struct net_device *dev) { memset(reply_data, 0, ops->reply_data_size); reply_data->dev = dev; } /* default ->doit() handler for GET type requests */ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) { struct ethnl_reply_data *reply_data = NULL; struct ethnl_req_info *req_info = NULL; const u8 cmd = info->genlhdr->cmd; const struct ethnl_request_ops *ops; int hdr_len, reply_len; struct sk_buff *rskb; void *reply_payload; int ret; ops = ethnl_default_requests[cmd]; if (WARN_ONCE(!ops, "cmd %u has no ethnl_request_ops\n", cmd)) return -EOPNOTSUPP; if (GENL_REQ_ATTR_CHECK(info, ops->hdr_attr)) return -EINVAL; req_info = kzalloc(ops->req_info_size, GFP_KERNEL); if (!req_info) return -ENOMEM; reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); if (!reply_data) { kfree(req_info); return -ENOMEM; } ret = ethnl_default_parse(req_info, info->attrs, genl_info_net(info), ops, info->extack, !ops->allow_nodev_do); if (ret < 0) goto err_dev; ethnl_init_reply_data(reply_data, ops, req_info->dev); rtnl_lock(); ret = ops->prepare_data(req_info, reply_data, info); rtnl_unlock(); if (ret < 0) goto err_cleanup; ret = ops->reply_size(req_info, reply_data); if (ret < 0) goto err_cleanup; reply_len = ret; ret = -ENOMEM; rskb = ethnl_reply_init(reply_len + ethnl_reply_header_size(), req_info->dev, ops->reply_cmd, ops->hdr_attr, info, &reply_payload); if (!rskb) goto err_cleanup; hdr_len = rskb->len; ret = ops->fill_reply(rskb, req_info, reply_data); if (ret < 0) goto err_msg; WARN_ONCE(rskb->len - hdr_len > reply_len, "ethnl cmd %d: calculated reply length %d, but consumed %d\n", cmd, reply_len, rskb->len - hdr_len); if (ops->cleanup_data) ops->cleanup_data(reply_data); genlmsg_end(rskb, reply_payload); netdev_put(req_info->dev, &req_info->dev_tracker); kfree(reply_data); kfree(req_info); return genlmsg_reply(rskb, info); err_msg: WARN_ONCE(ret == -EMSGSIZE, "calculated message payload length (%d) not sufficient\n", reply_len); nlmsg_free(rskb); err_cleanup: if (ops->cleanup_data) ops->cleanup_data(reply_data); err_dev: netdev_put(req_info->dev, &req_info->dev_tracker); kfree(reply_data); kfree(req_info); return ret; } static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev, const struct ethnl_dump_ctx *ctx, struct netlink_callback *cb) { void *ehdr; int ret; ehdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, ðtool_genl_family, NLM_F_MULTI, ctx->ops->reply_cmd); if (!ehdr) return -EMSGSIZE; ethnl_init_reply_data(ctx->reply_data, ctx->ops, dev); rtnl_lock(); ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, NULL); rtnl_unlock(); if (ret < 0) goto out; ret = ethnl_fill_reply_header(skb, dev, ctx->ops->hdr_attr); if (ret < 0) goto out; ret = ctx->ops->fill_reply(skb, ctx->req_info, ctx->reply_data); out: if (ctx->ops->cleanup_data) ctx->ops->cleanup_data(ctx->reply_data); ctx->reply_data->dev = NULL; if (ret < 0) genlmsg_cancel(skb, ehdr); else genlmsg_end(skb, ehdr); return ret; } /* Default ->dumpit() handler for GET requests. Device iteration copied from * rtnl_dump_ifinfo(); we have to be more careful about device hashtable * persistence as we cannot guarantee to hold RTNL lock through the whole * function as rtnetnlink does. */ static int ethnl_default_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); struct net *net = sock_net(skb->sk); int s_idx = ctx->pos_idx; int h, idx = 0; int ret = 0; rtnl_lock(); for (h = ctx->pos_hash; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { struct hlist_head *head; struct net_device *dev; unsigned int seq; head = &net->dev_index_head[h]; restart_chain: seq = net->dev_base_seq; cb->seq = seq; idx = 0; hlist_for_each_entry(dev, head, index_hlist) { if (idx < s_idx) goto cont; dev_hold(dev); rtnl_unlock(); ret = ethnl_default_dump_one(skb, dev, ctx, cb); dev_put(dev); if (ret < 0) { if (ret == -EOPNOTSUPP) goto lock_and_cont; if (likely(skb->len)) ret = skb->len; goto out; } lock_and_cont: rtnl_lock(); if (net->dev_base_seq != seq) { s_idx = idx + 1; goto restart_chain; } cont: idx++; } } rtnl_unlock(); out: ctx->pos_hash = h; ctx->pos_idx = idx; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return ret; } /* generic ->start() handler for GET requests */ static int ethnl_default_start(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); struct ethnl_reply_data *reply_data; const struct ethnl_request_ops *ops; struct ethnl_req_info *req_info; struct genlmsghdr *ghdr; int ret; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); ghdr = nlmsg_data(cb->nlh); ops = ethnl_default_requests[ghdr->cmd]; if (WARN_ONCE(!ops, "cmd %u has no ethnl_request_ops\n", ghdr->cmd)) return -EOPNOTSUPP; req_info = kzalloc(ops->req_info_size, GFP_KERNEL); if (!req_info) return -ENOMEM; reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); if (!reply_data) { ret = -ENOMEM; goto free_req_info; } ret = ethnl_default_parse(req_info, info->attrs, sock_net(cb->skb->sk), ops, cb->extack, false); if (req_info->dev) { /* We ignore device specification in dump requests but as the * same parser as for non-dump (doit) requests is used, it * would take reference to the device if it finds one */ netdev_put(req_info->dev, &req_info->dev_tracker); req_info->dev = NULL; } if (ret < 0) goto free_reply_data; ctx->ops = ops; ctx->req_info = req_info; ctx->reply_data = reply_data; ctx->pos_hash = 0; ctx->pos_idx = 0; return 0; free_reply_data: kfree(reply_data); free_req_info: kfree(req_info); return ret; } /* default ->done() handler for GET requests */ static int ethnl_default_done(struct netlink_callback *cb) { struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); kfree(ctx->reply_data); kfree(ctx->req_info); return 0; } static const struct ethnl_request_ops * ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = { [ETHTOOL_MSG_LINKINFO_NTF] = ðnl_linkinfo_request_ops, [ETHTOOL_MSG_LINKMODES_NTF] = ðnl_linkmodes_request_ops, [ETHTOOL_MSG_DEBUG_NTF] = ðnl_debug_request_ops, [ETHTOOL_MSG_WOL_NTF] = ðnl_wol_request_ops, [ETHTOOL_MSG_FEATURES_NTF] = ðnl_features_request_ops, [ETHTOOL_MSG_PRIVFLAGS_NTF] = ðnl_privflags_request_ops, [ETHTOOL_MSG_RINGS_NTF] = ðnl_rings_request_ops, [ETHTOOL_MSG_CHANNELS_NTF] = ðnl_channels_request_ops, [ETHTOOL_MSG_COALESCE_NTF] = ðnl_coalesce_request_ops, [ETHTOOL_MSG_PAUSE_NTF] = ðnl_pause_request_ops, [ETHTOOL_MSG_EEE_NTF] = ðnl_eee_request_ops, [ETHTOOL_MSG_FEC_NTF] = ðnl_fec_request_ops, [ETHTOOL_MSG_MODULE_NTF] = ðnl_module_request_ops, }; /* default notification handler */ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd, const void *data) { struct ethnl_reply_data *reply_data; const struct ethnl_request_ops *ops; struct ethnl_req_info *req_info; struct sk_buff *skb; void *reply_payload; int reply_len; int ret; if (WARN_ONCE(cmd > ETHTOOL_MSG_KERNEL_MAX || !ethnl_default_notify_ops[cmd], "unexpected notification type %u\n", cmd)) return; ops = ethnl_default_notify_ops[cmd]; req_info = kzalloc(ops->req_info_size, GFP_KERNEL); if (!req_info) return; reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); if (!reply_data) { kfree(req_info); return; } req_info->dev = dev; req_info->flags |= ETHTOOL_FLAG_COMPACT_BITSETS; ethnl_init_reply_data(reply_data, ops, dev); ret = ops->prepare_data(req_info, reply_data, NULL); if (ret < 0) goto err_cleanup; ret = ops->reply_size(req_info, reply_data); if (ret < 0) goto err_cleanup; reply_len = ret + ethnl_reply_header_size(); skb = genlmsg_new(reply_len, GFP_KERNEL); if (!skb) goto err_cleanup; reply_payload = ethnl_bcastmsg_put(skb, cmd); if (!reply_payload) goto err_skb; ret = ethnl_fill_reply_header(skb, dev, ops->hdr_attr); if (ret < 0) goto err_msg; ret = ops->fill_reply(skb, req_info, reply_data); if (ret < 0) goto err_msg; if (ops->cleanup_data) ops->cleanup_data(reply_data); genlmsg_end(skb, reply_payload); kfree(reply_data); kfree(req_info); ethnl_multicast(skb, dev); return; err_msg: WARN_ONCE(ret == -EMSGSIZE, "calculated message payload length (%d) not sufficient\n", reply_len); err_skb: nlmsg_free(skb); err_cleanup: if (ops->cleanup_data) ops->cleanup_data(reply_data); kfree(reply_data); kfree(req_info); return; } /* notifications */ typedef void (*ethnl_notify_handler_t)(struct net_device *dev, unsigned int cmd, const void *data); static const ethnl_notify_handler_t ethnl_notify_handlers[] = { [ETHTOOL_MSG_LINKINFO_NTF] = ethnl_default_notify, [ETHTOOL_MSG_LINKMODES_NTF] = ethnl_default_notify, [ETHTOOL_MSG_DEBUG_NTF] = ethnl_default_notify, [ETHTOOL_MSG_WOL_NTF] = ethnl_default_notify, [ETHTOOL_MSG_FEATURES_NTF] = ethnl_default_notify, [ETHTOOL_MSG_PRIVFLAGS_NTF] = ethnl_default_notify, [ETHTOOL_MSG_RINGS_NTF] = ethnl_default_notify, [ETHTOOL_MSG_CHANNELS_NTF] = ethnl_default_notify, [ETHTOOL_MSG_COALESCE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_PAUSE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_EEE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_FEC_NTF] = ethnl_default_notify, [ETHTOOL_MSG_MODULE_NTF] = ethnl_default_notify, }; void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data) { if (unlikely(!ethnl_ok)) return; ASSERT_RTNL(); if (likely(cmd < ARRAY_SIZE(ethnl_notify_handlers) && ethnl_notify_handlers[cmd])) ethnl_notify_handlers[cmd](dev, cmd, data); else WARN_ONCE(1, "notification %u not implemented (dev=%s)\n", cmd, netdev_name(dev)); } EXPORT_SYMBOL(ethtool_notify); static void ethnl_notify_features(struct netdev_notifier_info *info) { struct net_device *dev = netdev_notifier_info_to_dev(info); ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF, NULL); } static int ethnl_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { switch (event) { case NETDEV_FEAT_CHANGE: ethnl_notify_features(ptr); break; } return NOTIFY_DONE; } static struct notifier_block ethnl_netdev_notifier = { .notifier_call = ethnl_netdev_event, }; /* genetlink setup */ static const struct genl_ops ethtool_genl_ops[] = { { .cmd = ETHTOOL_MSG_STRSET_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_strset_get_policy, .maxattr = ARRAY_SIZE(ethnl_strset_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKINFO_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_linkinfo_get_policy, .maxattr = ARRAY_SIZE(ethnl_linkinfo_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKINFO_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_linkinfo, .policy = ethnl_linkinfo_set_policy, .maxattr = ARRAY_SIZE(ethnl_linkinfo_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKMODES_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_linkmodes_get_policy, .maxattr = ARRAY_SIZE(ethnl_linkmodes_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKMODES_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_linkmodes, .policy = ethnl_linkmodes_set_policy, .maxattr = ARRAY_SIZE(ethnl_linkmodes_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKSTATE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_linkstate_get_policy, .maxattr = ARRAY_SIZE(ethnl_linkstate_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_DEBUG_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_debug_get_policy, .maxattr = ARRAY_SIZE(ethnl_debug_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_DEBUG_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_debug, .policy = ethnl_debug_set_policy, .maxattr = ARRAY_SIZE(ethnl_debug_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_WOL_GET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_wol_get_policy, .maxattr = ARRAY_SIZE(ethnl_wol_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_WOL_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_wol, .policy = ethnl_wol_set_policy, .maxattr = ARRAY_SIZE(ethnl_wol_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEATURES_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_features_get_policy, .maxattr = ARRAY_SIZE(ethnl_features_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEATURES_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_features, .policy = ethnl_features_set_policy, .maxattr = ARRAY_SIZE(ethnl_features_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_PRIVFLAGS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_privflags_get_policy, .maxattr = ARRAY_SIZE(ethnl_privflags_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PRIVFLAGS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_privflags, .policy = ethnl_privflags_set_policy, .maxattr = ARRAY_SIZE(ethnl_privflags_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_RINGS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_rings_get_policy, .maxattr = ARRAY_SIZE(ethnl_rings_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_RINGS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_rings, .policy = ethnl_rings_set_policy, .maxattr = ARRAY_SIZE(ethnl_rings_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_CHANNELS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_channels_get_policy, .maxattr = ARRAY_SIZE(ethnl_channels_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_CHANNELS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_channels, .policy = ethnl_channels_set_policy, .maxattr = ARRAY_SIZE(ethnl_channels_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_COALESCE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_coalesce_get_policy, .maxattr = ARRAY_SIZE(ethnl_coalesce_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_COALESCE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_coalesce, .policy = ethnl_coalesce_set_policy, .maxattr = ARRAY_SIZE(ethnl_coalesce_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_PAUSE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_pause_get_policy, .maxattr = ARRAY_SIZE(ethnl_pause_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PAUSE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_pause, .policy = ethnl_pause_set_policy, .maxattr = ARRAY_SIZE(ethnl_pause_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_EEE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_eee_get_policy, .maxattr = ARRAY_SIZE(ethnl_eee_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_EEE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_eee, .policy = ethnl_eee_set_policy, .maxattr = ARRAY_SIZE(ethnl_eee_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_TSINFO_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_tsinfo_get_policy, .maxattr = ARRAY_SIZE(ethnl_tsinfo_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_CABLE_TEST_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_act_cable_test, .policy = ethnl_cable_test_act_policy, .maxattr = ARRAY_SIZE(ethnl_cable_test_act_policy) - 1, }, { .cmd = ETHTOOL_MSG_CABLE_TEST_TDR_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_act_cable_test_tdr, .policy = ethnl_cable_test_tdr_act_policy, .maxattr = ARRAY_SIZE(ethnl_cable_test_tdr_act_policy) - 1, }, { .cmd = ETHTOOL_MSG_TUNNEL_INFO_GET, .doit = ethnl_tunnel_info_doit, .start = ethnl_tunnel_info_start, .dumpit = ethnl_tunnel_info_dumpit, .policy = ethnl_tunnel_info_get_policy, .maxattr = ARRAY_SIZE(ethnl_tunnel_info_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEC_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_fec_get_policy, .maxattr = ARRAY_SIZE(ethnl_fec_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEC_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_fec, .policy = ethnl_fec_set_policy, .maxattr = ARRAY_SIZE(ethnl_fec_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_MODULE_EEPROM_GET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_module_eeprom_get_policy, .maxattr = ARRAY_SIZE(ethnl_module_eeprom_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_STATS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_stats_get_policy, .maxattr = ARRAY_SIZE(ethnl_stats_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_phc_vclocks_get_policy, .maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_MODULE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_module_get_policy, .maxattr = ARRAY_SIZE(ethnl_module_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_MODULE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_module, .policy = ethnl_module_set_policy, .maxattr = ARRAY_SIZE(ethnl_module_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_PSE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_pse_get_policy, .maxattr = ARRAY_SIZE(ethnl_pse_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PSE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_pse, .policy = ethnl_pse_set_policy, .maxattr = ARRAY_SIZE(ethnl_pse_set_policy) - 1, }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { [ETHNL_MCGRP_MONITOR] = { .name = ETHTOOL_MCGRP_MONITOR_NAME }, }; static struct genl_family ethtool_genl_family __ro_after_init = { .name = ETHTOOL_GENL_NAME, .version = ETHTOOL_GENL_VERSION, .netnsok = true, .parallel_ops = true, .ops = ethtool_genl_ops, .n_ops = ARRAY_SIZE(ethtool_genl_ops), .resv_start_op = ETHTOOL_MSG_MODULE_GET + 1, .mcgrps = ethtool_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(ethtool_nl_mcgrps), }; /* module setup */ static int __init ethnl_init(void) { int ret; ret = genl_register_family(ðtool_genl_family); if (WARN(ret < 0, "ethtool: genetlink family registration failed")) return ret; ethnl_ok = true; ret = register_netdevice_notifier(ðnl_netdev_notifier); WARN(ret < 0, "ethtool: net device notifier registration failed"); return ret; } subsys_initcall(ethnl_init); |
| 1876 73 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_UTSNAME_H #define _LINUX_UTSNAME_H #include <linux/sched.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/err.h> #include <uapi/linux/utsname.h> enum uts_proc { UTS_PROC_ARCH, UTS_PROC_OSTYPE, UTS_PROC_OSRELEASE, UTS_PROC_VERSION, UTS_PROC_HOSTNAME, UTS_PROC_DOMAINNAME, }; struct user_namespace; extern struct user_namespace init_user_ns; struct uts_namespace { struct new_utsname name; struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; } __randomize_layout; extern struct uts_namespace init_uts_ns; #ifdef CONFIG_UTS_NS static inline void get_uts_ns(struct uts_namespace *ns) { refcount_inc(&ns->ns.count); } extern struct uts_namespace *copy_utsname(unsigned long flags, struct user_namespace *user_ns, struct uts_namespace *old_ns); extern void free_uts_ns(struct uts_namespace *ns); static inline void put_uts_ns(struct uts_namespace *ns) { if (refcount_dec_and_test(&ns->ns.count)) free_uts_ns(ns); } void uts_ns_init(void); #else static inline void get_uts_ns(struct uts_namespace *ns) { } static inline void put_uts_ns(struct uts_namespace *ns) { } static inline struct uts_namespace *copy_utsname(unsigned long flags, struct user_namespace *user_ns, struct uts_namespace *old_ns) { if (flags & CLONE_NEWUTS) return ERR_PTR(-EINVAL); return old_ns; } static inline void uts_ns_init(void) { } #endif #ifdef CONFIG_PROC_SYSCTL extern void uts_proc_notify(enum uts_proc proc); #else static inline void uts_proc_notify(enum uts_proc proc) { } #endif static inline struct new_utsname *utsname(void) { return ¤t->nsproxy->uts_ns->name; } static inline struct new_utsname *init_utsname(void) { return &init_uts_ns.name; } extern struct rw_semaphore uts_sem; #endif /* _LINUX_UTSNAME_H */ |
| 3432 1143 1747 234 125 22 3624 1041 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Berkeley style UIO structures - Alan Cox 1994. */ #ifndef __LINUX_UIO_H #define __LINUX_UIO_H #include <linux/kernel.h> #include <linux/thread_info.h> #include <linux/mm_types.h> #include <uapi/linux/uio.h> struct page; struct pipe_inode_info; struct kvec { void *iov_base; /* and that should *never* hold a userland pointer */ size_t iov_len; }; enum iter_type { /* iter types */ ITER_IOVEC, ITER_KVEC, ITER_BVEC, ITER_PIPE, ITER_XARRAY, ITER_DISCARD, ITER_UBUF, }; struct iov_iter_state { size_t iov_offset; size_t count; unsigned long nr_segs; }; struct iov_iter { u8 iter_type; bool nofault; bool data_source; bool user_backed; union { size_t iov_offset; int last_offset; }; size_t count; union { const struct iovec *iov; const struct kvec *kvec; const struct bio_vec *bvec; struct xarray *xarray; struct pipe_inode_info *pipe; void __user *ubuf; }; union { unsigned long nr_segs; struct { unsigned int head; unsigned int start_head; }; loff_t xarray_start; }; }; static inline enum iter_type iov_iter_type(const struct iov_iter *i) { return i->iter_type; } static inline void iov_iter_save_state(struct iov_iter *iter, struct iov_iter_state *state) { state->iov_offset = iter->iov_offset; state->count = iter->count; state->nr_segs = iter->nr_segs; } static inline bool iter_is_ubuf(const struct iov_iter *i) { return iov_iter_type(i) == ITER_UBUF; } static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; } static inline bool iov_iter_is_kvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_KVEC; } static inline bool iov_iter_is_bvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_BVEC; } static inline bool iov_iter_is_pipe(const struct iov_iter *i) { return iov_iter_type(i) == ITER_PIPE; } static inline bool iov_iter_is_discard(const struct iov_iter *i) { return iov_iter_type(i) == ITER_DISCARD; } static inline bool iov_iter_is_xarray(const struct iov_iter *i) { return iov_iter_type(i) == ITER_XARRAY; } static inline unsigned char iov_iter_rw(const struct iov_iter *i) { return i->data_source ? WRITE : READ; } static inline bool user_backed_iter(const struct iov_iter *i) { return i->user_backed; } /* * Total number of bytes covered by an iovec. * * NOTE that it is not safe to use this function until all the iovec's * segment lengths have been validated. Because the individual lengths can * overflow a size_t when added together. */ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) { unsigned long seg; size_t ret = 0; for (seg = 0; seg < nr_segs; seg++) ret += iov[seg].iov_len; return ret; } static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) { return (struct iovec) { .iov_base = iter->iov->iov_base + iter->iov_offset, .iov_len = min(iter->count, iter->iov->iov_len - iter->iov_offset), }; } size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i); void iov_iter_advance(struct iov_iter *i, size_t bytes); void iov_iter_revert(struct iov_iter *i, size_t bytes); size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes); size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i) { return copy_page_to_iter(&folio->page, offset, bytes, i); } static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, true)) return _copy_to_iter(addr, bytes, i); return 0; } static __always_inline __must_check size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, false)) return _copy_from_iter(addr, bytes, i); return 0; } static __always_inline __must_check bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter(addr, bytes, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } static __always_inline __must_check size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, false)) return _copy_from_iter_nocache(addr, bytes, i); return 0; } static __always_inline __must_check bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter_nocache(addr, bytes, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /* * Note, users like pmem that depend on the stricter semantics of * _copy_from_iter_flushcache() than _copy_from_iter_nocache() must check for * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the * destination is flushed from the cache on return. */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_from_iter_flushcache _copy_from_iter_nocache #endif #ifdef CONFIG_ARCH_HAS_COPY_MC size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_mc_to_iter _copy_to_iter #endif size_t iov_iter_zero(size_t bytes, struct iov_iter *); bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask, unsigned len_mask); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count); void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count); ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); static inline size_t iov_iter_count(const struct iov_iter *i) { return i->count; } /* * Cap the iov_iter by given limit; note that the second argument is * *not* the new size - it's upper limit for such. Passing it a value * greater than the amount of data in iov_iter is fine - it'll just do * nothing in that case. */ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) { /* * count doesn't have to fit in size_t - comparison extends both * operands to u64 here and any value that would be truncated by * conversion in assignement is by definition greater than all * values of size_t, including old i->count. */ if (i->count > count) i->count = count; } /* * reexpand a previously truncated iterator; count must be no more than how much * we had shrunk it. */ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { i->count = count; } static inline int iov_iter_npages_cap(struct iov_iter *i, int maxpages, size_t max_bytes) { size_t shorted = 0; int npages; if (iov_iter_count(i) > max_bytes) { shorted = iov_iter_count(i) - max_bytes; iov_iter_truncate(i, max_bytes); } npages = iov_iter_npages(i, maxpages); if (shorted) iov_iter_reexpand(i, iov_iter_count(i) + shorted); return npages; } struct csum_state { __wsum csum; size_t off; }; size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csstate, struct iov_iter *i); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); static __always_inline __must_check bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) { size_t copied = csum_and_copy_from_iter(addr, bytes, csum, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, struct iov_iter *i); struct iovec *iovec_from_user(const struct iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat); ssize_t import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i); ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat); int import_single_range(int type, void __user *buf, size_t len, struct iovec *iov, struct iov_iter *i); static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, void __user *buf, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_UBUF, .user_backed = true, .data_source = direction, .ubuf = buf, .count = count }; } #endif |
| 1027 1027 1018 1018 1018 959 959 959 959 924 806 924 959 829 18 959 959 828 958 64 530 1027 1027 1027 1053 1053 1037 1027 23 1027 1027 174 174 27 1027 1027 174 1018 72 1027 1027 1027 12 1018 1018 304 980 987 174 980 498 987 1016 12 1053 33 1053 1143 1143 1143 1143 1143 1143 1143 1142 1143 1143 1143 1143 1016 959 959 951 861 959 220 959 828 828 828 828 959 1143 959 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Red Hat, Inc. * Copyright (c) 2016-2021 Christoph Hellwig. */ #include <linux/module.h> #include <linux/compiler.h> #include <linux/fs.h> #include <linux/fscrypt.h> #include <linux/pagemap.h> #include <linux/iomap.h> #include <linux/backing-dev.h> #include <linux/uio.h> #include <linux/task_io_accounting_ops.h> #include "trace.h" #include "../internal.h" /* * Private flags for iomap_dio, must not overlap with the public ones in * iomap.h: */ #define IOMAP_DIO_WRITE_FUA (1 << 28) #define IOMAP_DIO_NEED_SYNC (1 << 29) #define IOMAP_DIO_WRITE (1 << 30) #define IOMAP_DIO_DIRTY (1 << 31) struct iomap_dio { struct kiocb *iocb; const struct iomap_dio_ops *dops; loff_t i_size; loff_t size; atomic_t ref; unsigned flags; int error; size_t done_before; bool wait_for_completion; union { /* used during submission and for synchronous completion: */ struct { struct iov_iter *iter; struct task_struct *waiter; struct bio *poll_bio; } submit; /* used for aio completion: */ struct { struct work_struct work; } aio; }; }; static struct bio *iomap_dio_alloc_bio(const struct iomap_iter *iter, struct iomap_dio *dio, unsigned short nr_vecs, blk_opf_t opf) { if (dio->dops && dio->dops->bio_set) return bio_alloc_bioset(iter->iomap.bdev, nr_vecs, opf, GFP_KERNEL, dio->dops->bio_set); return bio_alloc(iter->iomap.bdev, nr_vecs, opf, GFP_KERNEL); } static void iomap_dio_submit_bio(const struct iomap_iter *iter, struct iomap_dio *dio, struct bio *bio, loff_t pos) { atomic_inc(&dio->ref); /* Sync dio can't be polled reliably */ if ((dio->iocb->ki_flags & IOCB_HIPRI) && !is_sync_kiocb(dio->iocb)) { bio_set_polled(bio, dio->iocb); dio->submit.poll_bio = bio; } if (dio->dops && dio->dops->submit_io) dio->dops->submit_io(iter, bio, pos); else submit_bio(bio); } ssize_t iomap_dio_complete(struct iomap_dio *dio) { const struct iomap_dio_ops *dops = dio->dops; struct kiocb *iocb = dio->iocb; struct inode *inode = file_inode(iocb->ki_filp); loff_t offset = iocb->ki_pos; ssize_t ret = dio->error; if (dops && dops->end_io) ret = dops->end_io(iocb, dio->size, ret, dio->flags); if (likely(!ret)) { ret = dio->size; /* check for short read */ if (offset + ret > dio->i_size && !(dio->flags & IOMAP_DIO_WRITE)) ret = dio->i_size - offset; iocb->ki_pos += ret; } /* * 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 ->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 (!dio->error && dio->size && (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) { int err; err = invalidate_inode_pages2_range(inode->i_mapping, offset >> PAGE_SHIFT, (offset + dio->size - 1) >> PAGE_SHIFT); if (err) dio_warn_stale_pagecache(iocb->ki_filp); } inode_dio_end(file_inode(iocb->ki_filp)); /* * If this is a DSYNC write, make sure we push it to stable storage now * that we've written data. */ if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC)) ret = generic_write_sync(iocb, ret); if (ret > 0) ret += dio->done_before; kfree(dio); return ret; } EXPORT_SYMBOL_GPL(iomap_dio_complete); static void iomap_dio_complete_work(struct work_struct *work) { struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work); struct kiocb *iocb = dio->iocb; iocb->ki_complete(iocb, iomap_dio_complete(dio)); } /* * Set an error in the dio if none is set yet. We have to use cmpxchg * as the submission context and the completion context(s) can race to * update the error. */ static inline void iomap_dio_set_error(struct iomap_dio *dio, int ret) { cmpxchg(&dio->error, 0, ret); } void iomap_dio_bio_end_io(struct bio *bio) { struct iomap_dio *dio = bio->bi_private; bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY); if (bio->bi_status) iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status)); if (atomic_dec_and_test(&dio->ref)) { if (dio->wait_for_completion) { struct task_struct *waiter = dio->submit.waiter; WRITE_ONCE(dio->submit.waiter, NULL); blk_wake_io_task(waiter); } else if (dio->flags & IOMAP_DIO_WRITE) { struct inode *inode = file_inode(dio->iocb->ki_filp); WRITE_ONCE(dio->iocb->private, NULL); INIT_WORK(&dio->aio.work, iomap_dio_complete_work); queue_work(inode->i_sb->s_dio_done_wq, &dio->aio.work); } else { WRITE_ONCE(dio->iocb->private, NULL); iomap_dio_complete_work(&dio->aio.work); } } if (should_dirty) { bio_check_pages_dirty(bio); } else { bio_release_pages(bio, false); bio_put(bio); } } EXPORT_SYMBOL_GPL(iomap_dio_bio_end_io); static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio, loff_t pos, unsigned len) { struct inode *inode = file_inode(dio->iocb->ki_filp); struct page *page = ZERO_PAGE(0); struct bio *bio; bio = iomap_dio_alloc_bio(iter, dio, 1, REQ_OP_WRITE | REQ_SYNC | REQ_IDLE); fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits, GFP_KERNEL); bio->bi_iter.bi_sector = iomap_sector(&iter->iomap, pos); bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; get_page(page); __bio_add_page(bio, page, len, 0); iomap_dio_submit_bio(iter, dio, bio, pos); } /* * Figure out the bio's operation flags from the dio request, the * mapping, and whether or not we want FUA. Note that we can end up * clearing the WRITE_FUA flag in the dio request. */ static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio, const struct iomap *iomap, bool use_fua) { blk_opf_t opflags = REQ_SYNC | REQ_IDLE; if (!(dio->flags & IOMAP_DIO_WRITE)) { WARN_ON_ONCE(iomap->flags & IOMAP_F_ZONE_APPEND); return REQ_OP_READ; } if (iomap->flags & IOMAP_F_ZONE_APPEND) opflags |= REQ_OP_ZONE_APPEND; else opflags |= REQ_OP_WRITE; if (use_fua) opflags |= REQ_FUA; else dio->flags &= ~IOMAP_DIO_WRITE_FUA; return opflags; } static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter, struct iomap_dio *dio) { const struct iomap *iomap = &iter->iomap; struct inode *inode = iter->inode; unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev)); unsigned int fs_block_size = i_blocksize(inode), pad; loff_t length = iomap_length(iter); loff_t pos = iter->pos; blk_opf_t bio_opf; struct bio *bio; bool need_zeroout = false; bool use_fua = false; int nr_pages, ret = 0; size_t copied = 0; size_t orig_count; if ((pos | length) & ((1 << blkbits) - 1) || !bdev_iter_is_aligned(iomap->bdev, dio->submit.iter)) return -EINVAL; if (iomap->type == IOMAP_UNWRITTEN) { dio->flags |= IOMAP_DIO_UNWRITTEN; need_zeroout = true; } if (iomap->flags & IOMAP_F_SHARED) dio->flags |= IOMAP_DIO_COW; if (iomap->flags & IOMAP_F_NEW) { need_zeroout = true; } else if (iomap->type == IOMAP_MAPPED) { /* * Use a FUA write if we need datasync semantics, this is a pure * data IO that doesn't require any metadata updates (including * after IO completion such as unwritten extent conversion) and * the underlying device supports FUA. This allows us to avoid * cache flushes on IO completion. */ if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) && (dio->flags & IOMAP_DIO_WRITE_FUA) && bdev_fua(iomap->bdev)) use_fua = true; } /* * Save the original count and trim the iter to just the extent we * are operating on right now. The iter will be re-expanded once * we are done. */ orig_count = iov_iter_count(dio->submit.iter); iov_iter_truncate(dio->submit.iter, length); if (!iov_iter_count(dio->submit.iter)) goto out; /* * We can only poll for single bio I/Os. */ if (need_zeroout || ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) dio->iocb->ki_flags &= ~IOCB_HIPRI; if (need_zeroout) { /* zero out from the start of the block to the write offset */ pad = pos & (fs_block_size - 1); if (pad) iomap_dio_zero(iter, dio, pos - pad, pad); } /* * Set the operation flags early so that bio_iov_iter_get_pages * can set up the page vector appropriately for a ZONE_APPEND * operation. */ bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua); nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS); do { size_t n; if (dio->error) { iov_iter_revert(dio->submit.iter, copied); copied = ret = 0; goto out; } bio = iomap_dio_alloc_bio(iter, dio, nr_pages, bio_opf); fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits, GFP_KERNEL); bio->bi_iter.bi_sector = iomap_sector(iomap, pos); bio->bi_ioprio = dio->iocb->ki_ioprio; bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; ret = bio_iov_iter_get_pages(bio, dio->submit.iter); if (unlikely(ret)) { /* * We have to stop part way through an IO. We must fall * through to the sub-block tail zeroing here, otherwise * this short IO may expose stale data in the tail of * the block we haven't written data to. */ bio_put(bio); goto zero_tail; } n = bio->bi_iter.bi_size; if (dio->flags & IOMAP_DIO_WRITE) { task_io_account_write(n); } else { if (dio->flags & IOMAP_DIO_DIRTY) bio_set_pages_dirty(bio); } dio->size += n; copied += n; nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS); /* * We can only poll for single bio I/Os. */ if (nr_pages) dio->iocb->ki_flags &= ~IOCB_HIPRI; iomap_dio_submit_bio(iter, dio, bio, pos); pos += n; } while (nr_pages); /* * We need to zeroout the tail of a sub-block write if the extent type * requires zeroing or the write extends beyond EOF. If we don't zero * the block tail in the latter case, we can expose stale data via mmap * reads of the EOF block. */ zero_tail: if (need_zeroout || ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) { /* zero out from the end of the write to the end of the block */ pad = pos & (fs_block_size - 1); if (pad) iomap_dio_zero(iter, dio, pos, fs_block_size - pad); } out: /* Undo iter limitation to current extent */ iov_iter_reexpand(dio->submit.iter, orig_count - copied); if (copied) return copied; return ret; } static loff_t iomap_dio_hole_iter(const struct iomap_iter *iter, struct iomap_dio *dio) { loff_t length = iov_iter_zero(iomap_length(iter), dio->submit.iter); dio->size += length; if (!length) return -EFAULT; return length; } static loff_t iomap_dio_inline_iter(const struct iomap_iter *iomi, struct iomap_dio *dio) { const struct iomap *iomap = &iomi->iomap; struct iov_iter *iter = dio->submit.iter; void *inline_data = iomap_inline_data(iomap, iomi->pos); loff_t length = iomap_length(iomi); loff_t pos = iomi->pos; size_t copied; if (WARN_ON_ONCE(!iomap_inline_data_valid(iomap))) return -EIO; if (dio->flags & IOMAP_DIO_WRITE) { loff_t size = iomi->inode->i_size; if (pos > size) memset(iomap_inline_data(iomap, size), 0, pos - size); copied = copy_from_iter(inline_data, length, iter); if (copied) { if (pos + copied > size) i_size_write(iomi->inode, pos + copied); mark_inode_dirty(iomi->inode); } } else { copied = copy_to_iter(inline_data, length, iter); } dio->size += copied; if (!copied) return -EFAULT; return copied; } static loff_t iomap_dio_iter(const struct iomap_iter *iter, struct iomap_dio *dio) { switch (iter->iomap.type) { case IOMAP_HOLE: if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE)) return -EIO; return iomap_dio_hole_iter(iter, dio); case IOMAP_UNWRITTEN: if (!(dio->flags & IOMAP_DIO_WRITE)) return iomap_dio_hole_iter(iter, dio); return iomap_dio_bio_iter(iter, dio); case IOMAP_MAPPED: return iomap_dio_bio_iter(iter, dio); case IOMAP_INLINE: return iomap_dio_inline_iter(iter, dio); case IOMAP_DELALLOC: /* * DIO is not serialised against mmap() access at all, and so * if the page_mkwrite occurs between the writeback and the * iomap_iter() call in the DIO path, then it will see the * DELALLOC block that the page-mkwrite allocated. */ pr_warn_ratelimited("Direct I/O collision with buffered writes! File: %pD4 Comm: %.20s\n", dio->iocb->ki_filp, current->comm); return -EIO; default: WARN_ON_ONCE(1); return -EIO; } } /* * iomap_dio_rw() always completes O_[D]SYNC writes regardless of whether the IO * is being issued as AIO or not. This allows us to optimise pure data writes * to use REQ_FUA rather than requiring generic_write_sync() to issue a * REQ_FLUSH post write. This is slightly tricky because a single request here * can be mapped into multiple disjoint IOs and only a subset of the IOs issued * may be pure data writes. In that case, we still need to do a full data sync * completion. * * When page faults are disabled and @dio_flags includes IOMAP_DIO_PARTIAL, * __iomap_dio_rw can return a partial result if it encounters a non-resident * page in @iter after preparing a transfer. In that case, the non-resident * pages can be faulted in and the request resumed with @done_before set to the * number of bytes previously transferred. The request will then complete with * the correct total number of bytes transferred; this is essential for * completing partial requests asynchronously. * * Returns -ENOTBLK In case of a page invalidation invalidation failure for * writes. The callers needs to fall back to buffered I/O in this case. */ struct iomap_dio * __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = file_inode(iocb->ki_filp); struct iomap_iter iomi = { .inode = inode, .pos = iocb->ki_pos, .len = iov_iter_count(iter), .flags = IOMAP_DIRECT, .private = private, }; loff_t end = iomi.pos + iomi.len - 1, ret = 0; bool wait_for_completion = is_sync_kiocb(iocb) || (dio_flags & IOMAP_DIO_FORCE_WAIT); struct blk_plug plug; struct iomap_dio *dio; if (!iomi.len) return NULL; dio = kmalloc(sizeof(*dio), GFP_KERNEL); if (!dio) return ERR_PTR(-ENOMEM); dio->iocb = iocb; atomic_set(&dio->ref, 1); dio->size = 0; dio->i_size = i_size_read(inode); dio->dops = dops; dio->error = 0; dio->flags = 0; dio->done_before = done_before; dio->submit.iter = iter; dio->submit.waiter = current; dio->submit.poll_bio = NULL; if (iov_iter_rw(iter) == READ) { if (iomi.pos >= dio->i_size) goto out_free_dio; if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_needs_writeback(mapping, iomi.pos, end)) { ret = -EAGAIN; goto out_free_dio; } iomi.flags |= IOMAP_NOWAIT; } if (user_backed_iter(iter)) dio->flags |= IOMAP_DIO_DIRTY; } else { iomi.flags |= IOMAP_WRITE; dio->flags |= IOMAP_DIO_WRITE; if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_has_page(mapping, iomi.pos, end)) { ret = -EAGAIN; goto out_free_dio; } iomi.flags |= IOMAP_NOWAIT; } /* for data sync or sync, we need sync completion processing */ if (iocb_is_dsync(iocb) && !(dio_flags & IOMAP_DIO_NOSYNC)) { dio->flags |= IOMAP_DIO_NEED_SYNC; /* * For datasync only writes, we optimistically try * using FUA for this IO. Any non-FUA write that * occurs will clear this flag, hence we know before * completion whether a cache flush is necessary. */ if (!(iocb->ki_flags & IOCB_SYNC)) dio->flags |= IOMAP_DIO_WRITE_FUA; } } if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) { ret = -EAGAIN; if (iomi.pos >= dio->i_size || iomi.pos + iomi.len > dio->i_size) goto out_free_dio; iomi.flags |= IOMAP_OVERWRITE_ONLY; } ret = filemap_write_and_wait_range(mapping, iomi.pos, end); if (ret) goto out_free_dio; if (iov_iter_rw(iter) == WRITE) { /* * Try to invalidate cache pages for the range we are writing. * If this invalidation fails, let the caller fall back to * buffered I/O. */ if (invalidate_inode_pages2_range(mapping, iomi.pos >> PAGE_SHIFT, end >> PAGE_SHIFT)) { trace_iomap_dio_invalidate_fail(inode, iomi.pos, iomi.len); ret = -ENOTBLK; goto out_free_dio; } if (!wait_for_completion && !inode->i_sb->s_dio_done_wq) { ret = sb_init_dio_done_wq(inode->i_sb); if (ret < 0) goto out_free_dio; } } inode_dio_begin(inode); blk_start_plug(&plug); while ((ret = iomap_iter(&iomi, ops)) > 0) { iomi.processed = iomap_dio_iter(&iomi, dio); /* * We can only poll for single bio I/Os. */ iocb->ki_flags &= ~IOCB_HIPRI; } blk_finish_plug(&plug); /* * We only report that we've read data up to i_size. * Revert iter to a state corresponding to that as some callers (such * as the splice code) rely on it. */ if (iov_iter_rw(iter) == READ && iomi.pos >= dio->i_size) iov_iter_revert(iter, iomi.pos - dio->i_size); if (ret == -EFAULT && dio->size && (dio_flags & IOMAP_DIO_PARTIAL)) { if (!(iocb->ki_flags & IOCB_NOWAIT)) wait_for_completion = true; ret = 0; } /* magic error code to fall back to buffered I/O */ if (ret == -ENOTBLK) { wait_for_completion = true; ret = 0; } if (ret < 0) iomap_dio_set_error(dio, ret); /* * If all the writes we issued were FUA, we don't need to flush the * cache on IO completion. Clear the sync flag for this case. */ if (dio->flags & IOMAP_DIO_WRITE_FUA) dio->flags &= ~IOMAP_DIO_NEED_SYNC; WRITE_ONCE(iocb->private, dio->submit.poll_bio); /* * We are about to drop our additional submission reference, which * might be the last reference to the dio. There are three different * ways we can progress here: * * (a) If this is the last reference we will always complete and free * the dio ourselves. * (b) If this is not the last reference, and we serve an asynchronous * iocb, we must never touch the dio after the decrement, the * I/O completion handler will complete and free it. * (c) If this is not the last reference, but we serve a synchronous * iocb, the I/O completion handler will wake us up on the drop * of the final reference, and we will complete and free it here * after we got woken by the I/O completion handler. */ dio->wait_for_completion = wait_for_completion; if (!atomic_dec_and_test(&dio->ref)) { if (!wait_for_completion) return ERR_PTR(-EIOCBQUEUED); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (!READ_ONCE(dio->submit.waiter)) break; blk_io_schedule(); } __set_current_state(TASK_RUNNING); } return dio; out_free_dio: kfree(dio); if (ret) return ERR_PTR(ret); return NULL; } EXPORT_SYMBOL_GPL(__iomap_dio_rw); ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before) { struct iomap_dio *dio; dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, private, done_before); if (IS_ERR_OR_NULL(dio)) return PTR_ERR_OR_ZERO(dio); return iomap_dio_complete(dio); } EXPORT_SYMBOL_GPL(iomap_dio_rw); |
| 4617 3107 3394 2741 894 868 4729 3418 4898 558 4611 4756 3777 129 1334 2094 725 1962 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/buffer_head.h * * Everything to do with buffer_heads. */ #ifndef _LINUX_BUFFER_HEAD_H #define _LINUX_BUFFER_HEAD_H #include <linux/types.h> #include <linux/blk_types.h> #include <linux/fs.h> #include <linux/linkage.h> #include <linux/pagemap.h> #include <linux/wait.h> #include <linux/atomic.h> #ifdef CONFIG_BLOCK enum bh_state_bits { BH_Uptodate, /* Contains valid data */ BH_Dirty, /* Is dirty */ BH_Lock, /* Is locked */ BH_Req, /* Has been submitted for I/O */ BH_Mapped, /* Has a disk mapping */ BH_New, /* Disk mapping was newly created by get_block */ BH_Async_Read, /* Is under end_buffer_async_read I/O */ BH_Async_Write, /* Is under end_buffer_async_write I/O */ BH_Delay, /* Buffer is not yet allocated on disk */ BH_Boundary, /* Block is followed by a discontiguity */ BH_Write_EIO, /* I/O error on write */ BH_Unwritten, /* Buffer is allocated on disk but not written */ BH_Quiet, /* Buffer Error Prinks to be quiet */ BH_Meta, /* Buffer contains metadata */ BH_Prio, /* Buffer should be submitted with REQ_PRIO */ BH_Defer_Completion, /* Defer AIO completion to workqueue */ BH_PrivateStart,/* not a state bit, but the first bit available * for private allocation by other entities */ }; #define MAX_BUF_PER_PAGE (PAGE_SIZE / 512) struct page; struct buffer_head; struct address_space; typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate); /* * Historically, a buffer_head was used to map a single block * within a page, and of course as the unit of I/O through the * filesystem and block layers. Nowadays the basic I/O unit * is the bio, and buffer_heads are used for extracting block * mappings (via a get_block_t call), for tracking state within * a page (via a page_mapping) and for wrapping bio submission * for backward compatibility reasons (e.g. submit_bh). */ struct buffer_head { unsigned long b_state; /* buffer state bitmap (see above) */ struct buffer_head *b_this_page;/* circular list of page's buffers */ struct page *b_page; /* the page this bh is mapped to */ sector_t b_blocknr; /* start block number */ size_t b_size; /* size of mapping */ char *b_data; /* pointer to data within the page */ struct block_device *b_bdev; bh_end_io_t *b_end_io; /* I/O completion */ void *b_private; /* reserved for b_end_io */ struct list_head b_assoc_buffers; /* associated with another mapping */ struct address_space *b_assoc_map; /* mapping this buffer is associated with */ atomic_t b_count; /* users using this buffer_head */ spinlock_t b_uptodate_lock; /* Used by the first bh in a page, to * serialise IO completion of other * buffers in the page */ }; /* * macro tricks to expand the set_buffer_foo(), clear_buffer_foo() * and buffer_foo() functions. * To avoid reset buffer flags that are already set, because that causes * a costly cache line transition, check the flag first. */ #define BUFFER_FNS(bit, name) \ static __always_inline void set_buffer_##name(struct buffer_head *bh) \ { \ if (!test_bit(BH_##bit, &(bh)->b_state)) \ set_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline void clear_buffer_##name(struct buffer_head *bh) \ { \ clear_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline int buffer_##name(const struct buffer_head *bh) \ { \ return test_bit(BH_##bit, &(bh)->b_state); \ } /* * test_set_buffer_foo() and test_clear_buffer_foo() */ #define TAS_BUFFER_FNS(bit, name) \ static __always_inline int test_set_buffer_##name(struct buffer_head *bh) \ { \ return test_and_set_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline int test_clear_buffer_##name(struct buffer_head *bh) \ { \ return test_and_clear_bit(BH_##bit, &(bh)->b_state); \ } \ /* * Emit the buffer bitops functions. Note that there are also functions * of the form "mark_buffer_foo()". These are higher-level functions which * do something in addition to setting a b_state bit. */ BUFFER_FNS(Dirty, dirty) TAS_BUFFER_FNS(Dirty, dirty) BUFFER_FNS(Lock, locked) BUFFER_FNS(Req, req) TAS_BUFFER_FNS(Req, req) BUFFER_FNS(Mapped, mapped) BUFFER_FNS(New, new) BUFFER_FNS(Async_Read, async_read) BUFFER_FNS(Async_Write, async_write) BUFFER_FNS(Delay, delay) BUFFER_FNS(Boundary, boundary) BUFFER_FNS(Write_EIO, write_io_error) BUFFER_FNS(Unwritten, unwritten) BUFFER_FNS(Meta, meta) BUFFER_FNS(Prio, prio) BUFFER_FNS(Defer_Completion, defer_completion) static __always_inline void set_buffer_uptodate(struct buffer_head *bh) { /* * If somebody else already set this uptodate, they will * have done the memory barrier, and a reader will thus * see *some* valid buffer state. * * Any other serialization (with IO errors or whatever that * might clear the bit) has to come from other state (eg BH_Lock). */ if (test_bit(BH_Uptodate, &bh->b_state)) return; /* * make it consistent with folio_mark_uptodate * pairs with smp_load_acquire in buffer_uptodate */ smp_mb__before_atomic(); set_bit(BH_Uptodate, &bh->b_state); } static __always_inline void clear_buffer_uptodate(struct buffer_head *bh) { clear_bit(BH_Uptodate, &bh->b_state); } static __always_inline int buffer_uptodate(const struct buffer_head *bh) { /* * make it consistent with folio_test_uptodate * pairs with smp_mb__before_atomic in set_buffer_uptodate */ return test_bit_acquire(BH_Uptodate, &bh->b_state); } #define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) /* If we *know* page->private refers to buffer_heads */ #define page_buffers(page) \ ({ \ BUG_ON(!PagePrivate(page)); \ ((struct buffer_head *)page_private(page)); \ }) #define page_has_buffers(page) PagePrivate(page) #define folio_buffers(folio) folio_get_private(folio) void buffer_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback); /* * Declarations */ void mark_buffer_dirty(struct buffer_head *bh); void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); bool try_to_free_buffers(struct folio *); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, unsigned long b_state); void end_buffer_read_sync(struct buffer_head *bh, int uptodate); void end_buffer_write_sync(struct buffer_head *bh, int uptodate); void end_buffer_async_write(struct buffer_head *bh, int uptodate); /* Things to do with buffers at mapping->private_list */ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode); int inode_has_buffers(struct inode *); void invalidate_inode_buffers(struct inode *); int remove_inode_buffers(struct inode *inode); int sync_mapping_buffers(struct address_space *mapping); void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len); static inline void clean_bdev_bh_alias(struct buffer_head *bh) { clean_bdev_aliases(bh->b_bdev, bh->b_blocknr, 1); } void mark_buffer_async_write(struct buffer_head *bh); void __wait_on_buffer(struct buffer_head *); wait_queue_head_t *bh_waitq_head(struct buffer_head *bh); struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block, unsigned size); struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp); void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); void invalidate_bh_lrus_cpu(void); bool has_bh_in_lru(int cpu, void *dummy); struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); void unlock_buffer(struct buffer_head *bh); void __lock_buffer(struct buffer_head *bh); int sync_dirty_buffer(struct buffer_head *bh); int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags); void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags); void submit_bh(blk_opf_t, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait); void __bh_read_batch(int nr, struct buffer_head *bhs[], blk_opf_t op_flags, bool force_lock); extern int buffer_heads_over_limit; /* * Generic address_space_operations implementations for buffer_head-backed * address_spaces. */ void block_invalidate_folio(struct folio *folio, size_t offset, size_t length); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler); int block_read_full_folio(struct folio *, get_block_t *); bool block_is_partially_uptodate(struct folio *, size_t from, size_t count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, get_block_t *get_block); int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); int generic_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); void clean_page_buffers(struct page *page); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, struct page **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); int block_commit_write(struct page *page, unsigned from, unsigned to); int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); /* Convert errno to return value from ->page_mkwrite() call */ static inline vm_fault_t block_page_mkwrite_return(int err) { if (err == 0) return VM_FAULT_LOCKED; if (err == -EFAULT || err == -EAGAIN) return VM_FAULT_NOPAGE; if (err == -ENOMEM) return VM_FAULT_OOM; /* -ENOSPC, -EDQUOT, -EIO ... */ return VM_FAULT_SIGBUS; } sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); #ifdef CONFIG_MIGRATION extern int buffer_migrate_folio(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); extern int buffer_migrate_folio_norefs(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); #else #define buffer_migrate_folio NULL #define buffer_migrate_folio_norefs NULL #endif void buffer_init(void); /* * inline definitions */ static inline void get_bh(struct buffer_head *bh) { atomic_inc(&bh->b_count); } static inline void put_bh(struct buffer_head *bh) { smp_mb__before_atomic(); atomic_dec(&bh->b_count); } static inline void brelse(struct buffer_head *bh) { if (bh) __brelse(bh); } static inline void bforget(struct buffer_head *bh) { if (bh) __bforget(bh); } static inline struct buffer_head * sb_bread(struct super_block *sb, sector_t block) { return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); } static inline struct buffer_head * sb_bread_unmovable(struct super_block *sb, sector_t block) { return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, 0); } static inline void sb_breadahead(struct super_block *sb, sector_t block) { __breadahead(sb->s_bdev, block, sb->s_blocksize); } static inline struct buffer_head * sb_getblk(struct super_block *sb, sector_t block) { return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); } static inline struct buffer_head * sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp) { return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp); } static inline struct buffer_head * sb_find_get_block(struct super_block *sb, sector_t block) { return __find_get_block(sb->s_bdev, block, sb->s_blocksize); } static inline void map_bh(struct buffer_head *bh, struct super_block *sb, sector_t block) { set_buffer_mapped(bh); bh->b_bdev = sb->s_bdev; bh->b_blocknr = block; bh->b_size = sb->s_blocksize; } static inline void wait_on_buffer(struct buffer_head *bh) { might_sleep(); if (buffer_locked(bh)) __wait_on_buffer(bh); } static inline int trylock_buffer(struct buffer_head *bh) { return likely(!test_and_set_bit_lock(BH_Lock, &bh->b_state)); } static inline void lock_buffer(struct buffer_head *bh) { might_sleep(); if (!trylock_buffer(bh)) __lock_buffer(bh); } static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, sector_t block, unsigned size) { return __getblk_gfp(bdev, block, size, 0); } static inline struct buffer_head *__getblk(struct block_device *bdev, sector_t block, unsigned size) { return __getblk_gfp(bdev, block, size, __GFP_MOVABLE); } static inline void bh_readahead(struct buffer_head *bh, blk_opf_t op_flags) { if (!buffer_uptodate(bh) && trylock_buffer(bh)) { if (!buffer_uptodate(bh)) __bh_read(bh, op_flags, false); else unlock_buffer(bh); } } static inline void bh_read_nowait(struct buffer_head *bh, blk_opf_t op_flags) { if (!bh_uptodate_or_lock(bh)) __bh_read(bh, op_flags, false); } /* Returns 1 if buffer uptodated, 0 on success, and -EIO on error. */ static inline int bh_read(struct buffer_head *bh, blk_opf_t op_flags) { if (bh_uptodate_or_lock(bh)) return 1; return __bh_read(bh, op_flags, true); } static inline void bh_read_batch(int nr, struct buffer_head *bhs[]) { __bh_read_batch(nr, bhs, 0, true); } static inline void bh_readahead_batch(int nr, struct buffer_head *bhs[], blk_opf_t op_flags) { __bh_read_batch(nr, bhs, op_flags, false); } /** * __bread() - reads a specified block and returns the bh * @bdev: the block_device to read from * @block: number of block * @size: size (in bytes) to read * * Reads a specified block, and returns buffer head that contains it. * The page cache is allocated from movable area so that it can be migrated. * It returns NULL if the block was unreadable. */ static inline struct buffer_head * __bread(struct block_device *bdev, sector_t block, unsigned size) { return __bread_gfp(bdev, block, size, __GFP_MOVABLE); } bool block_dirty_folio(struct address_space *mapping, struct folio *folio); #else /* CONFIG_BLOCK */ static inline void buffer_init(void) {} static inline bool try_to_free_buffers(struct folio *folio) { return true; } static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } static inline void invalidate_bh_lrus_cpu(void) {} static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; } #define buffer_heads_over_limit 0 #endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_H */ |
| 145 145 145 145 11 3 3 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/seq_file.c * * helper functions for making synthetic files from sequences of records. * initial implementation -- AV, Oct 2001. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/cache.h> #include <linux/fs.h> #include <linux/export.h> #include <linux/seq_file.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/mm.h> #include <linux/printk.h> #include <linux/string_helpers.h> #include <linux/uio.h> #include <linux/uaccess.h> #include <asm/page.h> static struct kmem_cache *seq_file_cache __ro_after_init; static void seq_set_overflow(struct seq_file *m) { m->count = m->size; } static void *seq_buf_alloc(unsigned long size) { if (unlikely(size > MAX_RW_COUNT)) return NULL; return kvmalloc(size, GFP_KERNEL_ACCOUNT); } /** * seq_open - initialize sequential file * @file: file we initialize * @op: method table describing the sequence * * seq_open() sets @file, associating it with a sequence described * by @op. @op->start() sets the iterator up and returns the first * element of sequence. @op->stop() shuts it down. @op->next() * returns the next element of sequence. @op->show() prints element * into the buffer. In case of error ->start() and ->next() return * ERR_PTR(error). In the end of sequence they return %NULL. ->show() * returns 0 in case of success and negative number in case of error. * Returning SEQ_SKIP means "discard this element and move on". * Note: seq_open() will allocate a struct seq_file and store its * pointer in @file->private_data. This pointer should not be modified. */ int seq_open(struct file *file, const struct seq_operations *op) { struct seq_file *p; WARN_ON(file->private_data); p = kmem_cache_zalloc(seq_file_cache, GFP_KERNEL); if (!p) return -ENOMEM; file->private_data = p; mutex_init(&p->lock); p->op = op; // No refcounting: the lifetime of 'p' is constrained // to the lifetime of the file. p->file = file; /* * seq_files support lseek() and pread(). They do not implement * write() at all, but we clear FMODE_PWRITE here for historical * reasons. * * If a client of seq_files a) implements file.write() and b) wishes to * support pwrite() then that client will need to implement its own * file.open() which calls seq_open() and then sets FMODE_PWRITE. */ file->f_mode &= ~FMODE_PWRITE; return 0; } EXPORT_SYMBOL(seq_open); static int traverse(struct seq_file *m, loff_t offset) { loff_t pos = 0; int error = 0; void *p; m->index = 0; m->count = m->from = 0; if (!offset) return 0; if (!m->buf) { m->buf = seq_buf_alloc(m->size = PAGE_SIZE); if (!m->buf) return -ENOMEM; } p = m->op->start(m, &m->index); while (p) { error = PTR_ERR(p); if (IS_ERR(p)) break; error = m->op->show(m, p); if (error < 0) break; if (unlikely(error)) { error = 0; m->count = 0; } if (seq_has_overflowed(m)) goto Eoverflow; p = m->op->next(m, p, &m->index); if (pos + m->count > offset) { m->from = offset - pos; m->count -= m->from; break; } pos += m->count; m->count = 0; if (pos == offset) break; } m->op->stop(m, p); return error; Eoverflow: m->op->stop(m, p); kvfree(m->buf); m->count = 0; m->buf = seq_buf_alloc(m->size <<= 1); return !m->buf ? -ENOMEM : -EAGAIN; } /** * seq_read - ->read() method for sequential files. * @file: the file to read from * @buf: the buffer to read to * @size: the maximum number of bytes to read * @ppos: the current position in the file * * Ready-made ->f_op->read() */ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) { struct iovec iov = { .iov_base = buf, .iov_len = size}; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, file); iov_iter_init(&iter, READ, &iov, 1, size); kiocb.ki_pos = *ppos; ret = seq_read_iter(&kiocb, &iter); *ppos = kiocb.ki_pos; return ret; } EXPORT_SYMBOL(seq_read); /* * Ready-made ->f_op->read_iter() */ ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct seq_file *m = iocb->ki_filp->private_data; size_t copied = 0; size_t n; void *p; int err = 0; if (!iov_iter_count(iter)) return 0; mutex_lock(&m->lock); /* * if request is to read from zero offset, reset iterator to first * record as it might have been already advanced by previous requests */ if (iocb->ki_pos == 0) { m->index = 0; m->count = 0; } /* Don't assume ki_pos is where we left it */ if (unlikely(iocb->ki_pos != m->read_pos)) { while ((err = traverse(m, iocb->ki_pos)) == -EAGAIN) ; if (err) { /* With prejudice... */ m->read_pos = 0; m->index = 0; m->count = 0; goto Done; } else { m->read_pos = iocb->ki_pos; } } /* grab buffer if we didn't have one */ if (!m->buf) { m->buf = seq_buf_alloc(m->size = PAGE_SIZE); if (!m->buf) goto Enomem; } // something left in the buffer - copy it out first if (m->count) { n = copy_to_iter(m->buf + m->from, m->count, iter); m->count -= n; m->from += n; copied += n; if (m->count) // hadn't managed to copy everything goto Done; } // get a non-empty record in the buffer m->from = 0; p = m->op->start(m, &m->index); while (1) { err = PTR_ERR(p); if (!p || IS_ERR(p)) // EOF or an error break; err = m->op->show(m, p); if (err < 0) // hard error break; if (unlikely(err)) // ->show() says "skip it" m->count = 0; if (unlikely(!m->count)) { // empty record p = m->op->next(m, p, &m->index); continue; } if (!seq_has_overflowed(m)) // got it goto Fill; // need a bigger buffer m->op->stop(m, p); kvfree(m->buf); m->count = 0; m->buf = seq_buf_alloc(m->size <<= 1); if (!m->buf) goto Enomem; p = m->op->start(m, &m->index); } // EOF or an error m->op->stop(m, p); m->count = 0; goto Done; Fill: // one non-empty record is in the buffer; if they want more, // try to fit more in, but in any case we need to advance // the iterator once for every record shown. while (1) { size_t offs = m->count; loff_t pos = m->index; p = m->op->next(m, p, &m->index); if (pos == m->index) { pr_info_ratelimited("buggy .next function %ps did not update position index\n", m->op->next); m->index++; } if (!p || IS_ERR(p)) // no next record for us break; if (m->count >= iov_iter_count(iter)) break; err = m->op->show(m, p); if (err > 0) { // ->show() says "skip it" m->count = offs; } else if (err || seq_has_overflowed(m)) { m->count = offs; break; } } m->op->stop(m, p); n = copy_to_iter(m->buf, m->count, iter); copied += n; m->count -= n; m->from = n; Done: if (unlikely(!copied)) { copied = m->count ? -EFAULT : err; } else { iocb->ki_pos += copied; m->read_pos += copied; } mutex_unlock(&m->lock); return copied; Enomem: err = -ENOMEM; goto Done; } EXPORT_SYMBOL(seq_read_iter); /** * seq_lseek - ->llseek() method for sequential files. * @file: the file in question * @offset: new position * @whence: 0 for absolute, 1 for relative position * * Ready-made ->f_op->llseek() */ loff_t seq_lseek(struct file *file, loff_t offset, int whence) { struct seq_file *m = file->private_data; loff_t retval = -EINVAL; mutex_lock(&m->lock); switch (whence) { case SEEK_CUR: offset += file->f_pos; fallthrough; case SEEK_SET: if (offset < 0) break; retval = offset; if (offset != m->read_pos) { while ((retval = traverse(m, offset)) == -EAGAIN) ; if (retval) { /* with extreme prejudice... */ file->f_pos = 0; m->read_pos = 0; m->index = 0; m->count = 0; } else { m->read_pos = offset; retval = file->f_pos = offset; } } else { file->f_pos = offset; } } mutex_unlock(&m->lock); return retval; } EXPORT_SYMBOL(seq_lseek); /** * seq_release - free the structures associated with sequential file. * @file: file in question * @inode: its inode * * Frees the structures associated with sequential file; can be used * as ->f_op->release() if you don't have private data to destroy. */ int seq_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; kvfree(m->buf); kmem_cache_free(seq_file_cache, m); return 0; } EXPORT_SYMBOL(seq_release); /** * seq_escape_mem - print data into buffer, escaping some characters * @m: target buffer * @src: source buffer * @len: size of source buffer * @flags: flags to pass to string_escape_mem() * @esc: set of characters that need escaping * * Puts data into buffer, replacing each occurrence of character from * given class (defined by @flags and @esc) with printable escaped sequence. * * Use seq_has_overflowed() to check for errors. */ void seq_escape_mem(struct seq_file *m, const char *src, size_t len, unsigned int flags, const char *esc) { char *buf; size_t size = seq_get_buf(m, &buf); int ret; ret = string_escape_mem(src, len, buf, size, flags, esc); seq_commit(m, ret < size ? ret : -1); } EXPORT_SYMBOL(seq_escape_mem); void seq_vprintf(struct seq_file *m, const char *f, va_list args) { int len; if (m->count < m->size) { len = vsnprintf(m->buf + m->count, m->size - m->count, f, args); if (m->count + len < m->size) { m->count += len; return; } } seq_set_overflow(m); } EXPORT_SYMBOL(seq_vprintf); void seq_printf(struct seq_file *m, const char *f, ...) { va_list args; va_start(args, f); seq_vprintf(m, f, args); va_end(args); } EXPORT_SYMBOL(seq_printf); #ifdef CONFIG_BINARY_PRINTF void seq_bprintf(struct seq_file *m, const char *f, const u32 *binary) { int len; if (m->count < m->size) { len = bstr_printf(m->buf + m->count, m->size - m->count, f, binary); if (m->count + len < m->size) { m->count += len; return; } } seq_set_overflow(m); } EXPORT_SYMBOL(seq_bprintf); #endif /* CONFIG_BINARY_PRINTF */ /** * mangle_path - mangle and copy path to buffer beginning * @s: buffer start * @p: beginning of path in above buffer * @esc: set of characters that need escaping * * Copy the path from @p to @s, replacing each occurrence of character from * @esc with usual octal escape. * Returns pointer past last written character in @s, or NULL in case of * failure. */ char *mangle_path(char *s, const char *p, const char *esc) { while (s <= p) { char c = *p++; if (!c) { return s; } else if (!strchr(esc, c)) { *s++ = c; } else if (s + 4 > p) { break; } else { *s++ = '\\'; *s++ = '0' + ((c & 0300) >> 6); *s++ = '0' + ((c & 070) >> 3); *s++ = '0' + (c & 07); } } return NULL; } EXPORT_SYMBOL(mangle_path); /** * seq_path - seq_file interface to print a pathname * @m: the seq_file handle * @path: the struct path to print * @esc: set of characters to escape in the output * * return the absolute path of 'path', as represented by the * dentry / mnt pair in the path parameter. */ int seq_path(struct seq_file *m, const struct path *path, const char *esc) { char *buf; size_t size = seq_get_buf(m, &buf); int res = -1; if (size) { char *p = d_path(path, buf, size); if (!IS_ERR(p)) { char *end = mangle_path(buf, p, esc); if (end) res = end - buf; } } seq_commit(m, res); return res; } EXPORT_SYMBOL(seq_path); /** * seq_file_path - seq_file interface to print a pathname of a file * @m: the seq_file handle * @file: the struct file to print * @esc: set of characters to escape in the output * * return the absolute path to the file. */ int seq_file_path(struct seq_file *m, struct file *file, const char *esc) { return seq_path(m, &file->f_path, esc); } EXPORT_SYMBOL(seq_file_path); /* * Same as seq_path, but relative to supplied root. */ int seq_path_root(struct seq_file *m, const struct path *path, const struct path *root, const char *esc) { char *buf; size_t size = seq_get_buf(m, &buf); int res = -ENAMETOOLONG; if (size) { char *p; p = __d_path(path, root, buf, size); if (!p) return SEQ_SKIP; res = PTR_ERR(p); if (!IS_ERR(p)) { char *end = mangle_path(buf, p, esc); if (end) res = end - buf; else res = -ENAMETOOLONG; } } seq_commit(m, res); return res < 0 && res != -ENAMETOOLONG ? res : 0; } /* * returns the path of the 'dentry' from the root of its filesystem. */ int seq_dentry(struct seq_file *m, struct dentry *dentry, const char *esc) { char *buf; size_t size = seq_get_buf(m, &buf); int res = -1; if (size) { char *p = dentry_path(dentry, buf, size); if (!IS_ERR(p)) { char *end = mangle_path(buf, p, esc); if (end) res = end - buf; } } seq_commit(m, res); return res; } EXPORT_SYMBOL(seq_dentry); void *single_start(struct seq_file *p, loff_t *pos) { return *pos ? NULL : SEQ_START_TOKEN; } static void *single_next(struct seq_file *p, void *v, loff_t *pos) { ++*pos; return NULL; } static void single_stop(struct seq_file *p, void *v) { } int single_open(struct file *file, int (*show)(struct seq_file *, void *), void *data) { struct seq_operations *op = kmalloc(sizeof(*op), GFP_KERNEL_ACCOUNT); int res = -ENOMEM; if (op) { op->start = single_start; op->next = single_next; op->stop = single_stop; op->show = show; res = seq_open(file, op); if (!res) ((struct seq_file *)file->private_data)->private = data; else kfree(op); } return res; } EXPORT_SYMBOL(single_open); int single_open_size(struct file *file, int (*show)(struct seq_file *, void *), void *data, size_t size) { char *buf = seq_buf_alloc(size); int ret; if (!buf) return -ENOMEM; ret = single_open(file, show, data); if (ret) { kvfree(buf); return ret; } ((struct seq_file *)file->private_data)->buf = buf; ((struct seq_file *)file->private_data)->size = size; return 0; } EXPORT_SYMBOL(single_open_size); int single_release(struct inode *inode, struct file *file) { const struct seq_operations *op = ((struct seq_file *)file->private_data)->op; int res = seq_release(inode, file); kfree(op); return res; } EXPORT_SYMBOL(single_release); int seq_release_private(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; kfree(seq->private); seq->private = NULL; return seq_release(inode, file); } EXPORT_SYMBOL(seq_release_private); void *__seq_open_private(struct file *f, const struct seq_operations *ops, int psize) { int rc; void *private; struct seq_file *seq; private = kzalloc(psize, GFP_KERNEL_ACCOUNT); if (private == NULL) goto out; rc = seq_open(f, ops); if (rc < 0) goto out_free; seq = f->private_data; seq->private = private; return private; out_free: kfree(private); out: return NULL; } EXPORT_SYMBOL(__seq_open_private); int seq_open_private(struct file *filp, const struct seq_operations *ops, int psize) { return __seq_open_private(filp, ops, psize) ? 0 : -ENOMEM; } EXPORT_SYMBOL(seq_open_private); void seq_putc(struct seq_file *m, char c) { if (m->count >= m->size) return; m->buf[m->count++] = c; } EXPORT_SYMBOL(seq_putc); void seq_puts(struct seq_file *m, const char *s) { int len = strlen(s); if (m->count + len >= m->size) { seq_set_overflow(m); return; } memcpy(m->buf + m->count, s, len); m->count += len; } EXPORT_SYMBOL(seq_puts); /** * seq_put_decimal_ull_width - A helper routine for putting decimal numbers * without rich format of printf(). * only 'unsigned long long' is supported. * @m: seq_file identifying the buffer to which data should be written * @delimiter: a string which is printed before the number * @num: the number * @width: a minimum field width * * This routine will put strlen(delimiter) + number into seq_filed. * This routine is very quick when you show lots of numbers. * In usual cases, it will be better to use seq_printf(). It's easier to read. */ void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter, unsigned long long num, unsigned int width) { int len; if (m->count + 2 >= m->size) /* we'll write 2 bytes at least */ goto overflow; if (delimiter && delimiter[0]) { if (delimiter[1] == 0) seq_putc(m, delimiter[0]); else seq_puts(m, delimiter); } if (!width) width = 1; if (m->count + width >= m->size) goto overflow; len = num_to_str(m->buf + m->count, m->size - m->count, num, width); if (!len) goto overflow; m->count += len; return; overflow: seq_set_overflow(m); } void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, unsigned long long num) { return seq_put_decimal_ull_width(m, delimiter, num, 0); } EXPORT_SYMBOL(seq_put_decimal_ull); /** * seq_put_hex_ll - put a number in hexadecimal notation * @m: seq_file identifying the buffer to which data should be written * @delimiter: a string which is printed before the number * @v: the number * @width: a minimum field width * * seq_put_hex_ll(m, "", v, 8) is equal to seq_printf(m, "%08llx", v) * * This routine is very quick when you show lots of numbers. * In usual cases, it will be better to use seq_printf(). It's easier to read. */ void seq_put_hex_ll(struct seq_file *m, const char *delimiter, unsigned long long v, unsigned int width) { unsigned int len; int i; if (delimiter && delimiter[0]) { if (delimiter[1] == 0) seq_putc(m, delimiter[0]); else seq_puts(m, delimiter); } /* If x is 0, the result of __builtin_clzll is undefined */ if (v == 0) len = 1; else len = (sizeof(v) * 8 - __builtin_clzll(v) + 3) / 4; if (len < width) len = width; if (m->count + len > m->size) { seq_set_overflow(m); return; } for (i = len - 1; i >= 0; i--) { m->buf[m->count + i] = hex_asc[0xf & v]; v = v >> 4; } m->count += len; } void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num) { int len; if (m->count + 3 >= m->size) /* we'll write 2 bytes at least */ goto overflow; if (delimiter && delimiter[0]) { if (delimiter[1] == 0) seq_putc(m, delimiter[0]); else seq_puts(m, delimiter); } if (m->count + 2 >= m->size) goto overflow; if (num < 0) { m->buf[m->count++] = '-'; num = -num; } if (num < 10) { m->buf[m->count++] = num + '0'; return; } len = num_to_str(m->buf + m->count, m->size - m->count, num, 0); if (!len) goto overflow; m->count += len; return; overflow: seq_set_overflow(m); } EXPORT_SYMBOL(seq_put_decimal_ll); /** * seq_write - write arbitrary data to buffer * @seq: seq_file identifying the buffer to which data should be written * @data: data address * @len: number of bytes * * Return 0 on success, non-zero otherwise. */ int seq_write(struct seq_file *seq, const void *data, size_t len) { if (seq->count + len < seq->size) { memcpy(seq->buf + seq->count, data, len); seq->count += len; return 0; } seq_set_overflow(seq); return -1; } EXPORT_SYMBOL(seq_write); /** * seq_pad - write padding spaces to buffer * @m: seq_file identifying the buffer to which data should be written * @c: the byte to append after padding if non-zero */ void seq_pad(struct seq_file *m, char c) { int size = m->pad_until - m->count; if (size > 0) { if (size + m->count > m->size) { seq_set_overflow(m); return; } memset(m->buf + m->count, ' ', size); m->count += size; } if (c) seq_putc(m, c); } EXPORT_SYMBOL(seq_pad); /* A complete analogue of print_hex_dump() */ void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { const u8 *ptr = buf; int i, linelen, remaining = len; char *buffer; size_t size; int ret; if (rowsize != 16 && rowsize != 32) rowsize = 16; for (i = 0; i < len && !seq_has_overflowed(m); i += rowsize) { linelen = min(remaining, rowsize); remaining -= rowsize; switch (prefix_type) { case DUMP_PREFIX_ADDRESS: seq_printf(m, "%s%p: ", prefix_str, ptr + i); break; case DUMP_PREFIX_OFFSET: seq_printf(m, "%s%.8x: ", prefix_str, i); break; default: seq_printf(m, "%s", prefix_str); break; } size = seq_get_buf(m, &buffer); ret = hex_dump_to_buffer(ptr + i, linelen, rowsize, groupsize, buffer, size, ascii); seq_commit(m, ret < size ? ret : -1); seq_putc(m, '\n'); } } EXPORT_SYMBOL(seq_hex_dump); struct list_head *seq_list_start(struct list_head *head, loff_t pos) { struct list_head *lh; list_for_each(lh, head) if (pos-- == 0) return lh; return NULL; } EXPORT_SYMBOL(seq_list_start); struct list_head *seq_list_start_head(struct list_head *head, loff_t pos) { if (!pos) return head; return seq_list_start(head, pos - 1); } EXPORT_SYMBOL(seq_list_start_head); struct list_head *seq_list_next(void *v, struct list_head *head, loff_t *ppos) { struct list_head *lh; lh = ((struct list_head *)v)->next; ++*ppos; return lh == head ? NULL : lh; } EXPORT_SYMBOL(seq_list_next); struct list_head *seq_list_start_rcu(struct list_head *head, loff_t pos) { struct list_head *lh; list_for_each_rcu(lh, head) if (pos-- == 0) return lh; return NULL; } EXPORT_SYMBOL(seq_list_start_rcu); struct list_head *seq_list_start_head_rcu(struct list_head *head, loff_t pos) { if (!pos) return head; return seq_list_start_rcu(head, pos - 1); } EXPORT_SYMBOL(seq_list_start_head_rcu); struct list_head *seq_list_next_rcu(void *v, struct list_head *head, loff_t *ppos) { struct list_head *lh; lh = list_next_rcu((struct list_head *)v); ++*ppos; return lh == head ? NULL : lh; } EXPORT_SYMBOL(seq_list_next_rcu); /** * seq_hlist_start - start an iteration of a hlist * @head: the head of the hlist * @pos: the start position of the sequence * * Called at seq_file->op->start(). */ struct hlist_node *seq_hlist_start(struct hlist_head *head, loff_t pos) { struct hlist_node *node; hlist_for_each(node, head) if (pos-- == 0) return node; return NULL; } EXPORT_SYMBOL(seq_hlist_start); /** * seq_hlist_start_head - start an iteration of a hlist * @head: the head of the hlist * @pos: the start position of the sequence * * Called at seq_file->op->start(). Call this function if you want to * print a header at the top of the output. */ struct hlist_node *seq_hlist_start_head(struct hlist_head *head, loff_t pos) { if (!pos) return SEQ_START_TOKEN; return seq_hlist_start(head, pos - 1); } EXPORT_SYMBOL(seq_hlist_start_head); /** * seq_hlist_next - move to the next position of the hlist * @v: the current iterator * @head: the head of the hlist * @ppos: the current position * * Called at seq_file->op->next(). */ struct hlist_node *seq_hlist_next(void *v, struct hlist_head *head, loff_t *ppos) { struct hlist_node *node = v; ++*ppos; if (v == SEQ_START_TOKEN) return head->first; else return node->next; } EXPORT_SYMBOL(seq_hlist_next); /** * seq_hlist_start_rcu - start an iteration of a hlist protected by RCU * @head: the head of the hlist * @pos: the start position of the sequence * * Called at seq_file->op->start(). * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ struct hlist_node *seq_hlist_start_rcu(struct hlist_head *head, loff_t pos) { struct hlist_node *node; __hlist_for_each_rcu(node, head) if (pos-- == 0) return node; return NULL; } EXPORT_SYMBOL(seq_hlist_start_rcu); /** * seq_hlist_start_head_rcu - start an iteration of a hlist protected by RCU * @head: the head of the hlist * @pos: the start position of the sequence * * Called at seq_file->op->start(). Call this function if you want to * print a header at the top of the output. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ struct hlist_node *seq_hlist_start_head_rcu(struct hlist_head *head, loff_t pos) { if (!pos) return SEQ_START_TOKEN; return seq_hlist_start_rcu(head, pos - 1); } EXPORT_SYMBOL(seq_hlist_start_head_rcu); /** * seq_hlist_next_rcu - move to the next position of the hlist protected by RCU * @v: the current iterator * @head: the head of the hlist * @ppos: the current position * * Called at seq_file->op->next(). * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ struct hlist_node *seq_hlist_next_rcu(void *v, struct hlist_head *head, loff_t *ppos) { struct hlist_node *node = v; ++*ppos; if (v == SEQ_START_TOKEN) return rcu_dereference(head->first); else return rcu_dereference(node->next); } EXPORT_SYMBOL(seq_hlist_next_rcu); /** * seq_hlist_start_percpu - start an iteration of a percpu hlist array * @head: pointer to percpu array of struct hlist_heads * @cpu: pointer to cpu "cursor" * @pos: start position of sequence * * Called at seq_file->op->start(). */ struct hlist_node * seq_hlist_start_percpu(struct hlist_head __percpu *head, int *cpu, loff_t pos) { struct hlist_node *node; for_each_possible_cpu(*cpu) { hlist_for_each(node, per_cpu_ptr(head, *cpu)) { if (pos-- == 0) return node; } } return NULL; } EXPORT_SYMBOL(seq_hlist_start_percpu); /** * seq_hlist_next_percpu - move to the next position of the percpu hlist array * @v: pointer to current hlist_node * @head: pointer to percpu array of struct hlist_heads * @cpu: pointer to cpu "cursor" * @pos: start position of sequence * * Called at seq_file->op->next(). */ struct hlist_node * seq_hlist_next_percpu(void *v, struct hlist_head __percpu *head, int *cpu, loff_t *pos) { struct hlist_node *node = v; ++*pos; if (node->next) return node->next; for (*cpu = cpumask_next(*cpu, cpu_possible_mask); *cpu < nr_cpu_ids; *cpu = cpumask_next(*cpu, cpu_possible_mask)) { struct hlist_head *bucket = per_cpu_ptr(head, *cpu); if (!hlist_empty(bucket)) return bucket->first; } return NULL; } EXPORT_SYMBOL(seq_hlist_next_percpu); void __init seq_file_init(void) { seq_file_cache = KMEM_CACHE(seq_file, SLAB_ACCOUNT|SLAB_PANIC); } |
| 73 73 73 73 45 45 45 45 45 45 45 45 44 44 45 73 73 209 209 209 225 224 519 19 19 3 476 455 455 73 29 14 91 91 91 91 3 3 96 122 45 45 122 122 122 122 122 122 122 122 122 122 122 122 30 248 248 91 248 247 248 62 62 45 62 62 501 501 63 1 1 1 1 29 498 72 29 100 72 100 122 72 50 1 102 30 29 24 24 96 224 224 247 224 209 208 209 209 209 209 209 209 652 652 209 209 14 14 14 32 3 1 1 1 3 1 1 31 14 29 31 28 11 28 1671 1671 469 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_generic.c Generic packet scheduler routines. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Jamal Hadi Salim, <hadi@cyberus.ca> 990601 * - Ingress support */ #include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/rcupdate.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/if_vlan.h> #include <linux/skb_array.h> #include <linux/if_macvlan.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> #include <trace/events/qdisc.h> #include <trace/events/net.h> #include <net/xfrm.h> /* Qdisc to use by default */ const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops; EXPORT_SYMBOL(default_qdisc_ops); static void qdisc_maybe_clear_missed(struct Qdisc *q, const struct netdev_queue *txq) { clear_bit(__QDISC_STATE_MISSED, &q->state); /* Make sure the below netif_xmit_frozen_or_stopped() * checking happens after clearing STATE_MISSED. */ smp_mb__after_atomic(); /* Checking netif_xmit_frozen_or_stopped() again to * make sure STATE_MISSED is set if the STATE_MISSED * set by netif_tx_wake_queue()'s rescheduling of * net_tx_action() is cleared by the above clear_bit(). */ if (!netif_xmit_frozen_or_stopped(txq)) set_bit(__QDISC_STATE_MISSED, &q->state); else set_bit(__QDISC_STATE_DRAINING, &q->state); } /* Main transmission queue. */ /* Modifications to data participating in scheduling must be protected with * qdisc_lock(qdisc) spinlock. * * The idea is the following: * - enqueue, dequeue are serialized via qdisc root lock * - ingress filtering is also serialized via qdisc root lock * - updates to tree and tree walking are only done under the rtnl mutex. */ #define SKB_XOFF_MAGIC ((struct sk_buff *)1UL) static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q) { const struct netdev_queue *txq = q->dev_queue; spinlock_t *lock = NULL; struct sk_buff *skb; if (q->flags & TCQ_F_NOLOCK) { lock = qdisc_lock(q); spin_lock(lock); } skb = skb_peek(&q->skb_bad_txq); if (skb) { /* check the reason of requeuing without tx lock first */ txq = skb_get_tx_queue(txq->dev, skb); if (!netif_xmit_frozen_or_stopped(txq)) { skb = __skb_dequeue(&q->skb_bad_txq); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_dec(q, skb); qdisc_qstats_cpu_qlen_dec(q); } else { qdisc_qstats_backlog_dec(q, skb); q->q.qlen--; } } else { skb = SKB_XOFF_MAGIC; qdisc_maybe_clear_missed(q, txq); } } if (lock) spin_unlock(lock); return skb; } static inline struct sk_buff *qdisc_dequeue_skb_bad_txq(struct Qdisc *q) { struct sk_buff *skb = skb_peek(&q->skb_bad_txq); if (unlikely(skb)) skb = __skb_dequeue_bad_txq(q); return skb; } static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q, struct sk_buff *skb) { spinlock_t *lock = NULL; if (q->flags & TCQ_F_NOLOCK) { lock = qdisc_lock(q); spin_lock(lock); } __skb_queue_tail(&q->skb_bad_txq, skb); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_inc(q, skb); qdisc_qstats_cpu_qlen_inc(q); } else { qdisc_qstats_backlog_inc(q, skb); q->q.qlen++; } if (lock) spin_unlock(lock); } static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) { spinlock_t *lock = NULL; if (q->flags & TCQ_F_NOLOCK) { lock = qdisc_lock(q); spin_lock(lock); } while (skb) { struct sk_buff *next = skb->next; __skb_queue_tail(&q->gso_skb, skb); /* it's still part of the queue */ if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_requeues_inc(q); qdisc_qstats_cpu_backlog_inc(q, skb); qdisc_qstats_cpu_qlen_inc(q); } else { q->qstats.requeues++; qdisc_qstats_backlog_inc(q, skb); q->q.qlen++; } skb = next; } if (lock) { spin_unlock(lock); set_bit(__QDISC_STATE_MISSED, &q->state); } else { __netif_schedule(q); } } static void try_bulk_dequeue_skb(struct Qdisc *q, struct sk_buff *skb, const struct netdev_queue *txq, int *packets) { int bytelimit = qdisc_avail_bulklimit(txq) - skb->len; while (bytelimit > 0) { struct sk_buff *nskb = q->dequeue(q); if (!nskb) break; bytelimit -= nskb->len; /* covers GSO len */ skb->next = nskb; skb = nskb; (*packets)++; /* GSO counts as one pkt */ } skb_mark_not_on_list(skb); } /* This variant of try_bulk_dequeue_skb() makes sure * all skbs in the chain are for the same txq */ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, struct sk_buff *skb, int *packets) { int mapping = skb_get_queue_mapping(skb); struct sk_buff *nskb; int cnt = 0; do { nskb = q->dequeue(q); if (!nskb) break; if (unlikely(skb_get_queue_mapping(nskb) != mapping)) { qdisc_enqueue_skb_bad_txq(q, nskb); break; } skb->next = nskb; skb = nskb; } while (++cnt < 8); (*packets) += cnt; skb_mark_not_on_list(skb); } /* Note that dequeue_skb can possibly return a SKB list (via skb->next). * A requeued skb (via q->gso_skb) can also be a SKB list. */ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, int *packets) { const struct netdev_queue *txq = q->dev_queue; struct sk_buff *skb = NULL; *packets = 1; if (unlikely(!skb_queue_empty(&q->gso_skb))) { spinlock_t *lock = NULL; if (q->flags & TCQ_F_NOLOCK) { lock = qdisc_lock(q); spin_lock(lock); } skb = skb_peek(&q->gso_skb); /* skb may be null if another cpu pulls gso_skb off in between * empty check and lock. */ if (!skb) { if (lock) spin_unlock(lock); goto validate; } /* skb in gso_skb were already validated */ *validate = false; if (xfrm_offload(skb)) *validate = true; /* check the reason of requeuing without tx lock first */ txq = skb_get_tx_queue(txq->dev, skb); if (!netif_xmit_frozen_or_stopped(txq)) { skb = __skb_dequeue(&q->gso_skb); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_dec(q, skb); qdisc_qstats_cpu_qlen_dec(q); } else { qdisc_qstats_backlog_dec(q, skb); q->q.qlen--; } } else { skb = NULL; qdisc_maybe_clear_missed(q, txq); } if (lock) spin_unlock(lock); goto trace; } validate: *validate = true; if ((q->flags & TCQ_F_ONETXQUEUE) && netif_xmit_frozen_or_stopped(txq)) { qdisc_maybe_clear_missed(q, txq); return skb; } skb = qdisc_dequeue_skb_bad_txq(q); if (unlikely(skb)) { if (skb == SKB_XOFF_MAGIC) return NULL; goto bulk; } skb = q->dequeue(q); if (skb) { bulk: if (qdisc_may_bulk(q)) try_bulk_dequeue_skb(q, skb, txq, packets); else try_bulk_dequeue_skb_slow(q, skb, packets); } trace: trace_qdisc_dequeue(q, txq, *packets, skb); return skb; } /* * Transmit possibly several skbs, and handle the return status as * required. Owning qdisc running bit guarantees that only one CPU * can execute this function. * * Returns to the caller: * false - hardware queue frozen backoff * true - feel free to send more pkts */ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq, spinlock_t *root_lock, bool validate) { int ret = NETDEV_TX_BUSY; bool again = false; /* And release qdisc */ if (root_lock) spin_unlock(root_lock); /* Note that we validate skb (GSO, checksum, ...) outside of locks */ if (validate) skb = validate_xmit_skb_list(skb, dev, &again); #ifdef CONFIG_XFRM_OFFLOAD if (unlikely(again)) { if (root_lock) spin_lock(root_lock); dev_requeue_skb(skb, q); return false; } #endif if (likely(skb)) { HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); else qdisc_maybe_clear_missed(q, txq); HARD_TX_UNLOCK(dev, txq); } else { if (root_lock) spin_lock(root_lock); return true; } if (root_lock) spin_lock(root_lock); if (!dev_xmit_complete(ret)) { /* Driver returned NETDEV_TX_BUSY - requeue skb */ if (unlikely(ret != NETDEV_TX_BUSY)) net_warn_ratelimited("BUG %s code %d qlen %d\n", dev->name, ret, q->q.qlen); dev_requeue_skb(skb, q); return false; } return true; } /* * NOTE: Called under qdisc_lock(q) with locally disabled BH. * * running seqcount guarantees only one CPU can process * this qdisc at a time. qdisc_lock(q) serializes queue accesses for * this queue. * * netif_tx_lock serializes accesses to device driver. * * qdisc_lock(q) and netif_tx_lock are mutually exclusive, * if one is grabbed, another must be free. * * Note, that this procedure can be called by a watchdog timer * * Returns to the caller: * 0 - queue is empty or throttled. * >0 - queue is not empty. * */ static inline bool qdisc_restart(struct Qdisc *q, int *packets) { spinlock_t *root_lock = NULL; struct netdev_queue *txq; struct net_device *dev; struct sk_buff *skb; bool validate; /* Dequeue packet */ skb = dequeue_skb(q, &validate, packets); if (unlikely(!skb)) return false; if (!(q->flags & TCQ_F_NOLOCK)) root_lock = qdisc_lock(q); dev = qdisc_dev(q); txq = skb_get_tx_queue(dev, skb); return sch_direct_xmit(skb, q, dev, txq, root_lock, validate); } void __qdisc_run(struct Qdisc *q) { int quota = READ_ONCE(dev_tx_weight); int packets; while (qdisc_restart(q, &packets)) { quota -= packets; if (quota <= 0) { if (q->flags & TCQ_F_NOLOCK) set_bit(__QDISC_STATE_MISSED, &q->state); else __netif_schedule(q); break; } } } unsigned long dev_trans_start(struct net_device *dev) { unsigned long res = READ_ONCE(netdev_get_tx_queue(dev, 0)->trans_start); unsigned long val; unsigned int i; for (i = 1; i < dev->num_tx_queues; i++) { val = READ_ONCE(netdev_get_tx_queue(dev, i)->trans_start); if (val && time_after(val, res)) res = val; } return res; } EXPORT_SYMBOL(dev_trans_start); static void netif_freeze_queues(struct net_device *dev) { unsigned int i; int cpu; cpu = smp_processor_id(); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); /* We are the only thread of execution doing a * freeze, but we have to grab the _xmit_lock in * order to synchronize with threads which are in * the ->hard_start_xmit() handler and already * checked the frozen bit. */ __netif_tx_lock(txq, cpu); set_bit(__QUEUE_STATE_FROZEN, &txq->state); __netif_tx_unlock(txq); } } void netif_tx_lock(struct net_device *dev) { spin_lock(&dev->tx_global_lock); netif_freeze_queues(dev); } EXPORT_SYMBOL(netif_tx_lock); static void netif_unfreeze_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); /* No need to grab the _xmit_lock here. If the * queue is not stopped for another reason, we * force a schedule. */ clear_bit(__QUEUE_STATE_FROZEN, &txq->state); netif_schedule_queue(txq); } } void netif_tx_unlock(struct net_device *dev) { netif_unfreeze_queues(dev); spin_unlock(&dev->tx_global_lock); } EXPORT_SYMBOL(netif_tx_unlock); static void dev_watchdog(struct timer_list *t) { struct net_device *dev = from_timer(dev, t, watchdog_timer); bool release = true; spin_lock(&dev->tx_global_lock); if (!qdisc_tx_is_noop(dev)) { if (netif_device_present(dev) && netif_running(dev) && netif_carrier_ok(dev)) { int some_queue_timedout = 0; unsigned int i; unsigned long trans_start; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq; txq = netdev_get_tx_queue(dev, i); trans_start = READ_ONCE(txq->trans_start); if (netif_xmit_stopped(txq) && time_after(jiffies, (trans_start + dev->watchdog_timeo))) { some_queue_timedout = 1; atomic_long_inc(&txq->trans_timeout); break; } } if (unlikely(some_queue_timedout)) { trace_net_dev_xmit_timeout(dev, i); WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n", dev->name, netdev_drivername(dev), i); netif_freeze_queues(dev); dev->netdev_ops->ndo_tx_timeout(dev, i); netif_unfreeze_queues(dev); } if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + dev->watchdog_timeo))) release = false; } } spin_unlock(&dev->tx_global_lock); if (release) netdev_put(dev, &dev->watchdog_dev_tracker); } void __netdev_watchdog_up(struct net_device *dev) { if (dev->netdev_ops->ndo_tx_timeout) { if (dev->watchdog_timeo <= 0) dev->watchdog_timeo = 5*HZ; if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + dev->watchdog_timeo))) netdev_hold(dev, &dev->watchdog_dev_tracker, GFP_ATOMIC); } } EXPORT_SYMBOL_GPL(__netdev_watchdog_up); static void dev_watchdog_up(struct net_device *dev) { __netdev_watchdog_up(dev); } static void dev_watchdog_down(struct net_device *dev) { netif_tx_lock_bh(dev); if (del_timer(&dev->watchdog_timer)) netdev_put(dev, &dev->watchdog_dev_tracker); netif_tx_unlock_bh(dev); } /** * netif_carrier_on - set carrier * @dev: network device * * Device has detected acquisition of carrier. */ void netif_carrier_on(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) { if (dev->reg_state == NETREG_UNINITIALIZED) return; atomic_inc(&dev->carrier_up_count); linkwatch_fire_event(dev); if (netif_running(dev)) __netdev_watchdog_up(dev); } } EXPORT_SYMBOL(netif_carrier_on); /** * netif_carrier_off - clear carrier * @dev: network device * * Device has detected loss of carrier. */ void netif_carrier_off(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) { if (dev->reg_state == NETREG_UNINITIALIZED) return; atomic_inc(&dev->carrier_down_count); linkwatch_fire_event(dev); } } EXPORT_SYMBOL(netif_carrier_off); /** * netif_carrier_event - report carrier state event * @dev: network device * * Device has detected a carrier event but the carrier state wasn't changed. * Use in drivers when querying carrier state asynchronously, to avoid missing * events (link flaps) if link recovers before it's queried. */ void netif_carrier_event(struct net_device *dev) { if (dev->reg_state == NETREG_UNINITIALIZED) return; atomic_inc(&dev->carrier_up_count); atomic_inc(&dev->carrier_down_count); linkwatch_fire_event(dev); } EXPORT_SYMBOL_GPL(netif_carrier_event); /* "NOOP" scheduler: the best scheduler, recommended for all interfaces under all circumstances. It is difficult to invent anything faster or cheaper. */ static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, struct sk_buff **to_free) { __qdisc_drop(skb, to_free); return NET_XMIT_CN; } static struct sk_buff *noop_dequeue(struct Qdisc *qdisc) { return NULL; } struct Qdisc_ops noop_qdisc_ops __read_mostly = { .id = "noop", .priv_size = 0, .enqueue = noop_enqueue, .dequeue = noop_dequeue, .peek = noop_dequeue, .owner = THIS_MODULE, }; static struct netdev_queue noop_netdev_queue = { RCU_POINTER_INITIALIZER(qdisc, &noop_qdisc), .qdisc_sleeping = &noop_qdisc, }; struct Qdisc noop_qdisc = { .enqueue = noop_enqueue, .dequeue = noop_dequeue, .flags = TCQ_F_BUILTIN, .ops = &noop_qdisc_ops, .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), .dev_queue = &noop_netdev_queue, .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), .gso_skb = { .next = (struct sk_buff *)&noop_qdisc.gso_skb, .prev = (struct sk_buff *)&noop_qdisc.gso_skb, .qlen = 0, .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.gso_skb.lock), }, .skb_bad_txq = { .next = (struct sk_buff *)&noop_qdisc.skb_bad_txq, .prev = (struct sk_buff *)&noop_qdisc.skb_bad_txq, .qlen = 0, .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.skb_bad_txq.lock), }, }; EXPORT_SYMBOL(noop_qdisc); static int noqueue_init(struct Qdisc *qdisc, struct nlattr *opt, struct netlink_ext_ack *extack) { /* register_qdisc() assigns a default of noop_enqueue if unset, * but __dev_queue_xmit() treats noqueue only as such * if this is NULL - so clear it here. */ qdisc->enqueue = NULL; return 0; } struct Qdisc_ops noqueue_qdisc_ops __read_mostly = { .id = "noqueue", .priv_size = 0, .init = noqueue_init, .enqueue = noop_enqueue, .dequeue = noop_dequeue, .peek = noop_dequeue, .owner = THIS_MODULE, }; static const u8 prio2band[TC_PRIO_MAX + 1] = { 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 }; /* 3-band FIFO queue: old style, but should be a bit faster than generic prio+fifo combination. */ #define PFIFO_FAST_BANDS 3 /* * Private data for a pfifo_fast scheduler containing: * - rings for priority bands */ struct pfifo_fast_priv { struct skb_array q[PFIFO_FAST_BANDS]; }; static inline struct skb_array *band2list(struct pfifo_fast_priv *priv, int band) { return &priv->q[band]; } static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, struct sk_buff **to_free) { int band = prio2band[skb->priority & TC_PRIO_MAX]; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct skb_array *q = band2list(priv, band); unsigned int pkt_len = qdisc_pkt_len(skb); int err; err = skb_array_produce(q, skb); if (unlikely(err)) { if (qdisc_is_percpu_stats(qdisc)) return qdisc_drop_cpu(skb, qdisc, to_free); else return qdisc_drop(skb, qdisc, to_free); } qdisc_update_stats_at_enqueue(qdisc, pkt_len); return NET_XMIT_SUCCESS; } static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct sk_buff *skb = NULL; bool need_retry = true; int band; retry: for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) { struct skb_array *q = band2list(priv, band); if (__skb_array_empty(q)) continue; skb = __skb_array_consume(q); } if (likely(skb)) { qdisc_update_stats_at_dequeue(qdisc, skb); } else if (need_retry && READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY) { /* Delay clearing the STATE_MISSED here to reduce * the overhead of the second spin_trylock() in * qdisc_run_begin() and __netif_schedule() calling * in qdisc_run_end(). */ clear_bit(__QDISC_STATE_MISSED, &qdisc->state); clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); /* Make sure dequeuing happens after clearing * STATE_MISSED. */ smp_mb__after_atomic(); need_retry = false; goto retry; } return skb; } static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct sk_buff *skb = NULL; int band; for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) { struct skb_array *q = band2list(priv, band); skb = __skb_array_peek(q); } return skb; } static void pfifo_fast_reset(struct Qdisc *qdisc) { int i, band; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); for (band = 0; band < PFIFO_FAST_BANDS; band++) { struct skb_array *q = band2list(priv, band); struct sk_buff *skb; /* NULL ring is possible if destroy path is due to a failed * skb_array_init() in pfifo_fast_init() case. */ if (!q->ring.queue) continue; while ((skb = __skb_array_consume(q)) != NULL) kfree_skb(skb); } if (qdisc_is_percpu_stats(qdisc)) { for_each_possible_cpu(i) { struct gnet_stats_queue *q; q = per_cpu_ptr(qdisc->cpu_qstats, i); q->backlog = 0; q->qlen = 0; } } } static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb) { struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS }; memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1); if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; return skb->len; nla_put_failure: return -1; } static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt, struct netlink_ext_ack *extack) { unsigned int qlen = qdisc_dev(qdisc)->tx_queue_len; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); int prio; /* guard against zero length rings */ if (!qlen) return -EINVAL; for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { struct skb_array *q = band2list(priv, prio); int err; err = skb_array_init(q, qlen, GFP_KERNEL); if (err) return -ENOMEM; } /* Can by-pass the queue discipline */ qdisc->flags |= TCQ_F_CAN_BYPASS; return 0; } static void pfifo_fast_destroy(struct Qdisc *sch) { struct pfifo_fast_priv *priv = qdisc_priv(sch); int prio; for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { struct skb_array *q = band2list(priv, prio); /* NULL ring is possible if destroy path is due to a failed * skb_array_init() in pfifo_fast_init() case. */ if (!q->ring.queue) continue; /* Destroy ring but no need to kfree_skb because a call to * pfifo_fast_reset() has already done that work. */ ptr_ring_cleanup(&q->ring, NULL); } } static int pfifo_fast_change_tx_queue_len(struct Qdisc *sch, unsigned int new_len) { struct pfifo_fast_priv *priv = qdisc_priv(sch); struct skb_array *bands[PFIFO_FAST_BANDS]; int prio; for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { struct skb_array *q = band2list(priv, prio); bands[prio] = q; } return skb_array_resize_multiple(bands, PFIFO_FAST_BANDS, new_len, GFP_KERNEL); } struct Qdisc_ops pfifo_fast_ops __read_mostly = { .id = "pfifo_fast", .priv_size = sizeof(struct pfifo_fast_priv), .enqueue = pfifo_fast_enqueue, .dequeue = pfifo_fast_dequeue, .peek = pfifo_fast_peek, .init = pfifo_fast_init, .destroy = pfifo_fast_destroy, .reset = pfifo_fast_reset, .dump = pfifo_fast_dump, .change_tx_queue_len = pfifo_fast_change_tx_queue_len, .owner = THIS_MODULE, .static_flags = TCQ_F_NOLOCK | TCQ_F_CPUSTATS, }; EXPORT_SYMBOL(pfifo_fast_ops); static struct lock_class_key qdisc_tx_busylock; struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack) { struct Qdisc *sch; unsigned int size = sizeof(*sch) + ops->priv_size; int err = -ENOBUFS; struct net_device *dev; if (!dev_queue) { NL_SET_ERR_MSG(extack, "No device queue given"); err = -EINVAL; goto errout; } dev = dev_queue->dev; sch = kzalloc_node(size, GFP_KERNEL, netdev_queue_numa_node_read(dev_queue)); if (!sch) goto errout; __skb_queue_head_init(&sch->gso_skb); __skb_queue_head_init(&sch->skb_bad_txq); gnet_stats_basic_sync_init(&sch->bstats); spin_lock_init(&sch->q.lock); if (ops->static_flags & TCQ_F_CPUSTATS) { sch->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); if (!sch->cpu_bstats) goto errout1; sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue); if (!sch->cpu_qstats) { free_percpu(sch->cpu_bstats); goto errout1; } } spin_lock_init(&sch->busylock); lockdep_set_class(&sch->busylock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); /* seqlock has the same scope of busylock, for NOLOCK qdisc */ spin_lock_init(&sch->seqlock); lockdep_set_class(&sch->seqlock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); sch->ops = ops; sch->flags = ops->static_flags; sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; netdev_hold(dev, &sch->dev_tracker, GFP_KERNEL); refcount_set(&sch->refcnt, 1); return sch; errout1: kfree(sch); errout: return ERR_PTR(err); } struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, unsigned int parentid, struct netlink_ext_ack *extack) { struct Qdisc *sch; if (!try_module_get(ops->owner)) { NL_SET_ERR_MSG(extack, "Failed to increase module reference counter"); return NULL; } sch = qdisc_alloc(dev_queue, ops, extack); if (IS_ERR(sch)) { module_put(ops->owner); return NULL; } sch->parent = parentid; if (!ops->init || ops->init(sch, NULL, extack) == 0) { trace_qdisc_create(ops, dev_queue->dev, parentid); return sch; } qdisc_put(sch); return NULL; } EXPORT_SYMBOL(qdisc_create_dflt); /* Under qdisc_lock(qdisc) and BH! */ void qdisc_reset(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; trace_qdisc_reset(qdisc); if (ops->reset) ops->reset(qdisc); __skb_queue_purge(&qdisc->gso_skb); __skb_queue_purge(&qdisc->skb_bad_txq); qdisc->q.qlen = 0; qdisc->qstats.backlog = 0; } EXPORT_SYMBOL(qdisc_reset); void qdisc_free(struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); free_percpu(qdisc->cpu_qstats); } kfree(qdisc); } static void qdisc_free_cb(struct rcu_head *head) { struct Qdisc *q = container_of(head, struct Qdisc, rcu); qdisc_free(q); } static void qdisc_destroy(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; #ifdef CONFIG_NET_SCHED qdisc_hash_del(qdisc); qdisc_put_stab(rtnl_dereference(qdisc->stab)); #endif gen_kill_estimator(&qdisc->rate_est); qdisc_reset(qdisc); if (ops->destroy) ops->destroy(qdisc); module_put(ops->owner); netdev_put(qdisc_dev(qdisc), &qdisc->dev_tracker); trace_qdisc_destroy(qdisc); call_rcu(&qdisc->rcu, qdisc_free_cb); } void qdisc_put(struct Qdisc *qdisc) { if (!qdisc) return; if (qdisc->flags & TCQ_F_BUILTIN || !refcount_dec_and_test(&qdisc->refcnt)) return; qdisc_destroy(qdisc); } EXPORT_SYMBOL(qdisc_put); /* Version of qdisc_put() that is called with rtnl mutex unlocked. * Intended to be used as optimization, this function only takes rtnl lock if * qdisc reference counter reached zero. */ void qdisc_put_unlocked(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN || !refcount_dec_and_rtnl_lock(&qdisc->refcnt)) return; qdisc_destroy(qdisc); rtnl_unlock(); } EXPORT_SYMBOL(qdisc_put_unlocked); /* Attach toplevel qdisc to device queue. */ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc) { struct Qdisc *oqdisc = dev_queue->qdisc_sleeping; spinlock_t *root_lock; root_lock = qdisc_lock(oqdisc); spin_lock_bh(root_lock); /* ... and graft new one */ if (qdisc == NULL) qdisc = &noop_qdisc; dev_queue->qdisc_sleeping = qdisc; rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc); spin_unlock_bh(root_lock); return oqdisc; } EXPORT_SYMBOL(dev_graft_qdisc); static void shutdown_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc_default) { struct Qdisc *qdisc = dev_queue->qdisc_sleeping; struct Qdisc *qdisc_default = _qdisc_default; if (qdisc) { rcu_assign_pointer(dev_queue->qdisc, qdisc_default); dev_queue->qdisc_sleeping = qdisc_default; qdisc_put(qdisc); } } static void attach_one_default_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_unused) { struct Qdisc *qdisc; const struct Qdisc_ops *ops = default_qdisc_ops; if (dev->priv_flags & IFF_NO_QUEUE) ops = &noqueue_qdisc_ops; else if(dev->type == ARPHRD_CAN) ops = &pfifo_fast_ops; qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT, NULL); if (!qdisc) return; if (!netif_is_multiqueue(dev)) qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; dev_queue->qdisc_sleeping = qdisc; } static void attach_default_qdiscs(struct net_device *dev) { struct netdev_queue *txq; struct Qdisc *qdisc; txq = netdev_get_tx_queue(dev, 0); if (!netif_is_multiqueue(dev) || dev->priv_flags & IFF_NO_QUEUE) { netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); qdisc = txq->qdisc_sleeping; rcu_assign_pointer(dev->qdisc, qdisc); qdisc_refcount_inc(qdisc); } else { qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT, NULL); if (qdisc) { rcu_assign_pointer(dev->qdisc, qdisc); qdisc->ops->attach(qdisc); } } qdisc = rtnl_dereference(dev->qdisc); /* Detect default qdisc setup/init failed and fallback to "noqueue" */ if (qdisc == &noop_qdisc) { netdev_warn(dev, "default qdisc (%s) fail, fallback to %s\n", default_qdisc_ops->id, noqueue_qdisc_ops.id); netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); dev->priv_flags |= IFF_NO_QUEUE; netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); qdisc = txq->qdisc_sleeping; rcu_assign_pointer(dev->qdisc, qdisc); qdisc_refcount_inc(qdisc); dev->priv_flags ^= IFF_NO_QUEUE; } #ifdef CONFIG_NET_SCHED if (qdisc != &noop_qdisc) qdisc_hash_add(qdisc, false); #endif } static void transition_one_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_need_watchdog) { struct Qdisc *new_qdisc = dev_queue->qdisc_sleeping; int *need_watchdog_p = _need_watchdog; if (!(new_qdisc->flags & TCQ_F_BUILTIN)) clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state); rcu_assign_pointer(dev_queue->qdisc, new_qdisc); if (need_watchdog_p) { WRITE_ONCE(dev_queue->trans_start, 0); *need_watchdog_p = 1; } } void dev_activate(struct net_device *dev) { int need_watchdog; /* No queueing discipline is attached to device; * create default one for devices, which need queueing * and noqueue_qdisc for virtual interfaces */ if (rtnl_dereference(dev->qdisc) == &noop_qdisc) attach_default_qdiscs(dev); if (!netif_carrier_ok(dev)) /* Delay activation until next carrier-on event */ return; need_watchdog = 0; netdev_for_each_tx_queue(dev, transition_one_qdisc, &need_watchdog); if (dev_ingress_queue(dev)) transition_one_qdisc(dev, dev_ingress_queue(dev), NULL); if (need_watchdog) { netif_trans_update(dev); dev_watchdog_up(dev); } } EXPORT_SYMBOL(dev_activate); static void qdisc_deactivate(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return; set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); } static void dev_deactivate_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc_default) { struct Qdisc *qdisc_default = _qdisc_default; struct Qdisc *qdisc; qdisc = rtnl_dereference(dev_queue->qdisc); if (qdisc) { qdisc_deactivate(qdisc); rcu_assign_pointer(dev_queue->qdisc, qdisc_default); } } static void dev_reset_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_unused) { struct Qdisc *qdisc; bool nolock; qdisc = dev_queue->qdisc_sleeping; if (!qdisc) return; nolock = qdisc->flags & TCQ_F_NOLOCK; if (nolock) spin_lock_bh(&qdisc->seqlock); spin_lock_bh(qdisc_lock(qdisc)); qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); if (nolock) { clear_bit(__QDISC_STATE_MISSED, &qdisc->state); clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); spin_unlock_bh(&qdisc->seqlock); } } static bool some_qdisc_is_busy(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *dev_queue; spinlock_t *root_lock; struct Qdisc *q; int val; dev_queue = netdev_get_tx_queue(dev, i); q = dev_queue->qdisc_sleeping; root_lock = qdisc_lock(q); spin_lock_bh(root_lock); val = (qdisc_is_running(q) || test_bit(__QDISC_STATE_SCHED, &q->state)); spin_unlock_bh(root_lock); if (val) return true; } return false; } /** * dev_deactivate_many - deactivate transmissions on several devices * @head: list of devices to deactivate * * This function returns only when all outstanding transmissions * have completed, unless all devices are in dismantle phase. */ void dev_deactivate_many(struct list_head *head) { struct net_device *dev; list_for_each_entry(dev, head, close_list) { netdev_for_each_tx_queue(dev, dev_deactivate_queue, &noop_qdisc); if (dev_ingress_queue(dev)) dev_deactivate_queue(dev, dev_ingress_queue(dev), &noop_qdisc); dev_watchdog_down(dev); } /* Wait for outstanding qdisc-less dev_queue_xmit calls or * outstanding qdisc enqueuing calls. * This is avoided if all devices are in dismantle phase : * Caller will call synchronize_net() for us */ synchronize_net(); list_for_each_entry(dev, head, close_list) { netdev_for_each_tx_queue(dev, dev_reset_queue, NULL); if (dev_ingress_queue(dev)) dev_reset_queue(dev, dev_ingress_queue(dev), NULL); } /* Wait for outstanding qdisc_run calls. */ list_for_each_entry(dev, head, close_list) { while (some_qdisc_is_busy(dev)) { /* wait_event() would avoid this sleep-loop but would * require expensive checks in the fast paths of packet * processing which isn't worth it. */ schedule_timeout_uninterruptible(1); } } } void dev_deactivate(struct net_device *dev) { LIST_HEAD(single); list_add(&dev->close_list, &single); dev_deactivate_many(&single); list_del(&single); } EXPORT_SYMBOL(dev_deactivate); static int qdisc_change_tx_queue_len(struct net_device *dev, struct netdev_queue *dev_queue) { struct Qdisc *qdisc = dev_queue->qdisc_sleeping; const struct Qdisc_ops *ops = qdisc->ops; if (ops->change_tx_queue_len) return ops->change_tx_queue_len(qdisc, dev->tx_queue_len); return 0; } void dev_qdisc_change_real_num_tx(struct net_device *dev, unsigned int new_real_tx) { struct Qdisc *qdisc = rtnl_dereference(dev->qdisc); if (qdisc->ops->change_real_num_tx) qdisc->ops->change_real_num_tx(qdisc, new_real_tx); } void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx) { #ifdef CONFIG_NET_SCHED struct net_device *dev = qdisc_dev(sch); struct Qdisc *qdisc; unsigned int i; for (i = new_real_tx; i < dev->real_num_tx_queues; i++) { qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; /* Only update the default qdiscs we created, * qdiscs with handles are always hashed. */ if (qdisc != &noop_qdisc && !qdisc->handle) qdisc_hash_del(qdisc); } for (i = dev->real_num_tx_queues; i < new_real_tx; i++) { qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; if (qdisc != &noop_qdisc && !qdisc->handle) qdisc_hash_add(qdisc, false); } #endif } EXPORT_SYMBOL(mq_change_real_num_tx); int dev_qdisc_change_tx_queue_len(struct net_device *dev) { bool up = dev->flags & IFF_UP; unsigned int i; int ret = 0; if (up) dev_deactivate(dev); for (i = 0; i < dev->num_tx_queues; i++) { ret = qdisc_change_tx_queue_len(dev, &dev->_tx[i]); /* TODO: revert changes on a partial failure */ if (ret) break; } if (up) dev_activate(dev); return ret; } static void dev_init_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc) { struct Qdisc *qdisc = _qdisc; rcu_assign_pointer(dev_queue->qdisc, qdisc); dev_queue->qdisc_sleeping = qdisc; } void dev_init_scheduler(struct net_device *dev) { rcu_assign_pointer(dev->qdisc, &noop_qdisc); netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); timer_setup(&dev->watchdog_timer, dev_watchdog, 0); } void dev_shutdown(struct net_device *dev) { netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); qdisc_put(rtnl_dereference(dev->qdisc)); rcu_assign_pointer(dev->qdisc, &noop_qdisc); WARN_ON(timer_pending(&dev->watchdog_timer)); } /** * psched_ratecfg_precompute__() - Pre-compute values for reciprocal division * @rate: Rate to compute reciprocal division values of * @mult: Multiplier for reciprocal division * @shift: Shift for reciprocal division * * The multiplier and shift for reciprocal division by rate are stored * in mult and shift. * * The deal here is to replace a divide by a reciprocal one * in fast path (a reciprocal divide is a multiply and a shift) * * Normal formula would be : * time_in_ns = (NSEC_PER_SEC * len) / rate_bps * * We compute mult/shift to use instead : * time_in_ns = (len * mult) >> shift; * * We try to get the highest possible mult value for accuracy, * but have to make sure no overflows will ever happen. * * reciprocal_value() is not used here it doesn't handle 64-bit values. */ static void psched_ratecfg_precompute__(u64 rate, u32 *mult, u8 *shift) { u64 factor = NSEC_PER_SEC; *mult = 1; *shift = 0; if (rate <= 0) return; for (;;) { *mult = div64_u64(factor, rate); if (*mult & (1U << 31) || factor & (1ULL << 63)) break; factor <<= 1; (*shift)++; } } void psched_ratecfg_precompute(struct psched_ratecfg *r, const struct tc_ratespec *conf, u64 rate64) { memset(r, 0, sizeof(*r)); r->overhead = conf->overhead; r->mpu = conf->mpu; r->rate_bytes_ps = max_t(u64, conf->rate, rate64); r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK); psched_ratecfg_precompute__(r->rate_bytes_ps, &r->mult, &r->shift); } EXPORT_SYMBOL(psched_ratecfg_precompute); void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64) { r->rate_pkts_ps = pktrate64; psched_ratecfg_precompute__(r->rate_pkts_ps, &r->mult, &r->shift); } EXPORT_SYMBOL(psched_ppscfg_precompute); void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, struct tcf_proto *tp_head) { /* Protected with chain0->filter_chain_lock. * Can't access chain directly because tp_head can be NULL. */ struct mini_Qdisc *miniq_old = rcu_dereference_protected(*miniqp->p_miniq, 1); struct mini_Qdisc *miniq; if (!tp_head) { RCU_INIT_POINTER(*miniqp->p_miniq, NULL); } else { miniq = miniq_old != &miniqp->miniq1 ? &miniqp->miniq1 : &miniqp->miniq2; /* We need to make sure that readers won't see the miniq * we are about to modify. So ensure that at least one RCU * grace period has elapsed since the miniq was made * inactive. */ if (IS_ENABLED(CONFIG_PREEMPT_RT)) cond_synchronize_rcu(miniq->rcu_state); else if (!poll_state_synchronize_rcu(miniq->rcu_state)) synchronize_rcu_expedited(); miniq->filter_list = tp_head; rcu_assign_pointer(*miniqp->p_miniq, miniq); } if (miniq_old) /* This is counterpart of the rcu sync above. We need to * block potential new user of miniq_old until all readers * are not seeing it. */ miniq_old->rcu_state = start_poll_synchronize_rcu(); } EXPORT_SYMBOL(mini_qdisc_pair_swap); void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, struct tcf_block *block) { miniqp->miniq1.block = block; miniqp->miniq2.block = block; } EXPORT_SYMBOL(mini_qdisc_pair_block_init); void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, struct mini_Qdisc __rcu **p_miniq) { miniqp->miniq1.cpu_bstats = qdisc->cpu_bstats; miniqp->miniq1.cpu_qstats = qdisc->cpu_qstats; miniqp->miniq2.cpu_bstats = qdisc->cpu_bstats; miniqp->miniq2.cpu_qstats = qdisc->cpu_qstats; miniqp->miniq1.rcu_state = get_state_synchronize_rcu(); miniqp->miniq2.rcu_state = miniqp->miniq1.rcu_state; miniqp->p_miniq = p_miniq; } EXPORT_SYMBOL(mini_qdisc_pair_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 | /* tnum: tracked (or tristate) numbers * * A tnum tracks knowledge about the bits of a value. Each bit can be either * known (0 or 1), or unknown (x). Arithmetic operations on tnums will * propagate the unknown bits such that the tnum result represents all the * possible results for possible values of the operands. */ #ifndef _LINUX_TNUM_H #define _LINUX_TNUM_H #include <linux/types.h> struct tnum { u64 value; u64 mask; }; /* Constructors */ /* Represent a known constant as a tnum. */ struct tnum tnum_const(u64 value); /* A completely unknown value */ extern const struct tnum tnum_unknown; /* An unknown value that is a superset of @min <= value <= @max. * * Could include values outside the range of [@min, @max]. * For example tnum_range(0, 2) is represented by {0, 1, 2, *3*}, * rather than the intended set of {0, 1, 2}. */ struct tnum tnum_range(u64 min, u64 max); /* Arithmetic and logical ops */ /* Shift a tnum left (by a fixed shift) */ struct tnum tnum_lshift(struct tnum a, u8 shift); /* Shift (rsh) a tnum right (by a fixed shift) */ struct tnum tnum_rshift(struct tnum a, u8 shift); /* Shift (arsh) a tnum right (by a fixed min_shift) */ struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness); /* Add two tnums, return @a + @b */ struct tnum tnum_add(struct tnum a, struct tnum b); /* Subtract two tnums, return @a - @b */ struct tnum tnum_sub(struct tnum a, struct tnum b); /* Bitwise-AND, return @a & @b */ struct tnum tnum_and(struct tnum a, struct tnum b); /* Bitwise-OR, return @a | @b */ struct tnum tnum_or(struct tnum a, struct tnum b); /* Bitwise-XOR, return @a ^ @b */ struct tnum tnum_xor(struct tnum a, struct tnum b); /* Multiply two tnums, return @a * @b */ struct tnum tnum_mul(struct tnum a, struct tnum b); /* Return a tnum representing numbers satisfying both @a and @b */ struct tnum tnum_intersect(struct tnum a, struct tnum b); /* Return @a with all but the lowest @size bytes cleared */ struct tnum tnum_cast(struct tnum a, u8 size); /* Returns true if @a is a known constant */ static inline bool tnum_is_const(struct tnum a) { return !a.mask; } /* Returns true if @a == tnum_const(@b) */ static inline bool tnum_equals_const(struct tnum a, u64 b) { return tnum_is_const(a) && a.value == b; } /* Returns true if @a is completely unknown */ static inline bool tnum_is_unknown(struct tnum a) { return !~a.mask; } /* Returns true if @a is known to be a multiple of @size. * @size must be a power of two. */ bool tnum_is_aligned(struct tnum a, u64 size); /* Returns true if @b represents a subset of @a. * * Note that using tnum_range() as @a requires extra cautions as tnum_in() may * return true unexpectedly due to tnum limited ability to represent tight * range, e.g. * * tnum_in(tnum_range(0, 2), tnum_const(3)) == true * * As a rule of thumb, if @a is explicitly coded rather than coming from * reg->var_off, it should be in form of tnum_const(), tnum_range(0, 2**n - 1), * or tnum_range(2**n, 2**(n+1) - 1). */ bool tnum_in(struct tnum a, struct tnum b); /* Formatting functions. These have snprintf-like semantics: they will write * up to @size bytes (including the terminating NUL byte), and return the number * of bytes (excluding the terminating NUL) which would have been written had * sufficient space been available. (Thus tnum_sbin always returns 64.) */ /* Format a tnum as a pair of hex numbers (value; mask) */ int tnum_strn(char *str, size_t size, struct tnum a); /* Format a tnum as tristate binary expansion */ int tnum_sbin(char *str, size_t size, struct tnum a); /* Returns the 32-bit subreg */ struct tnum tnum_subreg(struct tnum a); /* Returns the tnum with the lower 32-bit subreg cleared */ struct tnum tnum_clear_subreg(struct tnum a); /* Returns the tnum with the lower 32-bit subreg set to value */ struct tnum tnum_const_subreg(struct tnum a, u32 value); /* Returns true if 32-bit subreg @a is a known constant*/ static inline bool tnum_subreg_is_const(struct tnum a) { return !(tnum_subreg(a)).mask; } #endif /* _LINUX_TNUM_H */ |
| 1601 1600 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/net/sunrpc/stats.c * * procfs-based user access to generic RPC statistics. The stats files * reside in /proc/net/rpc. * * The read routines assume that the buffer passed in is just big enough. * If you implement an RPC service that has its own stats routine which * appends the generic RPC stats, make sure you don't exceed the PAGE_SIZE * limit. * * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/metrics.h> #include <linux/rcupdate.h> #include <trace/events/sunrpc.h> #include "netns.h" #define RPCDBG_FACILITY RPCDBG_MISC /* * Get RPC client stats */ static int rpc_proc_show(struct seq_file *seq, void *v) { const struct rpc_stat *statp = seq->private; const struct rpc_program *prog = statp->program; unsigned int i, j; seq_printf(seq, "net %u %u %u %u\n", statp->netcnt, statp->netudpcnt, statp->nettcpcnt, statp->nettcpconn); seq_printf(seq, "rpc %u %u %u\n", statp->rpccnt, statp->rpcretrans, statp->rpcauthrefresh); for (i = 0; i < prog->nrvers; i++) { const struct rpc_version *vers = prog->version[i]; if (!vers) continue; seq_printf(seq, "proc%u %u", vers->number, vers->nrprocs); for (j = 0; j < vers->nrprocs; j++) seq_printf(seq, " %u", vers->counts[j]); seq_putc(seq, '\n'); } return 0; } static int rpc_proc_open(struct inode *inode, struct file *file) { return single_open(file, rpc_proc_show, pde_data(inode)); } static const struct proc_ops rpc_proc_ops = { .proc_open = rpc_proc_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = single_release, }; /* * Get RPC server stats */ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) { const struct svc_program *prog = statp->program; const struct svc_version *vers; unsigned int i, j; seq_printf(seq, "net %u %u %u %u\n", statp->netcnt, statp->netudpcnt, statp->nettcpcnt, statp->nettcpconn); seq_printf(seq, "rpc %u %u %u %u %u\n", statp->rpccnt, statp->rpcbadfmt+statp->rpcbadauth+statp->rpcbadclnt, statp->rpcbadfmt, statp->rpcbadauth, statp->rpcbadclnt); for (i = 0; i < prog->pg_nvers; i++) { vers = prog->pg_vers[i]; if (!vers) continue; seq_printf(seq, "proc%d %u", i, vers->vs_nproc); for (j = 0; j < vers->vs_nproc; j++) seq_printf(seq, " %u", vers->vs_count[j]); seq_putc(seq, '\n'); } } EXPORT_SYMBOL_GPL(svc_seq_show); /** * rpc_alloc_iostats - allocate an rpc_iostats structure * @clnt: RPC program, version, and xprt * */ struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt) { struct rpc_iostats *stats; int i; stats = kcalloc(clnt->cl_maxproc, sizeof(*stats), GFP_KERNEL); if (stats) { for (i = 0; i < clnt->cl_maxproc; i++) spin_lock_init(&stats[i].om_lock); } return stats; } EXPORT_SYMBOL_GPL(rpc_alloc_iostats); /** * rpc_free_iostats - release an rpc_iostats structure * @stats: doomed rpc_iostats structure * */ void rpc_free_iostats(struct rpc_iostats *stats) { kfree(stats); } EXPORT_SYMBOL_GPL(rpc_free_iostats); /** * rpc_count_iostats_metrics - tally up per-task stats * @task: completed rpc_task * @op_metrics: stat structure for OP that will accumulate stats from @task */ void rpc_count_iostats_metrics(const struct rpc_task *task, struct rpc_iostats *op_metrics) { struct rpc_rqst *req = task->tk_rqstp; ktime_t backlog, execute, now; if (!op_metrics || !req) return; now = ktime_get(); spin_lock(&op_metrics->om_lock); op_metrics->om_ops++; /* kernel API: om_ops must never become larger than om_ntrans */ op_metrics->om_ntrans += max(req->rq_ntrans, 1); op_metrics->om_timeouts += task->tk_timeouts; op_metrics->om_bytes_sent += req->rq_xmit_bytes_sent; op_metrics->om_bytes_recv += req->rq_reply_bytes_recvd; backlog = 0; if (ktime_to_ns(req->rq_xtime)) { backlog = ktime_sub(req->rq_xtime, task->tk_start); op_metrics->om_queue = ktime_add(op_metrics->om_queue, backlog); } op_metrics->om_rtt = ktime_add(op_metrics->om_rtt, req->rq_rtt); execute = ktime_sub(now, task->tk_start); op_metrics->om_execute = ktime_add(op_metrics->om_execute, execute); if (task->tk_status < 0) op_metrics->om_error_status++; spin_unlock(&op_metrics->om_lock); trace_rpc_stats_latency(req->rq_task, backlog, req->rq_rtt, execute); } EXPORT_SYMBOL_GPL(rpc_count_iostats_metrics); /** * rpc_count_iostats - tally up per-task stats * @task: completed rpc_task * @stats: array of stat structures * * Uses the statidx from @task */ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) { rpc_count_iostats_metrics(task, &stats[task->tk_msg.rpc_proc->p_statidx]); } EXPORT_SYMBOL_GPL(rpc_count_iostats); static void _print_name(struct seq_file *seq, unsigned int op, const struct rpc_procinfo *procs) { if (procs[op].p_name) seq_printf(seq, "\t%12s: ", procs[op].p_name); else if (op == 0) seq_printf(seq, "\t NULL: "); else seq_printf(seq, "\t%12u: ", op); } static void _add_rpc_iostats(struct rpc_iostats *a, struct rpc_iostats *b) { a->om_ops += b->om_ops; a->om_ntrans += b->om_ntrans; a->om_timeouts += b->om_timeouts; a->om_bytes_sent += b->om_bytes_sent; a->om_bytes_recv += b->om_bytes_recv; a->om_queue = ktime_add(a->om_queue, b->om_queue); a->om_rtt = ktime_add(a->om_rtt, b->om_rtt); a->om_execute = ktime_add(a->om_execute, b->om_execute); a->om_error_status += b->om_error_status; } static void _print_rpc_iostats(struct seq_file *seq, struct rpc_iostats *stats, int op, const struct rpc_procinfo *procs) { _print_name(seq, op, procs); seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %llu %lu\n", stats->om_ops, stats->om_ntrans, stats->om_timeouts, stats->om_bytes_sent, stats->om_bytes_recv, ktime_to_ms(stats->om_queue), ktime_to_ms(stats->om_rtt), ktime_to_ms(stats->om_execute), stats->om_error_status); } static int do_print_stats(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *seqv) { struct seq_file *seq = seqv; xprt->ops->print_stats(xprt, seq); return 0; } void rpc_clnt_show_stats(struct seq_file *seq, struct rpc_clnt *clnt) { unsigned int op, maxproc = clnt->cl_maxproc; if (!clnt->cl_metrics) return; seq_printf(seq, "\tRPC iostats version: %s ", RPC_IOSTATS_VERS); seq_printf(seq, "p/v: %u/%u (%s)\n", clnt->cl_prog, clnt->cl_vers, clnt->cl_program->name); rpc_clnt_iterate_for_each_xprt(clnt, do_print_stats, seq); seq_printf(seq, "\tper-op statistics\n"); for (op = 0; op < maxproc; op++) { struct rpc_iostats stats = {}; struct rpc_clnt *next = clnt; do { _add_rpc_iostats(&stats, &next->cl_metrics[op]); if (next == next->cl_parent) break; next = next->cl_parent; } while (next); _print_rpc_iostats(seq, &stats, op, clnt->cl_procinfo); } } EXPORT_SYMBOL_GPL(rpc_clnt_show_stats); /* * Register/unregister RPC proc files */ static inline struct proc_dir_entry * do_register(struct net *net, const char *name, void *data, const struct proc_ops *proc_ops) { struct sunrpc_net *sn; dprintk("RPC: registering /proc/net/rpc/%s\n", name); sn = net_generic(net, sunrpc_net_id); return proc_create_data(name, 0, sn->proc_net_rpc, proc_ops, data); } struct proc_dir_entry * rpc_proc_register(struct net *net, struct rpc_stat *statp) { return do_register(net, statp->program->name, statp, &rpc_proc_ops); } EXPORT_SYMBOL_GPL(rpc_proc_register); void rpc_proc_unregister(struct net *net, const char *name) { struct sunrpc_net *sn; sn = net_generic(net, sunrpc_net_id); remove_proc_entry(name, sn->proc_net_rpc); } EXPORT_SYMBOL_GPL(rpc_proc_unregister); struct proc_dir_entry * svc_proc_register(struct net *net, struct svc_stat *statp, const struct proc_ops *proc_ops) { return do_register(net, statp->program->pg_name, statp, proc_ops); } EXPORT_SYMBOL_GPL(svc_proc_register); void svc_proc_unregister(struct net *net, const char *name) { struct sunrpc_net *sn; sn = net_generic(net, sunrpc_net_id); remove_proc_entry(name, sn->proc_net_rpc); } EXPORT_SYMBOL_GPL(svc_proc_unregister); int rpc_proc_init(struct net *net) { struct sunrpc_net *sn; dprintk("RPC: registering /proc/net/rpc\n"); sn = net_generic(net, sunrpc_net_id); sn->proc_net_rpc = proc_mkdir("rpc", net->proc_net); if (sn->proc_net_rpc == NULL) return -ENOMEM; return 0; } void rpc_proc_exit(struct net *net) { dprintk("RPC: unregistering /proc/net/rpc\n"); remove_proc_entry("rpc", net->proc_net); } |
| 11 11 10 9 8 11 7 7 2 6 5 3 6 5 4 3 3 3 9 33 27 8 9 9 10 30 30 8 30 30 30 30 30 8 8 8 29 30 30 30 29 29 29 29 28 30 2 2 2 2 1 1 1 1 2 2 2 3 2 1 3 4 2 2 1 4 6 6 5 4 4 1 4 1 3 1 6 33 1 34 1 33 34 33 33 33 6 27 33 33 26 10 29 29 10 1 1 1 1 1 4 4 24 1 24 24 27 27 26 2 25 24 24 2 27 6 3 2 5 4 5 6 21 21 21 19 18 17 17 17 16 16 16 1 6 6 5 2 1 37 8 27 5 3 5 1 3 2 2 2 5 2 3 3 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ #include <linux/bpf.h> #include <linux/btf_ids.h> #include <linux/filter.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/net.h> #include <linux/workqueue.h> #include <linux/skmsg.h> #include <linux/list.h> #include <linux/jhash.h> #include <linux/sock_diag.h> #include <net/udp.h> struct bpf_stab { struct bpf_map map; struct sock **sks; struct sk_psock_progs progs; raw_spinlock_t lock; }; #define SOCK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, struct bpf_prog *old, u32 which); static struct sk_psock_progs *sock_map_progs(struct bpf_map *map); static struct bpf_map *sock_map_alloc(union bpf_attr *attr) { struct bpf_stab *stab; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); if (attr->max_entries == 0 || attr->key_size != 4 || (attr->value_size != sizeof(u32) && attr->value_size != sizeof(u64)) || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); stab = bpf_map_area_alloc(sizeof(*stab), NUMA_NO_NODE); if (!stab) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&stab->map, attr); raw_spin_lock_init(&stab->lock); stab->sks = bpf_map_area_alloc((u64) stab->map.max_entries * sizeof(struct sock *), stab->map.numa_node); if (!stab->sks) { bpf_map_area_free(stab); return ERR_PTR(-ENOMEM); } return &stab->map; } int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) { u32 ufd = attr->target_fd; struct bpf_map *map; struct fd f; int ret; if (attr->attach_flags || attr->replace_bpf_fd) return -EINVAL; f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); ret = sock_map_prog_update(map, prog, NULL, attr->attach_type); fdput(f); return ret; } int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { u32 ufd = attr->target_fd; struct bpf_prog *prog; struct bpf_map *map; struct fd f; int ret; if (attr->attach_flags || attr->replace_bpf_fd) return -EINVAL; f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); prog = bpf_prog_get(attr->attach_bpf_fd); if (IS_ERR(prog)) { ret = PTR_ERR(prog); goto put_map; } if (prog->type != ptype) { ret = -EINVAL; goto put_prog; } ret = sock_map_prog_update(map, NULL, prog, attr->attach_type); put_prog: bpf_prog_put(prog); put_map: fdput(f); return ret; } static void sock_map_sk_acquire(struct sock *sk) __acquires(&sk->sk_lock.slock) { lock_sock(sk); preempt_disable(); rcu_read_lock(); } static void sock_map_sk_release(struct sock *sk) __releases(&sk->sk_lock.slock) { rcu_read_unlock(); preempt_enable(); release_sock(sk); } static void sock_map_add_link(struct sk_psock *psock, struct sk_psock_link *link, struct bpf_map *map, void *link_raw) { link->link_raw = link_raw; link->map = map; spin_lock_bh(&psock->link_lock); list_add_tail(&link->list, &psock->link); spin_unlock_bh(&psock->link_lock); } static void sock_map_del_link(struct sock *sk, struct sk_psock *psock, void *link_raw) { bool strp_stop = false, verdict_stop = false; struct sk_psock_link *link, *tmp; spin_lock_bh(&psock->link_lock); list_for_each_entry_safe(link, tmp, &psock->link, list) { if (link->link_raw == link_raw) { struct bpf_map *map = link->map; struct bpf_stab *stab = container_of(map, struct bpf_stab, map); if (psock->saved_data_ready && stab->progs.stream_parser) strp_stop = true; if (psock->saved_data_ready && stab->progs.stream_verdict) verdict_stop = true; if (psock->saved_data_ready && stab->progs.skb_verdict) verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); } } spin_unlock_bh(&psock->link_lock); if (strp_stop || verdict_stop) { write_lock_bh(&sk->sk_callback_lock); if (strp_stop) sk_psock_stop_strp(sk, psock); if (verdict_stop) sk_psock_stop_verdict(sk, psock); if (psock->psock_update_sk_prot) psock->psock_update_sk_prot(sk, psock, false); write_unlock_bh(&sk->sk_callback_lock); } } static void sock_map_unref(struct sock *sk, void *link_raw) { struct sk_psock *psock = sk_psock(sk); if (likely(psock)) { sock_map_del_link(sk, psock, link_raw); sk_psock_put(sk, psock); } } static int sock_map_init_proto(struct sock *sk, struct sk_psock *psock) { if (!sk->sk_prot->psock_update_sk_prot) return -EINVAL; psock->psock_update_sk_prot = sk->sk_prot->psock_update_sk_prot; return sk->sk_prot->psock_update_sk_prot(sk, psock, false); } static struct sk_psock *sock_map_psock_get_checked(struct sock *sk) { struct sk_psock *psock; rcu_read_lock(); psock = sk_psock(sk); if (psock) { if (sk->sk_prot->close != sock_map_close) { psock = ERR_PTR(-EBUSY); goto out; } if (!refcount_inc_not_zero(&psock->refcnt)) psock = ERR_PTR(-EBUSY); } out: rcu_read_unlock(); return psock; } static int sock_map_link(struct bpf_map *map, struct sock *sk) { struct sk_psock_progs *progs = sock_map_progs(map); struct bpf_prog *stream_verdict = NULL; struct bpf_prog *stream_parser = NULL; struct bpf_prog *skb_verdict = NULL; struct bpf_prog *msg_parser = NULL; struct sk_psock *psock; int ret; stream_verdict = READ_ONCE(progs->stream_verdict); if (stream_verdict) { stream_verdict = bpf_prog_inc_not_zero(stream_verdict); if (IS_ERR(stream_verdict)) return PTR_ERR(stream_verdict); } stream_parser = READ_ONCE(progs->stream_parser); if (stream_parser) { stream_parser = bpf_prog_inc_not_zero(stream_parser); if (IS_ERR(stream_parser)) { ret = PTR_ERR(stream_parser); goto out_put_stream_verdict; } } msg_parser = READ_ONCE(progs->msg_parser); if (msg_parser) { msg_parser = bpf_prog_inc_not_zero(msg_parser); if (IS_ERR(msg_parser)) { ret = PTR_ERR(msg_parser); goto out_put_stream_parser; } } skb_verdict = READ_ONCE(progs->skb_verdict); if (skb_verdict) { skb_verdict = bpf_prog_inc_not_zero(skb_verdict); if (IS_ERR(skb_verdict)) { ret = PTR_ERR(skb_verdict); goto out_put_msg_parser; } } psock = sock_map_psock_get_checked(sk); if (IS_ERR(psock)) { ret = PTR_ERR(psock); goto out_progs; } if (psock) { if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) || (stream_parser && READ_ONCE(psock->progs.stream_parser)) || (skb_verdict && READ_ONCE(psock->progs.skb_verdict)) || (skb_verdict && READ_ONCE(psock->progs.stream_verdict)) || (stream_verdict && READ_ONCE(psock->progs.skb_verdict)) || (stream_verdict && READ_ONCE(psock->progs.stream_verdict))) { sk_psock_put(sk, psock); ret = -EBUSY; goto out_progs; } } else { psock = sk_psock_init(sk, map->numa_node); if (IS_ERR(psock)) { ret = PTR_ERR(psock); goto out_progs; } } if (msg_parser) psock_set_prog(&psock->progs.msg_parser, msg_parser); if (stream_parser) psock_set_prog(&psock->progs.stream_parser, stream_parser); if (stream_verdict) psock_set_prog(&psock->progs.stream_verdict, stream_verdict); if (skb_verdict) psock_set_prog(&psock->progs.skb_verdict, skb_verdict); /* msg_* and stream_* programs references tracked in psock after this * point. Reference dec and cleanup will occur through psock destructor */ ret = sock_map_init_proto(sk, psock); if (ret < 0) { sk_psock_put(sk, psock); goto out; } write_lock_bh(&sk->sk_callback_lock); if (stream_parser && stream_verdict && !psock->saved_data_ready) { ret = sk_psock_init_strp(sk, psock); if (ret) { write_unlock_bh(&sk->sk_callback_lock); sk_psock_put(sk, psock); goto out; } sk_psock_start_strp(sk, psock); } else if (!stream_parser && stream_verdict && !psock->saved_data_ready) { sk_psock_start_verdict(sk,psock); } else if (!stream_verdict && skb_verdict && !psock->saved_data_ready) { sk_psock_start_verdict(sk, psock); } write_unlock_bh(&sk->sk_callback_lock); return 0; out_progs: if (skb_verdict) bpf_prog_put(skb_verdict); out_put_msg_parser: if (msg_parser) bpf_prog_put(msg_parser); out_put_stream_parser: if (stream_parser) bpf_prog_put(stream_parser); out_put_stream_verdict: if (stream_verdict) bpf_prog_put(stream_verdict); out: return ret; } static void sock_map_free(struct bpf_map *map) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); int i; /* After the sync no updates or deletes will be in-flight so it * is safe to walk map and remove entries without risking a race * in EEXIST update case. */ synchronize_rcu(); for (i = 0; i < stab->map.max_entries; i++) { struct sock **psk = &stab->sks[i]; struct sock *sk; sk = xchg(psk, NULL); if (sk) { lock_sock(sk); rcu_read_lock(); sock_map_unref(sk, psk); rcu_read_unlock(); release_sock(sk); } } /* wait for psock readers accessing its map link */ synchronize_rcu(); bpf_map_area_free(stab->sks); bpf_map_area_free(stab); } static void sock_map_release_progs(struct bpf_map *map) { psock_progs_drop(&container_of(map, struct bpf_stab, map)->progs); } static struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); WARN_ON_ONCE(!rcu_read_lock_held()); if (unlikely(key >= map->max_entries)) return NULL; return READ_ONCE(stab->sks[key]); } static void *sock_map_lookup(struct bpf_map *map, void *key) { struct sock *sk; sk = __sock_map_lookup_elem(map, *(u32 *)key); if (!sk) return NULL; if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; return sk; } static void *sock_map_lookup_sys(struct bpf_map *map, void *key) { struct sock *sk; if (map->value_size != sizeof(u64)) return ERR_PTR(-ENOSPC); sk = __sock_map_lookup_elem(map, *(u32 *)key); if (!sk) return ERR_PTR(-ENOENT); __sock_gen_cookie(sk); return &sk->sk_cookie; } static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock **psk) { struct sock *sk; int err = 0; raw_spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) sk = xchg(psk, NULL); if (likely(sk)) sock_map_unref(sk, psk); else err = -EINVAL; raw_spin_unlock_bh(&stab->lock); return err; } static void sock_map_delete_from_link(struct bpf_map *map, struct sock *sk, void *link_raw) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); __sock_map_delete(stab, sk, link_raw); } static int sock_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); u32 i = *(u32 *)key; struct sock **psk; if (unlikely(i >= map->max_entries)) return -EINVAL; psk = &stab->sks[i]; return __sock_map_delete(stab, NULL, psk); } static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); u32 i = key ? *(u32 *)key : U32_MAX; u32 *key_next = next; if (i == stab->map.max_entries - 1) return -ENOENT; if (i >= stab->map.max_entries) *key_next = 0; else *key_next = i + 1; return 0; } static int sock_map_update_common(struct bpf_map *map, u32 idx, struct sock *sk, u64 flags) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); struct sk_psock_link *link; struct sk_psock *psock; struct sock *osk; int ret; WARN_ON_ONCE(!rcu_read_lock_held()); if (unlikely(flags > BPF_EXIST)) return -EINVAL; if (unlikely(idx >= map->max_entries)) return -E2BIG; link = sk_psock_init_link(); if (!link) return -ENOMEM; ret = sock_map_link(map, sk); if (ret < 0) goto out_free; psock = sk_psock(sk); WARN_ON_ONCE(!psock); raw_spin_lock_bh(&stab->lock); osk = stab->sks[idx]; if (osk && flags == BPF_NOEXIST) { ret = -EEXIST; goto out_unlock; } else if (!osk && flags == BPF_EXIST) { ret = -ENOENT; goto out_unlock; } sock_map_add_link(psock, link, map, &stab->sks[idx]); stab->sks[idx] = sk; if (osk) sock_map_unref(osk, &stab->sks[idx]); raw_spin_unlock_bh(&stab->lock); return 0; out_unlock: raw_spin_unlock_bh(&stab->lock); if (psock) sk_psock_put(sk, psock); out_free: sk_psock_free_link(link); return ret; } static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops) { return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB || ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB || ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB; } static bool sock_map_redirect_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) return sk->sk_state != TCP_LISTEN; else return sk->sk_state == TCP_ESTABLISHED; } static bool sock_map_sk_is_suitable(const struct sock *sk) { return !!sk->sk_prot->psock_update_sk_prot; } static bool sock_map_sk_state_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); return true; } static int sock_hash_update_common(struct bpf_map *map, void *key, struct sock *sk, u64 flags); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags) { struct socket *sock; struct sock *sk; int ret; u64 ufd; if (map->value_size == sizeof(u64)) ufd = *(u64 *)value; else ufd = *(u32 *)value; if (ufd > S32_MAX) return -EINVAL; sock = sockfd_lookup(ufd, &ret); if (!sock) return ret; sk = sock->sk; if (!sk) { ret = -EINVAL; goto out; } if (!sock_map_sk_is_suitable(sk)) { ret = -EOPNOTSUPP; goto out; } sock_map_sk_acquire(sk); if (!sock_map_sk_state_allowed(sk)) ret = -EOPNOTSUPP; else if (map->map_type == BPF_MAP_TYPE_SOCKMAP) ret = sock_map_update_common(map, *(u32 *)key, sk, flags); else ret = sock_hash_update_common(map, key, sk, flags); sock_map_sk_release(sk); out: sockfd_put(sock); return ret; } static int sock_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { struct sock *sk = (struct sock *)value; int ret; if (unlikely(!sk || !sk_fullsock(sk))) return -EINVAL; if (!sock_map_sk_is_suitable(sk)) return -EOPNOTSUPP; local_bh_disable(); bh_lock_sock(sk); if (!sock_map_sk_state_allowed(sk)) ret = -EOPNOTSUPP; else if (map->map_type == BPF_MAP_TYPE_SOCKMAP) ret = sock_map_update_common(map, *(u32 *)key, sk, flags); else ret = sock_hash_update_common(map, key, sk, flags); bh_unlock_sock(sk); local_bh_enable(); return ret; } BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, sops, struct bpf_map *, map, void *, key, u64, flags) { WARN_ON_ONCE(!rcu_read_lock_held()); if (likely(sock_map_sk_is_suitable(sops->sk) && sock_map_op_okay(sops))) return sock_map_update_common(map, *(u32 *)key, sops->sk, flags); return -EOPNOTSUPP; } const struct bpf_func_proto bpf_sock_map_update_proto = { .func = bpf_sock_map_update, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, struct bpf_map *, map, u32, key, u64, flags) { struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; sk = __sock_map_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS; } const struct bpf_func_proto bpf_sk_redirect_map_proto = { .func = bpf_sk_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, struct bpf_map *, map, u32, key, u64, flags) { struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; sk = __sock_map_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; msg->flags = flags; msg->sk_redir = sk; return SK_PASS; } const struct bpf_func_proto bpf_msg_redirect_map_proto = { .func = bpf_msg_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; struct sock_map_seq_info { struct bpf_map *map; struct sock *sk; u32 index; }; struct bpf_iter__sockmap { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct bpf_map *, map); __bpf_md_ptr(void *, key); __bpf_md_ptr(struct sock *, sk); }; DEFINE_BPF_ITER_FUNC(sockmap, struct bpf_iter_meta *meta, struct bpf_map *map, void *key, struct sock *sk) static void *sock_map_seq_lookup_elem(struct sock_map_seq_info *info) { if (unlikely(info->index >= info->map->max_entries)) return NULL; info->sk = __sock_map_lookup_elem(info->map, info->index); /* can't return sk directly, since that might be NULL */ return info; } static void *sock_map_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { struct sock_map_seq_info *info = seq->private; if (*pos == 0) ++*pos; /* pairs with sock_map_seq_stop */ rcu_read_lock(); return sock_map_seq_lookup_elem(info); } static void *sock_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) __must_hold(rcu) { struct sock_map_seq_info *info = seq->private; ++*pos; ++info->index; return sock_map_seq_lookup_elem(info); } static int sock_map_seq_show(struct seq_file *seq, void *v) __must_hold(rcu) { struct sock_map_seq_info *info = seq->private; struct bpf_iter__sockmap ctx = {}; struct bpf_iter_meta meta; struct bpf_prog *prog; meta.seq = seq; prog = bpf_iter_get_info(&meta, !v); if (!prog) return 0; ctx.meta = &meta; ctx.map = info->map; if (v) { ctx.key = &info->index; ctx.sk = info->sk; } return bpf_iter_run_prog(prog, &ctx); } static void sock_map_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { if (!v) (void)sock_map_seq_show(seq, NULL); /* pairs with sock_map_seq_start */ rcu_read_unlock(); } static const struct seq_operations sock_map_seq_ops = { .start = sock_map_seq_start, .next = sock_map_seq_next, .stop = sock_map_seq_stop, .show = sock_map_seq_show, }; static int sock_map_init_seq_private(void *priv_data, struct bpf_iter_aux_info *aux) { struct sock_map_seq_info *info = priv_data; bpf_map_inc_with_uref(aux->map); info->map = aux->map; return 0; } static void sock_map_fini_seq_private(void *priv_data) { struct sock_map_seq_info *info = priv_data; bpf_map_put_with_uref(info->map); } static const struct bpf_iter_seq_info sock_map_iter_seq_info = { .seq_ops = &sock_map_seq_ops, .init_seq_private = sock_map_init_seq_private, .fini_seq_private = sock_map_fini_seq_private, .seq_priv_size = sizeof(struct sock_map_seq_info), }; BTF_ID_LIST_SINGLE(sock_map_btf_ids, struct, bpf_stab) const struct bpf_map_ops sock_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = sock_map_alloc, .map_free = sock_map_free, .map_get_next_key = sock_map_get_next_key, .map_lookup_elem_sys_only = sock_map_lookup_sys, .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_map_delete_elem, .map_lookup_elem = sock_map_lookup, .map_release_uref = sock_map_release_progs, .map_check_btf = map_check_no_btf, .map_btf_id = &sock_map_btf_ids[0], .iter_seq_info = &sock_map_iter_seq_info, }; struct bpf_shtab_elem { struct rcu_head rcu; u32 hash; struct sock *sk; struct hlist_node node; u8 key[]; }; struct bpf_shtab_bucket { struct hlist_head head; raw_spinlock_t lock; }; struct bpf_shtab { struct bpf_map map; struct bpf_shtab_bucket *buckets; u32 buckets_num; u32 elem_size; struct sk_psock_progs progs; atomic_t count; }; static inline u32 sock_hash_bucket_hash(const void *key, u32 len) { return jhash(key, len, 0); } static struct bpf_shtab_bucket *sock_hash_select_bucket(struct bpf_shtab *htab, u32 hash) { return &htab->buckets[hash & (htab->buckets_num - 1)]; } static struct bpf_shtab_elem * sock_hash_lookup_elem_raw(struct hlist_head *head, u32 hash, void *key, u32 key_size) { struct bpf_shtab_elem *elem; hlist_for_each_entry_rcu(elem, head, node) { if (elem->hash == hash && !memcmp(&elem->key, key, key_size)) return elem; } return NULL; } static struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); u32 key_size = map->key_size, hash; struct bpf_shtab_bucket *bucket; struct bpf_shtab_elem *elem; WARN_ON_ONCE(!rcu_read_lock_held()); hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size); return elem ? elem->sk : NULL; } static void sock_hash_free_elem(struct bpf_shtab *htab, struct bpf_shtab_elem *elem) { atomic_dec(&htab->count); kfree_rcu(elem, rcu); } static void sock_hash_delete_from_link(struct bpf_map *map, struct sock *sk, void *link_raw) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); struct bpf_shtab_elem *elem_probe, *elem = link_raw; struct bpf_shtab_bucket *bucket; WARN_ON_ONCE(!rcu_read_lock_held()); bucket = sock_hash_select_bucket(htab, elem->hash); /* elem may be deleted in parallel from the map, but access here * is okay since it's going away only after RCU grace period. * However, we need to check whether it's still present. */ raw_spin_lock_bh(&bucket->lock); elem_probe = sock_hash_lookup_elem_raw(&bucket->head, elem->hash, elem->key, map->key_size); if (elem_probe && elem_probe == elem) { hlist_del_rcu(&elem->node); sock_map_unref(elem->sk, elem); sock_hash_free_elem(htab, elem); } raw_spin_unlock_bh(&bucket->lock); } static int sock_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); u32 hash, key_size = map->key_size; struct bpf_shtab_bucket *bucket; struct bpf_shtab_elem *elem; int ret = -ENOENT; hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); raw_spin_lock_bh(&bucket->lock); elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size); if (elem) { hlist_del_rcu(&elem->node); sock_map_unref(elem->sk, elem); sock_hash_free_elem(htab, elem); ret = 0; } raw_spin_unlock_bh(&bucket->lock); return ret; } static struct bpf_shtab_elem *sock_hash_alloc_elem(struct bpf_shtab *htab, void *key, u32 key_size, u32 hash, struct sock *sk, struct bpf_shtab_elem *old) { struct bpf_shtab_elem *new; if (atomic_inc_return(&htab->count) > htab->map.max_entries) { if (!old) { atomic_dec(&htab->count); return ERR_PTR(-E2BIG); } } new = bpf_map_kmalloc_node(&htab->map, htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, htab->map.numa_node); if (!new) { atomic_dec(&htab->count); return ERR_PTR(-ENOMEM); } memcpy(new->key, key, key_size); new->sk = sk; new->hash = hash; return new; } static int sock_hash_update_common(struct bpf_map *map, void *key, struct sock *sk, u64 flags) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); u32 key_size = map->key_size, hash; struct bpf_shtab_elem *elem, *elem_new; struct bpf_shtab_bucket *bucket; struct sk_psock_link *link; struct sk_psock *psock; int ret; WARN_ON_ONCE(!rcu_read_lock_held()); if (unlikely(flags > BPF_EXIST)) return -EINVAL; link = sk_psock_init_link(); if (!link) return -ENOMEM; ret = sock_map_link(map, sk); if (ret < 0) goto out_free; psock = sk_psock(sk); WARN_ON_ONCE(!psock); hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); raw_spin_lock_bh(&bucket->lock); elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size); if (elem && flags == BPF_NOEXIST) { ret = -EEXIST; goto out_unlock; } else if (!elem && flags == BPF_EXIST) { ret = -ENOENT; goto out_unlock; } elem_new = sock_hash_alloc_elem(htab, key, key_size, hash, sk, elem); if (IS_ERR(elem_new)) { ret = PTR_ERR(elem_new); goto out_unlock; } sock_map_add_link(psock, link, map, elem_new); /* Add new element to the head of the list, so that * concurrent search will find it before old elem. */ hlist_add_head_rcu(&elem_new->node, &bucket->head); if (elem) { hlist_del_rcu(&elem->node); sock_map_unref(elem->sk, elem); sock_hash_free_elem(htab, elem); } raw_spin_unlock_bh(&bucket->lock); return 0; out_unlock: raw_spin_unlock_bh(&bucket->lock); sk_psock_put(sk, psock); out_free: sk_psock_free_link(link); return ret; } static int sock_hash_get_next_key(struct bpf_map *map, void *key, void *key_next) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); struct bpf_shtab_elem *elem, *elem_next; u32 hash, key_size = map->key_size; struct hlist_head *head; int i = 0; if (!key) goto find_first_elem; hash = sock_hash_bucket_hash(key, key_size); head = &sock_hash_select_bucket(htab, hash)->head; elem = sock_hash_lookup_elem_raw(head, hash, key, key_size); if (!elem) goto find_first_elem; elem_next = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&elem->node)), struct bpf_shtab_elem, node); if (elem_next) { memcpy(key_next, elem_next->key, key_size); return 0; } i = hash & (htab->buckets_num - 1); i++; find_first_elem: for (; i < htab->buckets_num; i++) { head = &sock_hash_select_bucket(htab, i)->head; elem_next = hlist_entry_safe(rcu_dereference(hlist_first_rcu(head)), struct bpf_shtab_elem, node); if (elem_next) { memcpy(key_next, elem_next->key, key_size); return 0; } } return -ENOENT; } static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) { struct bpf_shtab *htab; int i, err; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); if (attr->max_entries == 0 || attr->key_size == 0 || (attr->value_size != sizeof(u32) && attr->value_size != sizeof(u64)) || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); if (attr->key_size > MAX_BPF_STACK) return ERR_PTR(-E2BIG); htab = bpf_map_area_alloc(sizeof(*htab), NUMA_NO_NODE); if (!htab) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&htab->map, attr); htab->buckets_num = roundup_pow_of_two(htab->map.max_entries); htab->elem_size = sizeof(struct bpf_shtab_elem) + round_up(htab->map.key_size, 8); if (htab->buckets_num == 0 || htab->buckets_num > U32_MAX / sizeof(struct bpf_shtab_bucket)) { err = -EINVAL; goto free_htab; } htab->buckets = bpf_map_area_alloc(htab->buckets_num * sizeof(struct bpf_shtab_bucket), htab->map.numa_node); if (!htab->buckets) { err = -ENOMEM; goto free_htab; } for (i = 0; i < htab->buckets_num; i++) { INIT_HLIST_HEAD(&htab->buckets[i].head); raw_spin_lock_init(&htab->buckets[i].lock); } return &htab->map; free_htab: bpf_map_area_free(htab); return ERR_PTR(err); } static void sock_hash_free(struct bpf_map *map) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); struct bpf_shtab_bucket *bucket; struct hlist_head unlink_list; struct bpf_shtab_elem *elem; struct hlist_node *node; int i; /* After the sync no updates or deletes will be in-flight so it * is safe to walk map and remove entries without risking a race * in EEXIST update case. */ synchronize_rcu(); for (i = 0; i < htab->buckets_num; i++) { bucket = sock_hash_select_bucket(htab, i); /* We are racing with sock_hash_delete_from_link to * enter the spin-lock critical section. Every socket on * the list is still linked to sockhash. Since link * exists, psock exists and holds a ref to socket. That * lets us to grab a socket ref too. */ raw_spin_lock_bh(&bucket->lock); hlist_for_each_entry(elem, &bucket->head, node) sock_hold(elem->sk); hlist_move_list(&bucket->head, &unlink_list); raw_spin_unlock_bh(&bucket->lock); /* Process removed entries out of atomic context to * block for socket lock before deleting the psock's * link to sockhash. */ hlist_for_each_entry_safe(elem, node, &unlink_list, node) { hlist_del(&elem->node); lock_sock(elem->sk); rcu_read_lock(); sock_map_unref(elem->sk, elem); rcu_read_unlock(); release_sock(elem->sk); sock_put(elem->sk); sock_hash_free_elem(htab, elem); } } /* wait for psock readers accessing its map link */ synchronize_rcu(); bpf_map_area_free(htab->buckets); bpf_map_area_free(htab); } static void *sock_hash_lookup_sys(struct bpf_map *map, void *key) { struct sock *sk; if (map->value_size != sizeof(u64)) return ERR_PTR(-ENOSPC); sk = __sock_hash_lookup_elem(map, key); if (!sk) return ERR_PTR(-ENOENT); __sock_gen_cookie(sk); return &sk->sk_cookie; } static void *sock_hash_lookup(struct bpf_map *map, void *key) { struct sock *sk; sk = __sock_hash_lookup_elem(map, key); if (!sk) return NULL; if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; return sk; } static void sock_hash_release_progs(struct bpf_map *map) { psock_progs_drop(&container_of(map, struct bpf_shtab, map)->progs); } BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, sops, struct bpf_map *, map, void *, key, u64, flags) { WARN_ON_ONCE(!rcu_read_lock_held()); if (likely(sock_map_sk_is_suitable(sops->sk) && sock_map_op_okay(sops))) return sock_hash_update_common(map, key, sops->sk, flags); return -EOPNOTSUPP; } const struct bpf_func_proto bpf_sock_hash_update_proto = { .func = bpf_sock_hash_update, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, struct bpf_map *, map, void *, key, u64, flags) { struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; sk = __sock_hash_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS; } const struct bpf_func_proto bpf_sk_redirect_hash_proto = { .func = bpf_sk_redirect_hash, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, struct bpf_map *, map, void *, key, u64, flags) { struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; sk = __sock_hash_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; msg->flags = flags; msg->sk_redir = sk; return SK_PASS; } const struct bpf_func_proto bpf_msg_redirect_hash_proto = { .func = bpf_msg_redirect_hash, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; struct sock_hash_seq_info { struct bpf_map *map; struct bpf_shtab *htab; u32 bucket_id; }; static void *sock_hash_seq_find_next(struct sock_hash_seq_info *info, struct bpf_shtab_elem *prev_elem) { const struct bpf_shtab *htab = info->htab; struct bpf_shtab_bucket *bucket; struct bpf_shtab_elem *elem; struct hlist_node *node; /* try to find next elem in the same bucket */ if (prev_elem) { node = rcu_dereference(hlist_next_rcu(&prev_elem->node)); elem = hlist_entry_safe(node, struct bpf_shtab_elem, node); if (elem) return elem; /* no more elements, continue in the next bucket */ info->bucket_id++; } for (; info->bucket_id < htab->buckets_num; info->bucket_id++) { bucket = &htab->buckets[info->bucket_id]; node = rcu_dereference(hlist_first_rcu(&bucket->head)); elem = hlist_entry_safe(node, struct bpf_shtab_elem, node); if (elem) return elem; } return NULL; } static void *sock_hash_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { struct sock_hash_seq_info *info = seq->private; if (*pos == 0) ++*pos; /* pairs with sock_hash_seq_stop */ rcu_read_lock(); return sock_hash_seq_find_next(info, NULL); } static void *sock_hash_seq_next(struct seq_file *seq, void *v, loff_t *pos) __must_hold(rcu) { struct sock_hash_seq_info *info = seq->private; ++*pos; return sock_hash_seq_find_next(info, v); } static int sock_hash_seq_show(struct seq_file *seq, void *v) __must_hold(rcu) { struct sock_hash_seq_info *info = seq->private; struct bpf_iter__sockmap ctx = {}; struct bpf_shtab_elem *elem = v; struct bpf_iter_meta meta; struct bpf_prog *prog; meta.seq = seq; prog = bpf_iter_get_info(&meta, !elem); if (!prog) return 0; ctx.meta = &meta; ctx.map = info->map; if (elem) { ctx.key = elem->key; ctx.sk = elem->sk; } return bpf_iter_run_prog(prog, &ctx); } static void sock_hash_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { if (!v) (void)sock_hash_seq_show(seq, NULL); /* pairs with sock_hash_seq_start */ rcu_read_unlock(); } static const struct seq_operations sock_hash_seq_ops = { .start = sock_hash_seq_start, .next = sock_hash_seq_next, .stop = sock_hash_seq_stop, .show = sock_hash_seq_show, }; static int sock_hash_init_seq_private(void *priv_data, struct bpf_iter_aux_info *aux) { struct sock_hash_seq_info *info = priv_data; bpf_map_inc_with_uref(aux->map); info->map = aux->map; info->htab = container_of(aux->map, struct bpf_shtab, map); return 0; } static void sock_hash_fini_seq_private(void *priv_data) { struct sock_hash_seq_info *info = priv_data; bpf_map_put_with_uref(info->map); } static const struct bpf_iter_seq_info sock_hash_iter_seq_info = { .seq_ops = &sock_hash_seq_ops, .init_seq_private = sock_hash_init_seq_private, .fini_seq_private = sock_hash_fini_seq_private, .seq_priv_size = sizeof(struct sock_hash_seq_info), }; BTF_ID_LIST_SINGLE(sock_hash_map_btf_ids, struct, bpf_shtab) const struct bpf_map_ops sock_hash_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = sock_hash_alloc, .map_free = sock_hash_free, .map_get_next_key = sock_hash_get_next_key, .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_hash_delete_elem, .map_lookup_elem = sock_hash_lookup, .map_lookup_elem_sys_only = sock_hash_lookup_sys, .map_release_uref = sock_hash_release_progs, .map_check_btf = map_check_no_btf, .map_btf_id = &sock_hash_map_btf_ids[0], .iter_seq_info = &sock_hash_iter_seq_info, }; static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) { switch (map->map_type) { case BPF_MAP_TYPE_SOCKMAP: return &container_of(map, struct bpf_stab, map)->progs; case BPF_MAP_TYPE_SOCKHASH: return &container_of(map, struct bpf_shtab, map)->progs; default: break; } return NULL; } static int sock_map_prog_lookup(struct bpf_map *map, struct bpf_prog ***pprog, u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); if (!progs) return -EOPNOTSUPP; switch (which) { case BPF_SK_MSG_VERDICT: *pprog = &progs->msg_parser; break; #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) case BPF_SK_SKB_STREAM_PARSER: *pprog = &progs->stream_parser; break; #endif case BPF_SK_SKB_STREAM_VERDICT: if (progs->skb_verdict) return -EBUSY; *pprog = &progs->stream_verdict; break; case BPF_SK_SKB_VERDICT: if (progs->stream_verdict) return -EBUSY; *pprog = &progs->skb_verdict; break; default: return -EOPNOTSUPP; } return 0; } static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, struct bpf_prog *old, u32 which) { struct bpf_prog **pprog; int ret; ret = sock_map_prog_lookup(map, &pprog, which); if (ret) return ret; if (old) return psock_replace_prog(pprog, prog, old); psock_set_prog(pprog, prog); return 0; } int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); u32 prog_cnt = 0, flags = 0, ufd = attr->target_fd; struct bpf_prog **pprog; struct bpf_prog *prog; struct bpf_map *map; struct fd f; u32 id = 0; int ret; if (attr->query.query_flags) return -EINVAL; f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); rcu_read_lock(); ret = sock_map_prog_lookup(map, &pprog, attr->query.attach_type); if (ret) goto end; prog = *pprog; prog_cnt = !prog ? 0 : 1; if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) goto end; /* we do not hold the refcnt, the bpf prog may be released * asynchronously and the id would be set to 0. */ id = data_race(prog->aux->id); if (id == 0) prog_cnt = 0; end: rcu_read_unlock(); if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)) || (id != 0 && copy_to_user(prog_ids, &id, sizeof(u32))) || copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) ret = -EFAULT; fdput(f); return ret; } static void sock_map_unlink(struct sock *sk, struct sk_psock_link *link) { switch (link->map->map_type) { case BPF_MAP_TYPE_SOCKMAP: return sock_map_delete_from_link(link->map, sk, link->link_raw); case BPF_MAP_TYPE_SOCKHASH: return sock_hash_delete_from_link(link->map, sk, link->link_raw); default: break; } } static void sock_map_remove_links(struct sock *sk, struct sk_psock *psock) { struct sk_psock_link *link; while ((link = sk_psock_link_pop(psock))) { sock_map_unlink(sk, link); sk_psock_free_link(link); } } void sock_map_unhash(struct sock *sk) { void (*saved_unhash)(struct sock *sk); struct sk_psock *psock; rcu_read_lock(); psock = sk_psock(sk); if (unlikely(!psock)) { rcu_read_unlock(); if (sk->sk_prot->unhash) sk->sk_prot->unhash(sk); return; } saved_unhash = psock->saved_unhash; sock_map_remove_links(sk, psock); rcu_read_unlock(); saved_unhash(sk); } EXPORT_SYMBOL_GPL(sock_map_unhash); void sock_map_destroy(struct sock *sk) { void (*saved_destroy)(struct sock *sk); struct sk_psock *psock; rcu_read_lock(); psock = sk_psock_get(sk); if (unlikely(!psock)) { rcu_read_unlock(); if (sk->sk_prot->destroy) sk->sk_prot->destroy(sk); return; } saved_destroy = psock->saved_destroy; sock_map_remove_links(sk, psock); rcu_read_unlock(); sk_psock_stop(psock); sk_psock_put(sk, psock); saved_destroy(sk); } EXPORT_SYMBOL_GPL(sock_map_destroy); void sock_map_close(struct sock *sk, long timeout) { void (*saved_close)(struct sock *sk, long timeout); struct sk_psock *psock; lock_sock(sk); rcu_read_lock(); psock = sk_psock_get(sk); if (unlikely(!psock)) { rcu_read_unlock(); release_sock(sk); return sk->sk_prot->close(sk, timeout); } saved_close = psock->saved_close; sock_map_remove_links(sk, psock); rcu_read_unlock(); sk_psock_stop(psock); release_sock(sk); cancel_work_sync(&psock->work); sk_psock_put(sk, psock); saved_close(sk, timeout); } EXPORT_SYMBOL_GPL(sock_map_close); static int sock_map_iter_attach_target(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux) { struct bpf_map *map; int err = -EINVAL; if (!linfo->map.map_fd) return -EBADF; map = bpf_map_get_with_uref(linfo->map.map_fd); if (IS_ERR(map)) return PTR_ERR(map); if (map->map_type != BPF_MAP_TYPE_SOCKMAP && map->map_type != BPF_MAP_TYPE_SOCKHASH) goto put_map; if (prog->aux->max_rdonly_access > map->key_size) { err = -EACCES; goto put_map; } aux->map = map; return 0; put_map: bpf_map_put_with_uref(map); return err; } static void sock_map_iter_detach_target(struct bpf_iter_aux_info *aux) { bpf_map_put_with_uref(aux->map); } static struct bpf_iter_reg sock_map_iter_reg = { .target = "sockmap", .attach_target = sock_map_iter_attach_target, .detach_target = sock_map_iter_detach_target, .show_fdinfo = bpf_iter_map_show_fdinfo, .fill_link_info = bpf_iter_map_fill_link_info, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__sockmap, key), PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY }, { offsetof(struct bpf_iter__sockmap, sk), PTR_TO_BTF_ID_OR_NULL }, }, }; static int __init bpf_sockmap_iter_init(void) { sock_map_iter_reg.ctx_arg_info[1].btf_id = btf_sock_ids[BTF_SOCK_TYPE_SOCK]; return bpf_iter_reg_target(&sock_map_iter_reg); } late_initcall(bpf_sockmap_iter_init); |
| 363 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef INT_BLK_MQ_TAG_H #define INT_BLK_MQ_TAG_H struct blk_mq_alloc_data; extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, int alloc_policy); extern void blk_mq_free_tags(struct blk_mq_tags *tags); extern int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags, struct sbitmap_queue *breserved_tags, unsigned int queue_depth, unsigned int reserved, int node, int alloc_policy); extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags, unsigned int *offset); extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags); extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tags, unsigned int depth, bool can_grow); extern void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set, unsigned int size); extern void blk_mq_tag_update_sched_shared_tags(struct request_queue *q); extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool); void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn, void *priv); void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv); static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue *bt, struct blk_mq_hw_ctx *hctx) { if (!hctx) return &bt->ws[0]; return sbq_wait_ptr(bt, &hctx->wait_index); } enum { BLK_MQ_NO_TAG = -1U, BLK_MQ_TAG_MIN = 1, BLK_MQ_TAG_MAX = BLK_MQ_NO_TAG - 1, }; extern void __blk_mq_tag_busy(struct blk_mq_hw_ctx *); extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *); static inline void blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) __blk_mq_tag_busy(hctx); } static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) { if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) return; __blk_mq_tag_idle(hctx); } static inline bool blk_mq_tag_is_reserved(struct blk_mq_tags *tags, unsigned int tag) { return tag < tags->nr_reserved_tags; } #endif |
| 10874 10874 10877 10877 10876 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LOCAL_LOCK_H # error "Do not include directly, include linux/local_lock.h" #endif #include <linux/percpu-defs.h> #include <linux/lockdep.h> #ifndef CONFIG_PREEMPT_RT typedef struct { #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; struct task_struct *owner; #endif } local_lock_t; #ifdef CONFIG_DEBUG_LOCK_ALLOC # define LOCAL_LOCK_DEBUG_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_CONFIG, \ .lock_type = LD_LOCK_PERCPU, \ }, \ .owner = NULL, static inline void local_lock_acquire(local_lock_t *l) { lock_map_acquire(&l->dep_map); DEBUG_LOCKS_WARN_ON(l->owner); l->owner = current; } static inline void local_lock_release(local_lock_t *l) { DEBUG_LOCKS_WARN_ON(l->owner != current); l->owner = NULL; lock_map_release(&l->dep_map); } static inline void local_lock_debug_init(local_lock_t *l) { l->owner = NULL; } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) static inline void local_lock_acquire(local_lock_t *l) { } static inline void local_lock_release(local_lock_t *l) { } static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } #define __local_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ LD_LOCK_PERCPU); \ local_lock_debug_init(lock); \ } while (0) #define __local_lock(lock) \ do { \ preempt_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irq(lock) \ do { \ local_irq_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irqsave(lock, flags) \ do { \ local_irq_save(flags); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_unlock(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ preempt_enable(); \ } while (0) #define __local_unlock_irq(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ local_irq_enable(); \ } while (0) #define __local_unlock_irqrestore(lock, flags) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ local_irq_restore(flags); \ } while (0) #else /* !CONFIG_PREEMPT_RT */ /* * On PREEMPT_RT local_lock maps to a per CPU spinlock, which protects the * critical section while staying preemptible. */ typedef spinlock_t local_lock_t; #define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname)) #define __local_lock_init(l) \ do { \ local_spin_lock_init((l)); \ } while (0) #define __local_lock(__lock) \ do { \ migrate_disable(); \ spin_lock(this_cpu_ptr((__lock))); \ } while (0) #define __local_lock_irq(lock) __local_lock(lock) #define __local_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ flags = 0; \ __local_lock(lock); \ } while (0) #define __local_unlock(__lock) \ do { \ spin_unlock(this_cpu_ptr((__lock))); \ migrate_enable(); \ } while (0) #define __local_unlock_irq(lock) __local_unlock(lock) #define __local_unlock_irqrestore(lock, flags) __local_unlock(lock) #endif /* CONFIG_PREEMPT_RT */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2004 Infinicon Corporation. All rights reserved. * Copyright (c) 2004, 2020 Intel Corporation. All rights reserved. * Copyright (c) 2004 Topspin Corporation. All rights reserved. * Copyright (c) 2004 Voltaire Corporation. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2005, 2006, 2007 Cisco Systems. All rights reserved. */ #ifndef IB_VERBS_H #define IB_VERBS_H #include <linux/ethtool.h> #include <linux/types.h> #include <linux/device.h> #include <linux/dma-mapping.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/rwsem.h> #include <linux/workqueue.h> #include <linux/irq_poll.h> #include <uapi/linux/if_ether.h> #include <net/ipv6.h> #include <net/ip.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/refcount.h> #include <linux/if_link.h> #include <linux/atomic.h> #include <linux/mmu_notifier.h> #include <linux/uaccess.h> #include <linux/cgroup_rdma.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/dim.h> #include <uapi/rdma/ib_user_verbs.h> #include <rdma/rdma_counter.h> #include <rdma/restrack.h> #include <rdma/signature.h> #include <uapi/rdma/rdma_user_ioctl.h> #include <uapi/rdma/ib_user_ioctl_verbs.h> #define IB_FW_VERSION_NAME_MAX ETHTOOL_FWVERS_LEN struct ib_umem_odp; struct ib_uqp_object; struct ib_usrq_object; struct ib_uwq_object; struct rdma_cm_id; struct ib_port; struct hw_stats_device_data; extern struct workqueue_struct *ib_wq; extern struct workqueue_struct *ib_comp_wq; extern struct workqueue_struct *ib_comp_unbound_wq; struct ib_ucq_object; __printf(3, 4) __cold void ibdev_printk(const char *level, const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_emerg(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_alert(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_crit(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_err(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_warn(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_notice(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_info(const struct ib_device *ibdev, const char *format, ...); #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define ibdev_dbg(__dev, format, args...) \ dynamic_ibdev_dbg(__dev, format, ##args) #else __printf(2, 3) __cold static inline void ibdev_dbg(const struct ib_device *ibdev, const char *format, ...) {} #endif #define ibdev_level_ratelimited(ibdev_level, ibdev, fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ if (__ratelimit(&_rs)) \ ibdev_level(ibdev, fmt, ##__VA_ARGS__); \ } while (0) #define ibdev_emerg_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_emerg, ibdev, fmt, ##__VA_ARGS__) #define ibdev_alert_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_alert, ibdev, fmt, ##__VA_ARGS__) #define ibdev_crit_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_crit, ibdev, fmt, ##__VA_ARGS__) #define ibdev_err_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_err, ibdev, fmt, ##__VA_ARGS__) #define ibdev_warn_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_warn, ibdev, fmt, ##__VA_ARGS__) #define ibdev_notice_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_notice, ibdev, fmt, ##__VA_ARGS__) #define ibdev_info_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_info, ibdev, fmt, ##__VA_ARGS__) #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define ibdev_dbg_ratelimited(ibdev, fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ if (DYNAMIC_DEBUG_BRANCH(descriptor) && __ratelimit(&_rs)) \ __dynamic_ibdev_dbg(&descriptor, ibdev, fmt, \ ##__VA_ARGS__); \ } while (0) #else __printf(2, 3) __cold static inline void ibdev_dbg_ratelimited(const struct ib_device *ibdev, const char *format, ...) {} #endif union ib_gid { u8 raw[16]; struct { __be64 subnet_prefix; __be64 interface_id; } global; }; extern union ib_gid zgid; enum ib_gid_type { IB_GID_TYPE_IB = IB_UVERBS_GID_TYPE_IB, IB_GID_TYPE_ROCE = IB_UVERBS_GID_TYPE_ROCE_V1, IB_GID_TYPE_ROCE_UDP_ENCAP = IB_UVERBS_GID_TYPE_ROCE_V2, IB_GID_TYPE_SIZE }; #define ROCE_V2_UDP_DPORT 4791 struct ib_gid_attr { struct net_device __rcu *ndev; struct ib_device *device; union ib_gid gid; enum ib_gid_type gid_type; u16 index; u32 port_num; }; enum { /* set the local administered indication */ IB_SA_WELL_KNOWN_GUID = BIT_ULL(57) | 2, }; enum rdma_transport_type { RDMA_TRANSPORT_IB, RDMA_TRANSPORT_IWARP, RDMA_TRANSPORT_USNIC, RDMA_TRANSPORT_USNIC_UDP, RDMA_TRANSPORT_UNSPECIFIED, }; enum rdma_protocol_type { RDMA_PROTOCOL_IB, RDMA_PROTOCOL_IBOE, RDMA_PROTOCOL_IWARP, RDMA_PROTOCOL_USNIC_UDP }; __attribute_const__ enum rdma_transport_type rdma_node_get_transport(unsigned int node_type); enum rdma_network_type { RDMA_NETWORK_IB, RDMA_NETWORK_ROCE_V1, RDMA_NETWORK_IPV4, RDMA_NETWORK_IPV6 }; static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type network_type) { if (network_type == RDMA_NETWORK_IPV4 || network_type == RDMA_NETWORK_IPV6) return IB_GID_TYPE_ROCE_UDP_ENCAP; else if (network_type == RDMA_NETWORK_ROCE_V1) return IB_GID_TYPE_ROCE; else return IB_GID_TYPE_IB; } static inline enum rdma_network_type rdma_gid_attr_network_type(const struct ib_gid_attr *attr) { if (attr->gid_type == IB_GID_TYPE_IB) return RDMA_NETWORK_IB; if (attr->gid_type == IB_GID_TYPE_ROCE) return RDMA_NETWORK_ROCE_V1; if (ipv6_addr_v4mapped((struct in6_addr *)&attr->gid)) return RDMA_NETWORK_IPV4; else return RDMA_NETWORK_IPV6; } enum rdma_link_layer { IB_LINK_LAYER_UNSPECIFIED, IB_LINK_LAYER_INFINIBAND, IB_LINK_LAYER_ETHERNET, }; enum ib_device_cap_flags { IB_DEVICE_RESIZE_MAX_WR = IB_UVERBS_DEVICE_RESIZE_MAX_WR, IB_DEVICE_BAD_PKEY_CNTR = IB_UVERBS_DEVICE_BAD_PKEY_CNTR, IB_DEVICE_BAD_QKEY_CNTR = IB_UVERBS_DEVICE_BAD_QKEY_CNTR, IB_DEVICE_RAW_MULTI = IB_UVERBS_DEVICE_RAW_MULTI, IB_DEVICE_AUTO_PATH_MIG = IB_UVERBS_DEVICE_AUTO_PATH_MIG, IB_DEVICE_CHANGE_PHY_PORT = IB_UVERBS_DEVICE_CHANGE_PHY_PORT, IB_DEVICE_UD_AV_PORT_ENFORCE = IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE, IB_DEVICE_CURR_QP_STATE_MOD = IB_UVERBS_DEVICE_CURR_QP_STATE_MOD, IB_DEVICE_SHUTDOWN_PORT = IB_UVERBS_DEVICE_SHUTDOWN_PORT, /* IB_DEVICE_INIT_TYPE = IB_UVERBS_DEVICE_INIT_TYPE, (not in use) */ IB_DEVICE_PORT_ACTIVE_EVENT = IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT, IB_DEVICE_SYS_IMAGE_GUID = IB_UVERBS_DEVICE_SYS_IMAGE_GUID, IB_DEVICE_RC_RNR_NAK_GEN = IB_UVERBS_DEVICE_RC_RNR_NAK_GEN, IB_DEVICE_SRQ_RESIZE = IB_UVERBS_DEVICE_SRQ_RESIZE, IB_DEVICE_N_NOTIFY_CQ = IB_UVERBS_DEVICE_N_NOTIFY_CQ, /* Reserved, old SEND_W_INV = 1 << 16,*/ IB_DEVICE_MEM_WINDOW = IB_UVERBS_DEVICE_MEM_WINDOW, /* * Devices should set IB_DEVICE_UD_IP_SUM if they support * insertion of UDP and TCP checksum on outgoing UD IPoIB * messages and can verify the validity of checksum for * incoming messages. Setting this flag implies that the * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode. */ IB_DEVICE_UD_IP_CSUM = IB_UVERBS_DEVICE_UD_IP_CSUM, IB_DEVICE_XRC = IB_UVERBS_DEVICE_XRC, /* * This device supports the IB "base memory management extension", * which includes support for fast registrations (IB_WR_REG_MR, * IB_WR_LOCAL_INV and IB_WR_SEND_WITH_INV verbs). This flag should * also be set by any iWarp device which must support FRs to comply * to the iWarp verbs spec. iWarp devices also support the * IB_WR_RDMA_READ_WITH_INV verb for RDMA READs that invalidate the * stag. */ IB_DEVICE_MEM_MGT_EXTENSIONS = IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS, IB_DEVICE_MEM_WINDOW_TYPE_2A = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A, IB_DEVICE_MEM_WINDOW_TYPE_2B = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B, IB_DEVICE_RC_IP_CSUM = IB_UVERBS_DEVICE_RC_IP_CSUM, /* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */ IB_DEVICE_RAW_IP_CSUM = IB_UVERBS_DEVICE_RAW_IP_CSUM, IB_DEVICE_MANAGED_FLOW_STEERING = IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING, /* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */ IB_DEVICE_RAW_SCATTER_FCS = IB_UVERBS_DEVICE_RAW_SCATTER_FCS, /* The device supports padding incoming writes to cacheline. */ IB_DEVICE_PCI_WRITE_END_PADDING = IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING, }; enum ib_kernel_cap_flags { /* * This device supports a per-device lkey or stag that can be * used without performing a memory registration for the local * memory. Note that ULPs should never check this flag, but * instead of use the local_dma_lkey flag in the ib_pd structure, * which will always contain a usable lkey. */ IBK_LOCAL_DMA_LKEY = 1 << 0, /* IB_QP_CREATE_INTEGRITY_EN is supported to implement T10-PI */ IBK_INTEGRITY_HANDOVER = 1 << 1, /* IB_ACCESS_ON_DEMAND is supported during reg_user_mr() */ IBK_ON_DEMAND_PAGING = 1 << 2, /* IB_MR_TYPE_SG_GAPS is supported */ IBK_SG_GAPS_REG = 1 << 3, /* Driver supports RDMA_NLDEV_CMD_DELLINK */ IBK_ALLOW_USER_UNREG = 1 << 4, /* ipoib will use IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK */ IBK_BLOCK_MULTICAST_LOOPBACK = 1 << 5, /* iopib will use IB_QP_CREATE_IPOIB_UD_LSO for its QPs */ IBK_UD_TSO = 1 << 6, /* iopib will use the device ops: * get_vf_config * get_vf_guid * get_vf_stats * set_vf_guid * set_vf_link_state */ IBK_VIRTUAL_FUNCTION = 1 << 7, /* ipoib will use IB_QP_CREATE_NETDEV_USE for its QPs */ IBK_RDMA_NETDEV_OPA = 1 << 8, }; enum ib_atomic_cap { IB_ATOMIC_NONE, IB_ATOMIC_HCA, IB_ATOMIC_GLOB }; enum ib_odp_general_cap_bits { IB_ODP_SUPPORT = 1 << 0, IB_ODP_SUPPORT_IMPLICIT = 1 << 1, }; enum ib_odp_transport_cap_bits { IB_ODP_SUPPORT_SEND = 1 << 0, IB_ODP_SUPPORT_RECV = 1 << 1, IB_ODP_SUPPORT_WRITE = 1 << 2, IB_ODP_SUPPORT_READ = 1 << 3, IB_ODP_SUPPORT_ATOMIC = 1 << 4, IB_ODP_SUPPORT_SRQ_RECV = 1 << 5, }; struct ib_odp_caps { uint64_t general_caps; struct { uint32_t rc_odp_caps; uint32_t uc_odp_caps; uint32_t ud_odp_caps; uint32_t xrc_odp_caps; } per_transport_caps; }; struct ib_rss_caps { /* Corresponding bit will be set if qp type from * 'enum ib_qp_type' is supported, e.g. * supported_qpts |= 1 << IB_QPT_UD */ u32 supported_qpts; u32 max_rwq_indirection_tables; u32 max_rwq_indirection_table_size; }; enum ib_tm_cap_flags { /* Support tag matching with rendezvous offload for RC transport */ IB_TM_CAP_RNDV_RC = 1 << 0, }; struct ib_tm_caps { /* Max size of RNDV header */ u32 max_rndv_hdr_size; /* Max number of entries in tag matching list */ u32 max_num_tags; /* From enum ib_tm_cap_flags */ u32 flags; /* Max number of outstanding list operations */ u32 max_ops; /* Max number of SGE in tag matching entry */ u32 max_sge; }; struct ib_cq_init_attr { unsigned int cqe; u32 comp_vector; u32 flags; }; enum ib_cq_attr_mask { IB_CQ_MODERATE = 1 << 0, }; struct ib_cq_caps { u16 max_cq_moderation_count; u16 max_cq_moderation_period; }; struct ib_dm_mr_attr { u64 length; u64 offset; u32 access_flags; }; struct ib_dm_alloc_attr { u64 length; u32 alignment; u32 flags; }; struct ib_device_attr { u64 fw_ver; __be64 sys_image_guid; u64 max_mr_size; u64 page_size_cap; u32 vendor_id; u32 vendor_part_id; u32 hw_ver; int max_qp; int max_qp_wr; u64 device_cap_flags; u64 kernel_cap_flags; int max_send_sge; int max_recv_sge; int max_sge_rd; int max_cq; int max_cqe; int max_mr; int max_pd; int max_qp_rd_atom; int max_ee_rd_atom; int max_res_rd_atom; int max_qp_init_rd_atom; int max_ee_init_rd_atom; enum ib_atomic_cap atomic_cap; enum ib_atomic_cap masked_atomic_cap; int max_ee; int max_rdd; int max_mw; int max_raw_ipv6_qp; int max_raw_ethy_qp; int max_mcast_grp; int max_mcast_qp_attach; int max_total_mcast_qp_attach; int max_ah; int max_srq; int max_srq_wr; int max_srq_sge; unsigned int max_fast_reg_page_list_len; unsigned int max_pi_fast_reg_page_list_len; u16 max_pkeys; u8 local_ca_ack_delay; int sig_prot_cap; int sig_guard_cap; struct ib_odp_caps odp_caps; uint64_t timestamp_mask; uint64_t hca_core_clock; /* in KHZ */ struct ib_rss_caps rss_caps; u32 max_wq_type_rq; u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */ struct ib_tm_caps tm_caps; struct ib_cq_caps cq_caps; u64 max_dm_size; /* Max entries for sgl for optimized performance per READ */ u32 max_sgl_rd; }; enum ib_mtu { IB_MTU_256 = 1, IB_MTU_512 = 2, IB_MTU_1024 = 3, IB_MTU_2048 = 4, IB_MTU_4096 = 5 }; enum opa_mtu { OPA_MTU_8192 = 6, OPA_MTU_10240 = 7 }; static inline int ib_mtu_enum_to_int(enum ib_mtu mtu) { switch (mtu) { case IB_MTU_256: return 256; case IB_MTU_512: return 512; case IB_MTU_1024: return 1024; case IB_MTU_2048: return 2048; case IB_MTU_4096: return 4096; default: return -1; } } static inline enum ib_mtu ib_mtu_int_to_enum(int mtu) { if (mtu >= 4096) return IB_MTU_4096; else if (mtu >= 2048) return IB_MTU_2048; else if (mtu >= 1024) return IB_MTU_1024; else if (mtu >= 512) return IB_MTU_512; else return IB_MTU_256; } static inline int opa_mtu_enum_to_int(enum opa_mtu mtu) { switch (mtu) { case OPA_MTU_8192: return 8192; case OPA_MTU_10240: return 10240; default: return(ib_mtu_enum_to_int((enum ib_mtu)mtu)); } } static inline enum opa_mtu opa_mtu_int_to_enum(int mtu) { if (mtu >= 10240) return OPA_MTU_10240; else if (mtu >= 8192) return OPA_MTU_8192; else return ((enum opa_mtu)ib_mtu_int_to_enum(mtu)); } enum ib_port_state { IB_PORT_NOP = 0, IB_PORT_DOWN = 1, IB_PORT_INIT = 2, IB_PORT_ARMED = 3, IB_PORT_ACTIVE = 4, IB_PORT_ACTIVE_DEFER = 5 }; enum ib_port_phys_state { IB_PORT_PHYS_STATE_SLEEP = 1, IB_PORT_PHYS_STATE_POLLING = 2, IB_PORT_PHYS_STATE_DISABLED = 3, IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING = 4, IB_PORT_PHYS_STATE_LINK_UP = 5, IB_PORT_PHYS_STATE_LINK_ERROR_RECOVERY = 6, IB_PORT_PHYS_STATE_PHY_TEST = 7, }; enum ib_port_width { IB_WIDTH_1X = 1, IB_WIDTH_2X = 16, IB_WIDTH_4X = 2, IB_WIDTH_8X = 4, IB_WIDTH_12X = 8 }; static inline int ib_width_enum_to_int(enum ib_port_width width) { switch (width) { case IB_WIDTH_1X: return 1; case IB_WIDTH_2X: return 2; case IB_WIDTH_4X: return 4; case IB_WIDTH_8X: return 8; case IB_WIDTH_12X: return 12; default: return -1; } } enum ib_port_speed { IB_SPEED_SDR = 1, IB_SPEED_DDR = 2, IB_SPEED_QDR = 4, IB_SPEED_FDR10 = 8, IB_SPEED_FDR = 16, IB_SPEED_EDR = 32, IB_SPEED_HDR = 64, IB_SPEED_NDR = 128, }; enum ib_stat_flag { IB_STAT_FLAG_OPTIONAL = 1 << 0, }; /** * struct rdma_stat_desc * @name - The name of the counter * @flags - Flags of the counter; For example, IB_STAT_FLAG_OPTIONAL * @priv - Driver private information; Core code should not use */ struct rdma_stat_desc { const char *name; unsigned int flags; const void *priv; }; /** * struct rdma_hw_stats * @lock - Mutex to protect parallel write access to lifespan and values * of counters, which are 64bits and not guaranteed to be written * atomicaly on 32bits systems. * @timestamp - Used by the core code to track when the last update was * @lifespan - Used by the core code to determine how old the counters * should be before being updated again. Stored in jiffies, defaults * to 10 milliseconds, drivers can override the default be specifying * their own value during their allocation routine. * @descs - Array of pointers to static descriptors used for the counters * in directory. * @is_disabled - A bitmap to indicate each counter is currently disabled * or not. * @num_counters - How many hardware counters there are. If name is * shorter than this number, a kernel oops will result. Driver authors * are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters) * in their code to prevent this. * @value - Array of u64 counters that are accessed by the sysfs code and * filled in by the drivers get_stats routine */ struct rdma_hw_stats { struct mutex lock; /* Protect lifespan and values[] */ unsigned long timestamp; unsigned long lifespan; const struct rdma_stat_desc *descs; unsigned long *is_disabled; int num_counters; u64 value[]; }; #define RDMA_HW_STATS_DEFAULT_LIFESPAN 10 struct rdma_hw_stats *rdma_alloc_hw_stats_struct( const struct rdma_stat_desc *descs, int num_counters, unsigned long lifespan); void rdma_free_hw_stats_struct(struct rdma_hw_stats *stats); /* Define bits for the various functionality this port needs to be supported by * the core. */ /* Management 0x00000FFF */ #define RDMA_CORE_CAP_IB_MAD 0x00000001 #define RDMA_CORE_CAP_IB_SMI 0x00000002 #define RDMA_CORE_CAP_IB_CM 0x00000004 #define RDMA_CORE_CAP_IW_CM 0x00000008 #define RDMA_CORE_CAP_IB_SA 0x00000010 #define RDMA_CORE_CAP_OPA_MAD 0x00000020 /* Address format 0x000FF000 */ #define RDMA_CORE_CAP_AF_IB 0x00001000 #define RDMA_CORE_CAP_ETH_AH 0x00002000 #define RDMA_CORE_CAP_OPA_AH 0x00004000 #define RDMA_CORE_CAP_IB_GRH_REQUIRED 0x00008000 /* Protocol 0xFFF00000 */ #define RDMA_CORE_CAP_PROT_IB 0x00100000 #define RDMA_CORE_CAP_PROT_ROCE 0x00200000 #define RDMA_CORE_CAP_PROT_IWARP 0x00400000 #define RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP 0x00800000 #define RDMA_CORE_CAP_PROT_RAW_PACKET 0x01000000 #define RDMA_CORE_CAP_PROT_USNIC 0x02000000 #define RDMA_CORE_PORT_IB_GRH_REQUIRED (RDMA_CORE_CAP_IB_GRH_REQUIRED \ | RDMA_CORE_CAP_PROT_ROCE \ | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP) #define RDMA_CORE_PORT_IBA_IB (RDMA_CORE_CAP_PROT_IB \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_SMI \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_IB_SA \ | RDMA_CORE_CAP_AF_IB) #define RDMA_CORE_PORT_IBA_ROCE (RDMA_CORE_CAP_PROT_ROCE \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_AF_IB \ | RDMA_CORE_CAP_ETH_AH) #define RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP \ (RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_AF_IB \ | RDMA_CORE_CAP_ETH_AH) #define RDMA_CORE_PORT_IWARP (RDMA_CORE_CAP_PROT_IWARP \ | RDMA_CORE_CAP_IW_CM) #define RDMA_CORE_PORT_INTEL_OPA (RDMA_CORE_PORT_IBA_IB \ | RDMA_CORE_CAP_OPA_MAD) #define RDMA_CORE_PORT_RAW_PACKET (RDMA_CORE_CAP_PROT_RAW_PACKET) #define RDMA_CORE_PORT_USNIC (RDMA_CORE_CAP_PROT_USNIC) struct ib_port_attr { u64 subnet_prefix; enum ib_port_state state; enum ib_mtu max_mtu; enum ib_mtu active_mtu; u32 phys_mtu; int gid_tbl_len; unsigned int ip_gids:1; /* This is the value from PortInfo CapabilityMask, defined by IBA */ u32 port_cap_flags; u32 max_msg_sz; u32 bad_pkey_cntr; u32 qkey_viol_cntr; u16 pkey_tbl_len; u32 sm_lid; u32 lid; u8 lmc; u8 max_vl_num; u8 sm_sl; u8 subnet_timeout; u8 init_type_reply; u8 active_width; u16 active_speed; u8 phys_state; u16 port_cap_flags2; }; enum ib_device_modify_flags { IB_DEVICE_MODIFY_SYS_IMAGE_GUID = 1 << 0, IB_DEVICE_MODIFY_NODE_DESC = 1 << 1 }; #define IB_DEVICE_NODE_DESC_MAX 64 struct ib_device_modify { u64 sys_image_guid; char node_desc[IB_DEVICE_NODE_DESC_MAX]; }; enum ib_port_modify_flags { IB_PORT_SHUTDOWN = 1, IB_PORT_INIT_TYPE = (1<<2), IB_PORT_RESET_QKEY_CNTR = (1<<3), IB_PORT_OPA_MASK_CHG = (1<<4) }; struct ib_port_modify { u32 set_port_cap_mask; u32 clr_port_cap_mask; u8 init_type; }; enum ib_event_type { IB_EVENT_CQ_ERR, IB_EVENT_QP_FATAL, IB_EVENT_QP_REQ_ERR, IB_EVENT_QP_ACCESS_ERR, IB_EVENT_COMM_EST, IB_EVENT_SQ_DRAINED, IB_EVENT_PATH_MIG, IB_EVENT_PATH_MIG_ERR, IB_EVENT_DEVICE_FATAL, IB_EVENT_PORT_ACTIVE, IB_EVENT_PORT_ERR, IB_EVENT_LID_CHANGE, IB_EVENT_PKEY_CHANGE, IB_EVENT_SM_CHANGE, IB_EVENT_SRQ_ERR, IB_EVENT_SRQ_LIMIT_REACHED, IB_EVENT_QP_LAST_WQE_REACHED, IB_EVENT_CLIENT_REREGISTER, IB_EVENT_GID_CHANGE, IB_EVENT_WQ_FATAL, }; const char *__attribute_const__ ib_event_msg(enum ib_event_type event); struct ib_event { struct ib_device *device; union { struct ib_cq *cq; struct ib_qp *qp; struct ib_srq *srq; struct ib_wq *wq; u32 port_num; } element; enum ib_event_type event; }; struct ib_event_handler { struct ib_device *device; void (*handler)(struct ib_event_handler *, struct ib_event *); struct list_head list; }; #define INIT_IB_EVENT_HANDLER(_ptr, _device, _handler) \ do { \ (_ptr)->device = _device; \ (_ptr)->handler = _handler; \ INIT_LIST_HEAD(&(_ptr)->list); \ } while (0) struct ib_global_route { const struct ib_gid_attr *sgid_attr; union ib_gid dgid; u32 flow_label; u8 sgid_index; u8 hop_limit; u8 traffic_class; }; struct ib_grh { __be32 version_tclass_flow; __be16 paylen; u8 next_hdr; u8 hop_limit; union ib_gid sgid; union ib_gid dgid; }; union rdma_network_hdr { struct ib_grh ibgrh; struct { /* The IB spec states that if it's IPv4, the header * is located in the last 20 bytes of the header. */ u8 reserved[20]; struct iphdr roce4grh; }; }; #define IB_QPN_MASK 0xFFFFFF enum { IB_MULTICAST_QPN = 0xffffff }; #define IB_LID_PERMISSIVE cpu_to_be16(0xFFFF) #define IB_MULTICAST_LID_BASE cpu_to_be16(0xC000) enum ib_ah_flags { IB_AH_GRH = 1 }; enum ib_rate { IB_RATE_PORT_CURRENT = 0, IB_RATE_2_5_GBPS = 2, IB_RATE_5_GBPS = 5, IB_RATE_10_GBPS = 3, IB_RATE_20_GBPS = 6, IB_RATE_30_GBPS = 4, IB_RATE_40_GBPS = 7, IB_RATE_60_GBPS = 8, IB_RATE_80_GBPS = 9, IB_RATE_120_GBPS = 10, IB_RATE_14_GBPS = 11, IB_RATE_56_GBPS = 12, IB_RATE_112_GBPS = 13, IB_RATE_168_GBPS = 14, IB_RATE_25_GBPS = 15, IB_RATE_100_GBPS = 16, IB_RATE_200_GBPS = 17, IB_RATE_300_GBPS = 18, IB_RATE_28_GBPS = 19, IB_RATE_50_GBPS = 20, IB_RATE_400_GBPS = 21, IB_RATE_600_GBPS = 22, }; /** * ib_rate_to_mult - Convert the IB rate enum to a multiple of the * base rate of 2.5 Gbit/sec. For example, IB_RATE_5_GBPS will be * converted to 2, since 5 Gbit/sec is 2 * 2.5 Gbit/sec. * @rate: rate to convert. */ __attribute_const__ int ib_rate_to_mult(enum ib_rate rate); /** * ib_rate_to_mbps - Convert the IB rate enum to Mbps. * For example, IB_RATE_2_5_GBPS will be converted to 2500. * @rate: rate to convert. */ __attribute_const__ int ib_rate_to_mbps(enum ib_rate rate); /** * enum ib_mr_type - memory region type * @IB_MR_TYPE_MEM_REG: memory region that is used for * normal registration * @IB_MR_TYPE_SG_GAPS: memory region that is capable to * register any arbitrary sg lists (without * the normal mr constraints - see * ib_map_mr_sg) * @IB_MR_TYPE_DM: memory region that is used for device * memory registration * @IB_MR_TYPE_USER: memory region that is used for the user-space * application * @IB_MR_TYPE_DMA: memory region that is used for DMA operations * without address translations (VA=PA) * @IB_MR_TYPE_INTEGRITY: memory region that is used for * data integrity operations */ enum ib_mr_type { IB_MR_TYPE_MEM_REG, IB_MR_TYPE_SG_GAPS, IB_MR_TYPE_DM, IB_MR_TYPE_USER, IB_MR_TYPE_DMA, IB_MR_TYPE_INTEGRITY, }; enum ib_mr_status_check { IB_MR_CHECK_SIG_STATUS = 1, }; /** * struct ib_mr_status - Memory region status container * * @fail_status: Bitmask of MR checks status. For each * failed check a corresponding status bit is set. * @sig_err: Additional info for IB_MR_CEHCK_SIG_STATUS * failure. */ struct ib_mr_status { u32 fail_status; struct ib_sig_err sig_err; }; /** * mult_to_ib_rate - Convert a multiple of 2.5 Gbit/sec to an IB rate * enum. * @mult: multiple to convert. */ __attribute_const__ enum ib_rate mult_to_ib_rate(int mult); struct rdma_ah_init_attr { struct rdma_ah_attr *ah_attr; u32 flags; struct net_device *xmit_slave; }; enum rdma_ah_attr_type { RDMA_AH_ATTR_TYPE_UNDEFINED, RDMA_AH_ATTR_TYPE_IB, RDMA_AH_ATTR_TYPE_ROCE, RDMA_AH_ATTR_TYPE_OPA, }; struct ib_ah_attr { u16 dlid; u8 src_path_bits; }; struct roce_ah_attr { u8 dmac[ETH_ALEN]; }; struct opa_ah_attr { u32 dlid; u8 src_path_bits; bool make_grd; }; struct rdma_ah_attr { struct ib_global_route grh; u8 sl; u8 static_rate; u32 port_num; u8 ah_flags; enum rdma_ah_attr_type type; union { struct ib_ah_attr ib; struct roce_ah_attr roce; struct opa_ah_attr opa; }; }; enum ib_wc_status { IB_WC_SUCCESS, IB_WC_LOC_LEN_ERR, IB_WC_LOC_QP_OP_ERR, IB_WC_LOC_EEC_OP_ERR, IB_WC_LOC_PROT_ERR, IB_WC_WR_FLUSH_ERR, IB_WC_MW_BIND_ERR, IB_WC_BAD_RESP_ERR, IB_WC_LOC_ACCESS_ERR, IB_WC_REM_INV_REQ_ERR, IB_WC_REM_ACCESS_ERR, IB_WC_REM_OP_ERR, IB_WC_RETRY_EXC_ERR, IB_WC_RNR_RETRY_EXC_ERR, IB_WC_LOC_RDD_VIOL_ERR, IB_WC_REM_INV_RD_REQ_ERR, IB_WC_REM_ABORT_ERR, IB_WC_INV_EECN_ERR, IB_WC_INV_EEC_STATE_ERR, IB_WC_FATAL_ERR, IB_WC_RESP_TIMEOUT_ERR, IB_WC_GENERAL_ERR }; const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status); enum ib_wc_opcode { IB_WC_SEND = IB_UVERBS_WC_SEND, IB_WC_RDMA_WRITE = IB_UVERBS_WC_RDMA_WRITE, IB_WC_RDMA_READ = IB_UVERBS_WC_RDMA_READ, IB_WC_COMP_SWAP = IB_UVERBS_WC_COMP_SWAP, IB_WC_FETCH_ADD = IB_UVERBS_WC_FETCH_ADD, IB_WC_BIND_MW = IB_UVERBS_WC_BIND_MW, IB_WC_LOCAL_INV = IB_UVERBS_WC_LOCAL_INV, IB_WC_LSO = IB_UVERBS_WC_TSO, IB_WC_REG_MR, IB_WC_MASKED_COMP_SWAP, IB_WC_MASKED_FETCH_ADD, /* * Set value of IB_WC_RECV so consumers can test if a completion is a * receive by testing (opcode & IB_WC_RECV). */ IB_WC_RECV = 1 << 7, IB_WC_RECV_RDMA_WITH_IMM }; enum ib_wc_flags { IB_WC_GRH = 1, IB_WC_WITH_IMM = (1<<1), IB_WC_WITH_INVALIDATE = (1<<2), IB_WC_IP_CSUM_OK = (1<<3), IB_WC_WITH_SMAC = (1<<4), IB_WC_WITH_VLAN = (1<<5), IB_WC_WITH_NETWORK_HDR_TYPE = (1<<6), }; struct ib_wc { union { u64 wr_id; struct ib_cqe *wr_cqe; }; enum ib_wc_status status; enum ib_wc_opcode opcode; u32 vendor_err; u32 byte_len; struct ib_qp *qp; union { __be32 imm_data; u32 invalidate_rkey; } ex; u32 src_qp; u32 slid; int wc_flags; u16 pkey_index; u8 sl; u8 dlid_path_bits; u32 port_num; /* valid only for DR SMPs on switches */ u8 smac[ETH_ALEN]; u16 vlan_id; u8 network_hdr_type; }; enum ib_cq_notify_flags { IB_CQ_SOLICITED = 1 << 0, IB_CQ_NEXT_COMP = 1 << 1, IB_CQ_SOLICITED_MASK = IB_CQ_SOLICITED | IB_CQ_NEXT_COMP, IB_CQ_REPORT_MISSED_EVENTS = 1 << 2, }; enum ib_srq_type { IB_SRQT_BASIC = IB_UVERBS_SRQT_BASIC, IB_SRQT_XRC = IB_UVERBS_SRQT_XRC, IB_SRQT_TM = IB_UVERBS_SRQT_TM, }; static inline bool ib_srq_has_cq(enum ib_srq_type srq_type) { return srq_type == IB_SRQT_XRC || srq_type == IB_SRQT_TM; } enum ib_srq_attr_mask { IB_SRQ_MAX_WR = 1 << 0, IB_SRQ_LIMIT = 1 << 1, }; struct ib_srq_attr { u32 max_wr; u32 max_sge; u32 srq_limit; }; struct ib_srq_init_attr { void (*event_handler)(struct ib_event *, void *); void *srq_context; struct ib_srq_attr attr; enum ib_srq_type srq_type; struct { struct ib_cq *cq; union { struct { struct ib_xrcd *xrcd; } xrc; struct { u32 max_num_tags; } tag_matching; }; } ext; }; struct ib_qp_cap { u32 max_send_wr; u32 max_recv_wr; u32 max_send_sge; u32 max_recv_sge; u32 max_inline_data; /* * Maximum number of rdma_rw_ctx structures in flight at a time. * ib_create_qp() will calculate the right amount of neededed WRs * and MRs based on this. */ u32 max_rdma_ctxs; }; enum ib_sig_type { IB_SIGNAL_ALL_WR, IB_SIGNAL_REQ_WR }; enum ib_qp_type { /* * IB_QPT_SMI and IB_QPT_GSI have to be the first two entries * here (and in that order) since the MAD layer uses them as * indices into a 2-entry table. */ IB_QPT_SMI, IB_QPT_GSI, IB_QPT_RC = IB_UVERBS_QPT_RC, IB_QPT_UC = IB_UVERBS_QPT_UC, IB_QPT_UD = IB_UVERBS_QPT_UD, IB_QPT_RAW_IPV6, IB_QPT_RAW_ETHERTYPE, IB_QPT_RAW_PACKET = IB_UVERBS_QPT_RAW_PACKET, IB_QPT_XRC_INI = IB_UVERBS_QPT_XRC_INI, IB_QPT_XRC_TGT = IB_UVERBS_QPT_XRC_TGT, IB_QPT_MAX, IB_QPT_DRIVER = IB_UVERBS_QPT_DRIVER, /* Reserve a range for qp types internal to the low level driver. * These qp types will not be visible at the IB core layer, so the * IB_QPT_MAX usages should not be affected in the core layer */ IB_QPT_RESERVED1 = 0x1000, IB_QPT_RESERVED2, IB_QPT_RESERVED3, IB_QPT_RESERVED4, IB_QPT_RESERVED5, IB_QPT_RESERVED6, IB_QPT_RESERVED7, IB_QPT_RESERVED8, IB_QPT_RESERVED9, IB_QPT_RESERVED10, }; enum ib_qp_create_flags { IB_QP_CREATE_IPOIB_UD_LSO = 1 << 0, IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK = IB_UVERBS_QP_CREATE_BLOCK_MULTICAST_LOOPBACK, IB_QP_CREATE_CROSS_CHANNEL = 1 << 2, IB_QP_CREATE_MANAGED_SEND = 1 << 3, IB_QP_CREATE_MANAGED_RECV = 1 << 4, IB_QP_CREATE_NETIF_QP = 1 << 5, IB_QP_CREATE_INTEGRITY_EN = 1 << 6, IB_QP_CREATE_NETDEV_USE = 1 << 7, IB_QP_CREATE_SCATTER_FCS = IB_UVERBS_QP_CREATE_SCATTER_FCS, IB_QP_CREATE_CVLAN_STRIPPING = IB_UVERBS_QP_CREATE_CVLAN_STRIPPING, IB_QP_CREATE_SOURCE_QPN = 1 << 10, IB_QP_CREATE_PCI_WRITE_END_PADDING = IB_UVERBS_QP_CREATE_PCI_WRITE_END_PADDING, /* reserve bits 26-31 for low level drivers' internal use */ IB_QP_CREATE_RESERVED_START = 1 << 26, IB_QP_CREATE_RESERVED_END = 1 << 31, }; /* * Note: users may not call ib_close_qp or ib_destroy_qp from the event_handler * callback to destroy the passed in QP. */ struct ib_qp_init_attr { /* Consumer's event_handler callback must not block */ void (*event_handler)(struct ib_event *, void *); void *qp_context; struct ib_cq *send_cq; struct ib_cq *recv_cq; struct ib_srq *srq; struct ib_xrcd *xrcd; /* XRC TGT QPs only */ struct ib_qp_cap cap; enum ib_sig_type sq_sig_type; enum ib_qp_type qp_type; u32 create_flags; /* * Only needed for special QP types, or when using the RW API. */ u32 port_num; struct ib_rwq_ind_table *rwq_ind_tbl; u32 source_qpn; }; struct ib_qp_open_attr { void (*event_handler)(struct ib_event *, void *); void *qp_context; u32 qp_num; enum ib_qp_type qp_type; }; enum ib_rnr_timeout { IB_RNR_TIMER_655_36 = 0, IB_RNR_TIMER_000_01 = 1, IB_RNR_TIMER_000_02 = 2, IB_RNR_TIMER_000_03 = 3, IB_RNR_TIMER_000_04 = 4, IB_RNR_TIMER_000_06 = 5, IB_RNR_TIMER_000_08 = 6, IB_RNR_TIMER_000_12 = 7, IB_RNR_TIMER_000_16 = 8, IB_RNR_TIMER_000_24 = 9, IB_RNR_TIMER_000_32 = 10, IB_RNR_TIMER_000_48 = 11, IB_RNR_TIMER_000_64 = 12, IB_RNR_TIMER_000_96 = 13, IB_RNR_TIMER_001_28 = 14, IB_RNR_TIMER_001_92 = 15, IB_RNR_TIMER_002_56 = 16, IB_RNR_TIMER_003_84 = 17, IB_RNR_TIMER_005_12 = 18, IB_RNR_TIMER_007_68 = 19, IB_RNR_TIMER_010_24 = 20, IB_RNR_TIMER_015_36 = 21, IB_RNR_TIMER_020_48 = 22, IB_RNR_TIMER_030_72 = 23, IB_RNR_TIMER_040_96 = 24, IB_RNR_TIMER_061_44 = 25, IB_RNR_TIMER_081_92 = 26, IB_RNR_TIMER_122_88 = 27, IB_RNR_TIMER_163_84 = 28, IB_RNR_TIMER_245_76 = 29, IB_RNR_TIMER_327_68 = 30, IB_RNR_TIMER_491_52 = 31 }; enum ib_qp_attr_mask { IB_QP_STATE = 1, IB_QP_CUR_STATE = (1<<1), IB_QP_EN_SQD_ASYNC_NOTIFY = (1<<2), IB_QP_ACCESS_FLAGS = (1<<3), IB_QP_PKEY_INDEX = (1<<4), IB_QP_PORT = (1<<5), IB_QP_QKEY = (1<<6), IB_QP_AV = (1<<7), IB_QP_PATH_MTU = (1<<8), IB_QP_TIMEOUT = (1<<9), IB_QP_RETRY_CNT = (1<<10), IB_QP_RNR_RETRY = (1<<11), IB_QP_RQ_PSN = (1<<12), IB_QP_MAX_QP_RD_ATOMIC = (1<<13), IB_QP_ALT_PATH = (1<<14), IB_QP_MIN_RNR_TIMER = (1<<15), IB_QP_SQ_PSN = (1<<16), IB_QP_MAX_DEST_RD_ATOMIC = (1<<17), IB_QP_PATH_MIG_STATE = (1<<18), IB_QP_CAP = (1<<19), IB_QP_DEST_QPN = (1<<20), IB_QP_RESERVED1 = (1<<21), IB_QP_RESERVED2 = (1<<22), IB_QP_RESERVED3 = (1<<23), IB_QP_RESERVED4 = (1<<24), IB_QP_RATE_LIMIT = (1<<25), IB_QP_ATTR_STANDARD_BITS = GENMASK(20, 0), }; enum ib_qp_state { IB_QPS_RESET, IB_QPS_INIT, IB_QPS_RTR, IB_QPS_RTS, IB_QPS_SQD, IB_QPS_SQE, IB_QPS_ERR }; enum ib_mig_state { IB_MIG_MIGRATED, IB_MIG_REARM, IB_MIG_ARMED }; enum ib_mw_type { IB_MW_TYPE_1 = 1, IB_MW_TYPE_2 = 2 }; struct ib_qp_attr { enum ib_qp_state qp_state; enum ib_qp_state cur_qp_state; enum ib_mtu path_mtu; enum ib_mig_state path_mig_state; u32 qkey; u32 rq_psn; u32 sq_psn; u32 dest_qp_num; int qp_access_flags; struct ib_qp_cap cap; struct rdma_ah_attr ah_attr; struct rdma_ah_attr alt_ah_attr; u16 pkey_index; u16 alt_pkey_index; u8 en_sqd_async_notify; u8 sq_draining; u8 max_rd_atomic; u8 max_dest_rd_atomic; u8 min_rnr_timer; u32 port_num; u8 timeout; u8 retry_cnt; u8 rnr_retry; u32 alt_port_num; u8 alt_timeout; u32 rate_limit; struct net_device *xmit_slave; }; enum ib_wr_opcode { /* These are shared with userspace */ IB_WR_RDMA_WRITE = IB_UVERBS_WR_RDMA_WRITE, IB_WR_RDMA_WRITE_WITH_IMM = IB_UVERBS_WR_RDMA_WRITE_WITH_IMM, IB_WR_SEND = IB_UVERBS_WR_SEND, IB_WR_SEND_WITH_IMM = IB_UVERBS_WR_SEND_WITH_IMM, IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ, IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP, IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD, IB_WR_BIND_MW = IB_UVERBS_WR_BIND_MW, IB_WR_LSO = IB_UVERBS_WR_TSO, IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV, IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV, IB_WR_LOCAL_INV = IB_UVERBS_WR_LOCAL_INV, IB_WR_MASKED_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP, IB_WR_MASKED_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD, /* These are kernel only and can not be issued by userspace */ IB_WR_REG_MR = 0x20, IB_WR_REG_MR_INTEGRITY, /* reserve values for low level drivers' internal use. * These values will not be used at all in the ib core layer. */ IB_WR_RESERVED1 = 0xf0, IB_WR_RESERVED2, IB_WR_RESERVED3, IB_WR_RESERVED4, IB_WR_RESERVED5, IB_WR_RESERVED6, IB_WR_RESERVED7, IB_WR_RESERVED8, IB_WR_RESERVED9, IB_WR_RESERVED10, }; enum ib_send_flags { IB_SEND_FENCE = 1, IB_SEND_SIGNALED = (1<<1), IB_SEND_SOLICITED = (1<<2), IB_SEND_INLINE = (1<<3), IB_SEND_IP_CSUM = (1<<4), /* reserve bits 26-31 for low level drivers' internal use */ IB_SEND_RESERVED_START = (1 << 26), IB_SEND_RESERVED_END = (1 << 31), }; struct ib_sge { u64 addr; u32 length; u32 lkey; }; struct ib_cqe { void (*done)(struct ib_cq *cq, struct ib_wc *wc); }; struct ib_send_wr { struct ib_send_wr *next; union { u64 wr_id; struct ib_cqe *wr_cqe; }; struct ib_sge *sg_list; int num_sge; enum ib_wr_opcode opcode; int send_flags; union { __be32 imm_data; u32 invalidate_rkey; } ex; }; struct ib_rdma_wr { struct ib_send_wr wr; u64 remote_addr; u32 rkey; }; static inline const struct ib_rdma_wr *rdma_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_rdma_wr, wr); } struct ib_atomic_wr { struct ib_send_wr wr; u64 remote_addr; u64 compare_add; u64 swap; u64 compare_add_mask; u64 swap_mask; u32 rkey; }; static inline const struct ib_atomic_wr *atomic_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_atomic_wr, wr); } struct ib_ud_wr { struct ib_send_wr wr; struct ib_ah *ah; void *header; int hlen; int mss; u32 remote_qpn; u32 remote_qkey; u16 pkey_index; /* valid for GSI only */ u32 port_num; /* valid for DR SMPs on switch only */ }; static inline const struct ib_ud_wr *ud_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_ud_wr, wr); } struct ib_reg_wr { struct ib_send_wr wr; struct ib_mr *mr; u32 key; int access; }; static inline const struct ib_reg_wr *reg_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_reg_wr, wr); } struct ib_recv_wr { struct ib_recv_wr *next; union { u64 wr_id; struct ib_cqe *wr_cqe; }; struct ib_sge *sg_list; int num_sge; }; enum ib_access_flags { IB_ACCESS_LOCAL_WRITE = IB_UVERBS_ACCESS_LOCAL_WRITE, IB_ACCESS_REMOTE_WRITE = IB_UVERBS_ACCESS_REMOTE_WRITE, IB_ACCESS_REMOTE_READ = IB_UVERBS_ACCESS_REMOTE_READ, IB_ACCESS_REMOTE_ATOMIC = IB_UVERBS_ACCESS_REMOTE_ATOMIC, IB_ACCESS_MW_BIND = IB_UVERBS_ACCESS_MW_BIND, IB_ZERO_BASED = IB_UVERBS_ACCESS_ZERO_BASED, IB_ACCESS_ON_DEMAND = IB_UVERBS_ACCESS_ON_DEMAND, IB_ACCESS_HUGETLB = IB_UVERBS_ACCESS_HUGETLB, IB_ACCESS_RELAXED_ORDERING = IB_UVERBS_ACCESS_RELAXED_ORDERING, IB_ACCESS_OPTIONAL = IB_UVERBS_ACCESS_OPTIONAL_RANGE, IB_ACCESS_SUPPORTED = ((IB_ACCESS_HUGETLB << 1) - 1) | IB_ACCESS_OPTIONAL, }; /* * XXX: these are apparently used for ->rereg_user_mr, no idea why they * are hidden here instead of a uapi header! */ enum ib_mr_rereg_flags { IB_MR_REREG_TRANS = 1, IB_MR_REREG_PD = (1<<1), IB_MR_REREG_ACCESS = (1<<2), IB_MR_REREG_SUPPORTED = ((IB_MR_REREG_ACCESS << 1) - 1) }; struct ib_umem; enum rdma_remove_reason { /* * Userspace requested uobject deletion or initial try * to remove uobject via cleanup. Call could fail */ RDMA_REMOVE_DESTROY, /* Context deletion. This call should delete the actual object itself */ RDMA_REMOVE_CLOSE, /* Driver is being hot-unplugged. This call should delete the actual object itself */ RDMA_REMOVE_DRIVER_REMOVE, /* uobj is being cleaned-up before being committed */ RDMA_REMOVE_ABORT, /* The driver failed to destroy the uobject and is being disconnected */ RDMA_REMOVE_DRIVER_FAILURE, }; struct ib_rdmacg_object { #ifdef CONFIG_CGROUP_RDMA struct rdma_cgroup *cg; /* owner rdma cgroup */ #endif }; struct ib_ucontext { struct ib_device *device; struct ib_uverbs_file *ufile; struct ib_rdmacg_object cg_obj; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; struct xarray mmap_xa; }; struct ib_uobject { u64 user_handle; /* handle given to us by userspace */ /* ufile & ucontext owning this object */ struct ib_uverbs_file *ufile; /* FIXME, save memory: ufile->context == context */ struct ib_ucontext *context; /* associated user context */ void *object; /* containing object */ struct list_head list; /* link to context's list */ struct ib_rdmacg_object cg_obj; /* rdmacg object */ int id; /* index into kernel idr */ struct kref ref; atomic_t usecnt; /* protects exclusive access */ struct rcu_head rcu; /* kfree_rcu() overhead */ const struct uverbs_api_object *uapi_object; }; struct ib_udata { const void __user *inbuf; void __user *outbuf; size_t inlen; size_t outlen; }; struct ib_pd { u32 local_dma_lkey; u32 flags; struct ib_device *device; struct ib_uobject *uobject; atomic_t usecnt; /* count all resources */ u32 unsafe_global_rkey; /* * Implementation details of the RDMA core, don't use in drivers: */ struct ib_mr *__internal_mr; struct rdma_restrack_entry res; }; struct ib_xrcd { struct ib_device *device; atomic_t usecnt; /* count all exposed resources */ struct inode *inode; struct rw_semaphore tgt_qps_rwsem; struct xarray tgt_qps; }; struct ib_ah { struct ib_device *device; struct ib_pd *pd; struct ib_uobject *uobject; const struct ib_gid_attr *sgid_attr; enum rdma_ah_attr_type type; }; typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context); enum ib_poll_context { IB_POLL_SOFTIRQ, /* poll from softirq context */ IB_POLL_WORKQUEUE, /* poll from workqueue */ IB_POLL_UNBOUND_WORKQUEUE, /* poll from unbound workqueue */ IB_POLL_LAST_POOL_TYPE = IB_POLL_UNBOUND_WORKQUEUE, IB_POLL_DIRECT, /* caller context, no hw completions */ }; struct ib_cq { struct ib_device *device; struct ib_ucq_object *uobject; ib_comp_handler comp_handler; void (*event_handler)(struct ib_event *, void *); void *cq_context; int cqe; unsigned int cqe_used; atomic_t usecnt; /* count number of work queues */ enum ib_poll_context poll_ctx; struct ib_wc *wc; struct list_head pool_entry; union { struct irq_poll iop; struct work_struct work; }; struct workqueue_struct *comp_wq; struct dim *dim; /* updated only by trace points */ ktime_t timestamp; u8 interrupt:1; u8 shared:1; unsigned int comp_vector; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; struct ib_srq { struct ib_device *device; struct ib_pd *pd; struct ib_usrq_object *uobject; void (*event_handler)(struct ib_event *, void *); void *srq_context; enum ib_srq_type srq_type; atomic_t usecnt; struct { struct ib_cq *cq; union { struct { struct ib_xrcd *xrcd; u32 srq_num; } xrc; }; } ext; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; enum ib_raw_packet_caps { /* * Strip cvlan from incoming packet and report it in the matching work * completion is supported. */ IB_RAW_PACKET_CAP_CVLAN_STRIPPING = IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING, /* * Scatter FCS field of an incoming packet to host memory is supported. */ IB_RAW_PACKET_CAP_SCATTER_FCS = IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS, /* Checksum offloads are supported (for both send and receive). */ IB_RAW_PACKET_CAP_IP_CSUM = IB_UVERBS_RAW_PACKET_CAP_IP_CSUM, /* * When a packet is received for an RQ with no receive WQEs, the * packet processing is delayed. */ IB_RAW_PACKET_CAP_DELAY_DROP = IB_UVERBS_RAW_PACKET_CAP_DELAY_DROP, }; enum ib_wq_type { IB_WQT_RQ = IB_UVERBS_WQT_RQ, }; enum ib_wq_state { IB_WQS_RESET, IB_WQS_RDY, IB_WQS_ERR }; struct ib_wq { struct ib_device *device; struct ib_uwq_object *uobject; void *wq_context; void (*event_handler)(struct ib_event *, void *); struct ib_pd *pd; struct ib_cq *cq; u32 wq_num; enum ib_wq_state state; enum ib_wq_type wq_type; atomic_t usecnt; }; enum ib_wq_flags { IB_WQ_FLAGS_CVLAN_STRIPPING = IB_UVERBS_WQ_FLAGS_CVLAN_STRIPPING, IB_WQ_FLAGS_SCATTER_FCS = IB_UVERBS_WQ_FLAGS_SCATTER_FCS, IB_WQ_FLAGS_DELAY_DROP = IB_UVERBS_WQ_FLAGS_DELAY_DROP, IB_WQ_FLAGS_PCI_WRITE_END_PADDING = IB_UVERBS_WQ_FLAGS_PCI_WRITE_END_PADDING, }; struct ib_wq_init_attr { void *wq_context; enum ib_wq_type wq_type; u32 max_wr; u32 max_sge; struct ib_cq *cq; void (*event_handler)(struct ib_event *, void *); u32 create_flags; /* Use enum ib_wq_flags */ }; enum ib_wq_attr_mask { IB_WQ_STATE = 1 << 0, IB_WQ_CUR_STATE = 1 << 1, IB_WQ_FLAGS = 1 << 2, }; struct ib_wq_attr { enum ib_wq_state wq_state; enum ib_wq_state curr_wq_state; u32 flags; /* Use enum ib_wq_flags */ u32 flags_mask; /* Use enum ib_wq_flags */ }; struct ib_rwq_ind_table { struct ib_device *device; struct ib_uobject *uobject; atomic_t usecnt; u32 ind_tbl_num; u32 log_ind_tbl_size; struct ib_wq **ind_tbl; }; struct ib_rwq_ind_table_init_attr { u32 log_ind_tbl_size; /* Each entry is a pointer to Receive Work Queue */ struct ib_wq **ind_tbl; }; enum port_pkey_state { IB_PORT_PKEY_NOT_VALID = 0, IB_PORT_PKEY_VALID = 1, IB_PORT_PKEY_LISTED = 2, }; struct ib_qp_security; struct ib_port_pkey { enum port_pkey_state state; u16 pkey_index; u32 port_num; struct list_head qp_list; struct list_head to_error_list; struct ib_qp_security *sec; }; struct ib_ports_pkeys { struct ib_port_pkey main; struct ib_port_pkey alt; }; struct ib_qp_security { struct ib_qp *qp; struct ib_device *dev; /* Hold this mutex when changing port and pkey settings. */ struct mutex mutex; struct ib_ports_pkeys *ports_pkeys; /* A list of all open shared QP handles. Required to enforce security * properly for all users of a shared QP. */ struct list_head shared_qp_list; void *security; bool destroying; atomic_t error_list_count; struct completion error_complete; int error_comps_pending; }; /* * @max_write_sge: Maximum SGE elements per RDMA WRITE request. * @max_read_sge: Maximum SGE elements per RDMA READ request. */ struct ib_qp { struct ib_device *device; struct ib_pd *pd; struct ib_cq *send_cq; struct ib_cq *recv_cq; spinlock_t mr_lock; int mrs_used; struct list_head rdma_mrs; struct list_head sig_mrs; struct ib_srq *srq; struct ib_xrcd *xrcd; /* XRC TGT QPs only */ struct list_head xrcd_list; /* count times opened, mcast attaches, flow attaches */ atomic_t usecnt; struct list_head open_list; struct ib_qp *real_qp; struct ib_uqp_object *uobject; void (*event_handler)(struct ib_event *, void *); void *qp_context; /* sgid_attrs associated with the AV's */ const struct ib_gid_attr *av_sgid_attr; const struct ib_gid_attr *alt_path_sgid_attr; u32 qp_num; u32 max_write_sge; u32 max_read_sge; enum ib_qp_type qp_type; struct ib_rwq_ind_table *rwq_ind_tbl; struct ib_qp_security *qp_sec; u32 port; bool integrity_en; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; /* The counter the qp is bind to */ struct rdma_counter *counter; }; struct ib_dm { struct ib_device *device; u32 length; u32 flags; struct ib_uobject *uobject; atomic_t usecnt; }; struct ib_mr { struct ib_device *device; struct ib_pd *pd; u32 lkey; u32 rkey; u64 iova; u64 length; unsigned int page_size; enum ib_mr_type type; bool need_inval; union { struct ib_uobject *uobject; /* user */ struct list_head qp_entry; /* FR */ }; struct ib_dm *dm; struct ib_sig_attrs *sig_attrs; /* only for IB_MR_TYPE_INTEGRITY MRs */ /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; struct ib_mw { struct ib_device *device; struct ib_pd *pd; struct ib_uobject *uobject; u32 rkey; enum ib_mw_type type; }; /* Supported steering options */ enum ib_flow_attr_type { /* steering according to rule specifications */ IB_FLOW_ATTR_NORMAL = 0x0, /* default unicast and multicast rule - * receive all Eth traffic which isn't steered to any QP */ IB_FLOW_ATTR_ALL_DEFAULT = 0x1, /* default multicast rule - * receive all Eth multicast traffic which isn't steered to any QP */ IB_FLOW_ATTR_MC_DEFAULT = 0x2, /* sniffer rule - receive all port traffic */ IB_FLOW_ATTR_SNIFFER = 0x3 }; /* Supported steering header types */ enum ib_flow_spec_type { /* L2 headers*/ IB_FLOW_SPEC_ETH = 0x20, IB_FLOW_SPEC_IB = 0x22, /* L3 header*/ IB_FLOW_SPEC_IPV4 = 0x30, IB_FLOW_SPEC_IPV6 = 0x31, IB_FLOW_SPEC_ESP = 0x34, /* L4 headers*/ IB_FLOW_SPEC_TCP = 0x40, IB_FLOW_SPEC_UDP = 0x41, IB_FLOW_SPEC_VXLAN_TUNNEL = 0x50, IB_FLOW_SPEC_GRE = 0x51, IB_FLOW_SPEC_MPLS = 0x60, IB_FLOW_SPEC_INNER = 0x100, /* Actions */ IB_FLOW_SPEC_ACTION_TAG = 0x1000, IB_FLOW_SPEC_ACTION_DROP = 0x1001, IB_FLOW_SPEC_ACTION_HANDLE = 0x1002, IB_FLOW_SPEC_ACTION_COUNT = 0x1003, }; #define IB_FLOW_SPEC_LAYER_MASK 0xF0 #define IB_FLOW_SPEC_SUPPORT_LAYERS 10 enum ib_flow_flags { IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */ IB_FLOW_ATTR_FLAGS_EGRESS = 1UL << 2, /* Egress flow */ IB_FLOW_ATTR_FLAGS_RESERVED = 1UL << 3 /* Must be last */ }; struct ib_flow_eth_filter { u8 dst_mac[6]; u8 src_mac[6]; __be16 ether_type; __be16 vlan_tag; /* Must be last */ u8 real_sz[]; }; struct ib_flow_spec_eth { u32 type; u16 size; struct ib_flow_eth_filter val; struct ib_flow_eth_filter mask; }; struct ib_flow_ib_filter { __be16 dlid; __u8 sl; /* Must be last */ u8 real_sz[]; }; struct ib_flow_spec_ib { u32 type; u16 size; struct ib_flow_ib_filter val; struct ib_flow_ib_filter mask; }; /* IPv4 header flags */ enum ib_ipv4_flags { IB_IPV4_DONT_FRAG = 0x2, /* Don't enable packet fragmentation */ IB_IPV4_MORE_FRAG = 0X4 /* For All fragmented packets except the last have this flag set */ }; struct ib_flow_ipv4_filter { __be32 src_ip; __be32 dst_ip; u8 proto; u8 tos; u8 ttl; u8 flags; /* Must be last */ u8 real_sz[]; }; struct ib_flow_spec_ipv4 { u32 type; u16 size; struct ib_flow_ipv4_filter val; struct ib_flow_ipv4_filter mask; }; struct ib_flow_ipv6_filter { u8 src_ip[16]; u8 dst_ip[16]; __be32 flow_label; u8 next_hdr; u8 traffic_class; u8 hop_limit; /* Must be last */ u8 real_sz[]; }; struct ib_flow_spec_ipv6 { u32 type; u16 size; struct ib_flow_ipv6_filter val; struct ib_flow_ipv6_filter mask; }; struct ib_flow_tcp_udp_filter { __be16 dst_port; __be16 src_port; /* Must be last */ u8 real_sz[]; }; struct ib_flow_spec_tcp_udp { u32 type; u16 size; struct ib_flow_tcp_udp_filter val; struct ib_flow_tcp_udp_filter mask; }; struct ib_flow_tunnel_filter { __be32 tunnel_id; u8 real_sz[]; }; /* ib_flow_spec_tunnel describes the Vxlan tunnel * the tunnel_id from val has the vni value */ struct ib_flow_spec_tunnel { u32 type; u16 size; struct ib_flow_tunnel_filter val; struct ib_flow_tunnel_filter mask; }; struct ib_flow_esp_filter { __be32 spi; __be32 seq; /* Must be last */ u8 real_sz[]; }; struct ib_flow_spec_esp { u32 type; u16 size; struct ib_flow_esp_filter val; struct ib_flow_esp_filter mask; }; struct ib_flow_gre_filter { __be16 c_ks_res0_ver; __be16 protocol; __be32 key; /* Must be last */ u8 real_sz[]; }; struct ib_flow_spec_gre { u32 type; u16 size; struct ib_flow_gre_filter val; struct ib_flow_gre_filter mask; }; struct ib_flow_mpls_filter { __be32 tag; /* Must be last */ u8 real_sz[]; }; struct ib_flow_spec_mpls { u32 type; u16 size; struct ib_flow_mpls_filter val; struct ib_flow_mpls_filter mask; }; struct ib_flow_spec_action_tag { enum ib_flow_spec_type type; u16 size; u32 tag_id; }; struct ib_flow_spec_action_drop { enum ib_flow_spec_type type; u16 size; }; struct ib_flow_spec_action_handle { enum ib_flow_spec_type type; u16 size; struct ib_flow_action *act; }; enum ib_counters_description { IB_COUNTER_PACKETS, IB_COUNTER_BYTES, }; struct ib_flow_spec_action_count { enum ib_flow_spec_type type; u16 size; struct ib_counters *counters; }; union ib_flow_spec { struct { u32 type; u16 size; }; struct ib_flow_spec_eth eth; struct ib_flow_spec_ib ib; struct ib_flow_spec_ipv4 ipv4; struct ib_flow_spec_tcp_udp tcp_udp; struct ib_flow_spec_ipv6 ipv6; struct ib_flow_spec_tunnel tunnel; struct ib_flow_spec_esp esp; struct ib_flow_spec_gre gre; struct ib_flow_spec_mpls mpls; struct ib_flow_spec_action_tag flow_tag; struct ib_flow_spec_action_drop drop; struct ib_flow_spec_action_handle action; struct ib_flow_spec_action_count flow_count; }; struct ib_flow_attr { enum ib_flow_attr_type type; u16 size; u16 priority; u32 flags; u8 num_of_specs; u32 port; union ib_flow_spec flows[]; }; struct ib_flow { struct ib_qp *qp; struct ib_device *device; struct ib_uobject *uobject; }; enum ib_flow_action_type { IB_FLOW_ACTION_UNSPECIFIED, IB_FLOW_ACTION_ESP = 1, }; struct ib_flow_action_attrs_esp_keymats { enum ib_uverbs_flow_action_esp_keymat protocol; union { struct ib_uverbs_flow_action_esp_keymat_aes_gcm aes_gcm; } keymat; }; struct ib_flow_action_attrs_esp_replays { enum ib_uverbs_flow_action_esp_replay protocol; union { struct ib_uverbs_flow_action_esp_replay_bmp bmp; } replay; }; enum ib_flow_action_attrs_esp_flags { /* All user-space flags at the top: Use enum ib_uverbs_flow_action_esp_flags * This is done in order to share the same flags between user-space and * kernel and spare an unnecessary translation. */ /* Kernel flags */ IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED = 1ULL << 32, IB_FLOW_ACTION_ESP_FLAGS_MOD_ESP_ATTRS = 1ULL << 33, }; struct ib_flow_spec_list { struct ib_flow_spec_list *next; union ib_flow_spec spec; }; struct ib_flow_action_attrs_esp { struct ib_flow_action_attrs_esp_keymats *keymat; struct ib_flow_action_attrs_esp_replays *replay; struct ib_flow_spec_list *encap; /* Used only if IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED is enabled. * Value of 0 is a valid value. */ u32 esn; u32 spi; u32 seq; u32 tfc_pad; /* Use enum ib_flow_action_attrs_esp_flags */ u64 flags; u64 hard_limit_pkts; }; struct ib_flow_action { struct ib_device *device; struct ib_uobject *uobject; enum ib_flow_action_type type; atomic_t usecnt; }; struct ib_mad; enum ib_process_mad_flags { IB_MAD_IGNORE_MKEY = 1, IB_MAD_IGNORE_BKEY = 2, IB_MAD_IGNORE_ALL = IB_MAD_IGNORE_MKEY | IB_MAD_IGNORE_BKEY }; enum ib_mad_result { IB_MAD_RESULT_FAILURE = 0, /* (!SUCCESS is the important flag) */ IB_MAD_RESULT_SUCCESS = 1 << 0, /* MAD was successfully processed */ IB_MAD_RESULT_REPLY = 1 << 1, /* Reply packet needs to be sent */ IB_MAD_RESULT_CONSUMED = 1 << 2 /* Packet consumed: stop processing */ }; struct ib_port_cache { u64 subnet_prefix; struct ib_pkey_cache *pkey; struct ib_gid_table *gid; u8 lmc; enum ib_port_state port_state; }; struct ib_port_immutable { int pkey_tbl_len; int gid_tbl_len; u32 core_cap_flags; u32 max_mad_size; }; struct ib_port_data { struct ib_device *ib_dev; struct ib_port_immutable immutable; spinlock_t pkey_list_lock; spinlock_t netdev_lock; struct list_head pkey_list; struct ib_port_cache cache; struct net_device __rcu *netdev; struct hlist_node ndev_hash_link; struct rdma_port_counter port_counter; struct ib_port *sysfs; }; /* rdma netdev type - specifies protocol type */ enum rdma_netdev_t { RDMA_NETDEV_OPA_VNIC, RDMA_NETDEV_IPOIB, }; /** * struct rdma_netdev - rdma netdev * For cases where netstack interfacing is required. */ struct rdma_netdev { void *clnt_priv; struct ib_device *hca; u32 port_num; int mtu; /* * cleanup function must be specified. * FIXME: This is only used for OPA_VNIC and that usage should be * removed too. */ void (*free_rdma_netdev)(struct net_device *netdev); /* control functions */ void (*set_id)(struct net_device *netdev, int id); /* send packet */ int (*send)(struct net_device *dev, struct sk_buff *skb, struct ib_ah *address, u32 dqpn); /* multicast */ int (*attach_mcast)(struct net_device *dev, struct ib_device *hca, union ib_gid *gid, u16 mlid, int set_qkey, u32 qkey); int (*detach_mcast)(struct net_device *dev, struct ib_device *hca, union ib_gid *gid, u16 mlid); /* timeout */ void (*tx_timeout)(struct net_device *dev, unsigned int txqueue); }; struct rdma_netdev_alloc_params { size_t sizeof_priv; unsigned int txqs; unsigned int rxqs; void *param; int (*initialize_rdma_netdev)(struct ib_device *device, u32 port_num, struct net_device *netdev, void *param); }; struct ib_odp_counters { atomic64_t faults; atomic64_t invalidations; atomic64_t prefetch; }; struct ib_counters { struct ib_device *device; struct ib_uobject *uobject; /* num of objects attached */ atomic_t usecnt; }; struct ib_counters_read_attr { u64 *counters_buff; u32 ncounters; u32 flags; /* use enum ib_read_counters_flags */ }; struct uverbs_attr_bundle; struct iw_cm_id; struct iw_cm_conn_param; #define INIT_RDMA_OBJ_SIZE(ib_struct, drv_struct, member) \ .size_##ib_struct = \ (sizeof(struct drv_struct) + \ BUILD_BUG_ON_ZERO(offsetof(struct drv_struct, member)) + \ BUILD_BUG_ON_ZERO( \ !__same_type(((struct drv_struct *)NULL)->member, \ struct ib_struct))) #define rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, gfp) \ ((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \ gfp, false)) #define rdma_zalloc_drv_obj_numa(ib_dev, ib_type) \ ((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \ GFP_KERNEL, true)) #define rdma_zalloc_drv_obj(ib_dev, ib_type) \ rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, GFP_KERNEL) #define DECLARE_RDMA_OBJ_SIZE(ib_struct) size_t size_##ib_struct struct rdma_user_mmap_entry { struct kref ref; struct ib_ucontext *ucontext; unsigned long start_pgoff; size_t npages; bool driver_removed; }; /* Return the offset (in bytes) the user should pass to libc's mmap() */ static inline u64 rdma_user_mmap_get_offset(const struct rdma_user_mmap_entry *entry) { return (u64)entry->start_pgoff << PAGE_SHIFT; } /** * struct ib_device_ops - InfiniBand device operations * This structure defines all the InfiniBand device operations, providers will * need to define the supported operations, otherwise they will be set to null. */ struct ib_device_ops { struct module *owner; enum rdma_driver_id driver_id; u32 uverbs_abi_ver; unsigned int uverbs_no_driver_id_binding:1; /* * NOTE: New drivers should not make use of device_group; instead new * device parameter should be exposed via netlink command. This * mechanism exists only for existing drivers. */ const struct attribute_group *device_group; const struct attribute_group **port_groups; int (*post_send)(struct ib_qp *qp, const struct ib_send_wr *send_wr, const struct ib_send_wr **bad_send_wr); int (*post_recv)(struct ib_qp *qp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr); void (*drain_rq)(struct ib_qp *qp); void (*drain_sq)(struct ib_qp *qp); int (*poll_cq)(struct ib_cq *cq, int num_entries, struct ib_wc *wc); int (*peek_cq)(struct ib_cq *cq, int wc_cnt); int (*req_notify_cq)(struct ib_cq *cq, enum ib_cq_notify_flags flags); int (*post_srq_recv)(struct ib_srq *srq, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr); int (*process_mad)(struct ib_device *device, int process_mad_flags, u32 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh, const struct ib_mad *in_mad, struct ib_mad *out_mad, size_t *out_mad_size, u16 *out_mad_pkey_index); int (*query_device)(struct ib_device *device, struct ib_device_attr *device_attr, struct ib_udata *udata); int (*modify_device)(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify); void (*get_dev_fw_str)(struct ib_device *device, char *str); const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev, int comp_vector); int (*query_port)(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr); int (*modify_port)(struct ib_device *device, u32 port_num, int port_modify_mask, struct ib_port_modify *port_modify); /** * The following mandatory functions are used only at device * registration. Keep functions such as these at the end of this * structure to avoid cache line misses when accessing struct ib_device * in fast paths. */ int (*get_port_immutable)(struct ib_device *device, u32 port_num, struct ib_port_immutable *immutable); enum rdma_link_layer (*get_link_layer)(struct ib_device *device, u32 port_num); /** * When calling get_netdev, the HW vendor's driver should return the * net device of device @device at port @port_num or NULL if such * a net device doesn't exist. The vendor driver should call dev_hold * on this net device. The HW vendor's device driver must guarantee * that this function returns NULL before the net device has finished * NETDEV_UNREGISTER state. */ struct net_device *(*get_netdev)(struct ib_device *device, u32 port_num); /** * rdma netdev operation * * Driver implementing alloc_rdma_netdev or rdma_netdev_get_params * must return -EOPNOTSUPP if it doesn't support the specified type. */ struct net_device *(*alloc_rdma_netdev)( struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *)); int (*rdma_netdev_get_params)(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, struct rdma_netdev_alloc_params *params); /** * query_gid should be return GID value for @device, when @port_num * link layer is either IB or iWarp. It is no-op if @port_num port * is RoCE link layer. */ int (*query_gid)(struct ib_device *device, u32 port_num, int index, union ib_gid *gid); /** * When calling add_gid, the HW vendor's driver should add the gid * of device of port at gid index available at @attr. Meta-info of * that gid (for example, the network device related to this gid) is * available at @attr. @context allows the HW vendor driver to store * extra information together with a GID entry. The HW vendor driver may * allocate memory to contain this information and store it in @context * when a new GID entry is written to. Params are consistent until the * next call of add_gid or delete_gid. The function should return 0 on * success or error otherwise. The function could be called * concurrently for different ports. This function is only called when * roce_gid_table is used. */ int (*add_gid)(const struct ib_gid_attr *attr, void **context); /** * When calling del_gid, the HW vendor's driver should delete the * gid of device @device at gid index gid_index of port port_num * available in @attr. * Upon the deletion of a GID entry, the HW vendor must free any * allocated memory. The caller will clear @context afterwards. * This function is only called when roce_gid_table is used. */ int (*del_gid)(const struct ib_gid_attr *attr, void **context); int (*query_pkey)(struct ib_device *device, u32 port_num, u16 index, u16 *pkey); int (*alloc_ucontext)(struct ib_ucontext *context, struct ib_udata *udata); void (*dealloc_ucontext)(struct ib_ucontext *context); int (*mmap)(struct ib_ucontext *context, struct vm_area_struct *vma); /** * This will be called once refcount of an entry in mmap_xa reaches * zero. The type of the memory that was mapped may differ between * entries and is opaque to the rdma_user_mmap interface. * Therefore needs to be implemented by the driver in mmap_free. */ void (*mmap_free)(struct rdma_user_mmap_entry *entry); void (*disassociate_ucontext)(struct ib_ucontext *ibcontext); int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata); int (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata); int (*create_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr, struct ib_udata *udata); int (*create_user_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr, struct ib_udata *udata); int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*destroy_ah)(struct ib_ah *ah, u32 flags); int (*create_srq)(struct ib_srq *srq, struct ib_srq_init_attr *srq_init_attr, struct ib_udata *udata); int (*modify_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr, enum ib_srq_attr_mask srq_attr_mask, struct ib_udata *udata); int (*query_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr); int (*destroy_srq)(struct ib_srq *srq, struct ib_udata *udata); int (*create_qp)(struct ib_qp *qp, struct ib_qp_init_attr *qp_init_attr, struct ib_udata *udata); int (*modify_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_udata *udata); int (*query_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); int (*destroy_qp)(struct ib_qp *qp, struct ib_udata *udata); int (*create_cq)(struct ib_cq *cq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period); int (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata); int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata); struct ib_mr *(*get_dma_mr)(struct ib_pd *pd, int mr_access_flags); struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_udata *udata); struct ib_mr *(*reg_user_mr_dmabuf)(struct ib_pd *pd, u64 offset, u64 length, u64 virt_addr, int fd, int mr_access_flags, struct ib_udata *udata); struct ib_mr *(*rereg_user_mr)(struct ib_mr *mr, int flags, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_pd *pd, struct ib_udata *udata); int (*dereg_mr)(struct ib_mr *mr, struct ib_udata *udata); struct ib_mr *(*alloc_mr)(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg); struct ib_mr *(*alloc_mr_integrity)(struct ib_pd *pd, u32 max_num_data_sg, u32 max_num_meta_sg); int (*advise_mr)(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge, struct uverbs_attr_bundle *attrs); /* * Kernel users should universally support relaxed ordering (RO), as * they are designed to read data only after observing the CQE and use * the DMA API correctly. * * Some drivers implicitly enable RO if platform supports it. */ int (*map_mr_sg)(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset); int (*check_mr_status)(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); int (*alloc_mw)(struct ib_mw *mw, struct ib_udata *udata); int (*dealloc_mw)(struct ib_mw *mw); int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*alloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); int (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); struct ib_flow *(*create_flow)(struct ib_qp *qp, struct ib_flow_attr *flow_attr, struct ib_udata *udata); int (*destroy_flow)(struct ib_flow *flow_id); int (*destroy_flow_action)(struct ib_flow_action *action); int (*set_vf_link_state)(struct ib_device *device, int vf, u32 port, int state); int (*get_vf_config)(struct ib_device *device, int vf, u32 port, struct ifla_vf_info *ivf); int (*get_vf_stats)(struct ib_device *device, int vf, u32 port, struct ifla_vf_stats *stats); int (*get_vf_guid)(struct ib_device *device, int vf, u32 port, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid); int (*set_vf_guid)(struct ib_device *device, int vf, u32 port, u64 guid, int type); struct ib_wq *(*create_wq)(struct ib_pd *pd, struct ib_wq_init_attr *init_attr, struct ib_udata *udata); int (*destroy_wq)(struct ib_wq *wq, struct ib_udata *udata); int (*modify_wq)(struct ib_wq *wq, struct ib_wq_attr *attr, u32 wq_attr_mask, struct ib_udata *udata); int (*create_rwq_ind_table)(struct ib_rwq_ind_table *ib_rwq_ind_table, struct ib_rwq_ind_table_init_attr *init_attr, struct ib_udata *udata); int (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table); struct ib_dm *(*alloc_dm)(struct ib_device *device, struct ib_ucontext *context, struct ib_dm_alloc_attr *attr, struct uverbs_attr_bundle *attrs); int (*dealloc_dm)(struct ib_dm *dm, struct uverbs_attr_bundle *attrs); struct ib_mr *(*reg_dm_mr)(struct ib_pd *pd, struct ib_dm *dm, struct ib_dm_mr_attr *attr, struct uverbs_attr_bundle *attrs); int (*create_counters)(struct ib_counters *counters, struct uverbs_attr_bundle *attrs); int (*destroy_counters)(struct ib_counters *counters); int (*read_counters)(struct ib_counters *counters, struct ib_counters_read_attr *counters_read_attr, struct uverbs_attr_bundle *attrs); int (*map_mr_sg_pi)(struct ib_mr *mr, struct scatterlist *data_sg, int data_sg_nents, unsigned int *data_sg_offset, struct scatterlist *meta_sg, int meta_sg_nents, unsigned int *meta_sg_offset); /** * alloc_hw_[device,port]_stats - Allocate a struct rdma_hw_stats and * fill in the driver initialized data. The struct is kfree()'ed by * the sysfs core when the device is removed. A lifespan of -1 in the * return struct tells the core to set a default lifespan. */ struct rdma_hw_stats *(*alloc_hw_device_stats)(struct ib_device *device); struct rdma_hw_stats *(*alloc_hw_port_stats)(struct ib_device *device, u32 port_num); /** * get_hw_stats - Fill in the counter value(s) in the stats struct. * @index - The index in the value array we wish to have updated, or * num_counters if we want all stats updated * Return codes - * < 0 - Error, no counters updated * index - Updated the single counter pointed to by index * num_counters - Updated all counters (will reset the timestamp * and prevent further calls for lifespan milliseconds) * Drivers are allowed to update all counters in leiu of just the * one given in index at their option */ int (*get_hw_stats)(struct ib_device *device, struct rdma_hw_stats *stats, u32 port, int index); /** * modify_hw_stat - Modify the counter configuration * @enable: true/false when enable/disable a counter * Return codes - 0 on success or error code otherwise. */ int (*modify_hw_stat)(struct ib_device *device, u32 port, unsigned int counter_index, bool enable); /** * Allows rdma drivers to add their own restrack attributes. */ int (*fill_res_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr); int (*fill_res_mr_entry_raw)(struct sk_buff *msg, struct ib_mr *ibmr); int (*fill_res_cq_entry)(struct sk_buff *msg, struct ib_cq *ibcq); int (*fill_res_cq_entry_raw)(struct sk_buff *msg, struct ib_cq *ibcq); int (*fill_res_qp_entry)(struct sk_buff *msg, struct ib_qp *ibqp); int (*fill_res_qp_entry_raw)(struct sk_buff *msg, struct ib_qp *ibqp); int (*fill_res_cm_id_entry)(struct sk_buff *msg, struct rdma_cm_id *id); /* Device lifecycle callbacks */ /* * Called after the device becomes registered, before clients are * attached */ int (*enable_driver)(struct ib_device *dev); /* * This is called as part of ib_dealloc_device(). */ void (*dealloc_driver)(struct ib_device *dev); /* iWarp CM callbacks */ void (*iw_add_ref)(struct ib_qp *qp); void (*iw_rem_ref)(struct ib_qp *qp); struct ib_qp *(*iw_get_qp)(struct ib_device *device, int qpn); int (*iw_connect)(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param); int (*iw_accept)(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param); int (*iw_reject)(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len); int (*iw_create_listen)(struct iw_cm_id *cm_id, int backlog); int (*iw_destroy_listen)(struct iw_cm_id *cm_id); /** * counter_bind_qp - Bind a QP to a counter. * @counter - The counter to be bound. If counter->id is zero then * the driver needs to allocate a new counter and set counter->id */ int (*counter_bind_qp)(struct rdma_counter *counter, struct ib_qp *qp); /** * counter_unbind_qp - Unbind the qp from the dynamically-allocated * counter and bind it onto the default one */ int (*counter_unbind_qp)(struct ib_qp *qp); /** * counter_dealloc -De-allocate the hw counter */ int (*counter_dealloc)(struct rdma_counter *counter); /** * counter_alloc_stats - Allocate a struct rdma_hw_stats and fill in * the driver initialized data. */ struct rdma_hw_stats *(*counter_alloc_stats)( struct rdma_counter *counter); /** * counter_update_stats - Query the stats value of this counter */ int (*counter_update_stats)(struct rdma_counter *counter); /** * Allows rdma drivers to add their own restrack attributes * dumped via 'rdma stat' iproute2 command. */ int (*fill_stat_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr); /* query driver for its ucontext properties */ int (*query_ucontext)(struct ib_ucontext *context, struct uverbs_attr_bundle *attrs); /* * Provide NUMA node. This API exists for rdmavt/hfi1 only. * Everyone else relies on Linux memory management model. */ int (*get_numa_node)(struct ib_device *dev); DECLARE_RDMA_OBJ_SIZE(ib_ah); DECLARE_RDMA_OBJ_SIZE(ib_counters); DECLARE_RDMA_OBJ_SIZE(ib_cq); DECLARE_RDMA_OBJ_SIZE(ib_mw); DECLARE_RDMA_OBJ_SIZE(ib_pd); DECLARE_RDMA_OBJ_SIZE(ib_qp); DECLARE_RDMA_OBJ_SIZE(ib_rwq_ind_table); DECLARE_RDMA_OBJ_SIZE(ib_srq); DECLARE_RDMA_OBJ_SIZE(ib_ucontext); DECLARE_RDMA_OBJ_SIZE(ib_xrcd); }; struct ib_core_device { /* device must be the first element in structure until, * union of ib_core_device and device exists in ib_device. */ struct device dev; possible_net_t rdma_net; struct kobject *ports_kobj; struct list_head port_list; struct ib_device *owner; /* reach back to owner ib_device */ }; struct rdma_restrack_root; struct ib_device { /* Do not access @dma_device directly from ULP nor from HW drivers. */ struct device *dma_device; struct ib_device_ops ops; char name[IB_DEVICE_NAME_MAX]; struct rcu_head rcu_head; struct list_head event_handler_list; /* Protects event_handler_list */ struct rw_semaphore event_handler_rwsem; /* Protects QP's event_handler calls and open_qp list */ spinlock_t qp_open_list_lock; struct rw_semaphore client_data_rwsem; struct xarray client_data; struct mutex unregistration_lock; /* Synchronize GID, Pkey cache entries, subnet prefix, LMC */ rwlock_t cache_lock; /** * port_data is indexed by port number */ struct ib_port_data *port_data; int num_comp_vectors; union { struct device dev; struct ib_core_device coredev; }; /* First group is for device attributes, * Second group is for driver provided attributes (optional). * Third group is for the hw_stats * It is a NULL terminated array. */ const struct attribute_group *groups[4]; u64 uverbs_cmd_mask; char node_desc[IB_DEVICE_NODE_DESC_MAX]; __be64 node_guid; u32 local_dma_lkey; u16 is_switch:1; /* Indicates kernel verbs support, should not be used in drivers */ u16 kverbs_provider:1; /* CQ adaptive moderation (RDMA DIM) */ u16 use_cq_dim:1; u8 node_type; u32 phys_port_cnt; struct ib_device_attr attrs; struct hw_stats_device_data *hw_stats_data; #ifdef CONFIG_CGROUP_RDMA struct rdmacg_device cg_device; #endif u32 index; spinlock_t cq_pools_lock; struct list_head cq_pools[IB_POLL_LAST_POOL_TYPE + 1]; struct rdma_restrack_root *res; const struct uapi_definition *driver_def; /* * Positive refcount indicates that the device is currently * registered and cannot be unregistered. */ refcount_t refcount; struct completion unreg_completion; struct work_struct unregistration_work; const struct rdma_link_ops *link_ops; /* Protects compat_devs xarray modifications */ struct mutex compat_devs_mutex; /* Maintains compat devices for each net namespace */ struct xarray compat_devs; /* Used by iWarp CM */ char iw_ifname[IFNAMSIZ]; u32 iw_driver_flags; u32 lag_flags; }; static inline void *rdma_zalloc_obj(struct ib_device *dev, size_t size, gfp_t gfp, bool is_numa_aware) { if (is_numa_aware && dev->ops.get_numa_node) return kzalloc_node(size, gfp, dev->ops.get_numa_node(dev)); return kzalloc(size, gfp); } struct ib_client_nl_info; struct ib_client { const char *name; int (*add)(struct ib_device *ibdev); void (*remove)(struct ib_device *, void *client_data); void (*rename)(struct ib_device *dev, void *client_data); int (*get_nl_info)(struct ib_device *ibdev, void *client_data, struct ib_client_nl_info *res); int (*get_global_nl_info)(struct ib_client_nl_info *res); /* Returns the net_dev belonging to this ib_client and matching the * given parameters. * @dev: An RDMA device that the net_dev use for communication. * @port: A physical port number on the RDMA device. * @pkey: P_Key that the net_dev uses if applicable. * @gid: A GID that the net_dev uses to communicate. * @addr: An IP address the net_dev is configured with. * @client_data: The device's client data set by ib_set_client_data(). * * An ib_client that implements a net_dev on top of RDMA devices * (such as IP over IB) should implement this callback, allowing the * rdma_cm module to find the right net_dev for a given request. * * The caller is responsible for calling dev_put on the returned * netdev. */ struct net_device *(*get_net_dev_by_params)( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data); refcount_t uses; struct completion uses_zero; u32 client_id; /* kverbs are not required by the client */ u8 no_kverbs_req:1; }; /* * IB block DMA iterator * * Iterates the DMA-mapped SGL in contiguous memory blocks aligned * to a HW supported page size. */ struct ib_block_iter { /* internal states */ struct scatterlist *__sg; /* sg holding the current aligned block */ dma_addr_t __dma_addr; /* unaligned DMA address of this block */ unsigned int __sg_nents; /* number of SG entries */ unsigned int __sg_advance; /* number of bytes to advance in sg in next step */ unsigned int __pg_bit; /* alignment of current block */ }; struct ib_device *_ib_alloc_device(size_t size); #define ib_alloc_device(drv_struct, member) \ container_of(_ib_alloc_device(sizeof(struct drv_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ struct drv_struct, member))), \ struct drv_struct, member) void ib_dealloc_device(struct ib_device *device); void ib_get_device_fw_str(struct ib_device *device, char *str); int ib_register_device(struct ib_device *device, const char *name, struct device *dma_device); void ib_unregister_device(struct ib_device *device); void ib_unregister_driver(enum rdma_driver_id driver_id); void ib_unregister_device_and_put(struct ib_device *device); void ib_unregister_device_queued(struct ib_device *ib_dev); int ib_register_client (struct ib_client *client); void ib_unregister_client(struct ib_client *client); void __rdma_block_iter_start(struct ib_block_iter *biter, struct scatterlist *sglist, unsigned int nents, unsigned long pgsz); bool __rdma_block_iter_next(struct ib_block_iter *biter); /** * rdma_block_iter_dma_address - get the aligned dma address of the current * block held by the block iterator. * @biter: block iterator holding the memory block */ static inline dma_addr_t rdma_block_iter_dma_address(struct ib_block_iter *biter) { return biter->__dma_addr & ~(BIT_ULL(biter->__pg_bit) - 1); } /** * rdma_for_each_block - iterate over contiguous memory blocks of the sg list * @sglist: sglist to iterate over * @biter: block iterator holding the memory block * @nents: maximum number of sg entries to iterate over * @pgsz: best HW supported page size to use * * Callers may use rdma_block_iter_dma_address() to get each * blocks aligned DMA address. */ #define rdma_for_each_block(sglist, biter, nents, pgsz) \ for (__rdma_block_iter_start(biter, sglist, nents, \ pgsz); \ __rdma_block_iter_next(biter);) /** * ib_get_client_data - Get IB client context * @device:Device to get context for * @client:Client to get context for * * ib_get_client_data() returns the client context data set with * ib_set_client_data(). This can only be called while the client is * registered to the device, once the ib_client remove() callback returns this * cannot be called. */ static inline void *ib_get_client_data(struct ib_device *device, struct ib_client *client) { return xa_load(&device->client_data, client->client_id); } void ib_set_client_data(struct ib_device *device, struct ib_client *client, void *data); void ib_set_device_ops(struct ib_device *device, const struct ib_device_ops *ops); int rdma_user_mmap_io(struct ib_ucontext *ucontext, struct vm_area_struct *vma, unsigned long pfn, unsigned long size, pgprot_t prot, struct rdma_user_mmap_entry *entry); int rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length); int rdma_user_mmap_entry_insert_range(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length, u32 min_pgoff, u32 max_pgoff); static inline int rdma_user_mmap_entry_insert_exact(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length, u32 pgoff) { return rdma_user_mmap_entry_insert_range(ucontext, entry, length, pgoff, pgoff); } struct rdma_user_mmap_entry * rdma_user_mmap_entry_get_pgoff(struct ib_ucontext *ucontext, unsigned long pgoff); struct rdma_user_mmap_entry * rdma_user_mmap_entry_get(struct ib_ucontext *ucontext, struct vm_area_struct *vma); void rdma_user_mmap_entry_put(struct rdma_user_mmap_entry *entry); void rdma_user_mmap_entry_remove(struct rdma_user_mmap_entry *entry); static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t len) { return copy_from_user(dest, udata->inbuf, len) ? -EFAULT : 0; } static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len) { return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0; } static inline bool ib_is_buffer_cleared(const void __user *p, size_t len) { bool ret; u8 *buf; if (len > USHRT_MAX) return false; buf = memdup_user(p, len); if (IS_ERR(buf)) return false; ret = !memchr_inv(buf, 0, len); kfree(buf); return ret; } static inline bool ib_is_udata_cleared(struct ib_udata *udata, size_t offset, size_t len) { return ib_is_buffer_cleared(udata->inbuf + offset, len); } /** * ib_modify_qp_is_ok - Check that the supplied attribute mask * contains all required attributes and no attributes not allowed for * the given QP state transition. * @cur_state: Current QP state * @next_state: Next QP state * @type: QP type * @mask: Mask of supplied QP attributes * * This function is a helper function that a low-level driver's * modify_qp method can use to validate the consumer's input. It * checks that cur_state and next_state are valid QP states, that a * transition from cur_state to next_state is allowed by the IB spec, * and that the attribute mask supplied is allowed for the transition. */ bool ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state, enum ib_qp_type type, enum ib_qp_attr_mask mask); void ib_register_event_handler(struct ib_event_handler *event_handler); void ib_unregister_event_handler(struct ib_event_handler *event_handler); void ib_dispatch_event(const struct ib_event *event); int ib_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr); enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u32 port_num); /** * rdma_cap_ib_switch - Check if the device is IB switch * @device: Device to check * * Device driver is responsible for setting is_switch bit on * in ib_device structure at init time. * * Return: true if the device is IB switch. */ static inline bool rdma_cap_ib_switch(const struct ib_device *device) { return device->is_switch; } /** * rdma_start_port - Return the first valid port number for the device * specified * * @device: Device to be checked * * Return start port number */ static inline u32 rdma_start_port(const struct ib_device *device) { return rdma_cap_ib_switch(device) ? 0 : 1; } /** * rdma_for_each_port - Iterate over all valid port numbers of the IB device * @device - The struct ib_device * to iterate over * @iter - The unsigned int to store the port number */ #define rdma_for_each_port(device, iter) \ for (iter = rdma_start_port(device + \ BUILD_BUG_ON_ZERO(!__same_type(u32, \ iter))); \ iter <= rdma_end_port(device); iter++) /** * rdma_end_port - Return the last valid port number for the device * specified * * @device: Device to be checked * * Return last port number */ static inline u32 rdma_end_port(const struct ib_device *device) { return rdma_cap_ib_switch(device) ? 0 : device->phys_port_cnt; } static inline int rdma_is_port_valid(const struct ib_device *device, unsigned int port) { return (port >= rdma_start_port(device) && port <= rdma_end_port(device)); } static inline bool rdma_is_grh_required(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_PORT_IB_GRH_REQUIRED; } static inline bool rdma_protocol_ib(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_IB; } static inline bool rdma_protocol_roce(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & (RDMA_CORE_CAP_PROT_ROCE | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP); } static inline bool rdma_protocol_roce_udp_encap(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP; } static inline bool rdma_protocol_roce_eth_encap(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_ROCE; } static inline bool rdma_protocol_iwarp(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_IWARP; } static inline bool rdma_ib_or_roce(const struct ib_device *device, u32 port_num) { return rdma_protocol_ib(device, port_num) || rdma_protocol_roce(device, port_num); } static inline bool rdma_protocol_raw_packet(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_RAW_PACKET; } static inline bool rdma_protocol_usnic(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_USNIC; } /** * rdma_cap_ib_mad - Check if the port of a device supports Infiniband * Management Datagrams. * @device: Device to check * @port_num: Port number to check * * Management Datagrams (MAD) are a required part of the InfiniBand * specification and are supported on all InfiniBand devices. A slightly * extended version are also supported on OPA interfaces. * * Return: true if the port supports sending/receiving of MAD packets. */ static inline bool rdma_cap_ib_mad(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_MAD; } /** * rdma_cap_opa_mad - Check if the port of device provides support for OPA * Management Datagrams. * @device: Device to check * @port_num: Port number to check * * Intel OmniPath devices extend and/or replace the InfiniBand Management * datagrams with their own versions. These OPA MADs share many but not all of * the characteristics of InfiniBand MADs. * * OPA MADs differ in the following ways: * * 1) MADs are variable size up to 2K * IBTA defined MADs remain fixed at 256 bytes * 2) OPA SMPs must carry valid PKeys * 3) OPA SMP packets are a different format * * Return: true if the port supports OPA MAD packet formats. */ static inline bool rdma_cap_opa_mad(struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_OPA_MAD; } /** * rdma_cap_ib_smi - Check if the port of a device provides an Infiniband * Subnet Management Agent (SMA) on the Subnet Management Interface (SMI). * @device: Device to check * @port_num: Port number to check * * Each InfiniBand node is required to provide a Subnet Management Agent * that the subnet manager can access. Prior to the fabric being fully * configured by the subnet manager, the SMA is accessed via a well known * interface called the Subnet Management Interface (SMI). This interface * uses directed route packets to communicate with the SM to get around the * chicken and egg problem of the SM needing to know what's on the fabric * in order to configure the fabric, and needing to configure the fabric in * order to send packets to the devices on the fabric. These directed * route packets do not need the fabric fully configured in order to reach * their destination. The SMI is the only method allowed to send * directed route packets on an InfiniBand fabric. * * Return: true if the port provides an SMI. */ static inline bool rdma_cap_ib_smi(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_SMI; } /** * rdma_cap_ib_cm - Check if the port of device has the capability Infiniband * Communication Manager. * @device: Device to check * @port_num: Port number to check * * The InfiniBand Communication Manager is one of many pre-defined General * Service Agents (GSA) that are accessed via the General Service * Interface (GSI). It's role is to facilitate establishment of connections * between nodes as well as other management related tasks for established * connections. * * Return: true if the port supports an IB CM (this does not guarantee that * a CM is actually running however). */ static inline bool rdma_cap_ib_cm(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_CM; } /** * rdma_cap_iw_cm - Check if the port of device has the capability IWARP * Communication Manager. * @device: Device to check * @port_num: Port number to check * * Similar to above, but specific to iWARP connections which have a different * managment protocol than InfiniBand. * * Return: true if the port supports an iWARP CM (this does not guarantee that * a CM is actually running however). */ static inline bool rdma_cap_iw_cm(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IW_CM; } /** * rdma_cap_ib_sa - Check if the port of device has the capability Infiniband * Subnet Administration. * @device: Device to check * @port_num: Port number to check * * An InfiniBand Subnet Administration (SA) service is a pre-defined General * Service Agent (GSA) provided by the Subnet Manager (SM). On InfiniBand * fabrics, devices should resolve routes to other hosts by contacting the * SA to query the proper route. * * Return: true if the port should act as a client to the fabric Subnet * Administration interface. This does not imply that the SA service is * running locally. */ static inline bool rdma_cap_ib_sa(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_SA; } /** * rdma_cap_ib_mcast - Check if the port of device has the capability Infiniband * Multicast. * @device: Device to check * @port_num: Port number to check * * InfiniBand multicast registration is more complex than normal IPv4 or * IPv6 multicast registration. Each Host Channel Adapter must register * with the Subnet Manager when it wishes to join a multicast group. It * should do so only once regardless of how many queue pairs it subscribes * to this group. And it should leave the group only after all queue pairs * attached to the group have been detached. * * Return: true if the port must undertake the additional adminstrative * overhead of registering/unregistering with the SM and tracking of the * total number of queue pairs attached to the multicast group. */ static inline bool rdma_cap_ib_mcast(const struct ib_device *device, u32 port_num) { return rdma_cap_ib_sa(device, port_num); } /** * rdma_cap_af_ib - Check if the port of device has the capability * Native Infiniband Address. * @device: Device to check * @port_num: Port number to check * * InfiniBand addressing uses a port's GUID + Subnet Prefix to make a default * GID. RoCE uses a different mechanism, but still generates a GID via * a prescribed mechanism and port specific data. * * Return: true if the port uses a GID address to identify devices on the * network. */ static inline bool rdma_cap_af_ib(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_AF_IB; } /** * rdma_cap_eth_ah - Check if the port of device has the capability * Ethernet Address Handle. * @device: Device to check * @port_num: Port number to check * * RoCE is InfiniBand over Ethernet, and it uses a well defined technique * to fabricate GIDs over Ethernet/IP specific addresses native to the * port. Normally, packet headers are generated by the sending host * adapter, but when sending connectionless datagrams, we must manually * inject the proper headers for the fabric we are communicating over. * * Return: true if we are running as a RoCE port and must force the * addition of a Global Route Header built from our Ethernet Address * Handle into our header list for connectionless packets. */ static inline bool rdma_cap_eth_ah(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_ETH_AH; } /** * rdma_cap_opa_ah - Check if the port of device supports * OPA Address handles * @device: Device to check * @port_num: Port number to check * * Return: true if we are running on an OPA device which supports * the extended OPA addressing. */ static inline bool rdma_cap_opa_ah(struct ib_device *device, u32 port_num) { return (device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_OPA_AH) == RDMA_CORE_CAP_OPA_AH; } /** * rdma_max_mad_size - Return the max MAD size required by this RDMA Port. * * @device: Device * @port_num: Port number * * This MAD size includes the MAD headers and MAD payload. No other headers * are included. * * Return the max MAD size required by the Port. Will return 0 if the port * does not support MADs */ static inline size_t rdma_max_mad_size(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.max_mad_size; } /** * rdma_cap_roce_gid_table - Check if the port of device uses roce_gid_table * @device: Device to check * @port_num: Port number to check * * RoCE GID table mechanism manages the various GIDs for a device. * * NOTE: if allocating the port's GID table has failed, this call will still * return true, but any RoCE GID table API will fail. * * Return: true if the port uses RoCE GID table mechanism in order to manage * its GIDs. */ static inline bool rdma_cap_roce_gid_table(const struct ib_device *device, u32 port_num) { return rdma_protocol_roce(device, port_num) && device->ops.add_gid && device->ops.del_gid; } /* * Check if the device supports READ W/ INVALIDATE. */ static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num) { /* * iWarp drivers must support READ W/ INVALIDATE. No other protocol * has support for it yet. */ return rdma_protocol_iwarp(dev, port_num); } /** * rdma_core_cap_opa_port - Return whether the RDMA Port is OPA or not. * @device: Device * @port_num: 1 based Port number * * Return true if port is an Intel OPA port , false if not */ static inline bool rdma_core_cap_opa_port(struct ib_device *device, u32 port_num) { return (device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_PORT_INTEL_OPA) == RDMA_CORE_PORT_INTEL_OPA; } /** * rdma_mtu_enum_to_int - Return the mtu of the port as an integer value. * @device: Device * @port_num: Port number * @mtu: enum value of MTU * * Return the MTU size supported by the port as an integer value. Will return * -1 if enum value of mtu is not supported. */ static inline int rdma_mtu_enum_to_int(struct ib_device *device, u32 port, int mtu) { if (rdma_core_cap_opa_port(device, port)) return opa_mtu_enum_to_int((enum opa_mtu)mtu); else return ib_mtu_enum_to_int((enum ib_mtu)mtu); } /** * rdma_mtu_from_attr - Return the mtu of the port from the port attribute. * @device: Device * @port_num: Port number * @attr: port attribute * * Return the MTU size supported by the port as an integer value. */ static inline int rdma_mtu_from_attr(struct ib_device *device, u32 port, struct ib_port_attr *attr) { if (rdma_core_cap_opa_port(device, port)) return attr->phys_mtu; else return ib_mtu_enum_to_int(attr->max_mtu); } int ib_set_vf_link_state(struct ib_device *device, int vf, u32 port, int state); int ib_get_vf_config(struct ib_device *device, int vf, u32 port, struct ifla_vf_info *info); int ib_get_vf_stats(struct ib_device *device, int vf, u32 port, struct ifla_vf_stats *stats); int ib_get_vf_guid(struct ib_device *device, int vf, u32 port, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid); int ib_set_vf_guid(struct ib_device *device, int vf, u32 port, u64 guid, int type); int ib_query_pkey(struct ib_device *device, u32 port_num, u16 index, u16 *pkey); int ib_modify_device(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify); int ib_modify_port(struct ib_device *device, u32 port_num, int port_modify_mask, struct ib_port_modify *port_modify); int ib_find_gid(struct ib_device *device, union ib_gid *gid, u32 *port_num, u16 *index); int ib_find_pkey(struct ib_device *device, u32 port_num, u16 pkey, u16 *index); enum ib_pd_flags { /* * Create a memory registration for all memory in the system and place * the rkey for it into pd->unsafe_global_rkey. This can be used by * ULPs to avoid the overhead of dynamic MRs. * * This flag is generally considered unsafe and must only be used in * extremly trusted environments. Every use of it will log a warning * in the kernel log. */ IB_PD_UNSAFE_GLOBAL_RKEY = 0x01, }; struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags, const char *caller); /** * ib_alloc_pd - Allocates an unused protection domain. * @device: The device on which to allocate the protection domain. * @flags: protection domain flags * * A protection domain object provides an association between QPs, shared * receive queues, address handles, memory regions, and memory windows. * * Every PD has a local_dma_lkey which can be used as the lkey value for local * memory operations. */ #define ib_alloc_pd(device, flags) \ __ib_alloc_pd((device), (flags), KBUILD_MODNAME) int ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata); /** * ib_dealloc_pd - Deallocate kernel PD * @pd: The protection domain * * NOTE: for user PD use ib_dealloc_pd_user with valid udata! */ static inline void ib_dealloc_pd(struct ib_pd *pd) { int ret = ib_dealloc_pd_user(pd, NULL); WARN_ONCE(ret, "Destroy of kernel PD shouldn't fail"); } enum rdma_create_ah_flags { /* In a sleepable context */ RDMA_CREATE_AH_SLEEPABLE = BIT(0), }; /** * rdma_create_ah - Creates an address handle for the given address vector. * @pd: The protection domain associated with the address handle. * @ah_attr: The attributes of the address vector. * @flags: Create address handle flags (see enum rdma_create_ah_flags). * * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, u32 flags); /** * rdma_create_user_ah - Creates an address handle for the given address vector. * It resolves destination mac address for ah attribute of RoCE type. * @pd: The protection domain associated with the address handle. * @ah_attr: The attributes of the address vector. * @udata: pointer to user's input output buffer information need by * provider driver. * * It returns 0 on success and returns appropriate error code on error. * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *rdma_create_user_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, struct ib_udata *udata); /** * ib_get_gids_from_rdma_hdr - Get sgid and dgid from GRH or IPv4 header * work completion. * @hdr: the L3 header to parse * @net_type: type of header to parse * @sgid: place to store source gid * @dgid: place to store destination gid */ int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr, enum rdma_network_type net_type, union ib_gid *sgid, union ib_gid *dgid); /** * ib_get_rdma_header_version - Get the header version * @hdr: the L3 header to parse */ int ib_get_rdma_header_version(const union rdma_network_hdr *hdr); /** * ib_init_ah_attr_from_wc - Initializes address handle attributes from a * work completion. * @device: Device on which the received message arrived. * @port_num: Port on which the received message arrived. * @wc: Work completion associated with the received message. * @grh: References the received global route header. This parameter is * ignored unless the work completion indicates that the GRH is valid. * @ah_attr: Returned attributes that can be used when creating an address * handle for replying to the message. * When ib_init_ah_attr_from_wc() returns success, * (a) for IB link layer it optionally contains a reference to SGID attribute * when GRH is present for IB link layer. * (b) for RoCE link layer it contains a reference to SGID attribute. * User must invoke rdma_cleanup_ah_attr_gid_attr() to release reference to SGID * attributes which are initialized using ib_init_ah_attr_from_wc(). * */ int ib_init_ah_attr_from_wc(struct ib_device *device, u32 port_num, const struct ib_wc *wc, const struct ib_grh *grh, struct rdma_ah_attr *ah_attr); /** * ib_create_ah_from_wc - Creates an address handle associated with the * sender of the specified work completion. * @pd: The protection domain associated with the address handle. * @wc: Work completion information associated with a received message. * @grh: References the received global route header. This parameter is * ignored unless the work completion indicates that the GRH is valid. * @port_num: The outbound port number to associate with the address. * * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc, const struct ib_grh *grh, u32 port_num); /** * rdma_modify_ah - Modifies the address vector associated with an address * handle. * @ah: The address handle to modify. * @ah_attr: The new address vector attributes to associate with the * address handle. */ int rdma_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); /** * rdma_query_ah - Queries the address vector associated with an address * handle. * @ah: The address handle to query. * @ah_attr: The address vector attributes associated with the address * handle. */ int rdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); enum rdma_destroy_ah_flags { /* In a sleepable context */ RDMA_DESTROY_AH_SLEEPABLE = BIT(0), }; /** * rdma_destroy_ah_user - Destroys an address handle. * @ah: The address handle to destroy. * @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags). * @udata: Valid user data or NULL for kernel objects */ int rdma_destroy_ah_user(struct ib_ah *ah, u32 flags, struct ib_udata *udata); /** * rdma_destroy_ah - Destroys an kernel address handle. * @ah: The address handle to destroy. * @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags). * * NOTE: for user ah use rdma_destroy_ah_user with valid udata! */ static inline void rdma_destroy_ah(struct ib_ah *ah, u32 flags) { int ret = rdma_destroy_ah_user(ah, flags, NULL); WARN_ONCE(ret, "Destroy of kernel AH shouldn't fail"); } struct ib_srq *ib_create_srq_user(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr, struct ib_usrq_object *uobject, struct ib_udata *udata); static inline struct ib_srq * ib_create_srq(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr) { if (!pd->device->ops.create_srq) return ERR_PTR(-EOPNOTSUPP); return ib_create_srq_user(pd, srq_init_attr, NULL, NULL); } /** * ib_modify_srq - Modifies the attributes for the specified SRQ. * @srq: The SRQ to modify. * @srq_attr: On input, specifies the SRQ attributes to modify. On output, * the current values of selected SRQ attributes are returned. * @srq_attr_mask: A bit-mask used to specify which attributes of the SRQ * are being modified. * * The mask may contain IB_SRQ_MAX_WR to resize the SRQ and/or * IB_SRQ_LIMIT to set the SRQ's limit and request notification when * the number of receives queued drops below the limit. */ int ib_modify_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr, enum ib_srq_attr_mask srq_attr_mask); /** * ib_query_srq - Returns the attribute list and current values for the * specified SRQ. * @srq: The SRQ to query. * @srq_attr: The attributes of the specified SRQ. */ int ib_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr); /** * ib_destroy_srq_user - Destroys the specified SRQ. * @srq: The SRQ to destroy. * @udata: Valid user data or NULL for kernel objects */ int ib_destroy_srq_user(struct ib_srq *srq, struct ib_udata *udata); /** * ib_destroy_srq - Destroys the specified kernel SRQ. * @srq: The SRQ to destroy. * * NOTE: for user srq use ib_destroy_srq_user with valid udata! */ static inline void ib_destroy_srq(struct ib_srq *srq) { int ret = ib_destroy_srq_user(srq, NULL); WARN_ONCE(ret, "Destroy of kernel SRQ shouldn't fail"); } /** * ib_post_srq_recv - Posts a list of work requests to the specified SRQ. * @srq: The SRQ to post the work request on. * @recv_wr: A list of work requests to post on the receive queue. * @bad_recv_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. */ static inline int ib_post_srq_recv(struct ib_srq *srq, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr) { const struct ib_recv_wr *dummy; return srq->device->ops.post_srq_recv(srq, recv_wr, bad_recv_wr ? : &dummy); } struct ib_qp *ib_create_qp_kernel(struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr, const char *caller); /** * ib_create_qp - Creates a kernel QP associated with the specific protection * domain. * @pd: The protection domain associated with the QP. * @init_attr: A list of initial attributes required to create the * QP. If QP creation succeeds, then the attributes are updated to * the actual capabilities of the created QP. */ static inline struct ib_qp *ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *init_attr) { return ib_create_qp_kernel(pd, init_attr, KBUILD_MODNAME); } /** * ib_modify_qp_with_udata - Modifies the attributes for the specified QP. * @qp: The QP to modify. * @attr: On input, specifies the QP attributes to modify. On output, * the current values of selected QP attributes are returned. * @attr_mask: A bit-mask used to specify which attributes of the QP * are being modified. * @udata: pointer to user's input output buffer information * are being modified. * It returns 0 on success and returns appropriate error code on error. */ int ib_modify_qp_with_udata(struct ib_qp *qp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata); /** * ib_modify_qp - Modifies the attributes for the specified QP and then * transitions the QP to the given state. * @qp: The QP to modify. * @qp_attr: On input, specifies the QP attributes to modify. On output, * the current values of selected QP attributes are returned. * @qp_attr_mask: A bit-mask used to specify which attributes of the QP * are being modified. */ int ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask); /** * ib_query_qp - Returns the attribute list and current values for the * specified QP. * @qp: The QP to query. * @qp_attr: The attributes of the specified QP. * @qp_attr_mask: A bit-mask used to select specific attributes to query. * @qp_init_attr: Additional attributes of the selected QP. * * The qp_attr_mask may be used to limit the query to gathering only the * selected attributes. */ int ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); /** * ib_destroy_qp - Destroys the specified QP. * @qp: The QP to destroy. * @udata: Valid udata or NULL for kernel objects */ int ib_destroy_qp_user(struct ib_qp *qp, struct ib_udata *udata); /** * ib_destroy_qp - Destroys the specified kernel QP. * @qp: The QP to destroy. * * NOTE: for user qp use ib_destroy_qp_user with valid udata! */ static inline int ib_destroy_qp(struct ib_qp *qp) { return ib_destroy_qp_user(qp, NULL); } /** * ib_open_qp - Obtain a reference to an existing sharable QP. * @xrcd - XRC domain * @qp_open_attr: Attributes identifying the QP to open. * * Returns a reference to a sharable QP. */ struct ib_qp *ib_open_qp(struct ib_xrcd *xrcd, struct ib_qp_open_attr *qp_open_attr); /** * ib_close_qp - Release an external reference to a QP. * @qp: The QP handle to release * * The opened QP handle is released by the caller. The underlying * shared QP is not destroyed until all internal references are released. */ int ib_close_qp(struct ib_qp *qp); /** * ib_post_send - Posts a list of work requests to the send queue of * the specified QP. * @qp: The QP to post the work request on. * @send_wr: A list of work requests to post on the send queue. * @bad_send_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. * * While IBA Vol. 1 section 11.4.1.1 specifies that if an immediate * error is returned, the QP state shall not be affected, * ib_post_send() will return an immediate error after queueing any * earlier work requests in the list. */ static inline int ib_post_send(struct ib_qp *qp, const struct ib_send_wr *send_wr, const struct ib_send_wr **bad_send_wr) { const struct ib_send_wr *dummy; return qp->device->ops.post_send(qp, send_wr, bad_send_wr ? : &dummy); } /** * ib_post_recv - Posts a list of work requests to the receive queue of * the specified QP. * @qp: The QP to post the work request on. * @recv_wr: A list of work requests to post on the receive queue. * @bad_recv_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. */ static inline int ib_post_recv(struct ib_qp *qp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr) { const struct ib_recv_wr *dummy; return qp->device->ops.post_recv(qp, recv_wr, bad_recv_wr ? : &dummy); } struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx, const char *caller); static inline struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx) { return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx, KBUILD_MODNAME); } struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private, int nr_cqe, enum ib_poll_context poll_ctx, const char *caller); /** * ib_alloc_cq_any: Allocate kernel CQ * @dev: The IB device * @private: Private data attached to the CQE * @nr_cqe: Number of CQEs in the CQ * @poll_ctx: Context used for polling the CQ */ static inline struct ib_cq *ib_alloc_cq_any(struct ib_device *dev, void *private, int nr_cqe, enum ib_poll_context poll_ctx) { return __ib_alloc_cq_any(dev, private, nr_cqe, poll_ctx, KBUILD_MODNAME); } void ib_free_cq(struct ib_cq *cq); int ib_process_cq_direct(struct ib_cq *cq, int budget); /** * ib_create_cq - Creates a CQ on the specified device. * @device: The device on which to create the CQ. * @comp_handler: A user-specified callback that is invoked when a * completion event occurs on the CQ. * @event_handler: A user-specified callback that is invoked when an * asynchronous event not associated with a completion occurs on the CQ. * @cq_context: Context associated with the CQ returned to the user via * the associated completion and event handlers. * @cq_attr: The attributes the CQ should be created upon. * * Users can examine the cq structure to determine the actual CQ size. */ struct ib_cq *__ib_create_cq(struct ib_device *device, ib_comp_handler comp_handler, void (*event_handler)(struct ib_event *, void *), void *cq_context, const struct ib_cq_init_attr *cq_attr, const char *caller); #define ib_create_cq(device, cmp_hndlr, evt_hndlr, cq_ctxt, cq_attr) \ __ib_create_cq((device), (cmp_hndlr), (evt_hndlr), (cq_ctxt), (cq_attr), KBUILD_MODNAME) /** * ib_resize_cq - Modifies the capacity of the CQ. * @cq: The CQ to resize. * @cqe: The minimum size of the CQ. * * Users can examine the cq structure to determine the actual CQ size. */ int ib_resize_cq(struct ib_cq *cq, int cqe); /** * rdma_set_cq_moderation - Modifies moderation params of the CQ * @cq: The CQ to modify. * @cq_count: number of CQEs that will trigger an event * @cq_period: max period of time in usec before triggering an event * */ int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period); /** * ib_destroy_cq_user - Destroys the specified CQ. * @cq: The CQ to destroy. * @udata: Valid user data or NULL for kernel objects */ int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata); /** * ib_destroy_cq - Destroys the specified kernel CQ. * @cq: The CQ to destroy. * * NOTE: for user cq use ib_destroy_cq_user with valid udata! */ static inline void ib_destroy_cq(struct ib_cq *cq) { int ret = ib_destroy_cq_user(cq, NULL); WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail"); } /** * ib_poll_cq - poll a CQ for completion(s) * @cq:the CQ being polled * @num_entries:maximum number of completions to return * @wc:array of at least @num_entries &struct ib_wc where completions * will be returned * * Poll a CQ for (possibly multiple) completions. If the return value * is < 0, an error occurred. If the return value is >= 0, it is the * number of completions returned. If the return value is * non-negative and < num_entries, then the CQ was emptied. */ static inline int ib_poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc) { return cq->device->ops.poll_cq(cq, num_entries, wc); } /** * ib_req_notify_cq - Request completion notification on a CQ. * @cq: The CQ to generate an event for. * @flags: * Must contain exactly one of %IB_CQ_SOLICITED or %IB_CQ_NEXT_COMP * to request an event on the next solicited event or next work * completion at any type, respectively. %IB_CQ_REPORT_MISSED_EVENTS * may also be |ed in to request a hint about missed events, as * described below. * * Return Value: * < 0 means an error occurred while requesting notification * == 0 means notification was requested successfully, and if * IB_CQ_REPORT_MISSED_EVENTS was passed in, then no events * were missed and it is safe to wait for another event. In * this case is it guaranteed that any work completions added * to the CQ since the last CQ poll will trigger a completion * notification event. * > 0 is only returned if IB_CQ_REPORT_MISSED_EVENTS was passed * in. It means that the consumer must poll the CQ again to * make sure it is empty to avoid missing an event because of a * race between requesting notification and an entry being * added to the CQ. This return value means it is possible * (but not guaranteed) that a work completion has been added * to the CQ since the last poll without triggering a * completion notification event. */ static inline int ib_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags) { return cq->device->ops.req_notify_cq(cq, flags); } struct ib_cq *ib_cq_pool_get(struct ib_device *dev, unsigned int nr_cqe, int comp_vector_hint, enum ib_poll_context poll_ctx); void ib_cq_pool_put(struct ib_cq *cq, unsigned int nr_cqe); /* * Drivers that don't need a DMA mapping at the RDMA layer, set dma_device to * NULL. This causes the ib_dma* helpers to just stash the kernel virtual * address into the dma address. */ static inline bool ib_uses_virt_dma(struct ib_device *dev) { return IS_ENABLED(CONFIG_INFINIBAND_VIRT_DMA) && !dev->dma_device; } /* * Check if a IB device's underlying DMA mapping supports P2PDMA transfers. */ static inline bool ib_dma_pci_p2p_dma_supported(struct ib_device *dev) { if (ib_uses_virt_dma(dev)) return false; return dma_pci_p2pdma_supported(dev->dma_device); } /** * ib_dma_mapping_error - check a DMA addr for error * @dev: The device for which the dma_addr was created * @dma_addr: The DMA address to check */ static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr) { if (ib_uses_virt_dma(dev)) return 0; return dma_mapping_error(dev->dma_device, dma_addr); } /** * ib_dma_map_single - Map a kernel virtual address to DMA address * @dev: The device for which the dma_addr is to be created * @cpu_addr: The kernel virtual address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline u64 ib_dma_map_single(struct ib_device *dev, void *cpu_addr, size_t size, enum dma_data_direction direction) { if (ib_uses_virt_dma(dev)) return (uintptr_t)cpu_addr; return dma_map_single(dev->dma_device, cpu_addr, size, direction); } /** * ib_dma_unmap_single - Destroy a mapping created by ib_dma_map_single() * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline void ib_dma_unmap_single(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { if (!ib_uses_virt_dma(dev)) dma_unmap_single(dev->dma_device, addr, size, direction); } /** * ib_dma_map_page - Map a physical page to DMA address * @dev: The device for which the dma_addr is to be created * @page: The page to be mapped * @offset: The offset within the page * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline u64 ib_dma_map_page(struct ib_device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction) { if (ib_uses_virt_dma(dev)) return (uintptr_t)(page_address(page) + offset); return dma_map_page(dev->dma_device, page, offset, size, direction); } /** * ib_dma_unmap_page - Destroy a mapping created by ib_dma_map_page() * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline void ib_dma_unmap_page(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { if (!ib_uses_virt_dma(dev)) dma_unmap_page(dev->dma_device, addr, size, direction); } int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents); static inline int ib_dma_map_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, unsigned long dma_attrs) { if (ib_uses_virt_dma(dev)) return ib_dma_virt_map_sg(dev, sg, nents); return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, unsigned long dma_attrs) { if (!ib_uses_virt_dma(dev)) dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } /** * ib_dma_map_sgtable_attrs - Map a scatter/gather table to DMA addresses * @dev: The device for which the DMA addresses are to be created * @sg: The sg_table object describing the buffer * @direction: The direction of the DMA * @attrs: Optional DMA attributes for the map operation */ static inline int ib_dma_map_sgtable_attrs(struct ib_device *dev, struct sg_table *sgt, enum dma_data_direction direction, unsigned long dma_attrs) { int nents; if (ib_uses_virt_dma(dev)) { nents = ib_dma_virt_map_sg(dev, sgt->sgl, sgt->orig_nents); if (!nents) return -EIO; sgt->nents = nents; return 0; } return dma_map_sgtable(dev->dma_device, sgt, direction, dma_attrs); } static inline void ib_dma_unmap_sgtable_attrs(struct ib_device *dev, struct sg_table *sgt, enum dma_data_direction direction, unsigned long dma_attrs) { if (!ib_uses_virt_dma(dev)) dma_unmap_sgtable(dev->dma_device, sgt, direction, dma_attrs); } /** * ib_dma_map_sg - Map a scatter/gather list to DMA addresses * @dev: The device for which the DMA addresses are to be created * @sg: The array of scatter/gather entries * @nents: The number of scatter/gather entries * @direction: The direction of the DMA */ static inline int ib_dma_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { return ib_dma_map_sg_attrs(dev, sg, nents, direction, 0); } /** * ib_dma_unmap_sg - Unmap a scatter/gather list of DMA addresses * @dev: The device for which the DMA addresses were created * @sg: The array of scatter/gather entries * @nents: The number of scatter/gather entries * @direction: The direction of the DMA */ static inline void ib_dma_unmap_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { ib_dma_unmap_sg_attrs(dev, sg, nents, direction, 0); } /** * ib_dma_max_seg_size - Return the size limit of a single DMA transfer * @dev: The device to query * * The returned value represents a size in bytes. */ static inline unsigned int ib_dma_max_seg_size(struct ib_device *dev) { if (ib_uses_virt_dma(dev)) return UINT_MAX; return dma_get_max_seg_size(dev->dma_device); } /** * ib_dma_sync_single_for_cpu - Prepare DMA region to be accessed by CPU * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @dir: The direction of the DMA */ static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction dir) { if (!ib_uses_virt_dma(dev)) dma_sync_single_for_cpu(dev->dma_device, addr, size, dir); } /** * ib_dma_sync_single_for_device - Prepare DMA region to be accessed by device * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @dir: The direction of the DMA */ static inline void ib_dma_sync_single_for_device(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction dir) { if (!ib_uses_virt_dma(dev)) dma_sync_single_for_device(dev->dma_device, addr, size, dir); } /* ib_reg_user_mr - register a memory region for virtual addresses from kernel * space. This function should be called when 'current' is the owning MM. */ struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int mr_access_flags); /* ib_advise_mr - give an advice about an address range in a memory region */ int ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge); /** * ib_dereg_mr_user - Deregisters a memory region and removes it from the * HCA translation table. * @mr: The memory region to deregister. * @udata: Valid user data or NULL for kernel object * * This function can fail, if the memory region has memory windows bound to it. */ int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata); /** * ib_dereg_mr - Deregisters a kernel memory region and removes it from the * HCA translation table. * @mr: The memory region to deregister. * * This function can fail, if the memory region has memory windows bound to it. * * NOTE: for user mr use ib_dereg_mr_user with valid udata! */ static inline int ib_dereg_mr(struct ib_mr *mr) { return ib_dereg_mr_user(mr, NULL); } struct ib_mr *ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg); struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd, u32 max_num_data_sg, u32 max_num_meta_sg); /** * ib_update_fast_reg_key - updates the key portion of the fast_reg MR * R_Key and L_Key. * @mr - struct ib_mr pointer to be updated. * @newkey - new key to be used. */ static inline void ib_update_fast_reg_key(struct ib_mr *mr, u8 newkey) { mr->lkey = (mr->lkey & 0xffffff00) | newkey; mr->rkey = (mr->rkey & 0xffffff00) | newkey; } /** * ib_inc_rkey - increments the key portion of the given rkey. Can be used * for calculating a new rkey for type 2 memory windows. * @rkey - the rkey to increment. */ static inline u32 ib_inc_rkey(u32 rkey) { const u32 mask = 0x000000ff; return ((rkey + 1) & mask) | (rkey & ~mask); } /** * ib_attach_mcast - Attaches the specified QP to a multicast group. * @qp: QP to attach to the multicast group. The QP must be type * IB_QPT_UD. * @gid: Multicast group GID. * @lid: Multicast group LID in host byte order. * * In order to send and receive multicast packets, subnet * administration must have created the multicast group and configured * the fabric appropriately. The port associated with the specified * QP must also be a member of the multicast group. */ int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); /** * ib_detach_mcast - Detaches the specified QP from a multicast group. * @qp: QP to detach from the multicast group. * @gid: Multicast group GID. * @lid: Multicast group LID in host byte order. */ int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); struct ib_xrcd *ib_alloc_xrcd_user(struct ib_device *device, struct inode *inode, struct ib_udata *udata); int ib_dealloc_xrcd_user(struct ib_xrcd *xrcd, struct ib_udata *udata); static inline int ib_check_mr_access(struct ib_device *ib_dev, unsigned int flags) { /* * Local write permission is required if remote write or * remote atomic permission is also requested. */ if (flags & (IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_REMOTE_WRITE) && !(flags & IB_ACCESS_LOCAL_WRITE)) return -EINVAL; if (flags & ~IB_ACCESS_SUPPORTED) return -EINVAL; if (flags & IB_ACCESS_ON_DEMAND && !(ib_dev->attrs.kernel_cap_flags & IBK_ON_DEMAND_PAGING)) return -EINVAL; return 0; } static inline bool ib_access_writable(int access_flags) { /* * We have writable memory backing the MR if any of the following * access flags are set. "Local write" and "remote write" obviously * require write access. "Remote atomic" can do things like fetch and * add, which will modify memory, and "MW bind" can change permissions * by binding a window. */ return access_flags & (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND); } /** * ib_check_mr_status: lightweight check of MR status. * This routine may provide status checks on a selected * ib_mr. first use is for signature status check. * * @mr: A memory region. * @check_mask: Bitmask of which checks to perform from * ib_mr_status_check enumeration. * @mr_status: The container of relevant status checks. * failed checks will be indicated in the status bitmask * and the relevant info shall be in the error item. */ int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); /** * ib_device_try_get: Hold a registration lock * device: The device to lock * * A device under an active registration lock cannot become unregistered. It * is only possible to obtain a registration lock on a device that is fully * registered, otherwise this function returns false. * * The registration lock is only necessary for actions which require the * device to still be registered. Uses that only require the device pointer to * be valid should use get_device(&ibdev->dev) to hold the memory. * */ static inline bool ib_device_try_get(struct ib_device *dev) { return refcount_inc_not_zero(&dev->refcount); } void ib_device_put(struct ib_device *device); struct ib_device *ib_device_get_by_netdev(struct net_device *ndev, enum rdma_driver_id driver_id); struct ib_device *ib_device_get_by_name(const char *name, enum rdma_driver_id driver_id); struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr); int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev, unsigned int port); struct net_device *ib_device_netdev(struct ib_device *dev, u32 port); struct ib_wq *ib_create_wq(struct ib_pd *pd, struct ib_wq_init_attr *init_attr); int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata); int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size); int ib_map_mr_sg_pi(struct ib_mr *mr, struct scatterlist *data_sg, int data_sg_nents, unsigned int *data_sg_offset, struct scatterlist *meta_sg, int meta_sg_nents, unsigned int *meta_sg_offset, unsigned int page_size); static inline int ib_map_mr_sg_zbva(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size) { int n; n = ib_map_mr_sg(mr, sg, sg_nents, sg_offset, page_size); mr->iova = 0; return n; } int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents, unsigned int *sg_offset, int (*set_page)(struct ib_mr *, u64)); void ib_drain_rq(struct ib_qp *qp); void ib_drain_sq(struct ib_qp *qp); void ib_drain_qp(struct ib_qp *qp); int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width); static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_ROCE) return attr->roce.dmac; return NULL; } static inline void rdma_ah_set_dlid(struct rdma_ah_attr *attr, u32 dlid) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) attr->ib.dlid = (u16)dlid; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.dlid = dlid; } static inline u32 rdma_ah_get_dlid(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) return attr->ib.dlid; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.dlid; return 0; } static inline void rdma_ah_set_sl(struct rdma_ah_attr *attr, u8 sl) { attr->sl = sl; } static inline u8 rdma_ah_get_sl(const struct rdma_ah_attr *attr) { return attr->sl; } static inline void rdma_ah_set_path_bits(struct rdma_ah_attr *attr, u8 src_path_bits) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) attr->ib.src_path_bits = src_path_bits; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.src_path_bits = src_path_bits; } static inline u8 rdma_ah_get_path_bits(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) return attr->ib.src_path_bits; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.src_path_bits; return 0; } static inline void rdma_ah_set_make_grd(struct rdma_ah_attr *attr, bool make_grd) { if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.make_grd = make_grd; } static inline bool rdma_ah_get_make_grd(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.make_grd; return false; } static inline void rdma_ah_set_port_num(struct rdma_ah_attr *attr, u32 port_num) { attr->port_num = port_num; } static inline u32 rdma_ah_get_port_num(const struct rdma_ah_attr *attr) { return attr->port_num; } static inline void rdma_ah_set_static_rate(struct rdma_ah_attr *attr, u8 static_rate) { attr->static_rate = static_rate; } static inline u8 rdma_ah_get_static_rate(const struct rdma_ah_attr *attr) { return attr->static_rate; } static inline void rdma_ah_set_ah_flags(struct rdma_ah_attr *attr, enum ib_ah_flags flag) { attr->ah_flags = flag; } static inline enum ib_ah_flags rdma_ah_get_ah_flags(const struct rdma_ah_attr *attr) { return attr->ah_flags; } static inline const struct ib_global_route *rdma_ah_read_grh(const struct rdma_ah_attr *attr) { return &attr->grh; } /*To retrieve and modify the grh */ static inline struct ib_global_route *rdma_ah_retrieve_grh(struct rdma_ah_attr *attr) { return &attr->grh; } static inline void rdma_ah_set_dgid_raw(struct rdma_ah_attr *attr, void *dgid) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); memcpy(grh->dgid.raw, dgid, sizeof(grh->dgid)); } static inline void rdma_ah_set_subnet_prefix(struct rdma_ah_attr *attr, __be64 prefix) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); grh->dgid.global.subnet_prefix = prefix; } static inline void rdma_ah_set_interface_id(struct rdma_ah_attr *attr, __be64 if_id) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); grh->dgid.global.interface_id = if_id; } static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr, union ib_gid *dgid, u32 flow_label, u8 sgid_index, u8 hop_limit, u8 traffic_class) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); attr->ah_flags = IB_AH_GRH; if (dgid) grh->dgid = *dgid; grh->flow_label = flow_label; grh->sgid_index = sgid_index; grh->hop_limit = hop_limit; grh->traffic_class = traffic_class; grh->sgid_attr = NULL; } void rdma_destroy_ah_attr(struct rdma_ah_attr *ah_attr); void rdma_move_grh_sgid_attr(struct rdma_ah_attr *attr, union ib_gid *dgid, u32 flow_label, u8 hop_limit, u8 traffic_class, const struct ib_gid_attr *sgid_attr); void rdma_copy_ah_attr(struct rdma_ah_attr *dest, const struct rdma_ah_attr *src); void rdma_replace_ah_attr(struct rdma_ah_attr *old, const struct rdma_ah_attr *new); void rdma_move_ah_attr(struct rdma_ah_attr *dest, struct rdma_ah_attr *src); /** * rdma_ah_find_type - Return address handle type. * * @dev: Device to be checked * @port_num: Port number */ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev, u32 port_num) { if (rdma_protocol_roce(dev, port_num)) return RDMA_AH_ATTR_TYPE_ROCE; if (rdma_protocol_ib(dev, port_num)) { if (rdma_cap_opa_ah(dev, port_num)) return RDMA_AH_ATTR_TYPE_OPA; return RDMA_AH_ATTR_TYPE_IB; } return RDMA_AH_ATTR_TYPE_UNDEFINED; } /** * ib_lid_cpu16 - Return lid in 16bit CPU encoding. * In the current implementation the only way to * get the 32bit lid is from other sources for OPA. * For IB, lids will always be 16bits so cast the * value accordingly. * * @lid: A 32bit LID */ static inline u16 ib_lid_cpu16(u32 lid) { WARN_ON_ONCE(lid & 0xFFFF0000); return (u16)lid; } /** * ib_lid_be16 - Return lid in 16bit BE encoding. * * @lid: A 32bit LID */ static inline __be16 ib_lid_be16(u32 lid) { WARN_ON_ONCE(lid & 0xFFFF0000); return cpu_to_be16((u16)lid); } /** * ib_get_vector_affinity - Get the affinity mappings of a given completion * vector * @device: the rdma device * @comp_vector: index of completion vector * * Returns NULL on failure, otherwise a corresponding cpu map of the * completion vector (returns all-cpus map if the device driver doesn't * implement get_vector_affinity). */ static inline const struct cpumask * ib_get_vector_affinity(struct ib_device *device, int comp_vector) { if (comp_vector < 0 || comp_vector >= device->num_comp_vectors || !device->ops.get_vector_affinity) return NULL; return device->ops.get_vector_affinity(device, comp_vector); } /** * rdma_roce_rescan_device - Rescan all of the network devices in the system * and add their gids, as needed, to the relevant RoCE devices. * * @device: the rdma device */ void rdma_roce_rescan_device(struct ib_device *ibdev); struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile); int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs); struct net_device *rdma_alloc_netdev(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *)); int rdma_init_netdev(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), struct net_device *netdev); /** * rdma_device_to_ibdev - Get ib_device pointer from device pointer * * @device: device pointer for which ib_device pointer to retrieve * * rdma_device_to_ibdev() retrieves ib_device pointer from device. * */ static inline struct ib_device *rdma_device_to_ibdev(struct device *device) { struct ib_core_device *coredev = container_of(device, struct ib_core_device, dev); return coredev->owner; } /** * ibdev_to_node - return the NUMA node for a given ib_device * @dev: device to get the NUMA node for. */ static inline int ibdev_to_node(struct ib_device *ibdev) { struct device *parent = ibdev->dev.parent; if (!parent) return NUMA_NO_NODE; return dev_to_node(parent); } /** * rdma_device_to_drv_device - Helper macro to reach back to driver's * ib_device holder structure from device pointer. * * NOTE: New drivers should not make use of this API; This API is only for * existing drivers who have exposed sysfs entries using * ops->device_group. */ #define rdma_device_to_drv_device(dev, drv_dev_struct, ibdev_member) \ container_of(rdma_device_to_ibdev(dev), drv_dev_struct, ibdev_member) bool rdma_dev_access_netns(const struct ib_device *device, const struct net *net); #define IB_ROCE_UDP_ENCAP_VALID_PORT_MIN (0xC000) #define IB_ROCE_UDP_ENCAP_VALID_PORT_MAX (0xFFFF) #define IB_GRH_FLOWLABEL_MASK (0x000FFFFF) /** * rdma_flow_label_to_udp_sport - generate a RoCE v2 UDP src port value based * on the flow_label * * This function will convert the 20 bit flow_label input to a valid RoCE v2 * UDP src port 14 bit value. All RoCE V2 drivers should use this same * convention. */ static inline u16 rdma_flow_label_to_udp_sport(u32 fl) { u32 fl_low = fl & 0x03fff, fl_high = fl & 0xFC000; fl_low ^= fl_high >> 14; return (u16)(fl_low | IB_ROCE_UDP_ENCAP_VALID_PORT_MIN); } /** * rdma_calc_flow_label - generate a RDMA symmetric flow label value based on * local and remote qpn values * * This function folded the multiplication results of two qpns, 24 bit each, * fields, and converts it to a 20 bit results. * * This function will create symmetric flow_label value based on the local * and remote qpn values. this will allow both the requester and responder * to calculate the same flow_label for a given connection. * * This helper function should be used by driver in case the upper layer * provide a zero flow_label value. This is to improve entropy of RDMA * traffic in the network. */ static inline u32 rdma_calc_flow_label(u32 lqpn, u32 rqpn) { u64 v = (u64)lqpn * rqpn; v ^= v >> 20; v ^= v >> 40; return (u32)(v & IB_GRH_FLOWLABEL_MASK); } /** * rdma_get_udp_sport - Calculate and set UDP source port based on the flow * label. If flow label is not defined in GRH then * calculate it based on lqpn/rqpn. * * @fl: flow label from GRH * @lqpn: local qp number * @rqpn: remote qp number */ static inline u16 rdma_get_udp_sport(u32 fl, u32 lqpn, u32 rqpn) { if (!fl) fl = rdma_calc_flow_label(lqpn, rqpn); return rdma_flow_label_to_udp_sport(fl); } const struct ib_port_immutable* ib_port_immutable_read(struct ib_device *dev, unsigned int port); #endif /* IB_VERBS_H */ |
| 946 681 53 53 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #ifndef _NET_BATMAN_ADV_HARD_INTERFACE_H_ #define _NET_BATMAN_ADV_HARD_INTERFACE_H_ #include "main.h" #include <linux/compiler.h> #include <linux/kref.h> #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/rcupdate.h> #include <linux/stddef.h> #include <linux/types.h> /** * enum batadv_hard_if_state - State of a hard interface */ enum batadv_hard_if_state { /** * @BATADV_IF_NOT_IN_USE: interface is not used as slave interface of a * batman-adv soft interface */ BATADV_IF_NOT_IN_USE, /** * @BATADV_IF_TO_BE_REMOVED: interface will be removed from soft * interface */ BATADV_IF_TO_BE_REMOVED, /** @BATADV_IF_INACTIVE: interface is deactivated */ BATADV_IF_INACTIVE, /** @BATADV_IF_ACTIVE: interface is used */ BATADV_IF_ACTIVE, /** @BATADV_IF_TO_BE_ACTIVATED: interface is getting activated */ BATADV_IF_TO_BE_ACTIVATED, }; /** * enum batadv_hard_if_bcast - broadcast avoidance options */ enum batadv_hard_if_bcast { /** @BATADV_HARDIF_BCAST_OK: Do broadcast on according hard interface */ BATADV_HARDIF_BCAST_OK = 0, /** * @BATADV_HARDIF_BCAST_NORECIPIENT: Broadcast not needed, there is no * recipient */ BATADV_HARDIF_BCAST_NORECIPIENT, /** * @BATADV_HARDIF_BCAST_DUPFWD: There is just the neighbor we got it * from */ BATADV_HARDIF_BCAST_DUPFWD, /** @BATADV_HARDIF_BCAST_DUPORIG: There is just the originator */ BATADV_HARDIF_BCAST_DUPORIG, }; extern struct notifier_block batadv_hard_if_notifier; struct net_device *batadv_get_real_netdev(struct net_device *net_device); bool batadv_is_cfg80211_hardif(struct batadv_hard_iface *hard_iface); bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface); struct batadv_hard_iface* batadv_hardif_get_by_netdev(const struct net_device *net_dev); int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, struct net_device *soft_iface); void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface); int batadv_hardif_min_mtu(struct net_device *soft_iface); void batadv_update_min_mtu(struct net_device *soft_iface); void batadv_hardif_release(struct kref *ref); int batadv_hardif_no_broadcast(struct batadv_hard_iface *if_outgoing, u8 *orig_addr, u8 *orig_neigh); /** * batadv_hardif_put() - decrement the hard interface refcounter and possibly * release it * @hard_iface: the hard interface to free */ static inline void batadv_hardif_put(struct batadv_hard_iface *hard_iface) { if (!hard_iface) return; kref_put(&hard_iface->refcount, batadv_hardif_release); } /** * batadv_primary_if_get_selected() - Get reference to primary interface * @bat_priv: the bat priv with all the soft interface information * * Return: primary interface (with increased refcnt), otherwise NULL */ static inline struct batadv_hard_iface * batadv_primary_if_get_selected(struct batadv_priv *bat_priv) { struct batadv_hard_iface *hard_iface; rcu_read_lock(); hard_iface = rcu_dereference(bat_priv->primary_if); if (!hard_iface) goto out; if (!kref_get_unless_zero(&hard_iface->refcount)) hard_iface = NULL; out: rcu_read_unlock(); return hard_iface; } #endif /* _NET_BATMAN_ADV_HARD_INTERFACE_H_ */ |
| 12 12 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Scatterlist Cryptographic API. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2002 David S. Miller (davem@redhat.com) * Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au> * * Portions derived from Cryptoapi, by Alexander Kjeldaas <astor@fast.no> * and Nettle, by Niels Möller. */ #ifndef _LINUX_CRYPTO_H #define _LINUX_CRYPTO_H #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/bug.h> #include <linux/refcount.h> #include <linux/slab.h> #include <linux/completion.h> /* * Autoloaded crypto modules should only use a prefixed name to avoid allowing * arbitrary modules to be loaded. Loading from userspace may still need the * unprefixed names, so retains those aliases as well. * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3 * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro * expands twice on the same line. Instead, use a separate base name for the * alias. */ #define MODULE_ALIAS_CRYPTO(name) \ __MODULE_INFO(alias, alias_userspace, name); \ __MODULE_INFO(alias, alias_crypto, "crypto-" name) /* * Algorithm masks and types. */ #define CRYPTO_ALG_TYPE_MASK 0x0000000f #define CRYPTO_ALG_TYPE_CIPHER 0x00000001 #define CRYPTO_ALG_TYPE_COMPRESS 0x00000002 #define CRYPTO_ALG_TYPE_AEAD 0x00000003 #define CRYPTO_ALG_TYPE_SKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_KPP 0x00000008 #define CRYPTO_ALG_TYPE_ACOMPRESS 0x0000000a #define CRYPTO_ALG_TYPE_SCOMPRESS 0x0000000b #define CRYPTO_ALG_TYPE_RNG 0x0000000c #define CRYPTO_ALG_TYPE_AKCIPHER 0x0000000d #define CRYPTO_ALG_TYPE_HASH 0x0000000e #define CRYPTO_ALG_TYPE_SHASH 0x0000000e #define CRYPTO_ALG_TYPE_AHASH 0x0000000f #define CRYPTO_ALG_TYPE_HASH_MASK 0x0000000e #define CRYPTO_ALG_TYPE_AHASH_MASK 0x0000000e #define CRYPTO_ALG_TYPE_ACOMPRESS_MASK 0x0000000e #define CRYPTO_ALG_LARVAL 0x00000010 #define CRYPTO_ALG_DEAD 0x00000020 #define CRYPTO_ALG_DYING 0x00000040 #define CRYPTO_ALG_ASYNC 0x00000080 /* * Set if the algorithm (or an algorithm which it uses) requires another * algorithm of the same type to handle corner cases. */ #define CRYPTO_ALG_NEED_FALLBACK 0x00000100 /* * Set if the algorithm has passed automated run-time testing. Note that * if there is no run-time testing for a given algorithm it is considered * to have passed. */ #define CRYPTO_ALG_TESTED 0x00000400 /* * Set if the algorithm is an instance that is built from templates. */ #define CRYPTO_ALG_INSTANCE 0x00000800 /* Set this bit if the algorithm provided is hardware accelerated but * not available to userspace via instruction set or so. */ #define CRYPTO_ALG_KERN_DRIVER_ONLY 0x00001000 /* * Mark a cipher as a service implementation only usable by another * cipher and never by a normal user of the kernel crypto API */ #define CRYPTO_ALG_INTERNAL 0x00002000 /* * Set if the algorithm has a ->setkey() method but can be used without * calling it first, i.e. there is a default key. */ #define CRYPTO_ALG_OPTIONAL_KEY 0x00004000 /* * Don't trigger module loading */ #define CRYPTO_NOLOAD 0x00008000 /* * The algorithm may allocate memory during request processing, i.e. during * encryption, decryption, or hashing. Users can request an algorithm with this * flag unset if they can't handle memory allocation failures. * * This flag is currently only implemented for algorithms of type "skcipher", * "aead", "ahash", "shash", and "cipher". Algorithms of other types might not * have this flag set even if they allocate memory. * * In some edge cases, algorithms can allocate memory regardless of this flag. * To avoid these cases, users must obey the following usage constraints: * skcipher: * - The IV buffer and all scatterlist elements must be aligned to the * algorithm's alignmask. * - If the data were to be divided into chunks of size * crypto_skcipher_walksize() (with any remainder going at the end), no * chunk can cross a page boundary or a scatterlist element boundary. * aead: * - The IV buffer and all scatterlist elements must be aligned to the * algorithm's alignmask. * - The first scatterlist element must contain all the associated data, * and its pages must be !PageHighMem. * - If the plaintext/ciphertext were to be divided into chunks of size * crypto_aead_walksize() (with the remainder going at the end), no chunk * can cross a page boundary or a scatterlist element boundary. * ahash: * - The result buffer must be aligned to the algorithm's alignmask. * - crypto_ahash_finup() must not be used unless the algorithm implements * ->finup() natively. */ #define CRYPTO_ALG_ALLOCATES_MEMORY 0x00010000 /* * Mark an algorithm as a service implementation only usable by a * template and never by a normal user of the kernel crypto API. * This is intended to be used by algorithms that are themselves * not FIPS-approved but may instead be used to implement parts of * a FIPS-approved algorithm (e.g., dh vs. ffdhe2048(dh)). */ #define CRYPTO_ALG_FIPS_INTERNAL 0x00020000 /* * Transform masks and values (for crt_flags). */ #define CRYPTO_TFM_NEED_KEY 0x00000001 #define CRYPTO_TFM_REQ_MASK 0x000fff00 #define CRYPTO_TFM_REQ_FORBID_WEAK_KEYS 0x00000100 #define CRYPTO_TFM_REQ_MAY_SLEEP 0x00000200 #define CRYPTO_TFM_REQ_MAY_BACKLOG 0x00000400 /* * Miscellaneous stuff. */ #define CRYPTO_MAX_ALG_NAME 128 /* * The macro CRYPTO_MINALIGN_ATTR (along with the void * type in the actual * declaration) is used to ensure that the crypto_tfm context structure is * aligned correctly for the given architecture so that there are no alignment * faults for C data types. On architectures that support non-cache coherent * DMA, such as ARM or arm64, it also takes into account the minimal alignment * that is required to ensure that the context struct member does not share any * cachelines with the rest of the struct. This is needed to ensure that cache * maintenance for non-coherent DMA (cache invalidation in particular) does not * affect data that may be accessed by the CPU concurrently. */ #define CRYPTO_MINALIGN ARCH_KMALLOC_MINALIGN #define CRYPTO_MINALIGN_ATTR __attribute__ ((__aligned__(CRYPTO_MINALIGN))) struct scatterlist; struct crypto_async_request; struct crypto_tfm; struct crypto_type; typedef void (*crypto_completion_t)(struct crypto_async_request *req, int err); /** * DOC: Block Cipher Context Data Structures * * These data structures define the operating context for each block cipher * type. */ struct crypto_async_request { struct list_head list; crypto_completion_t complete; void *data; struct crypto_tfm *tfm; u32 flags; }; /** * DOC: Block Cipher Algorithm Definitions * * These data structures define modular crypto algorithm implementations, * managed via crypto_register_alg() and crypto_unregister_alg(). */ /** * struct cipher_alg - single-block symmetric ciphers definition * @cia_min_keysize: Minimum key size supported by the transformation. This is * the smallest key length supported by this transformation * algorithm. This must be set to one of the pre-defined * values as this is not hardware specific. Possible values * for this field can be found via git grep "_MIN_KEY_SIZE" * include/crypto/ * @cia_max_keysize: Maximum key size supported by the transformation. This is * the largest key length supported by this transformation * algorithm. This must be set to one of the pre-defined values * as this is not hardware specific. Possible values for this * field can be found via git grep "_MAX_KEY_SIZE" * include/crypto/ * @cia_setkey: Set key for the transformation. This function is used to either * program a supplied key into the hardware or store the key in the * transformation context for programming it later. Note that this * function does modify the transformation context. This function * can be called multiple times during the existence of the * transformation object, so one must make sure the key is properly * reprogrammed into the hardware. This function is also * responsible for checking the key length for validity. * @cia_encrypt: Encrypt a single block. This function is used to encrypt a * single block of data, which must be @cra_blocksize big. This * always operates on a full @cra_blocksize and it is not possible * to encrypt a block of smaller size. The supplied buffers must * therefore also be at least of @cra_blocksize size. Both the * input and output buffers are always aligned to @cra_alignmask. * In case either of the input or output buffer supplied by user * of the crypto API is not aligned to @cra_alignmask, the crypto * API will re-align the buffers. The re-alignment means that a * new buffer will be allocated, the data will be copied into the * new buffer, then the processing will happen on the new buffer, * then the data will be copied back into the original buffer and * finally the new buffer will be freed. In case a software * fallback was put in place in the @cra_init call, this function * might need to use the fallback if the algorithm doesn't support * all of the key sizes. In case the key was stored in * transformation context, the key might need to be re-programmed * into the hardware in this function. This function shall not * modify the transformation context, as this function may be * called in parallel with the same transformation object. * @cia_decrypt: Decrypt a single block. This is a reverse counterpart to * @cia_encrypt, and the conditions are exactly the same. * * All fields are mandatory and must be filled. */ struct cipher_alg { unsigned int cia_min_keysize; unsigned int cia_max_keysize; int (*cia_setkey)(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen); void (*cia_encrypt)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); void (*cia_decrypt)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); }; /** * struct compress_alg - compression/decompression algorithm * @coa_compress: Compress a buffer of specified length, storing the resulting * data in the specified buffer. Return the length of the * compressed data in dlen. * @coa_decompress: Decompress the source buffer, storing the uncompressed * data in the specified buffer. The length of the data is * returned in dlen. * * All fields are mandatory. */ struct compress_alg { int (*coa_compress)(struct crypto_tfm *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen); int (*coa_decompress)(struct crypto_tfm *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen); }; #ifdef CONFIG_CRYPTO_STATS /* * struct crypto_istat_aead - statistics for AEAD algorithm * @encrypt_cnt: number of encrypt requests * @encrypt_tlen: total data size handled by encrypt requests * @decrypt_cnt: number of decrypt requests * @decrypt_tlen: total data size handled by decrypt requests * @err_cnt: number of error for AEAD requests */ struct crypto_istat_aead { atomic64_t encrypt_cnt; atomic64_t encrypt_tlen; atomic64_t decrypt_cnt; atomic64_t decrypt_tlen; atomic64_t err_cnt; }; /* * struct crypto_istat_akcipher - statistics for akcipher algorithm * @encrypt_cnt: number of encrypt requests * @encrypt_tlen: total data size handled by encrypt requests * @decrypt_cnt: number of decrypt requests * @decrypt_tlen: total data size handled by decrypt requests * @verify_cnt: number of verify operation * @sign_cnt: number of sign requests * @err_cnt: number of error for akcipher requests */ struct crypto_istat_akcipher { atomic64_t encrypt_cnt; atomic64_t encrypt_tlen; atomic64_t decrypt_cnt; atomic64_t decrypt_tlen; atomic64_t verify_cnt; atomic64_t sign_cnt; atomic64_t err_cnt; }; /* * struct crypto_istat_cipher - statistics for cipher algorithm * @encrypt_cnt: number of encrypt requests * @encrypt_tlen: total data size handled by encrypt requests * @decrypt_cnt: number of decrypt requests * @decrypt_tlen: total data size handled by decrypt requests * @err_cnt: number of error for cipher requests */ struct crypto_istat_cipher { atomic64_t encrypt_cnt; atomic64_t encrypt_tlen; atomic64_t decrypt_cnt; atomic64_t decrypt_tlen; atomic64_t err_cnt; }; /* * struct crypto_istat_compress - statistics for compress algorithm * @compress_cnt: number of compress requests * @compress_tlen: total data size handled by compress requests * @decompress_cnt: number of decompress requests * @decompress_tlen: total data size handled by decompress requests * @err_cnt: number of error for compress requests */ struct crypto_istat_compress { atomic64_t compress_cnt; atomic64_t compress_tlen; atomic64_t decompress_cnt; atomic64_t decompress_tlen; atomic64_t err_cnt; }; /* * struct crypto_istat_hash - statistics for has algorithm * @hash_cnt: number of hash requests * @hash_tlen: total data size hashed * @err_cnt: number of error for hash requests */ struct crypto_istat_hash { atomic64_t hash_cnt; atomic64_t hash_tlen; atomic64_t err_cnt; }; /* * struct crypto_istat_kpp - statistics for KPP algorithm * @setsecret_cnt: number of setsecrey operation * @generate_public_key_cnt: number of generate_public_key operation * @compute_shared_secret_cnt: number of compute_shared_secret operation * @err_cnt: number of error for KPP requests */ struct crypto_istat_kpp { atomic64_t setsecret_cnt; atomic64_t generate_public_key_cnt; atomic64_t compute_shared_secret_cnt; atomic64_t err_cnt; }; /* * struct crypto_istat_rng: statistics for RNG algorithm * @generate_cnt: number of RNG generate requests * @generate_tlen: total data size of generated data by the RNG * @seed_cnt: number of times the RNG was seeded * @err_cnt: number of error for RNG requests */ struct crypto_istat_rng { atomic64_t generate_cnt; atomic64_t generate_tlen; atomic64_t seed_cnt; atomic64_t err_cnt; }; #endif /* CONFIG_CRYPTO_STATS */ #define cra_cipher cra_u.cipher #define cra_compress cra_u.compress /** * struct crypto_alg - definition of a cryptograpic cipher algorithm * @cra_flags: Flags describing this transformation. See include/linux/crypto.h * CRYPTO_ALG_* flags for the flags which go in here. Those are * used for fine-tuning the description of the transformation * algorithm. * @cra_blocksize: Minimum block size of this transformation. The size in bytes * of the smallest possible unit which can be transformed with * this algorithm. The users must respect this value. * In case of HASH transformation, it is possible for a smaller * block than @cra_blocksize to be passed to the crypto API for * transformation, in case of any other transformation type, an * error will be returned upon any attempt to transform smaller * than @cra_blocksize chunks. * @cra_ctxsize: Size of the operational context of the transformation. This * value informs the kernel crypto API about the memory size * needed to be allocated for the transformation context. * @cra_alignmask: Alignment mask for the input and output data buffer. The data * buffer containing the input data for the algorithm must be * aligned to this alignment mask. The data buffer for the * output data must be aligned to this alignment mask. Note that * the Crypto API will do the re-alignment in software, but * only under special conditions and there is a performance hit. * The re-alignment happens at these occasions for different * @cra_u types: cipher -- For both input data and output data * buffer; ahash -- For output hash destination buf; shash -- * For output hash destination buf. * This is needed on hardware which is flawed by design and * cannot pick data from arbitrary addresses. * @cra_priority: Priority of this transformation implementation. In case * multiple transformations with same @cra_name are available to * the Crypto API, the kernel will use the one with highest * @cra_priority. * @cra_name: Generic name (usable by multiple implementations) of the * transformation algorithm. This is the name of the transformation * itself. This field is used by the kernel when looking up the * providers of particular transformation. * @cra_driver_name: Unique name of the transformation provider. This is the * name of the provider of the transformation. This can be any * arbitrary value, but in the usual case, this contains the * name of the chip or provider and the name of the * transformation algorithm. * @cra_type: Type of the cryptographic transformation. This is a pointer to * struct crypto_type, which implements callbacks common for all * transformation types. There are multiple options, such as * &crypto_skcipher_type, &crypto_ahash_type, &crypto_rng_type. * This field might be empty. In that case, there are no common * callbacks. This is the case for: cipher, compress, shash. * @cra_u: Callbacks implementing the transformation. This is a union of * multiple structures. Depending on the type of transformation selected * by @cra_type and @cra_flags above, the associated structure must be * filled with callbacks. This field might be empty. This is the case * for ahash, shash. * @cra_init: Initialize the cryptographic transformation object. This function * is used to 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. * @cra_exit: Deinitialize the cryptographic transformation object. This is a * counterpart to @cra_init, used to remove various changes set in * @cra_init. * @cra_u.cipher: Union member which contains a single-block symmetric cipher * definition. See @struct @cipher_alg. * @cra_u.compress: Union member which contains a (de)compression algorithm. * See @struct @compress_alg. * @cra_module: Owner of this transformation implementation. Set to THIS_MODULE * @cra_list: internally used * @cra_users: internally used * @cra_refcnt: internally used * @cra_destroy: internally used * * @stats: union of all possible crypto_istat_xxx structures * @stats.aead: statistics for AEAD algorithm * @stats.akcipher: statistics for akcipher algorithm * @stats.cipher: statistics for cipher algorithm * @stats.compress: statistics for compress algorithm * @stats.hash: statistics for hash algorithm * @stats.rng: statistics for rng algorithm * @stats.kpp: statistics for KPP algorithm * * The struct crypto_alg describes a generic Crypto API algorithm and is common * for all of the transformations. Any variable not documented here shall not * be used by a cipher implementation as it is internal to the Crypto API. */ struct crypto_alg { struct list_head cra_list; struct list_head cra_users; u32 cra_flags; unsigned int cra_blocksize; unsigned int cra_ctxsize; unsigned int cra_alignmask; int cra_priority; refcount_t cra_refcnt; char cra_name[CRYPTO_MAX_ALG_NAME]; char cra_driver_name[CRYPTO_MAX_ALG_NAME]; const struct crypto_type *cra_type; union { struct cipher_alg cipher; struct compress_alg compress; } cra_u; int (*cra_init)(struct crypto_tfm *tfm); void (*cra_exit)(struct crypto_tfm *tfm); void (*cra_destroy)(struct crypto_alg *alg); struct module *cra_module; #ifdef CONFIG_CRYPTO_STATS union { struct crypto_istat_aead aead; struct crypto_istat_akcipher akcipher; struct crypto_istat_cipher cipher; struct crypto_istat_compress compress; struct crypto_istat_hash hash; struct crypto_istat_rng rng; struct crypto_istat_kpp kpp; } stats; #endif /* CONFIG_CRYPTO_STATS */ } CRYPTO_MINALIGN_ATTR; #ifdef CONFIG_CRYPTO_STATS void crypto_stats_init(struct crypto_alg *alg); void crypto_stats_get(struct crypto_alg *alg); void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret); void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret); void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg); void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg); void crypto_stats_akcipher_encrypt(unsigned int src_len, int ret, struct crypto_alg *alg); void crypto_stats_akcipher_decrypt(unsigned int src_len, int ret, struct crypto_alg *alg); void crypto_stats_akcipher_sign(int ret, struct crypto_alg *alg); void crypto_stats_akcipher_verify(int ret, struct crypto_alg *alg); void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg); void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg); void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret); void crypto_stats_kpp_generate_public_key(struct crypto_alg *alg, int ret); void crypto_stats_kpp_compute_shared_secret(struct crypto_alg *alg, int ret); void crypto_stats_rng_seed(struct crypto_alg *alg, int ret); void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret); void crypto_stats_skcipher_encrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg); void crypto_stats_skcipher_decrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg); #else static inline void crypto_stats_init(struct crypto_alg *alg) {} static inline void crypto_stats_get(struct crypto_alg *alg) {} static inline void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret) {} static inline void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret) {} static inline void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg) {} static inline void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg) {} static inline void crypto_stats_akcipher_encrypt(unsigned int src_len, int ret, struct crypto_alg *alg) {} static inline void crypto_stats_akcipher_decrypt(unsigned int src_len, int ret, struct crypto_alg *alg) {} static inline void crypto_stats_akcipher_sign(int ret, struct crypto_alg *alg) {} static inline void crypto_stats_akcipher_verify(int ret, struct crypto_alg *alg) {} static inline void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg) {} static inline void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg) {} static inline void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret) {} static inline void crypto_stats_kpp_generate_public_key(struct crypto_alg *alg, int ret) {} static inline void crypto_stats_kpp_compute_shared_secret(struct crypto_alg *alg, int ret) {} static inline void crypto_stats_rng_seed(struct crypto_alg *alg, int ret) {} static inline void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret) {} static inline void crypto_stats_skcipher_encrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg) {} static inline void crypto_stats_skcipher_decrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg) {} #endif /* * A helper struct for waiting for completion of async crypto ops */ struct crypto_wait { struct completion completion; int err; }; /* * Macro for declaring a crypto op async wait object on stack */ #define DECLARE_CRYPTO_WAIT(_wait) \ struct crypto_wait _wait = { \ COMPLETION_INITIALIZER_ONSTACK((_wait).completion), 0 } /* * Async ops completion helper functioons */ void crypto_req_done(struct crypto_async_request *req, int err); static inline int crypto_wait_req(int err, struct crypto_wait *wait) { switch (err) { case -EINPROGRESS: case -EBUSY: wait_for_completion(&wait->completion); reinit_completion(&wait->completion); err = wait->err; break; } return err; } static inline void crypto_init_wait(struct crypto_wait *wait) { init_completion(&wait->completion); } /* * Algorithm registration interface. */ int crypto_register_alg(struct crypto_alg *alg); void crypto_unregister_alg(struct crypto_alg *alg); int crypto_register_algs(struct crypto_alg *algs, int count); void crypto_unregister_algs(struct crypto_alg *algs, int count); /* * Algorithm query interface. */ int crypto_has_alg(const char *name, u32 type, u32 mask); /* * Transforms: user-instantiated objects which encapsulate algorithms * and core processing logic. Managed via crypto_alloc_*() and * crypto_free_*(), as well as the various helpers below. */ struct crypto_tfm { u32 crt_flags; int node; void (*exit)(struct crypto_tfm *tfm); struct crypto_alg *__crt_alg; void *__crt_ctx[] CRYPTO_MINALIGN_ATTR; }; struct crypto_comp { struct crypto_tfm base; }; /* * Transform user interface. */ struct crypto_tfm *crypto_alloc_base(const char *alg_name, u32 type, u32 mask); void crypto_destroy_tfm(void *mem, struct crypto_tfm *tfm); static inline void crypto_free_tfm(struct crypto_tfm *tfm) { return crypto_destroy_tfm(tfm, tfm); } int alg_test(const char *driver, const char *alg, u32 type, u32 mask); /* * Transform helpers which query the underlying algorithm. */ static inline const char *crypto_tfm_alg_name(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_name; } static inline const char *crypto_tfm_alg_driver_name(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_driver_name; } static inline int crypto_tfm_alg_priority(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_priority; } static inline u32 crypto_tfm_alg_type(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_flags & CRYPTO_ALG_TYPE_MASK; } static inline unsigned int crypto_tfm_alg_blocksize(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_blocksize; } static inline unsigned int crypto_tfm_alg_alignmask(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_alignmask; } static inline u32 crypto_tfm_get_flags(struct crypto_tfm *tfm) { return tfm->crt_flags; } static inline void crypto_tfm_set_flags(struct crypto_tfm *tfm, u32 flags) { tfm->crt_flags |= flags; } static inline void crypto_tfm_clear_flags(struct crypto_tfm *tfm, u32 flags) { tfm->crt_flags &= ~flags; } static inline void *crypto_tfm_ctx(struct crypto_tfm *tfm) { return tfm->__crt_ctx; } static inline unsigned int crypto_tfm_ctx_alignment(void) { struct crypto_tfm *tfm; return __alignof__(tfm->__crt_ctx); } static inline struct crypto_comp *__crypto_comp_cast(struct crypto_tfm *tfm) { return (struct crypto_comp *)tfm; } static inline struct crypto_comp *crypto_alloc_comp(const char *alg_name, u32 type, u32 mask) { type &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_COMPRESS; mask |= CRYPTO_ALG_TYPE_MASK; return __crypto_comp_cast(crypto_alloc_base(alg_name, type, mask)); } static inline struct crypto_tfm *crypto_comp_tfm(struct crypto_comp *tfm) { return &tfm->base; } static inline void crypto_free_comp(struct crypto_comp *tfm) { crypto_free_tfm(crypto_comp_tfm(tfm)); } static inline int crypto_has_comp(const char *alg_name, u32 type, u32 mask) { type &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_COMPRESS; mask |= CRYPTO_ALG_TYPE_MASK; return crypto_has_alg(alg_name, type, mask); } static inline const char *crypto_comp_name(struct crypto_comp *tfm) { return crypto_tfm_alg_name(crypto_comp_tfm(tfm)); } int crypto_comp_compress(struct crypto_comp *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen); int crypto_comp_decompress(struct crypto_comp *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen); #endif /* _LINUX_CRYPTO_H */ |
| 122 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_MROUTE6_H #define __LINUX_MROUTE6_H #include <linux/pim.h> #include <linux/skbuff.h> /* for struct sk_buff_head */ #include <net/net_namespace.h> #include <uapi/linux/mroute6.h> #include <linux/mroute_base.h> #include <linux/sockptr.h> #include <net/fib_rules.h> #ifdef CONFIG_IPV6_MROUTE static inline int ip6_mroute_opt(int opt) { return (opt >= MRT6_BASE) && (opt <= MRT6_MAX); } #else static inline int ip6_mroute_opt(int opt) { return 0; } #endif struct sock; #ifdef CONFIG_IPV6_MROUTE extern int ip6_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int); extern int ip6_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t); extern int ip6_mr_input(struct sk_buff *skb); extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg); extern int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); extern int ip6_mr_init(void); extern void ip6_mr_cleanup(void); #else static inline int ip6_mroute_setsockopt(struct sock *sock, int optname, sockptr_t optval, unsigned int optlen) { return -ENOPROTOOPT; } static inline int ip6_mroute_getsockopt(struct sock *sock, int optname, sockptr_t optval, sockptr_t optlen) { return -ENOPROTOOPT; } static inline int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) { return -ENOIOCTLCMD; } static inline int ip6_mr_init(void) { return 0; } static inline void ip6_mr_cleanup(void) { return; } #endif #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES bool ip6mr_rule_default(const struct fib_rule *rule); #else static inline bool ip6mr_rule_default(const struct fib_rule *rule) { return true; } #endif #define VIFF_STATIC 0x8000 struct mfc6_cache_cmp_arg { struct in6_addr mf6c_mcastgrp; struct in6_addr mf6c_origin; }; struct mfc6_cache { struct mr_mfc _c; union { struct { struct in6_addr mf6c_mcastgrp; struct in6_addr mf6c_origin; }; struct mfc6_cache_cmp_arg cmparg; }; }; #define MFC_ASSERT_THRESH (3*HZ) /* Maximal freq. of asserts */ struct rtmsg; extern int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, u32 portid); #ifdef CONFIG_IPV6_MROUTE bool mroute6_is_socket(struct net *net, struct sk_buff *skb); extern int ip6mr_sk_done(struct sock *sk); #else static inline bool mroute6_is_socket(struct net *net, struct sk_buff *skb) { return false; } static inline int ip6mr_sk_done(struct sock *sk) { return 0; } #endif #endif |
| 421 2 421 443 32 367 121 100 100 419 419 419 419 418 283 284 284 284 284 284 283 283 283 284 283 283 283 284 419 419 418 419 419 80 80 417 419 419 100 100 99 1 1 7 418 367 82 69 418 1 418 418 418 418 418 418 418 418 418 419 419 419 1 419 70 433 433 433 432 431 431 428 427 425 424 423 423 420 419 423 422 358 421 421 421 434 434 433 433 433 30 418 421 421 68 1 67 420 31 419 310 419 419 419 419 418 203 232 202 232 234 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 | // SPDX-License-Identifier: LGPL-2.1 /* * Copyright (c) 2008,2009 NEC Software Tohoku, Ltd. * Written by Takashi Sato <t-sato@yk.jp.nec.com> * Akira Fujita <a-fujita@rs.jp.nec.com> */ #include <linux/fs.h> #include <linux/quotaops.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include "ext4_jbd2.h" #include "ext4.h" #include "ext4_extents.h" /** * get_ext_path() - Find an extent path for designated logical block number. * @inode: inode to be searched * @lblock: logical block number to find an extent path * @ppath: pointer to an extent path pointer (for output) * * ext4_find_extent wrapper. Return 0 on success, or a negative error value * on failure. */ static inline int get_ext_path(struct inode *inode, ext4_lblk_t lblock, struct ext4_ext_path **ppath) { struct ext4_ext_path *path; path = ext4_find_extent(inode, lblock, ppath, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); if (path[ext_depth(inode)].p_ext == NULL) { ext4_free_ext_path(path); *ppath = NULL; return -ENODATA; } *ppath = path; return 0; } /** * ext4_double_down_write_data_sem() - write lock two inodes's i_data_sem * @first: inode to be locked * @second: inode to be locked * * Acquire write lock of i_data_sem of the two inodes */ void ext4_double_down_write_data_sem(struct inode *first, struct inode *second) { if (first < second) { down_write(&EXT4_I(first)->i_data_sem); down_write_nested(&EXT4_I(second)->i_data_sem, I_DATA_SEM_OTHER); } else { down_write(&EXT4_I(second)->i_data_sem); down_write_nested(&EXT4_I(first)->i_data_sem, I_DATA_SEM_OTHER); } } /** * ext4_double_up_write_data_sem - Release two inodes' write lock of i_data_sem * * @orig_inode: original inode structure to be released its lock first * @donor_inode: donor inode structure to be released its lock second * Release write lock of i_data_sem of two inodes (orig and donor). */ void ext4_double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode) { up_write(&EXT4_I(orig_inode)->i_data_sem); up_write(&EXT4_I(donor_inode)->i_data_sem); } /** * mext_check_coverage - Check that all extents in range has the same type * * @inode: inode in question * @from: block offset of inode * @count: block count to be checked * @unwritten: extents expected to be unwritten * @err: pointer to save error value * * Return 1 if all extents in range has expected type, and zero otherwise. */ static int mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count, int unwritten, int *err) { struct ext4_ext_path *path = NULL; struct ext4_extent *ext; int ret = 0; ext4_lblk_t last = from + count; while (from < last) { *err = get_ext_path(inode, from, &path); if (*err) goto out; ext = path[ext_depth(inode)].p_ext; if (unwritten != ext4_ext_is_unwritten(ext)) goto out; from += ext4_ext_get_actual_len(ext); } ret = 1; out: ext4_free_ext_path(path); return ret; } /** * mext_page_double_lock - Grab and lock pages on both @inode1 and @inode2 * * @inode1: the inode structure * @inode2: the inode structure * @index1: page index * @index2: page index * @page: result page vector * * Grab two locked pages for inode's by inode order */ static int mext_page_double_lock(struct inode *inode1, struct inode *inode2, pgoff_t index1, pgoff_t index2, struct page *page[2]) { struct address_space *mapping[2]; unsigned int flags; BUG_ON(!inode1 || !inode2); if (inode1 < inode2) { mapping[0] = inode1->i_mapping; mapping[1] = inode2->i_mapping; } else { swap(index1, index2); mapping[0] = inode2->i_mapping; mapping[1] = inode1->i_mapping; } flags = memalloc_nofs_save(); page[0] = grab_cache_page_write_begin(mapping[0], index1); if (!page[0]) { memalloc_nofs_restore(flags); return -ENOMEM; } page[1] = grab_cache_page_write_begin(mapping[1], index2); memalloc_nofs_restore(flags); if (!page[1]) { unlock_page(page[0]); put_page(page[0]); return -ENOMEM; } /* * grab_cache_page_write_begin() may not wait on page's writeback if * BDI not demand that. But it is reasonable to be very conservative * here and explicitly wait on page's writeback */ wait_on_page_writeback(page[0]); wait_on_page_writeback(page[1]); if (inode1 > inode2) swap(page[0], page[1]); return 0; } /* Force page buffers uptodate w/o dropping page's lock */ static int mext_page_mkuptodate(struct page *page, unsigned from, unsigned to) { struct inode *inode = page->mapping->host; sector_t block; struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE]; unsigned int blocksize, block_start, block_end; int i, err, nr = 0, partial = 0; BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); if (PageUptodate(page)) return 0; blocksize = i_blocksize(inode); if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); head = page_buffers(page); block = (sector_t)page->index << (PAGE_SHIFT - inode->i_blkbits); for (bh = head, block_start = 0; bh != head || !block_start; block++, block_start = block_end, bh = bh->b_this_page) { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (!buffer_uptodate(bh)) partial = 1; continue; } if (buffer_uptodate(bh)) continue; if (!buffer_mapped(bh)) { err = ext4_get_block(inode, block, bh, 0); if (err) { SetPageError(page); return err; } if (!buffer_mapped(bh)) { zero_user(page, block_start, blocksize); set_buffer_uptodate(bh); continue; } } BUG_ON(nr >= MAX_BUF_PER_PAGE); arr[nr++] = bh; } /* No io required */ if (!nr) goto out; for (i = 0; i < nr; i++) { bh = arr[i]; if (!bh_uptodate_or_lock(bh)) { err = ext4_read_bh(bh, 0, NULL); if (err) return err; } } out: if (!partial) SetPageUptodate(page); return 0; } /** * move_extent_per_page - Move extent data per page * * @o_filp: file structure of original file * @donor_inode: donor inode * @orig_page_offset: page index on original file * @donor_page_offset: page index on donor file * @data_offset_in_page: block index where data swapping starts * @block_len_in_page: the number of blocks to be swapped * @unwritten: orig extent is unwritten or not * @err: pointer to save return value * * Save the data in original inode blocks and replace original inode extents * with donor inode extents by calling ext4_swap_extents(). * Finally, write out the saved data in new original inode blocks. Return * replaced block count. */ static int move_extent_per_page(struct file *o_filp, struct inode *donor_inode, pgoff_t orig_page_offset, pgoff_t donor_page_offset, int data_offset_in_page, int block_len_in_page, int unwritten, int *err) { struct inode *orig_inode = file_inode(o_filp); struct page *pagep[2] = {NULL, NULL}; handle_t *handle; ext4_lblk_t orig_blk_offset, donor_blk_offset; unsigned long blocksize = orig_inode->i_sb->s_blocksize; unsigned int tmp_data_size, data_size, replaced_size; int i, err2, jblocks, retries = 0; int replaced_count = 0; int from = data_offset_in_page << orig_inode->i_blkbits; int blocks_per_page = PAGE_SIZE >> orig_inode->i_blkbits; struct super_block *sb = orig_inode->i_sb; struct buffer_head *bh = NULL; /* * It needs twice the amount of ordinary journal buffers because * inode and donor_inode may change each different metadata blocks. */ again: *err = 0; jblocks = ext4_writepage_trans_blocks(orig_inode) * 2; handle = ext4_journal_start(orig_inode, EXT4_HT_MOVE_EXTENTS, jblocks); if (IS_ERR(handle)) { *err = PTR_ERR(handle); return 0; } orig_blk_offset = orig_page_offset * blocks_per_page + data_offset_in_page; donor_blk_offset = donor_page_offset * blocks_per_page + data_offset_in_page; /* Calculate data_size */ if ((orig_blk_offset + block_len_in_page - 1) == ((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) { /* Replace the last block */ tmp_data_size = orig_inode->i_size & (blocksize - 1); /* * If data_size equal zero, it shows data_size is multiples of * blocksize. So we set appropriate value. */ if (tmp_data_size == 0) tmp_data_size = blocksize; data_size = tmp_data_size + ((block_len_in_page - 1) << orig_inode->i_blkbits); } else data_size = block_len_in_page << orig_inode->i_blkbits; replaced_size = data_size; *err = mext_page_double_lock(orig_inode, donor_inode, orig_page_offset, donor_page_offset, pagep); if (unlikely(*err < 0)) goto stop_journal; /* * If orig extent was unwritten it can become initialized * at any time after i_data_sem was dropped, in order to * serialize with delalloc we have recheck extent while we * hold page's lock, if it is still the case data copy is not * necessary, just swap data blocks between orig and donor. */ if (unwritten) { ext4_double_down_write_data_sem(orig_inode, donor_inode); /* If any of extents in range became initialized we have to * fallback to data copying */ unwritten = mext_check_coverage(orig_inode, orig_blk_offset, block_len_in_page, 1, err); if (*err) goto drop_data_sem; unwritten &= mext_check_coverage(donor_inode, donor_blk_offset, block_len_in_page, 1, err); if (*err) goto drop_data_sem; if (!unwritten) { ext4_double_up_write_data_sem(orig_inode, donor_inode); goto data_copy; } if ((page_has_private(pagep[0]) && !try_to_release_page(pagep[0], 0)) || (page_has_private(pagep[1]) && !try_to_release_page(pagep[1], 0))) { *err = -EBUSY; goto drop_data_sem; } replaced_count = ext4_swap_extents(handle, orig_inode, donor_inode, orig_blk_offset, donor_blk_offset, block_len_in_page, 1, err); drop_data_sem: ext4_double_up_write_data_sem(orig_inode, donor_inode); goto unlock_pages; } data_copy: *err = mext_page_mkuptodate(pagep[0], from, from + replaced_size); if (*err) goto unlock_pages; /* At this point all buffers in range are uptodate, old mapping layout * is no longer required, try to drop it now. */ if ((page_has_private(pagep[0]) && !try_to_release_page(pagep[0], 0)) || (page_has_private(pagep[1]) && !try_to_release_page(pagep[1], 0))) { *err = -EBUSY; goto unlock_pages; } ext4_double_down_write_data_sem(orig_inode, donor_inode); replaced_count = ext4_swap_extents(handle, orig_inode, donor_inode, orig_blk_offset, donor_blk_offset, block_len_in_page, 1, err); ext4_double_up_write_data_sem(orig_inode, donor_inode); if (*err) { if (replaced_count) { block_len_in_page = replaced_count; replaced_size = block_len_in_page << orig_inode->i_blkbits; } else goto unlock_pages; } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ if (!page_has_buffers(pagep[0])) create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0); bh = page_buffers(pagep[0]); for (i = 0; i < data_offset_in_page; i++) bh = bh->b_this_page; for (i = 0; i < block_len_in_page; i++) { *err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0); if (*err < 0) break; bh = bh->b_this_page; } if (!*err) *err = block_commit_write(pagep[0], from, from + replaced_size); if (unlikely(*err < 0)) goto repair_branches; /* Even in case of data=writeback it is reasonable to pin * inode to transaction, to prevent unexpected data loss */ *err = ext4_jbd2_inode_add_write(handle, orig_inode, (loff_t)orig_page_offset << PAGE_SHIFT, replaced_size); unlock_pages: unlock_page(pagep[0]); put_page(pagep[0]); unlock_page(pagep[1]); put_page(pagep[1]); stop_journal: ext4_journal_stop(handle); if (*err == -ENOSPC && ext4_should_retry_alloc(sb, &retries)) goto again; /* Buffer was busy because probably is pinned to journal transaction, * force transaction commit may help to free it. */ if (*err == -EBUSY && retries++ < 4 && EXT4_SB(sb)->s_journal && jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal)) goto again; return replaced_count; repair_branches: /* * This should never ever happen! * Extents are swapped already, but we are not able to copy data. * Try to swap extents to it's original places */ ext4_double_down_write_data_sem(orig_inode, donor_inode); replaced_count = ext4_swap_extents(handle, donor_inode, orig_inode, orig_blk_offset, donor_blk_offset, block_len_in_page, 0, &err2); ext4_double_up_write_data_sem(orig_inode, donor_inode); if (replaced_count != block_len_in_page) { ext4_error_inode_block(orig_inode, (sector_t)(orig_blk_offset), EIO, "Unable to copy data block," " data will be lost."); *err = -EIO; } replaced_count = 0; goto unlock_pages; } /** * mext_check_arguments - Check whether move extent can be done * * @orig_inode: original inode * @donor_inode: donor inode * @orig_start: logical start offset in block for orig * @donor_start: logical start offset in block for donor * @len: the number of blocks to be moved * * Check the arguments of ext4_move_extents() whether the files can be * exchanged with each other. * Return 0 on success, or a negative error value on failure. */ static int mext_check_arguments(struct inode *orig_inode, struct inode *donor_inode, __u64 orig_start, __u64 donor_start, __u64 *len) { __u64 orig_eof, donor_eof; unsigned int blkbits = orig_inode->i_blkbits; unsigned int blocksize = 1 << blkbits; orig_eof = (i_size_read(orig_inode) + blocksize - 1) >> blkbits; donor_eof = (i_size_read(donor_inode) + blocksize - 1) >> blkbits; if (donor_inode->i_mode & (S_ISUID|S_ISGID)) { ext4_debug("ext4 move extent: suid or sgid is set" " to donor file [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } if (IS_IMMUTABLE(donor_inode) || IS_APPEND(donor_inode)) return -EPERM; /* Ext4 move extent does not support swap files */ if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) { ext4_debug("ext4 move extent: The argument files should not be swap files [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -ETXTBSY; } if (ext4_is_quota_file(orig_inode) && ext4_is_quota_file(donor_inode)) { ext4_debug("ext4 move extent: The argument files should not be quota files [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EOPNOTSUPP; } /* Ext4 move extent supports only extent based file */ if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) { ext4_debug("ext4 move extent: orig file is not extents " "based file [ino:orig %lu]\n", orig_inode->i_ino); return -EOPNOTSUPP; } else if (!(ext4_test_inode_flag(donor_inode, EXT4_INODE_EXTENTS))) { ext4_debug("ext4 move extent: donor file is not extents " "based file [ino:donor %lu]\n", donor_inode->i_ino); return -EOPNOTSUPP; } if ((!orig_inode->i_size) || (!donor_inode->i_size)) { ext4_debug("ext4 move extent: File size is 0 byte\n"); return -EINVAL; } /* Start offset should be same */ if ((orig_start & ~(PAGE_MASK >> orig_inode->i_blkbits)) != (donor_start & ~(PAGE_MASK >> orig_inode->i_blkbits))) { ext4_debug("ext4 move extent: orig and donor's start " "offsets are not aligned [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } if ((orig_start >= EXT_MAX_BLOCKS) || (donor_start >= EXT_MAX_BLOCKS) || (*len > EXT_MAX_BLOCKS) || (donor_start + *len >= EXT_MAX_BLOCKS) || (orig_start + *len >= EXT_MAX_BLOCKS)) { ext4_debug("ext4 move extent: Can't handle over [%u] blocks " "[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCKS, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } if (orig_eof <= orig_start) *len = 0; else if (orig_eof < orig_start + *len - 1) *len = orig_eof - orig_start; if (donor_eof <= donor_start) *len = 0; else if (donor_eof < donor_start + *len - 1) *len = donor_eof - donor_start; if (!*len) { ext4_debug("ext4 move extent: len should not be 0 " "[ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } return 0; } /** * ext4_move_extents - Exchange the specified range of a file * * @o_filp: file structure of the original file * @d_filp: file structure of the donor file * @orig_blk: start offset in block for orig * @donor_blk: start offset in block for donor * @len: the number of blocks to be moved * @moved_len: moved block length * * This function returns 0 and moved block length is set in moved_len * if succeed, otherwise returns error value. * */ int ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, __u64 donor_blk, __u64 len, __u64 *moved_len) { struct inode *orig_inode = file_inode(o_filp); struct inode *donor_inode = file_inode(d_filp); struct ext4_ext_path *path = NULL; int blocks_per_page = PAGE_SIZE >> orig_inode->i_blkbits; ext4_lblk_t o_end, o_start = orig_blk; ext4_lblk_t d_start = donor_blk; int ret; if (orig_inode->i_sb != donor_inode->i_sb) { ext4_debug("ext4 move extent: The argument files " "should be in same FS [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } /* orig and donor should be different inodes */ if (orig_inode == donor_inode) { ext4_debug("ext4 move extent: The argument files should not " "be same inode [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } /* Regular file check */ if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) { ext4_debug("ext4 move extent: The argument files should be " "regular file [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } /* TODO: it's not obvious how to swap blocks for inodes with full journaling enabled */ if (ext4_should_journal_data(orig_inode) || ext4_should_journal_data(donor_inode)) { ext4_msg(orig_inode->i_sb, KERN_ERR, "Online defrag not supported with data journaling"); return -EOPNOTSUPP; } if (IS_ENCRYPTED(orig_inode) || IS_ENCRYPTED(donor_inode)) { ext4_msg(orig_inode->i_sb, KERN_ERR, "Online defrag not supported for encrypted files"); return -EOPNOTSUPP; } /* Protect orig and donor inodes against a truncate */ lock_two_nondirectories(orig_inode, donor_inode); /* Wait for all existing dio workers */ inode_dio_wait(orig_inode); inode_dio_wait(donor_inode); /* Protect extent tree against block allocations via delalloc */ ext4_double_down_write_data_sem(orig_inode, donor_inode); /* Check the filesystem environment whether move_extent can be done */ ret = mext_check_arguments(orig_inode, donor_inode, orig_blk, donor_blk, &len); if (ret) goto out; o_end = o_start + len; while (o_start < o_end) { struct ext4_extent *ex; ext4_lblk_t cur_blk, next_blk; pgoff_t orig_page_index, donor_page_index; int offset_in_page; int unwritten, cur_len; ret = get_ext_path(orig_inode, o_start, &path); if (ret) goto out; ex = path[path->p_depth].p_ext; cur_blk = le32_to_cpu(ex->ee_block); cur_len = ext4_ext_get_actual_len(ex); /* Check hole before the start pos */ if (cur_blk + cur_len - 1 < o_start) { next_blk = ext4_ext_next_allocated_block(path); if (next_blk == EXT_MAX_BLOCKS) { ret = -ENODATA; goto out; } d_start += next_blk - o_start; o_start = next_blk; continue; /* Check hole after the start pos */ } else if (cur_blk > o_start) { /* Skip hole */ d_start += cur_blk - o_start; o_start = cur_blk; /* Extent inside requested range ?*/ if (cur_blk >= o_end) goto out; } else { /* in_range(o_start, o_blk, o_len) */ cur_len += cur_blk - o_start; } unwritten = ext4_ext_is_unwritten(ex); if (o_end - o_start < cur_len) cur_len = o_end - o_start; orig_page_index = o_start >> (PAGE_SHIFT - orig_inode->i_blkbits); donor_page_index = d_start >> (PAGE_SHIFT - donor_inode->i_blkbits); offset_in_page = o_start % blocks_per_page; if (cur_len > blocks_per_page - offset_in_page) cur_len = blocks_per_page - offset_in_page; /* * Up semaphore to avoid following problems: * a. transaction deadlock among ext4_journal_start, * ->write_begin via pagefault, and jbd2_journal_commit * b. racing with ->read_folio, ->write_begin, and * ext4_get_block in move_extent_per_page */ ext4_double_up_write_data_sem(orig_inode, donor_inode); /* Swap original branches with new branches */ move_extent_per_page(o_filp, donor_inode, orig_page_index, donor_page_index, offset_in_page, cur_len, unwritten, &ret); ext4_double_down_write_data_sem(orig_inode, donor_inode); if (ret < 0) break; o_start += cur_len; d_start += cur_len; } *moved_len = o_start - orig_blk; if (*moved_len > len) *moved_len = len; out: if (*moved_len) { ext4_discard_preallocations(orig_inode, 0); ext4_discard_preallocations(donor_inode, 0); } ext4_free_ext_path(path); ext4_double_up_write_data_sem(orig_inode, donor_inode); unlock_two_nondirectories(orig_inode, donor_inode); return ret; } |
| 26 391 5214 57 72 84 90 126 136 196 218 5105 5110 5208 5214 384 886 8 47 862 263 492 858 4 4 4 56 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | #ifndef _LINUX_JHASH_H #define _LINUX_JHASH_H /* jhash.h: Jenkins hash support. * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * https://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * * These are functions for producing 32-bit hashes for hash table lookup. * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() * are externally useful functions. Routines to test the hash are included * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. * Jozsef */ #include <linux/bitops.h> #include <linux/unaligned/packed_struct.h> /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) /* __jhash_mix -- mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ b -= a; b ^= rol32(a, 6); a += c; \ c -= b; c ^= rol32(b, 8); b += a; \ a -= c; a ^= rol32(c, 16); c += b; \ b -= a; b ^= rol32(a, 19); a += c; \ c -= b; c ^= rol32(b, 4); b += a; \ } /* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ #define __jhash_final(a, b, c) \ { \ c ^= b; c -= rol32(b, 14); \ a ^= c; a -= rol32(c, 11); \ b ^= a; b -= rol32(a, 25); \ c ^= b; c -= rol32(b, 16); \ a ^= c; a -= rol32(c, 4); \ b ^= a; b -= rol32(a, 14); \ c ^= b; c -= rol32(b, 24); \ } /* An arbitrary initial parameter */ #define JHASH_INITVAL 0xdeadbeef /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key * @initval: the previous hash, or an arbitray value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. * * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { u32 a, b, c; const u8 *k = key; /* Set up the internal state */ a = b = c = JHASH_INITVAL + length + initval; /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { a += __get_unaligned_cpu32(k); b += __get_unaligned_cpu32(k + 4); c += __get_unaligned_cpu32(k + 8); __jhash_mix(a, b, c); length -= 12; k += 12; } /* Last block: affect all 32 bits of (c) */ switch (length) { case 12: c += (u32)k[11]<<24; fallthrough; case 11: c += (u32)k[10]<<16; fallthrough; case 10: c += (u32)k[9]<<8; fallthrough; case 9: c += k[8]; fallthrough; case 8: b += (u32)k[7]<<24; fallthrough; case 7: b += (u32)k[6]<<16; fallthrough; case 6: b += (u32)k[5]<<8; fallthrough; case 5: b += k[4]; fallthrough; case 4: a += (u32)k[3]<<24; fallthrough; case 3: a += (u32)k[2]<<16; fallthrough; case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key * @initval: the previous hash, or an arbitray value * * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { u32 a, b, c; /* Set up the internal state */ a = b = c = JHASH_INITVAL + (length<<2) + initval; /* Handle most of the key */ while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); length -= 3; k += 3; } /* Handle the last 3 u32's */ switch (length) { case 3: c += k[2]; fallthrough; case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; b += initval; c += initval; __jhash_final(a, b, c); return c; } static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); } static inline u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); } static inline u32 jhash_1word(u32 a, u32 initval) { return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); } #endif /* _LINUX_JHASH_H */ |
| 1565 1565 1565 1570 1565 1565 1565 1565 1565 1565 1570 1570 1570 1565 1565 1565 1565 1565 1565 1570 1570 1570 1570 1570 1565 1570 1570 1565 1570 1570 1564 640 640 1 95 96 96 96 1 1 1 1638 1638 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 | /* netfilter.c: look after the filters for various protocols. * Heavily influenced by the old firewall.c by David Bonn and Alan Cox. * * Thanks to Rob `CmdrTaco' Malda for not influencing this code in any * way. * * This code is GPL. */ #include <linux/kernel.h> #include <linux/netfilter.h> #include <net/protocol.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/wait.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/if.h> #include <linux/netdevice.h> #include <linux/netfilter_ipv6.h> #include <linux/inetdevice.h> #include <linux/proc_fs.h> #include <linux/mutex.h> #include <linux/mm.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include <net/netfilter/nf_queue.h> #include <net/sock.h> #include "nf_internals.h" const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_ipv6_ops); DEFINE_PER_CPU(bool, nf_skb_duplicated); EXPORT_SYMBOL_GPL(nf_skb_duplicated); #ifdef CONFIG_JUMP_LABEL struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; EXPORT_SYMBOL(nf_hooks_needed); #endif static DEFINE_MUTEX(nf_hook_mutex); /* max hooks per family/hooknum */ #define MAX_HOOK_COUNT 1024 #define nf_entry_dereference(e) \ rcu_dereference_protected(e, lockdep_is_held(&nf_hook_mutex)) static struct nf_hook_entries *allocate_hook_entries_size(u16 num) { struct nf_hook_entries *e; size_t alloc = sizeof(*e) + sizeof(struct nf_hook_entry) * num + sizeof(struct nf_hook_ops *) * num + sizeof(struct nf_hook_entries_rcu_head); if (num == 0) return NULL; e = kvzalloc(alloc, GFP_KERNEL_ACCOUNT); if (e) e->num_hook_entries = num; return e; } static void __nf_hook_entries_free(struct rcu_head *h) { struct nf_hook_entries_rcu_head *head; head = container_of(h, struct nf_hook_entries_rcu_head, head); kvfree(head->allocation); } static void nf_hook_entries_free(struct nf_hook_entries *e) { struct nf_hook_entries_rcu_head *head; struct nf_hook_ops **ops; unsigned int num; if (!e) return; num = e->num_hook_entries; ops = nf_hook_entries_get_hook_ops(e); head = (void *)&ops[num]; head->allocation = e; call_rcu(&head->head, __nf_hook_entries_free); } static unsigned int accept_all(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return NF_ACCEPT; /* ACCEPT makes nf_hook_slow call next hook */ } static const struct nf_hook_ops dummy_ops = { .hook = accept_all, .priority = INT_MIN, }; static struct nf_hook_entries * nf_hook_entries_grow(const struct nf_hook_entries *old, const struct nf_hook_ops *reg) { unsigned int i, alloc_entries, nhooks, old_entries; struct nf_hook_ops **orig_ops = NULL; struct nf_hook_ops **new_ops; struct nf_hook_entries *new; bool inserted = false; alloc_entries = 1; old_entries = old ? old->num_hook_entries : 0; if (old) { orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old_entries; i++) { if (orig_ops[i] != &dummy_ops) alloc_entries++; } } if (alloc_entries > MAX_HOOK_COUNT) return ERR_PTR(-E2BIG); new = allocate_hook_entries_size(alloc_entries); if (!new) return ERR_PTR(-ENOMEM); new_ops = nf_hook_entries_get_hook_ops(new); i = 0; nhooks = 0; while (i < old_entries) { if (orig_ops[i] == &dummy_ops) { ++i; continue; } if (inserted || reg->priority > orig_ops[i]->priority) { new_ops[nhooks] = (void *)orig_ops[i]; new->hooks[nhooks] = old->hooks[i]; i++; } else { new_ops[nhooks] = (void *)reg; new->hooks[nhooks].hook = reg->hook; new->hooks[nhooks].priv = reg->priv; inserted = true; } nhooks++; } if (!inserted) { new_ops[nhooks] = (void *)reg; new->hooks[nhooks].hook = reg->hook; new->hooks[nhooks].priv = reg->priv; } return new; } static void hooks_validate(const struct nf_hook_entries *hooks) { #ifdef CONFIG_DEBUG_MISC struct nf_hook_ops **orig_ops; int prio = INT_MIN; size_t i = 0; orig_ops = nf_hook_entries_get_hook_ops(hooks); for (i = 0; i < hooks->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) continue; WARN_ON(orig_ops[i]->priority < prio); if (orig_ops[i]->priority > prio) prio = orig_ops[i]->priority; } #endif } int nf_hook_entries_insert_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg) { struct nf_hook_entries *new_hooks; struct nf_hook_entries *p; p = rcu_dereference_raw(*pp); new_hooks = nf_hook_entries_grow(p, reg); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks); hooks_validate(new_hooks); rcu_assign_pointer(*pp, new_hooks); BUG_ON(p == new_hooks); nf_hook_entries_free(p); return 0; } EXPORT_SYMBOL_GPL(nf_hook_entries_insert_raw); /* * __nf_hook_entries_try_shrink - try to shrink hook array * * @old -- current hook blob at @pp * @pp -- location of hook blob * * Hook unregistration must always succeed, so to-be-removed hooks * are replaced by a dummy one that will just move to next hook. * * This counts the current dummy hooks, attempts to allocate new blob, * copies the live hooks, then replaces and discards old one. * * return values: * * Returns address to free, or NULL. */ static void *__nf_hook_entries_try_shrink(struct nf_hook_entries *old, struct nf_hook_entries __rcu **pp) { unsigned int i, j, skip = 0, hook_entries; struct nf_hook_entries *new = NULL; struct nf_hook_ops **orig_ops; struct nf_hook_ops **new_ops; if (WARN_ON_ONCE(!old)) return NULL; orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) skip++; } /* if skip == hook_entries all hooks have been removed */ hook_entries = old->num_hook_entries; if (skip == hook_entries) goto out_assign; if (skip == 0) return NULL; hook_entries -= skip; new = allocate_hook_entries_size(hook_entries); if (!new) return NULL; new_ops = nf_hook_entries_get_hook_ops(new); for (i = 0, j = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) continue; new->hooks[j] = old->hooks[i]; new_ops[j] = (void *)orig_ops[i]; j++; } hooks_validate(new); out_assign: rcu_assign_pointer(*pp, new); return old; } static struct nf_hook_entries __rcu ** nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, struct net_device *dev) { switch (pf) { case NFPROTO_NETDEV: break; #ifdef CONFIG_NETFILTER_FAMILY_ARP case NFPROTO_ARP: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_arp) <= hooknum)) return NULL; return net->nf.hooks_arp + hooknum; #endif #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE case NFPROTO_BRIDGE: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_bridge) <= hooknum)) return NULL; return net->nf.hooks_bridge + hooknum; #endif #ifdef CONFIG_NETFILTER_INGRESS case NFPROTO_INET: if (WARN_ON_ONCE(hooknum != NF_INET_INGRESS)) return NULL; if (!dev || dev_net(dev) != net) { WARN_ON_ONCE(1); return NULL; } return &dev->nf_hooks_ingress; #endif case NFPROTO_IPV4: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv4) <= hooknum)) return NULL; return net->nf.hooks_ipv4 + hooknum; case NFPROTO_IPV6: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv6) <= hooknum)) return NULL; return net->nf.hooks_ipv6 + hooknum; default: WARN_ON_ONCE(1); return NULL; } #ifdef CONFIG_NETFILTER_INGRESS if (hooknum == NF_NETDEV_INGRESS) { if (dev && dev_net(dev) == net) return &dev->nf_hooks_ingress; } #endif #ifdef CONFIG_NETFILTER_EGRESS if (hooknum == NF_NETDEV_EGRESS) { if (dev && dev_net(dev) == net) return &dev->nf_hooks_egress; } #endif WARN_ON_ONCE(1); return NULL; } static int nf_ingress_check(struct net *net, const struct nf_hook_ops *reg, int hooknum) { #ifndef CONFIG_NETFILTER_INGRESS if (reg->hooknum == hooknum) return -EOPNOTSUPP; #endif if (reg->hooknum != hooknum || !reg->dev || dev_net(reg->dev) != net) return -EINVAL; return 0; } static inline bool __maybe_unused nf_ingress_hook(const struct nf_hook_ops *reg, int pf) { if ((pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) || (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS)) return true; return false; } static inline bool __maybe_unused nf_egress_hook(const struct nf_hook_ops *reg, int pf) { return pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_EGRESS; } static void nf_static_key_inc(const struct nf_hook_ops *reg, int pf) { #ifdef CONFIG_JUMP_LABEL int hooknum; if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) { pf = NFPROTO_NETDEV; hooknum = NF_NETDEV_INGRESS; } else { hooknum = reg->hooknum; } static_key_slow_inc(&nf_hooks_needed[pf][hooknum]); #endif } static void nf_static_key_dec(const struct nf_hook_ops *reg, int pf) { #ifdef CONFIG_JUMP_LABEL int hooknum; if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) { pf = NFPROTO_NETDEV; hooknum = NF_NETDEV_INGRESS; } else { hooknum = reg->hooknum; } static_key_slow_dec(&nf_hooks_needed[pf][hooknum]); #endif } static int __nf_register_net_hook(struct net *net, int pf, const struct nf_hook_ops *reg) { struct nf_hook_entries *p, *new_hooks; struct nf_hook_entries __rcu **pp; int err; switch (pf) { case NFPROTO_NETDEV: #ifndef CONFIG_NETFILTER_INGRESS if (reg->hooknum == NF_NETDEV_INGRESS) return -EOPNOTSUPP; #endif #ifndef CONFIG_NETFILTER_EGRESS if (reg->hooknum == NF_NETDEV_EGRESS) return -EOPNOTSUPP; #endif if ((reg->hooknum != NF_NETDEV_INGRESS && reg->hooknum != NF_NETDEV_EGRESS) || !reg->dev || dev_net(reg->dev) != net) return -EINVAL; break; case NFPROTO_INET: if (reg->hooknum != NF_INET_INGRESS) break; err = nf_ingress_check(net, reg, NF_INET_INGRESS); if (err < 0) return err; break; } pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev); if (!pp) return -EINVAL; mutex_lock(&nf_hook_mutex); p = nf_entry_dereference(*pp); new_hooks = nf_hook_entries_grow(p, reg); if (!IS_ERR(new_hooks)) { hooks_validate(new_hooks); rcu_assign_pointer(*pp, new_hooks); } mutex_unlock(&nf_hook_mutex); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks); #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_inc_ingress_queue(); #endif #ifdef CONFIG_NETFILTER_EGRESS if (nf_egress_hook(reg, pf)) net_inc_egress_queue(); #endif nf_static_key_inc(reg, pf); BUG_ON(p == new_hooks); nf_hook_entries_free(p); return 0; } /* * nf_remove_net_hook - remove a hook from blob * * @oldp: current address of hook blob * @unreg: hook to unregister * * This cannot fail, hook unregistration must always succeed. * Therefore replace the to-be-removed hook with a dummy hook. */ static bool nf_remove_net_hook(struct nf_hook_entries *old, const struct nf_hook_ops *unreg) { struct nf_hook_ops **orig_ops; unsigned int i; orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] != unreg) continue; WRITE_ONCE(old->hooks[i].hook, accept_all); WRITE_ONCE(orig_ops[i], (void *)&dummy_ops); return true; } return false; } static void __nf_unregister_net_hook(struct net *net, int pf, const struct nf_hook_ops *reg) { struct nf_hook_entries __rcu **pp; struct nf_hook_entries *p; pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev); if (!pp) return; mutex_lock(&nf_hook_mutex); p = nf_entry_dereference(*pp); if (WARN_ON_ONCE(!p)) { mutex_unlock(&nf_hook_mutex); return; } if (nf_remove_net_hook(p, reg)) { #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_dec_ingress_queue(); #endif #ifdef CONFIG_NETFILTER_EGRESS if (nf_egress_hook(reg, pf)) net_dec_egress_queue(); #endif nf_static_key_dec(reg, pf); } else { WARN_ONCE(1, "hook not found, pf %d num %d", pf, reg->hooknum); } p = __nf_hook_entries_try_shrink(p, pp); mutex_unlock(&nf_hook_mutex); if (!p) return; nf_queue_nf_hook_drop(net); nf_hook_entries_free(p); } void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) { if (reg->pf == NFPROTO_INET) { if (reg->hooknum == NF_INET_INGRESS) { __nf_unregister_net_hook(net, NFPROTO_INET, reg); } else { __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); __nf_unregister_net_hook(net, NFPROTO_IPV6, reg); } } else { __nf_unregister_net_hook(net, reg->pf, reg); } } EXPORT_SYMBOL(nf_unregister_net_hook); void nf_hook_entries_delete_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg) { struct nf_hook_entries *p; p = rcu_dereference_raw(*pp); if (nf_remove_net_hook(p, reg)) { p = __nf_hook_entries_try_shrink(p, pp); nf_hook_entries_free(p); } } EXPORT_SYMBOL_GPL(nf_hook_entries_delete_raw); int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) { int err; if (reg->pf == NFPROTO_INET) { if (reg->hooknum == NF_INET_INGRESS) { err = __nf_register_net_hook(net, NFPROTO_INET, reg); if (err < 0) return err; } else { err = __nf_register_net_hook(net, NFPROTO_IPV4, reg); if (err < 0) return err; err = __nf_register_net_hook(net, NFPROTO_IPV6, reg); if (err < 0) { __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); return err; } } } else { err = __nf_register_net_hook(net, reg->pf, reg); if (err < 0) return err; } return 0; } EXPORT_SYMBOL(nf_register_net_hook); int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = nf_register_net_hook(net, ®[i]); if (err) goto err; } return err; err: if (i > 0) nf_unregister_net_hooks(net, reg, i); return err; } EXPORT_SYMBOL(nf_register_net_hooks); void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int hookcount) { unsigned int i; for (i = 0; i < hookcount; i++) nf_unregister_net_hook(net, ®[i]); } EXPORT_SYMBOL(nf_unregister_net_hooks); /* Returns 1 if okfn() needs to be executed by the caller, * -EPERM for NF_DROP, 0 otherwise. Caller must hold rcu_read_lock. */ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *e, unsigned int s) { unsigned int verdict; int ret; for (; s < e->num_hook_entries; s++) { verdict = nf_hook_entry_hookfn(&e->hooks[s], skb, state); switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: break; case NF_DROP: kfree_skb_reason(skb, SKB_DROP_REASON_NETFILTER_DROP); ret = NF_DROP_GETERR(verdict); if (ret == 0) ret = -EPERM; return ret; case NF_QUEUE: ret = nf_queue(skb, state, s, verdict); if (ret == 1) continue; return ret; default: /* Implicit handling for NF_STOLEN, as well as any other * non conventional verdicts. */ return 0; } } return 1; } EXPORT_SYMBOL(nf_hook_slow); void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state, const struct nf_hook_entries *e) { struct sk_buff *skb, *next; struct list_head sublist; int ret; INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); ret = nf_hook_slow(skb, state, e, 0); if (ret == 1) list_add_tail(&skb->list, &sublist); } /* Put passed packets back on main list */ list_splice(&sublist, head); } EXPORT_SYMBOL(nf_hook_slow_list); /* This needs to be compiled in any case to avoid dependencies between the * nfnetlink_queue code and nf_conntrack. */ const struct nfnl_ct_hook __rcu *nfnl_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nfnl_ct_hook); const struct nf_ct_hook __rcu *nf_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_hook); #if IS_ENABLED(CONFIG_NF_CONNTRACK) const struct nf_nat_hook __rcu *nf_nat_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_hook); /* This does not belong here, but locally generated errors need it if connection * tracking in use: without this, connection may not be in hash table, and hence * manufactured ICMP or RST packets will not be associated with it. */ void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb) { const struct nf_ct_hook *ct_hook; if (skb->_nfct) { rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ct_hook->attach(new, skb); rcu_read_unlock(); } } EXPORT_SYMBOL(nf_ct_attach); void nf_conntrack_destroy(struct nf_conntrack *nfct) { const struct nf_ct_hook *ct_hook; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); BUG_ON(ct_hook == NULL); ct_hook->destroy(nfct); rcu_read_unlock(); } EXPORT_SYMBOL(nf_conntrack_destroy); bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { const struct nf_ct_hook *ct_hook; bool ret = false; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ret = ct_hook->get_tuple_skb(dst_tuple, skb); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(nf_ct_get_tuple_skb); /* Built-in default zone used e.g. by modules. */ const struct nf_conntrack_zone nf_ct_zone_dflt = { .id = NF_CT_DEFAULT_ZONE_ID, .dir = NF_CT_DEFAULT_ZONE_DIR, }; EXPORT_SYMBOL_GPL(nf_ct_zone_dflt); #endif /* CONFIG_NF_CONNTRACK */ static void __net_init __netfilter_net_init(struct nf_hook_entries __rcu **e, int max) { int h; for (h = 0; h < max; h++) RCU_INIT_POINTER(e[h], NULL); } static int __net_init netfilter_net_init(struct net *net) { __netfilter_net_init(net->nf.hooks_ipv4, ARRAY_SIZE(net->nf.hooks_ipv4)); __netfilter_net_init(net->nf.hooks_ipv6, ARRAY_SIZE(net->nf.hooks_ipv6)); #ifdef CONFIG_NETFILTER_FAMILY_ARP __netfilter_net_init(net->nf.hooks_arp, ARRAY_SIZE(net->nf.hooks_arp)); #endif #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE __netfilter_net_init(net->nf.hooks_bridge, ARRAY_SIZE(net->nf.hooks_bridge)); #endif #ifdef CONFIG_PROC_FS net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter", net->proc_net); if (!net->nf.proc_netfilter) { if (!net_eq(net, &init_net)) pr_err("cannot create netfilter proc entry"); return -ENOMEM; } #endif return 0; } static void __net_exit netfilter_net_exit(struct net *net) { remove_proc_entry("netfilter", net->proc_net); } static struct pernet_operations netfilter_net_ops = { .init = netfilter_net_init, .exit = netfilter_net_exit, }; int __init netfilter_init(void) { int ret; ret = register_pernet_subsys(&netfilter_net_ops); if (ret < 0) goto err; ret = netfilter_log_init(); if (ret < 0) goto err_pernet; return 0; err_pernet: unregister_pernet_subsys(&netfilter_net_ops); err: return ret; } |
| 1593 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 | // SPDX-License-Identifier: GPL-2.0-only /* * Common code for control of lockd and nfsv4 grace periods. * * Transplanted from lockd code */ #include <linux/module.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/fs.h> static unsigned int grace_net_id; static DEFINE_SPINLOCK(grace_lock); /** * locks_start_grace * @net: net namespace that this lock manager belongs to * @lm: who this grace period is for * * A grace period is a period during which locks should not be given * out. Currently grace periods are only enforced by the two lock * managers (lockd and nfsd), using the locks_in_grace() function to * check when they are in a grace period. * * This function is called to start a grace period. */ void locks_start_grace(struct net *net, struct lock_manager *lm) { struct list_head *grace_list = net_generic(net, grace_net_id); spin_lock(&grace_lock); if (list_empty(&lm->list)) list_add(&lm->list, grace_list); else WARN(1, "double list_add attempt detected in net %x %s\n", net->ns.inum, (net == &init_net) ? "(init_net)" : ""); spin_unlock(&grace_lock); } EXPORT_SYMBOL_GPL(locks_start_grace); /** * locks_end_grace * @lm: who this grace period is for * * Call this function to state that the given lock manager is ready to * resume regular locking. The grace period will not end until all lock * managers that called locks_start_grace() also call locks_end_grace(). * Note that callers count on it being safe to call this more than once, * and the second call should be a no-op. */ void locks_end_grace(struct lock_manager *lm) { spin_lock(&grace_lock); list_del_init(&lm->list); spin_unlock(&grace_lock); } EXPORT_SYMBOL_GPL(locks_end_grace); static bool __state_in_grace(struct net *net, bool open) { struct list_head *grace_list = net_generic(net, grace_net_id); struct lock_manager *lm; if (!open) return !list_empty(grace_list); spin_lock(&grace_lock); list_for_each_entry(lm, grace_list, list) { if (lm->block_opens) { spin_unlock(&grace_lock); return true; } } spin_unlock(&grace_lock); return false; } /** * locks_in_grace * @net: network namespace * * Lock managers call this function to determine when it is OK for them * to answer ordinary lock requests, and when they should accept only * lock reclaims. */ bool locks_in_grace(struct net *net) { return __state_in_grace(net, false); } EXPORT_SYMBOL_GPL(locks_in_grace); bool opens_in_grace(struct net *net) { return __state_in_grace(net, true); } EXPORT_SYMBOL_GPL(opens_in_grace); static int __net_init grace_init_net(struct net *net) { struct list_head *grace_list = net_generic(net, grace_net_id); INIT_LIST_HEAD(grace_list); return 0; } static void __net_exit grace_exit_net(struct net *net) { struct list_head *grace_list = net_generic(net, grace_net_id); WARN_ONCE(!list_empty(grace_list), "net %x %s: grace_list is not empty\n", net->ns.inum, __func__); } static struct pernet_operations grace_net_ops = { .init = grace_init_net, .exit = grace_exit_net, .id = &grace_net_id, .size = sizeof(struct list_head), }; static int __init init_grace(void) { return register_pernet_subsys(&grace_net_ops); } static void __exit exit_grace(void) { unregister_pernet_subsys(&grace_net_ops); } MODULE_AUTHOR("Jeff Layton <jlayton@primarydata.com>"); MODULE_LICENSE("GPL"); module_init(init_grace) module_exit(exit_grace) |
| 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 25 26 26 26 26 25 26 26 26 25 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 25 33 34 34 34 34 34 34 34 34 36 36 36 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 24 23 23 23 23 23 23 23 23 12 12 12 12 12 12 12 12 12 11 12 12 12 12 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH * Copyright (C) 2018-2022 Intel Corporation * * utilities for mac80211 */ #include <net/mac80211.h> #include <linux/netdevice.h> #include <linux/export.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/skbuff.h> #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/bitmap.h> #include <linux/crc32.h> #include <net/net_namespace.h> #include <net/cfg80211.h> #include <net/rtnetlink.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "rate.h" #include "mesh.h" #include "wme.h" #include "led.h" #include "wep.h" /* privid for wiphys to determine whether they belong to us or not */ const void *const mac80211_wiphy_privid = &mac80211_wiphy_privid; struct ieee80211_hw *wiphy_to_ieee80211_hw(struct wiphy *wiphy) { struct ieee80211_local *local; local = wiphy_priv(wiphy); return &local->hw; } EXPORT_SYMBOL(wiphy_to_ieee80211_hw); u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, enum nl80211_iftype type) { __le16 fc = hdr->frame_control; if (ieee80211_is_data(fc)) { if (len < 24) /* drop incorrect hdr len (data) */ return NULL; if (ieee80211_has_a4(fc)) return NULL; if (ieee80211_has_tods(fc)) return hdr->addr1; if (ieee80211_has_fromds(fc)) return hdr->addr2; return hdr->addr3; } if (ieee80211_is_s1g_beacon(fc)) { struct ieee80211_ext *ext = (void *) hdr; return ext->u.s1g_beacon.sa; } if (ieee80211_is_mgmt(fc)) { if (len < 24) /* drop incorrect hdr len (mgmt) */ return NULL; return hdr->addr3; } if (ieee80211_is_ctl(fc)) { if (ieee80211_is_pspoll(fc)) return hdr->addr1; if (ieee80211_is_back_req(fc)) { switch (type) { case NL80211_IFTYPE_STATION: return hdr->addr2; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: return hdr->addr1; default: break; /* fall through to the return */ } } } return NULL; } EXPORT_SYMBOL(ieee80211_get_bssid); void ieee80211_tx_set_protected(struct ieee80211_tx_data *tx) { struct sk_buff *skb; struct ieee80211_hdr *hdr; skb_queue_walk(&tx->skbs, skb) { hdr = (struct ieee80211_hdr *) skb->data; hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); } } int ieee80211_frame_duration(enum nl80211_band band, size_t len, int rate, int erp, int short_preamble, int shift) { int dur; /* calculate duration (in microseconds, rounded up to next higher * integer if it includes a fractional microsecond) to send frame of * len bytes (does not include FCS) at the given rate. Duration will * also include SIFS. * * rate is in 100 kbps, so divident is multiplied by 10 in the * DIV_ROUND_UP() operations. * * shift may be 2 for 5 MHz channels or 1 for 10 MHz channels, and * is assumed to be 0 otherwise. */ if (band == NL80211_BAND_5GHZ || erp) { /* * OFDM: * * N_DBPS = DATARATE x 4 * N_SYM = Ceiling((16+8xLENGTH+6) / N_DBPS) * (16 = SIGNAL time, 6 = tail bits) * TXTIME = T_PREAMBLE + T_SIGNAL + T_SYM x N_SYM + Signal Ext * * T_SYM = 4 usec * 802.11a - 18.5.2: aSIFSTime = 16 usec * 802.11g - 19.8.4: aSIFSTime = 10 usec + * signal ext = 6 usec */ dur = 16; /* SIFS + signal ext */ dur += 16; /* IEEE 802.11-2012 18.3.2.4: T_PREAMBLE = 16 usec */ dur += 4; /* IEEE 802.11-2012 18.3.2.4: T_SIGNAL = 4 usec */ /* IEEE 802.11-2012 18.3.2.4: all values above are: * * times 4 for 5 MHz * * times 2 for 10 MHz */ dur *= 1 << shift; /* rates should already consider the channel bandwidth, * don't apply divisor again. */ dur += 4 * DIV_ROUND_UP((16 + 8 * (len + 4) + 6) * 10, 4 * rate); /* T_SYM x N_SYM */ } else { /* * 802.11b or 802.11g with 802.11b compatibility: * 18.3.4: TXTIME = PreambleLength + PLCPHeaderTime + * Ceiling(((LENGTH+PBCC)x8)/DATARATE). PBCC=0. * * 802.11 (DS): 15.3.3, 802.11b: 18.3.4 * aSIFSTime = 10 usec * aPreambleLength = 144 usec or 72 usec with short preamble * aPLCPHeaderLength = 48 usec or 24 usec with short preamble */ dur = 10; /* aSIFSTime = 10 usec */ dur += short_preamble ? (72 + 24) : (144 + 48); dur += DIV_ROUND_UP(8 * (len + 4) * 10, rate); } return dur; } /* Exported duration function for driver use */ __le16 ieee80211_generic_frame_duration(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum nl80211_band band, size_t frame_len, struct ieee80211_rate *rate) { struct ieee80211_sub_if_data *sdata; u16 dur; int erp, shift = 0; bool short_preamble = false; erp = 0; if (vif) { sdata = vif_to_sdata(vif); short_preamble = sdata->vif.bss_conf.use_short_preamble; if (sdata->deflink.operating_11g_mode) erp = rate->flags & IEEE80211_RATE_ERP_G; shift = ieee80211_vif_get_shift(vif); } dur = ieee80211_frame_duration(band, frame_len, rate->bitrate, erp, short_preamble, shift); return cpu_to_le16(dur); } EXPORT_SYMBOL(ieee80211_generic_frame_duration); __le16 ieee80211_rts_duration(struct ieee80211_hw *hw, struct ieee80211_vif *vif, size_t frame_len, const struct ieee80211_tx_info *frame_txctl) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_rate *rate; struct ieee80211_sub_if_data *sdata; bool short_preamble; int erp, shift = 0, bitrate; u16 dur; struct ieee80211_supported_band *sband; sband = local->hw.wiphy->bands[frame_txctl->band]; short_preamble = false; rate = &sband->bitrates[frame_txctl->control.rts_cts_rate_idx]; erp = 0; if (vif) { sdata = vif_to_sdata(vif); short_preamble = sdata->vif.bss_conf.use_short_preamble; if (sdata->deflink.operating_11g_mode) erp = rate->flags & IEEE80211_RATE_ERP_G; shift = ieee80211_vif_get_shift(vif); } bitrate = DIV_ROUND_UP(rate->bitrate, 1 << shift); /* CTS duration */ dur = ieee80211_frame_duration(sband->band, 10, bitrate, erp, short_preamble, shift); /* Data frame duration */ dur += ieee80211_frame_duration(sband->band, frame_len, bitrate, erp, short_preamble, shift); /* ACK duration */ dur += ieee80211_frame_duration(sband->band, 10, bitrate, erp, short_preamble, shift); return cpu_to_le16(dur); } EXPORT_SYMBOL(ieee80211_rts_duration); __le16 ieee80211_ctstoself_duration(struct ieee80211_hw *hw, struct ieee80211_vif *vif, size_t frame_len, const struct ieee80211_tx_info *frame_txctl) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_rate *rate; struct ieee80211_sub_if_data *sdata; bool short_preamble; int erp, shift = 0, bitrate; u16 dur; struct ieee80211_supported_band *sband; sband = local->hw.wiphy->bands[frame_txctl->band]; short_preamble = false; rate = &sband->bitrates[frame_txctl->control.rts_cts_rate_idx]; erp = 0; if (vif) { sdata = vif_to_sdata(vif); short_preamble = sdata->vif.bss_conf.use_short_preamble; if (sdata->deflink.operating_11g_mode) erp = rate->flags & IEEE80211_RATE_ERP_G; shift = ieee80211_vif_get_shift(vif); } bitrate = DIV_ROUND_UP(rate->bitrate, 1 << shift); /* Data frame duration */ dur = ieee80211_frame_duration(sband->band, frame_len, bitrate, erp, short_preamble, shift); if (!(frame_txctl->flags & IEEE80211_TX_CTL_NO_ACK)) { /* ACK duration */ dur += ieee80211_frame_duration(sband->band, 10, bitrate, erp, short_preamble, shift); } return cpu_to_le16(dur); } EXPORT_SYMBOL(ieee80211_ctstoself_duration); static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) { struct ieee80211_local *local = sdata->local; struct ieee80211_vif *vif = &sdata->vif; struct fq *fq = &local->fq; struct ps_data *ps = NULL; struct txq_info *txqi; struct sta_info *sta; int i; local_bh_disable(); spin_lock(&fq->lock); sdata->vif.txqs_stopped[ac] = false; if (!test_bit(SDATA_STATE_RUNNING, &sdata->state)) goto out; if (sdata->vif.type == NL80211_IFTYPE_AP) ps = &sdata->bss->ps; list_for_each_entry_rcu(sta, &local->sta_list, list) { if (sdata != sta->sdata) continue; for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { struct ieee80211_txq *txq = sta->sta.txq[i]; if (!txq) continue; txqi = to_txq_info(txq); if (ac != txq->ac) continue; if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags)) continue; spin_unlock(&fq->lock); drv_wake_tx_queue(local, txqi); spin_lock(&fq->lock); } } if (!vif->txq) goto out; txqi = to_txq_info(vif->txq); if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags) || (ps && atomic_read(&ps->num_sta_ps)) || ac != vif->txq->ac) goto out; spin_unlock(&fq->lock); drv_wake_tx_queue(local, txqi); local_bh_enable(); return; out: spin_unlock(&fq->lock); local_bh_enable(); } static void __releases(&local->queue_stop_reason_lock) __acquires(&local->queue_stop_reason_lock) _ieee80211_wake_txqs(struct ieee80211_local *local, unsigned long *flags) { struct ieee80211_sub_if_data *sdata; int n_acs = IEEE80211_NUM_ACS; int i; rcu_read_lock(); if (local->hw.queues < IEEE80211_NUM_ACS) n_acs = 1; for (i = 0; i < local->hw.queues; i++) { if (local->queue_stop_reasons[i]) continue; spin_unlock_irqrestore(&local->queue_stop_reason_lock, *flags); list_for_each_entry_rcu(sdata, &local->interfaces, list) { int ac; for (ac = 0; ac < n_acs; ac++) { int ac_queue = sdata->vif.hw_queue[ac]; if (ac_queue == i || sdata->vif.cab_queue == i) __ieee80211_wake_txqs(sdata, ac); } } spin_lock_irqsave(&local->queue_stop_reason_lock, *flags); } rcu_read_unlock(); } void ieee80211_wake_txqs(struct tasklet_struct *t) { struct ieee80211_local *local = from_tasklet(local, t, wake_txqs_tasklet); unsigned long flags; spin_lock_irqsave(&local->queue_stop_reason_lock, flags); _ieee80211_wake_txqs(local, &flags); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue) { struct ieee80211_sub_if_data *sdata; int n_acs = IEEE80211_NUM_ACS; if (local->ops->wake_tx_queue) return; if (local->hw.queues < IEEE80211_NUM_ACS) n_acs = 1; list_for_each_entry_rcu(sdata, &local->interfaces, list) { int ac; if (!sdata->dev) continue; if (sdata->vif.cab_queue != IEEE80211_INVAL_HW_QUEUE && local->queue_stop_reasons[sdata->vif.cab_queue] != 0) continue; for (ac = 0; ac < n_acs; ac++) { int ac_queue = sdata->vif.hw_queue[ac]; if (ac_queue == queue || (sdata->vif.cab_queue == queue && local->queue_stop_reasons[ac_queue] == 0 && skb_queue_empty(&local->pending[ac_queue]))) netif_wake_subqueue(sdata->dev, ac); } } } static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason, bool refcounted, unsigned long *flags) { struct ieee80211_local *local = hw_to_local(hw); trace_wake_queue(local, queue, reason); if (WARN_ON(queue >= hw->queues)) return; if (!test_bit(reason, &local->queue_stop_reasons[queue])) return; if (!refcounted) { local->q_stop_reasons[queue][reason] = 0; } else { local->q_stop_reasons[queue][reason]--; if (WARN_ON(local->q_stop_reasons[queue][reason] < 0)) local->q_stop_reasons[queue][reason] = 0; } if (local->q_stop_reasons[queue][reason] == 0) __clear_bit(reason, &local->queue_stop_reasons[queue]); if (local->queue_stop_reasons[queue] != 0) /* someone still has this queue stopped */ return; if (skb_queue_empty(&local->pending[queue])) { rcu_read_lock(); ieee80211_propagate_queue_wake(local, queue); rcu_read_unlock(); } else tasklet_schedule(&local->tx_pending_tasklet); /* * Calling _ieee80211_wake_txqs here can be a problem because it may * release queue_stop_reason_lock which has been taken by * __ieee80211_wake_queue's caller. It is certainly not very nice to * release someone's lock, but it is fine because all the callers of * __ieee80211_wake_queue call it right before releasing the lock. */ if (local->ops->wake_tx_queue) { if (reason == IEEE80211_QUEUE_STOP_REASON_DRIVER) tasklet_schedule(&local->wake_txqs_tasklet); else _ieee80211_wake_txqs(local, flags); } } void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason, bool refcounted) { struct ieee80211_local *local = hw_to_local(hw); unsigned long flags; spin_lock_irqsave(&local->queue_stop_reason_lock, flags); __ieee80211_wake_queue(hw, queue, reason, refcounted, &flags); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } void ieee80211_wake_queue(struct ieee80211_hw *hw, int queue) { ieee80211_wake_queue_by_reason(hw, queue, IEEE80211_QUEUE_STOP_REASON_DRIVER, false); } EXPORT_SYMBOL(ieee80211_wake_queue); static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason, bool refcounted) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; int n_acs = IEEE80211_NUM_ACS; trace_stop_queue(local, queue, reason); if (WARN_ON(queue >= hw->queues)) return; if (!refcounted) local->q_stop_reasons[queue][reason] = 1; else local->q_stop_reasons[queue][reason]++; if (__test_and_set_bit(reason, &local->queue_stop_reasons[queue])) return; if (local->hw.queues < IEEE80211_NUM_ACS) n_acs = 1; rcu_read_lock(); list_for_each_entry_rcu(sdata, &local->interfaces, list) { int ac; if (!sdata->dev) continue; for (ac = 0; ac < n_acs; ac++) { if (sdata->vif.hw_queue[ac] == queue || sdata->vif.cab_queue == queue) { if (!local->ops->wake_tx_queue) { netif_stop_subqueue(sdata->dev, ac); continue; } spin_lock(&local->fq.lock); sdata->vif.txqs_stopped[ac] = true; spin_unlock(&local->fq.lock); } } } rcu_read_unlock(); } void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason, bool refcounted) { struct ieee80211_local *local = hw_to_local(hw); unsigned long flags; spin_lock_irqsave(&local->queue_stop_reason_lock, flags); __ieee80211_stop_queue(hw, queue, reason, refcounted); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } void ieee80211_stop_queue(struct ieee80211_hw *hw, int queue) { ieee80211_stop_queue_by_reason(hw, queue, IEEE80211_QUEUE_STOP_REASON_DRIVER, false); } EXPORT_SYMBOL(ieee80211_stop_queue); void ieee80211_add_pending_skb(struct ieee80211_local *local, struct sk_buff *skb) { struct ieee80211_hw *hw = &local->hw; unsigned long flags; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); int queue = info->hw_queue; if (WARN_ON(!info->control.vif)) { ieee80211_free_txskb(&local->hw, skb); return; } spin_lock_irqsave(&local->queue_stop_reason_lock, flags); __ieee80211_stop_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_SKB_ADD, false); __skb_queue_tail(&local->pending[queue], skb); __ieee80211_wake_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_SKB_ADD, false, &flags); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } void ieee80211_add_pending_skbs(struct ieee80211_local *local, struct sk_buff_head *skbs) { struct ieee80211_hw *hw = &local->hw; struct sk_buff *skb; unsigned long flags; int queue, i; spin_lock_irqsave(&local->queue_stop_reason_lock, flags); while ((skb = skb_dequeue(skbs))) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); if (WARN_ON(!info->control.vif)) { ieee80211_free_txskb(&local->hw, skb); continue; } queue = info->hw_queue; __ieee80211_stop_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_SKB_ADD, false); __skb_queue_tail(&local->pending[queue], skb); } for (i = 0; i < hw->queues; i++) __ieee80211_wake_queue(hw, i, IEEE80211_QUEUE_STOP_REASON_SKB_ADD, false, &flags); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } void ieee80211_stop_queues_by_reason(struct ieee80211_hw *hw, unsigned long queues, enum queue_stop_reason reason, bool refcounted) { struct ieee80211_local *local = hw_to_local(hw); unsigned long flags; int i; spin_lock_irqsave(&local->queue_stop_reason_lock, flags); for_each_set_bit(i, &queues, hw->queues) __ieee80211_stop_queue(hw, i, reason, refcounted); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } void ieee80211_stop_queues(struct ieee80211_hw *hw) { ieee80211_stop_queues_by_reason(hw, IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_DRIVER, false); } EXPORT_SYMBOL(ieee80211_stop_queues); int ieee80211_queue_stopped(struct ieee80211_hw *hw, int queue) { struct ieee80211_local *local = hw_to_local(hw); unsigned long flags; int ret; if (WARN_ON(queue >= hw->queues)) return true; spin_lock_irqsave(&local->queue_stop_reason_lock, flags); ret = test_bit(IEEE80211_QUEUE_STOP_REASON_DRIVER, &local->queue_stop_reasons[queue]); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); return ret; } EXPORT_SYMBOL(ieee80211_queue_stopped); void ieee80211_wake_queues_by_reason(struct ieee80211_hw *hw, unsigned long queues, enum queue_stop_reason reason, bool refcounted) { struct ieee80211_local *local = hw_to_local(hw); unsigned long flags; int i; spin_lock_irqsave(&local->queue_stop_reason_lock, flags); for_each_set_bit(i, &queues, hw->queues) __ieee80211_wake_queue(hw, i, reason, refcounted, &flags); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } void ieee80211_wake_queues(struct ieee80211_hw *hw) { ieee80211_wake_queues_by_reason(hw, IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_DRIVER, false); } EXPORT_SYMBOL(ieee80211_wake_queues); static unsigned int ieee80211_get_vif_queues(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { unsigned int queues; if (sdata && ieee80211_hw_check(&local->hw, QUEUE_CONTROL)) { int ac; queues = 0; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) queues |= BIT(sdata->vif.hw_queue[ac]); if (sdata->vif.cab_queue != IEEE80211_INVAL_HW_QUEUE) queues |= BIT(sdata->vif.cab_queue); } else { /* all queues */ queues = BIT(local->hw.queues) - 1; } return queues; } void __ieee80211_flush_queues(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, unsigned int queues, bool drop) { if (!local->ops->flush) return; /* * If no queue was set, or if the HW doesn't support * IEEE80211_HW_QUEUE_CONTROL - flush all queues */ if (!queues || !ieee80211_hw_check(&local->hw, QUEUE_CONTROL)) queues = ieee80211_get_vif_queues(local, sdata); ieee80211_stop_queues_by_reason(&local->hw, queues, IEEE80211_QUEUE_STOP_REASON_FLUSH, false); drv_flush(local, sdata, queues, drop); ieee80211_wake_queues_by_reason(&local->hw, queues, IEEE80211_QUEUE_STOP_REASON_FLUSH, false); } void ieee80211_flush_queues(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, bool drop) { __ieee80211_flush_queues(local, sdata, 0, drop); } void ieee80211_stop_vif_queues(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, enum queue_stop_reason reason) { ieee80211_stop_queues_by_reason(&local->hw, ieee80211_get_vif_queues(local, sdata), reason, true); } void ieee80211_wake_vif_queues(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, enum queue_stop_reason reason) { ieee80211_wake_queues_by_reason(&local->hw, ieee80211_get_vif_queues(local, sdata), reason, true); } static void __iterate_interfaces(struct ieee80211_local *local, u32 iter_flags, void (*iterator)(void *data, u8 *mac, struct ieee80211_vif *vif), void *data) { struct ieee80211_sub_if_data *sdata; bool active_only = iter_flags & IEEE80211_IFACE_ITER_ACTIVE; list_for_each_entry_rcu(sdata, &local->interfaces, list) { switch (sdata->vif.type) { case NL80211_IFTYPE_MONITOR: if (!(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE)) continue; break; case NL80211_IFTYPE_AP_VLAN: continue; default: break; } if (!(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL) && active_only && !(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) continue; if ((iter_flags & IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER) && !(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) continue; if (ieee80211_sdata_running(sdata) || !active_only) iterator(data, sdata->vif.addr, &sdata->vif); } sdata = rcu_dereference_check(local->monitor_sdata, lockdep_is_held(&local->iflist_mtx) || lockdep_is_held(&local->hw.wiphy->mtx)); if (sdata && (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only || sdata->flags & IEEE80211_SDATA_IN_DRIVER)) iterator(data, sdata->vif.addr, &sdata->vif); } void ieee80211_iterate_interfaces( struct ieee80211_hw *hw, u32 iter_flags, void (*iterator)(void *data, u8 *mac, struct ieee80211_vif *vif), void *data) { struct ieee80211_local *local = hw_to_local(hw); mutex_lock(&local->iflist_mtx); __iterate_interfaces(local, iter_flags, iterator, data); mutex_unlock(&local->iflist_mtx); } EXPORT_SYMBOL_GPL(ieee80211_iterate_interfaces); void ieee80211_iterate_active_interfaces_atomic( struct ieee80211_hw *hw, u32 iter_flags, void (*iterator)(void *data, u8 *mac, struct ieee80211_vif *vif), void *data) { struct ieee80211_local *local = hw_to_local(hw); rcu_read_lock(); __iterate_interfaces(local, iter_flags | IEEE80211_IFACE_ITER_ACTIVE, iterator, data); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_atomic); void ieee80211_iterate_active_interfaces_mtx( struct ieee80211_hw *hw, u32 iter_flags, void (*iterator)(void *data, u8 *mac, struct ieee80211_vif *vif), void *data) { struct ieee80211_local *local = hw_to_local(hw); lockdep_assert_wiphy(hw->wiphy); __iterate_interfaces(local, iter_flags | IEEE80211_IFACE_ITER_ACTIVE, iterator, data); } EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_mtx); static void __iterate_stations(struct ieee80211_local *local, void (*iterator)(void *data, struct ieee80211_sta *sta), void *data) { struct sta_info *sta; list_for_each_entry_rcu(sta, &local->sta_list, list) { if (!sta->uploaded) continue; iterator(data, &sta->sta); } } void ieee80211_iterate_stations(struct ieee80211_hw *hw, void (*iterator)(void *data, struct ieee80211_sta *sta), void *data) { struct ieee80211_local *local = hw_to_local(hw); mutex_lock(&local->sta_mtx); __iterate_stations(local, iterator, data); mutex_unlock(&local->sta_mtx); } EXPORT_SYMBOL_GPL(ieee80211_iterate_stations); void ieee80211_iterate_stations_atomic(struct ieee80211_hw *hw, void (*iterator)(void *data, struct ieee80211_sta *sta), void *data) { struct ieee80211_local *local = hw_to_local(hw); rcu_read_lock(); __iterate_stations(local, iterator, data); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ieee80211_iterate_stations_atomic); struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (!ieee80211_sdata_running(sdata) || !(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) return NULL; return &sdata->vif; } EXPORT_SYMBOL_GPL(wdev_to_ieee80211_vif); struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif) { if (!vif) return NULL; return &vif_to_sdata(vif)->wdev; } EXPORT_SYMBOL_GPL(ieee80211_vif_to_wdev); /* * Nothing should have been stuffed into the workqueue during * the suspend->resume cycle. Since we can't check each caller * of this function if we are already quiescing / suspended, * check here and don't WARN since this can actually happen when * the rx path (for example) is racing against __ieee80211_suspend * and suspending / quiescing was set after the rx path checked * them. */ static bool ieee80211_can_queue_work(struct ieee80211_local *local) { if (local->quiescing || (local->suspended && !local->resuming)) { pr_warn("queueing ieee80211 work while going to suspend\n"); return false; } return true; } void ieee80211_queue_work(struct ieee80211_hw *hw, struct work_struct *work) { struct ieee80211_local *local = hw_to_local(hw); if (!ieee80211_can_queue_work(local)) return; queue_work(local->workqueue, work); } EXPORT_SYMBOL(ieee80211_queue_work); void ieee80211_queue_delayed_work(struct ieee80211_hw *hw, struct delayed_work *dwork, unsigned long delay) { struct ieee80211_local *local = hw_to_local(hw); if (!ieee80211_can_queue_work(local)) return; queue_delayed_work(local->workqueue, dwork, delay); } EXPORT_SYMBOL(ieee80211_queue_delayed_work); static void ieee80211_parse_extension_element(u32 *crc, const struct element *elem, struct ieee802_11_elems *elems, struct ieee80211_elems_parse_params *params) { const void *data = elem->data + 1; u8 len; if (!elem->datalen) return; len = elem->datalen - 1; switch (elem->data[0]) { case WLAN_EID_EXT_HE_MU_EDCA: if (len >= sizeof(*elems->mu_edca_param_set)) { elems->mu_edca_param_set = data; if (crc) *crc = crc32_be(*crc, (void *)elem, elem->datalen + 2); } break; case WLAN_EID_EXT_HE_CAPABILITY: if (ieee80211_he_capa_size_ok(data, len)) { elems->he_cap = data; elems->he_cap_len = len; } break; case WLAN_EID_EXT_HE_OPERATION: if (len >= sizeof(*elems->he_operation) && len >= ieee80211_he_oper_size(data) - 1) { if (crc) *crc = crc32_be(*crc, (void *)elem, elem->datalen + 2); elems->he_operation = data; } break; case WLAN_EID_EXT_UORA: if (len >= 1) elems->uora_element = data; break; case WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME: if (len == 3) elems->max_channel_switch_time = data; break; case WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION: if (len >= sizeof(*elems->mbssid_config_ie)) elems->mbssid_config_ie = data; break; case WLAN_EID_EXT_HE_SPR: if (len >= sizeof(*elems->he_spr) && len >= ieee80211_he_spr_size(data)) elems->he_spr = data; break; case WLAN_EID_EXT_HE_6GHZ_CAPA: if (len >= sizeof(*elems->he_6ghz_capa)) elems->he_6ghz_capa = data; break; case WLAN_EID_EXT_EHT_CAPABILITY: if (ieee80211_eht_capa_size_ok(elems->he_cap, data, len, params->from_ap)) { elems->eht_cap = data; elems->eht_cap_len = len; } break; case WLAN_EID_EXT_EHT_OPERATION: if (ieee80211_eht_oper_size_ok(data, len)) elems->eht_operation = data; break; case WLAN_EID_EXT_EHT_MULTI_LINK: if (ieee80211_mle_size_ok(data, len)) elems->multi_link = (void *)data; break; } } static u32 _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params, struct ieee802_11_elems *elems, const struct element *check_inherit) { const struct element *elem; bool calc_crc = params->filter != 0; DECLARE_BITMAP(seen_elems, 256); u32 crc = params->crc; const u8 *ie; bitmap_zero(seen_elems, 256); for_each_element(elem, params->start, params->len) { bool elem_parse_failed; u8 id = elem->id; u8 elen = elem->datalen; const u8 *pos = elem->data; if (check_inherit && !cfg80211_is_element_inherited(elem, check_inherit)) continue; switch (id) { case WLAN_EID_SSID: case WLAN_EID_SUPP_RATES: case WLAN_EID_FH_PARAMS: case WLAN_EID_DS_PARAMS: case WLAN_EID_CF_PARAMS: case WLAN_EID_TIM: case WLAN_EID_IBSS_PARAMS: case WLAN_EID_CHALLENGE: case WLAN_EID_RSN: case WLAN_EID_ERP_INFO: case WLAN_EID_EXT_SUPP_RATES: case WLAN_EID_HT_CAPABILITY: case WLAN_EID_HT_OPERATION: case WLAN_EID_VHT_CAPABILITY: case WLAN_EID_VHT_OPERATION: case WLAN_EID_MESH_ID: case WLAN_EID_MESH_CONFIG: case WLAN_EID_PEER_MGMT: case WLAN_EID_PREQ: case WLAN_EID_PREP: case WLAN_EID_PERR: case WLAN_EID_RANN: case WLAN_EID_CHANNEL_SWITCH: case WLAN_EID_EXT_CHANSWITCH_ANN: case WLAN_EID_COUNTRY: case WLAN_EID_PWR_CONSTRAINT: case WLAN_EID_TIMEOUT_INTERVAL: case WLAN_EID_SECONDARY_CHANNEL_OFFSET: case WLAN_EID_WIDE_BW_CHANNEL_SWITCH: case WLAN_EID_CHAN_SWITCH_PARAM: case WLAN_EID_EXT_CAPABILITY: case WLAN_EID_CHAN_SWITCH_TIMING: case WLAN_EID_LINK_ID: case WLAN_EID_BSS_MAX_IDLE_PERIOD: case WLAN_EID_RSNX: case WLAN_EID_S1G_BCN_COMPAT: case WLAN_EID_S1G_CAPABILITIES: case WLAN_EID_S1G_OPERATION: case WLAN_EID_AID_RESPONSE: case WLAN_EID_S1G_SHORT_BCN_INTERVAL: /* * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible * that if the content gets bigger it might be needed more than once */ if (test_bit(id, seen_elems)) { elems->parse_error = true; continue; } break; } if (calc_crc && id < 64 && (params->filter & (1ULL << id))) crc = crc32_be(crc, pos - 2, elen + 2); elem_parse_failed = false; switch (id) { case WLAN_EID_LINK_ID: if (elen + 2 < sizeof(struct ieee80211_tdls_lnkie)) { elem_parse_failed = true; break; } elems->lnk_id = (void *)(pos - 2); break; case WLAN_EID_CHAN_SWITCH_TIMING: if (elen < sizeof(struct ieee80211_ch_switch_timing)) { elem_parse_failed = true; break; } elems->ch_sw_timing = (void *)pos; break; case WLAN_EID_EXT_CAPABILITY: elems->ext_capab = pos; elems->ext_capab_len = elen; break; case WLAN_EID_SSID: elems->ssid = pos; elems->ssid_len = elen; break; case WLAN_EID_SUPP_RATES: elems->supp_rates = pos; elems->supp_rates_len = elen; break; case WLAN_EID_DS_PARAMS: if (elen >= 1) elems->ds_params = pos; else elem_parse_failed = true; break; case WLAN_EID_TIM: if (elen >= sizeof(struct ieee80211_tim_ie)) { elems->tim = (void *)pos; elems->tim_len = elen; } else elem_parse_failed = true; break; case WLAN_EID_VENDOR_SPECIFIC: if (elen >= 4 && pos[0] == 0x00 && pos[1] == 0x50 && pos[2] == 0xf2) { /* Microsoft OUI (00:50:F2) */ if (calc_crc) crc = crc32_be(crc, pos - 2, elen + 2); if (elen >= 5 && pos[3] == 2) { /* OUI Type 2 - WMM IE */ if (pos[4] == 0) { elems->wmm_info = pos; elems->wmm_info_len = elen; } else if (pos[4] == 1) { elems->wmm_param = pos; elems->wmm_param_len = elen; } } } break; case WLAN_EID_RSN: elems->rsn = pos; elems->rsn_len = elen; break; case WLAN_EID_ERP_INFO: if (elen >= 1) elems->erp_info = pos; else elem_parse_failed = true; break; case WLAN_EID_EXT_SUPP_RATES: elems->ext_supp_rates = pos; elems->ext_supp_rates_len = elen; break; case WLAN_EID_HT_CAPABILITY: if (elen >= sizeof(struct ieee80211_ht_cap)) elems->ht_cap_elem = (void *)pos; else elem_parse_failed = true; break; case WLAN_EID_HT_OPERATION: if (elen >= sizeof(struct ieee80211_ht_operation)) elems->ht_operation = (void *)pos; else elem_parse_failed = true; break; case WLAN_EID_VHT_CAPABILITY: if (elen >= sizeof(struct ieee80211_vht_cap)) elems->vht_cap_elem = (void *)pos; else elem_parse_failed = true; break; case WLAN_EID_VHT_OPERATION: if (elen >= sizeof(struct ieee80211_vht_operation)) { elems->vht_operation = (void *)pos; if (calc_crc) crc = crc32_be(crc, pos - 2, elen + 2); break; } elem_parse_failed = true; break; case WLAN_EID_OPMODE_NOTIF: if (elen > 0) { elems->opmode_notif = pos; if (calc_crc) crc = crc32_be(crc, pos - 2, elen + 2); break; } elem_parse_failed = true; break; case WLAN_EID_MESH_ID: elems->mesh_id = pos; elems->mesh_id_len = elen; break; case WLAN_EID_MESH_CONFIG: if (elen >= sizeof(struct ieee80211_meshconf_ie)) elems->mesh_config = (void *)pos; else elem_parse_failed = true; break; case WLAN_EID_PEER_MGMT: elems->peering = pos; elems->peering_len = elen; break; case WLAN_EID_MESH_AWAKE_WINDOW: if (elen >= 2) elems->awake_window = (void *)pos; break; case WLAN_EID_PREQ: elems->preq = pos; elems->preq_len = elen; break; case WLAN_EID_PREP: elems->prep = pos; elems->prep_len = elen; break; case WLAN_EID_PERR: elems->perr = pos; elems->perr_len = elen; break; case WLAN_EID_RANN: if (elen >= sizeof(struct ieee80211_rann_ie)) elems->rann = (void *)pos; else elem_parse_failed = true; break; case WLAN_EID_CHANNEL_SWITCH: if (elen != sizeof(struct ieee80211_channel_sw_ie)) { elem_parse_failed = true; break; } elems->ch_switch_ie = (void *)pos; break; case WLAN_EID_EXT_CHANSWITCH_ANN: if (elen != sizeof(struct ieee80211_ext_chansw_ie)) { elem_parse_failed = true; break; } elems->ext_chansw_ie = (void *)pos; break; case WLAN_EID_SECONDARY_CHANNEL_OFFSET: if (elen != sizeof(struct ieee80211_sec_chan_offs_ie)) { elem_parse_failed = true; break; } elems->sec_chan_offs = (void *)pos; break; case WLAN_EID_CHAN_SWITCH_PARAM: if (elen < sizeof(*elems->mesh_chansw_params_ie)) { elem_parse_failed = true; break; } elems->mesh_chansw_params_ie = (void *)pos; break; case WLAN_EID_WIDE_BW_CHANNEL_SWITCH: if (!params->action || elen < sizeof(*elems->wide_bw_chansw_ie)) { elem_parse_failed = true; break; } elems->wide_bw_chansw_ie = (void *)pos; break; case WLAN_EID_CHANNEL_SWITCH_WRAPPER: if (params->action) { elem_parse_failed = true; break; } /* * This is a bit tricky, but as we only care about * the wide bandwidth channel switch element, so * just parse it out manually. */ ie = cfg80211_find_ie(WLAN_EID_WIDE_BW_CHANNEL_SWITCH, pos, elen); if (ie) { if (ie[1] >= sizeof(*elems->wide_bw_chansw_ie)) elems->wide_bw_chansw_ie = (void *)(ie + 2); else elem_parse_failed = true; } break; case WLAN_EID_COUNTRY: elems->country_elem = pos; elems->country_elem_len = elen; break; case WLAN_EID_PWR_CONSTRAINT: if (elen != 1) { elem_parse_failed = true; break; } elems->pwr_constr_elem = pos; break; case WLAN_EID_CISCO_VENDOR_SPECIFIC: /* Lots of different options exist, but we only care * about the Dynamic Transmit Power Control element. * First check for the Cisco OUI, then for the DTPC * tag (0x00). */ if (elen < 4) { elem_parse_failed = true; break; } if (pos[0] != 0x00 || pos[1] != 0x40 || pos[2] != 0x96 || pos[3] != 0x00) break; if (elen != 6) { elem_parse_failed = true; break; } if (calc_crc) crc = crc32_be(crc, pos - 2, elen + 2); elems->cisco_dtpc_elem = pos; break; case WLAN_EID_ADDBA_EXT: if (elen < sizeof(struct ieee80211_addba_ext_ie)) { elem_parse_failed = true; break; } elems->addba_ext_ie = (void *)pos; break; case WLAN_EID_TIMEOUT_INTERVAL: if (elen >= sizeof(struct ieee80211_timeout_interval_ie)) elems->timeout_int = (void *)pos; else elem_parse_failed = true; break; case WLAN_EID_BSS_MAX_IDLE_PERIOD: if (elen >= sizeof(*elems->max_idle_period_ie)) elems->max_idle_period_ie = (void *)pos; break; case WLAN_EID_RSNX: elems->rsnx = pos; elems->rsnx_len = elen; break; case WLAN_EID_TX_POWER_ENVELOPE: if (elen < 1 || elen > sizeof(struct ieee80211_tx_pwr_env)) break; if (elems->tx_pwr_env_num >= ARRAY_SIZE(elems->tx_pwr_env)) break; elems->tx_pwr_env[elems->tx_pwr_env_num] = (void *)pos; elems->tx_pwr_env_len[elems->tx_pwr_env_num] = elen; elems->tx_pwr_env_num++; break; case WLAN_EID_EXTENSION: ieee80211_parse_extension_element(calc_crc ? &crc : NULL, elem, elems, params); break; case WLAN_EID_S1G_CAPABILITIES: if (elen >= sizeof(*elems->s1g_capab)) elems->s1g_capab = (void *)pos; else elem_parse_failed = true; break; case WLAN_EID_S1G_OPERATION: if (elen == sizeof(*elems->s1g_oper)) elems->s1g_oper = (void *)pos; else elem_parse_failed = true; break; case WLAN_EID_S1G_BCN_COMPAT: if (elen == sizeof(*elems->s1g_bcn_compat)) elems->s1g_bcn_compat = (void *)pos; else elem_parse_failed = true; break; case WLAN_EID_AID_RESPONSE: if (elen == sizeof(struct ieee80211_aid_response_ie)) elems->aid_resp = (void *)pos; else elem_parse_failed = true; break; default: break; } if (elem_parse_failed) elems->parse_error = true; else __set_bit(id, seen_elems); } if (!for_each_element_completed(elem, params->start, params->len)) elems->parse_error = true; return crc; } static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len, struct ieee802_11_elems *elems, struct cfg80211_bss *bss, u8 *nontransmitted_profile) { const struct element *elem, *sub; size_t profile_len = 0; bool found = false; if (!bss || !bss->transmitted_bss) return profile_len; for_each_element_id(elem, WLAN_EID_MULTIPLE_BSSID, start, len) { if (elem->datalen < 2) continue; if (elem->data[0] < 1 || elem->data[0] > 8) continue; for_each_element(sub, elem->data + 1, elem->datalen - 1) { u8 new_bssid[ETH_ALEN]; const u8 *index; if (sub->id != 0 || sub->datalen < 4) { /* not a valid BSS profile */ continue; } if (sub->data[0] != WLAN_EID_NON_TX_BSSID_CAP || sub->data[1] != 2) { /* The first element of the * Nontransmitted BSSID Profile is not * the Nontransmitted BSSID Capability * element. */ continue; } memset(nontransmitted_profile, 0, len); profile_len = cfg80211_merge_profile(start, len, elem, sub, nontransmitted_profile, len); /* found a Nontransmitted BSSID Profile */ index = cfg80211_find_ie(WLAN_EID_MULTI_BSSID_IDX, nontransmitted_profile, profile_len); if (!index || index[1] < 1 || index[2] == 0) { /* Invalid MBSSID Index element */ continue; } cfg80211_gen_new_bssid(bss->transmitted_bss->bssid, elem->data[0], index[2], new_bssid); if (ether_addr_equal(new_bssid, bss->bssid)) { found = true; elems->bssid_index_len = index[1]; elems->bssid_index = (void *)&index[2]; break; } } } return found ? profile_len : 0; } struct ieee802_11_elems * ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) { struct ieee802_11_elems *elems; const struct element *non_inherit = NULL; u8 *nontransmitted_profile; int nontransmitted_profile_len = 0; size_t scratch_len = params->len; elems = kzalloc(sizeof(*elems) + scratch_len, GFP_ATOMIC); if (!elems) return NULL; elems->ie_start = params->start; elems->total_len = params->len; elems->scratch_len = scratch_len; elems->scratch_pos = elems->scratch; nontransmitted_profile = elems->scratch_pos; nontransmitted_profile_len = ieee802_11_find_bssid_profile(params->start, params->len, elems, params->bss, nontransmitted_profile); elems->scratch_pos += nontransmitted_profile_len; elems->scratch_len -= nontransmitted_profile_len; non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, nontransmitted_profile, nontransmitted_profile_len); elems->crc = _ieee802_11_parse_elems_full(params, elems, non_inherit); /* Override with nontransmitted profile, if found */ if (nontransmitted_profile_len) { struct ieee80211_elems_parse_params sub = { .start = nontransmitted_profile, .len = nontransmitted_profile_len, .action = params->action, .link_id = params->link_id, }; _ieee802_11_parse_elems_full(&sub, elems, NULL); } if (elems->tim && !elems->parse_error) { const struct ieee80211_tim_ie *tim_ie = elems->tim; elems->dtim_period = tim_ie->dtim_period; elems->dtim_count = tim_ie->dtim_count; } /* Override DTIM period and count if needed */ if (elems->bssid_index && elems->bssid_index_len >= offsetofend(struct ieee80211_bssid_index, dtim_period)) elems->dtim_period = elems->bssid_index->dtim_period; if (elems->bssid_index && elems->bssid_index_len >= offsetofend(struct ieee80211_bssid_index, dtim_count)) elems->dtim_count = elems->bssid_index->dtim_count; return elems; } void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata, struct ieee80211_tx_queue_params *qparam, int ac) { struct ieee80211_chanctx_conf *chanctx_conf; const struct ieee80211_reg_rule *rrule; const struct ieee80211_wmm_ac *wmm_ac; u16 center_freq = 0; if (sdata->vif.type != NL80211_IFTYPE_AP && sdata->vif.type != NL80211_IFTYPE_STATION) return; rcu_read_lock(); chanctx_conf = rcu_dereference(sdata->vif.bss_conf.chanctx_conf); if (chanctx_conf) center_freq = chanctx_conf->def.chan->center_freq; if (!center_freq) { rcu_read_unlock(); return; } rrule = freq_reg_info(sdata->wdev.wiphy, MHZ_TO_KHZ(center_freq)); if (IS_ERR_OR_NULL(rrule) || !rrule->has_wmm) { rcu_read_unlock(); return; } if (sdata->vif.type == NL80211_IFTYPE_AP) wmm_ac = &rrule->wmm_rule.ap[ac]; else wmm_ac = &rrule->wmm_rule.client[ac]; qparam->cw_min = max_t(u16, qparam->cw_min, wmm_ac->cw_min); qparam->cw_max = max_t(u16, qparam->cw_max, wmm_ac->cw_max); qparam->aifs = max_t(u8, qparam->aifs, wmm_ac->aifsn); qparam->txop = min_t(u16, qparam->txop, wmm_ac->cot / 32); rcu_read_unlock(); } void ieee80211_set_wmm_default(struct ieee80211_link_data *link, bool bss_notify, bool enable_qos) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_tx_queue_params qparam; struct ieee80211_chanctx_conf *chanctx_conf; int ac; bool use_11b; bool is_ocb; /* Use another EDCA parameters if dot11OCBActivated=true */ int aCWmin, aCWmax; if (!local->ops->conf_tx) return; if (local->hw.queues < IEEE80211_NUM_ACS) return; memset(&qparam, 0, sizeof(qparam)); rcu_read_lock(); chanctx_conf = rcu_dereference(link->conf->chanctx_conf); use_11b = (chanctx_conf && chanctx_conf->def.chan->band == NL80211_BAND_2GHZ) && !link->operating_11g_mode; rcu_read_unlock(); is_ocb = (sdata->vif.type == NL80211_IFTYPE_OCB); /* Set defaults according to 802.11-2007 Table 7-37 */ aCWmax = 1023; if (use_11b) aCWmin = 31; else aCWmin = 15; /* Confiure old 802.11b/g medium access rules. */ qparam.cw_max = aCWmax; qparam.cw_min = aCWmin; qparam.txop = 0; qparam.aifs = 2; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { /* Update if QoS is enabled. */ if (enable_qos) { switch (ac) { case IEEE80211_AC_BK: qparam.cw_max = aCWmax; qparam.cw_min = aCWmin; qparam.txop = 0; if (is_ocb) qparam.aifs = 9; else qparam.aifs = 7; break; /* never happens but let's not leave undefined */ default: case IEEE80211_AC_BE: qparam.cw_max = aCWmax; qparam.cw_min = aCWmin; qparam.txop = 0; if (is_ocb) qparam.aifs = 6; else qparam.aifs = 3; break; case IEEE80211_AC_VI: qparam.cw_max = aCWmin; qparam.cw_min = (aCWmin + 1) / 2 - 1; if (is_ocb) qparam.txop = 0; else if (use_11b) qparam.txop = 6016/32; else qparam.txop = 3008/32; if (is_ocb) qparam.aifs = 3; else qparam.aifs = 2; break; case IEEE80211_AC_VO: qparam.cw_max = (aCWmin + 1) / 2 - 1; qparam.cw_min = (aCWmin + 1) / 4 - 1; if (is_ocb) qparam.txop = 0; else if (use_11b) qparam.txop = 3264/32; else qparam.txop = 1504/32; qparam.aifs = 2; break; } } ieee80211_regulatory_limit_wmm_params(sdata, &qparam, ac); qparam.uapsd = false; link->tx_conf[ac] = qparam; drv_conf_tx(local, link, ac, &qparam); } if (sdata->vif.type != NL80211_IFTYPE_MONITOR && sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && sdata->vif.type != NL80211_IFTYPE_NAN) { link->conf->qos = enable_qos; if (bss_notify) ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_QOS); } } void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, u16 status, const u8 *extra, size_t extra_len, const u8 *da, const u8 *bssid, const u8 *key, u8 key_len, u8 key_idx, u32 tx_flags) { struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; bool multi_link = sdata->vif.valid_links; struct { u8 id; u8 len; u8 ext_id; struct ieee80211_multi_link_elem ml; struct ieee80211_mle_basic_common_info basic; } __packed mle = { .id = WLAN_EID_EXTENSION, .len = sizeof(mle) - 2, .ext_id = WLAN_EID_EXT_EHT_MULTI_LINK, .ml.control = cpu_to_le16(IEEE80211_ML_CONTROL_TYPE_BASIC), .basic.len = sizeof(mle.basic), }; int err; memcpy(mle.basic.mld_mac_addr, sdata->vif.addr, ETH_ALEN); /* 24 + 6 = header + auth_algo + auth_transaction + status_code */ skb = dev_alloc_skb(local->hw.extra_tx_headroom + IEEE80211_WEP_IV_LEN + 24 + 6 + extra_len + IEEE80211_WEP_ICV_LEN + multi_link * sizeof(mle)); if (!skb) return; skb_reserve(skb, local->hw.extra_tx_headroom + IEEE80211_WEP_IV_LEN); mgmt = skb_put_zero(skb, 24 + 6); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH); memcpy(mgmt->da, da, ETH_ALEN); memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); memcpy(mgmt->bssid, bssid, ETH_ALEN); mgmt->u.auth.auth_alg = cpu_to_le16(auth_alg); mgmt->u.auth.auth_transaction = cpu_to_le16(transaction); mgmt->u.auth.status_code = cpu_to_le16(status); if (extra) skb_put_data(skb, extra, extra_len); if (multi_link) skb_put_data(skb, &mle, sizeof(mle)); if (auth_alg == WLAN_AUTH_SHARED_KEY && transaction == 3) { mgmt->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); err = ieee80211_wep_encrypt(local, skb, key, key_len, key_idx); if (WARN_ON(err)) { kfree_skb(skb); return; } } IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | tx_flags; ieee80211_tx_skb(sdata, skb); } void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, const u8 *da, const u8 *bssid, u16 stype, u16 reason, bool send_frame, u8 *frame_buf) { struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *mgmt = (void *)frame_buf; /* build frame */ mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | stype); mgmt->duration = 0; /* initialize only */ mgmt->seq_ctrl = 0; /* initialize only */ memcpy(mgmt->da, da, ETH_ALEN); memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); memcpy(mgmt->bssid, bssid, ETH_ALEN); /* u.deauth.reason_code == u.disassoc.reason_code */ mgmt->u.deauth.reason_code = cpu_to_le16(reason); if (send_frame) { skb = dev_alloc_skb(local->hw.extra_tx_headroom + IEEE80211_DEAUTH_FRAME_LEN); if (!skb) return; skb_reserve(skb, local->hw.extra_tx_headroom); /* copy in frame */ skb_put_data(skb, mgmt, IEEE80211_DEAUTH_FRAME_LEN); if (sdata->vif.type != NL80211_IFTYPE_STATION || !(sdata->u.mgd.flags & IEEE80211_STA_MFP_ENABLED)) IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; ieee80211_tx_skb(sdata, skb); } } static u8 *ieee80211_write_he_6ghz_cap(u8 *pos, __le16 cap, u8 *end) { if ((end - pos) < 5) return pos; *pos++ = WLAN_EID_EXTENSION; *pos++ = 1 + sizeof(cap); *pos++ = WLAN_EID_EXT_HE_6GHZ_CAPA; memcpy(pos, &cap, sizeof(cap)); return pos + 2; } static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata, u8 *buffer, size_t buffer_len, const u8 *ie, size_t ie_len, enum nl80211_band band, u32 rate_mask, struct cfg80211_chan_def *chandef, size_t *offset, u32 flags) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; const struct ieee80211_sta_he_cap *he_cap; const struct ieee80211_sta_eht_cap *eht_cap; u8 *pos = buffer, *end = buffer + buffer_len; size_t noffset; int supp_rates_len, i; u8 rates[32]; int num_rates; int ext_rates_len; int shift; u32 rate_flags; bool have_80mhz = false; *offset = 0; sband = local->hw.wiphy->bands[band]; if (WARN_ON_ONCE(!sband)) return 0; rate_flags = ieee80211_chandef_rate_flags(chandef); shift = ieee80211_chandef_get_shift(chandef); num_rates = 0; for (i = 0; i < sband->n_bitrates; i++) { if ((BIT(i) & rate_mask) == 0) continue; /* skip rate */ if ((rate_flags & sband->bitrates[i].flags) != rate_flags) continue; rates[num_rates++] = (u8) DIV_ROUND_UP(sband->bitrates[i].bitrate, (1 << shift) * 5); } supp_rates_len = min_t(int, num_rates, 8); if (end - pos < 2 + supp_rates_len) goto out_err; *pos++ = WLAN_EID_SUPP_RATES; *pos++ = supp_rates_len; memcpy(pos, rates, supp_rates_len); pos += supp_rates_len; /* insert "request information" if in custom IEs */ if (ie && ie_len) { static const u8 before_extrates[] = { WLAN_EID_SSID, WLAN_EID_SUPP_RATES, WLAN_EID_REQUEST, }; noffset = ieee80211_ie_split(ie, ie_len, before_extrates, ARRAY_SIZE(before_extrates), *offset); if (end - pos < noffset - *offset) goto out_err; memcpy(pos, ie + *offset, noffset - *offset); pos += noffset - *offset; *offset = noffset; } ext_rates_len = num_rates - supp_rates_len; if (ext_rates_len > 0) { if (end - pos < 2 + ext_rates_len) goto out_err; *pos++ = WLAN_EID_EXT_SUPP_RATES; *pos++ = ext_rates_len; memcpy(pos, rates + supp_rates_len, ext_rates_len); pos += ext_rates_len; } if (chandef->chan && sband->band == NL80211_BAND_2GHZ) { if (end - pos < 3) goto out_err; *pos++ = WLAN_EID_DS_PARAMS; *pos++ = 1; *pos++ = ieee80211_frequency_to_channel( chandef->chan->center_freq); } if (flags & IEEE80211_PROBE_FLAG_MIN_CONTENT) goto done; /* insert custom IEs that go before HT */ if (ie && ie_len) { static const u8 before_ht[] = { /* * no need to list the ones split off already * (or generated here) */ WLAN_EID_DS_PARAMS, WLAN_EID_SUPPORTED_REGULATORY_CLASSES, }; noffset = ieee80211_ie_split(ie, ie_len, before_ht, ARRAY_SIZE(before_ht), *offset); if (end - pos < noffset - *offset) goto out_err; memcpy(pos, ie + *offset, noffset - *offset); pos += noffset - *offset; *offset = noffset; } if (sband->ht_cap.ht_supported) { if (end - pos < 2 + sizeof(struct ieee80211_ht_cap)) goto out_err; pos = ieee80211_ie_build_ht_cap(pos, &sband->ht_cap, sband->ht_cap.cap); } /* insert custom IEs that go before VHT */ if (ie && ie_len) { static const u8 before_vht[] = { /* * no need to list the ones split off already * (or generated here) */ WLAN_EID_BSS_COEX_2040, WLAN_EID_EXT_CAPABILITY, WLAN_EID_SSID_LIST, WLAN_EID_CHANNEL_USAGE, WLAN_EID_INTERWORKING, WLAN_EID_MESH_ID, /* 60 GHz (Multi-band, DMG, MMS) can't happen */ }; noffset = ieee80211_ie_split(ie, ie_len, before_vht, ARRAY_SIZE(before_vht), *offset); if (end - pos < noffset - *offset) goto out_err; memcpy(pos, ie + *offset, noffset - *offset); pos += noffset - *offset; *offset = noffset; } /* Check if any channel in this sband supports at least 80 MHz */ for (i = 0; i < sband->n_channels; i++) { if (sband->channels[i].flags & (IEEE80211_CHAN_DISABLED | IEEE80211_CHAN_NO_80MHZ)) continue; have_80mhz = true; break; } if (sband->vht_cap.vht_supported && have_80mhz) { if (end - pos < 2 + sizeof(struct ieee80211_vht_cap)) goto out_err; pos = ieee80211_ie_build_vht_cap(pos, &sband->vht_cap, sband->vht_cap.cap); } /* insert custom IEs that go before HE */ if (ie && ie_len) { static const u8 before_he[] = { /* * no need to list the ones split off before VHT * or generated here */ WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_REQ_PARAMS, WLAN_EID_AP_CSN, /* TODO: add 11ah/11aj/11ak elements */ }; noffset = ieee80211_ie_split(ie, ie_len, before_he, ARRAY_SIZE(before_he), *offset); if (end - pos < noffset - *offset) goto out_err; memcpy(pos, ie + *offset, noffset - *offset); pos += noffset - *offset; *offset = noffset; } he_cap = ieee80211_get_he_iftype_cap(sband, ieee80211_vif_type_p2p(&sdata->vif)); if (he_cap && cfg80211_any_usable_channels(local->hw.wiphy, BIT(sband->band), IEEE80211_CHAN_NO_HE)) { pos = ieee80211_ie_build_he_cap(0, pos, he_cap, end); if (!pos) goto out_err; } eht_cap = ieee80211_get_eht_iftype_cap(sband, ieee80211_vif_type_p2p(&sdata->vif)); if (eht_cap && cfg80211_any_usable_channels(local->hw.wiphy, BIT(sband->band), IEEE80211_CHAN_NO_HE | IEEE80211_CHAN_NO_EHT)) { pos = ieee80211_ie_build_eht_cap(pos, he_cap, eht_cap, end, sdata->vif.type == NL80211_IFTYPE_AP); if (!pos) goto out_err; } if (cfg80211_any_usable_channels(local->hw.wiphy, BIT(NL80211_BAND_6GHZ), IEEE80211_CHAN_NO_HE)) { struct ieee80211_supported_band *sband6; sband6 = local->hw.wiphy->bands[NL80211_BAND_6GHZ]; he_cap = ieee80211_get_he_iftype_cap(sband6, ieee80211_vif_type_p2p(&sdata->vif)); if (he_cap) { enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif); __le16 cap = ieee80211_get_he_6ghz_capa(sband6, iftype); pos = ieee80211_write_he_6ghz_cap(pos, cap, end); } } /* * If adding more here, adjust code in main.c * that calculates local->scan_ies_len. */ return pos - buffer; out_err: WARN_ONCE(1, "not enough space for preq IEs\n"); done: return pos - buffer; } int ieee80211_build_preq_ies(struct ieee80211_sub_if_data *sdata, u8 *buffer, size_t buffer_len, struct ieee80211_scan_ies *ie_desc, const u8 *ie, size_t ie_len, u8 bands_used, u32 *rate_masks, struct cfg80211_chan_def *chandef, u32 flags) { size_t pos = 0, old_pos = 0, custom_ie_offset = 0; int i; memset(ie_desc, 0, sizeof(*ie_desc)); for (i = 0; i < NUM_NL80211_BANDS; i++) { if (bands_used & BIT(i)) { pos += ieee80211_build_preq_ies_band(sdata, buffer + pos, buffer_len - pos, ie, ie_len, i, rate_masks[i], chandef, &custom_ie_offset, flags); ie_desc->ies[i] = buffer + old_pos; ie_desc->len[i] = pos - old_pos; old_pos = pos; } } /* add any remaining custom IEs */ if (ie && ie_len) { if (WARN_ONCE(buffer_len - pos < ie_len - custom_ie_offset, "not enough space for preq custom IEs\n")) return pos; memcpy(buffer + pos, ie + custom_ie_offset, ie_len - custom_ie_offset); ie_desc->common_ies = buffer + pos; ie_desc->common_ie_len = ie_len - custom_ie_offset; pos += ie_len - custom_ie_offset; } return pos; }; struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, const u8 *src, const u8 *dst, u32 ratemask, struct ieee80211_channel *chan, const u8 *ssid, size_t ssid_len, const u8 *ie, size_t ie_len, u32 flags) { struct ieee80211_local *local = sdata->local; struct cfg80211_chan_def chandef; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; int ies_len; u32 rate_masks[NUM_NL80211_BANDS] = {}; struct ieee80211_scan_ies dummy_ie_desc; /* * Do not send DS Channel parameter for directed probe requests * in order to maximize the chance that we get a response. Some * badly-behaved APs don't respond when this parameter is included. */ chandef.width = sdata->vif.bss_conf.chandef.width; if (flags & IEEE80211_PROBE_FLAG_DIRECTED) chandef.chan = NULL; else chandef.chan = chan; skb = ieee80211_probereq_get(&local->hw, src, ssid, ssid_len, local->scan_ies_len + ie_len); if (!skb) return NULL; rate_masks[chan->band] = ratemask; ies_len = ieee80211_build_preq_ies(sdata, skb_tail_pointer(skb), skb_tailroom(skb), &dummy_ie_desc, ie, ie_len, BIT(chan->band), rate_masks, &chandef, flags); skb_put(skb, ies_len); if (dst) { mgmt = (struct ieee80211_mgmt *) skb->data; memcpy(mgmt->da, dst, ETH_ALEN); memcpy(mgmt->bssid, dst, ETH_ALEN); } IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; return skb; } u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems, enum nl80211_band band, u32 *basic_rates) { struct ieee80211_supported_band *sband; size_t num_rates; u32 supp_rates, rate_flags; int i, j, shift; sband = sdata->local->hw.wiphy->bands[band]; if (WARN_ON(!sband)) return 1; rate_flags = ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chandef); shift = ieee80211_vif_get_shift(&sdata->vif); num_rates = sband->n_bitrates; supp_rates = 0; for (i = 0; i < elems->supp_rates_len + elems->ext_supp_rates_len; i++) { u8 rate = 0; int own_rate; bool is_basic; if (i < elems->supp_rates_len) rate = elems->supp_rates[i]; else if (elems->ext_supp_rates) rate = elems->ext_supp_rates [i - elems->supp_rates_len]; own_rate = 5 * (rate & 0x7f); is_basic = !!(rate & 0x80); if (is_basic && (rate & 0x7f) == BSS_MEMBERSHIP_SELECTOR_HT_PHY) continue; for (j = 0; j < num_rates; j++) { int brate; if ((rate_flags & sband->bitrates[j].flags) != rate_flags) continue; brate = DIV_ROUND_UP(sband->bitrates[j].bitrate, 1 << shift); if (brate == own_rate) { supp_rates |= BIT(j); if (basic_rates && is_basic) *basic_rates |= BIT(j); } } } return supp_rates; } void ieee80211_stop_device(struct ieee80211_local *local) { ieee80211_led_radio(local, false); ieee80211_mod_tpt_led_trig(local, 0, IEEE80211_TPT_LEDTRIG_FL_RADIO); cancel_work_sync(&local->reconfig_filter); flush_workqueue(local->workqueue); drv_stop(local); } static void ieee80211_flush_completed_scan(struct ieee80211_local *local, bool aborted) { /* It's possible that we don't handle the scan completion in * time during suspend, so if it's still marked as completed * here, queue the work and flush it to clean things up. * Instead of calling the worker function directly here, we * really queue it to avoid potential races with other flows * scheduling the same work. */ if (test_bit(SCAN_COMPLETED, &local->scanning)) { /* If coming from reconfiguration failure, abort the scan so * we don't attempt to continue a partial HW scan - which is * possible otherwise if (e.g.) the 2.4 GHz portion was the * completed scan, and a 5 GHz portion is still pending. */ if (aborted) set_bit(SCAN_ABORTED, &local->scanning); ieee80211_queue_delayed_work(&local->hw, &local->scan_work, 0); flush_delayed_work(&local->scan_work); } } static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; struct ieee80211_chanctx *ctx; /* * We get here if during resume the device can't be restarted properly. * We might also get here if this happens during HW reset, which is a * slightly different situation and we need to drop all connections in * the latter case. * * Ask cfg80211 to turn off all interfaces, this will result in more * warnings but at least we'll then get into a clean stopped state. */ local->resuming = false; local->suspended = false; local->in_reconfig = false; ieee80211_flush_completed_scan(local, true); /* scheduled scan clearly can't be running any more, but tell * cfg80211 and clear local state */ ieee80211_sched_scan_end(local); list_for_each_entry(sdata, &local->interfaces, list) sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER; /* Mark channel contexts as not being in the driver any more to avoid * removing them from the driver during the shutdown process... */ mutex_lock(&local->chanctx_mtx); list_for_each_entry(ctx, &local->chanctx_list, list) ctx->driver_present = false; mutex_unlock(&local->chanctx_mtx); } static void ieee80211_assign_chanctx(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link) { struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *ctx; if (!local->use_chanctx) return; mutex_lock(&local->chanctx_mtx); conf = rcu_dereference_protected(link->conf->chanctx_conf, lockdep_is_held(&local->chanctx_mtx)); if (conf) { ctx = container_of(conf, struct ieee80211_chanctx, conf); drv_assign_vif_chanctx(local, sdata, link->conf, ctx); } mutex_unlock(&local->chanctx_mtx); } static void ieee80211_reconfig_stations(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; struct sta_info *sta; /* add STAs back */ mutex_lock(&local->sta_mtx); list_for_each_entry(sta, &local->sta_list, list) { enum ieee80211_sta_state state; if (!sta->uploaded || sta->sdata != sdata) continue; for (state = IEEE80211_STA_NOTEXIST; state < sta->sta_state; state++) WARN_ON(drv_sta_state(local, sta->sdata, sta, state, state + 1)); } mutex_unlock(&local->sta_mtx); } static int ieee80211_reconfig_nan(struct ieee80211_sub_if_data *sdata) { struct cfg80211_nan_func *func, **funcs; int res, id, i = 0; res = drv_start_nan(sdata->local, sdata, &sdata->u.nan.conf); if (WARN_ON(res)) return res; funcs = kcalloc(sdata->local->hw.max_nan_de_entries + 1, sizeof(*funcs), GFP_KERNEL); if (!funcs) return -ENOMEM; /* Add all the functions: * This is a little bit ugly. We need to call a potentially sleeping * callback for each NAN function, so we can't hold the spinlock. */ spin_lock_bh(&sdata->u.nan.func_lock); idr_for_each_entry(&sdata->u.nan.function_inst_ids, func, id) funcs[i++] = func; spin_unlock_bh(&sdata->u.nan.func_lock); for (i = 0; funcs[i]; i++) { res = drv_add_nan_func(sdata->local, sdata, funcs[i]); if (WARN_ON(res)) ieee80211_nan_func_terminated(&sdata->vif, funcs[i]->instance_id, NL80211_NAN_FUNC_TERM_REASON_ERROR, GFP_KERNEL); } kfree(funcs); return 0; } int ieee80211_reconfig(struct ieee80211_local *local) { struct ieee80211_hw *hw = &local->hw; struct ieee80211_sub_if_data *sdata; struct ieee80211_chanctx *ctx; struct sta_info *sta; int res, i; bool reconfig_due_to_wowlan = false; struct ieee80211_sub_if_data *sched_scan_sdata; struct cfg80211_sched_scan_request *sched_scan_req; bool sched_scan_stopped = false; bool suspended = local->suspended; bool in_reconfig = false; /* nothing to do if HW shouldn't run */ if (!local->open_count) goto wake_up; #ifdef CONFIG_PM if (suspended) local->resuming = true; if (local->wowlan) { /* * In the wowlan case, both mac80211 and the device * are functional when the resume op is called, so * clear local->suspended so the device could operate * normally (e.g. pass rx frames). */ local->suspended = false; res = drv_resume(local); local->wowlan = false; if (res < 0) { local->resuming = false; return res; } if (res == 0) goto wake_up; WARN_ON(res > 1); /* * res is 1, which means the driver requested * to go through a regular reset on wakeup. * restore local->suspended in this case. */ reconfig_due_to_wowlan = true; local->suspended = true; } #endif /* * In case of hw_restart during suspend (without wowlan), * cancel restart work, as we are reconfiguring the device * anyway. * Note that restart_work is scheduled on a frozen workqueue, * so we can't deadlock in this case. */ if (suspended && local->in_reconfig && !reconfig_due_to_wowlan) cancel_work_sync(&local->restart_work); local->started = false; /* * Upon resume hardware can sometimes be goofy due to * various platform / driver / bus issues, so restarting * the device may at times not work immediately. Propagate * the error. */ res = drv_start(local); if (res) { if (suspended) WARN(1, "Hardware became unavailable upon resume. This could be a software issue prior to suspend or a hardware issue.\n"); else WARN(1, "Hardware became unavailable during restart.\n"); ieee80211_handle_reconfig_failure(local); return res; } /* setup fragmentation threshold */ drv_set_frag_threshold(local, hw->wiphy->frag_threshold); /* setup RTS threshold */ drv_set_rts_threshold(local, hw->wiphy->rts_threshold); /* reset coverage class */ drv_set_coverage_class(local, hw->wiphy->coverage_class); ieee80211_led_radio(local, true); ieee80211_mod_tpt_led_trig(local, IEEE80211_TPT_LEDTRIG_FL_RADIO, 0); /* add interfaces */ sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (sdata) { /* in HW restart it exists already */ WARN_ON(local->resuming); res = drv_add_interface(local, sdata); if (WARN_ON(res)) { RCU_INIT_POINTER(local->monitor_sdata, NULL); synchronize_net(); kfree(sdata); } } list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN && sdata->vif.type != NL80211_IFTYPE_MONITOR && ieee80211_sdata_running(sdata)) { res = drv_add_interface(local, sdata); if (WARN_ON(res)) break; } } /* If adding any of the interfaces failed above, roll back and * report failure. */ if (res) { list_for_each_entry_continue_reverse(sdata, &local->interfaces, list) if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN && sdata->vif.type != NL80211_IFTYPE_MONITOR && ieee80211_sdata_running(sdata)) drv_remove_interface(local, sdata); ieee80211_handle_reconfig_failure(local); return res; } /* add channel contexts */ if (local->use_chanctx) { mutex_lock(&local->chanctx_mtx); list_for_each_entry(ctx, &local->chanctx_list, list) if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) WARN_ON(drv_add_chanctx(local, ctx)); mutex_unlock(&local->chanctx_mtx); sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (sdata && ieee80211_sdata_running(sdata)) ieee80211_assign_chanctx(local, sdata, &sdata->deflink); } /* reconfigure hardware */ ieee80211_hw_config(local, ~0); ieee80211_configure_filter(local); /* Finally also reconfigure all the BSS information */ list_for_each_entry(sdata, &local->interfaces, list) { unsigned int link_id; u32 changed; if (!ieee80211_sdata_running(sdata)) continue; sdata_lock(sdata); for (link_id = 0; link_id < ARRAY_SIZE(sdata->vif.link_conf); link_id++) { struct ieee80211_link_data *link; link = sdata_dereference(sdata->link[link_id], sdata); if (link) ieee80211_assign_chanctx(local, sdata, link); } switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: break; case NL80211_IFTYPE_ADHOC: if (sdata->vif.cfg.ibss_joined) WARN_ON(drv_join_ibss(local, sdata)); fallthrough; default: ieee80211_reconfig_stations(sdata); fallthrough; case NL80211_IFTYPE_AP: /* AP stations are handled later */ for (i = 0; i < IEEE80211_NUM_ACS; i++) drv_conf_tx(local, &sdata->deflink, i, &sdata->deflink.tx_conf[i]); break; } sdata_unlock(sdata); /* common change flags for all interface types */ changed = BSS_CHANGED_ERP_CTS_PROT | BSS_CHANGED_ERP_PREAMBLE | BSS_CHANGED_ERP_SLOT | BSS_CHANGED_HT | BSS_CHANGED_BASIC_RATES | BSS_CHANGED_BEACON_INT | BSS_CHANGED_BSSID | BSS_CHANGED_CQM | BSS_CHANGED_QOS | BSS_CHANGED_IDLE | BSS_CHANGED_TXPOWER | BSS_CHANGED_MCAST_RATE; if (sdata->vif.bss_conf.mu_mimo_owner) changed |= BSS_CHANGED_MU_GROUPS; switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: changed |= BSS_CHANGED_ASSOC | BSS_CHANGED_ARP_FILTER | BSS_CHANGED_PS; /* Re-send beacon info report to the driver */ if (sdata->deflink.u.mgd.have_beacon) changed |= BSS_CHANGED_BEACON_INFO; if (sdata->vif.bss_conf.max_idle_period || sdata->vif.bss_conf.protected_keep_alive) changed |= BSS_CHANGED_KEEP_ALIVE; sdata_lock(sdata); ieee80211_bss_info_change_notify(sdata, changed); sdata_unlock(sdata); break; case NL80211_IFTYPE_OCB: changed |= BSS_CHANGED_OCB; ieee80211_bss_info_change_notify(sdata, changed); break; case NL80211_IFTYPE_ADHOC: changed |= BSS_CHANGED_IBSS; fallthrough; case NL80211_IFTYPE_AP: changed |= BSS_CHANGED_SSID | BSS_CHANGED_P2P_PS; if (sdata->vif.bss_conf.ftm_responder == 1 && wiphy_ext_feature_isset(sdata->local->hw.wiphy, NL80211_EXT_FEATURE_ENABLE_FTM_RESPONDER)) changed |= BSS_CHANGED_FTM_RESPONDER; if (sdata->vif.type == NL80211_IFTYPE_AP) { changed |= BSS_CHANGED_AP_PROBE_RESP; if (rcu_access_pointer(sdata->deflink.u.ap.beacon)) drv_start_ap(local, sdata, sdata->deflink.conf); } fallthrough; case NL80211_IFTYPE_MESH_POINT: if (sdata->vif.bss_conf.enable_beacon) { changed |= BSS_CHANGED_BEACON | BSS_CHANGED_BEACON_ENABLED; ieee80211_bss_info_change_notify(sdata, changed); } break; case NL80211_IFTYPE_NAN: res = ieee80211_reconfig_nan(sdata); if (res < 0) { ieee80211_handle_reconfig_failure(local); return res; } break; case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_P2P_DEVICE: /* nothing to do */ break; case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_WDS: WARN_ON(1); break; } } ieee80211_recalc_ps(local); /* * The sta might be in psm against the ap (e.g. because * this was the state before a hw restart), so we * explicitly send a null packet in order to make sure * it'll sync against the ap (and get out of psm). */ if (!(local->hw.conf.flags & IEEE80211_CONF_PS)) { list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type != NL80211_IFTYPE_STATION) continue; if (!sdata->u.mgd.associated) continue; ieee80211_send_nullfunc(local, sdata, false); } } /* APs are now beaconing, add back stations */ list_for_each_entry(sdata, &local->interfaces, list) { if (!ieee80211_sdata_running(sdata)) continue; sdata_lock(sdata); switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_AP: ieee80211_reconfig_stations(sdata); break; default: break; } sdata_unlock(sdata); } /* add back keys */ list_for_each_entry(sdata, &local->interfaces, list) ieee80211_reenable_keys(sdata); /* Reconfigure sched scan if it was interrupted by FW restart */ mutex_lock(&local->mtx); sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata, lockdep_is_held(&local->mtx)); sched_scan_req = rcu_dereference_protected(local->sched_scan_req, lockdep_is_held(&local->mtx)); if (sched_scan_sdata && sched_scan_req) /* * Sched scan stopped, but we don't want to report it. Instead, * we're trying to reschedule. However, if more than one scan * plan was set, we cannot reschedule since we don't know which * scan plan was currently running (and some scan plans may have * already finished). */ if (sched_scan_req->n_scan_plans > 1 || __ieee80211_request_sched_scan_start(sched_scan_sdata, sched_scan_req)) { RCU_INIT_POINTER(local->sched_scan_sdata, NULL); RCU_INIT_POINTER(local->sched_scan_req, NULL); sched_scan_stopped = true; } mutex_unlock(&local->mtx); if (sched_scan_stopped) cfg80211_sched_scan_stopped_locked(local->hw.wiphy, 0); wake_up: if (local->monitors == local->open_count && local->monitors > 0) ieee80211_add_virtual_monitor(local); /* * Clear the WLAN_STA_BLOCK_BA flag so new aggregation * sessions can be established after a resume. * * Also tear down aggregation sessions since reconfiguring * them in a hardware restart scenario is not easily done * right now, and the hardware will have lost information * about the sessions, but we and the AP still think they * are active. This is really a workaround though. */ if (ieee80211_hw_check(hw, AMPDU_AGGREGATION)) { mutex_lock(&local->sta_mtx); list_for_each_entry(sta, &local->sta_list, list) { if (!local->resuming) ieee80211_sta_tear_down_BA_sessions( sta, AGG_STOP_LOCAL_REQUEST); clear_sta_flag(sta, WLAN_STA_BLOCK_BA); } mutex_unlock(&local->sta_mtx); } /* * If this is for hw restart things are still running. * We may want to change that later, however. */ if (local->open_count && (!suspended || reconfig_due_to_wowlan)) drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_RESTART); if (local->in_reconfig) { in_reconfig = local->in_reconfig; local->in_reconfig = false; barrier(); /* Restart deferred ROCs */ mutex_lock(&local->mtx); ieee80211_start_next_roc(local); mutex_unlock(&local->mtx); /* Requeue all works */ list_for_each_entry(sdata, &local->interfaces, list) ieee80211_queue_work(&local->hw, &sdata->work); } ieee80211_wake_queues_by_reason(hw, IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_SUSPEND, false); if (in_reconfig) { list_for_each_entry(sdata, &local->interfaces, list) { if (!ieee80211_sdata_running(sdata)) continue; if (sdata->vif.type == NL80211_IFTYPE_STATION) ieee80211_sta_restart(sdata); } } if (!suspended) return 0; #ifdef CONFIG_PM /* first set suspended false, then resuming */ local->suspended = false; mb(); local->resuming = false; ieee80211_flush_completed_scan(local, false); if (local->open_count && !reconfig_due_to_wowlan) drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_SUSPEND); list_for_each_entry(sdata, &local->interfaces, list) { if (!ieee80211_sdata_running(sdata)) continue; if (sdata->vif.type == NL80211_IFTYPE_STATION) ieee80211_sta_restart(sdata); } mod_timer(&local->sta_cleanup, jiffies + 1); #else WARN_ON(1); #endif return 0; } static void ieee80211_reconfig_disconnect(struct ieee80211_vif *vif, u8 flag) { struct ieee80211_sub_if_data *sdata; struct ieee80211_local *local; struct ieee80211_key *key; if (WARN_ON(!vif)) return; sdata = vif_to_sdata(vif); local = sdata->local; if (WARN_ON(flag & IEEE80211_SDATA_DISCONNECT_RESUME && !local->resuming)) return; if (WARN_ON(flag & IEEE80211_SDATA_DISCONNECT_HW_RESTART && !local->in_reconfig)) return; if (WARN_ON(vif->type != NL80211_IFTYPE_STATION)) return; sdata->flags |= flag; mutex_lock(&local->key_mtx); list_for_each_entry(key, &sdata->key_list, list) key->flags |= KEY_FLAG_TAINTED; mutex_unlock(&local->key_mtx); } void ieee80211_hw_restart_disconnect(struct ieee80211_vif *vif) { ieee80211_reconfig_disconnect(vif, IEEE80211_SDATA_DISCONNECT_HW_RESTART); } EXPORT_SYMBOL_GPL(ieee80211_hw_restart_disconnect); void ieee80211_resume_disconnect(struct ieee80211_vif *vif) { ieee80211_reconfig_disconnect(vif, IEEE80211_SDATA_DISCONNECT_RESUME); } EXPORT_SYMBOL_GPL(ieee80211_resume_disconnect); void ieee80211_recalc_smps(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link) { struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_chanctx *chanctx; mutex_lock(&local->chanctx_mtx); chanctx_conf = rcu_dereference_protected(link->conf->chanctx_conf, lockdep_is_held(&local->chanctx_mtx)); /* * This function can be called from a work, thus it may be possible * that the chanctx_conf is removed (due to a disconnection, for * example). * So nothing should be done in such case. */ if (!chanctx_conf) goto unlock; chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf); ieee80211_recalc_smps_chanctx(local, chanctx); unlock: mutex_unlock(&local->chanctx_mtx); } void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata, int link_id) { struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_chanctx *chanctx; int i; mutex_lock(&local->chanctx_mtx); for (i = 0; i < ARRAY_SIZE(sdata->vif.link_conf); i++) { struct ieee80211_bss_conf *bss_conf; if (link_id >= 0 && link_id != i) continue; rcu_read_lock(); bss_conf = rcu_dereference(sdata->vif.link_conf[i]); if (!bss_conf) { rcu_read_unlock(); continue; } chanctx_conf = rcu_dereference_protected(bss_conf->chanctx_conf, lockdep_is_held(&local->chanctx_mtx)); /* * Since we hold the chanctx_mtx (checked above) * we can take the chanctx_conf pointer out of the * RCU critical section, it cannot go away without * the mutex. Just the way we reached it could - in * theory - go away, but we don't really care and * it really shouldn't happen anyway. */ rcu_read_unlock(); if (!chanctx_conf) goto unlock; chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf); ieee80211_recalc_chanctx_min_def(local, chanctx); } unlock: mutex_unlock(&local->chanctx_mtx); } size_t ieee80211_ie_split_vendor(const u8 *ies, size_t ielen, size_t offset) { size_t pos = offset; while (pos < ielen && ies[pos] != WLAN_EID_VENDOR_SPECIFIC) pos += 2 + ies[pos + 1]; return pos; } u8 *ieee80211_ie_build_ht_cap(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, u16 cap) { __le16 tmp; *pos++ = WLAN_EID_HT_CAPABILITY; *pos++ = sizeof(struct ieee80211_ht_cap); memset(pos, 0, sizeof(struct ieee80211_ht_cap)); /* capability flags */ tmp = cpu_to_le16(cap); memcpy(pos, &tmp, sizeof(u16)); pos += sizeof(u16); /* AMPDU parameters */ *pos++ = ht_cap->ampdu_factor | (ht_cap->ampdu_density << IEEE80211_HT_AMPDU_PARM_DENSITY_SHIFT); /* MCS set */ memcpy(pos, &ht_cap->mcs, sizeof(ht_cap->mcs)); pos += sizeof(ht_cap->mcs); /* extended capabilities */ pos += sizeof(__le16); /* BF capabilities */ pos += sizeof(__le32); /* antenna selection */ pos += sizeof(u8); return pos; } u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, u32 cap) { __le32 tmp; *pos++ = WLAN_EID_VHT_CAPABILITY; *pos++ = sizeof(struct ieee80211_vht_cap); memset(pos, 0, sizeof(struct ieee80211_vht_cap)); /* capability flags */ tmp = cpu_to_le32(cap); memcpy(pos, &tmp, sizeof(u32)); pos += sizeof(u32); /* VHT MCS set */ memcpy(pos, &vht_cap->vht_mcs, sizeof(vht_cap->vht_mcs)); pos += sizeof(vht_cap->vht_mcs); return pos; } u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) { const struct ieee80211_sta_he_cap *he_cap; struct ieee80211_supported_band *sband; u8 n; sband = ieee80211_get_sband(sdata); if (!sband) return 0; he_cap = ieee80211_get_he_iftype_cap(sband, iftype); if (!he_cap) return 0; n = ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem); return 2 + 1 + sizeof(he_cap->he_cap_elem) + n + ieee80211_he_ppe_size(he_cap->ppe_thres[0], he_cap->he_cap_elem.phy_cap_info); } u8 *ieee80211_ie_build_he_cap(ieee80211_conn_flags_t disable_flags, u8 *pos, const struct ieee80211_sta_he_cap *he_cap, u8 *end) { struct ieee80211_he_cap_elem elem; u8 n; u8 ie_len; u8 *orig_pos = pos; /* Make sure we have place for the IE */ /* * TODO: the 1 added is because this temporarily is under the EXTENSION * IE. Get rid of it when it moves. */ if (!he_cap) return orig_pos; /* modify on stack first to calculate 'n' and 'ie_len' correctly */ elem = he_cap->he_cap_elem; if (disable_flags & IEEE80211_CONN_DISABLE_40MHZ) elem.phy_cap_info[0] &= ~(IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G); if (disable_flags & IEEE80211_CONN_DISABLE_160MHZ) elem.phy_cap_info[0] &= ~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; if (disable_flags & IEEE80211_CONN_DISABLE_80P80MHZ) elem.phy_cap_info[0] &= ~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G; n = ieee80211_he_mcs_nss_size(&elem); ie_len = 2 + 1 + sizeof(he_cap->he_cap_elem) + n + ieee80211_he_ppe_size(he_cap->ppe_thres[0], he_cap->he_cap_elem.phy_cap_info); if ((end - pos) < ie_len) return orig_pos; *pos++ = WLAN_EID_EXTENSION; pos++; /* We'll set the size later below */ *pos++ = WLAN_EID_EXT_HE_CAPABILITY; /* Fixed data */ memcpy(pos, &elem, sizeof(elem)); pos += sizeof(elem); memcpy(pos, &he_cap->he_mcs_nss_supp, n); pos += n; /* Check if PPE Threshold should be present */ if ((he_cap->he_cap_elem.phy_cap_info[6] & IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0) goto end; /* * Calculate how many PPET16/PPET8 pairs are to come. Algorithm: * (NSS_M1 + 1) x (num of 1 bits in RU_INDEX_BITMASK) */ n = hweight8(he_cap->ppe_thres[0] & IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK); n *= (1 + ((he_cap->ppe_thres[0] & IEEE80211_PPE_THRES_NSS_MASK) >> IEEE80211_PPE_THRES_NSS_POS)); /* * Each pair is 6 bits, and we need to add the 7 "header" bits to the * total size. */ n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7; n = DIV_ROUND_UP(n, 8); /* Copy PPE Thresholds */ memcpy(pos, &he_cap->ppe_thres, n); pos += n; end: orig_pos[1] = (pos - orig_pos) - 2; return pos; } void ieee80211_ie_build_he_6ghz_cap(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode smps_mode, struct sk_buff *skb) { struct ieee80211_supported_band *sband; const struct ieee80211_sband_iftype_data *iftd; enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif); u8 *pos; u16 cap; if (!cfg80211_any_usable_channels(sdata->local->hw.wiphy, BIT(NL80211_BAND_6GHZ), IEEE80211_CHAN_NO_HE)) return; sband = sdata->local->hw.wiphy->bands[NL80211_BAND_6GHZ]; iftd = ieee80211_get_sband_iftype_data(sband, iftype); if (!iftd) return; /* Check for device HE 6 GHz capability before adding element */ if (!iftd->he_6ghz_capa.capa) return; cap = le16_to_cpu(iftd->he_6ghz_capa.capa); cap &= ~IEEE80211_HE_6GHZ_CAP_SM_PS; switch (smps_mode) { case IEEE80211_SMPS_AUTOMATIC: case IEEE80211_SMPS_NUM_MODES: WARN_ON(1); fallthrough; case IEEE80211_SMPS_OFF: cap |= u16_encode_bits(WLAN_HT_CAP_SM_PS_DISABLED, IEEE80211_HE_6GHZ_CAP_SM_PS); break; case IEEE80211_SMPS_STATIC: cap |= u16_encode_bits(WLAN_HT_CAP_SM_PS_STATIC, IEEE80211_HE_6GHZ_CAP_SM_PS); break; case IEEE80211_SMPS_DYNAMIC: cap |= u16_encode_bits(WLAN_HT_CAP_SM_PS_DYNAMIC, IEEE80211_HE_6GHZ_CAP_SM_PS); break; } pos = skb_put(skb, 2 + 1 + sizeof(cap)); ieee80211_write_he_6ghz_cap(pos, cpu_to_le16(cap), pos + 2 + 1 + sizeof(cap)); } u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, const struct cfg80211_chan_def *chandef, u16 prot_mode, bool rifs_mode) { struct ieee80211_ht_operation *ht_oper; /* Build HT Information */ *pos++ = WLAN_EID_HT_OPERATION; *pos++ = sizeof(struct ieee80211_ht_operation); ht_oper = (struct ieee80211_ht_operation *)pos; ht_oper->primary_chan = ieee80211_frequency_to_channel( chandef->chan->center_freq); switch (chandef->width) { case NL80211_CHAN_WIDTH_160: case NL80211_CHAN_WIDTH_80P80: case NL80211_CHAN_WIDTH_80: case NL80211_CHAN_WIDTH_40: if (chandef->center_freq1 > chandef->chan->center_freq) ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_ABOVE; else ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_BELOW; break; case NL80211_CHAN_WIDTH_320: /* HT information element should not be included on 6GHz */ WARN_ON(1); return pos; default: ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_NONE; break; } if (ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 && chandef->width != NL80211_CHAN_WIDTH_20_NOHT && chandef->width != NL80211_CHAN_WIDTH_20) ht_oper->ht_param |= IEEE80211_HT_PARAM_CHAN_WIDTH_ANY; if (rifs_mode) ht_oper->ht_param |= IEEE80211_HT_PARAM_RIFS_MODE; ht_oper->operation_mode = cpu_to_le16(prot_mode); ht_oper->stbc_param = 0x0000; /* It seems that Basic MCS set and Supported MCS set are identical for the first 10 bytes */ memset(&ht_oper->basic_set, 0, 16); memcpy(&ht_oper->basic_set, &ht_cap->mcs, 10); return pos + sizeof(struct ieee80211_ht_operation); } void ieee80211_ie_build_wide_bw_cs(u8 *pos, const struct cfg80211_chan_def *chandef) { *pos++ = WLAN_EID_WIDE_BW_CHANNEL_SWITCH; /* EID */ *pos++ = 3; /* IE length */ /* New channel width */ switch (chandef->width) { case NL80211_CHAN_WIDTH_80: *pos++ = IEEE80211_VHT_CHANWIDTH_80MHZ; break; case NL80211_CHAN_WIDTH_160: *pos++ = IEEE80211_VHT_CHANWIDTH_160MHZ; break; case NL80211_CHAN_WIDTH_80P80: *pos++ = IEEE80211_VHT_CHANWIDTH_80P80MHZ; break; case NL80211_CHAN_WIDTH_320: /* The behavior is not defined for 320 MHz channels */ WARN_ON(1); fallthrough; default: *pos++ = IEEE80211_VHT_CHANWIDTH_USE_HT; } /* new center frequency segment 0 */ *pos++ = ieee80211_frequency_to_channel(chandef->center_freq1); /* new center frequency segment 1 */ if (chandef->center_freq2) *pos++ = ieee80211_frequency_to_channel(chandef->center_freq2); else *pos++ = 0; } u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, const struct cfg80211_chan_def *chandef) { struct ieee80211_vht_operation *vht_oper; *pos++ = WLAN_EID_VHT_OPERATION; *pos++ = sizeof(struct ieee80211_vht_operation); vht_oper = (struct ieee80211_vht_operation *)pos; vht_oper->center_freq_seg0_idx = ieee80211_frequency_to_channel( chandef->center_freq1); if (chandef->center_freq2) vht_oper->center_freq_seg1_idx = ieee80211_frequency_to_channel(chandef->center_freq2); else vht_oper->center_freq_seg1_idx = 0x00; switch (chandef->width) { case NL80211_CHAN_WIDTH_160: /* * Convert 160 MHz channel width to new style as interop * workaround. */ vht_oper->chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ; vht_oper->center_freq_seg1_idx = vht_oper->center_freq_seg0_idx; if (chandef->chan->center_freq < chandef->center_freq1) vht_oper->center_freq_seg0_idx -= 8; else vht_oper->center_freq_seg0_idx += 8; break; case NL80211_CHAN_WIDTH_80P80: /* * Convert 80+80 MHz channel width to new style as interop * workaround. */ vht_oper->chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ; break; case NL80211_CHAN_WIDTH_80: vht_oper->chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ; break; case NL80211_CHAN_WIDTH_320: /* VHT information element should not be included on 6GHz */ WARN_ON(1); return pos; default: vht_oper->chan_width = IEEE80211_VHT_CHANWIDTH_USE_HT; break; } /* don't require special VHT peer rates */ vht_oper->basic_mcs_set = cpu_to_le16(0xffff); return pos + sizeof(struct ieee80211_vht_operation); } u8 *ieee80211_ie_build_he_oper(u8 *pos, struct cfg80211_chan_def *chandef) { struct ieee80211_he_operation *he_oper; struct ieee80211_he_6ghz_oper *he_6ghz_op; u32 he_oper_params; u8 ie_len = 1 + sizeof(struct ieee80211_he_operation); if (chandef->chan->band == NL80211_BAND_6GHZ) ie_len += sizeof(struct ieee80211_he_6ghz_oper); *pos++ = WLAN_EID_EXTENSION; *pos++ = ie_len; *pos++ = WLAN_EID_EXT_HE_OPERATION; he_oper_params = 0; he_oper_params |= u32_encode_bits(1023, /* disabled */ IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK); he_oper_params |= u32_encode_bits(1, IEEE80211_HE_OPERATION_ER_SU_DISABLE); he_oper_params |= u32_encode_bits(1, IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED); if (chandef->chan->band == NL80211_BAND_6GHZ) he_oper_params |= u32_encode_bits(1, IEEE80211_HE_OPERATION_6GHZ_OP_INFO); he_oper = (struct ieee80211_he_operation *)pos; he_oper->he_oper_params = cpu_to_le32(he_oper_params); /* don't require special HE peer rates */ he_oper->he_mcs_nss_set = cpu_to_le16(0xffff); pos += sizeof(struct ieee80211_he_operation); if (chandef->chan->band != NL80211_BAND_6GHZ) goto out; /* TODO add VHT operational */ he_6ghz_op = (struct ieee80211_he_6ghz_oper *)pos; he_6ghz_op->minrate = 6; /* 6 Mbps */ he_6ghz_op->primary = ieee80211_frequency_to_channel(chandef->chan->center_freq); he_6ghz_op->ccfs0 = ieee80211_frequency_to_channel(chandef->center_freq1); if (chandef->center_freq2) he_6ghz_op->ccfs1 = ieee80211_frequency_to_channel(chandef->center_freq2); else he_6ghz_op->ccfs1 = 0; switch (chandef->width) { case NL80211_CHAN_WIDTH_320: /* * TODO: mesh operation is not defined over 6GHz 320 MHz * channels. */ WARN_ON(1); break; case NL80211_CHAN_WIDTH_160: /* Convert 160 MHz channel width to new style as interop * workaround. */ he_6ghz_op->control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ; he_6ghz_op->ccfs1 = he_6ghz_op->ccfs0; if (chandef->chan->center_freq < chandef->center_freq1) he_6ghz_op->ccfs0 -= 8; else he_6ghz_op->ccfs0 += 8; fallthrough; case NL80211_CHAN_WIDTH_80P80: he_6ghz_op->control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ; break; case NL80211_CHAN_WIDTH_80: he_6ghz_op->control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ; break; case NL80211_CHAN_WIDTH_40: he_6ghz_op->control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ; break; default: he_6ghz_op->control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ; break; } pos += sizeof(struct ieee80211_he_6ghz_oper); out: return pos; } bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper, struct cfg80211_chan_def *chandef) { enum nl80211_channel_type channel_type; if (!ht_oper) return false; switch (ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { case IEEE80211_HT_PARAM_CHA_SEC_NONE: channel_type = NL80211_CHAN_HT20; break; case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: channel_type = NL80211_CHAN_HT40PLUS; break; case IEEE80211_HT_PARAM_CHA_SEC_BELOW: channel_type = NL80211_CHAN_HT40MINUS; break; default: return false; } cfg80211_chandef_create(chandef, chandef->chan, channel_type); return true; } bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, u32 vht_cap_info, const struct ieee80211_vht_operation *oper, const struct ieee80211_ht_operation *htop, struct cfg80211_chan_def *chandef) { struct cfg80211_chan_def new = *chandef; int cf0, cf1; int ccfs0, ccfs1, ccfs2; int ccf0, ccf1; u32 vht_cap; bool support_80_80 = false; bool support_160 = false; u8 ext_nss_bw_supp = u32_get_bits(vht_cap_info, IEEE80211_VHT_CAP_EXT_NSS_BW_MASK); u8 supp_chwidth = u32_get_bits(vht_cap_info, IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK); if (!oper || !htop) return false; vht_cap = hw->wiphy->bands[chandef->chan->band]->vht_cap.cap; support_160 = (vht_cap & (IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK | IEEE80211_VHT_CAP_EXT_NSS_BW_MASK)); support_80_80 = ((vht_cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) || (vht_cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && vht_cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) || ((vht_cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) >> IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT > 1)); ccfs0 = oper->center_freq_seg0_idx; ccfs1 = oper->center_freq_seg1_idx; ccfs2 = (le16_to_cpu(htop->operation_mode) & IEEE80211_HT_OP_MODE_CCFS2_MASK) >> IEEE80211_HT_OP_MODE_CCFS2_SHIFT; ccf0 = ccfs0; /* if not supported, parse as though we didn't understand it */ if (!ieee80211_hw_check(hw, SUPPORTS_VHT_EXT_NSS_BW)) ext_nss_bw_supp = 0; /* * Cf. IEEE 802.11 Table 9-250 * * We really just consider that because it's inefficient to connect * at a higher bandwidth than we'll actually be able to use. */ switch ((supp_chwidth << 4) | ext_nss_bw_supp) { default: case 0x00: ccf1 = 0; support_160 = false; support_80_80 = false; break; case 0x01: support_80_80 = false; fallthrough; case 0x02: case 0x03: ccf1 = ccfs2; break; case 0x10: ccf1 = ccfs1; break; case 0x11: case 0x12: if (!ccfs1) ccf1 = ccfs2; else ccf1 = ccfs1; break; case 0x13: case 0x20: case 0x23: ccf1 = ccfs1; break; } cf0 = ieee80211_channel_to_frequency(ccf0, chandef->chan->band); cf1 = ieee80211_channel_to_frequency(ccf1, chandef->chan->band); switch (oper->chan_width) { case IEEE80211_VHT_CHANWIDTH_USE_HT: /* just use HT information directly */ break; case IEEE80211_VHT_CHANWIDTH_80MHZ: new.width = NL80211_CHAN_WIDTH_80; new.center_freq1 = cf0; /* If needed, adjust based on the newer interop workaround. */ if (ccf1) { unsigned int diff; diff = abs(ccf1 - ccf0); if ((diff == 8) && support_160) { new.width = NL80211_CHAN_WIDTH_160; new.center_freq1 = cf1; } else if ((diff > 8) && support_80_80) { new.width = NL80211_CHAN_WIDTH_80P80; new.center_freq2 = cf1; } } break; case IEEE80211_VHT_CHANWIDTH_160MHZ: /* deprecated encoding */ new.width = NL80211_CHAN_WIDTH_160; new.center_freq1 = cf0; break; case IEEE80211_VHT_CHANWIDTH_80P80MHZ: /* deprecated encoding */ new.width = NL80211_CHAN_WIDTH_80P80; new.center_freq1 = cf0; new.center_freq2 = cf1; break; default: return false; } if (!cfg80211_chandef_valid(&new)) return false; *chandef = new; return true; } void ieee80211_chandef_eht_oper(const struct ieee80211_eht_operation *eht_oper, bool support_160, bool support_320, struct cfg80211_chan_def *chandef) { struct ieee80211_eht_operation_info *info = (void *)eht_oper->optional; chandef->center_freq1 = ieee80211_channel_to_frequency(info->ccfs0, chandef->chan->band); switch (u8_get_bits(info->control, IEEE80211_EHT_OPER_CHAN_WIDTH)) { case IEEE80211_EHT_OPER_CHAN_WIDTH_20MHZ: chandef->width = NL80211_CHAN_WIDTH_20; break; case IEEE80211_EHT_OPER_CHAN_WIDTH_40MHZ: chandef->width = NL80211_CHAN_WIDTH_40; break; case IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ: chandef->width = NL80211_CHAN_WIDTH_80; break; case IEEE80211_EHT_OPER_CHAN_WIDTH_160MHZ: if (support_160) { chandef->width = NL80211_CHAN_WIDTH_160; chandef->center_freq1 = ieee80211_channel_to_frequency(info->ccfs1, chandef->chan->band); } else { chandef->width = NL80211_CHAN_WIDTH_80; } break; case IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ: if (support_320) { chandef->width = NL80211_CHAN_WIDTH_320; chandef->center_freq1 = ieee80211_channel_to_frequency(info->ccfs1, chandef->chan->band); } else if (support_160) { chandef->width = NL80211_CHAN_WIDTH_160; } else { chandef->width = NL80211_CHAN_WIDTH_80; if (chandef->center_freq1 > chandef->chan->center_freq) chandef->center_freq1 -= 40; else chandef->center_freq1 += 40; } break; } } bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, const struct ieee80211_he_operation *he_oper, const struct ieee80211_eht_operation *eht_oper, struct cfg80211_chan_def *chandef) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif); const struct ieee80211_sta_he_cap *he_cap; const struct ieee80211_sta_eht_cap *eht_cap; struct cfg80211_chan_def he_chandef = *chandef; const struct ieee80211_he_6ghz_oper *he_6ghz_oper; struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; bool support_80_80, support_160, support_320; u8 he_phy_cap, eht_phy_cap; u32 freq; if (chandef->chan->band != NL80211_BAND_6GHZ) return true; sband = local->hw.wiphy->bands[NL80211_BAND_6GHZ]; he_cap = ieee80211_get_he_iftype_cap(sband, iftype); if (!he_cap) { sdata_info(sdata, "Missing iftype sband data/HE cap"); return false; } he_phy_cap = he_cap->he_cap_elem.phy_cap_info[0]; support_160 = he_phy_cap & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; support_80_80 = he_phy_cap & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G; if (!he_oper) { sdata_info(sdata, "HE is not advertised on (on %d MHz), expect issues\n", chandef->chan->center_freq); return false; } eht_cap = ieee80211_get_eht_iftype_cap(sband, iftype); if (!eht_cap) { sdata_info(sdata, "Missing iftype sband data/EHT cap"); eht_oper = NULL; } he_6ghz_oper = ieee80211_he_6ghz_oper(he_oper); if (!he_6ghz_oper) { sdata_info(sdata, "HE 6GHz operation missing (on %d MHz), expect issues\n", chandef->chan->center_freq); return false; } /* * The EHT operation IE does not contain the primary channel so the * primary channel frequency should be taken from the 6 GHz operation * information. */ freq = ieee80211_channel_to_frequency(he_6ghz_oper->primary, NL80211_BAND_6GHZ); he_chandef.chan = ieee80211_get_channel(sdata->local->hw.wiphy, freq); switch (u8_get_bits(he_6ghz_oper->control, IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { case IEEE80211_6GHZ_CTRL_REG_LPI_AP: bss_conf->power_type = IEEE80211_REG_LPI_AP; break; case IEEE80211_6GHZ_CTRL_REG_SP_AP: bss_conf->power_type = IEEE80211_REG_SP_AP; break; default: bss_conf->power_type = IEEE80211_REG_UNSET_AP; break; } if (!eht_oper || !(eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT)) { switch (u8_get_bits(he_6ghz_oper->control, IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH)) { case IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ: he_chandef.width = NL80211_CHAN_WIDTH_20; break; case IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ: he_chandef.width = NL80211_CHAN_WIDTH_40; break; case IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ: he_chandef.width = NL80211_CHAN_WIDTH_80; break; case IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ: he_chandef.width = NL80211_CHAN_WIDTH_80; if (!he_6ghz_oper->ccfs1) break; if (abs(he_6ghz_oper->ccfs1 - he_6ghz_oper->ccfs0) == 8) { if (support_160) he_chandef.width = NL80211_CHAN_WIDTH_160; } else { if (support_80_80) he_chandef.width = NL80211_CHAN_WIDTH_80P80; } break; } if (he_chandef.width == NL80211_CHAN_WIDTH_160) { he_chandef.center_freq1 = ieee80211_channel_to_frequency(he_6ghz_oper->ccfs1, NL80211_BAND_6GHZ); } else { he_chandef.center_freq1 = ieee80211_channel_to_frequency(he_6ghz_oper->ccfs0, NL80211_BAND_6GHZ); if (support_80_80 || support_160) he_chandef.center_freq2 = ieee80211_channel_to_frequency(he_6ghz_oper->ccfs1, NL80211_BAND_6GHZ); } } else { eht_phy_cap = eht_cap->eht_cap_elem.phy_cap_info[0]; support_320 = eht_phy_cap & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ; ieee80211_chandef_eht_oper(eht_oper, support_160, support_320, &he_chandef); } if (!cfg80211_chandef_valid(&he_chandef)) { sdata_info(sdata, "HE 6GHz operation resulted in invalid chandef: %d MHz/%d/%d MHz/%d MHz\n", he_chandef.chan ? he_chandef.chan->center_freq : 0, he_chandef.width, he_chandef.center_freq1, he_chandef.center_freq2); return false; } *chandef = he_chandef; return true; } bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper, struct cfg80211_chan_def *chandef) { u32 oper_freq; if (!oper) return false; switch (FIELD_GET(S1G_OPER_CH_WIDTH_OPER, oper->ch_width)) { case IEEE80211_S1G_CHANWIDTH_1MHZ: chandef->width = NL80211_CHAN_WIDTH_1; break; case IEEE80211_S1G_CHANWIDTH_2MHZ: chandef->width = NL80211_CHAN_WIDTH_2; break; case IEEE80211_S1G_CHANWIDTH_4MHZ: chandef->width = NL80211_CHAN_WIDTH_4; break; case IEEE80211_S1G_CHANWIDTH_8MHZ: chandef->width = NL80211_CHAN_WIDTH_8; break; case IEEE80211_S1G_CHANWIDTH_16MHZ: chandef->width = NL80211_CHAN_WIDTH_16; break; default: return false; } oper_freq = ieee80211_channel_to_freq_khz(oper->oper_ch, NL80211_BAND_S1GHZ); chandef->center_freq1 = KHZ_TO_MHZ(oper_freq); chandef->freq1_offset = oper_freq % 1000; return true; } int ieee80211_parse_bitrates(enum nl80211_chan_width width, const struct ieee80211_supported_band *sband, const u8 *srates, int srates_len, u32 *rates) { u32 rate_flags = ieee80211_chanwidth_rate_flags(width); int shift = ieee80211_chanwidth_get_shift(width); struct ieee80211_rate *br; int brate, rate, i, j, count = 0; *rates = 0; for (i = 0; i < srates_len; i++) { rate = srates[i] & 0x7f; for (j = 0; j < sband->n_bitrates; j++) { br = &sband->bitrates[j]; if ((rate_flags & br->flags) != rate_flags) continue; brate = DIV_ROUND_UP(br->bitrate, (1 << shift) * 5); if (brate == rate) { *rates |= BIT(j); count++; break; } } } return count; } int ieee80211_add_srates_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, bool need_basic, enum nl80211_band band) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; int rate, shift; u8 i, rates, *pos; u32 basic_rates = sdata->vif.bss_conf.basic_rates; u32 rate_flags; shift = ieee80211_vif_get_shift(&sdata->vif); rate_flags = ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chandef); sband = local->hw.wiphy->bands[band]; rates = 0; for (i = 0; i < sband->n_bitrates; i++) { if ((rate_flags & sband->bitrates[i].flags) != rate_flags) continue; rates++; } if (rates > 8) rates = 8; if (skb_tailroom(skb) < rates + 2) return -ENOMEM; pos = skb_put(skb, rates + 2); *pos++ = WLAN_EID_SUPP_RATES; *pos++ = rates; for (i = 0; i < rates; i++) { u8 basic = 0; if ((rate_flags & sband->bitrates[i].flags) != rate_flags) continue; if (need_basic && basic_rates & BIT(i)) basic = 0x80; rate = DIV_ROUND_UP(sband->bitrates[i].bitrate, 5 * (1 << shift)); *pos++ = basic | (u8) rate; } return 0; } int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, bool need_basic, enum nl80211_band band) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; int rate, shift; u8 i, exrates, *pos; u32 basic_rates = sdata->vif.bss_conf.basic_rates; u32 rate_flags; rate_flags = ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chandef); shift = ieee80211_vif_get_shift(&sdata->vif); sband = local->hw.wiphy->bands[band]; exrates = 0; for (i = 0; i < sband->n_bitrates; i++) { if ((rate_flags & sband->bitrates[i].flags) != rate_flags) continue; exrates++; } if (exrates > 8) exrates -= 8; else exrates = 0; if (skb_tailroom(skb) < exrates + 2) return -ENOMEM; if (exrates) { pos = skb_put(skb, exrates + 2); *pos++ = WLAN_EID_EXT_SUPP_RATES; *pos++ = exrates; for (i = 8; i < sband->n_bitrates; i++) { u8 basic = 0; if ((rate_flags & sband->bitrates[i].flags) != rate_flags) continue; if (need_basic && basic_rates & BIT(i)) basic = 0x80; rate = DIV_ROUND_UP(sband->bitrates[i].bitrate, 5 * (1 << shift)); *pos++ = basic | (u8) rate; } } return 0; } int ieee80211_ave_rssi(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); if (WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION)) return 0; return -ewma_beacon_signal_read(&sdata->deflink.u.mgd.ave_beacon_signal); } EXPORT_SYMBOL_GPL(ieee80211_ave_rssi); u8 ieee80211_mcs_to_chains(const struct ieee80211_mcs_info *mcs) { if (!mcs) return 1; /* TODO: consider rx_highest */ if (mcs->rx_mask[3]) return 4; if (mcs->rx_mask[2]) return 3; if (mcs->rx_mask[1]) return 2; return 1; } /** * ieee80211_calculate_rx_timestamp - calculate timestamp in frame * @local: mac80211 hw info struct * @status: RX status * @mpdu_len: total MPDU length (including FCS) * @mpdu_offset: offset into MPDU to calculate timestamp at * * This function calculates the RX timestamp at the given MPDU offset, taking * into account what the RX timestamp was. An offset of 0 will just normalize * the timestamp to TSF at beginning of MPDU reception. */ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, struct ieee80211_rx_status *status, unsigned int mpdu_len, unsigned int mpdu_offset) { u64 ts = status->mactime; struct rate_info ri; u16 rate; u8 n_ltf; if (WARN_ON(!ieee80211_have_rx_timestamp(status))) return 0; memset(&ri, 0, sizeof(ri)); ri.bw = status->bw; /* Fill cfg80211 rate info */ switch (status->encoding) { case RX_ENC_HE: ri.flags |= RATE_INFO_FLAGS_HE_MCS; ri.mcs = status->rate_idx; ri.nss = status->nss; ri.he_ru_alloc = status->he_ru; if (status->enc_flags & RX_ENC_FLAG_SHORT_GI) ri.flags |= RATE_INFO_FLAGS_SHORT_GI; /* * See P802.11ax_D6.0, section 27.3.4 for * VHT PPDU format. */ if (status->flag & RX_FLAG_MACTIME_PLCP_START) { mpdu_offset += 2; ts += 36; /* * TODO: * For HE MU PPDU, add the HE-SIG-B. * For HE ER PPDU, add 8us for the HE-SIG-A. * For HE TB PPDU, add 4us for the HE-STF. * Add the HE-LTF durations - variable. */ } break; case RX_ENC_HT: ri.mcs = status->rate_idx; ri.flags |= RATE_INFO_FLAGS_MCS; if (status->enc_flags & RX_ENC_FLAG_SHORT_GI) ri.flags |= RATE_INFO_FLAGS_SHORT_GI; /* * See P802.11REVmd_D3.0, section 19.3.2 for * HT PPDU format. */ if (status->flag & RX_FLAG_MACTIME_PLCP_START) { mpdu_offset += 2; if (status->enc_flags & RX_ENC_FLAG_HT_GF) ts += 24; else ts += 32; /* * Add Data HT-LTFs per streams * TODO: add Extension HT-LTFs, 4us per LTF */ n_ltf = ((ri.mcs >> 3) & 3) + 1; n_ltf = n_ltf == 3 ? 4 : n_ltf; ts += n_ltf * 4; } break; case RX_ENC_VHT: ri.flags |= RATE_INFO_FLAGS_VHT_MCS; ri.mcs = status->rate_idx; ri.nss = status->nss; if (status->enc_flags & RX_ENC_FLAG_SHORT_GI) ri.flags |= RATE_INFO_FLAGS_SHORT_GI; /* * See P802.11REVmd_D3.0, section 21.3.2 for * VHT PPDU format. */ if (status->flag & RX_FLAG_MACTIME_PLCP_START) { mpdu_offset += 2; ts += 36; /* * Add VHT-LTFs per streams */ n_ltf = (ri.nss != 1) && (ri.nss % 2) ? ri.nss + 1 : ri.nss; ts += 4 * n_ltf; } break; default: WARN_ON(1); fallthrough; case RX_ENC_LEGACY: { struct ieee80211_supported_band *sband; int shift = 0; int bitrate; switch (status->bw) { case RATE_INFO_BW_10: shift = 1; break; case RATE_INFO_BW_5: shift = 2; break; } sband = local->hw.wiphy->bands[status->band]; bitrate = sband->bitrates[status->rate_idx].bitrate; ri.legacy = DIV_ROUND_UP(bitrate, (1 << shift)); if (status->flag & RX_FLAG_MACTIME_PLCP_START) { if (status->band == NL80211_BAND_5GHZ) { ts += 20 << shift; mpdu_offset += 2; } else if (status->enc_flags & RX_ENC_FLAG_SHORTPRE) { ts += 96; } else { ts += 192; } } break; } } rate = cfg80211_calculate_bitrate(&ri); if (WARN_ONCE(!rate, "Invalid bitrate: flags=0x%llx, idx=%d, vht_nss=%d\n", (unsigned long long)status->flag, status->rate_idx, status->nss)) return 0; /* rewind from end of MPDU */ if (status->flag & RX_FLAG_MACTIME_END) ts -= mpdu_len * 8 * 10 / rate; ts += mpdu_offset * 8 * 10 / rate; return ts; } void ieee80211_dfs_cac_cancel(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; struct cfg80211_chan_def chandef; /* for interface list, to avoid linking iflist_mtx and chanctx_mtx */ lockdep_assert_wiphy(local->hw.wiphy); mutex_lock(&local->mtx); list_for_each_entry(sdata, &local->interfaces, list) { /* it might be waiting for the local->mtx, but then * by the time it gets it, sdata->wdev.cac_started * will no longer be true */ cancel_delayed_work(&sdata->deflink.dfs_cac_timer_work); if (sdata->wdev.cac_started) { chandef = sdata->vif.bss_conf.chandef; ieee80211_link_release_channel(&sdata->deflink); cfg80211_cac_event(sdata->dev, &chandef, NL80211_RADAR_CAC_ABORTED, GFP_KERNEL); } } mutex_unlock(&local->mtx); } void ieee80211_dfs_radar_detected_work(struct work_struct *work) { struct ieee80211_local *local = container_of(work, struct ieee80211_local, radar_detected_work); struct cfg80211_chan_def chandef = local->hw.conf.chandef; struct ieee80211_chanctx *ctx; int num_chanctx = 0; mutex_lock(&local->chanctx_mtx); list_for_each_entry(ctx, &local->chanctx_list, list) { if (ctx->replace_state == IEEE80211_CHANCTX_REPLACES_OTHER) continue; num_chanctx++; chandef = ctx->conf.def; } mutex_unlock(&local->chanctx_mtx); wiphy_lock(local->hw.wiphy); ieee80211_dfs_cac_cancel(local); wiphy_unlock(local->hw.wiphy); if (num_chanctx > 1) /* XXX: multi-channel is not supported yet */ WARN_ON(1); else cfg80211_radar_event(local->hw.wiphy, &chandef, GFP_KERNEL); } void ieee80211_radar_detected(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); trace_api_radar_detected(local); schedule_work(&local->radar_detected_work); } EXPORT_SYMBOL(ieee80211_radar_detected); ieee80211_conn_flags_t ieee80211_chandef_downgrade(struct cfg80211_chan_def *c) { ieee80211_conn_flags_t ret; int tmp; switch (c->width) { case NL80211_CHAN_WIDTH_20: c->width = NL80211_CHAN_WIDTH_20_NOHT; ret = IEEE80211_CONN_DISABLE_HT | IEEE80211_CONN_DISABLE_VHT; break; case NL80211_CHAN_WIDTH_40: c->width = NL80211_CHAN_WIDTH_20; c->center_freq1 = c->chan->center_freq; ret = IEEE80211_CONN_DISABLE_40MHZ | IEEE80211_CONN_DISABLE_VHT; break; case NL80211_CHAN_WIDTH_80: tmp = (30 + c->chan->center_freq - c->center_freq1)/20; /* n_P40 */ tmp /= 2; /* freq_P40 */ c->center_freq1 = c->center_freq1 - 20 + 40 * tmp; c->width = NL80211_CHAN_WIDTH_40; ret = IEEE80211_CONN_DISABLE_VHT; break; case NL80211_CHAN_WIDTH_80P80: c->center_freq2 = 0; c->width = NL80211_CHAN_WIDTH_80; ret = IEEE80211_CONN_DISABLE_80P80MHZ | IEEE80211_CONN_DISABLE_160MHZ; break; case NL80211_CHAN_WIDTH_160: /* n_P20 */ tmp = (70 + c->chan->center_freq - c->center_freq1)/20; /* n_P80 */ tmp /= 4; c->center_freq1 = c->center_freq1 - 40 + 80 * tmp; c->width = NL80211_CHAN_WIDTH_80; ret = IEEE80211_CONN_DISABLE_80P80MHZ | IEEE80211_CONN_DISABLE_160MHZ; break; case NL80211_CHAN_WIDTH_320: /* n_P20 */ tmp = (150 + c->chan->center_freq - c->center_freq1) / 20; /* n_P160 */ tmp /= 8; c->center_freq1 = c->center_freq1 - 80 + 160 * tmp; c->width = NL80211_CHAN_WIDTH_160; ret = IEEE80211_CONN_DISABLE_320MHZ; break; default: case NL80211_CHAN_WIDTH_20_NOHT: WARN_ON_ONCE(1); c->width = NL80211_CHAN_WIDTH_20_NOHT; ret = IEEE80211_CONN_DISABLE_HT | IEEE80211_CONN_DISABLE_VHT; break; case NL80211_CHAN_WIDTH_1: case NL80211_CHAN_WIDTH_2: case NL80211_CHAN_WIDTH_4: case NL80211_CHAN_WIDTH_8: case NL80211_CHAN_WIDTH_16: case NL80211_CHAN_WIDTH_5: case NL80211_CHAN_WIDTH_10: WARN_ON_ONCE(1); /* keep c->width */ ret = IEEE80211_CONN_DISABLE_HT | IEEE80211_CONN_DISABLE_VHT; break; } WARN_ON_ONCE(!cfg80211_chandef_valid(c)); return ret; } /* * Returns true if smps_mode_new is strictly more restrictive than * smps_mode_old. */ bool ieee80211_smps_is_restrictive(enum ieee80211_smps_mode smps_mode_old, enum ieee80211_smps_mode smps_mode_new) { if (WARN_ON_ONCE(smps_mode_old == IEEE80211_SMPS_AUTOMATIC || smps_mode_new == IEEE80211_SMPS_AUTOMATIC)) return false; switch (smps_mode_old) { case IEEE80211_SMPS_STATIC: return false; case IEEE80211_SMPS_DYNAMIC: return smps_mode_new == IEEE80211_SMPS_STATIC; case IEEE80211_SMPS_OFF: return smps_mode_new != IEEE80211_SMPS_OFF; default: WARN_ON(1); } return false; } int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata, struct cfg80211_csa_settings *csa_settings) { struct sk_buff *skb; struct ieee80211_mgmt *mgmt; struct ieee80211_local *local = sdata->local; int freq; int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.chan_switch); u8 *pos; if (sdata->vif.type != NL80211_IFTYPE_ADHOC && sdata->vif.type != NL80211_IFTYPE_MESH_POINT) return -EOPNOTSUPP; skb = dev_alloc_skb(local->tx_headroom + hdr_len + 5 + /* channel switch announcement element */ 3 + /* secondary channel offset element */ 5 + /* wide bandwidth channel switch announcement */ 8); /* mesh channel switch parameters element */ if (!skb) return -ENOMEM; skb_reserve(skb, local->tx_headroom); mgmt = skb_put_zero(skb, hdr_len); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); eth_broadcast_addr(mgmt->da); memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); if (ieee80211_vif_is_mesh(&sdata->vif)) { memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN); } else { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; memcpy(mgmt->bssid, ifibss->bssid, ETH_ALEN); } mgmt->u.action.category = WLAN_CATEGORY_SPECTRUM_MGMT; mgmt->u.action.u.chan_switch.action_code = WLAN_ACTION_SPCT_CHL_SWITCH; pos = skb_put(skb, 5); *pos++ = WLAN_EID_CHANNEL_SWITCH; /* EID */ *pos++ = 3; /* IE length */ *pos++ = csa_settings->block_tx ? 1 : 0; /* CSA mode */ freq = csa_settings->chandef.chan->center_freq; *pos++ = ieee80211_frequency_to_channel(freq); /* channel */ *pos++ = csa_settings->count; /* count */ if (csa_settings->chandef.width == NL80211_CHAN_WIDTH_40) { enum nl80211_channel_type ch_type; skb_put(skb, 3); *pos++ = WLAN_EID_SECONDARY_CHANNEL_OFFSET; /* EID */ *pos++ = 1; /* IE length */ ch_type = cfg80211_get_chandef_type(&csa_settings->chandef); if (ch_type == NL80211_CHAN_HT40PLUS) *pos++ = IEEE80211_HT_PARAM_CHA_SEC_ABOVE; else *pos++ = IEEE80211_HT_PARAM_CHA_SEC_BELOW; } if (ieee80211_vif_is_mesh(&sdata->vif)) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; skb_put(skb, 8); *pos++ = WLAN_EID_CHAN_SWITCH_PARAM; /* EID */ *pos++ = 6; /* IE length */ *pos++ = sdata->u.mesh.mshcfg.dot11MeshTTL; /* Mesh TTL */ *pos = 0x00; /* Mesh Flag: Tx Restrict, Initiator, Reason */ *pos |= WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR; *pos++ |= csa_settings->block_tx ? WLAN_EID_CHAN_SWITCH_PARAM_TX_RESTRICT : 0x00; put_unaligned_le16(WLAN_REASON_MESH_CHAN, pos); /* Reason Cd */ pos += 2; put_unaligned_le16(ifmsh->pre_value, pos);/* Precedence Value */ pos += 2; } if (csa_settings->chandef.width == NL80211_CHAN_WIDTH_80 || csa_settings->chandef.width == NL80211_CHAN_WIDTH_80P80 || csa_settings->chandef.width == NL80211_CHAN_WIDTH_160) { skb_put(skb, 5); ieee80211_ie_build_wide_bw_cs(pos, &csa_settings->chandef); } ieee80211_tx_skb(sdata, skb); return 0; } static bool ieee80211_extend_noa_desc(struct ieee80211_noa_data *data, u32 tsf, int i) { s32 end = data->desc[i].start + data->desc[i].duration - (tsf + 1); int skip; if (end > 0) return false; /* One shot NOA */ if (data->count[i] == 1) return false; if (data->desc[i].interval == 0) return false; /* End time is in the past, check for repetitions */ skip = DIV_ROUND_UP(-end, data->desc[i].interval); if (data->count[i] < 255) { if (data->count[i] <= skip) { data->count[i] = 0; return false; } data->count[i] -= skip; } data->desc[i].start += skip * data->desc[i].interval; return true; } static bool ieee80211_extend_absent_time(struct ieee80211_noa_data *data, u32 tsf, s32 *offset) { bool ret = false; int i; for (i = 0; i < IEEE80211_P2P_NOA_DESC_MAX; i++) { s32 cur; if (!data->count[i]) continue; if (ieee80211_extend_noa_desc(data, tsf + *offset, i)) ret = true; cur = data->desc[i].start - tsf; if (cur > *offset) continue; cur = data->desc[i].start + data->desc[i].duration - tsf; if (cur > *offset) *offset = cur; } return ret; } static u32 ieee80211_get_noa_absent_time(struct ieee80211_noa_data *data, u32 tsf) { s32 offset = 0; int tries = 0; /* * arbitrary limit, used to avoid infinite loops when combined NoA * descriptors cover the full time period. */ int max_tries = 5; ieee80211_extend_absent_time(data, tsf, &offset); do { if (!ieee80211_extend_absent_time(data, tsf, &offset)) break; tries++; } while (tries < max_tries); return offset; } void ieee80211_update_p2p_noa(struct ieee80211_noa_data *data, u32 tsf) { u32 next_offset = BIT(31) - 1; int i; data->absent = 0; data->has_next_tsf = false; for (i = 0; i < IEEE80211_P2P_NOA_DESC_MAX; i++) { s32 start; if (!data->count[i]) continue; ieee80211_extend_noa_desc(data, tsf, i); start = data->desc[i].start - tsf; if (start <= 0) data->absent |= BIT(i); if (next_offset > start) next_offset = start; data->has_next_tsf = true; } if (data->absent) next_offset = ieee80211_get_noa_absent_time(data, tsf); data->next_tsf = tsf + next_offset; } EXPORT_SYMBOL(ieee80211_update_p2p_noa); int ieee80211_parse_p2p_noa(const struct ieee80211_p2p_noa_attr *attr, struct ieee80211_noa_data *data, u32 tsf) { int ret = 0; int i; memset(data, 0, sizeof(*data)); for (i = 0; i < IEEE80211_P2P_NOA_DESC_MAX; i++) { const struct ieee80211_p2p_noa_desc *desc = &attr->desc[i]; if (!desc->count || !desc->duration) continue; data->count[i] = desc->count; data->desc[i].start = le32_to_cpu(desc->start_time); data->desc[i].duration = le32_to_cpu(desc->duration); data->desc[i].interval = le32_to_cpu(desc->interval); if (data->count[i] > 1 && data->desc[i].interval < data->desc[i].duration) continue; ieee80211_extend_noa_desc(data, tsf, i); ret++; } if (ret) ieee80211_update_p2p_noa(data, tsf); return ret; } EXPORT_SYMBOL(ieee80211_parse_p2p_noa); void ieee80211_recalc_dtim(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { u64 tsf = drv_get_tsf(local, sdata); u64 dtim_count = 0; u16 beacon_int = sdata->vif.bss_conf.beacon_int * 1024; u8 dtim_period = sdata->vif.bss_conf.dtim_period; struct ps_data *ps; u8 bcns_from_dtim; if (tsf == -1ULL || !beacon_int || !dtim_period) return; if (sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { if (!sdata->bss) return; ps = &sdata->bss->ps; } else if (ieee80211_vif_is_mesh(&sdata->vif)) { ps = &sdata->u.mesh.ps; } else { return; } /* * actually finds last dtim_count, mac80211 will update in * __beacon_add_tim(). * dtim_count = dtim_period - (tsf / bcn_int) % dtim_period */ do_div(tsf, beacon_int); bcns_from_dtim = do_div(tsf, dtim_period); /* just had a DTIM */ if (!bcns_from_dtim) dtim_count = 0; else dtim_count = dtim_period - bcns_from_dtim; ps->dtim_count = dtim_count; } static u8 ieee80211_chanctx_radar_detect(struct ieee80211_local *local, struct ieee80211_chanctx *ctx) { struct ieee80211_link_data *link; u8 radar_detect = 0; lockdep_assert_held(&local->chanctx_mtx); if (WARN_ON(ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED)) return 0; list_for_each_entry(link, &ctx->reserved_links, reserved_chanctx_list) if (link->reserved_radar_required) radar_detect |= BIT(link->reserved_chandef.width); /* * An in-place reservation context should not have any assigned vifs * until it replaces the other context. */ WARN_ON(ctx->replace_state == IEEE80211_CHANCTX_REPLACES_OTHER && !list_empty(&ctx->assigned_links)); list_for_each_entry(link, &ctx->assigned_links, assigned_chanctx_list) { if (!link->radar_required) continue; radar_detect |= BIT(link->conf->chandef.width); } return radar_detect; } int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, const struct cfg80211_chan_def *chandef, enum ieee80211_chanctx_mode chanmode, u8 radar_detect) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *sdata_iter; enum nl80211_iftype iftype = sdata->wdev.iftype; struct ieee80211_chanctx *ctx; int total = 1; struct iface_combination_params params = { .radar_detect = radar_detect, }; lockdep_assert_held(&local->chanctx_mtx); if (WARN_ON(hweight32(radar_detect) > 1)) return -EINVAL; if (WARN_ON(chandef && chanmode == IEEE80211_CHANCTX_SHARED && !chandef->chan)) return -EINVAL; if (WARN_ON(iftype >= NUM_NL80211_IFTYPES)) return -EINVAL; if (sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_MESH_POINT) { /* * always passing this is harmless, since it'll be the * same value that cfg80211 finds if it finds the same * interface ... and that's always allowed */ params.new_beacon_int = sdata->vif.bss_conf.beacon_int; } /* Always allow software iftypes */ if (cfg80211_iftype_allowed(local->hw.wiphy, iftype, 0, 1)) { if (radar_detect) return -EINVAL; return 0; } if (chandef) params.num_different_channels = 1; if (iftype != NL80211_IFTYPE_UNSPECIFIED) params.iftype_num[iftype] = 1; list_for_each_entry(ctx, &local->chanctx_list, list) { if (ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED) continue; params.radar_detect |= ieee80211_chanctx_radar_detect(local, ctx); if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE) { params.num_different_channels++; continue; } if (chandef && chanmode == IEEE80211_CHANCTX_SHARED && cfg80211_chandef_compatible(chandef, &ctx->conf.def)) continue; params.num_different_channels++; } list_for_each_entry_rcu(sdata_iter, &local->interfaces, list) { struct wireless_dev *wdev_iter; wdev_iter = &sdata_iter->wdev; if (sdata_iter == sdata || !ieee80211_sdata_running(sdata_iter) || cfg80211_iftype_allowed(local->hw.wiphy, wdev_iter->iftype, 0, 1)) continue; params.iftype_num[wdev_iter->iftype]++; total++; } if (total == 1 && !params.radar_detect) return 0; return cfg80211_check_combinations(local->hw.wiphy, ¶ms); } static void ieee80211_iter_max_chans(const struct ieee80211_iface_combination *c, void *data) { u32 *max_num_different_channels = data; *max_num_different_channels = max(*max_num_different_channels, c->num_different_channels); } int ieee80211_max_num_channels(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; struct ieee80211_chanctx *ctx; u32 max_num_different_channels = 1; int err; struct iface_combination_params params = {0}; lockdep_assert_held(&local->chanctx_mtx); list_for_each_entry(ctx, &local->chanctx_list, list) { if (ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED) continue; params.num_different_channels++; params.radar_detect |= ieee80211_chanctx_radar_detect(local, ctx); } list_for_each_entry_rcu(sdata, &local->interfaces, list) params.iftype_num[sdata->wdev.iftype]++; err = cfg80211_iter_combinations(local->hw.wiphy, ¶ms, ieee80211_iter_max_chans, &max_num_different_channels); if (err < 0) return err; return max_num_different_channels; } void ieee80211_add_s1g_capab_ie(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta_s1g_cap *caps, struct sk_buff *skb) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_s1g_cap s1g_capab; u8 *pos; int i; if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) return; if (!caps->s1g) return; memcpy(s1g_capab.capab_info, caps->cap, sizeof(caps->cap)); memcpy(s1g_capab.supp_mcs_nss, caps->nss_mcs, sizeof(caps->nss_mcs)); /* override the capability info */ for (i = 0; i < sizeof(ifmgd->s1g_capa.capab_info); i++) { u8 mask = ifmgd->s1g_capa_mask.capab_info[i]; s1g_capab.capab_info[i] &= ~mask; s1g_capab.capab_info[i] |= ifmgd->s1g_capa.capab_info[i] & mask; } /* then MCS and NSS set */ for (i = 0; i < sizeof(ifmgd->s1g_capa.supp_mcs_nss); i++) { u8 mask = ifmgd->s1g_capa_mask.supp_mcs_nss[i]; s1g_capab.supp_mcs_nss[i] &= ~mask; s1g_capab.supp_mcs_nss[i] |= ifmgd->s1g_capa.supp_mcs_nss[i] & mask; } pos = skb_put(skb, 2 + sizeof(s1g_capab)); *pos++ = WLAN_EID_S1G_CAPABILITIES; *pos++ = sizeof(s1g_capab); memcpy(pos, &s1g_capab, sizeof(s1g_capab)); } void ieee80211_add_aid_request_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { u8 *pos = skb_put(skb, 3); *pos++ = WLAN_EID_AID_REQUEST; *pos++ = 1; *pos++ = 0; } u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo) { *buf++ = WLAN_EID_VENDOR_SPECIFIC; *buf++ = 7; /* len */ *buf++ = 0x00; /* Microsoft OUI 00:50:F2 */ *buf++ = 0x50; *buf++ = 0xf2; *buf++ = 2; /* WME */ *buf++ = 0; /* WME info */ *buf++ = 1; /* WME ver */ *buf++ = qosinfo; /* U-APSD no in use */ return buf; } void ieee80211_txq_get_depth(struct ieee80211_txq *txq, unsigned long *frame_cnt, unsigned long *byte_cnt) { struct txq_info *txqi = to_txq_info(txq); u32 frag_cnt = 0, frag_bytes = 0; struct sk_buff *skb; skb_queue_walk(&txqi->frags, skb) { frag_cnt++; frag_bytes += skb->len; } if (frame_cnt) *frame_cnt = txqi->tin.backlog_packets + frag_cnt; if (byte_cnt) *byte_cnt = txqi->tin.backlog_bytes + frag_bytes; } EXPORT_SYMBOL(ieee80211_txq_get_depth); const u8 ieee80211_ac_to_qos_mask[IEEE80211_NUM_ACS] = { IEEE80211_WMM_IE_STA_QOSINFO_AC_VO, IEEE80211_WMM_IE_STA_QOSINFO_AC_VI, IEEE80211_WMM_IE_STA_QOSINFO_AC_BE, IEEE80211_WMM_IE_STA_QOSINFO_AC_BK }; u16 ieee80211_encode_usf(int listen_interval) { static const int listen_int_usf[] = { 1, 10, 1000, 10000 }; u16 ui, usf = 0; /* find greatest USF */ while (usf < IEEE80211_MAX_USF) { if (listen_interval % listen_int_usf[usf + 1]) break; usf += 1; } ui = listen_interval / listen_int_usf[usf]; /* error if there is a remainder. Should've been checked by user */ WARN_ON_ONCE(ui > IEEE80211_MAX_UI); listen_interval = FIELD_PREP(LISTEN_INT_USF, usf) | FIELD_PREP(LISTEN_INT_UI, ui); return (u16) listen_interval; } u8 ieee80211_ie_len_eht_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) { const struct ieee80211_sta_he_cap *he_cap; const struct ieee80211_sta_eht_cap *eht_cap; struct ieee80211_supported_band *sband; bool is_ap; u8 n; sband = ieee80211_get_sband(sdata); if (!sband) return 0; he_cap = ieee80211_get_he_iftype_cap(sband, iftype); eht_cap = ieee80211_get_eht_iftype_cap(sband, iftype); if (!he_cap || !eht_cap) return 0; is_ap = iftype == NL80211_IFTYPE_AP || iftype == NL80211_IFTYPE_P2P_GO; n = ieee80211_eht_mcs_nss_size(&he_cap->he_cap_elem, &eht_cap->eht_cap_elem, is_ap); return 2 + 1 + sizeof(he_cap->he_cap_elem) + n + ieee80211_eht_ppe_size(eht_cap->eht_ppe_thres[0], eht_cap->eht_cap_elem.phy_cap_info); return 0; } u8 *ieee80211_ie_build_eht_cap(u8 *pos, const struct ieee80211_sta_he_cap *he_cap, const struct ieee80211_sta_eht_cap *eht_cap, u8 *end, bool for_ap) { u8 mcs_nss_len, ppet_len; u8 ie_len; u8 *orig_pos = pos; /* Make sure we have place for the IE */ if (!he_cap || !eht_cap) return orig_pos; mcs_nss_len = ieee80211_eht_mcs_nss_size(&he_cap->he_cap_elem, &eht_cap->eht_cap_elem, for_ap); ppet_len = ieee80211_eht_ppe_size(eht_cap->eht_ppe_thres[0], eht_cap->eht_cap_elem.phy_cap_info); ie_len = 2 + 1 + sizeof(eht_cap->eht_cap_elem) + mcs_nss_len + ppet_len; if ((end - pos) < ie_len) return orig_pos; *pos++ = WLAN_EID_EXTENSION; *pos++ = ie_len - 2; *pos++ = WLAN_EID_EXT_EHT_CAPABILITY; /* Fixed data */ memcpy(pos, &eht_cap->eht_cap_elem, sizeof(eht_cap->eht_cap_elem)); pos += sizeof(eht_cap->eht_cap_elem); memcpy(pos, &eht_cap->eht_mcs_nss_supp, mcs_nss_len); pos += mcs_nss_len; if (ppet_len) { memcpy(pos, &eht_cap->eht_ppe_thres, ppet_len); pos += ppet_len; } return pos; } void ieee80211_fragment_element(struct sk_buff *skb, u8 *len_pos) { unsigned int elem_len; if (!len_pos) return; elem_len = skb->data + skb->len - len_pos - 1; while (elem_len > 255) { /* this one is 255 */ *len_pos = 255; /* remaining data gets smaller */ elem_len -= 255; /* make space for the fragment ID/len in SKB */ skb_put(skb, 2); /* shift back the remaining data to place fragment ID/len */ memmove(len_pos + 255 + 3, len_pos + 255 + 1, elem_len); /* place the fragment ID */ len_pos += 255 + 1; *len_pos = WLAN_EID_FRAGMENT; /* and point to fragment length to update later */ len_pos++; } *len_pos = elem_len; } |
| 1554 1553 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us> */ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/filter.h> #include <linux/bpf.h> #include <net/netlink.h> #include <net/sock.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_bpf.h> #include <net/tc_act/tc_bpf.h> #define ACT_BPF_NAME_LEN 256 struct tcf_bpf_cfg { struct bpf_prog *filter; struct sock_filter *bpf_ops; const char *bpf_name; u16 bpf_num_ops; bool is_ebpf; }; static struct tc_action_ops act_bpf_ops; static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act, struct tcf_result *res) { bool at_ingress = skb_at_tc_ingress(skb); struct tcf_bpf *prog = to_bpf(act); struct bpf_prog *filter; int action, filter_res; tcf_lastuse_update(&prog->tcf_tm); bstats_update(this_cpu_ptr(prog->common.cpu_bstats), skb); filter = rcu_dereference(prog->filter); if (at_ingress) { __skb_push(skb, skb->mac_len); bpf_compute_data_pointers(skb); filter_res = bpf_prog_run(filter, skb); __skb_pull(skb, skb->mac_len); } else { bpf_compute_data_pointers(skb); filter_res = bpf_prog_run(filter, skb); } if (unlikely(!skb->tstamp && skb->mono_delivery_time)) skb->mono_delivery_time = 0; if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK) skb_orphan(skb); /* A BPF program may overwrite the default action opcode. * Similarly as in cls_bpf, if filter_res == -1 we use the * default action specified from tc. * * In case a different well-known TC_ACT opcode has been * returned, it will overwrite the default one. * * For everything else that is unknown, TC_ACT_UNSPEC is * returned. */ switch (filter_res) { case TC_ACT_PIPE: case TC_ACT_RECLASSIFY: case TC_ACT_OK: case TC_ACT_REDIRECT: action = filter_res; break; case TC_ACT_SHOT: action = filter_res; qstats_drop_inc(this_cpu_ptr(prog->common.cpu_qstats)); break; case TC_ACT_UNSPEC: action = prog->tcf_action; break; default: action = TC_ACT_UNSPEC; break; } return action; } static bool tcf_bpf_is_ebpf(const struct tcf_bpf *prog) { return !prog->bpf_ops; } static int tcf_bpf_dump_bpf_info(const struct tcf_bpf *prog, struct sk_buff *skb) { struct nlattr *nla; if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, prog->bpf_num_ops)) return -EMSGSIZE; nla = nla_reserve(skb, TCA_ACT_BPF_OPS, prog->bpf_num_ops * sizeof(struct sock_filter)); if (nla == NULL) return -EMSGSIZE; memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla)); return 0; } static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog, struct sk_buff *skb) { struct nlattr *nla; if (prog->bpf_name && nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name)) return -EMSGSIZE; if (nla_put_u32(skb, TCA_ACT_BPF_ID, prog->filter->aux->id)) return -EMSGSIZE; nla = nla_reserve(skb, TCA_ACT_BPF_TAG, sizeof(prog->filter->tag)); if (nla == NULL) return -EMSGSIZE; memcpy(nla_data(nla), prog->filter->tag, nla_len(nla)); return 0; } static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act, int bind, int ref) { unsigned char *tp = skb_tail_pointer(skb); struct tcf_bpf *prog = to_bpf(act); struct tc_act_bpf opt = { .index = prog->tcf_index, .refcnt = refcount_read(&prog->tcf_refcnt) - ref, .bindcnt = atomic_read(&prog->tcf_bindcnt) - bind, }; struct tcf_t tm; int ret; spin_lock_bh(&prog->tcf_lock); opt.action = prog->tcf_action; if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if (tcf_bpf_is_ebpf(prog)) ret = tcf_bpf_dump_ebpf_info(prog, skb); else ret = tcf_bpf_dump_bpf_info(prog, skb); if (ret) goto nla_put_failure; tcf_tm_dump(&tm, &prog->tcf_tm); if (nla_put_64bit(skb, TCA_ACT_BPF_TM, sizeof(tm), &tm, TCA_ACT_BPF_PAD)) goto nla_put_failure; spin_unlock_bh(&prog->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&prog->tcf_lock); nlmsg_trim(skb, tp); return -1; } static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = { [TCA_ACT_BPF_PARMS] = { .len = sizeof(struct tc_act_bpf) }, [TCA_ACT_BPF_FD] = { .type = NLA_U32 }, [TCA_ACT_BPF_NAME] = { .type = NLA_NUL_STRING, .len = ACT_BPF_NAME_LEN }, [TCA_ACT_BPF_OPS_LEN] = { .type = NLA_U16 }, [TCA_ACT_BPF_OPS] = { .type = NLA_BINARY, .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, }; static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg) { struct sock_filter *bpf_ops; struct sock_fprog_kern fprog_tmp; struct bpf_prog *fp; u16 bpf_size, bpf_num_ops; int ret; bpf_num_ops = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]); if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) return -EINVAL; bpf_size = bpf_num_ops * sizeof(*bpf_ops); if (bpf_size != nla_len(tb[TCA_ACT_BPF_OPS])) return -EINVAL; bpf_ops = kmemdup(nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size, GFP_KERNEL); if (bpf_ops == NULL) return -ENOMEM; fprog_tmp.len = bpf_num_ops; fprog_tmp.filter = bpf_ops; ret = bpf_prog_create(&fp, &fprog_tmp); if (ret < 0) { kfree(bpf_ops); return ret; } cfg->bpf_ops = bpf_ops; cfg->bpf_num_ops = bpf_num_ops; cfg->filter = fp; cfg->is_ebpf = false; return 0; } static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg) { struct bpf_prog *fp; char *name = NULL; u32 bpf_fd; bpf_fd = nla_get_u32(tb[TCA_ACT_BPF_FD]); fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_ACT); if (IS_ERR(fp)) return PTR_ERR(fp); if (tb[TCA_ACT_BPF_NAME]) { name = nla_memdup(tb[TCA_ACT_BPF_NAME], GFP_KERNEL); if (!name) { bpf_prog_put(fp); return -ENOMEM; } } cfg->bpf_name = name; cfg->filter = fp; cfg->is_ebpf = true; return 0; } static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg) { struct bpf_prog *filter = cfg->filter; if (filter) { if (cfg->is_ebpf) bpf_prog_put(filter); else bpf_prog_destroy(filter); } kfree(cfg->bpf_ops); kfree(cfg->bpf_name); } static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, struct tcf_bpf_cfg *cfg) { cfg->is_ebpf = tcf_bpf_is_ebpf(prog); /* updates to prog->filter are prevented, since it's called either * with tcf lock or during final cleanup in rcu callback */ cfg->filter = rcu_dereference_protected(prog->filter, 1); cfg->bpf_ops = prog->bpf_ops; cfg->bpf_name = prog->bpf_name; } static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_bpf_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tcf_bpf_cfg cfg, old; struct tc_act_bpf *parm; struct tcf_bpf *prog; bool is_bpf, is_ebpf; int ret, res = 0; u32 index; if (!nla) return -EINVAL; ret = nla_parse_nested_deprecated(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy, NULL); if (ret < 0) return ret; if (!tb[TCA_ACT_BPF_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_ACT_BPF_PARMS]); index = parm->index; ret = tcf_idr_check_alloc(tn, &index, act, bind); if (!ret) { ret = tcf_idr_create(tn, index, est, act, &act_bpf_ops, bind, true, flags); if (ret < 0) { tcf_idr_cleanup(tn, index); return ret; } res = ACT_P_CREATED; } else if (ret > 0) { /* Don't override defaults. */ if (bind) return 0; if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*act, bind); return -EEXIST; } } else { return ret; } ret = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (ret < 0) goto release_idr; is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS]; is_ebpf = tb[TCA_ACT_BPF_FD]; if (is_bpf == is_ebpf) { ret = -EINVAL; goto put_chain; } memset(&cfg, 0, sizeof(cfg)); ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) : tcf_bpf_init_from_efd(tb, &cfg); if (ret < 0) goto put_chain; prog = to_bpf(*act); spin_lock_bh(&prog->tcf_lock); if (res != ACT_P_CREATED) tcf_bpf_prog_fill_cfg(prog, &old); prog->bpf_ops = cfg.bpf_ops; prog->bpf_name = cfg.bpf_name; if (cfg.bpf_num_ops) prog->bpf_num_ops = cfg.bpf_num_ops; goto_ch = tcf_action_set_ctrlact(*act, parm->action, goto_ch); rcu_assign_pointer(prog->filter, cfg.filter); spin_unlock_bh(&prog->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (res != ACT_P_CREATED) { /* make sure the program being replaced is no longer executing */ synchronize_rcu(); tcf_bpf_cfg_cleanup(&old); } return res; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*act, bind); return ret; } static void tcf_bpf_cleanup(struct tc_action *act) { struct tcf_bpf_cfg tmp; tcf_bpf_prog_fill_cfg(to_bpf(act), &tmp); tcf_bpf_cfg_cleanup(&tmp); } static struct tc_action_ops act_bpf_ops __read_mostly = { .kind = "bpf", .id = TCA_ID_BPF, .owner = THIS_MODULE, .act = tcf_bpf_act, .dump = tcf_bpf_dump, .cleanup = tcf_bpf_cleanup, .init = tcf_bpf_init, .size = sizeof(struct tcf_bpf), }; static __net_init int bpf_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_bpf_ops.net_id); return tc_action_net_init(net, tn, &act_bpf_ops); } static void __net_exit bpf_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_bpf_ops.net_id); } static struct pernet_operations bpf_net_ops = { .init = bpf_init_net, .exit_batch = bpf_exit_net, .id = &act_bpf_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init bpf_init_module(void) { return tcf_register_action(&act_bpf_ops, &bpf_net_ops); } static void __exit bpf_cleanup_module(void) { tcf_unregister_action(&act_bpf_ops, &bpf_net_ops); } module_init(bpf_init_module); module_exit(bpf_cleanup_module); MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>"); MODULE_DESCRIPTION("TC BPF based action"); MODULE_LICENSE("GPL v2"); |
| 2039 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 | // SPDX-License-Identifier: GPL-2.0 #include <linux/string.h> #include <linux/kernel.h> #include <linux/of.h> #include <linux/of_device.h> #include <linux/of_address.h> #include <linux/of_iommu.h> #include <linux/of_reserved_mem.h> #include <linux/dma-direct.h> /* for bus_dma_region */ #include <linux/dma-map-ops.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mod_devicetable.h> #include <linux/slab.h> #include <linux/platform_device.h> #include <asm/errno.h> #include "of_private.h" /** * of_match_device - Tell if a struct device matches an of_device_id list * @matches: array of of device match structures to search in * @dev: the of device structure to match against * * Used by a driver to check whether an platform_device present in the * system is in its list of supported devices. */ const struct of_device_id *of_match_device(const struct of_device_id *matches, const struct device *dev) { if (!matches || !dev->of_node || dev->of_node_reused) return NULL; return of_match_node(matches, dev->of_node); } EXPORT_SYMBOL(of_match_device); int of_device_add(struct platform_device *ofdev) { BUG_ON(ofdev->dev.of_node == NULL); /* name and id have to be set so that the platform bus doesn't get * confused on matching */ ofdev->name = dev_name(&ofdev->dev); ofdev->id = PLATFORM_DEVID_NONE; /* * If this device has not binding numa node in devicetree, that is * of_node_to_nid returns NUMA_NO_NODE. device_add will assume that this * device is on the same node as the parent. */ set_dev_node(&ofdev->dev, of_node_to_nid(ofdev->dev.of_node)); return device_add(&ofdev->dev); } static void of_dma_set_restricted_buffer(struct device *dev, struct device_node *np) { struct device_node *node, *of_node = dev->of_node; int count, i; if (!IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL)) return; count = of_property_count_elems_of_size(of_node, "memory-region", sizeof(u32)); /* * If dev->of_node doesn't exist or doesn't contain memory-region, try * the OF node having DMA configuration. */ if (count <= 0) { of_node = np; count = of_property_count_elems_of_size( of_node, "memory-region", sizeof(u32)); } for (i = 0; i < count; i++) { node = of_parse_phandle(of_node, "memory-region", i); /* * There might be multiple memory regions, but only one * restricted-dma-pool region is allowed. */ if (of_device_is_compatible(node, "restricted-dma-pool") && of_device_is_available(node)) { of_node_put(node); break; } of_node_put(node); } /* * Attempt to initialize a restricted-dma-pool region if one was found. * Note that count can hold a negative error code. */ if (i < count && of_reserved_mem_device_init_by_idx(dev, of_node, i)) dev_warn(dev, "failed to initialise \"restricted-dma-pool\" memory node\n"); } /** * of_dma_configure_id - Setup DMA configuration * @dev: Device to apply DMA configuration * @np: Pointer to OF node having DMA configuration * @force_dma: Whether device is to be set up by of_dma_configure() even if * DMA capability is not explicitly described by firmware. * @id: Optional const pointer value input id * * Try to get devices's DMA configuration from DT and update it * accordingly. * * If platform code needs to use its own special DMA configuration, it * can use a platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE events * to fix up DMA configuration. */ int of_dma_configure_id(struct device *dev, struct device_node *np, bool force_dma, const u32 *id) { const struct iommu_ops *iommu; const struct bus_dma_region *map = NULL; struct device_node *bus_np; u64 dma_start = 0; u64 mask, end, size = 0; bool coherent; int ret; if (np == dev->of_node) bus_np = __of_get_dma_parent(np); else bus_np = of_node_get(np); ret = of_dma_get_range(bus_np, &map); of_node_put(bus_np); if (ret < 0) { /* * For legacy reasons, we have to assume some devices need * DMA configuration regardless of whether "dma-ranges" is * correctly specified or not. */ if (!force_dma) return ret == -ENODEV ? 0 : ret; } else { const struct bus_dma_region *r = map; u64 dma_end = 0; /* Determine the overall bounds of all DMA regions */ for (dma_start = ~0; r->size; r++) { /* Take lower and upper limits */ if (r->dma_start < dma_start) dma_start = r->dma_start; if (r->dma_start + r->size > dma_end) dma_end = r->dma_start + r->size; } size = dma_end - dma_start; /* * Add a work around to treat the size as mask + 1 in case * it is defined in DT as a mask. */ if (size & 1) { dev_warn(dev, "Invalid size 0x%llx for dma-range(s)\n", size); size = size + 1; } if (!size) { dev_err(dev, "Adjusted size 0x%llx invalid\n", size); kfree(map); return -EINVAL; } } /* * If @dev is expected to be DMA-capable then the bus code that created * it should have initialised its dma_mask pointer by this point. For * now, we'll continue the legacy behaviour of coercing it to the * coherent mask if not, but we'll no longer do so quietly. */ if (!dev->dma_mask) { dev_warn(dev, "DMA mask not set\n"); dev->dma_mask = &dev->coherent_dma_mask; } if (!size && dev->coherent_dma_mask) size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1); else if (!size) size = 1ULL << 32; /* * Limit coherent and dma mask based on size and default mask * set by the driver. */ end = dma_start + size - 1; mask = DMA_BIT_MASK(ilog2(end) + 1); dev->coherent_dma_mask &= mask; *dev->dma_mask &= mask; /* ...but only set bus limit and range map if we found valid dma-ranges earlier */ if (!ret) { dev->bus_dma_limit = end; dev->dma_range_map = map; } coherent = of_dma_is_coherent(np); dev_dbg(dev, "device is%sdma coherent\n", coherent ? " " : " not "); iommu = of_iommu_configure(dev, np, id); if (PTR_ERR(iommu) == -EPROBE_DEFER) { /* Don't touch range map if it wasn't set from a valid dma-ranges */ if (!ret) dev->dma_range_map = NULL; kfree(map); return -EPROBE_DEFER; } dev_dbg(dev, "device is%sbehind an iommu\n", iommu ? " " : " not "); arch_setup_dma_ops(dev, dma_start, size, iommu, coherent); if (!iommu) of_dma_set_restricted_buffer(dev, np); return 0; } EXPORT_SYMBOL_GPL(of_dma_configure_id); int of_device_register(struct platform_device *pdev) { device_initialize(&pdev->dev); return of_device_add(pdev); } EXPORT_SYMBOL(of_device_register); void of_device_unregister(struct platform_device *ofdev) { device_unregister(&ofdev->dev); } EXPORT_SYMBOL(of_device_unregister); const void *of_device_get_match_data(const struct device *dev) { const struct of_device_id *match; match = of_match_device(dev->driver->of_match_table, dev); if (!match) return NULL; return match->data; } EXPORT_SYMBOL(of_device_get_match_data); static ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len) { const char *compat; char *c; struct property *p; ssize_t csize; ssize_t tsize; if ((!dev) || (!dev->of_node)) return -ENODEV; /* Name & Type */ /* %p eats all alphanum characters, so %c must be used here */ csize = snprintf(str, len, "of:N%pOFn%c%s", dev->of_node, 'T', of_node_get_device_type(dev->of_node)); tsize = csize; len -= csize; if (str) str += csize; of_property_for_each_string(dev->of_node, "compatible", p, compat) { csize = strlen(compat) + 1; tsize += csize; if (csize > len) continue; csize = snprintf(str, len, "C%s", compat); for (c = str; c; ) { c = strchr(c, ' '); if (c) *c++ = '_'; } len -= csize; str += csize; } return tsize; } int of_device_request_module(struct device *dev) { char *str; ssize_t size; int ret; size = of_device_get_modalias(dev, NULL, 0); if (size < 0) return size; str = kmalloc(size + 1, GFP_KERNEL); if (!str) return -ENOMEM; of_device_get_modalias(dev, str, size); str[size] = '\0'; ret = request_module(str); kfree(str); return ret; } EXPORT_SYMBOL_GPL(of_device_request_module); /** * of_device_modalias - Fill buffer with newline terminated modalias string * @dev: Calling device * @str: Modalias string * @len: Size of @str */ ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len) { ssize_t sl = of_device_get_modalias(dev, str, len - 2); if (sl < 0) return sl; if (sl > len - 2) return -ENOMEM; str[sl++] = '\n'; str[sl] = 0; return sl; } EXPORT_SYMBOL_GPL(of_device_modalias); /** * of_device_uevent - Display OF related uevent information * @dev: Device to apply DMA configuration * @env: Kernel object's userspace event reference */ void of_device_uevent(struct device *dev, struct kobj_uevent_env *env) { const char *compat, *type; struct alias_prop *app; struct property *p; int seen = 0; if ((!dev) || (!dev->of_node)) return; add_uevent_var(env, "OF_NAME=%pOFn", dev->of_node); add_uevent_var(env, "OF_FULLNAME=%pOF", dev->of_node); type = of_node_get_device_type(dev->of_node); if (type) add_uevent_var(env, "OF_TYPE=%s", type); /* Since the compatible field can contain pretty much anything * it's not really legal to split it out with commas. We split it * up using a number of environment variables instead. */ of_property_for_each_string(dev->of_node, "compatible", p, compat) { add_uevent_var(env, "OF_COMPATIBLE_%d=%s", seen, compat); seen++; } add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen); seen = 0; mutex_lock(&of_mutex); list_for_each_entry(app, &aliases_lookup, link) { if (dev->of_node == app->np) { add_uevent_var(env, "OF_ALIAS_%d=%s", seen, app->alias); seen++; } } mutex_unlock(&of_mutex); } int of_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env) { int sl; if ((!dev) || (!dev->of_node)) return -ENODEV; /* Devicetree modalias is tricky, we add it in 2 steps */ if (add_uevent_var(env, "MODALIAS=")) return -ENOMEM; sl = of_device_get_modalias(dev, &env->buf[env->buflen-1], sizeof(env->buf) - env->buflen); if (sl >= (sizeof(env->buf) - env->buflen)) return -ENOMEM; env->buflen += sl; return 0; } EXPORT_SYMBOL_GPL(of_device_uevent_modalias); |
| 314 314 323 214 214 26 26 26 26 26 26 1 25 25 25 26 26 26 23 26 4 4 4 4 3 3 26 26 25 26 26 26 26 97 28 27 27 27 27 97 51 4 5 50 6 38 26 26 26 26 26 38 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 | /* * net/tipc/msg.c: TIPC message header routines * * Copyright (c) 2000-2006, 2014-2015, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include <net/sock.h> #include "core.h" #include "msg.h" #include "addr.h" #include "name_table.h" #include "crypto.h" #define BUF_ALIGN(x) ALIGN(x, 4) #define MAX_FORWARD_SIZE 1024 #ifdef CONFIG_TIPC_CRYPTO #define BUF_HEADROOM ALIGN(((LL_MAX_HEADER + 48) + EHDR_MAX_SIZE), 16) #define BUF_OVERHEAD (BUF_HEADROOM + TIPC_AES_GCM_TAG_SIZE) #else #define BUF_HEADROOM (LL_MAX_HEADER + 48) #define BUF_OVERHEAD BUF_HEADROOM #endif const int one_page_mtu = PAGE_SIZE - SKB_DATA_ALIGN(BUF_OVERHEAD) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); /** * tipc_buf_acquire - creates a TIPC message buffer * @size: message size (including TIPC header) * @gfp: memory allocation flags * * Return: a new buffer with data pointers set to the specified size. * * NOTE: * Headroom is reserved to allow prepending of a data link header. * There may also be unrequested tailroom present at the buffer's end. */ struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp) { struct sk_buff *skb; skb = alloc_skb_fclone(BUF_OVERHEAD + size, gfp); if (skb) { skb_reserve(skb, BUF_HEADROOM); skb_put(skb, size); skb->next = NULL; } return skb; } void tipc_msg_init(u32 own_node, struct tipc_msg *m, u32 user, u32 type, u32 hsize, u32 dnode) { memset(m, 0, hsize); msg_set_version(m); msg_set_user(m, user); msg_set_hdr_sz(m, hsize); msg_set_size(m, hsize); msg_set_prevnode(m, own_node); msg_set_type(m, type); if (hsize > SHORT_H_SIZE) { msg_set_orignode(m, own_node); msg_set_destnode(m, dnode); } } struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, uint data_sz, u32 dnode, u32 onode, u32 dport, u32 oport, int errcode) { struct tipc_msg *msg; struct sk_buff *buf; buf = tipc_buf_acquire(hdr_sz + data_sz, GFP_ATOMIC); if (unlikely(!buf)) return NULL; msg = buf_msg(buf); tipc_msg_init(onode, msg, user, type, hdr_sz, dnode); msg_set_size(msg, hdr_sz + data_sz); msg_set_origport(msg, oport); msg_set_destport(msg, dport); msg_set_errcode(msg, errcode); return buf; } /* tipc_buf_append(): Append a buffer to the fragment list of another buffer * @*headbuf: in: NULL for first frag, otherwise value returned from prev call * out: set when successful non-complete reassembly, otherwise NULL * @*buf: in: the buffer to append. Always defined * out: head buf after successful complete reassembly, otherwise NULL * Returns 1 when reassembly complete, otherwise 0 */ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) { struct sk_buff *head = *headbuf; struct sk_buff *frag = *buf; struct sk_buff *tail = NULL; struct tipc_msg *msg; u32 fragid; int delta; bool headstolen; if (!frag) goto err; msg = buf_msg(frag); fragid = msg_type(msg); frag->next = NULL; skb_pull(frag, msg_hdr_sz(msg)); if (fragid == FIRST_FRAGMENT) { if (unlikely(head)) goto err; *buf = NULL; if (skb_has_frag_list(frag) && __skb_linearize(frag)) goto err; frag = skb_unshare(frag, GFP_ATOMIC); if (unlikely(!frag)) goto err; head = *headbuf = frag; TIPC_SKB_CB(head)->tail = NULL; return 0; } if (!head) goto err; if (skb_try_coalesce(head, frag, &headstolen, &delta)) { kfree_skb_partial(frag, headstolen); } else { tail = TIPC_SKB_CB(head)->tail; if (!skb_has_frag_list(head)) skb_shinfo(head)->frag_list = frag; else tail->next = frag; head->truesize += frag->truesize; head->data_len += frag->len; head->len += frag->len; TIPC_SKB_CB(head)->tail = frag; } if (fragid == LAST_FRAGMENT) { TIPC_SKB_CB(head)->validated = 0; if (unlikely(!tipc_msg_validate(&head))) goto err; *buf = head; TIPC_SKB_CB(head)->tail = NULL; *headbuf = NULL; return 1; } *buf = NULL; return 0; err: kfree_skb(*buf); kfree_skb(*headbuf); *buf = *headbuf = NULL; return 0; } /** * tipc_msg_append(): Append data to tail of an existing buffer queue * @_hdr: header to be used * @m: the data to be appended * @mss: max allowable size of buffer * @dlen: size of data to be appended * @txq: queue to append to * * Return: the number of 1k blocks appended or errno value */ int tipc_msg_append(struct tipc_msg *_hdr, struct msghdr *m, int dlen, int mss, struct sk_buff_head *txq) { struct sk_buff *skb; int accounted, total, curr; int mlen, cpy, rem = dlen; struct tipc_msg *hdr; skb = skb_peek_tail(txq); accounted = skb ? msg_blocks(buf_msg(skb)) : 0; total = accounted; do { if (!skb || skb->len >= mss) { skb = tipc_buf_acquire(mss, GFP_KERNEL); if (unlikely(!skb)) return -ENOMEM; skb_orphan(skb); skb_trim(skb, MIN_H_SIZE); hdr = buf_msg(skb); skb_copy_to_linear_data(skb, _hdr, MIN_H_SIZE); msg_set_hdr_sz(hdr, MIN_H_SIZE); msg_set_size(hdr, MIN_H_SIZE); __skb_queue_tail(txq, skb); total += 1; } hdr = buf_msg(skb); curr = msg_blocks(hdr); mlen = msg_size(hdr); cpy = min_t(size_t, rem, mss - mlen); if (cpy != copy_from_iter(skb->data + mlen, cpy, &m->msg_iter)) return -EFAULT; msg_set_size(hdr, mlen + cpy); skb_put(skb, cpy); rem -= cpy; total += msg_blocks(hdr) - curr; } while (rem > 0); return total - accounted; } /* tipc_msg_validate - validate basic format of received message * * This routine ensures a TIPC message has an acceptable header, and at least * as much data as the header indicates it should. The routine also ensures * that the entire message header is stored in the main fragment of the message * buffer, to simplify future access to message header fields. * * Note: Having extra info present in the message header or data areas is OK. * TIPC will ignore the excess, under the assumption that it is optional info * introduced by a later release of the protocol. */ bool tipc_msg_validate(struct sk_buff **_skb) { struct sk_buff *skb = *_skb; struct tipc_msg *hdr; int msz, hsz; /* Ensure that flow control ratio condition is satisfied */ if (unlikely(skb->truesize / buf_roundup_len(skb) >= 4)) { skb = skb_copy_expand(skb, BUF_HEADROOM, 0, GFP_ATOMIC); if (!skb) return false; kfree_skb(*_skb); *_skb = skb; } if (unlikely(TIPC_SKB_CB(skb)->validated)) return true; if (unlikely(!pskb_may_pull(skb, MIN_H_SIZE))) return false; hsz = msg_hdr_sz(buf_msg(skb)); if (unlikely(hsz < MIN_H_SIZE) || (hsz > MAX_H_SIZE)) return false; if (unlikely(!pskb_may_pull(skb, hsz))) return false; hdr = buf_msg(skb); if (unlikely(msg_version(hdr) != TIPC_VERSION)) return false; msz = msg_size(hdr); if (unlikely(msz < hsz)) return false; if (unlikely((msz - hsz) > TIPC_MAX_USER_MSG_SIZE)) return false; if (unlikely(skb->len < msz)) return false; TIPC_SKB_CB(skb)->validated = 1; return true; } /** * tipc_msg_fragment - build a fragment skb list for TIPC message * * @skb: TIPC message skb * @hdr: internal msg header to be put on the top of the fragments * @pktmax: max size of a fragment incl. the header * @frags: returned fragment skb list * * Return: 0 if the fragmentation is successful, otherwise: -EINVAL * or -ENOMEM */ int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr, int pktmax, struct sk_buff_head *frags) { int pktno, nof_fragms, dsz, dmax, eat; struct tipc_msg *_hdr; struct sk_buff *_skb; u8 *data; /* Non-linear buffer? */ if (skb_linearize(skb)) return -ENOMEM; data = (u8 *)skb->data; dsz = msg_size(buf_msg(skb)); dmax = pktmax - INT_H_SIZE; if (dsz <= dmax || !dmax) return -EINVAL; nof_fragms = dsz / dmax + 1; for (pktno = 1; pktno <= nof_fragms; pktno++) { if (pktno < nof_fragms) eat = dmax; else eat = dsz % dmax; /* Allocate a new fragment */ _skb = tipc_buf_acquire(INT_H_SIZE + eat, GFP_ATOMIC); if (!_skb) goto error; skb_orphan(_skb); __skb_queue_tail(frags, _skb); /* Copy header & data to the fragment */ skb_copy_to_linear_data(_skb, hdr, INT_H_SIZE); skb_copy_to_linear_data_offset(_skb, INT_H_SIZE, data, eat); data += eat; /* Update the fragment's header */ _hdr = buf_msg(_skb); msg_set_fragm_no(_hdr, pktno); msg_set_nof_fragms(_hdr, nof_fragms); msg_set_size(_hdr, INT_H_SIZE + eat); } return 0; error: __skb_queue_purge(frags); __skb_queue_head_init(frags); return -ENOMEM; } /** * tipc_msg_build - create buffer chain containing specified header and data * @mhdr: Message header, to be prepended to data * @m: User message * @offset: buffer offset for fragmented messages (FIXME) * @dsz: Total length of user data * @pktmax: Max packet size that can be used * @list: Buffer or chain of buffers to be returned to caller * * Note that the recursive call we are making here is safe, since it can * logically go only one further level down. * * Return: message data size or errno: -ENOMEM, -EFAULT */ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int pktmax, struct sk_buff_head *list) { int mhsz = msg_hdr_sz(mhdr); struct tipc_msg pkthdr; int msz = mhsz + dsz; int pktrem = pktmax; struct sk_buff *skb; int drem = dsz; int pktno = 1; char *pktpos; int pktsz; int rc; msg_set_size(mhdr, msz); /* No fragmentation needed? */ if (likely(msz <= pktmax)) { skb = tipc_buf_acquire(msz, GFP_KERNEL); /* Fall back to smaller MTU if node local message */ if (unlikely(!skb)) { if (pktmax != MAX_MSG_SIZE) return -ENOMEM; rc = tipc_msg_build(mhdr, m, offset, dsz, one_page_mtu, list); if (rc != dsz) return rc; if (tipc_msg_assemble(list)) return dsz; return -ENOMEM; } skb_orphan(skb); __skb_queue_tail(list, skb); skb_copy_to_linear_data(skb, mhdr, mhsz); pktpos = skb->data + mhsz; if (copy_from_iter_full(pktpos, dsz, &m->msg_iter)) return dsz; rc = -EFAULT; goto error; } /* Prepare reusable fragment header */ tipc_msg_init(msg_prevnode(mhdr), &pkthdr, MSG_FRAGMENTER, FIRST_FRAGMENT, INT_H_SIZE, msg_destnode(mhdr)); msg_set_size(&pkthdr, pktmax); msg_set_fragm_no(&pkthdr, pktno); msg_set_importance(&pkthdr, msg_importance(mhdr)); /* Prepare first fragment */ skb = tipc_buf_acquire(pktmax, GFP_KERNEL); if (!skb) return -ENOMEM; skb_orphan(skb); __skb_queue_tail(list, skb); pktpos = skb->data; skb_copy_to_linear_data(skb, &pkthdr, INT_H_SIZE); pktpos += INT_H_SIZE; pktrem -= INT_H_SIZE; skb_copy_to_linear_data_offset(skb, INT_H_SIZE, mhdr, mhsz); pktpos += mhsz; pktrem -= mhsz; do { if (drem < pktrem) pktrem = drem; if (!copy_from_iter_full(pktpos, pktrem, &m->msg_iter)) { rc = -EFAULT; goto error; } drem -= pktrem; if (!drem) break; /* Prepare new fragment: */ if (drem < (pktmax - INT_H_SIZE)) pktsz = drem + INT_H_SIZE; else pktsz = pktmax; skb = tipc_buf_acquire(pktsz, GFP_KERNEL); if (!skb) { rc = -ENOMEM; goto error; } skb_orphan(skb); __skb_queue_tail(list, skb); msg_set_type(&pkthdr, FRAGMENT); msg_set_size(&pkthdr, pktsz); msg_set_fragm_no(&pkthdr, ++pktno); skb_copy_to_linear_data(skb, &pkthdr, INT_H_SIZE); pktpos = skb->data + INT_H_SIZE; pktrem = pktsz - INT_H_SIZE; } while (1); msg_set_type(buf_msg(skb), LAST_FRAGMENT); return dsz; error: __skb_queue_purge(list); __skb_queue_head_init(list); return rc; } /** * tipc_msg_bundle - Append contents of a buffer to tail of an existing one * @bskb: the bundle buffer to append to * @msg: message to be appended * @max: max allowable size for the bundle buffer * * Return: "true" if bundling has been performed, otherwise "false" */ static bool tipc_msg_bundle(struct sk_buff *bskb, struct tipc_msg *msg, u32 max) { struct tipc_msg *bmsg = buf_msg(bskb); u32 msz, bsz, offset, pad; msz = msg_size(msg); bsz = msg_size(bmsg); offset = BUF_ALIGN(bsz); pad = offset - bsz; if (unlikely(skb_tailroom(bskb) < (pad + msz))) return false; if (unlikely(max < (offset + msz))) return false; skb_put(bskb, pad + msz); skb_copy_to_linear_data_offset(bskb, offset, msg, msz); msg_set_size(bmsg, offset + msz); msg_set_msgcnt(bmsg, msg_msgcnt(bmsg) + 1); return true; } /** * tipc_msg_try_bundle - Try to bundle a new message to the last one * @tskb: the last/target message to which the new one will be appended * @skb: the new message skb pointer * @mss: max message size (header inclusive) * @dnode: destination node for the message * @new_bundle: if this call made a new bundle or not * * Return: "true" if the new message skb is potential for bundling this time or * later, in the case a bundling has been done this time, the skb is consumed * (the skb pointer = NULL). * Otherwise, "false" if the skb cannot be bundled at all. */ bool tipc_msg_try_bundle(struct sk_buff *tskb, struct sk_buff **skb, u32 mss, u32 dnode, bool *new_bundle) { struct tipc_msg *msg, *inner, *outer; u32 tsz; /* First, check if the new buffer is suitable for bundling */ msg = buf_msg(*skb); if (msg_user(msg) == MSG_FRAGMENTER) return false; if (msg_user(msg) == TUNNEL_PROTOCOL) return false; if (msg_user(msg) == BCAST_PROTOCOL) return false; if (mss <= INT_H_SIZE + msg_size(msg)) return false; /* Ok, but the last/target buffer can be empty? */ if (unlikely(!tskb)) return true; /* Is it a bundle already? Try to bundle the new message to it */ if (msg_user(buf_msg(tskb)) == MSG_BUNDLER) { *new_bundle = false; goto bundle; } /* Make a new bundle of the two messages if possible */ tsz = msg_size(buf_msg(tskb)); if (unlikely(mss < BUF_ALIGN(INT_H_SIZE + tsz) + msg_size(msg))) return true; if (unlikely(pskb_expand_head(tskb, INT_H_SIZE, mss - tsz - INT_H_SIZE, GFP_ATOMIC))) return true; inner = buf_msg(tskb); skb_push(tskb, INT_H_SIZE); outer = buf_msg(tskb); tipc_msg_init(msg_prevnode(inner), outer, MSG_BUNDLER, 0, INT_H_SIZE, dnode); msg_set_importance(outer, msg_importance(inner)); msg_set_size(outer, INT_H_SIZE + tsz); msg_set_msgcnt(outer, 1); *new_bundle = true; bundle: if (likely(tipc_msg_bundle(tskb, msg, mss))) { consume_skb(*skb); *skb = NULL; } return true; } /** * tipc_msg_extract(): extract bundled inner packet from buffer * @skb: buffer to be extracted from. * @iskb: extracted inner buffer, to be returned * @pos: position in outer message of msg to be extracted. * Returns position of next msg. * Consumes outer buffer when last packet extracted * Return: true when there is an extracted buffer, otherwise false */ bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos) { struct tipc_msg *hdr, *ihdr; int imsz; *iskb = NULL; if (unlikely(skb_linearize(skb))) goto none; hdr = buf_msg(skb); if (unlikely(*pos > (msg_data_sz(hdr) - MIN_H_SIZE))) goto none; ihdr = (struct tipc_msg *)(msg_data(hdr) + *pos); imsz = msg_size(ihdr); if ((*pos + imsz) > msg_data_sz(hdr)) goto none; *iskb = tipc_buf_acquire(imsz, GFP_ATOMIC); if (!*iskb) goto none; skb_copy_to_linear_data(*iskb, ihdr, imsz); if (unlikely(!tipc_msg_validate(iskb))) goto none; *pos += BUF_ALIGN(imsz); return true; none: kfree_skb(skb); kfree_skb(*iskb); *iskb = NULL; return false; } /** * tipc_msg_reverse(): swap source and destination addresses and add error code * @own_node: originating node id for reversed message * @skb: buffer containing message to be reversed; will be consumed * @err: error code to be set in message, if any * Replaces consumed buffer with new one when successful * Return: true if success, otherwise false */ bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err) { struct sk_buff *_skb = *skb; struct tipc_msg *_hdr, *hdr; int hlen, dlen; if (skb_linearize(_skb)) goto exit; _hdr = buf_msg(_skb); dlen = min_t(uint, msg_data_sz(_hdr), MAX_FORWARD_SIZE); hlen = msg_hdr_sz(_hdr); if (msg_dest_droppable(_hdr)) goto exit; if (msg_errcode(_hdr)) goto exit; /* Never return SHORT header */ if (hlen == SHORT_H_SIZE) hlen = BASIC_H_SIZE; /* Don't return data along with SYN+, - sender has a clone */ if (msg_is_syn(_hdr) && err == TIPC_ERR_OVERLOAD) dlen = 0; /* Allocate new buffer to return */ *skb = tipc_buf_acquire(hlen + dlen, GFP_ATOMIC); if (!*skb) goto exit; memcpy((*skb)->data, _skb->data, msg_hdr_sz(_hdr)); memcpy((*skb)->data + hlen, msg_data(_hdr), dlen); /* Build reverse header in new buffer */ hdr = buf_msg(*skb); msg_set_hdr_sz(hdr, hlen); msg_set_errcode(hdr, err); msg_set_non_seq(hdr, 0); msg_set_origport(hdr, msg_destport(_hdr)); msg_set_destport(hdr, msg_origport(_hdr)); msg_set_destnode(hdr, msg_prevnode(_hdr)); msg_set_prevnode(hdr, own_node); msg_set_orignode(hdr, own_node); msg_set_size(hdr, hlen + dlen); skb_orphan(_skb); kfree_skb(_skb); return true; exit: kfree_skb(_skb); *skb = NULL; return false; } bool tipc_msg_skb_clone(struct sk_buff_head *msg, struct sk_buff_head *cpy) { struct sk_buff *skb, *_skb; skb_queue_walk(msg, skb) { _skb = skb_clone(skb, GFP_ATOMIC); if (!_skb) { __skb_queue_purge(cpy); pr_err_ratelimited("Failed to clone buffer chain\n"); return false; } __skb_queue_tail(cpy, _skb); } return true; } /** * tipc_msg_lookup_dest(): try to find new destination for named message * @net: pointer to associated network namespace * @skb: the buffer containing the message. * @err: error code to be used by caller if lookup fails * Does not consume buffer * Return: true if a destination is found, false otherwise */ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) { struct tipc_msg *msg = buf_msg(skb); u32 scope = msg_lookup_scope(msg); u32 self = tipc_own_addr(net); u32 inst = msg_nameinst(msg); struct tipc_socket_addr sk; struct tipc_uaddr ua; if (!msg_isdata(msg)) return false; if (!msg_named(msg)) return false; if (msg_errcode(msg)) return false; *err = TIPC_ERR_NO_NAME; if (skb_linearize(skb)) return false; msg = buf_msg(skb); if (msg_reroute_cnt(msg)) return false; tipc_uaddr(&ua, TIPC_SERVICE_RANGE, scope, msg_nametype(msg), inst, inst); sk.node = tipc_scope2node(net, scope); if (!tipc_nametbl_lookup_anycast(net, &ua, &sk)) return false; msg_incr_reroute_cnt(msg); if (sk.node != self) msg_set_prevnode(msg, self); msg_set_destnode(msg, sk.node); msg_set_destport(msg, sk.ref); *err = TIPC_OK; return true; } /* tipc_msg_assemble() - assemble chain of fragments into one message */ bool tipc_msg_assemble(struct sk_buff_head *list) { struct sk_buff *skb, *tmp = NULL; if (skb_queue_len(list) == 1) return true; while ((skb = __skb_dequeue(list))) { skb->next = NULL; if (tipc_buf_append(&tmp, &skb)) { __skb_queue_tail(list, skb); return true; } if (!tmp) break; } __skb_queue_purge(list); __skb_queue_head_init(list); pr_warn("Failed do assemble buffer\n"); return false; } /* tipc_msg_reassemble() - clone a buffer chain of fragments and * reassemble the clones into one message */ bool tipc_msg_reassemble(struct sk_buff_head *list, struct sk_buff_head *rcvq) { struct sk_buff *skb, *_skb; struct sk_buff *frag = NULL; struct sk_buff *head = NULL; int hdr_len; /* Copy header if single buffer */ if (skb_queue_len(list) == 1) { skb = skb_peek(list); hdr_len = skb_headroom(skb) + msg_hdr_sz(buf_msg(skb)); _skb = __pskb_copy(skb, hdr_len, GFP_ATOMIC); if (!_skb) return false; __skb_queue_tail(rcvq, _skb); return true; } /* Clone all fragments and reassemble */ skb_queue_walk(list, skb) { frag = skb_clone(skb, GFP_ATOMIC); if (!frag) goto error; frag->next = NULL; if (tipc_buf_append(&head, &frag)) break; if (!head) goto error; } __skb_queue_tail(rcvq, frag); return true; error: pr_warn("Failed do clone local mcast rcv buffer\n"); kfree_skb(head); return false; } bool tipc_msg_pskb_copy(u32 dst, struct sk_buff_head *msg, struct sk_buff_head *cpy) { struct sk_buff *skb, *_skb; skb_queue_walk(msg, skb) { _skb = pskb_copy(skb, GFP_ATOMIC); if (!_skb) { __skb_queue_purge(cpy); return false; } msg_set_destnode(buf_msg(_skb), dst); __skb_queue_tail(cpy, _skb); } return true; } /* tipc_skb_queue_sorted(); sort pkt into list according to sequence number * @list: list to be appended to * @seqno: sequence number of buffer to add * @skb: buffer to add */ bool __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno, struct sk_buff *skb) { struct sk_buff *_skb, *tmp; if (skb_queue_empty(list) || less(seqno, buf_seqno(skb_peek(list)))) { __skb_queue_head(list, skb); return true; } if (more(seqno, buf_seqno(skb_peek_tail(list)))) { __skb_queue_tail(list, skb); return true; } skb_queue_walk_safe(list, _skb, tmp) { if (more(seqno, buf_seqno(_skb))) continue; if (seqno == buf_seqno(_skb)) break; __skb_queue_before(list, _skb, skb); return true; } kfree_skb(skb); return false; } void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb, struct sk_buff_head *xmitq) { if (tipc_msg_reverse(tipc_own_addr(net), &skb, err)) __skb_queue_tail(xmitq, skb); } |
| 280 1998 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAP_H #define _LINUX_SWAP_H #include <linux/spinlock.h> #include <linux/linkage.h> #include <linux/mmzone.h> #include <linux/list.h> #include <linux/memcontrol.h> #include <linux/sched.h> #include <linux/node.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/page-flags.h> #include <uapi/linux/mempolicy.h> #include <asm/page.h> struct notifier_block; struct bio; struct pagevec; #define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */ #define SWAP_FLAG_PRIO_MASK 0x7fff #define SWAP_FLAG_PRIO_SHIFT 0 #define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */ #define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */ #define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */ #define SWAP_FLAGS_VALID (SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \ SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \ SWAP_FLAG_DISCARD_PAGES) #define SWAP_BATCH 64 static inline int current_is_kswapd(void) { return current->flags & PF_KSWAPD; } /* * MAX_SWAPFILES defines the maximum number of swaptypes: things which can * be swapped to. The swap type and the offset into that swap type are * encoded into pte's and into pgoff_t's in the swapcache. Using five bits * for the type means that the maximum number of swapcache pages is 27 bits * on 32-bit-pgoff_t architectures. And that assumes that the architecture packs * the type/offset into the pte as 5/27 as well. */ #define MAX_SWAPFILES_SHIFT 5 /* * Use some of the swap files numbers for other purposes. This * is a convenient way to hook into the VM to trigger special * actions on faults. */ #define SWP_SWAPIN_ERROR_NUM 1 #define SWP_SWAPIN_ERROR (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ SWP_MIGRATION_NUM + SWP_DEVICE_NUM + \ SWP_PTE_MARKER_NUM) /* * PTE markers are used to persist information onto PTEs that are mapped with * file-backed memories. As its name "PTE" hints, it should only be applied to * the leaves of pgtables. */ #ifdef CONFIG_PTE_MARKER #define SWP_PTE_MARKER_NUM 1 #define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ SWP_MIGRATION_NUM + SWP_DEVICE_NUM) #else #define SWP_PTE_MARKER_NUM 0 #endif /* * Unaddressable device memory support. See include/linux/hmm.h and * Documentation/mm/hmm.rst. Short description is we need struct pages for * device memory that is unaddressable (inaccessible) by CPU, so that we can * migrate part of a process memory to device memory. * * When a page is migrated from CPU to device, we set the CPU page table entry * to a special SWP_DEVICE_{READ|WRITE} entry. * * When a page is mapped by the device for exclusive access we set the CPU page * table entries to special SWP_DEVICE_EXCLUSIVE_* entries. */ #ifdef CONFIG_DEVICE_PRIVATE #define SWP_DEVICE_NUM 4 #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) #define SWP_DEVICE_EXCLUSIVE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2) #define SWP_DEVICE_EXCLUSIVE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+3) #else #define SWP_DEVICE_NUM 0 #endif /* * Page migration support. * * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and * indicates that the referenced (part of) an anonymous page is exclusive to * a single process. For SWP_MIGRATION_WRITE, that information is implicit: * (part of) an anonymous page that are mapped writable are exclusive to a * single process. */ #ifdef CONFIG_MIGRATION #define SWP_MIGRATION_NUM 3 #define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) #define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) #define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2) #else #define SWP_MIGRATION_NUM 0 #endif /* * Handling of hardware poisoned pages with memory corruption. */ #ifdef CONFIG_MEMORY_FAILURE #define SWP_HWPOISON_NUM 1 #define SWP_HWPOISON MAX_SWAPFILES #else #define SWP_HWPOISON_NUM 0 #endif #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \ SWP_PTE_MARKER_NUM - SWP_SWAPIN_ERROR_NUM) /* * Magic header for a swap area. The first part of the union is * what the swap magic looks like for the old (limited to 128MB) * swap area format, the second part of the union adds - in the * old reserved area - some extra information. Note that the first * kilobyte is reserved for boot loader or disk label stuff... * * Having the magic at the end of the PAGE_SIZE makes detecting swap * areas somewhat tricky on machines that support multiple page sizes. * For 2.5 we'll probably want to move the magic to just beyond the * bootbits... */ union swap_header { struct { char reserved[PAGE_SIZE - 10]; char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */ } magic; struct { char bootbits[1024]; /* Space for disklabel etc. */ __u32 version; __u32 last_page; __u32 nr_badpages; unsigned char sws_uuid[16]; unsigned char sws_volume[16]; __u32 padding[117]; __u32 badpages[1]; } info; }; /* * current->reclaim_state points to one of these when a task is running * memory reclaim */ struct reclaim_state { unsigned long reclaimed_slab; #ifdef CONFIG_LRU_GEN /* per-thread mm walk data */ struct lru_gen_mm_walk *mm_walk; #endif }; #ifdef __KERNEL__ struct address_space; struct sysinfo; struct writeback_control; struct zone; /* * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of * disk blocks. A rbtree of swap extents maps the entire swapfile (Where the * term `swapfile' refers to either a blockdevice or an IS_REG file). Apart * from setup, they're handled identically. * * We always assume that blocks are of size PAGE_SIZE. */ struct swap_extent { struct rb_node rb_node; pgoff_t start_page; pgoff_t nr_pages; sector_t start_block; }; /* * Max bad pages in the new format.. */ #define MAX_SWAP_BADPAGES \ ((offsetof(union swap_header, magic.magic) - \ offsetof(union swap_header, info.badpages)) / sizeof(int)) enum { SWP_USED = (1 << 0), /* is slot in swap_info[] used? */ SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */ SWP_DISCARDABLE = (1 << 2), /* blkdev support discard */ SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */ SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ SWP_FS_OPS = (1 << 8), /* swapfile operations go through fs */ SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ SWP_SCANNING = (1 << 14), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* Bit flag in swap_map */ #define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */ #define COUNT_CONTINUED 0x80 /* Flag swap_map continuation for full count */ /* Special value in first swap_map */ #define SWAP_MAP_MAX 0x3e /* Max count */ #define SWAP_MAP_BAD 0x3f /* Note page is bad */ #define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */ /* Special value in each swap_map continuation */ #define SWAP_CONT_MAX 0x7f /* Max count */ /* * We use this to track usage of a cluster. A cluster is a block of swap disk * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All * free clusters are organized into a list. We fetch an entry from the list to * get a free cluster. * * The data field stores next cluster if the cluster is free or cluster usage * counter otherwise. The flags field determines if a cluster is free. This is * protected by swap_info_struct.lock. */ struct swap_cluster_info { spinlock_t lock; /* * Protect swap_cluster_info fields * and swap_info_struct->swap_map * elements correspond to the swap * cluster */ unsigned int data:24; unsigned int flags:8; }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ #define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */ /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from * its own cluster and swapout sequentially. The purpose is to optimize swapout * throughput. */ struct percpu_cluster { struct swap_cluster_info index; /* Current cluster index */ unsigned int next; /* Likely next allocation offset */ }; struct swap_cluster_list { struct swap_cluster_info head; struct swap_cluster_info tail; }; /* * The in-memory structure used to track swap areas. */ struct swap_info_struct { struct percpu_ref users; /* indicate and keep swap device valid. */ unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ struct swap_cluster_list free_clusters; /* free clusters list */ unsigned int lowest_bit; /* index of first free in swap_map */ unsigned int highest_bit; /* index of last free in swap_map */ unsigned int pages; /* total of usable pages of swap */ unsigned int inuse_pages; /* number of those currently in use */ unsigned int cluster_next; /* likely index for next allocation */ unsigned int cluster_nr; /* countdown to next cluster search */ unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ unsigned int old_block_size; /* seldom referenced */ struct completion comp; /* seldom referenced */ #ifdef CONFIG_FRONTSWAP unsigned long *frontswap_map; /* frontswap in-use, one bit per page */ atomic_t frontswap_pages; /* frontswap pages in-use counter */ #endif spinlock_t lock; /* * protect map scan related fields like * swap_map, lowest_bit, highest_bit, * inuse_pages, cluster_next, * cluster_nr, lowest_alloc, * highest_alloc, free/discard cluster * list. other fields are only changed * at swapon/swapoff, so are protected * by swap_lock. changing flags need * hold this lock and swap_lock. If * both locks need hold, hold swap_lock * first. */ spinlock_t cont_lock; /* * protect swap count continuation page * list. */ struct work_struct discard_work; /* discard worker */ struct swap_cluster_list discard_clusters; /* discard clusters list */ struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one * entry per node. * Must be last as the number of the * array is nr_node_ids, which is not * a fixed value so have to allocate * dynamically. * And it has to be an array so that * plist_for_each_* can work. */ }; #ifdef CONFIG_64BIT #define SWAP_RA_ORDER_CEILING 5 #else /* Avoid stack overflow, because we need to save part of page table */ #define SWAP_RA_ORDER_CEILING 3 #define SWAP_RA_PTE_CACHE_SIZE (1 << SWAP_RA_ORDER_CEILING) #endif struct vma_swap_readahead { unsigned short win; unsigned short offset; unsigned short nr_pte; #ifdef CONFIG_64BIT pte_t *ptes; #else pte_t ptes[SWAP_RA_PTE_CACHE_SIZE]; #endif }; static inline swp_entry_t folio_swap_entry(struct folio *folio) { swp_entry_t entry = { .val = page_private(&folio->page) }; return entry; } static inline void folio_set_swap_entry(struct folio *folio, swp_entry_t entry) { folio->private = (void *)entry.val; } /* linux/mm/workingset.c */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); void workingset_activation(struct folio *folio); /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); extern struct list_lru shadow_nodes; #define mapping_set_update(xas, mapping) do { \ if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \ xas_set_update(xas, workingset_update_node); \ xas_set_lru(xas, &shadow_nodes); \ } \ } while (0) /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) /* linux/mm/swap.c */ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages); void lru_note_cost_folio(struct folio *); void folio_add_lru(struct folio *); void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void lru_cache_add(struct page *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) { return atomic_read(&lru_disable_count); } static inline void lru_cache_enable(void) { atomic_dec(&lru_disable_count); } extern void lru_cache_disable(void); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); extern void deactivate_page(struct page *page); extern void mark_page_lazyfree(struct page *page); extern void swap_setup(void); extern void lru_cache_add_inactive_or_unevictable(struct page *page, struct vm_area_struct *vma); /* linux/mm/vmscan.c */ extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); #define MEMCG_RECLAIM_MAY_SWAP (1 << 1) #define MEMCG_RECLAIM_PROACTIVE (1 << 2) extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, unsigned int reclaim_options); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; long remove_mapping(struct address_space *mapping, struct folio *folio); extern unsigned long reclaim_pages(struct list_head *page_list); #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; extern int sysctl_min_slab_ratio; #else #define node_reclaim_mode 0 #endif static inline bool node_reclaim_enabled(void) { /* Is any node_reclaim_mode bit set? */ return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP); } void check_move_unevictable_folios(struct folio_batch *fbatch); void check_move_unevictable_pages(struct pagevec *pvec); extern void kswapd_run(int nid); extern void kswapd_stop(int nid); #ifdef CONFIG_SWAP int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); static inline unsigned long total_swapcache_pages(void) { return global_node_page_state(NR_SWAPCACHE); } extern void free_swap_cache(struct page *page); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; extern atomic_t nr_rotate_swap; extern bool has_usable_swap(void); /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages; } static inline long get_nr_swap_pages(void) { return atomic_long_read(&nr_swap_pages); } extern void si_swapinfo(struct sysinfo *); swp_entry_t folio_alloc_swap(struct folio *folio); bool folio_free_swap(struct folio *folio); void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t); extern void swap_free(swp_entry_t); extern void swapcache_free_entries(swp_entry_t *entries, int n); extern int free_swap_and_cache(swp_entry_t); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t swapdev_block(int, pgoff_t); extern int __swap_count(swp_entry_t entry); extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern struct swap_info_struct *swp_swap_info(swp_entry_t entry); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); extern void exit_swap_address_space(unsigned int type); extern struct swap_info_struct *get_swap_device(swp_entry_t entry); sector_t swap_page_sector(struct page *page); static inline void put_swap_device(struct swap_info_struct *si) { percpu_ref_put(&si->users); } #else /* CONFIG_SWAP */ static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return NULL; } static inline struct swap_info_struct *get_swap_device(swp_entry_t entry) { return NULL; } static inline void put_swap_device(struct swap_info_struct *si) { } #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL #define vm_swap_full() 0 #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) /* only sparc can not include linux/pagemap.h in this file * so leave put_page and release_pages undeclared... */ #define free_page_and_swap_cache(page) \ put_page(page) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); /* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ #define free_swap_and_cache(e) is_pfn_swap_entry(e) static inline void free_swap_cache(struct page *page) { } static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { return 0; } static inline void swap_shmem_alloc(swp_entry_t swp) { } static inline int swap_duplicate(swp_entry_t swp) { return 0; } static inline void swap_free(swp_entry_t swp) { } static inline void put_swap_folio(struct folio *folio, swp_entry_t swp) { } static inline int __swap_count(swp_entry_t entry) { return 0; } static inline int __swp_swapcount(swp_entry_t entry) { return 0; } static inline int swp_swapcount(swp_entry_t entry) { return 0; } static inline swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; entry.val = 0; return entry; } static inline bool folio_free_swap(struct folio *folio) { return false; } static inline int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { return -EINVAL; } #endif /* CONFIG_SWAP */ #ifdef CONFIG_THP_SWAP extern int split_swap_cluster(swp_entry_t entry); #else static inline int split_swap_cluster(swp_entry_t entry) { return 0; } #endif #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* Cgroup2 doesn't have per-cgroup swappiness */ if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return vm_swappiness; /* root ? */ if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) return vm_swappiness; return memcg->swappiness; } #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { return vm_swappiness; } #endif #ifdef CONFIG_ZSWAP extern u64 zswap_pool_total_size; extern atomic_t zswap_stored_pages; #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) extern void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { if (mem_cgroup_disabled()) return; __cgroup_throttle_swaprate(page, gfp_mask); } #else static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { } #endif static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { cgroup_throttle_swaprate(&folio->page, gfp); } #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { if (mem_cgroup_disabled()) return 0; return __mem_cgroup_try_charge_swap(folio, entry); } extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge_swap(entry, nr_pages); } extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct folio *folio); #else static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { } static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { return 0; } static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { } static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) { return get_nr_swap_pages(); } static inline bool mem_cgroup_swap_full(struct folio *folio) { return vm_swap_full(); } #endif #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Framework and drivers for configuring and reading different PHYs * Based on code in sungem_phy.c and (long-removed) gianfar_phy.c * * Author: Andy Fleming * * Copyright (c) 2004 Freescale Semiconductor, Inc. */ #ifndef __PHY_H #define __PHY_H #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/ethtool.h> #include <linux/linkmode.h> #include <linux/netlink.h> #include <linux/mdio.h> #include <linux/mii.h> #include <linux/mii_timestamper.h> #include <linux/module.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/mod_devicetable.h> #include <linux/u64_stats_sync.h> #include <linux/irqreturn.h> #include <linux/iopoll.h> #include <linux/refcount.h> #include <linux/atomic.h> #define PHY_DEFAULT_FEATURES (SUPPORTED_Autoneg | \ SUPPORTED_TP | \ SUPPORTED_MII) #define PHY_10BT_FEATURES (SUPPORTED_10baseT_Half | \ SUPPORTED_10baseT_Full) #define PHY_100BT_FEATURES (SUPPORTED_100baseT_Half | \ SUPPORTED_100baseT_Full) #define PHY_1000BT_FEATURES (SUPPORTED_1000baseT_Half | \ SUPPORTED_1000baseT_Full) extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; #define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) #define PHY_BASIC_T1_FEATURES ((unsigned long *)&phy_basic_t1_features) #define PHY_GBIT_FEATURES ((unsigned long *)&phy_gbit_features) #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) #define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) #define PHY_10GBIT_FEC_FEATURES ((unsigned long *)&phy_10gbit_fec_features) #define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) extern const int phy_basic_ports_array[3]; extern const int phy_fibre_port_array[1]; extern const int phy_all_ports_features_array[7]; extern const int phy_10_100_features_array[4]; extern const int phy_basic_t1_features_array[3]; extern const int phy_gbit_features_array[2]; extern const int phy_10gbit_features_array[1]; /* * Set phydev->irq to PHY_POLL if interrupts are not supported, * or not desired for this PHY. Set to PHY_MAC_INTERRUPT if * the attached MAC driver handles the interrupt */ #define PHY_POLL -1 #define PHY_MAC_INTERRUPT -2 #define PHY_IS_INTERNAL 0x00000001 #define PHY_RST_AFTER_CLK_EN 0x00000002 #define PHY_POLL_CABLE_TEST 0x00000004 #define MDIO_DEVICE_IS_PHY 0x80000000 /** * enum phy_interface_t - Interface Mode definitions * * @PHY_INTERFACE_MODE_NA: Not Applicable - don't touch * @PHY_INTERFACE_MODE_INTERNAL: No interface, MAC and PHY combined * @PHY_INTERFACE_MODE_MII: Media-independent interface * @PHY_INTERFACE_MODE_GMII: Gigabit media-independent interface * @PHY_INTERFACE_MODE_SGMII: Serial gigabit media-independent interface * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface * @PHY_INTERFACE_MODE_RMII: Reduced Media Independent Interface * @PHY_INTERFACE_MODE_REVRMII: Reduced Media Independent Interface in PHY role * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay * @PHY_INTERFACE_MODE_RGMII_TXID: RGMII with Internal RX delay * @PHY_INTERFACE_MODE_RTBI: Reduced TBI * @PHY_INTERFACE_MODE_SMII: Serial MII * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII * @PHY_INTERFACE_MODE_100BASEX: 100 BaseX * @PHY_INTERFACE_MODE_1000BASEX: 1000 BaseX * @PHY_INTERFACE_MODE_2500BASEX: 2500 BaseX * @PHY_INTERFACE_MODE_5GBASER: 5G BaseR * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR * @PHY_INTERFACE_MODE_25GBASER: 25G BaseR * @PHY_INTERFACE_MODE_USXGMII: Universal Serial 10GE MII * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN * @PHY_INTERFACE_MODE_QUSGMII: Quad Universal SGMII * @PHY_INTERFACE_MODE_1000BASEKX: 1000Base-KX - with Clause 73 AN * @PHY_INTERFACE_MODE_MAX: Book keeping * * Describes the interface between the MAC and PHY. */ typedef enum { PHY_INTERFACE_MODE_NA, PHY_INTERFACE_MODE_INTERNAL, PHY_INTERFACE_MODE_MII, PHY_INTERFACE_MODE_GMII, PHY_INTERFACE_MODE_SGMII, PHY_INTERFACE_MODE_TBI, PHY_INTERFACE_MODE_REVMII, PHY_INTERFACE_MODE_RMII, PHY_INTERFACE_MODE_REVRMII, PHY_INTERFACE_MODE_RGMII, PHY_INTERFACE_MODE_RGMII_ID, PHY_INTERFACE_MODE_RGMII_RXID, PHY_INTERFACE_MODE_RGMII_TXID, PHY_INTERFACE_MODE_RTBI, PHY_INTERFACE_MODE_SMII, PHY_INTERFACE_MODE_XGMII, PHY_INTERFACE_MODE_XLGMII, PHY_INTERFACE_MODE_MOCA, PHY_INTERFACE_MODE_QSGMII, PHY_INTERFACE_MODE_TRGMII, PHY_INTERFACE_MODE_100BASEX, PHY_INTERFACE_MODE_1000BASEX, PHY_INTERFACE_MODE_2500BASEX, PHY_INTERFACE_MODE_5GBASER, PHY_INTERFACE_MODE_RXAUI, PHY_INTERFACE_MODE_XAUI, /* 10GBASE-R, XFI, SFI - single lane 10G Serdes */ PHY_INTERFACE_MODE_10GBASER, PHY_INTERFACE_MODE_25GBASER, PHY_INTERFACE_MODE_USXGMII, /* 10GBASE-KR - with Clause 73 AN */ PHY_INTERFACE_MODE_10GKR, PHY_INTERFACE_MODE_QUSGMII, PHY_INTERFACE_MODE_1000BASEKX, PHY_INTERFACE_MODE_MAX, } phy_interface_t; /* PHY interface mode bitmap handling */ #define DECLARE_PHY_INTERFACE_MASK(name) \ DECLARE_BITMAP(name, PHY_INTERFACE_MODE_MAX) static inline void phy_interface_zero(unsigned long *intf) { bitmap_zero(intf, PHY_INTERFACE_MODE_MAX); } static inline bool phy_interface_empty(const unsigned long *intf) { return bitmap_empty(intf, PHY_INTERFACE_MODE_MAX); } static inline void phy_interface_and(unsigned long *dst, const unsigned long *a, const unsigned long *b) { bitmap_and(dst, a, b, PHY_INTERFACE_MODE_MAX); } static inline void phy_interface_or(unsigned long *dst, const unsigned long *a, const unsigned long *b) { bitmap_or(dst, a, b, PHY_INTERFACE_MODE_MAX); } static inline void phy_interface_set_rgmii(unsigned long *intf) { __set_bit(PHY_INTERFACE_MODE_RGMII, intf); __set_bit(PHY_INTERFACE_MODE_RGMII_ID, intf); __set_bit(PHY_INTERFACE_MODE_RGMII_RXID, intf); __set_bit(PHY_INTERFACE_MODE_RGMII_TXID, intf); } /* * phy_supported_speeds - return all speeds currently supported by a PHY device */ unsigned int phy_supported_speeds(struct phy_device *phy, unsigned int *speeds, unsigned int size); /** * phy_modes - map phy_interface_t enum to device tree binding of phy-mode * @interface: enum phy_interface_t value * * Description: maps enum &phy_interface_t defined in this file * into the device tree binding of 'phy-mode', so that Ethernet * device driver can get PHY interface from device tree. */ static inline const char *phy_modes(phy_interface_t interface) { switch (interface) { case PHY_INTERFACE_MODE_NA: return ""; case PHY_INTERFACE_MODE_INTERNAL: return "internal"; case PHY_INTERFACE_MODE_MII: return "mii"; case PHY_INTERFACE_MODE_GMII: return "gmii"; case PHY_INTERFACE_MODE_SGMII: return "sgmii"; case PHY_INTERFACE_MODE_TBI: return "tbi"; case PHY_INTERFACE_MODE_REVMII: return "rev-mii"; case PHY_INTERFACE_MODE_RMII: return "rmii"; case PHY_INTERFACE_MODE_REVRMII: return "rev-rmii"; case PHY_INTERFACE_MODE_RGMII: return "rgmii"; case PHY_INTERFACE_MODE_RGMII_ID: return "rgmii-id"; case PHY_INTERFACE_MODE_RGMII_RXID: return "rgmii-rxid"; case PHY_INTERFACE_MODE_RGMII_TXID: return "rgmii-txid"; case PHY_INTERFACE_MODE_RTBI: return "rtbi"; case PHY_INTERFACE_MODE_SMII: return "smii"; case PHY_INTERFACE_MODE_XGMII: return "xgmii"; case PHY_INTERFACE_MODE_XLGMII: return "xlgmii"; case PHY_INTERFACE_MODE_MOCA: return "moca"; case PHY_INTERFACE_MODE_QSGMII: return "qsgmii"; case PHY_INTERFACE_MODE_TRGMII: return "trgmii"; case PHY_INTERFACE_MODE_1000BASEX: return "1000base-x"; case PHY_INTERFACE_MODE_1000BASEKX: return "1000base-kx"; case PHY_INTERFACE_MODE_2500BASEX: return "2500base-x"; case PHY_INTERFACE_MODE_5GBASER: return "5gbase-r"; case PHY_INTERFACE_MODE_RXAUI: return "rxaui"; case PHY_INTERFACE_MODE_XAUI: return "xaui"; case PHY_INTERFACE_MODE_10GBASER: return "10gbase-r"; case PHY_INTERFACE_MODE_25GBASER: return "25gbase-r"; case PHY_INTERFACE_MODE_USXGMII: return "usxgmii"; case PHY_INTERFACE_MODE_10GKR: return "10gbase-kr"; case PHY_INTERFACE_MODE_100BASEX: return "100base-x"; case PHY_INTERFACE_MODE_QUSGMII: return "qusgmii"; default: return "unknown"; } } #define PHY_INIT_TIMEOUT 100000 #define PHY_FORCE_TIMEOUT 10 #define PHY_MAX_ADDR 32 /* Used when trying to connect to a specific phy (mii bus id:phy device id) */ #define PHY_ID_FMT "%s:%02x" #define MII_BUS_ID_SIZE 61 struct device; struct phylink; struct sfp_bus; struct sfp_upstream_ops; struct sk_buff; /** * struct mdio_bus_stats - Statistics counters for MDIO busses * @transfers: Total number of transfers, i.e. @writes + @reads * @errors: Number of MDIO transfers that returned an error * @writes: Number of write transfers * @reads: Number of read transfers * @syncp: Synchronisation for incrementing statistics */ struct mdio_bus_stats { u64_stats_t transfers; u64_stats_t errors; u64_stats_t writes; u64_stats_t reads; /* Must be last, add new statistics above */ struct u64_stats_sync syncp; }; /** * struct phy_package_shared - Shared information in PHY packages * @addr: Common PHY address used to combine PHYs in one package * @refcnt: Number of PHYs connected to this shared data * @flags: Initialization of PHY package * @priv_size: Size of the shared private data @priv * @priv: Driver private data shared across a PHY package * * Represents a shared structure between different phydev's in the same * package, for example a quad PHY. See phy_package_join() and * phy_package_leave(). */ struct phy_package_shared { int addr; refcount_t refcnt; unsigned long flags; size_t priv_size; /* private data pointer */ /* note that this pointer is shared between different phydevs and * the user has to take care of appropriate locking. It is allocated * and freed automatically by phy_package_join() and * phy_package_leave(). */ void *priv; }; /* used as bit number in atomic bitops */ #define PHY_SHARED_F_INIT_DONE 0 #define PHY_SHARED_F_PROBE_DONE 1 /** * struct mii_bus - Represents an MDIO bus * * @owner: Who owns this device * @name: User friendly name for this MDIO device, or driver name * @id: Unique identifier for this bus, typical from bus hierarchy * @priv: Driver private data * * The Bus class for PHYs. Devices which provide access to * PHYs should register using this structure */ struct mii_bus { struct module *owner; const char *name; char id[MII_BUS_ID_SIZE]; void *priv; /** @read: Perform a read transfer on the bus */ int (*read)(struct mii_bus *bus, int addr, int regnum); /** @write: Perform a write transfer on the bus */ int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val); /** @reset: Perform a reset of the bus */ int (*reset)(struct mii_bus *bus); /** @stats: Statistic counters per device on the bus */ struct mdio_bus_stats stats[PHY_MAX_ADDR]; /** * @mdio_lock: A lock to ensure that only one thing can read/write * the MDIO bus at a time */ struct mutex mdio_lock; /** @parent: Parent device of this bus */ struct device *parent; /** @state: State of bus structure */ enum { MDIOBUS_ALLOCATED = 1, MDIOBUS_REGISTERED, MDIOBUS_UNREGISTERED, MDIOBUS_RELEASED, } state; /** @dev: Kernel device representation */ struct device dev; /** @mdio_map: list of all MDIO devices on bus */ struct mdio_device *mdio_map[PHY_MAX_ADDR]; /** @phy_mask: PHY addresses to be ignored when probing */ u32 phy_mask; /** @phy_ignore_ta_mask: PHY addresses to ignore the TA/read failure */ u32 phy_ignore_ta_mask; /** * @irq: An array of interrupts, each PHY's interrupt at the index * matching its address */ int irq[PHY_MAX_ADDR]; /** @reset_delay_us: GPIO reset pulse width in microseconds */ int reset_delay_us; /** @reset_post_delay_us: GPIO reset deassert delay in microseconds */ int reset_post_delay_us; /** @reset_gpiod: Reset GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; /** @probe_capabilities: bus capabilities, used for probing */ enum { MDIOBUS_NO_CAP = 0, MDIOBUS_C22, MDIOBUS_C45, MDIOBUS_C22_C45, } probe_capabilities; /** @shared_lock: protect access to the shared element */ struct mutex shared_lock; /** @shared: shared state across different PHYs */ struct phy_package_shared *shared[PHY_MAX_ADDR]; }; #define to_mii_bus(d) container_of(d, struct mii_bus, dev) struct mii_bus *mdiobus_alloc_size(size_t size); /** * mdiobus_alloc - Allocate an MDIO bus structure * * The internal state of the MDIO bus will be set of MDIOBUS_ALLOCATED ready * for the driver to register the bus. */ static inline struct mii_bus *mdiobus_alloc(void) { return mdiobus_alloc_size(0); } int __mdiobus_register(struct mii_bus *bus, struct module *owner); int __devm_mdiobus_register(struct device *dev, struct mii_bus *bus, struct module *owner); #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) #define devm_mdiobus_register(dev, bus) \ __devm_mdiobus_register(dev, bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) { return devm_mdiobus_alloc_size(dev, 0); } struct mii_bus *mdio_find_bus(const char *mdio_name); struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); #define PHY_INTERRUPT_DISABLED false #define PHY_INTERRUPT_ENABLED true /** * enum phy_state - PHY state machine states: * * @PHY_DOWN: PHY device and driver are not ready for anything. probe * should be called if and only if the PHY is in this state, * given that the PHY device exists. * - PHY driver probe function will set the state to @PHY_READY * * @PHY_READY: PHY is ready to send and receive packets, but the * controller is not. By default, PHYs which do not implement * probe will be set to this state by phy_probe(). * - start will set the state to UP * * @PHY_UP: The PHY and attached device are ready to do work. * Interrupts should be started here. * - timer moves to @PHY_NOLINK or @PHY_RUNNING * * @PHY_NOLINK: PHY is up, but not currently plugged in. * - irq or timer will set @PHY_RUNNING if link comes back * - phy_stop moves to @PHY_HALTED * * @PHY_RUNNING: PHY is currently up, running, and possibly sending * and/or receiving packets * - irq or timer will set @PHY_NOLINK if link goes down * - phy_stop moves to @PHY_HALTED * * @PHY_CABLETEST: PHY is performing a cable test. Packet reception/sending * is not expected to work, carrier will be indicated as down. PHY will be * poll once per second, or on interrupt for it current state. * Once complete, move to UP to restart the PHY. * - phy_stop aborts the running test and moves to @PHY_HALTED * * @PHY_HALTED: PHY is up, but no polling or interrupts are done. Or * PHY is in an error state. * - phy_start moves to @PHY_UP */ enum phy_state { PHY_DOWN = 0, PHY_READY, PHY_HALTED, PHY_UP, PHY_RUNNING, PHY_NOLINK, PHY_CABLETEST, }; #define MDIO_MMD_NUM 32 /** * struct phy_c45_device_ids - 802.3-c45 Device Identifiers * @devices_in_package: IEEE 802.3 devices in package register value. * @mmds_present: bit vector of MMDs present. * @device_ids: The device identifer for each present device. */ struct phy_c45_device_ids { u32 devices_in_package; u32 mmds_present; u32 device_ids[MDIO_MMD_NUM]; }; struct macsec_context; struct macsec_ops; /** * struct phy_device - An instance of a PHY * * @mdio: MDIO bus this PHY is on * @drv: Pointer to the driver for this PHY instance * @phy_id: UID for this device found during discovery * @c45_ids: 802.3-c45 Device Identifiers if is_c45. * @is_c45: Set to true if this PHY uses clause 45 addressing. * @is_internal: Set to true if this PHY is internal to a MAC. * @is_pseudo_fixed_link: Set to true if this PHY is an Ethernet switch, etc. * @is_gigabit_capable: Set to true if PHY supports 1000Mbps * @has_fixups: Set to true if this PHY has fixups/quirks. * @suspended: Set to true if this PHY has been suspended successfully. * @suspended_by_mdio_bus: Set to true if this PHY was suspended by MDIO bus. * @sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. * @loopback_enabled: Set true if this PHY has been loopbacked successfully. * @downshifted_rate: Set true if link speed has been downshifted. * @is_on_sfp_module: Set true if PHY is located on an SFP module. * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. * * - Bits [15:0] are free to use by the PHY driver to communicate * driver specific behavior. * - Bits [23:16] are currently reserved for future use. * - Bits [31:24] are reserved for defining generic * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) * @phy_timer: The timer for handling the state machine * @phylink: Pointer to phylink instance for this PHY * @sfp_bus_attached: Flag indicating whether the SFP bus has been attached * @sfp_bus: SFP bus attached to this PHY's fiber port * @attached_dev: The attached enet driver's device instance ptr * @adjust_link: Callback for the enet controller to respond to changes: in the * link state. * @phy_link_change: Callback for phylink for notification of link change * @macsec_ops: MACsec offloading ops. * * @speed: Current link speed * @duplex: Current duplex * @port: Current port * @pause: Current pause * @asym_pause: Current asymmetric pause * @supported: Combined MAC/PHY supported linkmodes * @advertising: Currently advertised linkmodes * @adv_old: Saved advertised while power saving for WoL * @lp_advertising: Current link partner advertised linkmodes * @host_interfaces: PHY interface modes supported by host * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited * @autoneg: Flag autoneg being used * @rate_matching: Current rate matching mode * @link: Current link state * @autoneg_complete: Flag auto negotiation of the link has completed * @mdix: Current crossover * @mdix_ctrl: User setting of crossover * @pma_extable: Cached value of PMA/PMD Extended Abilities Register * @interrupts: Flag interrupts have been enabled * @irq_suspended: Flag indicating PHY is suspended and therefore interrupt * handling shall be postponed until PHY has resumed * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended, * requiring a rerun of the interrupt handler after resume * @interface: enum phy_interface_t value * @skb: Netlink message for cable diagnostics * @nest: Netlink nest used for cable diagnostics * @ehdr: nNtlink header for cable diagnostics * @phy_led_triggers: Array of LED triggers * @phy_num_led_triggers: Number of triggers in @phy_led_triggers * @led_link_trigger: LED trigger for link up/down * @last_triggered: last LED trigger for link speed * @master_slave_set: User requested master/slave configuration * @master_slave_get: Current master/slave advertisement * @master_slave_state: Current master/slave configuration * @mii_ts: Pointer to time stamper callbacks * @psec: Pointer to Power Sourcing Equipment control struct * @lock: Mutex for serialization access to PHY * @state_queue: Work queue for state machine * @shared: Pointer to private data shared by phys in one package * @priv: Pointer to driver private data * * interrupts currently only supports enabled or disabled, * but could be changed in the future to support enabling * and disabling specific interrupts * * Contains some infrastructure for polling and interrupt * handling, as well as handling shifts in PHY hardware state */ struct phy_device { struct mdio_device mdio; /* Information about the PHY type */ /* And management functions */ struct phy_driver *drv; u32 phy_id; struct phy_c45_device_ids c45_ids; unsigned is_c45:1; unsigned is_internal:1; unsigned is_pseudo_fixed_link:1; unsigned is_gigabit_capable:1; unsigned has_fixups:1; unsigned suspended:1; unsigned suspended_by_mdio_bus:1; unsigned sysfs_links:1; unsigned loopback_enabled:1; unsigned downshifted_rate:1; unsigned is_on_sfp_module:1; unsigned mac_managed_pm:1; unsigned autoneg:1; /* The most recently read link state */ unsigned link:1; unsigned autoneg_complete:1; /* Interrupts are enabled */ unsigned interrupts:1; unsigned irq_suspended:1; unsigned irq_rerun:1; int rate_matching; enum phy_state state; u32 dev_flags; phy_interface_t interface; /* * forced speed & duplex (no autoneg) * partner speed & duplex & pause (autoneg) */ int speed; int duplex; int port; int pause; int asym_pause; u8 master_slave_get; u8 master_slave_set; u8 master_slave_state; /* Union of PHY and Attached devices' supported link modes */ /* See ethtool.h for more info */ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); /* used with phy_speed_down */ __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); /* Host supported PHY interface types. Should be ignored if empty. */ DECLARE_PHY_INTERFACE_MASK(host_interfaces); /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; #ifdef CONFIG_LED_TRIGGER_PHY struct phy_led_trigger *phy_led_triggers; unsigned int phy_num_led_triggers; struct phy_led_trigger *last_triggered; struct phy_led_trigger *led_link_trigger; #endif /* * Interrupt number for this PHY * -1 means no interrupt */ int irq; /* private data pointer */ /* For use by PHYs to maintain extra state */ void *priv; /* shared data pointer */ /* For use by PHYs inside the same package that need a shared state. */ struct phy_package_shared *shared; /* Reporting cable test results */ struct sk_buff *skb; void *ehdr; struct nlattr *nest; /* Interrupt and Polling infrastructure */ struct delayed_work state_queue; struct mutex lock; /* This may be modified under the rtnl lock */ bool sfp_bus_attached; struct sfp_bus *sfp_bus; struct phylink *phylink; struct net_device *attached_dev; struct mii_timestamper *mii_ts; struct pse_control *psec; u8 mdix; u8 mdix_ctrl; int pma_extable; void (*phy_link_change)(struct phy_device *phydev, bool up); void (*adjust_link)(struct net_device *dev); #if IS_ENABLED(CONFIG_MACSEC) /* MACsec management functions */ const struct macsec_ops *macsec_ops; #endif }; static inline struct phy_device *to_phy_device(const struct device *dev) { return container_of(to_mdio_device(dev), struct phy_device, mdio); } /** * struct phy_tdr_config - Configuration of a TDR raw test * * @first: Distance for first data collection point * @last: Distance for last data collection point * @step: Step between data collection points * @pair: Bitmap of cable pairs to collect data for * * A structure containing possible configuration parameters * for a TDR cable test. The driver does not need to implement * all the parameters, but should report what is actually used. * All distances are in centimeters. */ struct phy_tdr_config { u32 first; u32 last; u32 step; s8 pair; }; #define PHY_PAIR_ALL -1 /** * struct phy_driver - Driver structure for a particular PHY type * * @mdiodrv: Data common to all MDIO devices * @phy_id: The result of reading the UID registers of this PHY * type, and ANDing them with the phy_id_mask. This driver * only works for PHYs with IDs which match this field * @name: The friendly name of this PHY type * @phy_id_mask: Defines the important bits of the phy_id * @features: A mandatory list of features (speed, duplex, etc) * supported by this PHY * @flags: A bitfield defining certain other features this PHY * supports (like interrupts) * @driver_data: Static driver data * * All functions are optional. If config_aneg or read_status * are not implemented, the phy core uses the genphy versions. * Note that none of these functions should be called from * interrupt time. The goal is for the bus read/write functions * to be able to block when the bus transaction is happening, * and be freed up by an interrupt (The MPC85xx has this ability, * though it is not currently supported in the driver). */ struct phy_driver { struct mdio_driver_common mdiodrv; u32 phy_id; char *name; u32 phy_id_mask; const unsigned long * const features; u32 flags; const void *driver_data; /** * @soft_reset: Called to issue a PHY software reset */ int (*soft_reset)(struct phy_device *phydev); /** * @config_init: Called to initialize the PHY, * including after a reset */ int (*config_init)(struct phy_device *phydev); /** * @probe: Called during discovery. Used to set * up device-specific structures, if any */ int (*probe)(struct phy_device *phydev); /** * @get_features: Probe the hardware to determine what * abilities it has. Should only set phydev->supported. */ int (*get_features)(struct phy_device *phydev); /** * @get_rate_matching: Get the supported type of rate matching for a * particular phy interface. This is used by phy consumers to determine * whether to advertise lower-speed modes for that interface. It is * assumed that if a rate matching mode is supported on an interface, * then that interface's rate can be adapted to all slower link speeds * supported by the phy. If iface is %PHY_INTERFACE_MODE_NA, and the phy * supports any kind of rate matching for any interface, then it must * return that rate matching mode (preferring %RATE_MATCH_PAUSE to * %RATE_MATCH_CRS). If the interface is not supported, this should * return %RATE_MATCH_NONE. */ int (*get_rate_matching)(struct phy_device *phydev, phy_interface_t iface); /* PHY Power Management */ /** @suspend: Suspend the hardware, saving state if needed */ int (*suspend)(struct phy_device *phydev); /** @resume: Resume the hardware, restoring state if needed */ int (*resume)(struct phy_device *phydev); /** * @config_aneg: Configures the advertisement and resets * autonegotiation if phydev->autoneg is on, * forces the speed to the current settings in phydev * if phydev->autoneg is off */ int (*config_aneg)(struct phy_device *phydev); /** @aneg_done: Determines the auto negotiation result */ int (*aneg_done)(struct phy_device *phydev); /** @read_status: Determines the negotiated speed and duplex */ int (*read_status)(struct phy_device *phydev); /** * @config_intr: Enables or disables interrupts. * It should also clear any pending interrupts prior to enabling the * IRQs and after disabling them. */ int (*config_intr)(struct phy_device *phydev); /** @handle_interrupt: Override default interrupt handling */ irqreturn_t (*handle_interrupt)(struct phy_device *phydev); /** @remove: Clears up any memory if needed */ void (*remove)(struct phy_device *phydev); /** * @match_phy_device: Returns true if this is a suitable * driver for the given phydev. If NULL, matching is based on * phy_id and phy_id_mask. */ int (*match_phy_device)(struct phy_device *phydev); /** * @set_wol: Some devices (e.g. qnap TS-119P II) require PHY * register changes to enable Wake on LAN, so set_wol is * provided to be called in the ethernet driver's set_wol * function. */ int (*set_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); /** * @get_wol: See set_wol, but for checking whether Wake on LAN * is enabled. */ void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); /** * @link_change_notify: Called to inform a PHY device driver * when the core is about to change the link state. This * callback is supposed to be used as fixup hook for drivers * that need to take action when the link state * changes. Drivers are by no means allowed to mess with the * PHY device structure in their implementations. */ void (*link_change_notify)(struct phy_device *dev); /** * @read_mmd: PHY specific driver override for reading a MMD * register. This function is optional for PHY specific * drivers. When not provided, the default MMD read function * will be used by phy_read_mmd(), which will use either a * direct read for Clause 45 PHYs or an indirect read for * Clause 22 PHYs. devnum is the MMD device number within the * PHY device, regnum is the register within the selected MMD * device. */ int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum); /** * @write_mmd: PHY specific driver override for writing a MMD * register. This function is optional for PHY specific * drivers. When not provided, the default MMD write function * will be used by phy_write_mmd(), which will use either a * direct write for Clause 45 PHYs, or an indirect write for * Clause 22 PHYs. devnum is the MMD device number within the * PHY device, regnum is the register within the selected MMD * device. val is the value to be written. */ int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum, u16 val); /** @read_page: Return the current PHY register page number */ int (*read_page)(struct phy_device *dev); /** @write_page: Set the current PHY register page number */ int (*write_page)(struct phy_device *dev, int page); /** * @module_info: Get the size and type of the eeprom contained * within a plug-in module */ int (*module_info)(struct phy_device *dev, struct ethtool_modinfo *modinfo); /** * @module_eeprom: Get the eeprom information from the plug-in * module */ int (*module_eeprom)(struct phy_device *dev, struct ethtool_eeprom *ee, u8 *data); /** @cable_test_start: Start a cable test */ int (*cable_test_start)(struct phy_device *dev); /** @cable_test_tdr_start: Start a raw TDR cable test */ int (*cable_test_tdr_start)(struct phy_device *dev, const struct phy_tdr_config *config); /** * @cable_test_get_status: Once per second, or on interrupt, * request the status of the test. */ int (*cable_test_get_status)(struct phy_device *dev, bool *finished); /* Get statistics from the PHY using ethtool */ /** @get_sset_count: Number of statistic counters */ int (*get_sset_count)(struct phy_device *dev); /** @get_strings: Names of the statistic counters */ void (*get_strings)(struct phy_device *dev, u8 *data); /** @get_stats: Return the statistic counter values */ void (*get_stats)(struct phy_device *dev, struct ethtool_stats *stats, u64 *data); /* Get and Set PHY tunables */ /** @get_tunable: Return the value of a tunable */ int (*get_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, void *data); /** @set_tunable: Set the value of a tunable */ int (*set_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, const void *data); /** @set_loopback: Set the loopback mood of the PHY */ int (*set_loopback)(struct phy_device *dev, bool enable); /** @get_sqi: Get the signal quality indication */ int (*get_sqi)(struct phy_device *dev); /** @get_sqi_max: Get the maximum signal quality indication */ int (*get_sqi_max)(struct phy_device *dev); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) #define PHY_ANY_ID "MATCH ANY PHY" #define PHY_ANY_UID 0xffffffff #define PHY_ID_MATCH_EXACT(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 0) #define PHY_ID_MATCH_MODEL(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 4) #define PHY_ID_MATCH_VENDOR(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 10) /* A Structure for boards to register fixups with the PHY Lib */ struct phy_fixup { struct list_head list; char bus_id[MII_BUS_ID_SIZE + 3]; u32 phy_uid; u32 phy_uid_mask; int (*run)(struct phy_device *phydev); }; const char *phy_speed_to_str(int speed); const char *phy_duplex_to_str(unsigned int duplex); const char *phy_rate_matching_to_str(int rate_matching); int phy_interface_num_ports(phy_interface_t interface); /* A structure for mapping a particular speed and duplex * combination to a particular SUPPORTED and ADVERTISED value */ struct phy_setting { u32 speed; u8 duplex; u8 bit; }; const struct phy_setting * phy_lookup_setting(int speed, int duplex, const unsigned long *mask, bool exact); size_t phy_speeds(unsigned int *speeds, size_t size, unsigned long *mask); void of_set_phy_supported(struct phy_device *phydev); void of_set_phy_eee_broken(struct phy_device *phydev); int phy_speed_down_core(struct phy_device *phydev); /** * phy_is_started - Convenience function to check whether PHY is started * @phydev: The phy_device struct */ static inline bool phy_is_started(struct phy_device *phydev) { return phydev->state >= PHY_UP; } void phy_resolve_aneg_pause(struct phy_device *phydev); void phy_resolve_aneg_linkmode(struct phy_device *phydev); void phy_check_downshift(struct phy_device *phydev); /** * phy_read - Convenience function for reading a given PHY register * @phydev: the phy_device struct * @regnum: register number to read * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. */ static inline int phy_read(struct phy_device *phydev, u32 regnum) { return mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, regnum); } #define phy_read_poll_timeout(phydev, regnum, val, cond, sleep_us, \ timeout_us, sleep_before_read) \ ({ \ int __ret = read_poll_timeout(phy_read, val, (cond) || val < 0, \ sleep_us, timeout_us, sleep_before_read, phydev, regnum); \ if (val < 0) \ __ret = val; \ if (__ret) \ phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ __ret; \ }) /** * __phy_read - convenience function for reading a given PHY register * @phydev: the phy_device struct * @regnum: register number to read * * The caller must have taken the MDIO bus lock. */ static inline int __phy_read(struct phy_device *phydev, u32 regnum) { return __mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, regnum); } /** * phy_write - Convenience function for writing a given PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: value to write to @regnum * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. */ static inline int phy_write(struct phy_device *phydev, u32 regnum, u16 val) { return mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val); } /** * __phy_write - Convenience function for writing a given PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: value to write to @regnum * * The caller must have taken the MDIO bus lock. */ static inline int __phy_write(struct phy_device *phydev, u32 regnum, u16 val) { return __mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val); } /** * __phy_modify_changed() - Convenience function for modifying a PHY register * @phydev: a pointer to a &struct phy_device * @regnum: register number * @mask: bit mask of bits to clear * @set: bit mask of bits to set * * Unlocked helper function which allows a PHY register to be modified as * new register value = (old register value & ~mask) | set * * Returns negative errno, 0 if there was no change, and 1 in case of change */ static inline int __phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) { return __mdiobus_modify_changed(phydev->mdio.bus, phydev->mdio.addr, regnum, mask, set); } /* * phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. */ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); /** * phy_read_mmd_poll_timeout - Periodically poll a PHY register until a * condition is met or a timeout occurs * * @phydev: The phy_device struct * @devaddr: The MMD to read from * @regnum: The register on the MMD to read * @val: Variable to read the register into * @cond: Break condition (usually involving @val) * @sleep_us: Maximum time to sleep between reads in us (0 * tight-loops). Should be less than ~20ms since usleep_range * is used (see Documentation/timers/timers-howto.rst). * @timeout_us: Timeout in us, 0 means never timeout * @sleep_before_read: if it is true, sleep @sleep_us before read. * Returns 0 on success and -ETIMEDOUT upon a timeout. In either * case, the last read value at @args is stored in @val. Must not * be called from atomic context if sleep_us or timeout_us are used. */ #define phy_read_mmd_poll_timeout(phydev, devaddr, regnum, val, cond, \ sleep_us, timeout_us, sleep_before_read) \ ({ \ int __ret = read_poll_timeout(phy_read_mmd, val, (cond) || val < 0, \ sleep_us, timeout_us, sleep_before_read, \ phydev, devaddr, regnum); \ if (val < 0) \ __ret = val; \ if (__ret) \ phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ __ret; \ }) /* * __phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. */ int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); /* * phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. */ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); /* * __phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. */ int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); int __phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int __phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int __phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int __phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); /** * __phy_set_bits - Convenience function for setting bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to set * * The caller must have taken the MDIO bus lock. */ static inline int __phy_set_bits(struct phy_device *phydev, u32 regnum, u16 val) { return __phy_modify(phydev, regnum, 0, val); } /** * __phy_clear_bits - Convenience function for clearing bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to clear * * The caller must have taken the MDIO bus lock. */ static inline int __phy_clear_bits(struct phy_device *phydev, u32 regnum, u16 val) { return __phy_modify(phydev, regnum, val, 0); } /** * phy_set_bits - Convenience function for setting bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to set */ static inline int phy_set_bits(struct phy_device *phydev, u32 regnum, u16 val) { return phy_modify(phydev, regnum, 0, val); } /** * phy_clear_bits - Convenience function for clearing bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to clear */ static inline int phy_clear_bits(struct phy_device *phydev, u32 regnum, u16 val) { return phy_modify(phydev, regnum, val, 0); } /** * __phy_set_bits_mmd - Convenience function for setting bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to set * * The caller must have taken the MDIO bus lock. */ static inline int __phy_set_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return __phy_modify_mmd(phydev, devad, regnum, 0, val); } /** * __phy_clear_bits_mmd - Convenience function for clearing bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to clear * * The caller must have taken the MDIO bus lock. */ static inline int __phy_clear_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return __phy_modify_mmd(phydev, devad, regnum, val, 0); } /** * phy_set_bits_mmd - Convenience function for setting bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to set */ static inline int phy_set_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return phy_modify_mmd(phydev, devad, regnum, 0, val); } /** * phy_clear_bits_mmd - Convenience function for clearing bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to clear */ static inline int phy_clear_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return phy_modify_mmd(phydev, devad, regnum, val, 0); } /** * phy_interrupt_is_valid - Convenience function for testing a given PHY irq * @phydev: the phy_device struct * * NOTE: must be kept in sync with addition/removal of PHY_POLL and * PHY_MAC_INTERRUPT */ static inline bool phy_interrupt_is_valid(struct phy_device *phydev) { return phydev->irq != PHY_POLL && phydev->irq != PHY_MAC_INTERRUPT; } /** * phy_polling_mode - Convenience function for testing whether polling is * used to detect PHY status changes * @phydev: the phy_device struct */ static inline bool phy_polling_mode(struct phy_device *phydev) { if (phydev->state == PHY_CABLETEST) if (phydev->drv->flags & PHY_POLL_CABLE_TEST) return true; return phydev->irq == PHY_POLL; } /** * phy_has_hwtstamp - Tests whether a PHY time stamp configuration. * @phydev: the phy_device struct */ static inline bool phy_has_hwtstamp(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->hwtstamp; } /** * phy_has_rxtstamp - Tests whether a PHY supports receive time stamping. * @phydev: the phy_device struct */ static inline bool phy_has_rxtstamp(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->rxtstamp; } /** * phy_has_tsinfo - Tests whether a PHY reports time stamping and/or * PTP hardware clock capabilities. * @phydev: the phy_device struct */ static inline bool phy_has_tsinfo(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->ts_info; } /** * phy_has_txtstamp - Tests whether a PHY supports transmit time stamping. * @phydev: the phy_device struct */ static inline bool phy_has_txtstamp(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->txtstamp; } static inline int phy_hwtstamp(struct phy_device *phydev, struct ifreq *ifr) { return phydev->mii_ts->hwtstamp(phydev->mii_ts, ifr); } static inline bool phy_rxtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { return phydev->mii_ts->rxtstamp(phydev->mii_ts, skb, type); } static inline int phy_ts_info(struct phy_device *phydev, struct ethtool_ts_info *tsinfo) { return phydev->mii_ts->ts_info(phydev->mii_ts, tsinfo); } static inline void phy_txtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { phydev->mii_ts->txtstamp(phydev->mii_ts, skb, type); } /** * phy_is_internal - Convenience function for testing if a PHY is internal * @phydev: the phy_device struct */ static inline bool phy_is_internal(struct phy_device *phydev) { return phydev->is_internal; } /** * phy_on_sfp - Convenience function for testing if a PHY is on an SFP module * @phydev: the phy_device struct */ static inline bool phy_on_sfp(struct phy_device *phydev) { return phydev->is_on_sfp_module; } /** * phy_interface_mode_is_rgmii - Convenience function for testing if a * PHY interface mode is RGMII (all variants) * @mode: the &phy_interface_t enum */ static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode) { return mode >= PHY_INTERFACE_MODE_RGMII && mode <= PHY_INTERFACE_MODE_RGMII_TXID; }; /** * phy_interface_mode_is_8023z() - does the PHY interface mode use 802.3z * negotiation * @mode: one of &enum phy_interface_t * * Returns true if the PHY interface mode uses the 16-bit negotiation * word as defined in 802.3z. (See 802.3-2015 37.2.1 Config_Reg encoding) */ static inline bool phy_interface_mode_is_8023z(phy_interface_t mode) { return mode == PHY_INTERFACE_MODE_1000BASEX || mode == PHY_INTERFACE_MODE_2500BASEX; } /** * phy_interface_is_rgmii - Convenience function for testing if a PHY interface * is RGMII (all variants) * @phydev: the phy_device struct */ static inline bool phy_interface_is_rgmii(struct phy_device *phydev) { return phy_interface_mode_is_rgmii(phydev->interface); }; /** * phy_is_pseudo_fixed_link - Convenience function for testing if this * PHY is the CPU port facing side of an Ethernet switch, or similar. * @phydev: the phy_device struct */ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev) { return phydev->is_pseudo_fixed_link; } int phy_save_page(struct phy_device *phydev); int phy_select_page(struct phy_device *phydev, int page); int phy_restore_page(struct phy_device *phydev, int oldpage, int ret); int phy_read_paged(struct phy_device *phydev, int page, u32 regnum); int phy_write_paged(struct phy_device *phydev, int page, u32 regnum, u16 val); int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); struct phy_device *device_phy_find_device(struct device *dev); struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); #else static inline int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id) { return 0; } static inline struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) { return 0; } static inline struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode) { return NULL; } static inline struct phy_device *device_phy_find_device(struct device *dev) { return NULL; } static inline struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode) { return NULL; } static inline struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) { return NULL; } static inline int phy_device_register(struct phy_device *phy) { return 0; } static inline void phy_device_free(struct phy_device *phydev) { } #endif /* CONFIG_PHYLIB */ void phy_device_remove(struct phy_device *phydev); int phy_get_c45_ids(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); void phy_sfp_attach(void *upstream, struct sfp_bus *bus); void phy_sfp_detach(void *upstream, struct sfp_bus *bus); int phy_sfp_probe(struct phy_device *phydev, const struct sfp_upstream_ops *ops); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); struct phy_device *phy_find_first(struct mii_bus *bus); int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, u32 flags, phy_interface_t interface); int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, void (*handler)(struct net_device *), phy_interface_t interface); struct phy_device *phy_connect(struct net_device *dev, const char *bus_id, void (*handler)(struct net_device *), phy_interface_t interface); void phy_disconnect(struct phy_device *phydev); void phy_detach(struct phy_device *phydev); void phy_start(struct phy_device *phydev); void phy_stop(struct phy_device *phydev); int phy_config_aneg(struct phy_device *phydev); int phy_start_aneg(struct phy_device *phydev); int phy_aneg_done(struct phy_device *phydev); int phy_speed_down(struct phy_device *phydev, bool sync); int phy_speed_up(struct phy_device *phydev); int phy_restart_aneg(struct phy_device *phydev); int phy_reset_after_clk_enable(struct phy_device *phydev); #if IS_ENABLED(CONFIG_PHYLIB) int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack); int phy_start_cable_test_tdr(struct phy_device *phydev, struct netlink_ext_ack *extack, const struct phy_tdr_config *config); #else static inline int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); return -EOPNOTSUPP; } static inline int phy_start_cable_test_tdr(struct phy_device *phydev, struct netlink_ext_ack *extack, const struct phy_tdr_config *config) { NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); return -EOPNOTSUPP; } #endif int phy_cable_test_result(struct phy_device *phydev, u8 pair, u16 result); int phy_cable_test_fault_length(struct phy_device *phydev, u8 pair, u16 cm); static inline void phy_device_reset(struct phy_device *phydev, int value) { mdio_device_reset(&phydev->mdio, value); } #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) #define phydev_err_probe(_phydev, err, format, args...) \ dev_err_probe(&_phydev->mdio.dev, err, format, ##args) #define phydev_info(_phydev, format, args...) \ dev_info(&_phydev->mdio.dev, format, ##args) #define phydev_warn(_phydev, format, args...) \ dev_warn(&_phydev->mdio.dev, format, ##args) #define phydev_dbg(_phydev, format, args...) \ dev_dbg(&_phydev->mdio.dev, format, ##args) static inline const char *phydev_name(const struct phy_device *phydev) { return dev_name(&phydev->mdio.dev); } static inline void phy_lock_mdio_bus(struct phy_device *phydev) { mutex_lock(&phydev->mdio.bus->mdio_lock); } static inline void phy_unlock_mdio_bus(struct phy_device *phydev) { mutex_unlock(&phydev->mdio.bus->mdio_lock); } void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) __printf(2, 3); char *phy_attached_info_irq(struct phy_device *phydev) __malloc; void phy_attached_info(struct phy_device *phydev); /* Clause 22 PHY */ int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart); int genphy_config_eee_advert(struct phy_device *phydev); int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); int genphy_read_lpa(struct phy_device *phydev); int genphy_read_status_fixed(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_read_master_slave(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_loopback(struct phy_device *phydev, bool enable); int genphy_soft_reset(struct phy_device *phydev); irqreturn_t genphy_handle_interrupt_no_ack(struct phy_device *phydev); static inline int genphy_config_aneg(struct phy_device *phydev) { return __genphy_config_aneg(phydev, false); } static inline int genphy_no_config_intr(struct phy_device *phydev) { return 0; } int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, u16 regnum); int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, u16 regnum, u16 val); /* Clause 37 */ int genphy_c37_config_aneg(struct phy_device *phydev); int genphy_c37_read_status(struct phy_device *phydev); /* Clause 45 PHY */ int genphy_c45_restart_aneg(struct phy_device *phydev); int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart); int genphy_c45_aneg_done(struct phy_device *phydev); int genphy_c45_read_link(struct phy_device *phydev); int genphy_c45_read_lpa(struct phy_device *phydev); int genphy_c45_read_pma(struct phy_device *phydev); int genphy_c45_pma_setup_forced(struct phy_device *phydev); int genphy_c45_pma_baset1_setup_master_slave(struct phy_device *phydev); int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); int genphy_c45_baset1_read_status(struct phy_device *phydev); int genphy_c45_config_aneg(struct phy_device *phydev); int genphy_c45_loopback(struct phy_device *phydev, bool enable); int genphy_c45_pma_resume(struct phy_device *phydev); int genphy_c45_pma_suspend(struct phy_device *phydev); int genphy_c45_fast_retrain(struct phy_device *phydev, bool enable); /* Generic C45 PHY driver */ extern struct phy_driver genphy_c45_driver; /* The gen10g_* functions are the old Clause 45 stub */ int gen10g_config_aneg(struct phy_device *phydev); static inline int phy_read_status(struct phy_device *phydev) { if (!phydev->drv) return -EIO; if (phydev->drv->read_status) return phydev->drv->read_status(phydev); else return genphy_read_status(phydev); } void phy_driver_unregister(struct phy_driver *drv); void phy_drivers_unregister(struct phy_driver *drv, int n); int phy_driver_register(struct phy_driver *new_driver, struct module *owner); int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_error(struct phy_device *phydev); void phy_state_machine(struct work_struct *work); void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies); void phy_trigger_machine(struct phy_device *phydev); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd); int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd); int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_get_rate_matching(struct phy_device *phydev, phy_interface_t iface); void phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_advertise_supported(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); bool phy_validate_pause(struct phy_device *phydev, struct ethtool_pauseparam *pp); void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause); s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, const int *delay_values, int size, bool is_rx); void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv, bool *tx_pause, bool *rx_pause); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); int phy_register_fixup_for_id(const char *bus_id, int (*run)(struct phy_device *)); int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); int phy_unregister_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask); int phy_unregister_fixup_for_id(const char *bus_id); int phy_unregister_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask); int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); int phy_get_eee_err(struct phy_device *phydev); int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data); int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data); int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); void phy_ethtool_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); int phy_ethtool_get_link_ksettings(struct net_device *ndev, struct ethtool_link_ksettings *cmd); int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); int phy_ethtool_nway_reset(struct net_device *ndev); int phy_package_join(struct phy_device *phydev, int addr, size_t priv_size); void phy_package_leave(struct phy_device *phydev); int devm_phy_package_join(struct device *dev, struct phy_device *phydev, int addr, size_t priv_size); #if IS_ENABLED(CONFIG_PHYLIB) int __init mdio_bus_init(void); void mdio_bus_exit(void); #endif int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); int phy_ethtool_get_stats(struct phy_device *phydev, struct ethtool_stats *stats, u64 *data); static inline int phy_package_read(struct phy_device *phydev, u32 regnum) { struct phy_package_shared *shared = phydev->shared; if (!shared) return -EIO; return mdiobus_read(phydev->mdio.bus, shared->addr, regnum); } static inline int __phy_package_read(struct phy_device *phydev, u32 regnum) { struct phy_package_shared *shared = phydev->shared; if (!shared) return -EIO; return __mdiobus_read(phydev->mdio.bus, shared->addr, regnum); } static inline int phy_package_write(struct phy_device *phydev, u32 regnum, u16 val) { struct phy_package_shared *shared = phydev->shared; if (!shared) return -EIO; return mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val); } static inline int __phy_package_write(struct phy_device *phydev, u32 regnum, u16 val) { struct phy_package_shared *shared = phydev->shared; if (!shared) return -EIO; return __mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val); } static inline bool __phy_package_set_once(struct phy_device *phydev, unsigned int b) { struct phy_package_shared *shared = phydev->shared; if (!shared) return false; return !test_and_set_bit(b, &shared->flags); } static inline bool phy_package_init_once(struct phy_device *phydev) { return __phy_package_set_once(phydev, PHY_SHARED_F_INIT_DONE); } static inline bool phy_package_probe_once(struct phy_device *phydev) { return __phy_package_set_once(phydev, PHY_SHARED_F_PROBE_DONE); } extern struct bus_type mdio_bus_type; struct mdio_board_info { const char *bus_id; char modalias[MDIO_NAME_SIZE]; int mdio_addr; const void *platform_data; }; #if IS_ENABLED(CONFIG_MDIO_DEVICE) int mdiobus_register_board_info(const struct mdio_board_info *info, unsigned int n); #else static inline int mdiobus_register_board_info(const struct mdio_board_info *i, unsigned int n) { return 0; } #endif /** * phy_module_driver() - Helper macro for registering PHY drivers * @__phy_drivers: array of PHY drivers to register * @__count: Numbers of members in array * * Helper macro for PHY drivers which do not do anything special in module * init/exit. Each module may only use this macro once, and calling it * replaces module_init() and module_exit(). */ #define phy_module_driver(__phy_drivers, __count) \ static int __init phy_module_init(void) \ { \ return phy_drivers_register(__phy_drivers, __count, THIS_MODULE); \ } \ module_init(phy_module_init); \ static void __exit phy_module_exit(void) \ { \ phy_drivers_unregister(__phy_drivers, __count); \ } \ module_exit(phy_module_exit) #define module_phy_driver(__phy_drivers) \ phy_module_driver(__phy_drivers, ARRAY_SIZE(__phy_drivers)) bool phy_driver_is_genphy(struct phy_device *phydev); bool phy_driver_is_genphy_10g(struct phy_device *phydev); #endif /* __PHY_H */ |
| 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs */ #ifndef _ASM_X86_STACKTRACE_H #define _ASM_X86_STACKTRACE_H #include <linux/uaccess.h> #include <linux/ptrace.h> #include <asm/cpu_entry_area.h> #include <asm/switch_to.h> enum stack_type { STACK_TYPE_UNKNOWN, STACK_TYPE_TASK, STACK_TYPE_IRQ, STACK_TYPE_SOFTIRQ, STACK_TYPE_ENTRY, STACK_TYPE_EXCEPTION, STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1, }; struct stack_info { enum stack_type type; unsigned long *begin, *end, *next_sp; }; bool in_task_stack(unsigned long *stack, struct task_struct *task, struct stack_info *info); bool in_entry_stack(unsigned long *stack, struct stack_info *info); int get_stack_info(unsigned long *stack, struct task_struct *task, struct stack_info *info, unsigned long *visit_mask); bool get_stack_info_noinstr(unsigned long *stack, struct task_struct *task, struct stack_info *info); static __always_inline bool get_stack_guard_info(unsigned long *stack, struct stack_info *info) { /* make sure it's not in the stack proper */ if (get_stack_info_noinstr(stack, current, info)) return false; /* but if it is in the page below it, we hit a guard */ return get_stack_info_noinstr((void *)stack + PAGE_SIZE, current, info); } const char *stack_type_name(enum stack_type type); static inline bool on_stack(struct stack_info *info, void *addr, size_t len) { void *begin = info->begin; void *end = info->end; return (info->type != STACK_TYPE_UNKNOWN && addr >= begin && addr < end && addr + len > begin && addr + len <= end); } #ifdef CONFIG_X86_32 #define STACKSLOTS_PER_LINE 8 #else #define STACKSLOTS_PER_LINE 4 #endif #ifdef CONFIG_FRAME_POINTER static inline unsigned long * get_frame_pointer(struct task_struct *task, struct pt_regs *regs) { if (regs) return (unsigned long *)regs->bp; if (task == current) return __builtin_frame_address(0); return &((struct inactive_task_frame *)task->thread.sp)->bp; } #else static inline unsigned long * get_frame_pointer(struct task_struct *task, struct pt_regs *regs) { return NULL; } #endif /* CONFIG_FRAME_POINTER */ static inline unsigned long * get_stack_pointer(struct task_struct *task, struct pt_regs *regs) { if (regs) return (unsigned long *)regs->sp; if (task == current) return __builtin_frame_address(0); return (unsigned long *)task->thread.sp; } /* The form of the top of the frame on the stack */ struct stack_frame { struct stack_frame *next_frame; unsigned long return_address; }; struct stack_frame_ia32 { u32 next_frame; u32 return_address; }; void show_opcodes(struct pt_regs *regs, const char *loglvl); void show_ip(struct pt_regs *regs, const char *loglvl); #endif /* _ASM_X86_STACKTRACE_H */ |
| 1634 1634 1634 1634 1634 1634 1634 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 | // SPDX-License-Identifier: GPL-2.0 #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <net/wext.h> #include "dev.h" #define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1) #define get_bucket(x) ((x) >> BUCKET_SPACE) #define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1)) #define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); struct net_device *dev; struct hlist_head *h; unsigned int count = 0, offset = get_offset(*pos); h = &net->dev_index_head[get_bucket(*pos)]; hlist_for_each_entry_rcu(dev, h, index_hlist) { if (++count == offset) return dev; } return NULL; } static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos) { struct net_device *dev; unsigned int bucket; do { dev = dev_from_same_bucket(seq, pos); if (dev) return dev; bucket = get_bucket(*pos) + 1; *pos = set_bucket_offset(bucket, 1); } while (bucket < NETDEV_HASHENTRIES); return NULL; } /* * This is invoked by the /proc filesystem handler to display a device * in detail. */ static void *dev_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; if (get_bucket(*pos) >= NETDEV_HASHENTRIES) return NULL; return dev_from_bucket(seq, pos); } static void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return dev_from_bucket(seq, pos); } static void dev_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", dev->name, stats->rx_bytes, stats->rx_packets, stats->rx_errors, stats->rx_dropped + stats->rx_missed_errors, stats->rx_fifo_errors, stats->rx_length_errors + stats->rx_over_errors + stats->rx_crc_errors + stats->rx_frame_errors, stats->rx_compressed, stats->multicast, stats->tx_bytes, stats->tx_packets, stats->tx_errors, stats->tx_dropped, stats->tx_fifo_errors, stats->collisions, stats->tx_carrier_errors + stats->tx_aborted_errors + stats->tx_window_errors + stats->tx_heartbeat_errors, stats->tx_compressed); } /* * Called from the PROCfs module. This now uses the new arbitrary sized * /proc/net interface to create /proc/net/dev */ static int dev_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "Inter-| Receive " " | Transmit\n" " face |bytes packets errs drop fifo frame " "compressed multicast|bytes packets errs " "drop fifo colls carrier compressed\n"); else dev_seq_printf_stats(seq, v); return 0; } static u32 softnet_backlog_len(struct softnet_data *sd) { return skb_queue_len_lockless(&sd->input_pkt_queue) + skb_queue_len_lockless(&sd->process_queue); } static struct softnet_data *softnet_get_online(loff_t *pos) { struct softnet_data *sd = NULL; while (*pos < nr_cpu_ids) if (cpu_online(*pos)) { sd = &per_cpu(softnet_data, *pos); break; } else ++*pos; return sd; } static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) { return softnet_get_online(pos); } static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return softnet_get_online(pos); } static void softnet_seq_stop(struct seq_file *seq, void *v) { } static int softnet_seq_show(struct seq_file *seq, void *v) { struct softnet_data *sd = v; unsigned int flow_limit_count = 0; #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit *fl; rcu_read_lock(); fl = rcu_dereference(sd->flow_limit); if (fl) flow_limit_count = fl->count; rcu_read_unlock(); #endif /* the index is the CPU id owing this sd. Since offline CPUs are not * displayed, it would be othrwise not trivial for the user-space * mapping the data a specific CPU */ seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", sd->processed, sd->dropped, sd->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ 0, /* was cpu_collision */ sd->received_rps, flow_limit_count, softnet_backlog_len(sd), (int)seq->index); return 0; } static const struct seq_operations dev_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = dev_seq_show, }; static const struct seq_operations softnet_seq_ops = { .start = softnet_seq_start, .next = softnet_seq_next, .stop = softnet_seq_stop, .show = softnet_seq_show, }; static void *ptype_get_idx(struct seq_file *seq, loff_t pos) { struct list_head *ptype_list = NULL; struct packet_type *pt = NULL; struct net_device *dev; loff_t i = 0; int t; for_each_netdev_rcu(seq_file_net(seq), dev) { ptype_list = &dev->ptype_all; list_for_each_entry_rcu(pt, ptype_list, list) { if (i == pos) return pt; ++i; } } list_for_each_entry_rcu(pt, &ptype_all, list) { if (i == pos) return pt; ++i; } for (t = 0; t < PTYPE_HASH_SIZE; t++) { list_for_each_entry_rcu(pt, &ptype_base[t], list) { if (i == pos) return pt; ++i; } } return NULL; } static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return *pos ? ptype_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net_device *dev; struct packet_type *pt; struct list_head *nxt; int hash; ++*pos; if (v == SEQ_START_TOKEN) return ptype_get_idx(seq, 0); pt = v; nxt = pt->list.next; if (pt->dev) { if (nxt != &pt->dev->ptype_all) goto found; dev = pt->dev; for_each_netdev_continue_rcu(seq_file_net(seq), dev) { if (!list_empty(&dev->ptype_all)) { nxt = dev->ptype_all.next; goto found; } } nxt = ptype_all.next; goto ptype_all; } if (pt->type == htons(ETH_P_ALL)) { ptype_all: if (nxt != &ptype_all) goto found; hash = 0; nxt = ptype_base[0].next; } else hash = ntohs(pt->type) & PTYPE_HASH_MASK; while (nxt == &ptype_base[hash]) { if (++hash >= PTYPE_HASH_SIZE) return NULL; nxt = ptype_base[hash].next; } found: return list_entry(nxt, struct packet_type, list); } static void ptype_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ptype_seq_show(struct seq_file *seq, void *v) { struct packet_type *pt = v; if (v == SEQ_START_TOKEN) seq_puts(seq, "Type Device Function\n"); else if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && (!pt->dev || net_eq(dev_net(pt->dev), seq_file_net(seq)))) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else seq_printf(seq, "%04x", ntohs(pt->type)); seq_printf(seq, " %-8s %ps\n", pt->dev ? pt->dev->name : "", pt->func); } return 0; } static const struct seq_operations ptype_seq_ops = { .start = ptype_seq_start, .next = ptype_seq_next, .stop = ptype_seq_stop, .show = ptype_seq_show, }; static int __net_init dev_proc_net_init(struct net *net) { int rc = -ENOMEM; if (!proc_create_net("dev", 0444, net->proc_net, &dev_seq_ops, sizeof(struct seq_net_private))) goto out; if (!proc_create_seq("softnet_stat", 0444, net->proc_net, &softnet_seq_ops)) goto out_dev; if (!proc_create_net("ptype", 0444, net->proc_net, &ptype_seq_ops, sizeof(struct seq_net_private))) goto out_softnet; if (wext_proc_init(net)) goto out_ptype; rc = 0; out: return rc; out_ptype: remove_proc_entry("ptype", net->proc_net); out_softnet: remove_proc_entry("softnet_stat", net->proc_net); out_dev: remove_proc_entry("dev", net->proc_net); goto out; } static void __net_exit dev_proc_net_exit(struct net *net) { wext_proc_exit(net); remove_proc_entry("ptype", net->proc_net); remove_proc_entry("softnet_stat", net->proc_net); remove_proc_entry("dev", net->proc_net); } static struct pernet_operations __net_initdata dev_proc_ops = { .init = dev_proc_net_init, .exit = dev_proc_net_exit, }; static int dev_mc_seq_show(struct seq_file *seq, void *v) { struct netdev_hw_addr *ha; struct net_device *dev = v; if (v == SEQ_START_TOKEN) return 0; netif_addr_lock_bh(dev); netdev_for_each_mc_addr(ha, dev) { seq_printf(seq, "%-4d %-15s %-5d %-5d %*phN\n", dev->ifindex, dev->name, ha->refcount, ha->global_use, (int)dev->addr_len, ha->addr); } netif_addr_unlock_bh(dev); return 0; } static const struct seq_operations dev_mc_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = dev_mc_seq_show, }; static int __net_init dev_mc_net_init(struct net *net) { if (!proc_create_net("dev_mcast", 0, net->proc_net, &dev_mc_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } static void __net_exit dev_mc_net_exit(struct net *net) { remove_proc_entry("dev_mcast", net->proc_net); } static struct pernet_operations __net_initdata dev_mc_net_ops = { .init = dev_mc_net_init, .exit = dev_mc_net_exit, }; int __init dev_proc_init(void) { int ret = register_pernet_subsys(&dev_proc_ops); if (!ret) return register_pernet_subsys(&dev_mc_net_ops); return ret; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_KSTRTOX_H #define _LINUX_KSTRTOX_H #include <linux/compiler.h> #include <linux/types.h> /* Internal, do not use. */ int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); int __must_check _kstrtol(const char *s, unsigned int base, long *res); int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res); int __must_check kstrtoll(const char *s, unsigned int base, long long *res); /** * kstrtoul - convert a string to an unsigned long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign, but not a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoul(). Return code must be checked. */ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) { /* * We want to shortcut function call, but * __builtin_types_compatible_p(unsigned long, unsigned long long) = 0. */ if (sizeof(unsigned long) == sizeof(unsigned long long) && __alignof__(unsigned long) == __alignof__(unsigned long long)) return kstrtoull(s, base, (unsigned long long *)res); else return _kstrtoul(s, base, res); } /** * kstrtol - convert a string to a long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign or a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtol(). Return code must be checked. */ static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) { /* * We want to shortcut function call, but * __builtin_types_compatible_p(long, long long) = 0. */ if (sizeof(long) == sizeof(long long) && __alignof__(long) == __alignof__(long long)) return kstrtoll(s, base, (long long *)res); else return _kstrtol(s, base, res); } int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res); int __must_check kstrtoint(const char *s, unsigned int base, int *res); static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res) { return kstrtoull(s, base, res); } static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res) { return kstrtoll(s, base, res); } static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res) { return kstrtouint(s, base, res); } static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res) { return kstrtoint(s, base, res); } int __must_check kstrtou16(const char *s, unsigned int base, u16 *res); int __must_check kstrtos16(const char *s, unsigned int base, s16 *res); int __must_check kstrtou8(const char *s, unsigned int base, u8 *res); int __must_check kstrtos8(const char *s, unsigned int base, s8 *res); int __must_check kstrtobool(const char *s, bool *res); int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res); int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res); int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res); int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res); int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res); int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res); int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res); int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res); int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res); int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res); int __must_check kstrtobool_from_user(const char __user *s, size_t count, bool *res); static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res) { return kstrtoull_from_user(s, count, base, res); } static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res) { return kstrtoll_from_user(s, count, base, res); } static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res) { return kstrtouint_from_user(s, count, base, res); } static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res) { return kstrtoint_from_user(s, count, base, res); } /* * Use kstrto<foo> instead. * * NOTE: simple_strto<foo> does not check for the range overflow and, * depending on the input, may give interesting results. * * Use these functions if and only if you cannot use kstrto<foo>, because * the conversion ends on the first non-digit character, which may be far * beyond the supported range. It might be useful to parse the strings like * 10x50 or 12:21 without altering original string or temporary buffer in use. * Keep in mind above caveat. */ extern unsigned long simple_strtoul(const char *,char **,unsigned int); extern long simple_strtol(const char *,char **,unsigned int); extern unsigned long long simple_strtoull(const char *,char **,unsigned int); extern long long simple_strtoll(const char *,char **,unsigned int); static inline int strtobool(const char *s, bool *res) { return kstrtobool(s, res); } #endif /* _LINUX_KSTRTOX_H */ |
| 2138 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Virtio PCI driver - common functionality for all device versions * * This module allows virtio devices to be used over a virtual PCI device. * This can be used with QEMU based VMMs like KVM or Xen. * * Copyright IBM Corp. 2007 * Copyright Red Hat, Inc. 2014 * * Authors: * Anthony Liguori <aliguori@us.ibm.com> * Rusty Russell <rusty@rustcorp.com.au> * Michael S. Tsirkin <mst@redhat.com> */ #include "virtio_pci_common.h" static bool force_legacy = false; #if IS_ENABLED(CONFIG_VIRTIO_PCI_LEGACY) module_param(force_legacy, bool, 0444); MODULE_PARM_DESC(force_legacy, "Force legacy mode for transitional virtio 1 devices"); #endif /* wait for pending irq handlers */ void vp_synchronize_vectors(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); int i; if (vp_dev->intx_enabled) synchronize_irq(vp_dev->pci_dev->irq); for (i = 0; i < vp_dev->msix_vectors; ++i) synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i)); } /* the notify function used when creating a virt queue */ bool vp_notify(struct virtqueue *vq) { /* we write the queue's selector into the notification register to * signal the other end */ iowrite16(vq->index, (void __iomem *)vq->priv); return true; } /* Handle a configuration change: Tell driver if it wants to know. */ static irqreturn_t vp_config_changed(int irq, void *opaque) { struct virtio_pci_device *vp_dev = opaque; virtio_config_changed(&vp_dev->vdev); return IRQ_HANDLED; } /* Notify all virtqueues on an interrupt. */ static irqreturn_t vp_vring_interrupt(int irq, void *opaque) { struct virtio_pci_device *vp_dev = opaque; struct virtio_pci_vq_info *info; irqreturn_t ret = IRQ_NONE; unsigned long flags; spin_lock_irqsave(&vp_dev->lock, flags); list_for_each_entry(info, &vp_dev->virtqueues, node) { if (vring_interrupt(irq, info->vq) == IRQ_HANDLED) ret = IRQ_HANDLED; } spin_unlock_irqrestore(&vp_dev->lock, flags); return ret; } /* A small wrapper to also acknowledge the interrupt when it's handled. * I really need an EIO hook for the vring so I can ack the interrupt once we * know that we'll be handling the IRQ but before we invoke the callback since * the callback may notify the host which results in the host attempting to * raise an interrupt that we would then mask once we acknowledged the * interrupt. */ static irqreturn_t vp_interrupt(int irq, void *opaque) { struct virtio_pci_device *vp_dev = opaque; u8 isr; /* reading the ISR has the effect of also clearing it so it's very * important to save off the value. */ isr = ioread8(vp_dev->isr); /* It's definitely not us if the ISR was not high */ if (!isr) return IRQ_NONE; /* Configuration change? Tell driver if it wants to know. */ if (isr & VIRTIO_PCI_ISR_CONFIG) vp_config_changed(irq, opaque); return vp_vring_interrupt(irq, opaque); } static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors, bool per_vq_vectors, struct irq_affinity *desc) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); const char *name = dev_name(&vp_dev->vdev.dev); unsigned int flags = PCI_IRQ_MSIX; unsigned int i, v; int err = -ENOMEM; vp_dev->msix_vectors = nvectors; vp_dev->msix_names = kmalloc_array(nvectors, sizeof(*vp_dev->msix_names), GFP_KERNEL); if (!vp_dev->msix_names) goto error; vp_dev->msix_affinity_masks = kcalloc(nvectors, sizeof(*vp_dev->msix_affinity_masks), GFP_KERNEL); if (!vp_dev->msix_affinity_masks) goto error; for (i = 0; i < nvectors; ++i) if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i], GFP_KERNEL)) goto error; if (desc) { flags |= PCI_IRQ_AFFINITY; desc->pre_vectors++; /* virtio config vector */ } err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors, nvectors, flags, desc); if (err < 0) goto error; vp_dev->msix_enabled = 1; /* Set the vector used for configuration */ v = vp_dev->msix_used_vectors; snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names, "%s-config", name); err = request_irq(pci_irq_vector(vp_dev->pci_dev, v), vp_config_changed, 0, vp_dev->msix_names[v], vp_dev); if (err) goto error; ++vp_dev->msix_used_vectors; v = vp_dev->config_vector(vp_dev, v); /* Verify we had enough resources to assign the vector */ if (v == VIRTIO_MSI_NO_VECTOR) { err = -EBUSY; goto error; } if (!per_vq_vectors) { /* Shared vector for all VQs */ v = vp_dev->msix_used_vectors; snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names, "%s-virtqueues", name); err = request_irq(pci_irq_vector(vp_dev->pci_dev, v), vp_vring_interrupt, 0, vp_dev->msix_names[v], vp_dev); if (err) goto error; ++vp_dev->msix_used_vectors; } return 0; error: return err; } static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int index, void (*callback)(struct virtqueue *vq), const char *name, bool ctx, u16 msix_vec) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL); struct virtqueue *vq; unsigned long flags; /* fill out our structure that represents an active queue */ if (!info) return ERR_PTR(-ENOMEM); vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, ctx, msix_vec); if (IS_ERR(vq)) goto out_info; info->vq = vq; if (callback) { spin_lock_irqsave(&vp_dev->lock, flags); list_add(&info->node, &vp_dev->virtqueues); spin_unlock_irqrestore(&vp_dev->lock, flags); } else { INIT_LIST_HEAD(&info->node); } vp_dev->vqs[index] = info; return vq; out_info: kfree(info); return vq; } static void vp_del_vq(struct virtqueue *vq) { struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index]; unsigned long flags; /* * If it fails during re-enable reset vq. This way we won't rejoin * info->node to the queue. Prevent unexpected irqs. */ if (!vq->reset) { spin_lock_irqsave(&vp_dev->lock, flags); list_del(&info->node); spin_unlock_irqrestore(&vp_dev->lock, flags); } vp_dev->del_vq(info); kfree(info); } /* the config->del_vqs() implementation */ void vp_del_vqs(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); struct virtqueue *vq, *n; int i; list_for_each_entry_safe(vq, n, &vdev->vqs, list) { if (vp_dev->per_vq_vectors) { int v = vp_dev->vqs[vq->index]->msix_vector; if (v != VIRTIO_MSI_NO_VECTOR) { int irq = pci_irq_vector(vp_dev->pci_dev, v); irq_set_affinity_hint(irq, NULL); free_irq(irq, vq); } } vp_del_vq(vq); } vp_dev->per_vq_vectors = false; if (vp_dev->intx_enabled) { free_irq(vp_dev->pci_dev->irq, vp_dev); vp_dev->intx_enabled = 0; } for (i = 0; i < vp_dev->msix_used_vectors; ++i) free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev); if (vp_dev->msix_affinity_masks) { for (i = 0; i < vp_dev->msix_vectors; i++) free_cpumask_var(vp_dev->msix_affinity_masks[i]); } if (vp_dev->msix_enabled) { /* Disable the vector used for configuration */ vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR); pci_free_irq_vectors(vp_dev->pci_dev); vp_dev->msix_enabled = 0; } vp_dev->msix_vectors = 0; vp_dev->msix_used_vectors = 0; kfree(vp_dev->msix_names); vp_dev->msix_names = NULL; kfree(vp_dev->msix_affinity_masks); vp_dev->msix_affinity_masks = NULL; kfree(vp_dev->vqs); vp_dev->vqs = NULL; } static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], const char * const names[], bool per_vq_vectors, const bool *ctx, struct irq_affinity *desc) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); u16 msix_vec; int i, err, nvectors, allocated_vectors, queue_idx = 0; vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); if (!vp_dev->vqs) return -ENOMEM; if (per_vq_vectors) { /* Best option: one for change interrupt, one per vq. */ nvectors = 1; for (i = 0; i < nvqs; ++i) if (names[i] && callbacks[i]) ++nvectors; } else { /* Second best: one for change, shared for all vqs. */ nvectors = 2; } err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors, per_vq_vectors ? desc : NULL); if (err) goto error_find; vp_dev->per_vq_vectors = per_vq_vectors; allocated_vectors = vp_dev->msix_used_vectors; for (i = 0; i < nvqs; ++i) { if (!names[i]) { vqs[i] = NULL; continue; } if (!callbacks[i]) msix_vec = VIRTIO_MSI_NO_VECTOR; else if (vp_dev->per_vq_vectors) msix_vec = allocated_vectors++; else msix_vec = VP_MSIX_VQ_VECTOR; vqs[i] = vp_setup_vq(vdev, queue_idx++, callbacks[i], names[i], ctx ? ctx[i] : false, msix_vec); if (IS_ERR(vqs[i])) { err = PTR_ERR(vqs[i]); goto error_find; } if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR) continue; /* allocate per-vq irq if available and necessary */ snprintf(vp_dev->msix_names[msix_vec], sizeof *vp_dev->msix_names, "%s-%s", dev_name(&vp_dev->vdev.dev), names[i]); err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec), vring_interrupt, 0, vp_dev->msix_names[msix_vec], vqs[i]); if (err) goto error_find; } return 0; error_find: vp_del_vqs(vdev); return err; } static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], const char * const names[], const bool *ctx) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); int i, err, queue_idx = 0; vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); if (!vp_dev->vqs) return -ENOMEM; err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED, dev_name(&vdev->dev), vp_dev); if (err) goto out_del_vqs; vp_dev->intx_enabled = 1; vp_dev->per_vq_vectors = false; for (i = 0; i < nvqs; ++i) { if (!names[i]) { vqs[i] = NULL; continue; } vqs[i] = vp_setup_vq(vdev, queue_idx++, callbacks[i], names[i], ctx ? ctx[i] : false, VIRTIO_MSI_NO_VECTOR); if (IS_ERR(vqs[i])) { err = PTR_ERR(vqs[i]); goto out_del_vqs; } } return 0; out_del_vqs: vp_del_vqs(vdev); return err; } /* the config->find_vqs() implementation */ int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], const char * const names[], const bool *ctx, struct irq_affinity *desc) { int err; /* Try MSI-X with one vector per queue. */ err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true, ctx, desc); if (!err) return 0; /* Fallback: MSI-X with one vector for config, one shared for queues. */ err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false, ctx, desc); if (!err) return 0; /* Is there an interrupt? If not give up. */ if (!(to_vp_device(vdev)->pci_dev->irq)) return err; /* Finally fall back to regular interrupts. */ return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names, ctx); } const char *vp_bus_name(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); return pci_name(vp_dev->pci_dev); } /* Setup the affinity for a virtqueue: * - force the affinity for per vq vector * - OR over all affinities for shared MSI * - ignore the affinity request if we're using INTX */ int vp_set_vq_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask) { struct virtio_device *vdev = vq->vdev; struct virtio_pci_device *vp_dev = to_vp_device(vdev); struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index]; struct cpumask *mask; unsigned int irq; if (!vq->callback) return -EINVAL; if (vp_dev->msix_enabled) { mask = vp_dev->msix_affinity_masks[info->msix_vector]; irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector); if (!cpu_mask) irq_set_affinity_hint(irq, NULL); else { cpumask_copy(mask, cpu_mask); irq_set_affinity_hint(irq, mask); } } return 0; } const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); if (!vp_dev->per_vq_vectors || vp_dev->vqs[index]->msix_vector == VIRTIO_MSI_NO_VECTOR) return NULL; return pci_irq_get_affinity(vp_dev->pci_dev, vp_dev->vqs[index]->msix_vector); } #ifdef CONFIG_PM_SLEEP static int virtio_pci_freeze(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); int ret; ret = virtio_device_freeze(&vp_dev->vdev); if (!ret) pci_disable_device(pci_dev); return ret; } static int virtio_pci_restore(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); int ret; ret = pci_enable_device(pci_dev); if (ret) return ret; pci_set_master(pci_dev); return virtio_device_restore(&vp_dev->vdev); } static const struct dev_pm_ops virtio_pci_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(virtio_pci_freeze, virtio_pci_restore) }; #endif /* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */ static const struct pci_device_id virtio_pci_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_REDHAT_QUMRANET, PCI_ANY_ID) }, { 0 } }; MODULE_DEVICE_TABLE(pci, virtio_pci_id_table); static void virtio_pci_release_dev(struct device *_d) { struct virtio_device *vdev = dev_to_virtio(_d); struct virtio_pci_device *vp_dev = to_vp_device(vdev); /* As struct device is a kobject, it's not safe to * free the memory (including the reference counter itself) * until it's release callback. */ kfree(vp_dev); } static int virtio_pci_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) { struct virtio_pci_device *vp_dev, *reg_dev = NULL; int rc; /* allocate our structure and fill it out */ vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL); if (!vp_dev) return -ENOMEM; pci_set_drvdata(pci_dev, vp_dev); vp_dev->vdev.dev.parent = &pci_dev->dev; vp_dev->vdev.dev.release = virtio_pci_release_dev; vp_dev->pci_dev = pci_dev; INIT_LIST_HEAD(&vp_dev->virtqueues); spin_lock_init(&vp_dev->lock); /* enable the device */ rc = pci_enable_device(pci_dev); if (rc) goto err_enable_device; if (force_legacy) { rc = virtio_pci_legacy_probe(vp_dev); /* Also try modern mode if we can't map BAR0 (no IO space). */ if (rc == -ENODEV || rc == -ENOMEM) rc = virtio_pci_modern_probe(vp_dev); if (rc) goto err_probe; } else { rc = virtio_pci_modern_probe(vp_dev); if (rc == -ENODEV) rc = virtio_pci_legacy_probe(vp_dev); if (rc) goto err_probe; } pci_set_master(pci_dev); vp_dev->is_legacy = vp_dev->ldev.ioaddr ? true : false; rc = register_virtio_device(&vp_dev->vdev); reg_dev = vp_dev; if (rc) goto err_register; return 0; err_register: if (vp_dev->is_legacy) virtio_pci_legacy_remove(vp_dev); else virtio_pci_modern_remove(vp_dev); err_probe: pci_disable_device(pci_dev); err_enable_device: if (reg_dev) put_device(&vp_dev->vdev.dev); else kfree(vp_dev); return rc; } static void virtio_pci_remove(struct pci_dev *pci_dev) { struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); struct device *dev = get_device(&vp_dev->vdev.dev); /* * Device is marked broken on surprise removal so that virtio upper * layers can abort any ongoing operation. */ if (!pci_device_is_present(pci_dev)) virtio_break_device(&vp_dev->vdev); pci_disable_sriov(pci_dev); unregister_virtio_device(&vp_dev->vdev); if (vp_dev->is_legacy) virtio_pci_legacy_remove(vp_dev); else virtio_pci_modern_remove(vp_dev); pci_disable_device(pci_dev); put_device(dev); } static int virtio_pci_sriov_configure(struct pci_dev *pci_dev, int num_vfs) { struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); struct virtio_device *vdev = &vp_dev->vdev; int ret; if (!(vdev->config->get_status(vdev) & VIRTIO_CONFIG_S_DRIVER_OK)) return -EBUSY; if (!__virtio_test_bit(vdev, VIRTIO_F_SR_IOV)) return -EINVAL; if (pci_vfs_assigned(pci_dev)) return -EPERM; if (num_vfs == 0) { pci_disable_sriov(pci_dev); return 0; } ret = pci_enable_sriov(pci_dev, num_vfs); if (ret < 0) return ret; return num_vfs; } static struct pci_driver virtio_pci_driver = { .name = "virtio-pci", .id_table = virtio_pci_id_table, .probe = virtio_pci_probe, .remove = virtio_pci_remove, #ifdef CONFIG_PM_SLEEP .driver.pm = &virtio_pci_pm_ops, #endif .sriov_configure = virtio_pci_sriov_configure, }; module_pci_driver(virtio_pci_driver); MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>"); MODULE_DESCRIPTION("virtio-pci"); MODULE_LICENSE("GPL"); MODULE_VERSION("1"); |
| 7 7 7 4 4 4 2 2 2 5 4 4 3 3 4 3 3 3 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 | // SPDX-License-Identifier: GPL-2.0-only /* * * Author Karsten Keil <kkeil@novell.com> * * Copyright 2008 by Karsten Keil <kkeil@novell.com> */ #include <linux/mISDNif.h> #include <linux/slab.h> #include <linux/export.h> #include "core.h" static u_int *debug; static struct proto mISDN_proto = { .name = "misdn", .owner = THIS_MODULE, .obj_size = sizeof(struct mISDN_sock) }; #define _pms(sk) ((struct mISDN_sock *)sk) static struct mISDN_sock_list data_sockets = { .lock = __RW_LOCK_UNLOCKED(data_sockets.lock) }; static struct mISDN_sock_list base_sockets = { .lock = __RW_LOCK_UNLOCKED(base_sockets.lock) }; #define L2_HEADER_LEN 4 static inline struct sk_buff * _l2_alloc_skb(unsigned int len, gfp_t gfp_mask) { struct sk_buff *skb; skb = alloc_skb(len + L2_HEADER_LEN, gfp_mask); if (likely(skb)) skb_reserve(skb, L2_HEADER_LEN); return skb; } static void mISDN_sock_link(struct mISDN_sock_list *l, struct sock *sk) { write_lock_bh(&l->lock); sk_add_node(sk, &l->head); write_unlock_bh(&l->lock); } static void mISDN_sock_unlink(struct mISDN_sock_list *l, struct sock *sk) { write_lock_bh(&l->lock); sk_del_node_init(sk); write_unlock_bh(&l->lock); } static int mISDN_send(struct mISDNchannel *ch, struct sk_buff *skb) { struct mISDN_sock *msk; int err; msk = container_of(ch, struct mISDN_sock, ch); if (*debug & DEBUG_SOCKET) printk(KERN_DEBUG "%s len %d %p\n", __func__, skb->len, skb); if (msk->sk.sk_state == MISDN_CLOSED) return -EUNATCH; __net_timestamp(skb); err = sock_queue_rcv_skb(&msk->sk, skb); if (err) printk(KERN_WARNING "%s: error %d\n", __func__, err); return err; } static int mISDN_ctrl(struct mISDNchannel *ch, u_int cmd, void *arg) { struct mISDN_sock *msk; msk = container_of(ch, struct mISDN_sock, ch); if (*debug & DEBUG_SOCKET) printk(KERN_DEBUG "%s(%p, %x, %p)\n", __func__, ch, cmd, arg); switch (cmd) { case CLOSE_CHANNEL: msk->sk.sk_state = MISDN_CLOSED; break; } return 0; } static inline void mISDN_sock_cmsg(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { struct __kernel_old_timeval tv; if (_pms(sk)->cmask & MISDN_TIME_STAMP) { skb_get_timestamp(skb, &tv); put_cmsg(msg, SOL_MISDN, MISDN_TIME_STAMP, sizeof(tv), &tv); } } static int mISDN_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sk_buff *skb; struct sock *sk = sock->sk; int copied, err; if (*debug & DEBUG_SOCKET) printk(KERN_DEBUG "%s: len %d, flags %x ch.nr %d, proto %x\n", __func__, (int)len, flags, _pms(sk)->ch.nr, sk->sk_protocol); if (flags & (MSG_OOB)) return -EOPNOTSUPP; if (sk->sk_state == MISDN_CLOSED) return 0; skb = skb_recv_datagram(sk, flags, &err); if (!skb) return err; if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_mISDN *, maddr, msg->msg_name); maddr->family = AF_ISDN; maddr->dev = _pms(sk)->dev->id; if ((sk->sk_protocol == ISDN_P_LAPD_TE) || (sk->sk_protocol == ISDN_P_LAPD_NT)) { maddr->channel = (mISDN_HEAD_ID(skb) >> 16) & 0xff; maddr->tei = (mISDN_HEAD_ID(skb) >> 8) & 0xff; maddr->sapi = mISDN_HEAD_ID(skb) & 0xff; } else { maddr->channel = _pms(sk)->ch.nr; maddr->sapi = _pms(sk)->ch.addr & 0xFF; maddr->tei = (_pms(sk)->ch.addr >> 8) & 0xFF; } msg->msg_namelen = sizeof(*maddr); } copied = skb->len + MISDN_HEADER_LEN; if (len < copied) { if (flags & MSG_PEEK) refcount_dec(&skb->users); else skb_queue_head(&sk->sk_receive_queue, skb); return -ENOSPC; } memcpy(skb_push(skb, MISDN_HEADER_LEN), mISDN_HEAD_P(skb), MISDN_HEADER_LEN); err = skb_copy_datagram_msg(skb, 0, msg, copied); mISDN_sock_cmsg(sk, msg, skb); skb_free_datagram(sk, skb); return err ? : copied; } static int mISDN_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sk_buff *skb; int err = -ENOMEM; if (*debug & DEBUG_SOCKET) printk(KERN_DEBUG "%s: len %d flags %x ch %d proto %x\n", __func__, (int)len, msg->msg_flags, _pms(sk)->ch.nr, sk->sk_protocol); if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_NOSIGNAL | MSG_ERRQUEUE)) return -EINVAL; if (len < MISDN_HEADER_LEN) return -EINVAL; if (sk->sk_state != MISDN_BOUND) return -EBADFD; lock_sock(sk); skb = _l2_alloc_skb(len, GFP_KERNEL); if (!skb) goto done; if (memcpy_from_msg(skb_put(skb, len), msg, len)) { err = -EFAULT; goto done; } memcpy(mISDN_HEAD_P(skb), skb->data, MISDN_HEADER_LEN); skb_pull(skb, MISDN_HEADER_LEN); if (msg->msg_namelen >= sizeof(struct sockaddr_mISDN)) { /* if we have a address, we use it */ DECLARE_SOCKADDR(struct sockaddr_mISDN *, maddr, msg->msg_name); mISDN_HEAD_ID(skb) = maddr->channel; } else { /* use default for L2 messages */ if ((sk->sk_protocol == ISDN_P_LAPD_TE) || (sk->sk_protocol == ISDN_P_LAPD_NT)) mISDN_HEAD_ID(skb) = _pms(sk)->ch.nr; } if (*debug & DEBUG_SOCKET) printk(KERN_DEBUG "%s: ID:%x\n", __func__, mISDN_HEAD_ID(skb)); err = -ENODEV; if (!_pms(sk)->ch.peer) goto done; err = _pms(sk)->ch.recv(_pms(sk)->ch.peer, skb); if (err) goto done; else { skb = NULL; err = len; } done: kfree_skb(skb); release_sock(sk); return err; } static int data_sock_release(struct socket *sock) { struct sock *sk = sock->sk; if (*debug & DEBUG_SOCKET) printk(KERN_DEBUG "%s(%p) sk=%p\n", __func__, sock, sk); if (!sk) return 0; switch (sk->sk_protocol) { case ISDN_P_TE_S0: case ISDN_P_NT_S0: case ISDN_P_TE_E1: case ISDN_P_NT_E1: if (sk->sk_state == MISDN_BOUND) delete_channel(&_pms(sk)->ch); else mISDN_sock_unlink(&data_sockets, sk); break; case ISDN_P_LAPD_TE: case ISDN_P_LAPD_NT: case ISDN_P_B_RAW: case ISDN_P_B_HDLC: case ISDN_P_B_X75SLP: case ISDN_P_B_L2DTMF: case ISDN_P_B_L2DSP: case ISDN_P_B_L2DSPHDLC: delete_channel(&_pms(sk)->ch); mISDN_sock_unlink(&data_sockets, sk); break; } lock_sock(sk); sock_orphan(sk); skb_queue_purge(&sk->sk_receive_queue); release_sock(sk); sock_put(sk); return 0; } static int data_sock_ioctl_bound(struct sock *sk, unsigned int cmd, void __user *p) { struct mISDN_ctrl_req cq; int err = -EINVAL, val[2]; struct mISDNchannel *bchan, *next; lock_sock(sk); if (!_pms(sk)->dev) { err = -ENODEV; goto done; } switch (cmd) { case IMCTRLREQ: if (copy_from_user(&cq, p, sizeof(cq))) { err = -EFAULT; break; } if ((sk->sk_protocol & ~ISDN_P_B_MASK) == ISDN_P_B_START) { list_for_each_entry_safe(bchan, next, &_pms(sk)->dev->bchannels, list) { if (bchan->nr == cq.channel) { err = bchan->ctrl(bchan, CONTROL_CHANNEL, &cq); break; } } } else err = _pms(sk)->dev->D.ctrl(&_pms(sk)->dev->D, CONTROL_CHANNEL, &cq); if (err) break; if (copy_to_user(p, &cq, sizeof(cq))) err = -EFAULT; break; case IMCLEAR_L2: if (sk->sk_protocol != ISDN_P_LAPD_NT) { err = -EINVAL; break; } val[0] = cmd; if (get_user(val[1], (int __user *)p)) { err = -EFAULT; break; } err = _pms(sk)->dev->teimgr->ctrl(_pms(sk)->dev->teimgr, CONTROL_CHANNEL, val); break; case IMHOLD_L1: if (sk->sk_protocol != ISDN_P_LAPD_NT && sk->sk_protocol != ISDN_P_LAPD_TE) { err = -EINVAL; break; } val[0] = cmd; if (get_user(val[1], (int __user *)p)) { err = -EFAULT; break; } err = _pms(sk)->dev->teimgr->ctrl(_pms(sk)->dev->teimgr, CONTROL_CHANNEL, val); break; default: err = -EINVAL; break; } done: release_sock(sk); return err; } static int data_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { int err = 0, id; struct sock *sk = sock->sk; struct mISDNdevice *dev; struct mISDNversion ver; switch (cmd) { case IMGETVERSION: ver.major = MISDN_MAJOR_VERSION; ver.minor = MISDN_MINOR_VERSION; ver.release = MISDN_RELEASE; if (copy_to_user((void __user *)arg, &ver, sizeof(ver))) err = -EFAULT; break; case IMGETCOUNT: id = get_mdevice_count(); if (put_user(id, (int __user *)arg)) err = -EFAULT; break; case IMGETDEVINFO: if (get_user(id, (int __user *)arg)) { err = -EFAULT; break; } dev = get_mdevice(id); if (dev) { struct mISDN_devinfo di; memset(&di, 0, sizeof(di)); di.id = dev->id; di.Dprotocols = dev->Dprotocols; di.Bprotocols = dev->Bprotocols | get_all_Bprotocols(); di.protocol = dev->D.protocol; memcpy(di.channelmap, dev->channelmap, sizeof(di.channelmap)); di.nrbchan = dev->nrbchan; strscpy(di.name, dev_name(&dev->dev), sizeof(di.name)); if (copy_to_user((void __user *)arg, &di, sizeof(di))) err = -EFAULT; } else err = -ENODEV; break; default: if (sk->sk_state == MISDN_BOUND) err = data_sock_ioctl_bound(sk, cmd, (void __user *)arg); else err = -ENOTCONN; } return err; } static int data_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int len) { struct sock *sk = sock->sk; int err = 0, opt = 0; if (*debug & DEBUG_SOCKET) printk(KERN_DEBUG "%s(%p, %d, %x, optval, %d)\n", __func__, sock, level, optname, len); lock_sock(sk); switch (optname) { case MISDN_TIME_STAMP: if (copy_from_sockptr(&opt, optval, sizeof(int))) { err = -EFAULT; break; } if (opt) _pms(sk)->cmask |= MISDN_TIME_STAMP; else _pms(sk)->cmask &= ~MISDN_TIME_STAMP; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int data_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; int len, opt; if (get_user(len, optlen)) return -EFAULT; if (len != sizeof(char)) return -EINVAL; switch (optname) { case MISDN_TIME_STAMP: if (_pms(sk)->cmask & MISDN_TIME_STAMP) opt = 1; else opt = 0; if (put_user(opt, optval)) return -EFAULT; break; default: return -ENOPROTOOPT; } return 0; } static int data_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_mISDN *maddr = (struct sockaddr_mISDN *) addr; struct sock *sk = sock->sk; struct sock *csk; int err = 0; if (*debug & DEBUG_SOCKET) printk(KERN_DEBUG "%s(%p) sk=%p\n", __func__, sock, sk); if (addr_len != sizeof(struct sockaddr_mISDN)) return -EINVAL; if (!maddr || maddr->family != AF_ISDN) return -EINVAL; lock_sock(sk); if (_pms(sk)->dev) { err = -EALREADY; goto done; } _pms(sk)->dev = get_mdevice(maddr->dev); if (!_pms(sk)->dev) { err = -ENODEV; goto done; } if (sk->sk_protocol < ISDN_P_B_START) { read_lock_bh(&data_sockets.lock); sk_for_each(csk, &data_sockets.head) { if (sk == csk) continue; if (_pms(csk)->dev != _pms(sk)->dev) continue; if (csk->sk_protocol >= ISDN_P_B_START) continue; if (IS_ISDN_P_TE(csk->sk_protocol) == IS_ISDN_P_TE(sk->sk_protocol)) continue; read_unlock_bh(&data_sockets.lock); err = -EBUSY; goto done; } read_unlock_bh(&data_sockets.lock); } _pms(sk)->ch.send = mISDN_send; _pms(sk)->ch.ctrl = mISDN_ctrl; switch (sk->sk_protocol) { case ISDN_P_TE_S0: case ISDN_P_NT_S0: case ISDN_P_TE_E1: case ISDN_P_NT_E1: mISDN_sock_unlink(&data_sockets, sk); err = connect_layer1(_pms(sk)->dev, &_pms(sk)->ch, sk->sk_protocol, maddr); if (err) mISDN_sock_link(&data_sockets, sk); break; case ISDN_P_LAPD_TE: case ISDN_P_LAPD_NT: err = create_l2entity(_pms(sk)->dev, &_pms(sk)->ch, sk->sk_protocol, maddr); break; case ISDN_P_B_RAW: case ISDN_P_B_HDLC: case ISDN_P_B_X75SLP: case ISDN_P_B_L2DTMF: case ISDN_P_B_L2DSP: case ISDN_P_B_L2DSPHDLC: err = connect_Bstack(_pms(sk)->dev, &_pms(sk)->ch, sk->sk_protocol, maddr); break; default: err = -EPROTONOSUPPORT; } if (err) goto done; sk->sk_state = MISDN_BOUND; _pms(sk)->ch.protocol = sk->sk_protocol; done: release_sock(sk); return err; } static int data_sock_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sockaddr_mISDN *maddr = (struct sockaddr_mISDN *) addr; struct sock *sk = sock->sk; if (!_pms(sk)->dev) return -EBADFD; lock_sock(sk); maddr->family = AF_ISDN; maddr->dev = _pms(sk)->dev->id; maddr->channel = _pms(sk)->ch.nr; maddr->sapi = _pms(sk)->ch.addr & 0xff; maddr->tei = (_pms(sk)->ch.addr >> 8) & 0xff; release_sock(sk); return sizeof(*maddr); } static const struct proto_ops data_sock_ops = { .family = PF_ISDN, .owner = THIS_MODULE, .release = data_sock_release, .ioctl = data_sock_ioctl, .bind = data_sock_bind, .getname = data_sock_getname, .sendmsg = mISDN_sock_sendmsg, .recvmsg = mISDN_sock_recvmsg, .poll = datagram_poll, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = data_sock_setsockopt, .getsockopt = data_sock_getsockopt, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .mmap = sock_no_mmap }; static int data_sock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; if (sock->type != SOCK_DGRAM) return -ESOCKTNOSUPPORT; sk = sk_alloc(net, PF_ISDN, GFP_KERNEL, &mISDN_proto, kern); if (!sk) return -ENOMEM; sock_init_data(sock, sk); sock->ops = &data_sock_ops; sock->state = SS_UNCONNECTED; sock_reset_flag(sk, SOCK_ZAPPED); sk->sk_protocol = protocol; sk->sk_state = MISDN_OPEN; mISDN_sock_link(&data_sockets, sk); return 0; } static int base_sock_release(struct socket *sock) { struct sock *sk = sock->sk; printk(KERN_DEBUG "%s(%p) sk=%p\n", __func__, sock, sk); if (!sk) return 0; mISDN_sock_unlink(&base_sockets, sk); sock_orphan(sk); sock_put(sk); return 0; } static int base_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { int err = 0, id; struct mISDNdevice *dev; struct mISDNversion ver; switch (cmd) { case IMGETVERSION: ver.major = MISDN_MAJOR_VERSION; ver.minor = MISDN_MINOR_VERSION; ver.release = MISDN_RELEASE; if (copy_to_user((void __user *)arg, &ver, sizeof(ver))) err = -EFAULT; break; case IMGETCOUNT: id = get_mdevice_count(); if (put_user(id, (int __user *)arg)) err = -EFAULT; break; case IMGETDEVINFO: if (get_user(id, (int __user *)arg)) { err = -EFAULT; break; } dev = get_mdevice(id); if (dev) { struct mISDN_devinfo di; memset(&di, 0, sizeof(di)); di.id = dev->id; di.Dprotocols = dev->Dprotocols; di.Bprotocols = dev->Bprotocols | get_all_Bprotocols(); di.protocol = dev->D.protocol; memcpy(di.channelmap, dev->channelmap, sizeof(di.channelmap)); di.nrbchan = dev->nrbchan; strscpy(di.name, dev_name(&dev->dev), sizeof(di.name)); if (copy_to_user((void __user *)arg, &di, sizeof(di))) err = -EFAULT; } else err = -ENODEV; break; case IMSETDEVNAME: { struct mISDN_devrename dn; if (copy_from_user(&dn, (void __user *)arg, sizeof(dn))) { err = -EFAULT; break; } dn.name[sizeof(dn.name) - 1] = '\0'; dev = get_mdevice(dn.id); if (dev) err = device_rename(&dev->dev, dn.name); else err = -ENODEV; } break; default: err = -EINVAL; } return err; } static int base_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_mISDN *maddr = (struct sockaddr_mISDN *) addr; struct sock *sk = sock->sk; int err = 0; if (addr_len < sizeof(struct sockaddr_mISDN)) return -EINVAL; if (!maddr || maddr->family != AF_ISDN) return -EINVAL; lock_sock(sk); if (_pms(sk)->dev) { err = -EALREADY; goto done; } _pms(sk)->dev = get_mdevice(maddr->dev); if (!_pms(sk)->dev) { err = -ENODEV; goto done; } sk->sk_state = MISDN_BOUND; done: release_sock(sk); return err; } static const struct proto_ops base_sock_ops = { .family = PF_ISDN, .owner = THIS_MODULE, .release = base_sock_release, .ioctl = base_sock_ioctl, .bind = base_sock_bind, .getname = sock_no_getname, .sendmsg = sock_no_sendmsg, .recvmsg = sock_no_recvmsg, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .mmap = sock_no_mmap }; static int base_sock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; if (!capable(CAP_NET_RAW)) return -EPERM; sk = sk_alloc(net, PF_ISDN, GFP_KERNEL, &mISDN_proto, kern); if (!sk) return -ENOMEM; sock_init_data(sock, sk); sock->ops = &base_sock_ops; sock->state = SS_UNCONNECTED; sock_reset_flag(sk, SOCK_ZAPPED); sk->sk_protocol = protocol; sk->sk_state = MISDN_OPEN; mISDN_sock_link(&base_sockets, sk); return 0; } static int mISDN_sock_create(struct net *net, struct socket *sock, int proto, int kern) { int err = -EPROTONOSUPPORT; switch (proto) { case ISDN_P_BASE: err = base_sock_create(net, sock, proto, kern); break; case ISDN_P_TE_S0: case ISDN_P_NT_S0: case ISDN_P_TE_E1: case ISDN_P_NT_E1: case ISDN_P_LAPD_TE: case ISDN_P_LAPD_NT: case ISDN_P_B_RAW: case ISDN_P_B_HDLC: case ISDN_P_B_X75SLP: case ISDN_P_B_L2DTMF: case ISDN_P_B_L2DSP: case ISDN_P_B_L2DSPHDLC: err = data_sock_create(net, sock, proto, kern); break; default: return err; } return err; } static const struct net_proto_family mISDN_sock_family_ops = { .owner = THIS_MODULE, .family = PF_ISDN, .create = mISDN_sock_create, }; int misdn_sock_init(u_int *deb) { int err; debug = deb; err = sock_register(&mISDN_sock_family_ops); if (err) printk(KERN_ERR "%s: error(%d)\n", __func__, err); return err; } void misdn_sock_cleanup(void) { sock_unregister(PF_ISDN); } |
| 281 280 45 45 293 293 293 211 211 211 280 280 281 280 280 279 280 281 281 25 281 1659 1575 1659 211 1659 1659 1575 1575 281 281 280 279 280 214 280 280 280 204 199 280 280 2 281 281 281 281 281 281 281 194 281 4 281 281 25 25 25 25 25 25 25 25 273 273 270 112 269 160 270 34 273 160 189 189 189 102 182 182 144 189 189 189 187 189 189 99 93 28 41 189 189 189 189 189 189 188 119 155 99 115 112 112 174 181 189 189 189 189 191 191 191 191 191 142 191 191 191 191 191 191 191 189 189 189 189 184 189 191 187 187 174 191 189 189 189 189 189 189 189 89 189 89 189 167 168 168 168 168 168 168 168 175 168 159 280 281 281 281 281 281 280 281 281 281 281 142 280 147 281 281 281 281 281 281 281 281 280 281 281 191 191 191 189 191 1 1 281 281 281 281 281 280 281 281 281 281 281 281 281 281 281 24 281 281 25 281 113 281 281 281 281 281 281 274 274 281 281 281 281 281 281 281 280 280 274 274 274 273 274 274 272 273 272 147 265 281 281 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Swap reorganised 29.12.95, Stephen Tweedie. * kswapd added: 7.1.96 sct * Removed kswapd_ctl limits, and swap out as many pages as needed * to bring the system back to freepages.high: 2.4.97, Rik van Riel. * Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com). * Multiqueue VM started 5.8.00, Rik van Riel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/module.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/vmpressure.h> #include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> /* for buffer_heads_over_limit */ #include <linux/mm_inline.h> #include <linux/backing-dev.h> #include <linux/rmap.h> #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> #include <linux/rwsem.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/memcontrol.h> #include <linux/migrate.h> #include <linux/delayacct.h> #include <linux/sysctl.h> #include <linux/memory-tiers.h> #include <linux/oom.h> #include <linux/pagevec.h> #include <linux/prefetch.h> #include <linux/printk.h> #include <linux/dax.h> #include <linux/psi.h> #include <linux/pagewalk.h> #include <linux/shmem_fs.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include <linux/swapops.h> #include <linux/balloon_compaction.h> #include <linux/sched/sysctl.h> #include "internal.h" #include "swap.h" #define CREATE_TRACE_POINTS #include <trace/events/vmscan.h> struct scan_control { /* How many pages shrink_list() should reclaim */ unsigned long nr_to_reclaim; /* * Nodemask of nodes allowed by the caller. If NULL, all nodes * are scanned. */ nodemask_t *nodemask; /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. */ struct mem_cgroup *target_mem_cgroup; /* * Scan pressure balancing between anon and file LRUs */ unsigned long anon_cost; unsigned long file_cost; /* Can active folios be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 unsigned int may_deactivate:2; unsigned int force_deactivate:1; unsigned int skipped_deactivate:1; /* Writepage batching in laptop mode; RECLAIM_WRITE */ unsigned int may_writepage:1; /* Can mapped folios be reclaimed? */ unsigned int may_unmap:1; /* Can folios be swapped as part of reclaim? */ unsigned int may_swap:1; /* Proactive reclaim invoked by userspace through memory.reclaim */ unsigned int proactive:1; /* * Cgroup memory below memory.low is protected as long as we * don't threaten to OOM. If any cgroup is reclaimed at * reduced force or passed over entirely due to its memory.low * setting (memcg_low_skipped), and nothing is reclaimed as a * result, then go back for one more cycle that reclaims the protected * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; unsigned int hibernation_mode:1; /* One of the zones is ready for compaction */ unsigned int compaction_ready:1; /* There is easily reclaimable cold cache in the current node */ unsigned int cache_trim_mode:1; /* The file folios on the current node are dangerously low */ unsigned int file_is_tiny:1; /* Always discard instead of demoting to lower tier memory */ unsigned int no_demotion:1; #ifdef CONFIG_LRU_GEN /* help kswapd make better choices among multiple memcgs */ unsigned int memcgs_need_aging:1; unsigned long last_reclaimed; #endif /* Allocation order */ s8 order; /* Scan (total_size >> priority) pages at once */ s8 priority; /* The highest zone to isolate folios for reclaim from */ s8 reclaim_idx; /* This context's GFP mask */ gfp_t gfp_mask; /* Incremented by the number of inactive pages that were scanned */ unsigned long nr_scanned; /* Number of pages freed so far during a call to shrink_zones() */ unsigned long nr_reclaimed; struct { unsigned int dirty; unsigned int unqueued_dirty; unsigned int congested; unsigned int writeback; unsigned int immediate; unsigned int file_taken; unsigned int taken; } nr; /* for recording the reclaimed slab by now */ struct reclaim_state reclaim_state; }; #ifdef ARCH_HAS_PREFETCHW #define prefetchw_prev_lru_folio(_folio, _base, _field) \ do { \ if ((_folio)->lru.prev != _base) { \ struct folio *prev; \ \ prev = lru_to_folio(&(_folio->lru)); \ prefetchw(&prev->_field); \ } \ } while (0) #else #define prefetchw_prev_lru_folio(_folio, _base, _field) do { } while (0) #endif /* * From 0 .. 200. Higher means more swappy. */ int vm_swappiness = 60; static void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs) { /* Check for an overwrite */ WARN_ON_ONCE(rs && task->reclaim_state); /* Check for the nulling of an already-nulled member */ WARN_ON_ONCE(!rs && !task->reclaim_state); task->reclaim_state = rs; } LIST_HEAD(shrinker_list); DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG static int shrinker_nr_max; /* The shrinker_info is expanded in a batch of BITS_PER_LONG */ static inline int shrinker_map_size(int nr_items) { return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long)); } static inline int shrinker_defer_size(int nr_items) { return (round_up(nr_items, BITS_PER_LONG) * sizeof(atomic_long_t)); } static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, int nid) { return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, lockdep_is_held(&shrinker_rwsem)); } static int expand_one_shrinker_info(struct mem_cgroup *memcg, int map_size, int defer_size, int old_map_size, int old_defer_size) { struct shrinker_info *new, *old; struct mem_cgroup_per_node *pn; int nid; int size = map_size + defer_size; for_each_node(nid) { pn = memcg->nodeinfo[nid]; old = shrinker_info_protected(memcg, nid); /* Not yet online memcg */ if (!old) return 0; new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid); if (!new) return -ENOMEM; new->nr_deferred = (atomic_long_t *)(new + 1); new->map = (void *)new->nr_deferred + defer_size; /* map: set all old bits, clear all new bits */ memset(new->map, (int)0xff, old_map_size); memset((void *)new->map + old_map_size, 0, map_size - old_map_size); /* nr_deferred: copy old values, clear all new values */ memcpy(new->nr_deferred, old->nr_deferred, old_defer_size); memset((void *)new->nr_deferred + old_defer_size, 0, defer_size - old_defer_size); rcu_assign_pointer(pn->shrinker_info, new); kvfree_rcu(old, rcu); } return 0; } void free_shrinker_info(struct mem_cgroup *memcg) { struct mem_cgroup_per_node *pn; struct shrinker_info *info; int nid; for_each_node(nid) { pn = memcg->nodeinfo[nid]; info = rcu_dereference_protected(pn->shrinker_info, true); kvfree(info); rcu_assign_pointer(pn->shrinker_info, NULL); } } int alloc_shrinker_info(struct mem_cgroup *memcg) { struct shrinker_info *info; int nid, size, ret = 0; int map_size, defer_size = 0; down_write(&shrinker_rwsem); map_size = shrinker_map_size(shrinker_nr_max); defer_size = shrinker_defer_size(shrinker_nr_max); size = map_size + defer_size; for_each_node(nid) { info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid); if (!info) { free_shrinker_info(memcg); ret = -ENOMEM; break; } info->nr_deferred = (atomic_long_t *)(info + 1); info->map = (void *)info->nr_deferred + defer_size; rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } up_write(&shrinker_rwsem); return ret; } static inline bool need_expand(int nr_max) { return round_up(nr_max, BITS_PER_LONG) > round_up(shrinker_nr_max, BITS_PER_LONG); } static int expand_shrinker_info(int new_id) { int ret = 0; int new_nr_max = new_id + 1; int map_size, defer_size = 0; int old_map_size, old_defer_size = 0; struct mem_cgroup *memcg; if (!need_expand(new_nr_max)) goto out; if (!root_mem_cgroup) goto out; lockdep_assert_held(&shrinker_rwsem); map_size = shrinker_map_size(new_nr_max); defer_size = shrinker_defer_size(new_nr_max); old_map_size = shrinker_map_size(shrinker_nr_max); old_defer_size = shrinker_defer_size(shrinker_nr_max); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { ret = expand_one_shrinker_info(memcg, map_size, defer_size, old_map_size, old_defer_size); if (ret) { mem_cgroup_iter_break(NULL, memcg); goto out; } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); out: if (!ret) shrinker_nr_max = new_nr_max; return ret; } void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { struct shrinker_info *info; rcu_read_lock(); info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); /* Pairs with smp mb in shrink_slab() */ smp_mb__before_atomic(); set_bit(shrinker_id, info->map); rcu_read_unlock(); } } static DEFINE_IDR(shrinker_idr); static int prealloc_memcg_shrinker(struct shrinker *shrinker) { int id, ret = -ENOMEM; if (mem_cgroup_disabled()) return -ENOSYS; down_write(&shrinker_rwsem); /* This may call shrinker, so it must use down_read_trylock() */ id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; if (id >= shrinker_nr_max) { if (expand_shrinker_info(id)) { idr_remove(&shrinker_idr, id); goto unlock; } } shrinker->id = id; ret = 0; unlock: up_write(&shrinker_rwsem); return ret; } static void unregister_memcg_shrinker(struct shrinker *shrinker) { int id = shrinker->id; BUG_ON(id < 0); lockdep_assert_held(&shrinker_rwsem); idr_remove(&shrinker_idr, id); } static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, struct mem_cgroup *memcg) { struct shrinker_info *info; info = shrinker_info_protected(memcg, nid); return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0); } static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, struct mem_cgroup *memcg) { struct shrinker_info *info; info = shrinker_info_protected(memcg, nid); return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]); } void reparent_shrinker_deferred(struct mem_cgroup *memcg) { int i, nid; long nr; struct mem_cgroup *parent; struct shrinker_info *child_info, *parent_info; parent = parent_mem_cgroup(memcg); if (!parent) parent = root_mem_cgroup; /* Prevent from concurrent shrinker_info expand */ down_read(&shrinker_rwsem); for_each_node(nid) { child_info = shrinker_info_protected(memcg, nid); parent_info = shrinker_info_protected(parent, nid); for (i = 0; i < shrinker_nr_max; i++) { nr = atomic_long_read(&child_info->nr_deferred[i]); atomic_long_add(nr, &parent_info->nr_deferred[i]); } } up_read(&shrinker_rwsem); } static bool cgroup_reclaim(struct scan_control *sc) { return sc->target_mem_cgroup; } /** * writeback_throttling_sane - is the usual dirty throttling mechanism available? * @sc: scan_control in question * * The normal page dirty throttling mechanism in balance_dirty_pages() is * completely broken with the legacy memcg and direct stalling in * shrink_folio_list() is used for throttling instead, which lacks all the * niceties such as fairness, adaptive pausing, bandwidth proportional * allocation and configurability. * * This function tests whether the vmscan currently in progress can assume * that the normal dirty throttling mechanism is operational. */ static bool writeback_throttling_sane(struct scan_control *sc) { if (!cgroup_reclaim(sc)) return true; #ifdef CONFIG_CGROUP_WRITEBACK if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return true; #endif return false; } #else static int prealloc_memcg_shrinker(struct shrinker *shrinker) { return -ENOSYS; } static void unregister_memcg_shrinker(struct shrinker *shrinker) { } static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, struct mem_cgroup *memcg) { return 0; } static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, struct mem_cgroup *memcg) { return 0; } static bool cgroup_reclaim(struct scan_control *sc) { return false; } static bool writeback_throttling_sane(struct scan_control *sc) { return true; } #endif static long xchg_nr_deferred(struct shrinker *shrinker, struct shrink_control *sc) { int nid = sc->nid; if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) nid = 0; if (sc->memcg && (shrinker->flags & SHRINKER_MEMCG_AWARE)) return xchg_nr_deferred_memcg(nid, shrinker, sc->memcg); return atomic_long_xchg(&shrinker->nr_deferred[nid], 0); } static long add_nr_deferred(long nr, struct shrinker *shrinker, struct shrink_control *sc) { int nid = sc->nid; if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) nid = 0; if (sc->memcg && (shrinker->flags & SHRINKER_MEMCG_AWARE)) return add_nr_deferred_memcg(nr, nid, shrinker, sc->memcg); return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); } static bool can_demote(int nid, struct scan_control *sc) { if (!numa_demotion_enabled) return false; if (sc && sc->no_demotion) return false; if (next_demotion_node(nid) == NUMA_NO_NODE) return false; return true; } static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, int nid, struct scan_control *sc) { if (memcg == NULL) { /* * For non-memcg reclaim, is there * space in any swap device? */ if (get_nr_swap_pages() > 0) return true; } else { /* Is the memcg below its swap limit? */ if (mem_cgroup_get_nr_swap_pages(memcg) > 0) return true; } /* * The page can not be swapped. * * Can it be reclaimed from this node via demotion? */ return can_demote(nid, sc); } /* * This misses isolated folios which are not accounted for to save counters. * As the data only determines if reclaim or compaction continues, it is * not expected that isolated folios will be a dominating factor. */ unsigned long zone_reclaimable_pages(struct zone *zone) { unsigned long nr; nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); return nr; } /** * lruvec_lru_size - Returns the number of pages on the given LRU list. * @lruvec: lru vector * @lru: lru to use * @zone_idx: zones to consider (use MAX_NR_ZONES - 1 for the whole LRU list) */ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { unsigned long size = 0; int zid; for (zid = 0; zid <= zone_idx; zid++) { struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid]; if (!managed_zone(zone)) continue; if (!mem_cgroup_disabled()) size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); else size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru); } return size; } /* * Add a shrinker callback to be called from the vm. */ static int __prealloc_shrinker(struct shrinker *shrinker) { unsigned int size; int err; if (shrinker->flags & SHRINKER_MEMCG_AWARE) { err = prealloc_memcg_shrinker(shrinker); if (err != -ENOSYS) return err; shrinker->flags &= ~SHRINKER_MEMCG_AWARE; } size = sizeof(*shrinker->nr_deferred); if (shrinker->flags & SHRINKER_NUMA_AWARE) size *= nr_node_ids; shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); if (!shrinker->nr_deferred) return -ENOMEM; return 0; } #ifdef CONFIG_SHRINKER_DEBUG int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) { va_list ap; int err; va_start(ap, fmt); shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); va_end(ap); if (!shrinker->name) return -ENOMEM; err = __prealloc_shrinker(shrinker); if (err) { kfree_const(shrinker->name); shrinker->name = NULL; } return err; } #else int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) { return __prealloc_shrinker(shrinker); } #endif void free_prealloced_shrinker(struct shrinker *shrinker) { #ifdef CONFIG_SHRINKER_DEBUG kfree_const(shrinker->name); shrinker->name = NULL; #endif if (shrinker->flags & SHRINKER_MEMCG_AWARE) { down_write(&shrinker_rwsem); unregister_memcg_shrinker(shrinker); up_write(&shrinker_rwsem); return; } kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; } void register_shrinker_prepared(struct shrinker *shrinker) { down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); shrinker->flags |= SHRINKER_REGISTERED; shrinker_debugfs_add(shrinker); up_write(&shrinker_rwsem); } static int __register_shrinker(struct shrinker *shrinker) { int err = __prealloc_shrinker(shrinker); if (err) return err; register_shrinker_prepared(shrinker); return 0; } #ifdef CONFIG_SHRINKER_DEBUG int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) { va_list ap; int err; va_start(ap, fmt); shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); va_end(ap); if (!shrinker->name) return -ENOMEM; err = __register_shrinker(shrinker); if (err) { kfree_const(shrinker->name); shrinker->name = NULL; } return err; } #else int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) { return __register_shrinker(shrinker); } #endif EXPORT_SYMBOL(register_shrinker); /* * Remove one */ void unregister_shrinker(struct shrinker *shrinker) { if (!(shrinker->flags & SHRINKER_REGISTERED)) return; down_write(&shrinker_rwsem); list_del(&shrinker->list); shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); shrinker_debugfs_remove(shrinker); up_write(&shrinker_rwsem); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; } EXPORT_SYMBOL(unregister_shrinker); /** * synchronize_shrinkers - Wait for all running shrinkers to complete. * * This is equivalent to calling unregister_shrink() and register_shrinker(), * but atomically and with less overhead. This is useful to guarantee that all * shrinker invocations have seen an update, before freeing memory, similar to * rcu. */ void synchronize_shrinkers(void) { down_write(&shrinker_rwsem); up_write(&shrinker_rwsem); } EXPORT_SYMBOL(synchronize_shrinkers); #define SHRINK_BATCH 128 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, struct shrinker *shrinker, int priority) { unsigned long freed = 0; unsigned long long delta; long total_scan; long freeable; long nr; long new_nr; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; long scanned = 0, next_deferred; freeable = shrinker->count_objects(shrinker, shrinkctl); if (freeable == 0 || freeable == SHRINK_EMPTY) return freeable; /* * copy the current shrinker scan count into a local variable * and zero it so that other concurrent shrinker invocations * don't also do this scanning work. */ nr = xchg_nr_deferred(shrinker, shrinkctl); if (shrinker->seeks) { delta = freeable >> priority; delta *= 4; do_div(delta, shrinker->seeks); } else { /* * These objects don't require any IO to create. Trim * them aggressively under memory pressure to keep * them from causing refetches in the IO caches. */ delta = freeable / 2; } total_scan = nr >> priority; total_scan += delta; total_scan = min(total_scan, (2 * freeable)); trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, freeable, delta, total_scan, priority); /* * Normally, we should not scan less than batch_size objects in one * pass to avoid too frequent shrinker calls, but if the slab has less * than batch_size objects in total and we are really tight on memory, * we will try to reclaim all available objects, otherwise we can end * up failing allocations although there are plenty of reclaimable * objects spread over several slabs with usage less than the * batch_size. * * We detect the "tight on memory" situations by looking at the total * number of objects we want to scan (total_scan). If it is greater * than the total number of objects on slab (freeable), we must be * scanning at high prio and therefore should try to reclaim as much as * possible. */ while (total_scan >= batch_size || total_scan >= freeable) { unsigned long ret; unsigned long nr_to_scan = min(batch_size, total_scan); shrinkctl->nr_to_scan = nr_to_scan; shrinkctl->nr_scanned = nr_to_scan; ret = shrinker->scan_objects(shrinker, shrinkctl); if (ret == SHRINK_STOP) break; freed += ret; count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); total_scan -= shrinkctl->nr_scanned; scanned += shrinkctl->nr_scanned; cond_resched(); } /* * The deferred work is increased by any new work (delta) that wasn't * done, decreased by old deferred work that was done now. * * And it is capped to two times of the freeable items. */ next_deferred = max_t(long, (nr + delta - scanned), 0); next_deferred = min(next_deferred, (2 * freeable)); /* * move the unused scan count back into the shrinker in a * manner that handles concurrent updates. */ new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl); trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan); return freed; } #ifdef CONFIG_MEMCG static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { struct shrinker_info *info; unsigned long ret, freed = 0; int i; if (!mem_cgroup_online(memcg)) return 0; if (!down_read_trylock(&shrinker_rwsem)) return 0; info = shrinker_info_protected(memcg, nid); if (unlikely(!info)) goto unlock; for_each_set_bit(i, info->map, shrinker_nr_max) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, .memcg = memcg, }; struct shrinker *shrinker; shrinker = idr_find(&shrinker_idr, i); if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) { if (!shrinker) clear_bit(i, info->map); continue; } /* Call non-slab shrinkers even though kmem is disabled */ if (!memcg_kmem_enabled() && !(shrinker->flags & SHRINKER_NONSLAB)) continue; ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) { clear_bit(i, info->map); /* * After the shrinker reported that it had no objects to * free, but before we cleared the corresponding bit in * the memcg shrinker map, a new object might have been * added. To make sure, we have the bit set in this * case, we invoke the shrinker one more time and reset * the bit if it reports that it is not empty anymore. * The memory barrier here pairs with the barrier in * set_shrinker_bit(): * * list_lru_add() shrink_slab_memcg() * list_add_tail() clear_bit() * <MB> <MB> * set_bit() do_shrink_slab() */ smp_mb__after_atomic(); ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) ret = 0; else set_shrinker_bit(memcg, nid, i); } freed += ret; if (rwsem_is_contended(&shrinker_rwsem)) { freed = freed ? : 1; break; } } unlock: up_read(&shrinker_rwsem); return freed; } #else /* CONFIG_MEMCG */ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { return 0; } #endif /* CONFIG_MEMCG */ /** * shrink_slab - shrink slab caches * @gfp_mask: allocation context * @nid: node whose slab caches to target * @memcg: memory cgroup whose slab caches to target * @priority: the reclaim priority * * Call the shrink functions to age shrinkable caches. * * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, * unaware shrinkers will receive a node id of 0 instead. * * @memcg specifies the memory cgroup to target. Unaware shrinkers * are called only if it is the root cgroup. * * @priority is sc->priority, we take the number of objects and >> by priority * in order to get the scan target. * * Returns the number of reclaimed slab objects. */ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { unsigned long ret, freed = 0; struct shrinker *shrinker; /* * The root memcg might be allocated even though memcg is disabled * via "cgroup_disable=memory" boot parameter. This could make * mem_cgroup_is_root() return false, then just run memcg slab * shrink, but skip global shrink. This may result in premature * oom. */ if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); if (!down_read_trylock(&shrinker_rwsem)) goto out; list_for_each_entry(shrinker, &shrinker_list, list) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, .memcg = memcg, }; ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) ret = 0; freed += ret; /* * Bail out if someone want to register a new shrinker to * prevent the registration from being stalled for long periods * by parallel ongoing shrinking. */ if (rwsem_is_contended(&shrinker_rwsem)) { freed = freed ? : 1; break; } } up_read(&shrinker_rwsem); out: cond_resched(); return freed; } static void drop_slab_node(int nid) { unsigned long freed; int shift = 0; do { struct mem_cgroup *memcg = NULL; if (fatal_signal_pending(current)) return; freed = 0; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); } while ((freed >> shift++) > 1); } void drop_slab(void) { int nid; for_each_online_node(nid) drop_slab_node(nid); } static inline int is_page_cache_freeable(struct folio *folio) { /* * A freeable page cache folio is referenced only by the caller * that isolated the folio, the page cache and optional filesystem * private data at folio->private. */ return folio_ref_count(folio) - folio_test_private(folio) == 1 + folio_nr_pages(folio); } /* * We detected a synchronous write error writing a folio out. Probably * -ENOSPC. We need to propagate that into the address_space for a subsequent * fsync(), msync() or close(). * * The tricky part is that after writepage we cannot touch the mapping: nothing * prevents it from being freed up. But we have a ref on the folio and once * that folio is locked, the mapping is pinned. * * We're allowed to run sleeping folio_lock() here because we know the caller has * __GFP_FS. */ static void handle_write_error(struct address_space *mapping, struct folio *folio, int error) { folio_lock(folio); if (folio_mapping(folio) == mapping) mapping_set_error(mapping, error); folio_unlock(folio); } static bool skip_throttle_noprogress(pg_data_t *pgdat) { int reclaimable = 0, write_pending = 0; int i; /* * If kswapd is disabled, reschedule if necessary but do not * throttle as the system is likely near OOM. */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; /* * If there are a lot of dirty/writeback folios then do not * throttle as throttling will occur when the folios cycle * towards the end of the LRU if still under writeback. */ for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; reclaimable += zone_reclaimable_pages(zone); write_pending += zone_page_state_snapshot(zone, NR_ZONE_WRITE_PENDING); } if (2 * write_pending <= reclaimable) return true; return false; } void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) { wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; long timeout, ret; DEFINE_WAIT(wait); /* * Do not throttle IO workers, kthreads other than kswapd or * workqueues. They may be required for reclaim to make * forward progress (e.g. journalling workqueues or kthreads). */ if (!current_is_kswapd() && current->flags & (PF_IO_WORKER|PF_KTHREAD)) { cond_resched(); return; } /* * These figures are pulled out of thin air. * VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many * parallel reclaimers which is a short-lived event so the timeout is * short. Failing to make progress or waiting on writeback are * potentially long-lived events so use a longer timeout. This is shaky * logic as a failure to make progress could be due to anything from * writeback to a slow device to excessive referenced folios at the tail * of the inactive LRU. */ switch(reason) { case VMSCAN_THROTTLE_WRITEBACK: timeout = HZ/10; if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { WRITE_ONCE(pgdat->nr_reclaim_start, node_page_state(pgdat, NR_THROTTLED_WRITTEN)); } break; case VMSCAN_THROTTLE_CONGESTED: fallthrough; case VMSCAN_THROTTLE_NOPROGRESS: if (skip_throttle_noprogress(pgdat)) { cond_resched(); return; } timeout = 1; break; case VMSCAN_THROTTLE_ISOLATED: timeout = HZ/50; break; default: WARN_ON_ONCE(1); timeout = HZ; break; } prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = schedule_timeout(timeout); finish_wait(wqh, &wait); if (reason == VMSCAN_THROTTLE_WRITEBACK) atomic_dec(&pgdat->nr_writeback_throttled); trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), jiffies_to_usecs(timeout - ret), reason); } /* * Account for folios written if tasks are throttled waiting on dirty * folios to clean. If enough folios have been cleaned since throttling * started then wakeup the throttled tasks. */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled) { unsigned long nr_written; node_stat_add_folio(folio, NR_THROTTLED_WRITTEN); /* * This is an inaccurate read as the per-cpu deltas may not * be synchronised. However, given that the system is * writeback throttled, it is not worth taking the penalty * of getting an accurate count. At worst, the throttle * timeout guarantees forward progress. */ nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) - READ_ONCE(pgdat->nr_reclaim_start); if (nr_written > SWAP_CLUSTER_MAX * nr_throttled) wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]); } /* possible outcome of pageout() */ typedef enum { /* failed to write folio out, folio is locked */ PAGE_KEEP, /* move folio to the active list, folio is locked */ PAGE_ACTIVATE, /* folio has been sent to the disk successfully, folio is unlocked */ PAGE_SUCCESS, /* folio is clean and locked */ PAGE_CLEAN, } pageout_t; /* * pageout is called by shrink_folio_list() for each dirty folio. * Calls ->writepage(). */ static pageout_t pageout(struct folio *folio, struct address_space *mapping, struct swap_iocb **plug) { /* * If the folio is dirty, only perform writeback if that write * will be non-blocking. To prevent this allocation from being * stalled by pagecache activity. But note that there may be * stalls if we need to run get_block(). We could test * PagePrivate for that. * * If this process is currently in __generic_file_write_iter() against * this folio's queue, we can perform writeback even if that * will block. * * If the folio is swapcache, write it back even if that would * block, for some throttling. This happens by accident, because * swap_backing_dev_info is bust: it doesn't reflect the * congestion state of the swapdevs. Easy to fix, if needed. */ if (!is_page_cache_freeable(folio)) return PAGE_KEEP; if (!mapping) { /* * Some data journaling orphaned folios can have * folio->mapping == NULL while being dirty with clean buffers. */ if (folio_test_private(folio)) { if (try_to_free_buffers(folio)) { folio_clear_dirty(folio); pr_info("%s: orphaned folio\n", __func__); return PAGE_CLEAN; } } return PAGE_KEEP; } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; if (folio_clear_dirty_for_io(folio)) { int res; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = SWAP_CLUSTER_MAX, .range_start = 0, .range_end = LLONG_MAX, .for_reclaim = 1, .swap_plug = plug, }; folio_set_reclaim(folio); res = mapping->a_ops->writepage(&folio->page, &wbc); if (res < 0) handle_write_error(mapping, folio, res); if (res == AOP_WRITEPAGE_ACTIVATE) { folio_clear_reclaim(folio); return PAGE_ACTIVATE; } if (!folio_test_writeback(folio)) { /* synchronous write or broken a_ops? */ folio_clear_reclaim(folio); } trace_mm_vmscan_write_folio(folio); node_stat_add_folio(folio, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } return PAGE_CLEAN; } /* * Same as remove_mapping, but if the folio is removed from the mapping, it * gets returned with a refcount of 0. */ static int __remove_mapping(struct address_space *mapping, struct folio *folio, bool reclaimed, struct mem_cgroup *target_memcg) { int refcount; void *shadow = NULL; BUG_ON(!folio_test_locked(folio)); BUG_ON(mapping != folio_mapping(folio)); if (!folio_test_swapcache(folio)) spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); /* * The non racy check for a busy folio. * * Must be careful with the order of the tests. When someone has * a ref to the folio, it may be possible that they dirty it then * drop the reference. So if the dirty flag is tested before the * refcount here, then the following race may occur: * * get_user_pages(&page); * [user mapping goes away] * write_to(page); * !folio_test_dirty(folio) [good] * folio_set_dirty(folio); * folio_put(folio); * !refcount(folio) [good, discard it] * * [oops, our write_to data is lost] * * Reversing the order of the tests ensures such a situation cannot * escape unnoticed. The smp_rmb is needed to ensure the folio->flags * load is not satisfied before that of folio->_refcount. * * Note that if the dirty flag is always set via folio_mark_dirty, * and thus under the i_pages lock, then this ordering is not required. */ refcount = 1 + folio_nr_pages(folio); if (!folio_ref_freeze(folio, refcount)) goto cannot_free; /* note: atomic_cmpxchg in folio_ref_freeze provides the smp_rmb */ if (unlikely(folio_test_dirty(folio))) { folio_ref_unfreeze(folio, refcount); goto cannot_free; } if (folio_test_swapcache(folio)) { swp_entry_t swap = folio_swap_entry(folio); /* get a shadow entry before mem_cgroup_swapout() clears folio_memcg() */ if (reclaimed && !mapping_exiting(mapping)) shadow = workingset_eviction(folio, target_memcg); mem_cgroup_swapout(folio, swap); __delete_from_swap_cache(folio, swap, shadow); xa_unlock_irq(&mapping->i_pages); put_swap_folio(folio, swap); } else { void (*free_folio)(struct folio *); free_folio = mapping->a_ops->free_folio; /* * Remember a shadow entry for reclaimed file cache in * order to detect refaults, thus thrashing, later on. * * But don't store shadows in an address space that is * already exiting. This is not just an optimization, * inode reclaim needs to empty out the radix tree or * the nodes are lost. Don't plant shadows behind its * back. * * We also don't store shadows for DAX mappings because the * only page cache folios found in these are zero pages * covering holes, and because we don't want to mix DAX * exceptional entries and shadow exceptional entries in the * same address_space. */ if (reclaimed && folio_is_file_lru(folio) && !mapping_exiting(mapping) && !dax_mapping(mapping)) shadow = workingset_eviction(folio, target_memcg); __filemap_remove_folio(folio, shadow); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); if (free_folio) free_folio(folio); } return 1; cannot_free: xa_unlock_irq(&mapping->i_pages); if (!folio_test_swapcache(folio)) spin_unlock(&mapping->host->i_lock); return 0; } /** * remove_mapping() - Attempt to remove a folio from its mapping. * @mapping: The address space. * @folio: The folio to remove. * * If the folio is dirty, under writeback or if someone else has a ref * on it, removal will fail. * Return: The number of pages removed from the mapping. 0 if the folio * could not be removed. * Context: The caller should have a single refcount on the folio and * hold its lock. */ long remove_mapping(struct address_space *mapping, struct folio *folio) { if (__remove_mapping(mapping, folio, false, NULL)) { /* * Unfreezing the refcount with 1 effectively * drops the pagecache ref for us without requiring another * atomic operation. */ folio_ref_unfreeze(folio, 1); return folio_nr_pages(folio); } return 0; } /** * folio_putback_lru - Put previously isolated folio onto appropriate LRU list. * @folio: Folio to be returned to an LRU list. * * Add previously isolated @folio to appropriate LRU list. * The folio may still be unevictable for other reasons. * * Context: lru_lock must not be held, interrupts must be enabled. */ void folio_putback_lru(struct folio *folio) { folio_add_lru(folio); folio_put(folio); /* drop ref from isolate */ } enum folio_references { FOLIOREF_RECLAIM, FOLIOREF_RECLAIM_CLEAN, FOLIOREF_KEEP, FOLIOREF_ACTIVATE, }; static enum folio_references folio_check_references(struct folio *folio, struct scan_control *sc) { int referenced_ptes, referenced_folio; unsigned long vm_flags; referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup, &vm_flags); referenced_folio = folio_test_clear_referenced(folio); /* * The supposedly reclaimable folio was found to be in a VM_LOCKED vma. * Let the folio, now marked Mlocked, be moved to the unevictable list. */ if (vm_flags & VM_LOCKED) return FOLIOREF_ACTIVATE; /* rmap lock contention: rotate */ if (referenced_ptes == -1) return FOLIOREF_KEEP; if (referenced_ptes) { /* * All mapped folios start out with page table * references from the instantiating fault, so we need * to look twice if a mapped file/anon folio is used more * than once. * * Mark it and spare it for another trip around the * inactive list. Another page table reference will * lead to its activation. * * Note: the mark is set for activated folios as well * so that recently deactivated but used folios are * quickly recovered. */ folio_set_referenced(folio); if (referenced_folio || referenced_ptes > 1) return FOLIOREF_ACTIVATE; /* * Activate file-backed executable folios after first usage. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) return FOLIOREF_ACTIVATE; return FOLIOREF_KEEP; } /* Reclaim if clean, defer dirty folios to writeback */ if (referenced_folio && folio_is_file_lru(folio)) return FOLIOREF_RECLAIM_CLEAN; return FOLIOREF_RECLAIM; } /* Check if a folio is dirty or under writeback */ static void folio_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct address_space *mapping; /* * Anonymous folios are not handled by flushers and must be written * from reclaim context. Do not stall reclaim based on them. * MADV_FREE anonymous folios are put into inactive file list too. * They could be mistakenly treated as file lru. So further anon * test is needed. */ if (!folio_is_file_lru(folio) || (folio_test_anon(folio) && !folio_test_swapbacked(folio))) { *dirty = false; *writeback = false; return; } /* By default assume that the folio flags are accurate */ *dirty = folio_test_dirty(folio); *writeback = folio_test_writeback(folio); /* Verify dirty/writeback state if the filesystem supports it */ if (!folio_test_private(folio)) return; mapping = folio_mapping(folio); if (mapping && mapping->a_ops->is_dirty_writeback) mapping->a_ops->is_dirty_writeback(folio, dirty, writeback); } static struct page *alloc_demote_page(struct page *page, unsigned long private) { struct page *target_page; nodemask_t *allowed_mask; struct migration_target_control *mtc; mtc = (struct migration_target_control *)private; allowed_mask = mtc->nmask; /* * make sure we allocate from the target node first also trying to * demote or reclaim pages from the target node via kswapd if we are * low on free memory on target node. If we don't do this and if * we have free memory on the slower(lower) memtier, we would start * allocating pages from slower(lower) memory tiers without even forcing * a demotion of cold pages from the target memtier. This can result * in the kernel placing hot pages in slower(lower) memory tiers. */ mtc->nmask = NULL; mtc->gfp_mask |= __GFP_THISNODE; target_page = alloc_migration_target(page, (unsigned long)mtc); if (target_page) return target_page; mtc->gfp_mask &= ~__GFP_THISNODE; mtc->nmask = allowed_mask; return alloc_migration_target(page, (unsigned long)mtc); } /* * Take folios on @demote_folios and attempt to demote them to another node. * Folios which are not demoted are left on @demote_folios. */ static unsigned int demote_folio_list(struct list_head *demote_folios, struct pglist_data *pgdat) { int target_nid = next_demotion_node(pgdat->node_id); unsigned int nr_succeeded; nodemask_t allowed_mask; struct migration_target_control mtc = { /* * Allocate from 'node', or fail quickly and quietly. * When this happens, 'page' will likely just be discarded * instead of migrated. */ .gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | __GFP_NOWARN | __GFP_NOMEMALLOC | GFP_NOWAIT, .nid = target_nid, .nmask = &allowed_mask }; if (list_empty(demote_folios)) return 0; if (target_nid == NUMA_NO_NODE) return 0; node_get_allowed_targets(pgdat, &allowed_mask); /* Demotion ignores all cpuset and mempolicy settings */ migrate_pages(demote_folios, alloc_demote_page, NULL, (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION, &nr_succeeded); if (current_is_kswapd()) __count_vm_events(PGDEMOTE_KSWAPD, nr_succeeded); else __count_vm_events(PGDEMOTE_DIRECT, nr_succeeded); return nr_succeeded; } static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask) { if (gfp_mask & __GFP_FS) return true; if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO)) return false; /* * We can "enter_fs" for swap-cache with only __GFP_IO * providing this isn't SWP_FS_OPS. * ->flags can be updated non-atomicially (scan_swap_map_slots), * but that will never affect SWP_FS_OPS, so the data_race * is safe. */ return !data_race(folio_swap_flags(folio) & SWP_FS_OPS); } /* * shrink_folio_list() returns the number of reclaimed pages */ static unsigned int shrink_folio_list(struct list_head *folio_list, struct pglist_data *pgdat, struct scan_control *sc, struct reclaim_stat *stat, bool ignore_references) { LIST_HEAD(ret_folios); LIST_HEAD(free_folios); LIST_HEAD(demote_folios); unsigned int nr_reclaimed = 0; unsigned int pgactivate = 0; bool do_demote_pass; struct swap_iocb *plug = NULL; memset(stat, 0, sizeof(*stat)); cond_resched(); do_demote_pass = can_demote(pgdat->node_id, sc); retry: while (!list_empty(folio_list)) { struct address_space *mapping; struct folio *folio; enum folio_references references = FOLIOREF_RECLAIM; bool dirty, writeback; unsigned int nr_pages; cond_resched(); folio = lru_to_folio(folio_list); list_del(&folio->lru); if (!folio_trylock(folio)) goto keep; VM_BUG_ON_FOLIO(folio_test_active(folio), folio); nr_pages = folio_nr_pages(folio); /* Account the number of base pages */ sc->nr_scanned += nr_pages; if (unlikely(!folio_evictable(folio))) goto activate_locked; if (!sc->may_unmap && folio_mapped(folio)) goto keep_locked; /* folio_update_gen() tried to promote this page? */ if (lru_gen_enabled() && !ignore_references && folio_mapped(folio) && folio_test_referenced(folio)) goto keep_locked; /* * The number of dirty pages determines if a node is marked * reclaim_congested. kswapd will stall and start writing * folios if the tail of the LRU is all dirty unqueued folios. */ folio_check_dirty_writeback(folio, &dirty, &writeback); if (dirty || writeback) stat->nr_dirty += nr_pages; if (dirty && !writeback) stat->nr_unqueued_dirty += nr_pages; /* * Treat this folio as congested if folios are cycling * through the LRU so quickly that the folios marked * for immediate reclaim are making it to the end of * the LRU a second time. */ if (writeback && folio_test_reclaim(folio)) stat->nr_congested += nr_pages; /* * If a folio at the tail of the LRU is under writeback, there * are three cases to consider. * * 1) If reclaim is encountering an excessive number * of folios under writeback and this folio has both * the writeback and reclaim flags set, then it * indicates that folios are being queued for I/O but * are being recycled through the LRU before the I/O * can complete. Waiting on the folio itself risks an * indefinite stall if it is impossible to writeback * the folio due to I/O error or disconnected storage * so instead note that the LRU is being scanned too * quickly and the caller can stall after the folio * list has been processed. * * 2) Global or new memcg reclaim encounters a folio that is * not marked for immediate reclaim, or the caller does not * have __GFP_FS (or __GFP_IO if it's simply going to swap, * not to fs). In this case mark the folio for immediate * reclaim and continue scanning. * * Require may_enter_fs() because we would wait on fs, which * may not have submitted I/O yet. And the loop driver might * enter reclaim, and deadlock if it waits on a folio for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * * 3) Legacy memcg encounters a folio that already has the * reclaim flag set. memcg does not have any dirty folio * throttling so we could easily OOM just because too many * folios are in writeback and there is nothing else to * reclaim. Wait for the writeback to complete. * * In cases 1) and 2) we activate the folios to get them out of * the way while we continue scanning for clean folios on the * inactive list and refilling from the active list. The * observation here is that waiting for disk writes is more * expensive than potentially causing reloads down the line. * Since they're marked for immediate reclaim, they won't put * memory pressure on the cache working set any longer than it * takes to write them to disk. */ if (folio_test_writeback(folio)) { /* Case 1 above */ if (current_is_kswapd() && folio_test_reclaim(folio) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { stat->nr_immediate += nr_pages; goto activate_locked; /* Case 2 above */ } else if (writeback_throttling_sane(sc) || !folio_test_reclaim(folio) || !may_enter_fs(folio, sc->gfp_mask)) { /* * This is slightly racy - * folio_end_writeback() might have * just cleared the reclaim flag, then * setting the reclaim flag here ends up * interpreted as the readahead flag - but * that does not matter enough to care. * What we do want is for this folio to * have the reclaim flag set next time * memcg reclaim reaches the tests above, * so it will then wait for writeback to * avoid OOM; and it's also appropriate * in global reclaim. */ folio_set_reclaim(folio); stat->nr_writeback += nr_pages; goto activate_locked; /* Case 3 above */ } else { folio_unlock(folio); folio_wait_writeback(folio); /* then go back and try same folio again */ list_add_tail(&folio->lru, folio_list); continue; } } if (!ignore_references) references = folio_check_references(folio, sc); switch (references) { case FOLIOREF_ACTIVATE: goto activate_locked; case FOLIOREF_KEEP: stat->nr_ref_keep += nr_pages; goto keep_locked; case FOLIOREF_RECLAIM: case FOLIOREF_RECLAIM_CLEAN: ; /* try to reclaim the folio below */ } /* * Before reclaiming the folio, try to relocate * its contents to another node. */ if (do_demote_pass && (thp_migration_supported() || !folio_test_large(folio))) { list_add(&folio->lru, &demote_folios); folio_unlock(folio); continue; } /* * Anonymous process memory has backing store? * Try to allocate it some swap space here. * Lazyfree folio could be freed directly */ if (folio_test_anon(folio) && folio_test_swapbacked(folio)) { if (!folio_test_swapcache(folio)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; if (folio_maybe_dma_pinned(folio)) goto keep_locked; if (folio_test_large(folio)) { /* cannot split folio, skip it */ if (!can_split_folio(folio, NULL)) goto activate_locked; /* * Split folios without a PMD map right * away. Chances are some or all of the * tail pages can be freed without IO. */ if (!folio_entire_mapcount(folio) && split_folio_to_list(folio, folio_list)) goto activate_locked; } if (!add_to_swap(folio)) { if (!folio_test_large(folio)) goto activate_locked_split; /* Fallback to swap normal pages */ if (split_folio_to_list(folio, folio_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE count_vm_event(THP_SWPOUT_FALLBACK); #endif if (!add_to_swap(folio)) goto activate_locked_split; } } } else if (folio_test_swapbacked(folio) && folio_test_large(folio)) { /* Split shmem folio */ if (split_folio_to_list(folio, folio_list)) goto keep_locked; } /* * If the folio was split above, the tail pages will make * their own pass through this function and be accounted * then. */ if ((nr_pages > 1) && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } /* * The folio is mapped into the page tables of one or more * processes. Try to unmap it here. */ if (folio_mapped(folio)) { enum ttu_flags flags = TTU_BATCH_FLUSH; bool was_swapbacked = folio_test_swapbacked(folio); if (folio_test_pmd_mappable(folio)) flags |= TTU_SPLIT_HUGE_PMD; try_to_unmap(folio, flags); if (folio_mapped(folio)) { stat->nr_unmap_fail += nr_pages; if (!was_swapbacked && folio_test_swapbacked(folio)) stat->nr_lazyfree_fail += nr_pages; goto activate_locked; } } mapping = folio_mapping(folio); if (folio_test_dirty(folio)) { /* * Only kswapd can writeback filesystem folios * to avoid risk of stack overflow. But avoid * injecting inefficient single-folio I/O into * flusher writeback as much as possible: only * write folios when we've encountered many * dirty folios, and when we've already scanned * the rest of the LRU for clean folios and see * the same dirty folios again (with the reclaim * flag set). */ if (folio_is_file_lru(folio) && (!current_is_kswapd() || !folio_test_reclaim(folio) || !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. * Similar in principle to deactivate_page() * except we already have the folio isolated * and know it's dirty */ node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE, nr_pages); folio_set_reclaim(folio); goto activate_locked; } if (references == FOLIOREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs(folio, sc->gfp_mask)) goto keep_locked; if (!sc->may_writepage) goto keep_locked; /* * Folio is dirty. Flush the TLB if a writable entry * potentially exists to avoid CPU writes after I/O * starts and then write it out here. */ try_to_unmap_flush_dirty(); switch (pageout(folio, mapping, &plug)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: goto activate_locked; case PAGE_SUCCESS: stat->nr_pageout += nr_pages; if (folio_test_writeback(folio)) goto keep; if (folio_test_dirty(folio)) goto keep; /* * A synchronous write - probably a ramdisk. Go * ahead and try to reclaim the folio. */ if (!folio_trylock(folio)) goto keep; if (folio_test_dirty(folio) || folio_test_writeback(folio)) goto keep_locked; mapping = folio_mapping(folio); fallthrough; case PAGE_CLEAN: ; /* try to free the folio below */ } } /* * If the folio has buffers, try to free the buffer * mappings associated with this folio. If we succeed * we try to free the folio as well. * * We do this even if the folio is dirty. * filemap_release_folio() does not perform I/O, but it * is possible for a folio to have the dirty flag set, * but it is actually clean (all its buffers are clean). * This happens if the buffers were written out directly, * with submit_bh(). ext3 will do this, as well as * the blockdev mapping. filemap_release_folio() will * discover that cleanness and will drop the buffers * and mark the folio clean - it can be freed. * * Rarely, folios can have buffers and no ->mapping. * These are the folios which were not successfully * invalidated in truncate_cleanup_folio(). We try to * drop those buffers here and if that worked, and the * folio is no longer mapped into process address space * (refcount == 1) it can be freed. Otherwise, leave * the folio on the LRU so it is swappable. */ if (folio_has_private(folio)) { if (!filemap_release_folio(folio, sc->gfp_mask)) goto activate_locked; if (!mapping && folio_ref_count(folio) == 1) { folio_unlock(folio); if (folio_put_testzero(folio)) goto free_it; else { /* * rare race with speculative reference. * the speculative reference will free * this folio shortly, so we may * increment nr_reclaimed here (and * leave it off the LRU). */ nr_reclaimed += nr_pages; continue; } } } if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) { /* follow __remove_mapping for reference */ if (!folio_ref_freeze(folio, 1)) goto keep_locked; /* * The folio has only one reference left, which is * from the isolation. After the caller puts the * folio back on the lru and drops the reference, the * folio will be freed anyway. It doesn't matter * which lru it goes on. So we don't bother checking * the dirty flag here. */ count_vm_events(PGLAZYFREED, nr_pages); count_memcg_folio_events(folio, PGLAZYFREED, nr_pages); } else if (!mapping || !__remove_mapping(mapping, folio, true, sc->target_mem_cgroup)) goto keep_locked; folio_unlock(folio); free_it: /* * Folio may get swapped out as a whole, need to account * all pages in it. */ nr_reclaimed += nr_pages; /* * Is there need to periodically free_folio_list? It would * appear not as the counts should be low */ if (unlikely(folio_test_large(folio))) destroy_large_folio(folio); else list_add(&folio->lru, &free_folios); continue; activate_locked_split: /* * The tail pages that are failed to add into swap cache * reach here. Fixup nr_scanned and nr_pages. */ if (nr_pages > 1) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (folio_test_swapcache(folio) && (mem_cgroup_swap_full(folio) || folio_test_mlocked(folio))) folio_free_swap(folio); VM_BUG_ON_FOLIO(folio_test_active(folio), folio); if (!folio_test_mlocked(folio)) { int type = folio_is_file_lru(folio); folio_set_active(folio); stat->nr_activate[type] += nr_pages; count_memcg_folio_events(folio, PGACTIVATE, nr_pages); } keep_locked: folio_unlock(folio); keep: list_add(&folio->lru, &ret_folios); VM_BUG_ON_FOLIO(folio_test_lru(folio) || folio_test_unevictable(folio), folio); } /* 'folio_list' is always empty here */ /* Migrate folios selected for demotion */ nr_reclaimed += demote_folio_list(&demote_folios, pgdat); /* Folios that could not be demoted are still in @demote_folios */ if (!list_empty(&demote_folios)) { /* Folios which weren't demoted go back on @folio_list for retry: */ list_splice_init(&demote_folios, folio_list); do_demote_pass = false; goto retry; } pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; mem_cgroup_uncharge_list(&free_folios); try_to_unmap_flush(); free_unref_page_list(&free_folios); list_splice(&ret_folios, folio_list); count_vm_events(PGACTIVATE, pgactivate); if (plug) swap_write_unplug(plug); return nr_reclaimed; } unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list) { struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_unmap = 1, }; struct reclaim_stat stat; unsigned int nr_reclaimed; struct folio *folio, *next; LIST_HEAD(clean_folios); unsigned int noreclaim_flag; list_for_each_entry_safe(folio, next, folio_list, lru) { if (!folio_test_hugetlb(folio) && folio_is_file_lru(folio) && !folio_test_dirty(folio) && !__folio_test_movable(folio) && !folio_test_unevictable(folio)) { folio_clear_active(folio); list_move(&folio->lru, &clean_folios); } } /* * We should be safe here since we are only dealing with file pages and * we are not kswapd and therefore cannot write dirty file pages. But * call memalloc_noreclaim_save() anyway, just in case these conditions * change in the future. */ noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = shrink_folio_list(&clean_folios, zone->zone_pgdat, &sc, &stat, true); memalloc_noreclaim_restore(noreclaim_flag); list_splice(&clean_folios, folio_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)nr_reclaimed); /* * Since lazyfree pages are isolated from file LRU from the beginning, * they will rotate back to anonymous LRU in the end if it failed to * discard so isolated count will be mismatched. * Compensate the isolated count for both LRU lists. */ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, stat.nr_lazyfree_fail); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)stat.nr_lazyfree_fail); return nr_reclaimed; } /* * Update LRU sizes after isolating pages. The LRU size updates must * be complete before mem_cgroup_update_lru_size due to a sanity check. */ static __always_inline void update_lru_sizes(struct lruvec *lruvec, enum lru_list lru, unsigned long *nr_zone_taken) { int zid; for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_zone_taken[zid]) continue; update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); } } /* * Isolating page from the lruvec to fill in @dst list by nr_to_scan times. * * lruvec->lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages * and working on them outside the LRU lock. * * For pagecache intensive workloads, this function is the hottest * spot in the kernel (apart from copy_*_user functions). * * Lru_lock must be held before calling this function. * * @nr_to_scan: The number of eligible pages to look through on the list. * @lruvec: The LRU vector to pull pages from. * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. */ static unsigned long isolate_lru_folios(unsigned long nr_to_scan, struct lruvec *lruvec, struct list_head *dst, unsigned long *nr_scanned, struct scan_control *sc, enum lru_list lru) { struct list_head *src = &lruvec->lists[lru]; unsigned long nr_taken = 0; unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0; unsigned long scan, total_scan, nr_pages; LIST_HEAD(folios_skipped); total_scan = 0; scan = 0; while (scan < nr_to_scan && !list_empty(src)) { struct list_head *move_to = src; struct folio *folio; folio = lru_to_folio(src); prefetchw_prev_lru_folio(folio, src, flags); nr_pages = folio_nr_pages(folio); total_scan += nr_pages; if (folio_zonenum(folio) > sc->reclaim_idx) { nr_skipped[folio_zonenum(folio)] += nr_pages; move_to = &folios_skipped; goto move; } /* * Do not count skipped folios because that makes the function * return with no isolated folios if the LRU mostly contains * ineligible folios. This causes the VM to not reclaim any * folios, triggering a premature OOM. * Account all pages in a folio. */ scan += nr_pages; if (!folio_test_lru(folio)) goto move; if (!sc->may_unmap && folio_mapped(folio)) goto move; /* * Be careful not to clear the lru flag until after we're * sure the folio is not being freed elsewhere -- the * folio release code relies on it. */ if (unlikely(!folio_try_get(folio))) goto move; if (!folio_test_clear_lru(folio)) { /* Another thread is already isolating this folio */ folio_put(folio); goto move; } nr_taken += nr_pages; nr_zone_taken[folio_zonenum(folio)] += nr_pages; move_to = dst; move: list_move(&folio->lru, move_to); } /* * Splice any skipped folios to the start of the LRU list. Note that * this disrupts the LRU order when reclaiming for lower zones but * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX * scanning would soon rescan the same folios to skip and waste lots * of cpu cycles. */ if (!list_empty(&folios_skipped)) { int zid; list_splice(&folios_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); skipped += nr_skipped[zid]; } } *nr_scanned = total_scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, total_scan, skipped, nr_taken, sc->may_unmap ? 0 : ISOLATE_UNMAPPED, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } /** * folio_isolate_lru() - Try to isolate a folio from its LRU list. * @folio: Folio to isolate from its LRU list. * * Isolate a @folio from an LRU list and adjust the vmstat statistic * corresponding to whatever LRU list the folio was on. * * The folio will have its LRU flag cleared. If it was found on the * active list, it will have the Active flag set. If it was found on the * unevictable list, it will have the Unevictable flag set. These flags * may need to be cleared by the caller before letting the page go. * * Context: * * (1) Must be called with an elevated refcount on the folio. This is a * fundamental difference from isolate_lru_folios() (which is called * without a stable reference). * (2) The lru_lock must not be held. * (3) Interrupts must be enabled. * * Return: 0 if the folio was removed from an LRU list. * -EBUSY if the folio was not on an LRU list. */ int folio_isolate_lru(struct folio *folio) { int ret = -EBUSY; VM_BUG_ON_FOLIO(!folio_ref_count(folio), folio); if (folio_test_clear_lru(folio)) { struct lruvec *lruvec; folio_get(folio); lruvec = folio_lruvec_lock_irq(folio); lruvec_del_folio(lruvec, folio); unlock_page_lruvec_irq(lruvec); ret = 0; } return ret; } /* * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and * then get rescheduled. When there are massive number of tasks doing page * allocation, such sleeping direct reclaimers may keep piling up on each CPU, * the LRU list will go small and be scanned faster than necessary, leading to * unnecessary swapping, thrashing and OOM. */ static int too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; bool too_many; if (current_is_kswapd()) return 0; if (!writeback_throttling_sane(sc)) return 0; if (file) { inactive = node_page_state(pgdat, NR_INACTIVE_FILE); isolated = node_page_state(pgdat, NR_ISOLATED_FILE); } else { inactive = node_page_state(pgdat, NR_INACTIVE_ANON); isolated = node_page_state(pgdat, NR_ISOLATED_ANON); } /* * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they * won't get blocked by normal direct-reclaimers, forming a circular * deadlock. */ if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) inactive >>= 3; too_many = isolated > inactive; /* Wake up tasks throttled due to too_many_isolated. */ if (!too_many) wake_throttle_isolated(pgdat); return too_many; } /* * move_folios_to_lru() moves folios from private @list to appropriate LRU list. * On return, @list is reused as a list of folios to be freed by the caller. * * Returns the number of pages moved to the given lruvec. */ static unsigned int move_folios_to_lru(struct lruvec *lruvec, struct list_head *list) { int nr_pages, nr_moved = 0; LIST_HEAD(folios_to_free); while (!list_empty(list)) { struct folio *folio = lru_to_folio(list); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { spin_unlock_irq(&lruvec->lru_lock); folio_putback_lru(folio); spin_lock_irq(&lruvec->lru_lock); continue; } /* * The folio_set_lru needs to be kept here for list integrity. * Otherwise: * #0 move_folios_to_lru #1 release_pages * if (!folio_put_testzero()) * if (folio_put_testzero()) * !lru //skip lru_lock * folio_set_lru() * list_add(&folio->lru,) * list_add(&folio->lru,) */ folio_set_lru(folio); if (unlikely(folio_put_testzero(folio))) { __folio_clear_lru_flags(folio); if (unlikely(folio_test_large(folio))) { spin_unlock_irq(&lruvec->lru_lock); destroy_large_folio(folio); spin_lock_irq(&lruvec->lru_lock); } else list_add(&folio->lru, &folios_to_free); continue; } /* * All pages were isolated from the same lruvec (and isolation * inhibits memcg migration). */ VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); lruvec_add_folio(lruvec, folio); nr_pages = folio_nr_pages(folio); nr_moved += nr_pages; if (folio_test_active(folio)) workingset_age_nonresident(lruvec, nr_pages); } /* * To save our caller's stack, now use input list for pages to free. */ list_splice(&folios_to_free, list); return nr_moved; } /* * If a kernel thread (such as nfsd for loop-back mounts) services a backing * device by writing to the page cache it sets PF_LOCAL_THROTTLE. In this case * we should not throttle. Otherwise it is safe to do so. */ static int current_may_throttle(void) { return !(current->flags & PF_LOCAL_THROTTLE); } /* * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ static unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { LIST_HEAD(folio_list); unsigned long nr_scanned; unsigned int nr_reclaimed = 0; unsigned long nr_taken; struct reclaim_stat stat; bool file = is_file_lru(lru); enum vm_event_item item; struct pglist_data *pgdat = lruvec_pgdat(lruvec); bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { if (stalled) return 0; /* wait a bit for the reclaimer. */ stalled = true; reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) return SWAP_CLUSTER_MAX; } lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &folio_list, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); __count_vm_events(PGSCAN_ANON + file, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); if (nr_taken == 0) return 0; nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false); spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &folio_list); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); spin_unlock_irq(&lruvec->lru_lock); lru_note_cost(lruvec, file, stat.nr_pageout); mem_cgroup_uncharge_list(&folio_list); free_unref_page_list(&folio_list); /* * If dirty folios are scanned that are not queued for IO, it * implies that flushers are not doing their job. This can * happen when memory pressure pushes dirty folios to the end of * the LRU before the dirty limits are breached and the dirty * data has expired. It can also happen when the proportion of * dirty folios grows not through writes but through memory * pressure reclaiming all the clean cache. And in some cases, * the flushers simply cannot keep up with the allocation * rate. Nudge the flusher threads in case they are asleep. */ if (stat.nr_unqueued_dirty == nr_taken) { wakeup_flusher_threads(WB_REASON_VMSCAN); /* * For cgroupv1 dirty throttling is achieved by waking up * the kernel flusher here and later waiting on folios * which are in writeback to finish (see shrink_folio_list()). * * Flusher may not be able to issue writeback quickly * enough for cgroupv1 writeback throttling to work * on a large system. */ if (!writeback_throttling_sane(sc)) reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } sc->nr.dirty += stat.nr_dirty; sc->nr.congested += stat.nr_congested; sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr.writeback += stat.nr_writeback; sc->nr.immediate += stat.nr_immediate; sc->nr.taken += nr_taken; if (file) sc->nr.file_taken += nr_taken; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, nr_scanned, nr_reclaimed, &stat, sc->priority, file); return nr_reclaimed; } /* * shrink_active_list() moves folios from the active LRU to the inactive LRU. * * We move them the other way if the folio is referenced by one or more * processes. * * If the folios are mostly unmapped, the processing is fast and it is * appropriate to hold lru_lock across the whole operation. But if * the folios are mapped, the processing is slow (folio_referenced()), so * we should drop lru_lock around each folio. It's impossible to balance * this, so instead we remove the folios from the LRU while processing them. * It is safe to rely on the active flag against the non-LRU folios in here * because nobody will play with that bit on a non-LRU folio. * * The downside is that we have to touch folio->_refcount against each folio. * But we had to alter folio->flags anyway. */ static void shrink_active_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { unsigned long nr_taken; unsigned long nr_scanned; unsigned long vm_flags; LIST_HEAD(l_hold); /* The folios which were snipped off */ LIST_HEAD(l_active); LIST_HEAD(l_inactive); unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; int file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); if (!cgroup_reclaim(sc)) __count_vm_events(PGREFILL, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); while (!list_empty(&l_hold)) { struct folio *folio; cond_resched(); folio = lru_to_folio(&l_hold); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { folio_putback_lru(folio); continue; } if (unlikely(buffer_heads_over_limit)) { if (folio_test_private(folio) && folio_trylock(folio)) { if (folio_test_private(folio)) filemap_release_folio(folio, 0); folio_unlock(folio); } } /* Referenced or rmap lock contention: rotate */ if (folio_referenced(folio, 0, sc->target_mem_cgroup, &vm_flags) != 0) { /* * Identify referenced, file-backed active folios and * give them one more trip around the active list. So * that executable code get better chances to stay in * memory under moderate memory pressure. Anon folios * are not likely to be evicted by use-once streaming * IO, plus JVM can create lots of anon VM_EXEC folios, * so we ignore them here. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) { nr_rotated += folio_nr_pages(folio); list_add(&folio->lru, &l_active); continue; } } folio_clear_active(folio); /* we are de-activating */ folio_set_workingset(folio); list_add(&folio->lru, &l_inactive); } /* * Move folios back to the lru list. */ spin_lock_irq(&lruvec->lru_lock); nr_activate = move_folios_to_lru(lruvec, &l_active); nr_deactivate = move_folios_to_lru(lruvec, &l_inactive); /* Keep all free folios in l_active list */ list_splice(&l_inactive, &l_active); __count_vm_events(PGDEACTIVATE, nr_deactivate); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_list(&l_active); free_unref_page_list(&l_active); trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate, nr_deactivate, nr_rotated, sc->priority, file); } static unsigned int reclaim_folio_list(struct list_head *folio_list, struct pglist_data *pgdat) { struct reclaim_stat dummy_stat; unsigned int nr_reclaimed; struct folio *folio; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .no_demotion = 1, }; nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &dummy_stat, false); while (!list_empty(folio_list)) { folio = lru_to_folio(folio_list); list_del(&folio->lru); folio_putback_lru(folio); } return nr_reclaimed; } unsigned long reclaim_pages(struct list_head *folio_list) { int nid; unsigned int nr_reclaimed = 0; LIST_HEAD(node_folio_list); unsigned int noreclaim_flag; if (list_empty(folio_list)) return nr_reclaimed; noreclaim_flag = memalloc_noreclaim_save(); nid = folio_nid(lru_to_folio(folio_list)); do { struct folio *folio = lru_to_folio(folio_list); if (nid == folio_nid(folio)) { folio_clear_active(folio); list_move(&folio->lru, &node_folio_list); continue; } nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); nid = folio_nid(lru_to_folio(folio_list)); } while (!list_empty(folio_list)); nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); memalloc_noreclaim_restore(noreclaim_flag); return nr_reclaimed; } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { if (sc->may_deactivate & (1 << is_file_lru(lru))) shrink_active_list(nr_to_scan, lruvec, sc, lru); else sc->skipped_deactivate = 1; return 0; } return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } /* * The inactive anon list should be small enough that the VM never has * to do too much work. * * The inactive file list should be small enough to leave most memory * to the established workingset on the scan-resistant active list, * but large enough to avoid thrashing the aggregate readahead window. * * Both inactive lists should also be large enough that each inactive * folio has a chance to be referenced again before it is reclaimed. * * If that fails and refaulting is observed, the inactive list grows. * * The inactive_ratio is the target ratio of ACTIVE to INACTIVE folios * on this LRU, maintained by the pageout code. An inactive_ratio * of 3 means 3:1 or 25% of the folios are kept on the inactive list. * * total target max * memory ratio inactive * ------------------------------------- * 10MB 1 5MB * 100MB 1 50MB * 1GB 3 250MB * 10GB 10 0.9GB * 100GB 31 3GB * 1TB 101 10GB * 10TB 320 32GB */ static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) { enum lru_list active_lru = inactive_lru + LRU_ACTIVE; unsigned long inactive, active; unsigned long inactive_ratio; unsigned long gb; inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) inactive_ratio = int_sqrt(10 * gb); else inactive_ratio = 1; return inactive * inactive_ratio < active; } enum scan_balance { SCAN_EQUAL, SCAN_FRACT, SCAN_ANON, SCAN_FILE, }; static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc) { unsigned long file; struct lruvec *target_lruvec; if (lru_gen_enabled()) return; target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); /* * Flush the memory cgroup stats, so that we read accurate per-memcg * lruvec stats for heuristics. */ mem_cgroup_flush_stats(); /* * Determine the scan balance between anon and file LRUs. */ spin_lock_irq(&target_lruvec->lru_lock); sc->anon_cost = target_lruvec->anon_cost; sc->file_cost = target_lruvec->file_cost; spin_unlock_irq(&target_lruvec->lru_lock); /* * Target desirable inactive:active list ratios for the anon * and file LRU lists. */ if (!sc->force_deactivate) { unsigned long refaults; /* * When refaults are being observed, it means a new * workingset is being established. Deactivate to get * rid of any stale active pages quickly. */ refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); if (refaults != target_lruvec->refaults[WORKINGSET_ANON] || inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) sc->may_deactivate |= DEACTIVATE_ANON; else sc->may_deactivate &= ~DEACTIVATE_ANON; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); if (refaults != target_lruvec->refaults[WORKINGSET_FILE] || inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) sc->may_deactivate |= DEACTIVATE_FILE; else sc->may_deactivate &= ~DEACTIVATE_FILE; } else sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE; /* * If we have plenty of inactive file pages that aren't * thrashing, try to reclaim those first before touching * anonymous pages. */ file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE)) sc->cache_trim_mode = 1; else sc->cache_trim_mode = 0; /* * Prevent the reclaimer from falling into the cache trap: as * cache pages start out inactive, every cache fault will tip * the scan balance towards the file LRU. And as the file LRU * shrinks, so does the window for rotation from references. * This means we have a runaway feedback loop where a tiny * thrashing file LRU becomes infinitely more attractive than * anon pages. Try to detect this based on file LRU size. */ if (!cgroup_reclaim(sc)) { unsigned long total_high_wmark = 0; unsigned long free, anon; int z; free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); file = node_page_state(pgdat, NR_ACTIVE_FILE) + node_page_state(pgdat, NR_INACTIVE_FILE); for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; total_high_wmark += high_wmark_pages(zone); } /* * Consider anon: if that's low too, this isn't a * runaway file reclaim problem, but rather just * extreme pressure. Reclaim as per usual then. */ anon = node_page_state(pgdat, NR_INACTIVE_ANON); sc->file_is_tiny = file + free <= total_high_wmark && !(sc->may_deactivate & DEACTIVATE_ANON) && anon >> sc->priority; } } /* * Determine how aggressively the anon and file LRU lists should be * scanned. * * nr[0] = anon inactive folios to scan; nr[1] = anon active folios to scan * nr[2] = file inactive folios to scan; nr[3] = file active folios to scan */ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); unsigned long anon_cost, file_cost, total_cost; int swappiness = mem_cgroup_swappiness(memcg); u64 fraction[ANON_AND_FILE]; u64 denominator = 0; /* gcc */ enum scan_balance scan_balance; unsigned long ap, fp; enum lru_list lru; /* If we have no swap space, do not bother scanning anon folios. */ if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) { scan_balance = SCAN_FILE; goto out; } /* * Global reclaim will swap to prevent OOM even with no * swappiness, but memcg users want to use this knob to * disable swapping for individual groups completely when * using the memory controller's swap limit feature would be * too expensive. */ if (cgroup_reclaim(sc) && !swappiness) { scan_balance = SCAN_FILE; goto out; } /* * Do not apply any pressure balancing cleverness when the * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ if (!sc->priority && swappiness) { scan_balance = SCAN_EQUAL; goto out; } /* * If the system is almost out of file pages, force-scan anon. */ if (sc->file_is_tiny) { scan_balance = SCAN_ANON; goto out; } /* * If there is enough inactive page cache, we do not reclaim * anything from the anonymous working right now. */ if (sc->cache_trim_mode) { scan_balance = SCAN_FILE; goto out; } scan_balance = SCAN_FRACT; /* * Calculate the pressure balance between anon and file pages. * * The amount of pressure we put on each LRU is inversely * proportional to the cost of reclaiming each list, as * determined by the share of pages that are refaulting, times * the relative IO cost of bringing back a swapped out * anonymous page vs reloading a filesystem page (swappiness). * * Although we limit that influence to ensure no list gets * left behind completely: at least a third of the pressure is * applied, before swappiness. * * With swappiness at 100, anon and file have equal IO cost. */ total_cost = sc->anon_cost + sc->file_cost; anon_cost = total_cost + sc->anon_cost; file_cost = total_cost + sc->file_cost; total_cost = anon_cost + file_cost; ap = swappiness * (total_cost + 1); ap /= anon_cost + 1; fp = (200 - swappiness) * (total_cost + 1); fp /= file_cost + 1; fraction[0] = ap; fraction[1] = fp; denominator = ap + fp; out: for_each_evictable_lru(lru) { int file = is_file_lru(lru); unsigned long lruvec_size; unsigned long low, min; unsigned long scan; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low); if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min * setting. * * This is important, as otherwise scanning aggression * becomes extremely binary -- from nothing as we * approach the memory protection threshold, to totally * nominal as we exceed it. This results in requiring * setting extremely liberal protection thresholds. It * also means we simply get no protection at all if we * set it too low, which is not ideal. * * If there is any protection in place, we reduce scan * pressure by how much of the total memory used is * within protection thresholds. * * There is one special case: in the first reclaim pass, * we skip over all groups that are within their low * protection. If that fails to reclaim enough pages to * satisfy the reclaim goal, we come back and override * the best-effort low protection. However, we still * ideally want to honor how well-behaved groups are in * that case instead of simply punishing them all * equally. As such, we reclaim them based on how much * memory they are using, reducing the scan pressure * again by how much of the total memory used is under * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); unsigned long protection; /* memory.low scaling, make sure we retry before OOM */ if (!sc->memcg_low_reclaim && low > min) { protection = low; sc->memcg_low_skipped = 1; } else { protection = min; } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); scan = lruvec_size - lruvec_size * protection / (cgroup_size + 1); /* * Minimally target SWAP_CLUSTER_MAX pages to keep * reclaim moving forwards, avoiding decrementing * sc->priority further than desirable. */ scan = max(scan, SWAP_CLUSTER_MAX); } else { scan = lruvec_size; } scan >>= sc->priority; /* * If the cgroup's already been deleted, make sure to * scrape out the remaining cache. */ if (!scan && !mem_cgroup_online(memcg)) scan = min(lruvec_size, SWAP_CLUSTER_MAX); switch (scan_balance) { case SCAN_EQUAL: /* Scan lists relative to size */ break; case SCAN_FRACT: /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. * Make sure we don't miss the last page on * the offlined memory cgroups because of a * round-off error. */ scan = mem_cgroup_online(memcg) ? div64_u64(scan * fraction[file], denominator) : DIV64_U64_ROUND_UP(scan * fraction[file], denominator); break; case SCAN_FILE: case SCAN_ANON: /* Scan one type exclusively */ if ((scan_balance == SCAN_FILE) != file) scan = 0; break; default: /* Look ma, no brain */ BUG(); } nr[lru] = scan; } } /* * Anonymous LRU management is a waste if there is * ultimately no way to reclaim the memory. */ static bool can_age_anon_pages(struct pglist_data *pgdat, struct scan_control *sc) { /* Aging the anon LRU is valuable if swap is present: */ if (total_swap_pages > 0) return true; /* Also valuable if anon pages can be demoted: */ return can_demote(pgdat->node_id, sc); } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED DEFINE_STATIC_KEY_ARRAY_TRUE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_likely(&lru_gen_caps[cap]) #else DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_unlikely(&lru_gen_caps[cap]) #endif /****************************************************************************** * shorthand helpers ******************************************************************************/ #define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset)) #define DEFINE_MAX_SEQ(lruvec) \ unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq) #define DEFINE_MIN_SEQ(lruvec) \ unsigned long min_seq[ANON_AND_FILE] = { \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_ANON]), \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_FILE]), \ } #define for_each_gen_type_zone(gen, type, zone) \ for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++) \ for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \ for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++) static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid) { struct pglist_data *pgdat = NODE_DATA(nid); #ifdef CONFIG_MEMCG if (memcg) { struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec; /* for hotadd_new_pgdat() */ if (!lruvec->pgdat) lruvec->pgdat = pgdat; return lruvec; } #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return pgdat ? &pgdat->__lruvec : NULL; } static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc) { struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); if (!can_demote(pgdat->node_id, sc) && mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH) return 0; return mem_cgroup_swappiness(memcg); } static int get_nr_gens(struct lruvec *lruvec, int type) { return lruvec->lrugen.max_seq - lruvec->lrugen.min_seq[type] + 1; } static bool __maybe_unused seq_is_valid(struct lruvec *lruvec) { /* see the comment on lru_gen_struct */ return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS && get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) && get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS; } /****************************************************************************** * mm_struct list ******************************************************************************/ static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg) { static struct lru_gen_mm_list mm_list = { .fifo = LIST_HEAD_INIT(mm_list.fifo), .lock = __SPIN_LOCK_UNLOCKED(mm_list.lock), }; #ifdef CONFIG_MEMCG if (memcg) return &memcg->mm_list; #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return &mm_list; } void lru_gen_add_mm(struct mm_struct *mm) { int nid; struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); VM_WARN_ON_ONCE(!list_empty(&mm->lru_gen.list)); #ifdef CONFIG_MEMCG VM_WARN_ON_ONCE(mm->lru_gen.memcg); mm->lru_gen.memcg = memcg; #endif spin_lock(&mm_list->lock); for_each_node_state(nid, N_MEMORY) { struct lruvec *lruvec = get_lruvec(memcg, nid); if (!lruvec) continue; /* the first addition since the last iteration */ if (lruvec->mm_state.tail == &mm_list->fifo) lruvec->mm_state.tail = &mm->lru_gen.list; } list_add_tail(&mm->lru_gen.list, &mm_list->fifo); spin_unlock(&mm_list->lock); } void lru_gen_del_mm(struct mm_struct *mm) { int nid; struct lru_gen_mm_list *mm_list; struct mem_cgroup *memcg = NULL; if (list_empty(&mm->lru_gen.list)) return; #ifdef CONFIG_MEMCG memcg = mm->lru_gen.memcg; #endif mm_list = get_mm_list(memcg); spin_lock(&mm_list->lock); for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); if (!lruvec) continue; /* where the last iteration ended (exclusive) */ if (lruvec->mm_state.tail == &mm->lru_gen.list) lruvec->mm_state.tail = lruvec->mm_state.tail->next; /* where the current iteration continues (inclusive) */ if (lruvec->mm_state.head != &mm->lru_gen.list) continue; lruvec->mm_state.head = lruvec->mm_state.head->next; /* the deletion ends the current iteration */ if (lruvec->mm_state.head == &mm_list->fifo) WRITE_ONCE(lruvec->mm_state.seq, lruvec->mm_state.seq + 1); } list_del_init(&mm->lru_gen.list); spin_unlock(&mm_list->lock); #ifdef CONFIG_MEMCG mem_cgroup_put(mm->lru_gen.memcg); mm->lru_gen.memcg = NULL; #endif } #ifdef CONFIG_MEMCG void lru_gen_migrate_mm(struct mm_struct *mm) { struct mem_cgroup *memcg; struct task_struct *task = rcu_dereference_protected(mm->owner, true); VM_WARN_ON_ONCE(task->mm != mm); lockdep_assert_held(&task->alloc_lock); /* for mm_update_next_owner() */ if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(task); rcu_read_unlock(); if (memcg == mm->lru_gen.memcg) return; VM_WARN_ON_ONCE(!mm->lru_gen.memcg); VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list)); lru_gen_del_mm(mm); lru_gen_add_mm(mm); } #endif /* * Bloom filters with m=1<<15, k=2 and the false positive rates of ~1/5 when * n=10,000 and ~1/2 when n=20,000, where, conventionally, m is the number of * bits in a bitmap, k is the number of hash functions and n is the number of * inserted items. * * Page table walkers use one of the two filters to reduce their search space. * To get rid of non-leaf entries that no longer have enough leaf entries, the * aging uses the double-buffering technique to flip to the other filter each * time it produces a new generation. For non-leaf entries that have enough * leaf entries, the aging carries them over to the next generation in * walk_pmd_range(); the eviction also report them when walking the rmap * in lru_gen_look_around(). * * For future optimizations: * 1. It's not necessary to keep both filters all the time. The spare one can be * freed after the RCU grace period and reallocated if needed again. * 2. And when reallocating, it's worth scaling its size according to the number * of inserted entries in the other filter, to reduce the memory overhead on * small systems and false positives on large systems. * 3. Jenkins' hash function is an alternative to Knuth's. */ #define BLOOM_FILTER_SHIFT 15 static inline int filter_gen_from_seq(unsigned long seq) { return seq % NR_BLOOM_FILTERS; } static void get_item_key(void *item, int *key) { u32 hash = hash_ptr(item, BLOOM_FILTER_SHIFT * 2); BUILD_BUG_ON(BLOOM_FILTER_SHIFT * 2 > BITS_PER_TYPE(u32)); key[0] = hash & (BIT(BLOOM_FILTER_SHIFT) - 1); key[1] = hash >> BLOOM_FILTER_SHIFT; } static void reset_bloom_filter(struct lruvec *lruvec, unsigned long seq) { unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = lruvec->mm_state.filters[gen]; if (filter) { bitmap_clear(filter, 0, BIT(BLOOM_FILTER_SHIFT)); return; } filter = bitmap_zalloc(BIT(BLOOM_FILTER_SHIFT), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); WRITE_ONCE(lruvec->mm_state.filters[gen], filter); } static void update_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(lruvec->mm_state.filters[gen]); if (!filter) return; get_item_key(item, key); if (!test_bit(key[0], filter)) set_bit(key[0], filter); if (!test_bit(key[1], filter)) set_bit(key[1], filter); } static bool test_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(lruvec->mm_state.filters[gen]); if (!filter) return true; get_item_key(item, key); return test_bit(key[0], filter) && test_bit(key[1], filter); } static void reset_mm_stats(struct lruvec *lruvec, struct lru_gen_mm_walk *walk, bool last) { int i; int hist; lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock); if (walk) { hist = lru_hist_from_seq(walk->max_seq); for (i = 0; i < NR_MM_STATS; i++) { WRITE_ONCE(lruvec->mm_state.stats[hist][i], lruvec->mm_state.stats[hist][i] + walk->mm_stats[i]); walk->mm_stats[i] = 0; } } if (NR_HIST_GENS > 1 && last) { hist = lru_hist_from_seq(lruvec->mm_state.seq + 1); for (i = 0; i < NR_MM_STATS; i++) WRITE_ONCE(lruvec->mm_state.stats[hist][i], 0); } } static bool should_skip_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk) { int type; unsigned long size = 0; struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); int key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap); if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap)) return true; clear_bit(key, &mm->lru_gen.bitmap); for (type = !walk->can_swap; type < ANON_AND_FILE; type++) { size += type ? get_mm_counter(mm, MM_FILEPAGES) : get_mm_counter(mm, MM_ANONPAGES) + get_mm_counter(mm, MM_SHMEMPAGES); } if (size < MIN_LRU_BATCH) return true; return !mmget_not_zero(mm); } static bool iterate_mm_list(struct lruvec *lruvec, struct lru_gen_mm_walk *walk, struct mm_struct **iter) { bool first = false; bool last = true; struct mm_struct *mm = NULL; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = &lruvec->mm_state; /* * There are four interesting cases for this page table walker: * 1. It tries to start a new iteration of mm_list with a stale max_seq; * there is nothing left to do. * 2. It's the first of the current generation, and it needs to reset * the Bloom filter for the next generation. * 3. It reaches the end of mm_list, and it needs to increment * mm_state->seq; the iteration is done. * 4. It's the last of the current generation, and it needs to reset the * mm stats counters for the next generation. */ spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < walk->max_seq); VM_WARN_ON_ONCE(*iter && mm_state->seq > walk->max_seq); VM_WARN_ON_ONCE(*iter && !mm_state->nr_walkers); if (walk->max_seq <= mm_state->seq) { if (!*iter) last = false; goto done; } if (!mm_state->nr_walkers) { VM_WARN_ON_ONCE(mm_state->head && mm_state->head != &mm_list->fifo); mm_state->head = mm_list->fifo.next; first = true; } while (!mm && mm_state->head != &mm_list->fifo) { mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list); mm_state->head = mm_state->head->next; /* force scan for those added after the last iteration */ if (!mm_state->tail || mm_state->tail == &mm->lru_gen.list) { mm_state->tail = mm_state->head; walk->force_scan = true; } if (should_skip_mm(mm, walk)) mm = NULL; } if (mm_state->head == &mm_list->fifo) WRITE_ONCE(mm_state->seq, mm_state->seq + 1); done: if (*iter && !mm) mm_state->nr_walkers--; if (!*iter && mm) mm_state->nr_walkers++; if (mm_state->nr_walkers) last = false; if (*iter || last) reset_mm_stats(lruvec, walk, last); spin_unlock(&mm_list->lock); if (mm && first) reset_bloom_filter(lruvec, walk->max_seq + 1); if (*iter) mmput_async(*iter); *iter = mm; return last; } static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long max_seq) { bool success = false; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = &lruvec->mm_state; spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < max_seq); if (max_seq > mm_state->seq && !mm_state->nr_walkers) { VM_WARN_ON_ONCE(mm_state->head && mm_state->head != &mm_list->fifo); WRITE_ONCE(mm_state->seq, mm_state->seq + 1); reset_mm_stats(lruvec, NULL, true); success = true; } spin_unlock(&mm_list->lock); return success; } /****************************************************************************** * refault feedback loop ******************************************************************************/ /* * A feedback loop based on Proportional-Integral-Derivative (PID) controller. * * The P term is refaulted/(evicted+protected) from a tier in the generation * currently being evicted; the I term is the exponential moving average of the * P term over the generations previously evicted, using the smoothing factor * 1/2; the D term isn't supported. * * The setpoint (SP) is always the first tier of one type; the process variable * (PV) is either any tier of the other type or any other tier of the same * type. * * The error is the difference between the SP and the PV; the correction is to * turn off protection when SP>PV or turn on protection when SP<PV. * * For future optimizations: * 1. The D term may discount the other two terms over time so that long-lived * generations can resist stale information. */ struct ctrl_pos { unsigned long refaulted; unsigned long total; int gain; }; static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain, struct ctrl_pos *pos) { struct lru_gen_struct *lrugen = &lruvec->lrugen; int hist = lru_hist_from_seq(lrugen->min_seq[type]); pos->refaulted = lrugen->avg_refaulted[type][tier] + atomic_long_read(&lrugen->refaulted[hist][type][tier]); pos->total = lrugen->avg_total[type][tier] + atomic_long_read(&lrugen->evicted[hist][type][tier]); if (tier) pos->total += lrugen->protected[hist][type][tier - 1]; pos->gain = gain; } static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover) { int hist, tier; struct lru_gen_struct *lrugen = &lruvec->lrugen; bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1; unsigned long seq = carryover ? lrugen->min_seq[type] : lrugen->max_seq + 1; lockdep_assert_held(&lruvec->lru_lock); if (!carryover && !clear) return; hist = lru_hist_from_seq(seq); for (tier = 0; tier < MAX_NR_TIERS; tier++) { if (carryover) { unsigned long sum; sum = lrugen->avg_refaulted[type][tier] + atomic_long_read(&lrugen->refaulted[hist][type][tier]); WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2); sum = lrugen->avg_total[type][tier] + atomic_long_read(&lrugen->evicted[hist][type][tier]); if (tier) sum += lrugen->protected[hist][type][tier - 1]; WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2); } if (clear) { atomic_long_set(&lrugen->refaulted[hist][type][tier], 0); atomic_long_set(&lrugen->evicted[hist][type][tier], 0); if (tier) WRITE_ONCE(lrugen->protected[hist][type][tier - 1], 0); } } } static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv) { /* * Return true if the PV has a limited number of refaults or a lower * refaulted/total than the SP. */ return pv->refaulted < MIN_LRU_BATCH || pv->refaulted * (sp->total + MIN_LRU_BATCH) * sp->gain <= (sp->refaulted + 1) * pv->total * pv->gain; } /****************************************************************************** * the aging ******************************************************************************/ /* promote pages accessed through page tables */ static int folio_update_gen(struct folio *folio, int gen) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(!rcu_read_lock_held()); do { /* lru_gen_del_folio() has isolated this page? */ if (!(old_flags & LRU_GEN_MASK)) { /* for shrink_folio_list() */ new_flags = old_flags | BIT(PG_referenced); continue; } new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS); new_flags |= (gen + 1UL) << LRU_GEN_PGOFF; } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } /* protect pages accessed multiple times through file descriptors */ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { int type = folio_is_file_lru(folio); struct lru_gen_struct *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE_FOLIO(!(old_flags & LRU_GEN_MASK), folio); do { new_gen = ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; /* folio_update_gen() has promoted this page? */ if (new_gen >= 0 && new_gen != old_gen) return new_gen; new_gen = (old_gen + 1) % MAX_NR_GENS; new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS); new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF; /* for folio_end_writeback() */ if (reclaiming) new_flags |= BIT(PG_reclaim); } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); lru_gen_update_size(lruvec, folio, old_gen, new_gen); return new_gen; } static void update_batch_size(struct lru_gen_mm_walk *walk, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE(old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen >= MAX_NR_GENS); walk->batched++; walk->nr_pages[old_gen][type][zone] -= delta; walk->nr_pages[new_gen][type][zone] += delta; } static void reset_batch_size(struct lruvec *lruvec, struct lru_gen_mm_walk *walk) { int gen, type, zone; struct lru_gen_struct *lrugen = &lruvec->lrugen; walk->batched = 0; for_each_gen_type_zone(gen, type, zone) { enum lru_list lru = type * LRU_INACTIVE_FILE; int delta = walk->nr_pages[gen][type][zone]; if (!delta) continue; walk->nr_pages[gen][type][zone] = 0; WRITE_ONCE(lrugen->nr_pages[gen][type][zone], lrugen->nr_pages[gen][type][zone] + delta); if (lru_gen_is_active(lruvec, gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); } } static int should_skip_vma(unsigned long start, unsigned long end, struct mm_walk *args) { struct address_space *mapping; struct vm_area_struct *vma = args->vma; struct lru_gen_mm_walk *walk = args->private; if (!vma_is_accessible(vma)) return true; if (is_vm_hugetlb_page(vma)) return true; if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL | VM_SEQ_READ | VM_RAND_READ)) return true; if (vma == get_gate_vma(vma->vm_mm)) return true; if (vma_is_anonymous(vma)) return !walk->can_swap; if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping)) return true; mapping = vma->vm_file->f_mapping; if (mapping_unevictable(mapping)) return true; if (shmem_mapping(mapping)) return !walk->can_swap; /* to exclude special mappings like dax, etc. */ return !mapping->a_ops->read_folio; } /* * Some userspace memory allocators map many single-page VMAs. Instead of * returning back to the PGD table for each of such VMAs, finish an entire PMD * table to reduce zigzags and improve cache performance. */ static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk *args, unsigned long *vm_start, unsigned long *vm_end) { unsigned long start = round_up(*vm_end, size); unsigned long end = (start | ~mask) + 1; VMA_ITERATOR(vmi, args->mm, start); VM_WARN_ON_ONCE(mask & size); VM_WARN_ON_ONCE((start & mask) != (*vm_start & mask)); for_each_vma(vmi, args->vma) { if (end && end <= args->vma->vm_start) return false; if (should_skip_vma(args->vma->vm_start, args->vma->vm_end, args)) continue; *vm_start = max(start, args->vma->vm_start); *vm_end = min(end - 1, args->vma->vm_end - 1) + 1; return true; } return false; } static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr) { unsigned long pfn = pte_pfn(pte); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pte_present(pte) || is_zero_pfn(pfn)) return -1; if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte))) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; return pfn; } #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr) { unsigned long pfn = pmd_pfn(pmd); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pmd_present(pmd) || is_huge_zero_pmd(pmd)) return -1; if (WARN_ON_ONCE(pmd_devmap(pmd))) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; return pfn; } #endif static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, struct pglist_data *pgdat, bool can_swap) { struct folio *folio; /* try to avoid unnecessary memory loads */ if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) return NULL; folio = pfn_folio(pfn); if (folio_nid(folio) != pgdat->node_id) return NULL; if (folio_memcg_rcu(folio) != memcg) return NULL; /* file VMAs can contain anon pages from COW */ if (!folio_is_file_lru(folio) && !can_swap) return NULL; return folio; } static bool suitable_to_scan(int total, int young) { int n = clamp_t(int, cache_line_size() / sizeof(pte_t), 2, 8); /* suitable if the average number of young PTEs per cacheline is >=1 */ return young * n >= total; } static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pte_t *pte; spinlock_t *ptl; unsigned long addr; int total = 0; int young = 0; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); int old_gen, new_gen = lru_gen_from_seq(walk->max_seq); VM_WARN_ON_ONCE(pmd_leaf(*pmd)); ptl = pte_lockptr(args->mm, pmd); if (!spin_trylock(ptl)) return false; arch_enter_lazy_mmu_mode(); pte = pte_offset_map(pmd, start & PMD_MASK); restart: for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; struct folio *folio; total++; walk->mm_stats[MM_LEAF_TOTAL]++; pfn = get_pte_pfn(pte[i], args->vma, addr); if (pfn == -1) continue; if (!pte_young(pte[i])) { walk->mm_stats[MM_LEAF_OLD]++; continue; } folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) continue; if (!ptep_test_and_clear_young(args->vma, addr, pte + i)) VM_WARN_ON_ONCE(true); young++; walk->mm_stats[MM_LEAF_YOUNG]++; if (pte_dirty(pte[i]) && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); } if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end)) goto restart; pte_unmap(pte); arch_leave_lazy_mmu_mode(); spin_unlock(ptl); return suitable_to_scan(total, young); } #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) static void walk_pmd_range_locked(pud_t *pud, unsigned long next, struct vm_area_struct *vma, struct mm_walk *args, unsigned long *bitmap, unsigned long *start) { int i; pmd_t *pmd; spinlock_t *ptl; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); int old_gen, new_gen = lru_gen_from_seq(walk->max_seq); VM_WARN_ON_ONCE(pud_leaf(*pud)); /* try to batch at most 1+MIN_LRU_BATCH+1 entries */ if (*start == -1) { *start = next; return; } i = next == -1 ? 0 : pmd_index(next) - pmd_index(*start); if (i && i <= MIN_LRU_BATCH) { __set_bit(i - 1, bitmap); return; } pmd = pmd_offset(pud, *start); ptl = pmd_lockptr(args->mm, pmd); if (!spin_trylock(ptl)) goto done; arch_enter_lazy_mmu_mode(); do { unsigned long pfn; struct folio *folio; unsigned long addr = i ? (*start & PMD_MASK) + i * PMD_SIZE : *start; pfn = get_pmd_pfn(pmd[i], vma, addr); if (pfn == -1) goto next; if (!pmd_trans_huge(pmd[i])) { if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG)) pmdp_test_and_clear_young(vma, addr, pmd + i); goto next; } folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) goto next; if (!pmdp_test_and_clear_young(vma, addr, pmd + i)) goto next; walk->mm_stats[MM_LEAF_YOUNG]++; if (pmd_dirty(pmd[i]) && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); next: i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1; } while (i <= MIN_LRU_BATCH); arch_leave_lazy_mmu_mode(); spin_unlock(ptl); done: *start = -1; bitmap_zero(bitmap, MIN_LRU_BATCH); } #else static void walk_pmd_range_locked(pud_t *pud, unsigned long next, struct vm_area_struct *vma, struct mm_walk *args, unsigned long *bitmap, unsigned long *start) { } #endif static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pmd_t *pmd; unsigned long next; unsigned long addr; struct vm_area_struct *vma; unsigned long pos = -1; struct lru_gen_mm_walk *walk = args->private; unsigned long bitmap[BITS_TO_LONGS(MIN_LRU_BATCH)] = {}; VM_WARN_ON_ONCE(pud_leaf(*pud)); /* * Finish an entire PMD in two passes: the first only reaches to PTE * tables to avoid taking the PMD lock; the second, if necessary, takes * the PMD lock to clear the accessed bit in PMD entries. */ pmd = pmd_offset(pud, start & PUD_MASK); restart: /* walk_pte_range() may call get_next_vma() */ vma = args->vma; for (i = pmd_index(start), addr = start; addr != end; i++, addr = next) { pmd_t val = pmd_read_atomic(pmd + i); /* for pmd_read_atomic() */ barrier(); next = pmd_addr_end(addr, end); if (!pmd_present(val) || is_huge_zero_pmd(val)) { walk->mm_stats[MM_LEAF_TOTAL]++; continue; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(val)) { unsigned long pfn = pmd_pfn(val); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); walk->mm_stats[MM_LEAF_TOTAL]++; if (!pmd_young(val)) { walk->mm_stats[MM_LEAF_OLD]++; continue; } /* try to avoid unnecessary memory loads */ if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) continue; walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos); continue; } #endif walk->mm_stats[MM_NONLEAF_TOTAL]++; if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG)) { if (!pmd_young(val)) continue; walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos); } if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i)) continue; walk->mm_stats[MM_NONLEAF_FOUND]++; if (!walk_pte_range(&val, addr, next, args)) continue; walk->mm_stats[MM_NONLEAF_ADDED]++; /* carry over to the next generation */ update_bloom_filter(walk->lruvec, walk->max_seq + 1, pmd + i); } walk_pmd_range_locked(pud, -1, vma, args, bitmap, &pos); if (i < PTRS_PER_PMD && get_next_vma(PUD_MASK, PMD_SIZE, args, &start, &end)) goto restart; } static int walk_pud_range(p4d_t *p4d, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pud_t *pud; unsigned long addr; unsigned long next; struct lru_gen_mm_walk *walk = args->private; VM_WARN_ON_ONCE(p4d_leaf(*p4d)); pud = pud_offset(p4d, start & P4D_MASK); restart: for (i = pud_index(start), addr = start; addr != end; i++, addr = next) { pud_t val = READ_ONCE(pud[i]); next = pud_addr_end(addr, end); if (!pud_present(val) || WARN_ON_ONCE(pud_leaf(val))) continue; walk_pmd_range(&val, addr, next, args); /* a racy check to curtail the waiting time */ if (wq_has_sleeper(&walk->lruvec->mm_state.wait)) return 1; if (need_resched() || walk->batched >= MAX_LRU_BATCH) { end = (addr | ~PUD_MASK) + 1; goto done; } } if (i < PTRS_PER_PUD && get_next_vma(P4D_MASK, PUD_SIZE, args, &start, &end)) goto restart; end = round_up(end, P4D_SIZE); done: if (!end || !args->vma) return 1; walk->next_addr = max(end, args->vma->vm_start); return -EAGAIN; } static void walk_mm(struct lruvec *lruvec, struct mm_struct *mm, struct lru_gen_mm_walk *walk) { static const struct mm_walk_ops mm_walk_ops = { .test_walk = should_skip_vma, .p4d_entry = walk_pud_range, }; int err; struct mem_cgroup *memcg = lruvec_memcg(lruvec); walk->next_addr = FIRST_USER_ADDRESS; do { err = -EBUSY; /* folio_update_gen() requires stable folio_memcg() */ if (!mem_cgroup_trylock_pages(memcg)) break; /* the caller might be holding the lock for write */ if (mmap_read_trylock(mm)) { err = walk_page_range(mm, walk->next_addr, ULONG_MAX, &mm_walk_ops, walk); mmap_read_unlock(mm); } mem_cgroup_unlock_pages(); if (walk->batched) { spin_lock_irq(&lruvec->lru_lock); reset_batch_size(lruvec, walk); spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while (err == -EAGAIN); } static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; if (pgdat && current_is_kswapd()) { VM_WARN_ON_ONCE(walk); walk = &pgdat->mm_walk; } else if (!pgdat && !walk) { VM_WARN_ON_ONCE(current_is_kswapd()); walk = kzalloc(sizeof(*walk), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); } current->reclaim_state->mm_walk = walk; return walk; } static void clear_mm_walk(void) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; VM_WARN_ON_ONCE(walk && memchr_inv(walk->nr_pages, 0, sizeof(walk->nr_pages))); VM_WARN_ON_ONCE(walk && memchr_inv(walk->mm_stats, 0, sizeof(walk->mm_stats))); current->reclaim_state->mm_walk = NULL; if (!current_is_kswapd()) kfree(walk); } static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap) { int zone; int remaining = MAX_LRU_BATCH; struct lru_gen_struct *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); if (type == LRU_GEN_ANON && !can_swap) goto done; /* prevent cold/hot inversion if force_scan is true */ for (zone = 0; zone < MAX_NR_ZONES; zone++) { struct list_head *head = &lrugen->lists[old_gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); new_gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->lists[new_gen][type][zone]); if (!--remaining) return false; } } done: reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1); return true; } static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap) { int gen, type, zone; bool success = false; struct lru_gen_struct *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); /* find the oldest populated generation */ for (type = !can_swap; type < ANON_AND_FILE; type++) { while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) { gen = lru_gen_from_seq(min_seq[type]); for (zone = 0; zone < MAX_NR_ZONES; zone++) { if (!list_empty(&lrugen->lists[gen][type][zone])) goto next; } min_seq[type]++; } next: ; } /* see the comment on lru_gen_struct */ if (can_swap) { min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]); min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]); } for (type = !can_swap; type < ANON_AND_FILE; type++) { if (min_seq[type] == lrugen->min_seq[type]) continue; reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], min_seq[type]); success = true; } return success; } static void inc_max_seq(struct lruvec *lruvec, bool can_swap, bool force_scan) { int prev, next; int type, zone; struct lru_gen_struct *lrugen = &lruvec->lrugen; spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); for (type = ANON_AND_FILE - 1; type >= 0; type--) { if (get_nr_gens(lruvec, type) != MAX_NR_GENS) continue; VM_WARN_ON_ONCE(!force_scan && (type == LRU_GEN_FILE || can_swap)); while (!inc_min_seq(lruvec, type, can_swap)) { spin_unlock_irq(&lruvec->lru_lock); cond_resched(); spin_lock_irq(&lruvec->lru_lock); } } /* * Update the active/inactive LRU sizes for compatibility. Both sides of * the current max_seq need to be covered, since max_seq+1 can overlap * with min_seq[LRU_GEN_ANON] if swapping is constrained. And if they do * overlap, cold/hot inversion happens. */ prev = lru_gen_from_seq(lrugen->max_seq - 1); next = lru_gen_from_seq(lrugen->max_seq + 1); for (type = 0; type < ANON_AND_FILE; type++) { for (zone = 0; zone < MAX_NR_ZONES; zone++) { enum lru_list lru = type * LRU_INACTIVE_FILE; long delta = lrugen->nr_pages[prev][type][zone] - lrugen->nr_pages[next][type][zone]; if (!delta) continue; __update_lru_size(lruvec, lru, zone, delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, -delta); } } for (type = 0; type < ANON_AND_FILE; type++) reset_ctrl_pos(lruvec, type, false); WRITE_ONCE(lrugen->timestamps[next], jiffies); /* make sure preceding modifications appear */ smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1); spin_unlock_irq(&lruvec->lru_lock); } static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq, struct scan_control *sc, bool can_swap, bool force_scan) { bool success; struct lru_gen_mm_walk *walk; struct mm_struct *mm = NULL; struct lru_gen_struct *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(max_seq > READ_ONCE(lrugen->max_seq)); /* see the comment in iterate_mm_list() */ if (max_seq <= READ_ONCE(lruvec->mm_state.seq)) { success = false; goto done; } /* * If the hardware doesn't automatically set the accessed bit, fallback * to lru_gen_look_around(), which only clears the accessed bit in a * handful of PTEs. Spreading the work out over a period of time usually * is less efficient, but it avoids bursty page faults. */ if (!force_scan && !(arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))) { success = iterate_mm_list_nowalk(lruvec, max_seq); goto done; } walk = set_mm_walk(NULL); if (!walk) { success = iterate_mm_list_nowalk(lruvec, max_seq); goto done; } walk->lruvec = lruvec; walk->max_seq = max_seq; walk->can_swap = can_swap; walk->force_scan = force_scan; do { success = iterate_mm_list(lruvec, walk, &mm); if (mm) walk_mm(lruvec, mm, walk); cond_resched(); } while (mm); done: if (!success) { if (sc->priority <= DEF_PRIORITY - 2) wait_event_killable(lruvec->mm_state.wait, max_seq < READ_ONCE(lrugen->max_seq)); return max_seq < READ_ONCE(lrugen->max_seq); } VM_WARN_ON_ONCE(max_seq != READ_ONCE(lrugen->max_seq)); inc_max_seq(lruvec, can_swap, force_scan); /* either this sees any waiters or they will see updated max_seq */ if (wq_has_sleeper(&lruvec->mm_state.wait)) wake_up_all(&lruvec->mm_state.wait); return true; } static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, unsigned long *min_seq, struct scan_control *sc, bool can_swap, unsigned long *nr_to_scan) { int gen, type, zone; unsigned long old = 0; unsigned long young = 0; unsigned long total = 0; struct lru_gen_struct *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); for (type = !can_swap; type < ANON_AND_FILE; type++) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { unsigned long size = 0; gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); total += size; if (seq == max_seq) young += size; else if (seq + MIN_NR_GENS == max_seq) old += size; } } /* try to scrape all its memory if this memcg was deleted */ *nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total; /* * The aging tries to be lazy to reduce the overhead, while the eviction * stalls when the number of generations reaches MIN_NR_GENS. Hence, the * ideal number of generations is MIN_NR_GENS+1. */ if (min_seq[!can_swap] + MIN_NR_GENS > max_seq) return true; if (min_seq[!can_swap] + MIN_NR_GENS < max_seq) return false; /* * It's also ideal to spread pages out evenly, i.e., 1/(MIN_NR_GENS+1) * of the total number of pages for each generation. A reasonable range * for this average portion is [1/MIN_NR_GENS, 1/(MIN_NR_GENS+2)]. The * aging cares about the upper bound of hot pages, while the eviction * cares about the lower bound of cold pages. */ if (young * MIN_NR_GENS > total) return true; if (old * (MIN_NR_GENS + 2) < total) return true; return false; } static bool age_lruvec(struct lruvec *lruvec, struct scan_control *sc, unsigned long min_ttl) { bool need_aging; unsigned long nr_to_scan; int swappiness = get_swappiness(lruvec, sc); struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); VM_WARN_ON_ONCE(sc->memcg_low_reclaim); mem_cgroup_calculate_protection(NULL, memcg); if (mem_cgroup_below_min(memcg)) return false; need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, swappiness, &nr_to_scan); if (min_ttl) { int gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]); unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); if (time_is_after_jiffies(birth + min_ttl)) return false; /* the size is likely too small to be helpful */ if (!nr_to_scan && sc->priority != DEF_PRIORITY) return false; } if (need_aging) try_to_inc_max_seq(lruvec, max_seq, sc, swappiness, false); return true; } /* to protect the working set of the last N jiffies */ static unsigned long lru_gen_min_ttl __read_mostly; static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; bool success = false; unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl); VM_WARN_ON_ONCE(!current_is_kswapd()); sc->last_reclaimed = sc->nr_reclaimed; /* * To reduce the chance of going into the aging path, which can be * costly, optimistically skip it if the flag below was cleared in the * eviction path. This improves the overall performance when multiple * memcgs are available. */ if (!sc->memcgs_need_aging) { sc->memcgs_need_aging = true; return; } set_mm_walk(pgdat); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); if (age_lruvec(lruvec, sc, min_ttl)) success = true; cond_resched(); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); clear_mm_walk(); /* check the order to exclude compaction-induced reclaim */ if (success || !min_ttl || sc->order) return; /* * The main goal is to OOM kill if every generation from all memcgs is * younger than min_ttl. However, another possibility is all memcgs are * either below min or empty. */ if (mutex_trylock(&oom_lock)) { struct oom_control oc = { .gfp_mask = sc->gfp_mask, }; out_of_memory(&oc); mutex_unlock(&oom_lock); } } /* * This function exploits spatial locality when shrink_folio_list() walks the * rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages. If * the scan was done cacheline efficiently, it adds the PMD entry pointing to * the PTE table to the Bloom filter. This forms a feedback loop between the * eviction and the aging. */ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { int i; pte_t *pte; unsigned long start; unsigned long end; unsigned long addr; struct lru_gen_mm_walk *walk; int young = 0; unsigned long bitmap[BITS_TO_LONGS(MIN_LRU_BATCH)] = {}; struct folio *folio = pfn_folio(pvmw->pfn); struct mem_cgroup *memcg = folio_memcg(folio); struct pglist_data *pgdat = folio_pgdat(folio); struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); DEFINE_MAX_SEQ(lruvec); int old_gen, new_gen = lru_gen_from_seq(max_seq); lockdep_assert_held(pvmw->ptl); VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); if (spin_is_contended(pvmw->ptl)) return; /* avoid taking the LRU lock under the PTL when possible */ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; start = max(pvmw->address & PMD_MASK, pvmw->vma->vm_start); end = min(pvmw->address | ~PMD_MASK, pvmw->vma->vm_end - 1) + 1; if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { if (pvmw->address - start < MIN_LRU_BATCH * PAGE_SIZE / 2) end = start + MIN_LRU_BATCH * PAGE_SIZE; else if (end - pvmw->address < MIN_LRU_BATCH * PAGE_SIZE / 2) start = end - MIN_LRU_BATCH * PAGE_SIZE; else { start = pvmw->address - MIN_LRU_BATCH * PAGE_SIZE / 2; end = pvmw->address + MIN_LRU_BATCH * PAGE_SIZE / 2; } } pte = pvmw->pte - (pvmw->address - start) / PAGE_SIZE; rcu_read_lock(); arch_enter_lazy_mmu_mode(); for (i = 0, addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; pfn = get_pte_pfn(pte[i], pvmw->vma, addr); if (pfn == -1) continue; if (!pte_young(pte[i])) continue; folio = get_pfn_folio(pfn, memcg, pgdat, !walk || walk->can_swap); if (!folio) continue; if (!ptep_test_and_clear_young(pvmw->vma, addr, pte + i)) VM_WARN_ON_ONCE(true); young++; if (pte_dirty(pte[i]) && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); old_gen = folio_lru_gen(folio); if (old_gen < 0) folio_set_referenced(folio); else if (old_gen != new_gen) __set_bit(i, bitmap); } arch_leave_lazy_mmu_mode(); rcu_read_unlock(); /* feedback from rmap walkers to page table walkers */ if (suitable_to_scan(i, young)) update_bloom_filter(lruvec, max_seq, pvmw->pmd); if (!walk && bitmap_weight(bitmap, MIN_LRU_BATCH) < PAGEVEC_SIZE) { for_each_set_bit(i, bitmap, MIN_LRU_BATCH) { folio = pfn_folio(pte_pfn(pte[i])); folio_activate(folio); } return; } /* folio_update_gen() requires stable folio_memcg() */ if (!mem_cgroup_trylock_pages(memcg)) return; if (!walk) { spin_lock_irq(&lruvec->lru_lock); new_gen = lru_gen_from_seq(lruvec->lrugen.max_seq); } for_each_set_bit(i, bitmap, MIN_LRU_BATCH) { folio = pfn_folio(pte_pfn(pte[i])); if (folio_memcg_rcu(folio) != memcg) continue; old_gen = folio_update_gen(folio, new_gen); if (old_gen < 0 || old_gen == new_gen) continue; if (walk) update_batch_size(walk, folio, old_gen, new_gen); else lru_gen_update_size(lruvec, folio, old_gen, new_gen); } if (!walk) spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_unlock_pages(); } /****************************************************************************** * the eviction ******************************************************************************/ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, int tier_idx) { bool success; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); int tier = lru_tier_from_refs(refs); struct lru_gen_struct *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio); /* unevictable */ if (!folio_evictable(folio)) { success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); folio_set_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGCULLED, delta); return true; } /* dirty lazyfree */ if (type == LRU_GEN_FILE && folio_test_anon(folio) && folio_test_dirty(folio)) { success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); folio_set_swapbacked(folio); lruvec_add_folio_tail(lruvec, folio); return true; } /* promoted */ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) { list_move(&folio->lru, &lrugen->lists[gen][type][zone]); return true; } /* protected */ if (tier > tier_idx) { int hist = lru_hist_from_seq(lrugen->min_seq[type]); gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->lists[gen][type][zone]); WRITE_ONCE(lrugen->protected[hist][type][tier - 1], lrugen->protected[hist][type][tier - 1] + delta); __mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta); return true; } /* waiting for writeback */ if (folio_test_locked(folio) || folio_test_writeback(folio) || (type == LRU_GEN_FILE && folio_test_dirty(folio))) { gen = folio_inc_gen(lruvec, folio, true); list_move(&folio->lru, &lrugen->lists[gen][type][zone]); return true; } return false; } static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc) { bool success; /* unmapping inhibited */ if (!sc->may_unmap && folio_mapped(folio)) return false; /* swapping inhibited */ if (!(sc->may_writepage && (sc->gfp_mask & __GFP_IO)) && (folio_test_dirty(folio) || (folio_test_anon(folio) && !folio_test_swapcache(folio)))) return false; /* raced with release_pages() */ if (!folio_try_get(folio)) return false; /* raced with another isolation */ if (!folio_test_clear_lru(folio)) { folio_put(folio); return false; } /* see the comment on MAX_NR_TIERS */ if (!folio_test_referenced(folio)) set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); /* for shrink_folio_list() */ folio_clear_reclaim(folio); folio_clear_referenced(folio); success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); return true; } static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, int type, int tier, struct list_head *list) { int gen, zone; enum vm_event_item item; int sorted = 0; int scanned = 0; int isolated = 0; int remaining = MAX_LRU_BATCH; struct lru_gen_struct *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); VM_WARN_ON_ONCE(!list_empty(list)); if (get_nr_gens(lruvec, type) == MIN_NR_GENS) return 0; gen = lru_gen_from_seq(lrugen->min_seq[type]); for (zone = sc->reclaim_idx; zone >= 0; zone--) { LIST_HEAD(moved); int skipped = 0; struct list_head *head = &lrugen->lists[gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); scanned += delta; if (sort_folio(lruvec, folio, tier)) sorted += delta; else if (isolate_folio(lruvec, folio, sc)) { list_add(&folio->lru, list); isolated += delta; } else { list_move(&folio->lru, &moved); skipped += delta; } if (!--remaining || max(isolated, skipped) >= MIN_LRU_BATCH) break; } if (skipped) { list_splice(&moved, head); __count_zid_vm_events(PGSCAN_SKIP, zone, skipped); } if (!remaining || isolated >= MIN_LRU_BATCH) break; } item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT; if (!cgroup_reclaim(sc)) { __count_vm_events(item, isolated); __count_vm_events(PGREFILL, sorted); } __count_memcg_events(memcg, item, isolated); __count_memcg_events(memcg, PGREFILL, sorted); __count_vm_events(PGSCAN_ANON + type, isolated); /* * There might not be eligible pages due to reclaim_idx, may_unmap and * may_writepage. Check the remaining to prevent livelock if it's not * making progress. */ return isolated || !remaining ? scanned : 0; } static int get_tier_idx(struct lruvec *lruvec, int type) { int tier; struct ctrl_pos sp, pv; /* * To leave a margin for fluctuations, use a larger gain factor (1:2). * This value is chosen because any other tier would have at least twice * as many refaults as the first tier. */ read_ctrl_pos(lruvec, type, 0, 1, &sp); for (tier = 1; tier < MAX_NR_TIERS; tier++) { read_ctrl_pos(lruvec, type, tier, 2, &pv); if (!positive_ctrl_err(&sp, &pv)) break; } return tier - 1; } static int get_type_to_scan(struct lruvec *lruvec, int swappiness, int *tier_idx) { int type, tier; struct ctrl_pos sp, pv; int gain[ANON_AND_FILE] = { swappiness, 200 - swappiness }; /* * Compare the first tier of anon with that of file to determine which * type to scan. Also need to compare other tiers of the selected type * with the first tier of the other type to determine the last tier (of * the selected type) to evict. */ read_ctrl_pos(lruvec, LRU_GEN_ANON, 0, gain[LRU_GEN_ANON], &sp); read_ctrl_pos(lruvec, LRU_GEN_FILE, 0, gain[LRU_GEN_FILE], &pv); type = positive_ctrl_err(&sp, &pv); read_ctrl_pos(lruvec, !type, 0, gain[!type], &sp); for (tier = 1; tier < MAX_NR_TIERS; tier++) { read_ctrl_pos(lruvec, type, tier, gain[type], &pv); if (!positive_ctrl_err(&sp, &pv)) break; } *tier_idx = tier - 1; return type; } static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness, int *type_scanned, struct list_head *list) { int i; int type; int scanned; int tier = -1; DEFINE_MIN_SEQ(lruvec); /* * Try to make the obvious choice first. When anon and file are both * available from the same generation, interpret swappiness 1 as file * first and 200 as anon first. */ if (!swappiness) type = LRU_GEN_FILE; else if (min_seq[LRU_GEN_ANON] < min_seq[LRU_GEN_FILE]) type = LRU_GEN_ANON; else if (swappiness == 1) type = LRU_GEN_FILE; else if (swappiness == 200) type = LRU_GEN_ANON; else type = get_type_to_scan(lruvec, swappiness, &tier); for (i = !swappiness; i < ANON_AND_FILE; i++) { if (tier < 0) tier = get_tier_idx(lruvec, type); scanned = scan_folios(lruvec, sc, type, tier, list); if (scanned) break; type = !type; tier = -1; } *type_scanned = type; return scanned; } static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness, bool *need_swapping) { int type; int scanned; int reclaimed; LIST_HEAD(list); LIST_HEAD(clean); struct folio *folio; struct folio *next; enum vm_event_item item; struct reclaim_stat stat; struct lru_gen_mm_walk *walk; bool skip_retry = false; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); spin_lock_irq(&lruvec->lru_lock); scanned = isolate_folios(lruvec, sc, swappiness, &type, &list); scanned += try_to_inc_min_seq(lruvec, swappiness); if (get_nr_gens(lruvec, !swappiness) == MIN_NR_GENS) scanned = 0; spin_unlock_irq(&lruvec->lru_lock); if (list_empty(&list)) return scanned; retry: reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false); sc->nr_reclaimed += reclaimed; list_for_each_entry_safe_reverse(folio, next, &list, lru) { if (!folio_evictable(folio)) { list_del(&folio->lru); folio_putback_lru(folio); continue; } if (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio))) { /* restore LRU_REFS_FLAGS cleared by isolate_folio() */ if (folio_test_workingset(folio)) folio_set_referenced(folio); continue; } if (skip_retry || folio_test_active(folio) || folio_test_referenced(folio) || folio_mapped(folio) || folio_test_locked(folio) || folio_test_dirty(folio) || folio_test_writeback(folio)) { /* don't add rejected folios to the oldest generation */ set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, BIT(PG_active)); continue; } /* retry folios that may have missed folio_rotate_reclaimable() */ list_move(&folio->lru, &clean); sc->nr_scanned -= folio_nr_pages(folio); } spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &list); walk = current->reclaim_state->mm_walk; if (walk && walk->batched) reset_batch_size(lruvec, walk); item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, reclaimed); __count_memcg_events(memcg, item, reclaimed); __count_vm_events(PGSTEAL_ANON + type, reclaimed); spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_list(&list); free_unref_page_list(&list); INIT_LIST_HEAD(&list); list_splice_init(&clean, &list); if (!list_empty(&list)) { skip_retry = true; goto retry; } if (need_swapping && type == LRU_GEN_ANON) *need_swapping = true; return scanned; } /* * For future optimizations: * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg * reclaim. */ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool can_swap, bool *need_aging) { unsigned long nr_to_scan; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); if (mem_cgroup_below_min(memcg) || (mem_cgroup_below_low(memcg) && !sc->memcg_low_reclaim)) return 0; *need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, can_swap, &nr_to_scan); if (!*need_aging) return nr_to_scan; /* skip the aging path at the default priority */ if (sc->priority == DEF_PRIORITY) goto done; /* leave the work to lru_gen_age_node() */ if (current_is_kswapd()) return 0; if (try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false)) return nr_to_scan; done: return min_seq[!can_swap] + MIN_NR_GENS <= max_seq ? nr_to_scan : 0; } static bool should_abort_scan(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc, bool need_swapping) { int i; DEFINE_MAX_SEQ(lruvec); if (!current_is_kswapd()) { /* age each memcg at most once to ensure fairness */ if (max_seq - seq > 1) return true; /* over-swapping can increase allocation latency */ if (sc->nr_reclaimed >= sc->nr_to_reclaim && need_swapping) return true; /* give this thread a chance to exit and free its memory */ if (fatal_signal_pending(current)) { sc->nr_reclaimed += MIN_LRU_BATCH; return true; } if (cgroup_reclaim(sc)) return false; } else if (sc->nr_reclaimed - sc->last_reclaimed < sc->nr_to_reclaim) return false; /* keep scanning at low priorities to ensure fairness */ if (sc->priority > DEF_PRIORITY - 2) return false; /* * A minimum amount of work was done under global memory pressure. For * kswapd, it may be overshooting. For direct reclaim, the allocation * may succeed if all suitable zones are somewhat safe. In either case, * it's better to stop now, and restart later if necessary. */ for (i = 0; i <= sc->reclaim_idx; i++) { unsigned long wmark; struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i; if (!managed_zone(zone)) continue; wmark = current_is_kswapd() ? high_wmark_pages(zone) : low_wmark_pages(zone); if (wmark > zone_page_state(zone, NR_FREE_PAGES)) return false; } sc->nr_reclaimed += MIN_LRU_BATCH; return true; } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { struct blk_plug plug; bool need_aging = false; bool need_swapping = false; unsigned long scanned = 0; unsigned long reclaimed = sc->nr_reclaimed; DEFINE_MAX_SEQ(lruvec); lru_add_drain(); blk_start_plug(&plug); set_mm_walk(lruvec_pgdat(lruvec)); while (true) { int delta; int swappiness; unsigned long nr_to_scan; if (sc->may_swap) swappiness = get_swappiness(lruvec, sc); else if (!cgroup_reclaim(sc) && get_swappiness(lruvec, sc)) swappiness = 1; else swappiness = 0; nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness, &need_aging); if (!nr_to_scan) goto done; delta = evict_folios(lruvec, sc, swappiness, &need_swapping); if (!delta) goto done; scanned += delta; if (scanned >= nr_to_scan) break; if (should_abort_scan(lruvec, max_seq, sc, need_swapping)) break; cond_resched(); } /* see the comment in lru_gen_age_node() */ if (sc->nr_reclaimed - reclaimed >= MIN_LRU_BATCH && !need_aging) sc->memcgs_need_aging = false; done: clear_mm_walk(); blk_finish_plug(&plug); } /****************************************************************************** * state change ******************************************************************************/ static bool __maybe_unused state_is_valid(struct lruvec *lruvec) { struct lru_gen_struct *lrugen = &lruvec->lrugen; if (lrugen->enabled) { enum lru_list lru; for_each_evictable_lru(lru) { if (!list_empty(&lruvec->lists[lru])) return false; } } else { int gen, type, zone; for_each_gen_type_zone(gen, type, zone) { if (!list_empty(&lrugen->lists[gen][type][zone])) return false; } } return true; } static bool fill_evictable(struct lruvec *lruvec) { enum lru_list lru; int remaining = MAX_LRU_BATCH; for_each_evictable_lru(lru) { int type = is_file_lru(lru); bool active = is_active_lru(lru); struct list_head *head = &lruvec->lists[lru]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio) != active, folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_lru_gen(folio) != -1, folio); lruvec_del_folio(lruvec, folio); success = lru_gen_add_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); if (!--remaining) return false; } } return true; } static bool drain_evictable(struct lruvec *lruvec) { int gen, type, zone; int remaining = MAX_LRU_BATCH; for_each_gen_type_zone(gen, type, zone) { struct list_head *head = &lruvec->lrugen.lists[gen][type][zone]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); success = lru_gen_del_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); lruvec_add_folio(lruvec, folio); if (!--remaining) return false; } } return true; } static void lru_gen_change_state(bool enabled) { static DEFINE_MUTEX(state_mutex); struct mem_cgroup *memcg; cgroup_lock(); cpus_read_lock(); get_online_mems(); mutex_lock(&state_mutex); if (enabled == lru_gen_enabled()) goto unlock; if (enabled) static_branch_enable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); else static_branch_disable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); if (!lruvec) continue; spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); VM_WARN_ON_ONCE(!state_is_valid(lruvec)); lruvec->lrugen.enabled = enabled; while (!(enabled ? fill_evictable(lruvec) : drain_evictable(lruvec))) { spin_unlock_irq(&lruvec->lru_lock); cond_resched(); spin_lock_irq(&lruvec->lru_lock); } spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); unlock: mutex_unlock(&state_mutex); put_online_mems(); cpus_read_unlock(); cgroup_unlock(); } /****************************************************************************** * sysfs interface ******************************************************************************/ static ssize_t show_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sprintf(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl))); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t store_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { unsigned int msecs; if (kstrtouint(buf, 0, &msecs)) return -EINVAL; WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs)); return len; } static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR( min_ttl_ms, 0644, show_min_ttl, store_min_ttl ); static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { unsigned int caps = 0; if (get_cap(LRU_GEN_CORE)) caps |= BIT(LRU_GEN_CORE); if (arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK)) caps |= BIT(LRU_GEN_MM_WALK); if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG)) caps |= BIT(LRU_GEN_NONLEAF_YOUNG); return snprintf(buf, PAGE_SIZE, "0x%04x\n", caps); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t store_enabled(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { int i; unsigned int caps; if (tolower(*buf) == 'n') caps = 0; else if (tolower(*buf) == 'y') caps = -1; else if (kstrtouint(buf, 0, &caps)) return -EINVAL; for (i = 0; i < NR_LRU_GEN_CAPS; i++) { bool enabled = caps & BIT(i); if (i == LRU_GEN_CORE) lru_gen_change_state(enabled); else if (enabled) static_branch_enable(&lru_gen_caps[i]); else static_branch_disable(&lru_gen_caps[i]); } return len; } static struct kobj_attribute lru_gen_enabled_attr = __ATTR( enabled, 0644, show_enabled, store_enabled ); static struct attribute *lru_gen_attrs[] = { &lru_gen_min_ttl_attr.attr, &lru_gen_enabled_attr.attr, NULL }; static struct attribute_group lru_gen_attr_group = { .name = "lru_gen", .attrs = lru_gen_attrs, }; /****************************************************************************** * debugfs interface ******************************************************************************/ static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos) { struct mem_cgroup *memcg; loff_t nr_to_skip = *pos; m->private = kvmalloc(PATH_MAX, GFP_KERNEL); if (!m->private) return ERR_PTR(-ENOMEM); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node_state(nid, N_MEMORY) { if (!nr_to_skip--) return get_lruvec(memcg, nid); } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); return NULL; } static void lru_gen_seq_stop(struct seq_file *m, void *v) { if (!IS_ERR_OR_NULL(v)) mem_cgroup_iter_break(NULL, lruvec_memcg(v)); kvfree(m->private); m->private = NULL; } static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos) { int nid = lruvec_pgdat(v)->node_id; struct mem_cgroup *memcg = lruvec_memcg(v); ++*pos; nid = next_memory_node(nid); if (nid == MAX_NUMNODES) { memcg = mem_cgroup_iter(NULL, memcg, NULL); if (!memcg) return NULL; nid = first_memory_node; } return get_lruvec(memcg, nid); } static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, unsigned long max_seq, unsigned long *min_seq, unsigned long seq) { int i; int type, tier; int hist = lru_hist_from_seq(seq); struct lru_gen_struct *lrugen = &lruvec->lrugen; for (tier = 0; tier < MAX_NR_TIERS; tier++) { seq_printf(m, " %10d", tier); for (type = 0; type < ANON_AND_FILE; type++) { const char *s = " "; unsigned long n[3] = {}; if (seq == max_seq) { s = "RT "; n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]); n[1] = READ_ONCE(lrugen->avg_total[type][tier]); } else if (seq == min_seq[type] || NR_HIST_GENS > 1) { s = "rep"; n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]); n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]); if (tier) n[2] = READ_ONCE(lrugen->protected[hist][type][tier - 1]); } for (i = 0; i < 3; i++) seq_printf(m, " %10lu%c", n[i], s[i]); } seq_putc(m, '\n'); } seq_puts(m, " "); for (i = 0; i < NR_MM_STATS; i++) { const char *s = " "; unsigned long n = 0; if (seq == max_seq && NR_HIST_GENS == 1) { s = "LOYNFA"; n = READ_ONCE(lruvec->mm_state.stats[hist][i]); } else if (seq != max_seq && NR_HIST_GENS > 1) { s = "loynfa"; n = READ_ONCE(lruvec->mm_state.stats[hist][i]); } seq_printf(m, " %10lu%c", n, s[i]); } seq_putc(m, '\n'); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static int lru_gen_seq_show(struct seq_file *m, void *v) { unsigned long seq; bool full = !debugfs_real_fops(m->file)->write; struct lruvec *lruvec = v; struct lru_gen_struct *lrugen = &lruvec->lrugen; int nid = lruvec_pgdat(lruvec)->node_id; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); if (nid == first_memory_node) { const char *path = memcg ? m->private : ""; #ifdef CONFIG_MEMCG if (memcg) cgroup_path(memcg->css.cgroup, m->private, PATH_MAX); #endif seq_printf(m, "memcg %5hu %s\n", mem_cgroup_id(memcg), path); } seq_printf(m, " node %5d\n", nid); if (!full) seq = min_seq[LRU_GEN_ANON]; else if (max_seq >= MAX_NR_GENS) seq = max_seq - MAX_NR_GENS + 1; else seq = 0; for (; seq <= max_seq; seq++) { int type, zone; int gen = lru_gen_from_seq(seq); unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); seq_printf(m, " %10lu %10u", seq, jiffies_to_msecs(jiffies - birth)); for (type = 0; type < ANON_AND_FILE; type++) { unsigned long size = 0; char mark = full && seq < min_seq[type] ? 'x' : ' '; for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); seq_printf(m, " %10lu%c", size, mark); } seq_putc(m, '\n'); if (full) lru_gen_seq_show_full(m, lruvec, max_seq, min_seq, seq); } return 0; } static const struct seq_operations lru_gen_seq_ops = { .start = lru_gen_seq_start, .stop = lru_gen_seq_stop, .next = lru_gen_seq_next, .show = lru_gen_seq_show, }; static int run_aging(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc, bool can_swap, bool force_scan) { DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); if (seq < max_seq) return 0; if (seq > max_seq) return -EINVAL; if (!force_scan && min_seq[!can_swap] + MAX_NR_GENS - 1 <= max_seq) return -ERANGE; try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, force_scan); return 0; } static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long nr_to_reclaim) { DEFINE_MAX_SEQ(lruvec); if (seq + MIN_NR_GENS > max_seq) return -EINVAL; sc->nr_reclaimed = 0; while (!signal_pending(current)) { DEFINE_MIN_SEQ(lruvec); if (seq < min_seq[!swappiness]) return 0; if (sc->nr_reclaimed >= nr_to_reclaim) return 0; if (!evict_folios(lruvec, sc, swappiness, NULL)) return 0; cond_resched(); } return -EINTR; } static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long opt) { struct lruvec *lruvec; int err = -EINVAL; struct mem_cgroup *memcg = NULL; if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY)) return -EINVAL; if (!mem_cgroup_disabled()) { rcu_read_lock(); memcg = mem_cgroup_from_id(memcg_id); #ifdef CONFIG_MEMCG if (memcg && !css_tryget(&memcg->css)) memcg = NULL; #endif rcu_read_unlock(); if (!memcg) return -EINVAL; } if (memcg_id != mem_cgroup_id(memcg)) goto done; lruvec = get_lruvec(memcg, nid); if (swappiness < 0) swappiness = get_swappiness(lruvec, sc); else if (swappiness > 200) goto done; switch (cmd) { case '+': err = run_aging(lruvec, seq, sc, swappiness, opt); break; case '-': err = run_eviction(lruvec, seq, sc, swappiness, opt); break; } done: mem_cgroup_put(memcg); return err; } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t lru_gen_seq_write(struct file *file, const char __user *src, size_t len, loff_t *pos) { void *buf; char *cur, *next; unsigned int flags; struct blk_plug plug; int err = -EINVAL; struct scan_control sc = { .may_writepage = true, .may_unmap = true, .may_swap = true, .reclaim_idx = MAX_NR_ZONES - 1, .gfp_mask = GFP_KERNEL, }; buf = kvmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; if (copy_from_user(buf, src, len)) { kvfree(buf); return -EFAULT; } set_task_reclaim_state(current, &sc.reclaim_state); flags = memalloc_noreclaim_save(); blk_start_plug(&plug); if (!set_mm_walk(NULL)) { err = -ENOMEM; goto done; } next = buf; next[len] = '\0'; while ((cur = strsep(&next, ",;\n"))) { int n; int end; char cmd; unsigned int memcg_id; unsigned int nid; unsigned long seq; unsigned int swappiness = -1; unsigned long opt = -1; cur = skip_spaces(cur); if (!*cur) continue; n = sscanf(cur, "%c %u %u %lu %n %u %n %lu %n", &cmd, &memcg_id, &nid, &seq, &end, &swappiness, &end, &opt, &end); if (n < 4 || cur[end]) { err = -EINVAL; break; } err = run_cmd(cmd, memcg_id, nid, seq, &sc, swappiness, opt); if (err) break; } done: clear_mm_walk(); blk_finish_plug(&plug); memalloc_noreclaim_restore(flags); set_task_reclaim_state(current, NULL); kvfree(buf); return err ? : len; } static int lru_gen_seq_open(struct inode *inode, struct file *file) { return seq_open(file, &lru_gen_seq_ops); } static const struct file_operations lru_gen_rw_fops = { .open = lru_gen_seq_open, .read = seq_read, .write = lru_gen_seq_write, .llseek = seq_lseek, .release = seq_release, }; static const struct file_operations lru_gen_ro_fops = { .open = lru_gen_seq_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; /****************************************************************************** * initialization ******************************************************************************/ void lru_gen_init_lruvec(struct lruvec *lruvec) { int i; int gen, type, zone; struct lru_gen_struct *lrugen = &lruvec->lrugen; lrugen->max_seq = MIN_NR_GENS + 1; lrugen->enabled = lru_gen_enabled(); for (i = 0; i <= MIN_NR_GENS + 1; i++) lrugen->timestamps[i] = jiffies; for_each_gen_type_zone(gen, type, zone) INIT_LIST_HEAD(&lrugen->lists[gen][type][zone]); lruvec->mm_state.seq = MIN_NR_GENS; init_waitqueue_head(&lruvec->mm_state.wait); } #ifdef CONFIG_MEMCG void lru_gen_init_memcg(struct mem_cgroup *memcg) { INIT_LIST_HEAD(&memcg->mm_list.fifo); spin_lock_init(&memcg->mm_list.lock); } void lru_gen_exit_memcg(struct mem_cgroup *memcg) { int i; int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0, sizeof(lruvec->lrugen.nr_pages))); for (i = 0; i < NR_BLOOM_FILTERS; i++) { bitmap_free(lruvec->mm_state.filters[i]); lruvec->mm_state.filters[i] = NULL; } } } #endif static int __init init_lru_gen(void) { BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS); BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS); if (sysfs_create_group(mm_kobj, &lru_gen_attr_group)) pr_err("lru_gen: failed to create sysfs group\n"); debugfs_create_file("lru_gen", 0644, NULL, NULL, &lru_gen_rw_fops); debugfs_create_file("lru_gen_full", 0444, NULL, NULL, &lru_gen_ro_fops); return 0; }; late_initcall(init_lru_gen); #else /* !CONFIG_LRU_GEN */ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { } #endif /* CONFIG_LRU_GEN */ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; enum lru_list lru; unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; bool proportional_reclaim; struct blk_plug plug; if (lru_gen_enabled()) { lru_gen_shrink_lruvec(lruvec, sc); return; } get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); /* * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal * event that can occur when there is little memory pressure e.g. * multiple streaming readers/writers. Hence, we do not abort scanning * when the requested number of pages are reclaimed when scanning at * DEF_PRIORITY on the assumption that the fact we are direct * reclaiming implies that kswapd is not keeping up and it is best to * do a batch of work at once. For memcg reclaim one check is made to * abort proportional reclaim if either the file or anon lru has already * dropped to zero at the first pass. */ proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() && sc->priority == DEF_PRIORITY); blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { unsigned long nr_anon, nr_file, percentage; unsigned long nr_scanned; for_each_evictable_lru(lru) { if (nr[lru]) { nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, lruvec, sc); } } cond_resched(); if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) continue; /* * For kswapd and memcg, reclaim at least the number of pages * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. */ nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; /* * It's just vindictive to attack the larger once the smaller * has gone to zero. And given the way we stop scanning the * smaller below, this makes sure that we only make one nudge * towards proportionality once we've got nr_to_reclaim. */ if (!nr_file || !nr_anon) break; if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; lru = LRU_BASE; percentage = nr_anon * 100 / scan_target; } else { unsigned long scan_target = targets[LRU_INACTIVE_FILE] + targets[LRU_ACTIVE_FILE] + 1; lru = LRU_FILE; percentage = nr_file * 100 / scan_target; } /* Stop scanning the smaller of the LRU */ nr[lru] = 0; nr[lru + LRU_ACTIVE] = 0; /* * Recalculate the other LRU scan count based on its original * scan target and the percentage scanning already complete */ lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); lru += LRU_ACTIVE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); } blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; /* * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ if (can_age_anon_pages(lruvec_pgdat(lruvec), sc) && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { if (IS_ENABLED(CONFIG_COMPACTION) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; return false; } /* * Reclaim/compaction is used for high-order allocation requests. It reclaims * order-0 pages before compacting the zone. should_continue_reclaim() returns * true if more pages should be reclaimed such that when the page allocator * calls try_to_compact_pages() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ static inline bool should_continue_reclaim(struct pglist_data *pgdat, unsigned long nr_reclaimed, struct scan_control *sc) { unsigned long pages_for_compaction; unsigned long inactive_lru_pages; int z; /* If not in reclaim/compaction mode, stop */ if (!in_reclaim_compaction(sc)) return false; /* * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX * number of pages that were scanned. This will return to the caller * with the risk reclaim/compaction and the resulting allocation attempt * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL * allocations through requiring that the full LRU list has been scanned * first, by assuming that zero delta of sc->nr_scanned means full LRU * scan, but that approximation was wrong, and there were corner cases * where always a non-zero amount of pages were scanned. */ if (!nr_reclaimed) return false; /* If compaction would go ahead or the allocation would succeed, stop */ for (z = 0; z <= sc->reclaim_idx; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) { case COMPACT_SUCCESS: case COMPACT_CONTINUE: return false; default: /* check next zone */ ; } } /* * If we have not reclaimed enough pages for compaction and the * inactive lists are large enough, continue reclaiming */ pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); return inactive_lru_pages > pages_for_compaction; } static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) { struct mem_cgroup *target_memcg = sc->target_mem_cgroup; struct mem_cgroup *memcg; memcg = mem_cgroup_iter(target_memcg, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); unsigned long reclaimed; unsigned long scanned; /* * This loop can become CPU-bound when target memcgs * aren't eligible for reclaim - either because they * don't have any reclaimable pages, or because their * memory is explicitly protected. Avoid soft lockups. */ cond_resched(); mem_cgroup_calculate_protection(target_memcg, memcg); if (mem_cgroup_below_min(memcg)) { /* * Hard protection. * If there is no reclaimable memory, OOM. */ continue; } else if (mem_cgroup_below_low(memcg)) { /* * Soft protection. * Respect the protection only as long as * there is an unprotected supply * of reclaimable memory from other cgroups. */ if (!sc->memcg_low_reclaim) { sc->memcg_low_skipped = 1; continue; } memcg_memory_event(memcg, MEMCG_LOW); } reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); /* Record the group's reclaim efficiency */ if (!sc->proactive) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); } while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL))); } static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long nr_reclaimed, nr_scanned; struct lruvec *target_lruvec; bool reclaimable = false; target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); again: memset(&sc->nr, 0, sizeof(sc->nr)); nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; prepare_scan_count(pgdat, sc); shrink_node_memcgs(pgdat, sc); if (reclaim_state) { sc->nr_reclaimed += reclaim_state->reclaimed_slab; reclaim_state->reclaimed_slab = 0; } /* Record the subtree's reclaim efficiency */ if (!sc->proactive) vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, sc->nr_scanned - nr_scanned, sc->nr_reclaimed - nr_reclaimed); if (sc->nr_reclaimed - nr_reclaimed) reclaimable = true; if (current_is_kswapd()) { /* * If reclaim is isolating dirty pages under writeback, * it implies that the long-lived page allocation rate * is exceeding the page laundering rate. Either the * global limits are not being effective at throttling * processes due to the page distribution throughout * zones or there is heavy usage of a slow backing * device. The only option is to throttle from reclaim * context which is not ideal as there is no guarantee * the dirtying process is throttled in the same way * balance_dirty_pages() manages. * * Once a node is flagged PGDAT_WRITEBACK, kswapd will * count the number of pages under pages flagged for * immediate reclaim and stall if any are encountered * in the nr_immediate check below. */ if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken) set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* Allow kswapd to start writing pages during reclaim.*/ if (sc->nr.unqueued_dirty == sc->nr.file_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); /* * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU * faster than they are written so forcibly stall * until some pages complete writeback. */ if (sc->nr.immediate) reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } /* * Tag a node/memcg as congested if all the dirty pages were marked * for writeback and immediate reclaim (counted in nr.congested). * * Legacy memcg will stall in page writeback so avoid forcibly * stalling in reclaim_throttle(). */ if ((current_is_kswapd() || (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) && sc->nr.dirty && sc->nr.dirty == sc->nr.congested) set_bit(LRUVEC_CONGESTED, &target_lruvec->flags); /* * Stall direct reclaim for IO completions if the lruvec is * node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED); if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc)) goto again; /* * Kswapd gives up on balancing particular nodes after too * many failures to reclaim anything from them and goes to * sleep. On reclaim progress, reset the failure counter. A * successful direct reclaim run will revive a dormant kswapd. */ if (reclaimable) pgdat->kswapd_failures = 0; } /* * Returns true if compaction should go ahead for a costly-order request, or * the allocation would already succeed without compaction. Return false if we * should reclaim first. */ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) { unsigned long watermark; enum compact_result suitable; suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx); if (suitable == COMPACT_SUCCESS) /* Allocation should succeed already. Don't reclaim. */ return true; if (suitable == COMPACT_SKIPPED) /* Compaction cannot yet proceed. Do reclaim. */ return false; /* * Compaction is already possible, but it takes time to run and there * are potentially other callers using the pages just freed. So proceed * with reclaim to make a buffer of free pages available to give * compaction a reasonable chance of completing and allocating the page. * Note that we won't actually reclaim the whole buffer in one attempt * as the target watermark in should_continue_reclaim() is lower. But if * we are already above the high+gap watermark, don't reclaim at all. */ watermark = high_wmark_pages(zone) + compact_gap(sc->order); return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); } static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) { /* * If reclaim is making progress greater than 12% efficiency then * wake all the NOPROGRESS throttled tasks. */ if (sc->nr_reclaimed > (sc->nr_scanned >> 3)) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS]; if (waitqueue_active(wqh)) wake_up(wqh); return; } /* * Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will * throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages * under writeback and marked for immediate reclaim at the tail of the * LRU. */ if (current_is_kswapd() || cgroup_reclaim(sc)) return; /* Throttle if making no progress at high prioities. */ if (sc->priority == 1 && !sc->nr_reclaimed) reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS); } /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation * request. * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. */ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; gfp_t orig_mask; pg_data_t *last_pgdat = NULL; pg_data_t *first_pgdat = NULL; /* * If the number of buffer_heads in the machine exceeds the maximum * allowed level, force direct reclaim to scan the highmem zone as * highmem pages could be pinning lowmem pages storing buffer_heads */ orig_mask = sc->gfp_mask; if (buffer_heads_over_limit) { sc->gfp_mask |= __GFP_HIGHMEM; sc->reclaim_idx = gfp_zone(sc->gfp_mask); } for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { /* * Take care memory controller reclaiming has small influence * to global LRU. */ if (!cgroup_reclaim(sc)) { if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) continue; /* * If we already have plenty of memory free for * compaction in this zone, don't free any more. * Even though compaction is invoked for any * non-zero order, only frequent costly order * reclamation is disruptive enough to become a * noticeable problem, like transparent huge * page allocations. */ if (IS_ENABLED(CONFIG_COMPACTION) && sc->order > PAGE_ALLOC_COSTLY_ORDER && compaction_ready(zone, sc)) { sc->compaction_ready = true; continue; } /* * Shrink each node in the zonelist once. If the * zonelist is ordered by zone (not the default) then a * node may be shrunk multiple times but in that case * the user prefers lower zones being preserved. */ if (zone->zone_pgdat == last_pgdat) continue; /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and * scanned pages. This works for global memory pressure * and balancing, not for a memcg's limit. */ nr_soft_scanned = 0; nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone->zone_pgdat, sc->order, sc->gfp_mask, &nr_soft_scanned); sc->nr_reclaimed += nr_soft_reclaimed; sc->nr_scanned += nr_soft_scanned; /* need some check for avoid more shrink_zone() */ } if (!first_pgdat) first_pgdat = zone->zone_pgdat; /* See comment about same check for global reclaim above */ if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); } if (first_pgdat) consider_reclaim_throttle(first_pgdat, sc); /* * Restore to original mask to avoid the impact on the caller if we * promoted it to __GFP_HIGHMEM. */ sc->gfp_mask = orig_mask; } static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) { struct lruvec *target_lruvec; unsigned long refaults; if (lru_gen_enabled()) return; target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat); refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); target_lruvec->refaults[WORKINGSET_ANON] = refaults; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); target_lruvec->refaults[WORKINGSET_FILE] = refaults; } /* * This is the main entry point to direct page reclaim. * * If a full scan of the inactive list fails to free enough memory then we * are "out of memory" and something needs to be killed. * * If the caller is !__GFP_FS then the probability of a failure is reasonably * high - the zone may be full of dirty or under-writeback pages, which this * caller can't do much about. We kick the writeback threads and take explicit * naps in the hope that some of these pages can be written. But if the * allocating task holds filesystem locks which prevent writeout this might not * work, and the allocation attempt will fail. * * returns: 0, if no pages reclaimed * else, the number of pages reclaimed */ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int initial_priority = sc->priority; pg_data_t *last_pgdat; struct zoneref *z; struct zone *zone; retry: delayacct_freepages_start(); if (!cgroup_reclaim(sc)) __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); do { if (!sc->proactive) vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, sc->priority); sc->nr_scanned = 0; shrink_zones(zonelist, sc); if (sc->nr_reclaimed >= sc->nr_to_reclaim) break; if (sc->compaction_ready) break; /* * If we're getting trouble reclaiming, start doing * writepage even in laptop mode. */ if (sc->priority < DEF_PRIORITY - 2) sc->may_writepage = 1; } while (--sc->priority >= 0); last_pgdat = NULL; for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); if (cgroup_reclaim(sc)) { struct lruvec *lruvec; lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, zone->zone_pgdat); clear_bit(LRUVEC_CONGESTED, &lruvec->flags); } } delayacct_freepages_end(); if (sc->nr_reclaimed) return sc->nr_reclaimed; /* Aborted reclaim to try compaction? don't OOM, then */ if (sc->compaction_ready) return 1; /* * We make inactive:active ratio decisions based on the node's * composition of memory, but a restrictive reclaim_idx or a * memory.low cgroup setting can exempt large amounts of * memory from reclaim. Neither of which are very common, so * instead of doing costly eligibility calculations of the * entire cgroup subtree up front, we assume the estimates are * good, and retry with forcible deactivation if that fails. */ if (sc->skipped_deactivate) { sc->priority = initial_priority; sc->force_deactivate = 1; sc->skipped_deactivate = 0; goto retry; } /* Untapped cgroup reserves? Don't OOM, retry. */ if (sc->memcg_low_skipped) { sc->priority = initial_priority; sc->force_deactivate = 0; sc->memcg_low_reclaim = 1; sc->memcg_low_skipped = 0; goto retry; } return 0; } static bool allow_direct_reclaim(pg_data_t *pgdat) { struct zone *zone; unsigned long pfmemalloc_reserve = 0; unsigned long free_pages = 0; int i; bool wmark_ok; if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; if (!managed_zone(zone)) continue; if (!zone_reclaimable_pages(zone)) continue; pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state(zone, NR_FREE_PAGES); } /* If there are no reserves (unexpected config) then do not throttle */ if (!pfmemalloc_reserve) return true; wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL); wake_up_interruptible(&pgdat->kswapd_wait); } return wmark_ok; } /* * Throttle direct reclaimers if backing storage is backed by the network * and the PFMEMALLOC reserve for the preferred node is getting dangerously * depleted. kswapd will continue to make progress and wake the processes * when the low watermark is reached. * * Returns true if a fatal signal was delivered during throttling. If this * happens, the page allocator should not consider triggering the OOM killer. */ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { struct zoneref *z; struct zone *zone; pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly * responsible for cleaning pages necessary for reclaim to make forward * progress. kjournald for example may enter direct reclaim while * committing a transaction where throttling it could forcing other * processes to block on log_wait_commit(). */ if (current->flags & PF_KTHREAD) goto out; /* * If a fatal signal is pending, this process should not throttle. * It should return quickly so it can exit and free its memory */ if (fatal_signal_pending(current)) goto out; /* * Check if the pfmemalloc reserves are ok by finding the first node * with a usable ZONE_NORMAL or lower zone. The expectation is that * GFP_KERNEL will be required for allocating network buffers when * swapping over the network so ZONE_HIGHMEM is unusable. * * Throttling is based on the first usable node and throttled processes * wait on a queue until kswapd makes progress and wakes them. There * is an affinity then between processes waking up and where reclaim * progress has been made assuming the process wakes on the same node. * More importantly, processes running on remote nodes will not compete * for remote pfmemalloc reserves and processes on different nodes * should make reasonable progress. */ for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) { if (zone_idx(zone) > ZONE_NORMAL) continue; /* Throttle based on the first usable node */ pgdat = zone->zone_pgdat; if (allow_direct_reclaim(pgdat)) goto out; break; } /* If no zone was usable by the allocation flags then do not throttle */ if (!pgdat) goto out; /* Account for the throttling */ count_vm_event(PGSCAN_DIRECT_THROTTLE); /* * If the caller cannot enter the filesystem, it's possible that it * is due to the caller holding an FS lock or performing a journal * transaction in the case of a filesystem like ext[3|4]. In this case, * it is not safe to block on pfmemalloc_wait as kswapd could be * blocked waiting on the same lock. Instead, throttle for up to a * second before continuing. */ if (!(gfp_mask & __GFP_FS)) wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat), HZ); else /* Throttle until kswapd wakes the process */ wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat)); if (fatal_signal_pending(current)) return true; out: return false; } unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) { unsigned long nr_reclaimed; struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .gfp_mask = current_gfp_context(gfp_mask), .reclaim_idx = gfp_zone(gfp_mask), .order = order, .nodemask = nodemask, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = 1, }; /* * scan_control uses s8 fields for order, priority, and reclaim_idx. * Confirm they are large enough for max values. */ BUILD_BUG_ON(MAX_ORDER > S8_MAX); BUILD_BUG_ON(DEF_PRIORITY > S8_MAX); BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX); /* * Do not enter reclaim if fatal signal was delivered while throttled. * 1 is returned so that the page allocator does not OOM kill at this * point. */ if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask)) return 1; set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #ifdef CONFIG_MEMCG /* Only used by soft limit reclaim. Do not reuse for anything else. */ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned) { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .target_mem_cgroup = memcg, .may_writepage = !laptop_mode, .may_unmap = 1, .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, }; WARN_ON_ONCE(!current->reclaim_state); sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, sc.gfp_mask); /* * NOTE: Although we can get the priority field, using it * here is not a good idea, since it limits the pages we can scan. * if we don't reclaim here, the shrink_node from balance_pgdat * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ shrink_lruvec(lruvec, &sc); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); *nr_scanned = sc.nr_scanned; return sc.nr_reclaimed; } unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, unsigned int reclaim_options) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), .reclaim_idx = MAX_NR_ZONES - 1, .target_mem_cgroup = memcg, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP), .proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE), }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put * equal pressure on all the nodes. This is based on the assumption that * the reclaim does not bail out early. */ struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); memalloc_noreclaim_restore(noreclaim_flag); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #endif static void kswapd_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; struct lruvec *lruvec; if (lru_gen_enabled()) { lru_gen_age_node(pgdat, sc); return; } if (!can_age_anon_pages(pgdat, sc)) return; lruvec = mem_cgroup_lruvec(NULL, pgdat); if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON)) return; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { lruvec = mem_cgroup_lruvec(memcg, pgdat); shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); memcg = mem_cgroup_iter(NULL, memcg, NULL); } while (memcg); } static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx) { int i; struct zone *zone; /* * Check for watermark boosts top-down as the higher zones * are more likely to be boosted. Both watermarks and boosts * should not be checked at the same time as reclaim would * start prematurely when there is no boosting and a lower * zone is balanced. */ for (i = highest_zoneidx; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (zone->watermark_boost) return true; } return false; } /* * Returns true if there is an eligible zone balanced for the request order * and highest_zoneidx */ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long mark = -1; struct zone *zone; /* * Check watermarks bottom-up as lower zones are more likely to * meet watermarks. */ for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) mark = wmark_pages(zone, WMARK_PROMO); else mark = high_wmark_pages(zone); if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) return true; } /* * If a node has no managed zone within highest_zoneidx, it does not * need balancing by definition. This can happen if a zone-restricted * allocation tries to wake a remote kswapd. */ if (mark == -1) return true; return false; } /* Clear pgdat state for congested, dirty or under writeback. */ static void clear_pgdat_congested(pg_data_t *pgdat) { struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); clear_bit(LRUVEC_CONGESTED, &lruvec->flags); clear_bit(PGDAT_DIRTY, &pgdat->flags); clear_bit(PGDAT_WRITEBACK, &pgdat->flags); } /* * Prepare kswapd for sleeping. This verifies that there are no processes * waiting in throttle_direct_reclaim() and that watermarks have been met. * * Returns true if kswapd is ready to sleep */ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int highest_zoneidx) { /* * The throttled processes are normally woken up in balance_pgdat() as * soon as allow_direct_reclaim() is true. But there is a potential * race between when kswapd checks the watermarks and a process gets * throttled. There is also a potential race if processes get * throttled, kswapd wakes, a large process exits thereby balancing the * zones, which causes kswapd to exit balance_pgdat() before reaching * the wake up checks. If kswapd is going to sleep, no process should * be sleeping on pfmemalloc_wait, so wake them now if necessary. If * the wake up is premature, processes will wake kswapd and get * throttled again. The difference from wake ups in balance_pgdat() is * that here we are under prepare_to_wait(). */ if (waitqueue_active(&pgdat->pfmemalloc_wait)) wake_up_all(&pgdat->pfmemalloc_wait); /* Hopeless node, leave it to direct reclaim */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; if (pgdat_balanced(pgdat, order, highest_zoneidx)) { clear_pgdat_congested(pgdat); return true; } return false; } /* * kswapd shrinks a node of pages that are at or below the highest usable * zone that is currently unbalanced. * * Returns true if kswapd scanned at least the requested number of pages to * reclaim or if the lack of progress was due to pages under writeback. * This is used to determine if the scanning priority needs to be raised. */ static bool kswapd_shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct zone *zone; int z; /* Reclaim a number of pages proportional to the number of zones */ sc->nr_to_reclaim = 0; for (z = 0; z <= sc->reclaim_idx; z++) { zone = pgdat->node_zones + z; if (!managed_zone(zone)) continue; sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); } /* * Historically care was taken to put equal pressure on all zones but * now pressure is applied based on node LRU order. */ shrink_node(pgdat, sc); /* * Fragmentation may mean that the system cannot be rebalanced for * high-order allocations. If twice the allocation size has been * reclaimed then recheck watermarks only at order-0 to prevent * excessive reclaim. Assume that a process requested a high-order * can direct reclaim/compact. */ if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order)) sc->order = 0; return sc->nr_scanned >= sc->nr_to_reclaim; } /* Page allocator PCP high watermark is lowered if reclaim is active. */ static inline void update_reclaim_active(pg_data_t *pgdat, int highest_zoneidx, bool active) { int i; struct zone *zone; for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (active) set_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); else clear_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); } } static inline void set_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) { update_reclaim_active(pgdat, highest_zoneidx, true); } static inline void clear_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) { update_reclaim_active(pgdat, highest_zoneidx, false); } /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is * balanced. * * Returns the order kswapd finished reclaiming at. * * kswapd scans the zones in the highmem->normal->dma direction. It skips * zones which have free_pages > high_wmark_pages(zone), but once a zone is * found to have free_pages <= high_wmark_pages(zone), any page in that zone * or lower is eligible for reclaim until at least one usable zone is * balanced. */ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; unsigned long pflags; unsigned long nr_boost_reclaim; unsigned long zone_boosts[MAX_NR_ZONES] = { 0, }; bool boosted; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .order = order, .may_unmap = 1, }; set_task_reclaim_state(current, &sc.reclaim_state); psi_memstall_enter(&pflags); __fs_reclaim_acquire(_THIS_IP_); count_vm_event(PAGEOUTRUN); /* * Account for the reclaim boost. Note that the zone boost is left in * place so that parallel allocations that are near the watermark will * stall or direct reclaim until kswapd is finished. */ nr_boost_reclaim = 0; for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; nr_boost_reclaim += zone->watermark_boost; zone_boosts[i] = zone->watermark_boost; } boosted = nr_boost_reclaim; restart: set_reclaim_active(pgdat, highest_zoneidx); sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; bool raise_priority = true; bool balanced; bool ret; sc.reclaim_idx = highest_zoneidx; /* * If the number of buffer_heads exceeds the maximum allowed * then consider reclaiming from all zones. This has a dual * purpose -- on 64-bit systems it is expected that * buffer_heads are stripped during active rotation. On 32-bit * systems, highmem pages can pin lowmem memory and shrinking * buffers can relieve lowmem pressure. Reclaim may still not * go ahead if all eligible zones for the original allocation * request are balanced to avoid excessive reclaim from kswapd. */ if (buffer_heads_over_limit) { for (i = MAX_NR_ZONES - 1; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; sc.reclaim_idx = i; break; } } /* * If the pgdat is imbalanced then ignore boosting and preserve * the watermarks for a later time and restart. Note that the * zone watermarks will be still reset at the end of balancing * on the grounds that the normal reclaim should be enough to * re-evaluate if boosting is required when kswapd next wakes. */ balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx); if (!balanced && nr_boost_reclaim) { nr_boost_reclaim = 0; goto restart; } /* * If boosting is not active then only reclaim if there are no * eligible zones. Note that sc.reclaim_idx is not used as * buffer_heads_over_limit may have adjusted it. */ if (!nr_boost_reclaim && balanced) goto out; /* Limit the priority of boosting to avoid reclaim writeback */ if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2) raise_priority = false; /* * Do not writeback or swap pages for boosted reclaim. The * intent is to relieve pressure not issue sub-optimal IO * from reclaim context. If no pages are reclaimed, the * reclaim will be aborted. */ sc.may_writepage = !laptop_mode && !nr_boost_reclaim; sc.may_swap = !nr_boost_reclaim; /* * Do some background aging, to give pages a chance to be * referenced before reclaiming. All pages are rotated * regardless of classzone as this is about consistent aging. */ kswapd_age_node(pgdat, &sc); /* * If we're getting trouble reclaiming, start doing writepage * even in laptop mode. */ if (sc.priority < DEF_PRIORITY - 2) sc.may_writepage = 1; /* Call soft limit reclaim before calling shrink_node. */ sc.nr_scanned = 0; nr_soft_scanned = 0; nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order, sc.gfp_mask, &nr_soft_scanned); sc.nr_reclaimed += nr_soft_reclaimed; /* * There should be no need to raise the scanning priority if * enough pages are already being scanned that that high * watermark would be met at 100% efficiency. */ if (kswapd_shrink_node(pgdat, &sc)) raise_priority = false; /* * If the low watermark is met there is no need for processes * to be throttled on pfmemalloc_wait as they should not be * able to safely make forward progress. Wake them */ if (waitqueue_active(&pgdat->pfmemalloc_wait) && allow_direct_reclaim(pgdat)) wake_up_all(&pgdat->pfmemalloc_wait); /* Check if kswapd should be suspending */ __fs_reclaim_release(_THIS_IP_); ret = try_to_freeze(); __fs_reclaim_acquire(_THIS_IP_); if (ret || kthread_should_stop()) break; /* * Raise priority if scanning rate is too low or there was no * progress in reclaiming pages */ nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed); /* * If reclaim made no progress for a boost, stop reclaim as * IO cannot be queued and it could be an infinite loop in * extreme circumstances. */ if (nr_boost_reclaim && !nr_reclaimed) break; if (raise_priority || !nr_reclaimed) sc.priority--; } while (sc.priority >= 1); if (!sc.nr_reclaimed) pgdat->kswapd_failures++; out: clear_reclaim_active(pgdat, highest_zoneidx); /* If reclaim was boosted, account for the reclaim done in this pass */ if (boosted) { unsigned long flags; for (i = 0; i <= highest_zoneidx; i++) { if (!zone_boosts[i]) continue; /* Increments are under the zone lock */ zone = pgdat->node_zones + i; spin_lock_irqsave(&zone->lock, flags); zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]); spin_unlock_irqrestore(&zone->lock, flags); } /* * As there is now likely space, wakeup kcompact to defragment * pageblocks. */ wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx); } snapshot_refaults(NULL, pgdat); __fs_reclaim_release(_THIS_IP_); psi_memstall_leave(&pflags); set_task_reclaim_state(current, NULL); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller * entered the allocator slow path while kswapd was awake, order will * remain at the higher level. */ return sc.order; } /* * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is * not a valid index then either kswapd runs for first time or kswapd couldn't * sleep after previous reclaim attempt (node is still unbalanced). In that * case return the zone index of the previous kswapd reclaim cycle. */ static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat, enum zone_type prev_highest_zoneidx) { enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, unsigned int highest_zoneidx) { long remaining = 0; DEFINE_WAIT(wait); if (freezing(current) || kthread_should_stop()) return; prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); /* * Try to sleep for a short interval. Note that kcompactd will only be * woken if it is possible to sleep for a short interval. This is * deliberate on the assumption that if reclaim cannot keep an * eligible zone balanced that it's also unlikely that compaction will * succeed. */ if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { /* * Compaction records what page blocks it recently failed to * isolate pages from and skips them in the future scanning. * When kswapd is going to sleep, it is reasonable to assume * that pages and compaction may succeed so reset the cache. */ reset_isolation_suitable(pgdat); /* * We have freed the memory, now we should compact it to make * allocation of the requested order possible. */ wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx); remaining = schedule_timeout(HZ/10); /* * If woken prematurely then reset kswapd_highest_zoneidx and * order. The values will either be from a wakeup request or * the previous request that slept prematurely. */ if (remaining) { WRITE_ONCE(pgdat->kswapd_highest_zoneidx, kswapd_highest_zoneidx(pgdat, highest_zoneidx)); if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) WRITE_ONCE(pgdat->kswapd_order, reclaim_order); } finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); } /* * After a short sleep, check if it was a premature sleep. If not, then * go fully to sleep until explicitly woken up. */ if (!remaining && prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* * vmstat counters are not perfectly accurate and the estimated * value for counters such as NR_FREE_PAGES can deviate from the * true value by nr_online_cpus * threshold. To avoid the zone * watermarks being breached while under pressure, we reduce the * per-cpu vmstat threshold while kswapd is awake and restore * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); if (!kthread_should_stop()) schedule(); set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); else count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY); } finish_wait(&pgdat->kswapd_wait, &wait); } /* * The background pageout daemon, started as a kernel thread * from the init process. * * This basically trickles out pages so that we have _some_ * free memory available even if there is no other activity * that frees anything up. This is needed for things like routing * etc, where we otherwise might have all activity going on in * asynchronous contexts that cannot page things out. * * If there are applications that are active memory-allocators * (most normal use), this basically shouldn't matter. */ static int kswapd(void *p) { unsigned int alloc_order, reclaim_order; unsigned int highest_zoneidx = MAX_NR_ZONES - 1; pg_data_t *pgdat = (pg_data_t *)p; struct task_struct *tsk = current; const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); if (!cpumask_empty(cpumask)) set_cpus_allowed_ptr(tsk, cpumask); /* * Tell the memory management that we're a "memory allocator", * and that if we need more memory we should get access to it * regardless (see "__alloc_pages()"). "kswapd" should * never get caught in the normal page freeing logic. * * (Kswapd normally doesn't need memory anyway, but sometimes * you need a small amount of memory in order to be able to * page out something else, and this flag essentially protects * us from recursively trying to free more memory as we're * trying to free the first piece of memory in the first place). */ tsk->flags |= PF_MEMALLOC | PF_KSWAPD; set_freezable(); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); atomic_set(&pgdat->nr_writeback_throttled, 0); for ( ; ; ) { bool ret; alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); kswapd_try_sleep: kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, highest_zoneidx); /* Read the new order and highest_zoneidx */ alloc_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); ret = try_to_freeze(); if (kthread_should_stop()) break; /* * We can speed up thawing tasks if we don't call balance_pgdat * after returning from the refrigerator */ if (ret) continue; /* * Reclaim begins at the requested order but if a high-order * reclaim fails then kswapd falls back to reclaiming for * order-0. If that happens, kswapd will consider sleeping * for the order it finished reclaiming at (reclaim_order) * but kcompactd is woken to compact for the original * request (alloc_order). */ trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, alloc_order); reclaim_order = balance_pgdat(pgdat, alloc_order, highest_zoneidx); if (reclaim_order < alloc_order) goto kswapd_try_sleep; } tsk->flags &= ~(PF_MEMALLOC | PF_KSWAPD); return 0; } /* * A zone is low on free memory or too fragmented for high-order memory. If * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's * pgdat. It will wake up kcompactd after reclaiming memory. If kswapd reclaim * has failed or is not needed, still wake up kcompactd if only compaction is * needed. */ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, enum zone_type highest_zoneidx) { pg_data_t *pgdat; enum zone_type curr_idx; if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, gfp_flags)) return; pgdat = zone->zone_pgdat; curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx); if (READ_ONCE(pgdat->kswapd_order) < order) WRITE_ONCE(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; /* Hopeless node, leave it to direct reclaim if possible */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || (pgdat_balanced(pgdat, order, highest_zoneidx) && !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { /* * There may be plenty of free memory available, but it's too * fragmented for high-order allocations. Wake up kcompactd * and rely on compaction_suitable() to determine if it's * needed. If it fails, it will defer subsequent attempts to * ratelimit its work. */ if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) wakeup_kcompactd(pgdat, order, highest_zoneidx); return; } trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order, gfp_flags); wake_up_interruptible(&pgdat->kswapd_wait); } #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of * freed pages. * * Rather than trying to age LRUs the aim is to preserve the overall * LRU order by reclaiming preferentially * inactive > active > active referenced > active mapped */ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) { struct scan_control sc = { .nr_to_reclaim = nr_to_reclaim, .gfp_mask = GFP_HIGHUSER_MOVABLE, .reclaim_idx = MAX_NR_ZONES - 1, .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .hibernation_mode = 1, }; struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); unsigned long nr_reclaimed; unsigned int noreclaim_flag; fs_reclaim_acquire(sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(current, &sc.reclaim_state); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); set_task_reclaim_state(current, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); return nr_reclaimed; } #endif /* CONFIG_HIBERNATION */ /* * This kswapd start function will be called by init and node-hot-add. */ void kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); pgdat_kswapd_lock(pgdat); if (!pgdat->kswapd) { pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ BUG_ON(system_state < SYSTEM_RUNNING); pr_err("Failed to start kswapd on node %d\n", nid); pgdat->kswapd = NULL; } } pgdat_kswapd_unlock(pgdat); } /* * Called by memory hotplug when all memory in a node is offlined. Caller must * be holding mem_hotplug_begin/done(). */ void kswapd_stop(int nid) { pg_data_t *pgdat = NODE_DATA(nid); struct task_struct *kswapd; pgdat_kswapd_lock(pgdat); kswapd = pgdat->kswapd; if (kswapd) { kthread_stop(kswapd); pgdat->kswapd = NULL; } pgdat_kswapd_unlock(pgdat); } static int __init kswapd_init(void) { int nid; swap_setup(); for_each_node_state(nid, N_MEMORY) kswapd_run(nid); return 0; } module_init(kswapd_init) #ifdef CONFIG_NUMA /* * Node reclaim mode * * If non-zero call node_reclaim when the number of free pages falls below * the watermarks. */ int node_reclaim_mode __read_mostly; /* * Priority for NODE_RECLAIM. This determines the fraction of pages * of a node considered for each zone_reclaim. 4 scans 1/16th of * a zone. */ #define NODE_RECLAIM_PRIORITY 4 /* * Percentage of pages in a zone that must be unmapped for node_reclaim to * occur. */ int sysctl_min_unmapped_ratio = 1; /* * If the number of slab pages in a zone grows beyond this percentage then * slab reclaim needs to occur. */ int sysctl_min_slab_ratio = 5; static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat) { unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED); unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) + node_page_state(pgdat, NR_ACTIVE_FILE); /* * It's possible for there to be more file mapped pages than * accounted for by the pages on the file LRU lists because * tmpfs pages accounted for as ANON can also be FILE_MAPPED */ return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0; } /* Work out how many page cache pages we can reclaim in this reclaim_mode */ static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat) { unsigned long nr_pagecache_reclaimable; unsigned long delta = 0; /* * If RECLAIM_UNMAP is set, then all file pages are considered * potentially reclaimable. Otherwise, we have to worry about * pages like swapcache and node_unmapped_file_pages() provides * a better estimate */ if (node_reclaim_mode & RECLAIM_UNMAP) nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES); else nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat); /* If we can't clean pages, remove dirty pages from consideration */ if (!(node_reclaim_mode & RECLAIM_WRITE)) delta += node_page_state(pgdat, NR_FILE_DIRTY); /* Watch for any possible underflows due to delta */ if (unlikely(delta > nr_pagecache_reclaimable)) delta = nr_pagecache_reclaimable; return nr_pagecache_reclaimable - delta; } /* * Try to free up some pages from this node through reclaim. */ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { /* Minimum pages needed in order to stay on node */ const unsigned long nr_pages = 1 << order; struct task_struct *p = current; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = current_gfp_context(gfp_mask), .order = order, .priority = NODE_RECLAIM_PRIORITY, .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP), .may_swap = 1, .reclaim_idx = gfp_zone(gfp_mask), }; unsigned long pflags; trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order, sc.gfp_mask); cond_resched(); psi_memstall_enter(&pflags); fs_reclaim_acquire(sc.gfp_mask); /* * We need to be able to allocate from the reserves for RECLAIM_UNMAP */ noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(p, &sc.reclaim_state); if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages || node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) > pgdat->min_slab_pages) { /* * Free memory by calling shrink node with increasing * priorities until we have enough memory freed. */ do { shrink_node(pgdat, &sc); } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0); } set_task_reclaim_state(p, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); psi_memstall_leave(&pflags); trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); return sc.nr_reclaimed >= nr_pages; } int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { int ret; /* * Node reclaim reclaims unmapped file backed pages and * slab pages if we are over the defined limits. * * A small portion of unmapped file backed pages is needed for * file I/O otherwise pages read by file I/O will be immediately * thrown out if the node is overallocated. So we do not reclaim * if less than a specified percentage of the node is used by * unmapped file backed pages. */ if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <= pgdat->min_slab_pages) return NODE_RECLAIM_FULL; /* * Do not scan if the allocation should not be delayed. */ if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) return NODE_RECLAIM_NOSCAN; /* * Only run node reclaim on the local node or on nodes that do not * have associated processors. This will favor the local processor * over remote processors and spread off node memory allocations * as wide as possible. */ if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id()) return NODE_RECLAIM_NOSCAN; if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags)) return NODE_RECLAIM_NOSCAN; ret = __node_reclaim(pgdat, gfp_mask, order); clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags); if (!ret) count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); return ret; } #endif void check_move_unevictable_pages(struct pagevec *pvec) { struct folio_batch fbatch; unsigned i; folio_batch_init(&fbatch); for (i = 0; i < pvec->nr; i++) { struct page *page = pvec->pages[i]; if (PageTransTail(page)) continue; folio_batch_add(&fbatch, page_folio(page)); } check_move_unevictable_folios(&fbatch); } EXPORT_SYMBOL_GPL(check_move_unevictable_pages); /** * check_move_unevictable_folios - Move evictable folios to appropriate zone * lru list * @fbatch: Batch of lru folios to check. * * Checks folios for evictability, if an evictable folio is in the unevictable * lru list, moves it to the appropriate evictable lru list. This function * should be only used for lru folios. */ void check_move_unevictable_folios(struct folio_batch *fbatch) { struct lruvec *lruvec = NULL; int pgscanned = 0; int pgrescued = 0; int i; for (i = 0; i < fbatch->nr; i++) { struct folio *folio = fbatch->folios[i]; int nr_pages = folio_nr_pages(folio); pgscanned += nr_pages; /* block memcg migration while the folio moves between lrus */ if (!folio_test_clear_lru(folio)) continue; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (folio_evictable(folio) && folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); pgrescued += nr_pages; } folio_set_lru(folio); } if (lruvec) { __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); unlock_page_lruvec_irq(lruvec); } else if (pgscanned) { count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); } } EXPORT_SYMBOL_GPL(check_move_unevictable_folios); |
| 1538 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 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-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/types.h> #include <linux/jiffies.h> #include <linux/timer.h> #include <linux/netfilter.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_timeout.h> static const unsigned int nf_ct_generic_timeout = 600*HZ; #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> static int generic_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { struct nf_generic_net *gn = nf_generic_pernet(net); unsigned int *timeout = data; if (!timeout) timeout = &gn->timeout; if (tb[CTA_TIMEOUT_GENERIC_TIMEOUT]) *timeout = ntohl(nla_get_be32(tb[CTA_TIMEOUT_GENERIC_TIMEOUT])) * HZ; else { /* Set default generic timeout. */ *timeout = gn->timeout; } return 0; } static int generic_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeout = data; if (nla_put_be32(skb, CTA_TIMEOUT_GENERIC_TIMEOUT, htonl(*timeout / HZ))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static const struct nla_policy generic_timeout_nla_policy[CTA_TIMEOUT_GENERIC_MAX+1] = { [CTA_TIMEOUT_GENERIC_TIMEOUT] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ void nf_conntrack_generic_init_net(struct net *net) { struct nf_generic_net *gn = nf_generic_pernet(net); gn->timeout = nf_ct_generic_timeout; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = { .l4proto = 255, #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = generic_timeout_nlattr_to_obj, .obj_to_nlattr = generic_timeout_obj_to_nlattr, .nlattr_max = CTA_TIMEOUT_GENERIC_MAX, .obj_size = sizeof(unsigned int), .nla_policy = generic_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ }; |
| 2 1 1 1460 1459 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * "Ping" sockets * * Based on ipv4/ping.c code. * * Authors: Lorenzo Colitti (IPv6 support) * Vasiliy Kulikov / Openwall (IPv4 implementation, for Linux 2.6), * Pavel Kankovsky (IPv4 implementation, for Linux 2.4.32) */ #include <net/addrconf.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/protocol.h> #include <net/udp.h> #include <net/transp_v6.h> #include <linux/proc_fs.h> #include <linux/bpf-cgroup.h> #include <net/ping.h> static void ping_v6_destroy(struct sock *sk) { inet6_destroy_sock(sk); } /* Compatibility glue so we can support IPv6 when it's compiled as a module */ static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { return -EAFNOSUPPORT; } static void dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { } static int dummy_icmpv6_err_convert(u8 type, u8 code, int *err) { return -EAFNOSUPPORT; } static void dummy_ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) {} static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict) { return 0; } static int ping_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { /* This check is replicated from __ip6_datagram_connect() and * intended to prevent BPF program called below from accessing * bytes that are out of the bound specified by user in addr_len. */ if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr); } static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct icmp6hdr user_icmph; int addr_type; struct in6_addr *daddr; int oif = 0; struct flowi6 fl6; int err; struct dst_entry *dst; struct rt6_info *rt; struct pingfakehdr pfh; struct ipcm6_cookie ipc6; err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph, sizeof(user_icmph)); if (err) return err; memset(&fl6, 0, sizeof(fl6)); if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name); if (msg->msg_namelen < sizeof(*u)) return -EINVAL; if (u->sin6_family != AF_INET6) { return -EAFNOSUPPORT; } daddr = &(u->sin6_addr); if (np->sndflow) fl6.flowlabel = u->sin6_flowinfo & IPV6_FLOWINFO_MASK; if (__ipv6_addr_needs_scope_id(ipv6_addr_type(daddr))) oif = u->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; } if (!oif) oif = sk->sk_bound_dev_if; if (!oif) oif = np->sticky_pktinfo.ipi6_ifindex; if (!oif && ipv6_addr_is_multicast(daddr)) oif = np->mcast_oif; else if (!oif) oif = np->ucast_oif; addr_type = ipv6_addr_type(daddr); if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) || (addr_type & IPV6_ADDR_MAPPED) || (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if)) return -EINVAL; ipcm6_init_sk(&ipc6, np); ipc6.sockc.tsflags = sk->sk_tsflags; ipc6.sockc.mark = sk->sk_mark; fl6.flowi6_oif = oif; if (msg->msg_controllen) { struct ipv6_txoptions opt = {}; opt.tot_len = sizeof(opt); ipc6.opt = &opt; err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); if (err < 0) return err; /* Changes to txoptions and flow info are not implemented, yet. * Drop the options. */ ipc6.opt = NULL; } fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.saddr = np->saddr; fl6.daddr = *daddr; fl6.flowi6_mark = ipc6.sockc.mark; fl6.flowi6_uid = sk->sk_uid; fl6.fl6_icmp_type = user_icmph.icmp6_type; fl6.fl6_icmp_code = user_icmph.icmp6_code; security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false); if (IS_ERR(dst)) return PTR_ERR(dst); rt = (struct rt6_info *) dst; if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = np->mcast_oif; else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; pfh.icmph.type = user_icmph.icmp6_type; pfh.icmph.code = user_icmph.icmp6_code; pfh.icmph.checksum = 0; pfh.icmph.un.echo.id = inet->inet_sport; pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence; pfh.msg = msg; pfh.wcheck = 0; pfh.family = AF_INET6; if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); lock_sock(sk); err = ip6_append_data(sk, ping_getfrag, &pfh, len, sizeof(struct icmp6hdr), &ipc6, &fl6, rt, MSG_DONTWAIT); if (err) { ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { icmpv6_push_pending_frames(sk, &fl6, (struct icmp6hdr *)&pfh.icmph, len); } release_sock(sk); dst_release(dst); if (err) return err; return len; } struct proto pingv6_prot = { .name = "PINGv6", .owner = THIS_MODULE, .init = ping_init_sock, .close = ping_close, .destroy = ping_v6_destroy, .pre_connect = ping_v6_pre_connect, .connect = ip6_datagram_connect_v6_only, .disconnect = __udp_disconnect, .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .sendmsg = ping_v6_sendmsg, .recvmsg = ping_recvmsg, .bind = ping_bind, .backlog_rcv = ping_queue_rcv_skb, .hash = ping_hash, .unhash = ping_unhash, .get_port = ping_get_port, .put_port = ping_unhash, .obj_size = sizeof(struct raw6_sock), }; EXPORT_SYMBOL_GPL(pingv6_prot); static struct inet_protosw pingv6_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_ICMPV6, .prot = &pingv6_prot, .ops = &inet6_sockraw_ops, .flags = INET_PROTOSW_REUSE, }; #ifdef CONFIG_PROC_FS static void *ping_v6_seq_start(struct seq_file *seq, loff_t *pos) { return ping_seq_start(seq, pos, AF_INET6); } static int ping_v6_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); } else { int bucket = ((struct ping_iter_state *) seq->private)->bucket; struct inet_sock *inet = inet_sk(v); __u16 srcp = ntohs(inet->inet_sport); __u16 destp = ntohs(inet->inet_dport); ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket); } return 0; } static const struct seq_operations ping_v6_seq_ops = { .start = ping_v6_seq_start, .show = ping_v6_seq_show, .next = ping_seq_next, .stop = ping_seq_stop, }; static int __net_init ping_v6_proc_init_net(struct net *net) { if (!proc_create_net("icmp6", 0444, net->proc_net, &ping_v6_seq_ops, sizeof(struct ping_iter_state))) return -ENOMEM; return 0; } static void __net_exit ping_v6_proc_exit_net(struct net *net) { remove_proc_entry("icmp6", net->proc_net); } static struct pernet_operations ping_v6_net_ops = { .init = ping_v6_proc_init_net, .exit = ping_v6_proc_exit_net, }; #endif int __init pingv6_init(void) { #ifdef CONFIG_PROC_FS int ret = register_pernet_subsys(&ping_v6_net_ops); if (ret) return ret; #endif pingv6_ops.ipv6_recv_error = ipv6_recv_error; pingv6_ops.ip6_datagram_recv_common_ctl = ip6_datagram_recv_common_ctl; pingv6_ops.ip6_datagram_recv_specific_ctl = ip6_datagram_recv_specific_ctl; pingv6_ops.icmpv6_err_convert = icmpv6_err_convert; pingv6_ops.ipv6_icmp_error = ipv6_icmp_error; pingv6_ops.ipv6_chk_addr = ipv6_chk_addr; return inet6_register_protosw(&pingv6_protosw); } /* This never gets called because it's not possible to unload the ipv6 module, * but just in case. */ void pingv6_exit(void) { pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error; pingv6_ops.ip6_datagram_recv_common_ctl = dummy_ip6_datagram_recv_ctl; pingv6_ops.ip6_datagram_recv_specific_ctl = dummy_ip6_datagram_recv_ctl; pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert; pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error; pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr; #ifdef CONFIG_PROC_FS unregister_pernet_subsys(&ping_v6_net_ops); #endif inet6_unregister_protosw(&pingv6_protosw); } |
| 2678 2678 9 9 9 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * net/tipc/bearer.c: TIPC bearer code * * Copyright (c) 1996-2006, 2013-2016, Ericsson AB * Copyright (c) 2004-2006, 2010-2013, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include <net/sock.h> #include "core.h" #include "bearer.h" #include "link.h" #include "discover.h" #include "monitor.h" #include "bcast.h" #include "netlink.h" #include "udp_media.h" #include "trace.h" #include "crypto.h" #define MAX_ADDR_STR 60 static struct tipc_media * const media_info_array[] = { ð_media_info, #ifdef CONFIG_TIPC_MEDIA_IB &ib_media_info, #endif #ifdef CONFIG_TIPC_MEDIA_UDP &udp_media_info, #endif NULL }; static struct tipc_bearer *bearer_get(struct net *net, int bearer_id) { struct tipc_net *tn = tipc_net(net); return rcu_dereference(tn->bearer_list[bearer_id]); } static void bearer_disable(struct net *net, struct tipc_bearer *b); static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); /** * tipc_media_find - locates specified media object by name * @name: name to locate */ struct tipc_media *tipc_media_find(const char *name) { u32 i; for (i = 0; media_info_array[i] != NULL; i++) { if (!strcmp(media_info_array[i]->name, name)) break; } return media_info_array[i]; } /** * media_find_id - locates specified media object by type identifier * @type: type identifier to locate */ static struct tipc_media *media_find_id(u8 type) { u32 i; for (i = 0; media_info_array[i] != NULL; i++) { if (media_info_array[i]->type_id == type) break; } return media_info_array[i]; } /** * tipc_media_addr_printf - record media address in print buffer * @buf: output buffer * @len: output buffer size remaining * @a: input media address */ int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a) { char addr_str[MAX_ADDR_STR]; struct tipc_media *m; int ret; m = media_find_id(a->media_id); if (m && !m->addr2str(a, addr_str, sizeof(addr_str))) ret = scnprintf(buf, len, "%s(%s)", m->name, addr_str); else { u32 i; ret = scnprintf(buf, len, "UNKNOWN(%u)", a->media_id); for (i = 0; i < sizeof(a->value); i++) ret += scnprintf(buf + ret, len - ret, "-%x", a->value[i]); } return ret; } /** * bearer_name_validate - validate & (optionally) deconstruct bearer name * @name: ptr to bearer name string * @name_parts: ptr to area for bearer name components (or NULL if not needed) * * Return: 1 if bearer name is valid, otherwise 0. */ static int bearer_name_validate(const char *name, struct tipc_bearer_names *name_parts) { char name_copy[TIPC_MAX_BEARER_NAME]; char *media_name; char *if_name; u32 media_len; u32 if_len; /* copy bearer name & ensure length is OK */ if (strscpy(name_copy, name, TIPC_MAX_BEARER_NAME) < 0) return 0; /* ensure all component parts of bearer name are present */ media_name = name_copy; if_name = strchr(media_name, ':'); if (if_name == NULL) return 0; *(if_name++) = 0; media_len = if_name - media_name; if_len = strlen(if_name) + 1; /* validate component parts of bearer name */ if ((media_len <= 1) || (media_len > TIPC_MAX_MEDIA_NAME) || (if_len <= 1) || (if_len > TIPC_MAX_IF_NAME)) return 0; /* return bearer name components, if necessary */ if (name_parts) { strcpy(name_parts->media_name, media_name); strcpy(name_parts->if_name, if_name); } return 1; } /** * tipc_bearer_find - locates bearer object with matching bearer name * @net: the applicable net namespace * @name: bearer name to locate */ struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name) { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b; u32 i; for (i = 0; i < MAX_BEARERS; i++) { b = rtnl_dereference(tn->bearer_list[i]); if (b && (!strcmp(b->name, name))) return b; } return NULL; } /* tipc_bearer_get_name - get the bearer name from its id. * @net: network namespace * @name: a pointer to the buffer where the name will be stored. * @bearer_id: the id to get the name from. */ int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id) { struct tipc_net *tn = tipc_net(net); struct tipc_bearer *b; if (bearer_id >= MAX_BEARERS) return -EINVAL; b = rtnl_dereference(tn->bearer_list[bearer_id]); if (!b) return -EINVAL; strcpy(name, b->name); return 0; } void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest) { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b; rcu_read_lock(); b = rcu_dereference(tn->bearer_list[bearer_id]); if (b) tipc_disc_add_dest(b->disc); rcu_read_unlock(); } void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest) { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b; rcu_read_lock(); b = rcu_dereference(tn->bearer_list[bearer_id]); if (b) tipc_disc_remove_dest(b->disc); rcu_read_unlock(); } /** * tipc_enable_bearer - enable bearer with the given name * @net: the applicable net namespace * @name: bearer name to enable * @disc_domain: bearer domain * @prio: bearer priority * @attr: nlattr array * @extack: netlink extended ack */ static int tipc_enable_bearer(struct net *net, const char *name, u32 disc_domain, u32 prio, struct nlattr *attr[], struct netlink_ext_ack *extack) { struct tipc_net *tn = tipc_net(net); struct tipc_bearer_names b_names; int with_this_prio = 1; struct tipc_bearer *b; struct tipc_media *m; struct sk_buff *skb; int bearer_id = 0; int res = -EINVAL; char *errstr = ""; u32 i; if (!bearer_name_validate(name, &b_names)) { NL_SET_ERR_MSG(extack, "Illegal name"); return res; } if (prio > TIPC_MAX_LINK_PRI && prio != TIPC_MEDIA_LINK_PRI) { errstr = "illegal priority"; NL_SET_ERR_MSG(extack, "Illegal priority"); goto rejected; } m = tipc_media_find(b_names.media_name); if (!m) { errstr = "media not registered"; NL_SET_ERR_MSG(extack, "Media not registered"); goto rejected; } if (prio == TIPC_MEDIA_LINK_PRI) prio = m->priority; /* Check new bearer vs existing ones and find free bearer id if any */ bearer_id = MAX_BEARERS; i = MAX_BEARERS; while (i-- != 0) { b = rtnl_dereference(tn->bearer_list[i]); if (!b) { bearer_id = i; continue; } if (!strcmp(name, b->name)) { errstr = "already enabled"; NL_SET_ERR_MSG(extack, "Already enabled"); goto rejected; } if (b->priority == prio && (++with_this_prio > 2)) { pr_warn("Bearer <%s>: already 2 bearers with priority %u\n", name, prio); if (prio == TIPC_MIN_LINK_PRI) { errstr = "cannot adjust to lower"; NL_SET_ERR_MSG(extack, "Cannot adjust to lower"); goto rejected; } pr_warn("Bearer <%s>: trying with adjusted priority\n", name); prio--; bearer_id = MAX_BEARERS; i = MAX_BEARERS; with_this_prio = 1; } } if (bearer_id >= MAX_BEARERS) { errstr = "max 3 bearers permitted"; NL_SET_ERR_MSG(extack, "Max 3 bearers permitted"); goto rejected; } b = kzalloc(sizeof(*b), GFP_ATOMIC); if (!b) return -ENOMEM; strcpy(b->name, name); b->media = m; res = m->enable_media(net, b, attr); if (res) { kfree(b); errstr = "failed to enable media"; NL_SET_ERR_MSG(extack, "Failed to enable media"); goto rejected; } b->identity = bearer_id; b->tolerance = m->tolerance; b->min_win = m->min_win; b->max_win = m->max_win; b->domain = disc_domain; b->net_plane = bearer_id + 'A'; b->priority = prio; refcount_set(&b->refcnt, 1); res = tipc_disc_create(net, b, &b->bcast_addr, &skb); if (res) { bearer_disable(net, b); errstr = "failed to create discoverer"; NL_SET_ERR_MSG(extack, "Failed to create discoverer"); goto rejected; } /* Create monitoring data before accepting activate messages */ if (tipc_mon_create(net, bearer_id)) { bearer_disable(net, b); kfree_skb(skb); return -ENOMEM; } test_and_set_bit_lock(0, &b->up); rcu_assign_pointer(tn->bearer_list[bearer_id], b); if (skb) tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr); pr_info("Enabled bearer <%s>, priority %u\n", name, prio); return res; rejected: pr_warn("Enabling of bearer <%s> rejected, %s\n", name, errstr); return res; } /** * tipc_reset_bearer - Reset all links established over this bearer * @net: the applicable net namespace * @b: the target bearer */ static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b) { pr_info("Resetting bearer <%s>\n", b->name); tipc_node_delete_links(net, b->identity); tipc_disc_reset(net, b); return 0; } bool tipc_bearer_hold(struct tipc_bearer *b) { return (b && refcount_inc_not_zero(&b->refcnt)); } void tipc_bearer_put(struct tipc_bearer *b) { if (b && refcount_dec_and_test(&b->refcnt)) kfree_rcu(b, rcu); } /** * bearer_disable - disable this bearer * @net: the applicable net namespace * @b: the bearer to disable * * Note: This routine assumes caller holds RTNL lock. */ static void bearer_disable(struct net *net, struct tipc_bearer *b) { struct tipc_net *tn = tipc_net(net); int bearer_id = b->identity; pr_info("Disabling bearer <%s>\n", b->name); clear_bit_unlock(0, &b->up); tipc_node_delete_links(net, bearer_id); b->media->disable_media(b); RCU_INIT_POINTER(b->media_ptr, NULL); if (b->disc) tipc_disc_delete(b->disc); RCU_INIT_POINTER(tn->bearer_list[bearer_id], NULL); tipc_bearer_put(b); tipc_mon_delete(net, bearer_id); } int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, struct nlattr *attr[]) { char *dev_name = strchr((const char *)b->name, ':') + 1; int hwaddr_len = b->media->hwaddr_len; u8 node_id[NODE_ID_LEN] = {0,}; struct net_device *dev; /* Find device with specified name */ dev = dev_get_by_name(net, dev_name); if (!dev) return -ENODEV; if (tipc_mtu_bad(dev, 0)) { dev_put(dev); return -EINVAL; } if (dev == net->loopback_dev) { dev_put(dev); pr_info("Enabling <%s> not permitted\n", b->name); return -EINVAL; } /* Autoconfigure own node identity if needed */ if (!tipc_own_id(net) && hwaddr_len <= NODE_ID_LEN) { memcpy(node_id, dev->dev_addr, hwaddr_len); tipc_net_init(net, node_id, 0); } if (!tipc_own_id(net)) { dev_put(dev); pr_warn("Failed to obtain node identity\n"); return -EINVAL; } /* Associate TIPC bearer with L2 bearer */ rcu_assign_pointer(b->media_ptr, dev); b->pt.dev = dev; b->pt.type = htons(ETH_P_TIPC); b->pt.func = tipc_l2_rcv_msg; dev_add_pack(&b->pt); memset(&b->bcast_addr, 0, sizeof(b->bcast_addr)); memcpy(b->bcast_addr.value, dev->broadcast, hwaddr_len); b->bcast_addr.media_id = b->media->type_id; b->bcast_addr.broadcast = TIPC_BROADCAST_SUPPORT; b->mtu = dev->mtu; b->media->raw2addr(b, &b->addr, (const char *)dev->dev_addr); rcu_assign_pointer(dev->tipc_ptr, b); return 0; } /* tipc_disable_l2_media - detach TIPC bearer from an L2 interface * @b: the target bearer * * Mark L2 bearer as inactive so that incoming buffers are thrown away */ void tipc_disable_l2_media(struct tipc_bearer *b) { struct net_device *dev; dev = (struct net_device *)rtnl_dereference(b->media_ptr); dev_remove_pack(&b->pt); RCU_INIT_POINTER(dev->tipc_ptr, NULL); synchronize_net(); dev_put(dev); } /** * tipc_l2_send_msg - send a TIPC packet out over an L2 interface * @net: the associated network namespace * @skb: the packet to be sent * @b: the bearer through which the packet is to be sent * @dest: peer destination address */ int tipc_l2_send_msg(struct net *net, struct sk_buff *skb, struct tipc_bearer *b, struct tipc_media_addr *dest) { struct net_device *dev; int delta; dev = (struct net_device *)rcu_dereference(b->media_ptr); if (!dev) return 0; delta = SKB_DATA_ALIGN(dev->hard_header_len - skb_headroom(skb)); if ((delta > 0) && pskb_expand_head(skb, delta, 0, GFP_ATOMIC)) { kfree_skb(skb); return 0; } skb_reset_network_header(skb); skb->dev = dev; skb->protocol = htons(ETH_P_TIPC); dev_hard_header(skb, dev, ETH_P_TIPC, dest->value, dev->dev_addr, skb->len); dev_queue_xmit(skb); return 0; } bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id) { bool supp = false; struct tipc_bearer *b; rcu_read_lock(); b = bearer_get(net, bearer_id); if (b) supp = (b->bcast_addr.broadcast == TIPC_BROADCAST_SUPPORT); rcu_read_unlock(); return supp; } int tipc_bearer_mtu(struct net *net, u32 bearer_id) { int mtu = 0; struct tipc_bearer *b; rcu_read_lock(); b = rcu_dereference(tipc_net(net)->bearer_list[bearer_id]); if (b) mtu = b->mtu; rcu_read_unlock(); return mtu; } /* tipc_bearer_xmit_skb - sends buffer to destination over bearer */ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, struct tipc_media_addr *dest) { struct tipc_msg *hdr = buf_msg(skb); struct tipc_bearer *b; rcu_read_lock(); b = bearer_get(net, bearer_id); if (likely(b && (test_bit(0, &b->up) || msg_is_reset(hdr)))) { #ifdef CONFIG_TIPC_CRYPTO tipc_crypto_xmit(net, &skb, b, dest, NULL); if (skb) #endif b->media->send_msg(net, skb, b, dest); } else { kfree_skb(skb); } rcu_read_unlock(); } /* tipc_bearer_xmit() -send buffer to destination over bearer */ void tipc_bearer_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq, struct tipc_media_addr *dst, struct tipc_node *__dnode) { struct tipc_bearer *b; struct sk_buff *skb, *tmp; if (skb_queue_empty(xmitq)) return; rcu_read_lock(); b = bearer_get(net, bearer_id); if (unlikely(!b)) __skb_queue_purge(xmitq); skb_queue_walk_safe(xmitq, skb, tmp) { __skb_dequeue(xmitq); if (likely(test_bit(0, &b->up) || msg_is_reset(buf_msg(skb)))) { #ifdef CONFIG_TIPC_CRYPTO tipc_crypto_xmit(net, &skb, b, dst, __dnode); if (skb) #endif b->media->send_msg(net, skb, b, dst); } else { kfree_skb(skb); } } rcu_read_unlock(); } /* tipc_bearer_bc_xmit() - broadcast buffers to all destinations */ void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq) { struct tipc_net *tn = tipc_net(net); struct tipc_media_addr *dst; int net_id = tn->net_id; struct tipc_bearer *b; struct sk_buff *skb, *tmp; struct tipc_msg *hdr; rcu_read_lock(); b = bearer_get(net, bearer_id); if (unlikely(!b || !test_bit(0, &b->up))) __skb_queue_purge(xmitq); skb_queue_walk_safe(xmitq, skb, tmp) { hdr = buf_msg(skb); msg_set_non_seq(hdr, 1); msg_set_mc_netid(hdr, net_id); __skb_dequeue(xmitq); dst = &b->bcast_addr; #ifdef CONFIG_TIPC_CRYPTO tipc_crypto_xmit(net, &skb, b, dst, NULL); if (skb) #endif b->media->send_msg(net, skb, b, dst); } rcu_read_unlock(); } /** * tipc_l2_rcv_msg - handle incoming TIPC message from an interface * @skb: the received message * @dev: the net device that the packet was received on * @pt: the packet_type structure which was used to register this handler * @orig_dev: the original receive net device in case the device is a bond * * Accept only packets explicitly sent to this node, or broadcast packets; * ignores packets sent using interface multicast, and traffic sent to other * nodes (which can happen if interface is running in promiscuous mode). */ static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct tipc_bearer *b; rcu_read_lock(); b = rcu_dereference(dev->tipc_ptr) ?: rcu_dereference(orig_dev->tipc_ptr); if (likely(b && test_bit(0, &b->up) && (skb->pkt_type <= PACKET_MULTICAST))) { skb_mark_not_on_list(skb); TIPC_SKB_CB(skb)->flags = 0; tipc_rcv(dev_net(b->pt.dev), skb, b); rcu_read_unlock(); return NET_RX_SUCCESS; } rcu_read_unlock(); kfree_skb(skb); return NET_RX_DROP; } /** * tipc_l2_device_event - handle device events from network device * @nb: the context of the notification * @evt: the type of event * @ptr: the net device that the event was on * * This function is called by the Ethernet driver in case of link * change event. */ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct tipc_bearer *b; b = rtnl_dereference(dev->tipc_ptr); if (!b) return NOTIFY_DONE; trace_tipc_l2_device_event(dev, b, evt); switch (evt) { case NETDEV_CHANGE: if (netif_carrier_ok(dev) && netif_oper_up(dev)) { test_and_set_bit_lock(0, &b->up); break; } fallthrough; case NETDEV_GOING_DOWN: clear_bit_unlock(0, &b->up); tipc_reset_bearer(net, b); break; case NETDEV_UP: test_and_set_bit_lock(0, &b->up); break; case NETDEV_CHANGEMTU: if (tipc_mtu_bad(dev, 0)) { bearer_disable(net, b); break; } b->mtu = dev->mtu; tipc_reset_bearer(net, b); break; case NETDEV_CHANGEADDR: b->media->raw2addr(b, &b->addr, (const char *)dev->dev_addr); tipc_reset_bearer(net, b); break; case NETDEV_UNREGISTER: case NETDEV_CHANGENAME: bearer_disable(net, b); break; } return NOTIFY_OK; } static struct notifier_block notifier = { .notifier_call = tipc_l2_device_event, .priority = 0, }; int tipc_bearer_setup(void) { return register_netdevice_notifier(¬ifier); } void tipc_bearer_cleanup(void) { unregister_netdevice_notifier(¬ifier); } void tipc_bearer_stop(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b; u32 i; for (i = 0; i < MAX_BEARERS; i++) { b = rtnl_dereference(tn->bearer_list[i]); if (b) { bearer_disable(net, b); tn->bearer_list[i] = NULL; } } } void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts) { struct net_device *dev = net->loopback_dev; struct sk_buff *skb, *_skb; int exp; skb_queue_walk(pkts, _skb) { skb = pskb_copy(_skb, GFP_ATOMIC); if (!skb) continue; exp = SKB_DATA_ALIGN(dev->hard_header_len - skb_headroom(skb)); if (exp > 0 && pskb_expand_head(skb, exp, 0, GFP_ATOMIC)) { kfree_skb(skb); continue; } skb_reset_network_header(skb); dev_hard_header(skb, dev, ETH_P_TIPC, dev->dev_addr, dev->dev_addr, skb->len); skb->dev = dev; skb->pkt_type = PACKET_HOST; skb->ip_summed = CHECKSUM_UNNECESSARY; skb->protocol = eth_type_trans(skb, dev); netif_rx(skb); } } static int tipc_loopback_rcv_pkt(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *od) { consume_skb(skb); return NET_RX_SUCCESS; } int tipc_attach_loopback(struct net *net) { struct net_device *dev = net->loopback_dev; struct tipc_net *tn = tipc_net(net); if (!dev) return -ENODEV; netdev_hold(dev, &tn->loopback_pt.dev_tracker, GFP_KERNEL); tn->loopback_pt.dev = dev; tn->loopback_pt.type = htons(ETH_P_TIPC); tn->loopback_pt.func = tipc_loopback_rcv_pkt; dev_add_pack(&tn->loopback_pt); return 0; } void tipc_detach_loopback(struct net *net) { struct tipc_net *tn = tipc_net(net); dev_remove_pack(&tn->loopback_pt); netdev_put(net->loopback_dev, &tn->loopback_pt.dev_tracker); } /* Caller should hold rtnl_lock to protect the bearer */ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, struct tipc_bearer *bearer, int nlflags) { void *hdr; struct nlattr *attrs; struct nlattr *prop; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, nlflags, TIPC_NL_BEARER_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER); if (!attrs) goto msg_full; if (nla_put_string(msg->skb, TIPC_NLA_BEARER_NAME, bearer->name)) goto attr_msg_full; prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER_PROP); if (!prop) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, bearer->priority)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, bearer->tolerance)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bearer->max_win)) goto prop_msg_full; if (bearer->media->type_id == TIPC_MEDIA_TYPE_UDP) if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, bearer->mtu)) goto prop_msg_full; nla_nest_end(msg->skb, prop); #ifdef CONFIG_TIPC_MEDIA_UDP if (bearer->media->type_id == TIPC_MEDIA_TYPE_UDP) { if (tipc_udp_nl_add_bearer_data(msg, bearer)) goto attr_msg_full; } #endif nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; prop_msg_full: nla_nest_cancel(msg->skb, prop); attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb) { int err; int i = cb->args[0]; struct tipc_bearer *bearer; struct tipc_nl_msg msg; struct net *net = sock_net(skb->sk); struct tipc_net *tn = net_generic(net, tipc_net_id); if (i == MAX_BEARERS) return 0; msg.skb = skb; msg.portid = NETLINK_CB(cb->skb).portid; msg.seq = cb->nlh->nlmsg_seq; rtnl_lock(); for (i = 0; i < MAX_BEARERS; i++) { bearer = rtnl_dereference(tn->bearer_list[i]); if (!bearer) continue; err = __tipc_nl_add_bearer(&msg, bearer, NLM_F_MULTI); if (err) break; } rtnl_unlock(); cb->args[0] = i; return skb->len; } int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info) { int err; char *name; struct sk_buff *rep; struct tipc_bearer *bearer; struct tipc_nl_msg msg; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; struct net *net = genl_info_net(info); if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, info->attrs[TIPC_NLA_BEARER], tipc_nl_bearer_policy, info->extack); if (err) return err; if (!attrs[TIPC_NLA_BEARER_NAME]) return -EINVAL; name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!rep) return -ENOMEM; msg.skb = rep; msg.portid = info->snd_portid; msg.seq = info->snd_seq; rtnl_lock(); bearer = tipc_bearer_find(net, name); if (!bearer) { err = -EINVAL; NL_SET_ERR_MSG(info->extack, "Bearer not found"); goto err_out; } err = __tipc_nl_add_bearer(&msg, bearer, 0); if (err) goto err_out; rtnl_unlock(); return genlmsg_reply(rep, info); err_out: rtnl_unlock(); nlmsg_free(rep); return err; } int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) { int err; char *name; struct tipc_bearer *bearer; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; struct net *net = sock_net(skb->sk); if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, info->attrs[TIPC_NLA_BEARER], tipc_nl_bearer_policy, info->extack); if (err) return err; if (!attrs[TIPC_NLA_BEARER_NAME]) return -EINVAL; name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); bearer = tipc_bearer_find(net, name); if (!bearer) { NL_SET_ERR_MSG(info->extack, "Bearer not found"); return -EINVAL; } bearer_disable(net, bearer); return 0; } int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) { int err; rtnl_lock(); err = __tipc_nl_bearer_disable(skb, info); rtnl_unlock(); return err; } int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) { int err; char *bearer; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; struct net *net = sock_net(skb->sk); u32 domain = 0; u32 prio; prio = TIPC_MEDIA_LINK_PRI; if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, info->attrs[TIPC_NLA_BEARER], tipc_nl_bearer_policy, info->extack); if (err) return err; if (!attrs[TIPC_NLA_BEARER_NAME]) return -EINVAL; bearer = nla_data(attrs[TIPC_NLA_BEARER_NAME]); if (attrs[TIPC_NLA_BEARER_DOMAIN]) domain = nla_get_u32(attrs[TIPC_NLA_BEARER_DOMAIN]); if (attrs[TIPC_NLA_BEARER_PROP]) { struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_BEARER_PROP], props); if (err) return err; if (props[TIPC_NLA_PROP_PRIO]) prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); } return tipc_enable_bearer(net, bearer, domain, prio, attrs, info->extack); } int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) { int err; rtnl_lock(); err = __tipc_nl_bearer_enable(skb, info); rtnl_unlock(); return err; } int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) { int err; char *name; struct tipc_bearer *b; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; struct net *net = sock_net(skb->sk); if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, info->attrs[TIPC_NLA_BEARER], tipc_nl_bearer_policy, info->extack); if (err) return err; if (!attrs[TIPC_NLA_BEARER_NAME]) return -EINVAL; name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); rtnl_lock(); b = tipc_bearer_find(net, name); if (!b) { rtnl_unlock(); NL_SET_ERR_MSG(info->extack, "Bearer not found"); return -EINVAL; } #ifdef CONFIG_TIPC_MEDIA_UDP if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) { err = tipc_udp_nl_bearer_add(b, attrs[TIPC_NLA_BEARER_UDP_OPTS]); if (err) { rtnl_unlock(); return err; } } #endif rtnl_unlock(); return 0; } int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) { struct tipc_bearer *b; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; struct net *net = sock_net(skb->sk); char *name; int err; if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, info->attrs[TIPC_NLA_BEARER], tipc_nl_bearer_policy, info->extack); if (err) return err; if (!attrs[TIPC_NLA_BEARER_NAME]) return -EINVAL; name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); b = tipc_bearer_find(net, name); if (!b) { NL_SET_ERR_MSG(info->extack, "Bearer not found"); return -EINVAL; } if (attrs[TIPC_NLA_BEARER_PROP]) { struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_BEARER_PROP], props); if (err) return err; if (props[TIPC_NLA_PROP_TOL]) { b->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]); tipc_node_apply_property(net, b, TIPC_NLA_PROP_TOL); } if (props[TIPC_NLA_PROP_PRIO]) b->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (props[TIPC_NLA_PROP_WIN]) b->max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); if (props[TIPC_NLA_PROP_MTU]) { if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) { NL_SET_ERR_MSG(info->extack, "MTU property is unsupported"); return -EINVAL; } #ifdef CONFIG_TIPC_MEDIA_UDP if (tipc_udp_mtu_bad(nla_get_u32 (props[TIPC_NLA_PROP_MTU]))) { NL_SET_ERR_MSG(info->extack, "MTU value is out-of-range"); return -EINVAL; } b->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]); tipc_node_apply_property(net, b, TIPC_NLA_PROP_MTU); #endif } } return 0; } int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) { int err; rtnl_lock(); err = __tipc_nl_bearer_set(skb, info); rtnl_unlock(); return err; } static int __tipc_nl_add_media(struct tipc_nl_msg *msg, struct tipc_media *media, int nlflags) { void *hdr; struct nlattr *attrs; struct nlattr *prop; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, nlflags, TIPC_NL_MEDIA_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA); if (!attrs) goto msg_full; if (nla_put_string(msg->skb, TIPC_NLA_MEDIA_NAME, media->name)) goto attr_msg_full; prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA_PROP); if (!prop) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, media->priority)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, media->tolerance)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, media->max_win)) goto prop_msg_full; if (media->type_id == TIPC_MEDIA_TYPE_UDP) if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, media->mtu)) goto prop_msg_full; nla_nest_end(msg->skb, prop); nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; prop_msg_full: nla_nest_cancel(msg->skb, prop); attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb) { int err; int i = cb->args[0]; struct tipc_nl_msg msg; if (i == MAX_MEDIA) return 0; msg.skb = skb; msg.portid = NETLINK_CB(cb->skb).portid; msg.seq = cb->nlh->nlmsg_seq; rtnl_lock(); for (; media_info_array[i] != NULL; i++) { err = __tipc_nl_add_media(&msg, media_info_array[i], NLM_F_MULTI); if (err) break; } rtnl_unlock(); cb->args[0] = i; return skb->len; } int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info) { int err; char *name; struct tipc_nl_msg msg; struct tipc_media *media; struct sk_buff *rep; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; if (!info->attrs[TIPC_NLA_MEDIA]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MEDIA_MAX, info->attrs[TIPC_NLA_MEDIA], tipc_nl_media_policy, info->extack); if (err) return err; if (!attrs[TIPC_NLA_MEDIA_NAME]) return -EINVAL; name = nla_data(attrs[TIPC_NLA_MEDIA_NAME]); rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!rep) return -ENOMEM; msg.skb = rep; msg.portid = info->snd_portid; msg.seq = info->snd_seq; rtnl_lock(); media = tipc_media_find(name); if (!media) { NL_SET_ERR_MSG(info->extack, "Media not found"); err = -EINVAL; goto err_out; } err = __tipc_nl_add_media(&msg, media, 0); if (err) goto err_out; rtnl_unlock(); return genlmsg_reply(rep, info); err_out: rtnl_unlock(); nlmsg_free(rep); return err; } int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) { int err; char *name; struct tipc_media *m; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; if (!info->attrs[TIPC_NLA_MEDIA]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MEDIA_MAX, info->attrs[TIPC_NLA_MEDIA], tipc_nl_media_policy, info->extack); if (!attrs[TIPC_NLA_MEDIA_NAME]) return -EINVAL; name = nla_data(attrs[TIPC_NLA_MEDIA_NAME]); m = tipc_media_find(name); if (!m) { NL_SET_ERR_MSG(info->extack, "Media not found"); return -EINVAL; } if (attrs[TIPC_NLA_MEDIA_PROP]) { struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_MEDIA_PROP], props); if (err) return err; if (props[TIPC_NLA_PROP_TOL]) m->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]); if (props[TIPC_NLA_PROP_PRIO]) m->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (props[TIPC_NLA_PROP_WIN]) m->max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); if (props[TIPC_NLA_PROP_MTU]) { if (m->type_id != TIPC_MEDIA_TYPE_UDP) { NL_SET_ERR_MSG(info->extack, "MTU property is unsupported"); return -EINVAL; } #ifdef CONFIG_TIPC_MEDIA_UDP if (tipc_udp_mtu_bad(nla_get_u32 (props[TIPC_NLA_PROP_MTU]))) { NL_SET_ERR_MSG(info->extack, "MTU value is out-of-range"); return -EINVAL; } m->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]); #endif } } return 0; } int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) { int err; rtnl_lock(); err = __tipc_nl_media_set(skb, info); rtnl_unlock(); return err; } |
| 2016 2921 2921 3238 2913 1895 1699 1089 1070 3238 1799 1798 1798 658 1760 642 207 643 505 9 1712 1712 3 3 631 631 631 2204 2205 2801 2791 2790 2801 1475 842 843 1475 2794 2795 2223 2223 136 87 22 22 1696 48 48 2806 2789 2795 2468 136 136 2467 2210 2134 1508 2801 2807 2807 2797 2796 2796 2796 2795 2797 2797 2796 2796 2797 1118 1119 1118 1119 1119 1117 432 1119 4317 4316 4165 2643 1738 2241 736 1689 4317 3900 3900 3 2 2 4317 772 58 58 575 575 3234 3233 2614 2606 772 2463 2607 613 2369 1479 613 582 2352 493 2369 425 18 43 1474 1472 572 1472 1139 3 3 3 2 1474 575 3232 1507 1507 1507 1506 1506 4 2 2 2 2016 904 904 904 904 904 903 904 1137 3 3 3 3 3 1137 1137 1137 1137 1136 1137 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/ext4/extents_status.c * * Written by Yongqiang Yang <xiaoqiangnk@gmail.com> * Modified by * Allison Henderson <achender@linux.vnet.ibm.com> * Hugh Dickins <hughd@google.com> * Zheng Liu <wenqing.lz@taobao.com> * * Ext4 extents status tree core functions. */ #include <linux/list_sort.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include "ext4.h" #include <trace/events/ext4.h> /* * According to previous discussion in Ext4 Developer Workshop, we * will introduce a new structure called io tree to track all extent * status in order to solve some problems that we have met * (e.g. Reservation space warning), and provide extent-level locking. * Delay extent tree is the first step to achieve this goal. It is * original built by Yongqiang Yang. At that time it is called delay * extent tree, whose goal is only track delayed extents in memory to * simplify the implementation of fiemap and bigalloc, and introduce * lseek SEEK_DATA/SEEK_HOLE support. That is why it is still called * delay extent tree at the first commit. But for better understand * what it does, it has been rename to extent status tree. * * Step1: * Currently the first step has been done. All delayed extents are * tracked in the tree. It maintains the delayed extent when a delayed * allocation is issued, and the delayed extent is written out or * invalidated. Therefore the implementation of fiemap and bigalloc * are simplified, and SEEK_DATA/SEEK_HOLE are introduced. * * The following comment describes the implemenmtation of extent * status tree and future works. * * Step2: * In this step all extent status are tracked by extent status tree. * Thus, we can first try to lookup a block mapping in this tree before * finding it in extent tree. Hence, single extent cache can be removed * because extent status tree can do a better job. Extents in status * tree are loaded on-demand. Therefore, the extent status tree may not * contain all of the extents in a file. Meanwhile we define a shrinker * to reclaim memory from extent status tree because fragmented extent * tree will make status tree cost too much memory. written/unwritten/- * hole extents in the tree will be reclaimed by this shrinker when we * are under high memory pressure. Delayed extents will not be * reclimed because fiemap, bigalloc, and seek_data/hole need it. */ /* * Extent status tree implementation for ext4. * * * ========================================================================== * Extent status tree tracks all extent status. * * 1. Why we need to implement extent status tree? * * Without extent status tree, ext4 identifies a delayed extent by looking * up page cache, this has several deficiencies - complicated, buggy, * and inefficient code. * * FIEMAP, SEEK_HOLE/DATA, bigalloc, and writeout all need to know if a * block or a range of blocks are belonged to a delayed extent. * * Let us have a look at how they do without extent status tree. * -- FIEMAP * FIEMAP looks up page cache to identify delayed allocations from holes. * * -- SEEK_HOLE/DATA * SEEK_HOLE/DATA has the same problem as FIEMAP. * * -- bigalloc * bigalloc looks up page cache to figure out if a block is * already under delayed allocation or not to determine whether * quota reserving is needed for the cluster. * * -- writeout * Writeout looks up whole page cache to see if a buffer is * mapped, If there are not very many delayed buffers, then it is * time consuming. * * With extent status tree implementation, FIEMAP, SEEK_HOLE/DATA, * bigalloc and writeout can figure out if a block or a range of * blocks is under delayed allocation(belonged to a delayed extent) or * not by searching the extent tree. * * * ========================================================================== * 2. Ext4 extent status tree impelmentation * * -- extent * A extent is a range of blocks which are contiguous logically and * physically. Unlike extent in extent tree, this extent in ext4 is * a in-memory struct, there is no corresponding on-disk data. There * is no limit on length of extent, so an extent can contain as many * blocks as they are contiguous logically and physically. * * -- extent status tree * Every inode has an extent status tree and all allocation blocks * are added to the tree with different status. The extent in the * tree are ordered by logical block no. * * -- operations on a extent status tree * There are three important operations on a delayed extent tree: find * next extent, adding a extent(a range of blocks) and removing a extent. * * -- race on a extent status tree * Extent status tree is protected by inode->i_es_lock. * * -- memory consumption * Fragmented extent tree will make extent status tree cost too much * memory. Hence, we will reclaim written/unwritten/hole extents from * the tree under a heavy memory pressure. * * * ========================================================================== * 3. Performance analysis * * -- overhead * 1. There is a cache extent for write access, so if writes are * not very random, adding space operaions are in O(1) time. * * -- gain * 2. Code is much simpler, more readable, more maintainable and * more efficient. * * * ========================================================================== * 4. TODO list * * -- Refactor delayed space reservation * * -- Extent-level locking */ static struct kmem_cache *ext4_es_cachep; static struct kmem_cache *ext4_pending_cachep; static int __es_insert_extent(struct inode *inode, struct extent_status *newes); static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end, int *reserved); static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan); static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei); static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len); int __init ext4_init_es(void) { ext4_es_cachep = kmem_cache_create("ext4_extent_status", sizeof(struct extent_status), 0, (SLAB_RECLAIM_ACCOUNT), NULL); if (ext4_es_cachep == NULL) return -ENOMEM; return 0; } void ext4_exit_es(void) { kmem_cache_destroy(ext4_es_cachep); } void ext4_es_init_tree(struct ext4_es_tree *tree) { tree->root = RB_ROOT; tree->cache_es = NULL; } #ifdef ES_DEBUG__ static void ext4_es_print_tree(struct inode *inode) { struct ext4_es_tree *tree; struct rb_node *node; printk(KERN_DEBUG "status extents for inode %lu:", inode->i_ino); tree = &EXT4_I(inode)->i_es_tree; node = rb_first(&tree->root); while (node) { struct extent_status *es; es = rb_entry(node, struct extent_status, rb_node); printk(KERN_DEBUG " [%u/%u) %llu %x", es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); node = rb_next(node); } printk(KERN_DEBUG "\n"); } #else #define ext4_es_print_tree(inode) #endif static inline ext4_lblk_t ext4_es_end(struct extent_status *es) { BUG_ON(es->es_lblk + es->es_len < es->es_lblk); return es->es_lblk + es->es_len - 1; } /* * search through the tree for an delayed extent with a given offset. If * it can't be found, try to find next extent. */ static struct extent_status *__es_tree_search(struct rb_root *root, ext4_lblk_t lblk) { struct rb_node *node = root->rb_node; struct extent_status *es = NULL; while (node) { es = rb_entry(node, struct extent_status, rb_node); if (lblk < es->es_lblk) node = node->rb_left; else if (lblk > ext4_es_end(es)) node = node->rb_right; else return es; } if (es && lblk < es->es_lblk) return es; if (es && lblk > ext4_es_end(es)) { node = rb_next(&es->rb_node); return node ? rb_entry(node, struct extent_status, rb_node) : NULL; } return NULL; } /* * ext4_es_find_extent_range - find extent with specified status within block * range or next extent following block range in * extents status tree * * @inode - file containing the range * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block defining start of range * @end - logical block defining end of range * @es - extent found, if any * * Find the first extent within the block range specified by @lblk and @end * in the extents status tree that satisfies @matching_fn. If a match * is found, it's returned in @es. If not, and a matching extent is found * beyond the block range, it's returned in @es. If no match is found, an * extent is returned in @es whose es_lblk, es_len, and es_pblk components * are 0. */ static void __es_find_extent_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es) { struct ext4_es_tree *tree = NULL; struct extent_status *es1 = NULL; struct rb_node *node; WARN_ON(es == NULL); WARN_ON(end < lblk); tree = &EXT4_I(inode)->i_es_tree; /* see if the extent has been cached */ es->es_lblk = es->es_len = es->es_pblk = 0; if (tree->cache_es) { es1 = tree->cache_es; if (in_range(lblk, es1->es_lblk, es1->es_len)) { es_debug("%u cached by [%u/%u) %llu %x\n", lblk, es1->es_lblk, es1->es_len, ext4_es_pblock(es1), ext4_es_status(es1)); goto out; } } es1 = __es_tree_search(&tree->root, lblk); out: if (es1 && !matching_fn(es1)) { while ((node = rb_next(&es1->rb_node)) != NULL) { es1 = rb_entry(node, struct extent_status, rb_node); if (es1->es_lblk > end) { es1 = NULL; break; } if (matching_fn(es1)) break; } } if (es1 && matching_fn(es1)) { tree->cache_es = es1; es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; } } /* * Locking for __es_find_extent_range() for external use */ void ext4_es_find_extent_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es) { if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; trace_ext4_es_find_extent_range_enter(inode, lblk); read_lock(&EXT4_I(inode)->i_es_lock); __es_find_extent_range(inode, matching_fn, lblk, end, es); read_unlock(&EXT4_I(inode)->i_es_lock); trace_ext4_es_find_extent_range_exit(inode, es); } /* * __es_scan_range - search block range for block with specified status * in extents status tree * * @inode - file containing the range * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block defining start of range * @end - logical block defining end of range * * Returns true if at least one block in the specified block range satisfies * the criterion specified by @matching_fn, and false if not. If at least * one extent has the specified status, then there is at least one block * in the cluster with that status. Should only be called by code that has * taken i_es_lock. */ static bool __es_scan_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t start, ext4_lblk_t end) { struct extent_status es; __es_find_extent_range(inode, matching_fn, start, end, &es); if (es.es_len == 0) return false; /* no matching extent in the tree */ else if (es.es_lblk <= start && start < es.es_lblk + es.es_len) return true; else if (start <= es.es_lblk && es.es_lblk <= end) return true; else return false; } /* * Locking for __es_scan_range() for external use */ bool ext4_es_scan_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end) { bool ret; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return false; read_lock(&EXT4_I(inode)->i_es_lock); ret = __es_scan_range(inode, matching_fn, lblk, end); read_unlock(&EXT4_I(inode)->i_es_lock); return ret; } /* * __es_scan_clu - search cluster for block with specified status in * extents status tree * * @inode - file containing the cluster * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block in cluster to be searched * * Returns true if at least one extent in the cluster containing @lblk * satisfies the criterion specified by @matching_fn, and false if not. If at * least one extent has the specified status, then there is at least one block * in the cluster with that status. Should only be called by code that has * taken i_es_lock. */ static bool __es_scan_clu(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t lblk_start, lblk_end; lblk_start = EXT4_LBLK_CMASK(sbi, lblk); lblk_end = lblk_start + sbi->s_cluster_ratio - 1; return __es_scan_range(inode, matching_fn, lblk_start, lblk_end); } /* * Locking for __es_scan_clu() for external use */ bool ext4_es_scan_clu(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk) { bool ret; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return false; read_lock(&EXT4_I(inode)->i_es_lock); ret = __es_scan_clu(inode, matching_fn, lblk); read_unlock(&EXT4_I(inode)->i_es_lock); return ret; } static void ext4_es_list_add(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (!list_empty(&ei->i_es_list)) return; spin_lock(&sbi->s_es_lock); if (list_empty(&ei->i_es_list)) { list_add_tail(&ei->i_es_list, &sbi->s_es_list); sbi->s_es_nr_inode++; } spin_unlock(&sbi->s_es_lock); } static void ext4_es_list_del(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); spin_lock(&sbi->s_es_lock); if (!list_empty(&ei->i_es_list)) { list_del_init(&ei->i_es_list); sbi->s_es_nr_inode--; WARN_ON_ONCE(sbi->s_es_nr_inode < 0); } spin_unlock(&sbi->s_es_lock); } static struct extent_status * ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk) { struct extent_status *es; es = kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC); if (es == NULL) return NULL; es->es_lblk = lblk; es->es_len = len; es->es_pblk = pblk; /* * We don't count delayed extent because we never try to reclaim them */ if (!ext4_es_is_delayed(es)) { if (!EXT4_I(inode)->i_es_shk_nr++) ext4_es_list_add(inode); percpu_counter_inc(&EXT4_SB(inode->i_sb)-> s_es_stats.es_stats_shk_cnt); } EXT4_I(inode)->i_es_all_nr++; percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt); return es; } static void ext4_es_free_extent(struct inode *inode, struct extent_status *es) { EXT4_I(inode)->i_es_all_nr--; percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt); /* Decrease the shrink counter when this es is not delayed */ if (!ext4_es_is_delayed(es)) { BUG_ON(EXT4_I(inode)->i_es_shk_nr == 0); if (!--EXT4_I(inode)->i_es_shk_nr) ext4_es_list_del(inode); percpu_counter_dec(&EXT4_SB(inode->i_sb)-> s_es_stats.es_stats_shk_cnt); } kmem_cache_free(ext4_es_cachep, es); } /* * Check whether or not two extents can be merged * Condition: * - logical block number is contiguous * - physical block number is contiguous * - status is equal */ static int ext4_es_can_be_merged(struct extent_status *es1, struct extent_status *es2) { if (ext4_es_type(es1) != ext4_es_type(es2)) return 0; if (((__u64) es1->es_len) + es2->es_len > EXT_MAX_BLOCKS) { pr_warn("ES assertion failed when merging extents. " "The sum of lengths of es1 (%d) and es2 (%d) " "is bigger than allowed file size (%d)\n", es1->es_len, es2->es_len, EXT_MAX_BLOCKS); WARN_ON(1); return 0; } if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk) return 0; if ((ext4_es_is_written(es1) || ext4_es_is_unwritten(es1)) && (ext4_es_pblock(es1) + es1->es_len == ext4_es_pblock(es2))) return 1; if (ext4_es_is_hole(es1)) return 1; /* we need to check delayed extent is without unwritten status */ if (ext4_es_is_delayed(es1) && !ext4_es_is_unwritten(es1)) return 1; return 0; } static struct extent_status * ext4_es_try_to_merge_left(struct inode *inode, struct extent_status *es) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es1; struct rb_node *node; node = rb_prev(&es->rb_node); if (!node) return es; es1 = rb_entry(node, struct extent_status, rb_node); if (ext4_es_can_be_merged(es1, es)) { es1->es_len += es->es_len; if (ext4_es_is_referenced(es)) ext4_es_set_referenced(es1); rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); es = es1; } return es; } static struct extent_status * ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es1; struct rb_node *node; node = rb_next(&es->rb_node); if (!node) return es; es1 = rb_entry(node, struct extent_status, rb_node); if (ext4_es_can_be_merged(es, es1)) { es->es_len += es1->es_len; if (ext4_es_is_referenced(es1)) ext4_es_set_referenced(es); rb_erase(node, &tree->root); ext4_es_free_extent(inode, es1); } return es; } #ifdef ES_AGGRESSIVE_TEST #include "ext4_extents.h" /* Needed when ES_AGGRESSIVE_TEST is defined */ static void ext4_es_insert_extent_ext_check(struct inode *inode, struct extent_status *es) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t ee_block; ext4_fsblk_t ee_start; unsigned short ee_len; int depth, ee_status, es_status; path = ext4_find_extent(inode, es->es_lblk, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return; depth = ext_depth(inode); ex = path[depth].p_ext; if (ex) { ee_block = le32_to_cpu(ex->ee_block); ee_start = ext4_ext_pblock(ex); ee_len = ext4_ext_get_actual_len(ex); ee_status = ext4_ext_is_unwritten(ex) ? 1 : 0; es_status = ext4_es_is_unwritten(es) ? 1 : 0; /* * Make sure ex and es are not overlap when we try to insert * a delayed/hole extent. */ if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) { if (in_range(es->es_lblk, ee_block, ee_len)) { pr_warn("ES insert assertion failed for " "inode: %lu we can find an extent " "at block [%d/%d/%llu/%c], but we " "want to add a delayed/hole extent " "[%d/%d/%llu/%x]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); } goto out; } /* * We don't check ee_block == es->es_lblk, etc. because es * might be a part of whole extent, vice versa. */ if (es->es_lblk < ee_block || ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) { pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), es_status ? 'u' : 'w'); goto out; } if (ee_status ^ es_status) { pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), es_status ? 'u' : 'w'); } } else { /* * We can't find an extent on disk. So we need to make sure * that we don't want to add an written/unwritten extent. */ if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) { pr_warn("ES insert assertion failed for inode: %lu " "can't find an extent at block %d but we want " "to add a written/unwritten extent " "[%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); } } out: ext4_free_ext_path(path); } static void ext4_es_insert_extent_ind_check(struct inode *inode, struct extent_status *es) { struct ext4_map_blocks map; int retval; /* * Here we call ext4_ind_map_blocks to lookup a block mapping because * 'Indirect' structure is defined in indirect.c. So we couldn't * access direct/indirect tree from outside. It is too dirty to define * this function in indirect.c file. */ map.m_lblk = es->es_lblk; map.m_len = es->es_len; retval = ext4_ind_map_blocks(NULL, inode, &map, 0); if (retval > 0) { if (ext4_es_is_delayed(es) || ext4_es_is_hole(es)) { /* * We want to add a delayed/hole extent but this * block has been allocated. */ pr_warn("ES insert assertion failed for inode: %lu " "We can find blocks but we want to add a " "delayed/hole extent [%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); return; } else if (ext4_es_is_written(es)) { if (retval != es->es_len) { pr_warn("ES insert assertion failed for " "inode: %lu retval %d != es_len %d\n", inode->i_ino, retval, es->es_len); return; } if (map.m_pblk != ext4_es_pblock(es)) { pr_warn("ES insert assertion failed for " "inode: %lu m_pblk %llu != " "es_pblk %llu\n", inode->i_ino, map.m_pblk, ext4_es_pblock(es)); return; } } else { /* * We don't need to check unwritten extent because * indirect-based file doesn't have it. */ BUG(); } } else if (retval == 0) { if (ext4_es_is_written(es)) { pr_warn("ES insert assertion failed for inode: %lu " "We can't find the block but we want to add " "a written extent [%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); return; } } } static inline void ext4_es_insert_extent_check(struct inode *inode, struct extent_status *es) { /* * We don't need to worry about the race condition because * caller takes i_data_sem locking. */ BUG_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ext4_es_insert_extent_ext_check(inode, es); else ext4_es_insert_extent_ind_check(inode, es); } #else static inline void ext4_es_insert_extent_check(struct inode *inode, struct extent_status *es) { } #endif static int __es_insert_extent(struct inode *inode, struct extent_status *newes) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct rb_node **p = &tree->root.rb_node; struct rb_node *parent = NULL; struct extent_status *es; while (*p) { parent = *p; es = rb_entry(parent, struct extent_status, rb_node); if (newes->es_lblk < es->es_lblk) { if (ext4_es_can_be_merged(newes, es)) { /* * Here we can modify es_lblk directly * because it isn't overlapped. */ es->es_lblk = newes->es_lblk; es->es_len += newes->es_len; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) ext4_es_store_pblock(es, newes->es_pblk); es = ext4_es_try_to_merge_left(inode, es); goto out; } p = &(*p)->rb_left; } else if (newes->es_lblk > ext4_es_end(es)) { if (ext4_es_can_be_merged(es, newes)) { es->es_len += newes->es_len; es = ext4_es_try_to_merge_right(inode, es); goto out; } p = &(*p)->rb_right; } else { BUG(); return -EINVAL; } } es = ext4_es_alloc_extent(inode, newes->es_lblk, newes->es_len, newes->es_pblk); if (!es) return -ENOMEM; rb_link_node(&es->rb_node, parent, p); rb_insert_color(&es->rb_node, &tree->root); out: tree->cache_es = es; return 0; } /* * ext4_es_insert_extent() adds information to an inode's extent * status tree. * * Return 0 on success, error code on failure. */ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status) { struct extent_status newes; ext4_lblk_t end = lblk + len - 1; int err = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return 0; es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n", lblk, len, pblk, status, inode->i_ino); if (!len) return 0; BUG_ON(end < lblk); if ((status & EXTENT_STATUS_DELAYED) && (status & EXTENT_STATUS_WRITTEN)) { ext4_warning(inode->i_sb, "Inserting extent [%u/%u] as " " delayed and written which can potentially " " cause data loss.", lblk, len); WARN_ON(1); } newes.es_lblk = lblk; newes.es_len = len; ext4_es_store_pblock_status(&newes, pblk, status); trace_ext4_es_insert_extent(inode, &newes); ext4_es_insert_extent_check(inode, &newes); write_lock(&EXT4_I(inode)->i_es_lock); err = __es_remove_extent(inode, lblk, end, NULL); if (err != 0) goto error; retry: err = __es_insert_extent(inode, &newes); if (err == -ENOMEM && __es_shrink(EXT4_SB(inode->i_sb), 128, EXT4_I(inode))) goto retry; if (err == -ENOMEM && !ext4_es_is_delayed(&newes)) err = 0; if (sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) && (status & EXTENT_STATUS_WRITTEN || status & EXTENT_STATUS_UNWRITTEN)) __revise_pending(inode, lblk, len); error: write_unlock(&EXT4_I(inode)->i_es_lock); ext4_es_print_tree(inode); return err; } /* * ext4_es_cache_extent() inserts information into the extent status * tree if and only if there isn't information about the range in * question already. */ void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status) { struct extent_status *es; struct extent_status newes; ext4_lblk_t end = lblk + len - 1; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; newes.es_lblk = lblk; newes.es_len = len; ext4_es_store_pblock_status(&newes, pblk, status); trace_ext4_es_cache_extent(inode, &newes); if (!len) return; BUG_ON(end < lblk); write_lock(&EXT4_I(inode)->i_es_lock); es = __es_tree_search(&EXT4_I(inode)->i_es_tree.root, lblk); if (!es || es->es_lblk > end) __es_insert_extent(inode, &newes); write_unlock(&EXT4_I(inode)->i_es_lock); } /* * ext4_es_lookup_extent() looks up an extent in extent status tree. * * ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks. * * Return: 1 on found, 0 on not */ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t *next_lblk, struct extent_status *es) { struct ext4_es_tree *tree; struct ext4_es_stats *stats; struct extent_status *es1 = NULL; struct rb_node *node; int found = 0; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return 0; trace_ext4_es_lookup_extent_enter(inode, lblk); es_debug("lookup extent in block %u\n", lblk); tree = &EXT4_I(inode)->i_es_tree; read_lock(&EXT4_I(inode)->i_es_lock); /* find extent in cache firstly */ es->es_lblk = es->es_len = es->es_pblk = 0; if (tree->cache_es) { es1 = tree->cache_es; if (in_range(lblk, es1->es_lblk, es1->es_len)) { es_debug("%u cached by [%u/%u)\n", lblk, es1->es_lblk, es1->es_len); found = 1; goto out; } } node = tree->root.rb_node; while (node) { es1 = rb_entry(node, struct extent_status, rb_node); if (lblk < es1->es_lblk) node = node->rb_left; else if (lblk > ext4_es_end(es1)) node = node->rb_right; else { found = 1; break; } } out: stats = &EXT4_SB(inode->i_sb)->s_es_stats; if (found) { BUG_ON(!es1); es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; if (!ext4_es_is_referenced(es1)) ext4_es_set_referenced(es1); percpu_counter_inc(&stats->es_stats_cache_hits); if (next_lblk) { node = rb_next(&es1->rb_node); if (node) { es1 = rb_entry(node, struct extent_status, rb_node); *next_lblk = es1->es_lblk; } else *next_lblk = 0; } } else { percpu_counter_inc(&stats->es_stats_cache_misses); } read_unlock(&EXT4_I(inode)->i_es_lock); trace_ext4_es_lookup_extent_exit(inode, es, found); return found; } struct rsvd_count { int ndelonly; bool first_do_lblk_found; ext4_lblk_t first_do_lblk; ext4_lblk_t last_do_lblk; struct extent_status *left_es; bool partial; ext4_lblk_t lclu; }; /* * init_rsvd - initialize reserved count data before removing block range * in file from extent status tree * * @inode - file containing range * @lblk - first block in range * @es - pointer to first extent in range * @rc - pointer to reserved count data * * Assumes es is not NULL */ static void init_rsvd(struct inode *inode, ext4_lblk_t lblk, struct extent_status *es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct rb_node *node; rc->ndelonly = 0; /* * for bigalloc, note the first delonly block in the range has not * been found, record the extent containing the block to the left of * the region to be removed, if any, and note that there's no partial * cluster to track */ if (sbi->s_cluster_ratio > 1) { rc->first_do_lblk_found = false; if (lblk > es->es_lblk) { rc->left_es = es; } else { node = rb_prev(&es->rb_node); rc->left_es = node ? rb_entry(node, struct extent_status, rb_node) : NULL; } rc->partial = false; } } /* * count_rsvd - count the clusters containing delayed and not unwritten * (delonly) blocks in a range within an extent and add to * the running tally in rsvd_count * * @inode - file containing extent * @lblk - first block in range * @len - length of range in blocks * @es - pointer to extent containing clusters to be counted * @rc - pointer to reserved count data * * Tracks partial clusters found at the beginning and end of extents so * they aren't overcounted when they span adjacent extents */ static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len, struct extent_status *es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t i, end, nclu; if (!ext4_es_is_delonly(es)) return; WARN_ON(len <= 0); if (sbi->s_cluster_ratio == 1) { rc->ndelonly += (int) len; return; } /* bigalloc */ i = (lblk < es->es_lblk) ? es->es_lblk : lblk; end = lblk + (ext4_lblk_t) len - 1; end = (end > ext4_es_end(es)) ? ext4_es_end(es) : end; /* record the first block of the first delonly extent seen */ if (!rc->first_do_lblk_found) { rc->first_do_lblk = i; rc->first_do_lblk_found = true; } /* update the last lblk in the region seen so far */ rc->last_do_lblk = end; /* * if we're tracking a partial cluster and the current extent * doesn't start with it, count it and stop tracking */ if (rc->partial && (rc->lclu != EXT4_B2C(sbi, i))) { rc->ndelonly++; rc->partial = false; } /* * if the first cluster doesn't start on a cluster boundary but * ends on one, count it */ if (EXT4_LBLK_COFF(sbi, i) != 0) { if (end >= EXT4_LBLK_CFILL(sbi, i)) { rc->ndelonly++; rc->partial = false; i = EXT4_LBLK_CFILL(sbi, i) + 1; } } /* * if the current cluster starts on a cluster boundary, count the * number of whole delonly clusters in the extent */ if ((i + sbi->s_cluster_ratio - 1) <= end) { nclu = (end - i + 1) >> sbi->s_cluster_bits; rc->ndelonly += nclu; i += nclu << sbi->s_cluster_bits; } /* * start tracking a partial cluster if there's a partial at the end * of the current extent and we're not already tracking one */ if (!rc->partial && i <= end) { rc->partial = true; rc->lclu = EXT4_B2C(sbi, i); } } /* * __pr_tree_search - search for a pending cluster reservation * * @root - root of pending reservation tree * @lclu - logical cluster to search for * * Returns the pending reservation for the cluster identified by @lclu * if found. If not, returns a reservation for the next cluster if any, * and if not, returns NULL. */ static struct pending_reservation *__pr_tree_search(struct rb_root *root, ext4_lblk_t lclu) { struct rb_node *node = root->rb_node; struct pending_reservation *pr = NULL; while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); if (lclu < pr->lclu) node = node->rb_left; else if (lclu > pr->lclu) node = node->rb_right; else return pr; } if (pr && lclu < pr->lclu) return pr; if (pr && lclu > pr->lclu) { node = rb_next(&pr->rb_node); return node ? rb_entry(node, struct pending_reservation, rb_node) : NULL; } return NULL; } /* * get_rsvd - calculates and returns the number of cluster reservations to be * released when removing a block range from the extent status tree * and releases any pending reservations within the range * * @inode - file containing block range * @end - last block in range * @right_es - pointer to extent containing next block beyond end or NULL * @rc - pointer to reserved count data * * The number of reservations to be released is equal to the number of * clusters containing delayed and not unwritten (delonly) blocks within * the range, minus the number of clusters still containing delonly blocks * at the ends of the range, and minus the number of pending reservations * within the range. */ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end, struct extent_status *right_es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct pending_reservation *pr; struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; struct rb_node *node; ext4_lblk_t first_lclu, last_lclu; bool left_delonly, right_delonly, count_pending; struct extent_status *es; if (sbi->s_cluster_ratio > 1) { /* count any remaining partial cluster */ if (rc->partial) rc->ndelonly++; if (rc->ndelonly == 0) return 0; first_lclu = EXT4_B2C(sbi, rc->first_do_lblk); last_lclu = EXT4_B2C(sbi, rc->last_do_lblk); /* * decrease the delonly count by the number of clusters at the * ends of the range that still contain delonly blocks - * these clusters still need to be reserved */ left_delonly = right_delonly = false; es = rc->left_es; while (es && ext4_es_end(es) >= EXT4_LBLK_CMASK(sbi, rc->first_do_lblk)) { if (ext4_es_is_delonly(es)) { rc->ndelonly--; left_delonly = true; break; } node = rb_prev(&es->rb_node); if (!node) break; es = rb_entry(node, struct extent_status, rb_node); } if (right_es && (!left_delonly || first_lclu != last_lclu)) { if (end < ext4_es_end(right_es)) { es = right_es; } else { node = rb_next(&right_es->rb_node); es = node ? rb_entry(node, struct extent_status, rb_node) : NULL; } while (es && es->es_lblk <= EXT4_LBLK_CFILL(sbi, rc->last_do_lblk)) { if (ext4_es_is_delonly(es)) { rc->ndelonly--; right_delonly = true; break; } node = rb_next(&es->rb_node); if (!node) break; es = rb_entry(node, struct extent_status, rb_node); } } /* * Determine the block range that should be searched for * pending reservations, if any. Clusters on the ends of the * original removed range containing delonly blocks are * excluded. They've already been accounted for and it's not * possible to determine if an associated pending reservation * should be released with the information available in the * extents status tree. */ if (first_lclu == last_lclu) { if (left_delonly | right_delonly) count_pending = false; else count_pending = true; } else { if (left_delonly) first_lclu++; if (right_delonly) last_lclu--; if (first_lclu <= last_lclu) count_pending = true; else count_pending = false; } /* * a pending reservation found between first_lclu and last_lclu * represents an allocated cluster that contained at least one * delonly block, so the delonly total must be reduced by one * for each pending reservation found and released */ if (count_pending) { pr = __pr_tree_search(&tree->root, first_lclu); while (pr && pr->lclu <= last_lclu) { rc->ndelonly--; node = rb_next(&pr->rb_node); rb_erase(&pr->rb_node, &tree->root); kmem_cache_free(ext4_pending_cachep, pr); if (!node) break; pr = rb_entry(node, struct pending_reservation, rb_node); } } } return rc->ndelonly; } /* * __es_remove_extent - removes block range from extent status tree * * @inode - file containing range * @lblk - first block in range * @end - last block in range * @reserved - number of cluster reservations released * * If @reserved is not NULL and delayed allocation is enabled, counts * block/cluster reservations freed by removing range and if bigalloc * enabled cancels pending reservations as needed. Returns 0 on success, * error code on failure. */ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end, int *reserved) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct rb_node *node; struct extent_status *es; struct extent_status orig_es; ext4_lblk_t len1, len2; ext4_fsblk_t block; int err; bool count_reserved = true; struct rsvd_count rc; if (reserved == NULL || !test_opt(inode->i_sb, DELALLOC)) count_reserved = false; retry: err = 0; es = __es_tree_search(&tree->root, lblk); if (!es) goto out; if (es->es_lblk > end) goto out; /* Simply invalidate cache_es. */ tree->cache_es = NULL; if (count_reserved) init_rsvd(inode, lblk, es, &rc); orig_es.es_lblk = es->es_lblk; orig_es.es_len = es->es_len; orig_es.es_pblk = es->es_pblk; len1 = lblk > es->es_lblk ? lblk - es->es_lblk : 0; len2 = ext4_es_end(es) > end ? ext4_es_end(es) - end : 0; if (len1 > 0) es->es_len = len1; if (len2 > 0) { if (len1 > 0) { struct extent_status newes; newes.es_lblk = end + 1; newes.es_len = len2; block = 0x7FDEADBEEFULL; if (ext4_es_is_written(&orig_es) || ext4_es_is_unwritten(&orig_es)) block = ext4_es_pblock(&orig_es) + orig_es.es_len - len2; ext4_es_store_pblock_status(&newes, block, ext4_es_status(&orig_es)); err = __es_insert_extent(inode, &newes); if (err) { es->es_lblk = orig_es.es_lblk; es->es_len = orig_es.es_len; if ((err == -ENOMEM) && __es_shrink(EXT4_SB(inode->i_sb), 128, EXT4_I(inode))) goto retry; goto out; } } else { es->es_lblk = end + 1; es->es_len = len2; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) { block = orig_es.es_pblk + orig_es.es_len - len2; ext4_es_store_pblock(es, block); } } if (count_reserved) count_rsvd(inode, lblk, orig_es.es_len - len1 - len2, &orig_es, &rc); goto out; } if (len1 > 0) { if (count_reserved) count_rsvd(inode, lblk, orig_es.es_len - len1, &orig_es, &rc); node = rb_next(&es->rb_node); if (node) es = rb_entry(node, struct extent_status, rb_node); else es = NULL; } while (es && ext4_es_end(es) <= end) { if (count_reserved) count_rsvd(inode, es->es_lblk, es->es_len, es, &rc); node = rb_next(&es->rb_node); rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); if (!node) { es = NULL; break; } es = rb_entry(node, struct extent_status, rb_node); } if (es && es->es_lblk < end + 1) { ext4_lblk_t orig_len = es->es_len; len1 = ext4_es_end(es) - end; if (count_reserved) count_rsvd(inode, es->es_lblk, orig_len - len1, es, &rc); es->es_lblk = end + 1; es->es_len = len1; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) { block = es->es_pblk + orig_len - len1; ext4_es_store_pblock(es, block); } } if (count_reserved) *reserved = get_rsvd(inode, end, es, &rc); out: return err; } /* * ext4_es_remove_extent - removes block range from extent status tree * * @inode - file containing range * @lblk - first block in range * @len - number of blocks to remove * * Reduces block/cluster reservation count and for bigalloc cancels pending * reservations as needed. Returns 0 on success, error code on failure. */ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len) { ext4_lblk_t end; int err = 0; int reserved = 0; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return 0; trace_ext4_es_remove_extent(inode, lblk, len); es_debug("remove [%u/%u) from extent status tree of inode %lu\n", lblk, len, inode->i_ino); if (!len) return err; end = lblk + len - 1; BUG_ON(end < lblk); /* * ext4_clear_inode() depends on us taking i_es_lock unconditionally * so that we are sure __es_shrink() is done with the inode before it * is reclaimed. */ write_lock(&EXT4_I(inode)->i_es_lock); err = __es_remove_extent(inode, lblk, end, &reserved); write_unlock(&EXT4_I(inode)->i_es_lock); ext4_es_print_tree(inode); ext4_da_release_space(inode, reserved); return err; } static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei) { struct ext4_inode_info *ei; struct ext4_es_stats *es_stats; ktime_t start_time; u64 scan_time; int nr_to_walk; int nr_shrunk = 0; int retried = 0, nr_skipped = 0; es_stats = &sbi->s_es_stats; start_time = ktime_get(); retry: spin_lock(&sbi->s_es_lock); nr_to_walk = sbi->s_es_nr_inode; while (nr_to_walk-- > 0) { if (list_empty(&sbi->s_es_list)) { spin_unlock(&sbi->s_es_lock); goto out; } ei = list_first_entry(&sbi->s_es_list, struct ext4_inode_info, i_es_list); /* Move the inode to the tail */ list_move_tail(&ei->i_es_list, &sbi->s_es_list); /* * Normally we try hard to avoid shrinking precached inodes, * but we will as a last resort. */ if (!retried && ext4_test_inode_state(&ei->vfs_inode, EXT4_STATE_EXT_PRECACHED)) { nr_skipped++; continue; } if (ei == locked_ei || !write_trylock(&ei->i_es_lock)) { nr_skipped++; continue; } /* * Now we hold i_es_lock which protects us from inode reclaim * freeing inode under us */ spin_unlock(&sbi->s_es_lock); nr_shrunk += es_reclaim_extents(ei, &nr_to_scan); write_unlock(&ei->i_es_lock); if (nr_to_scan <= 0) goto out; spin_lock(&sbi->s_es_lock); } spin_unlock(&sbi->s_es_lock); /* * If we skipped any inodes, and we weren't able to make any * forward progress, try again to scan precached inodes. */ if ((nr_shrunk == 0) && nr_skipped && !retried) { retried++; goto retry; } if (locked_ei && nr_shrunk == 0) nr_shrunk = es_reclaim_extents(locked_ei, &nr_to_scan); out: scan_time = ktime_to_ns(ktime_sub(ktime_get(), start_time)); if (likely(es_stats->es_stats_scan_time)) es_stats->es_stats_scan_time = (scan_time + es_stats->es_stats_scan_time*3) / 4; else es_stats->es_stats_scan_time = scan_time; if (scan_time > es_stats->es_stats_max_scan_time) es_stats->es_stats_max_scan_time = scan_time; if (likely(es_stats->es_stats_shrunk)) es_stats->es_stats_shrunk = (nr_shrunk + es_stats->es_stats_shrunk*3) / 4; else es_stats->es_stats_shrunk = nr_shrunk; trace_ext4_es_shrink(sbi->s_sb, nr_shrunk, scan_time, nr_skipped, retried); return nr_shrunk; } static unsigned long ext4_es_count(struct shrinker *shrink, struct shrink_control *sc) { unsigned long nr; struct ext4_sb_info *sbi; sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker); nr = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_count(sbi->s_sb, sc->nr_to_scan, nr); return nr; } static unsigned long ext4_es_scan(struct shrinker *shrink, struct shrink_control *sc) { struct ext4_sb_info *sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker); int nr_to_scan = sc->nr_to_scan; int ret, nr_shrunk; ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_enter(sbi->s_sb, nr_to_scan, ret); nr_shrunk = __es_shrink(sbi, nr_to_scan, NULL); ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_exit(sbi->s_sb, nr_shrunk, ret); return nr_shrunk; } int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v) { struct ext4_sb_info *sbi = EXT4_SB((struct super_block *) seq->private); struct ext4_es_stats *es_stats = &sbi->s_es_stats; struct ext4_inode_info *ei, *max = NULL; unsigned int inode_cnt = 0; if (v != SEQ_START_TOKEN) return 0; /* here we just find an inode that has the max nr. of objects */ spin_lock(&sbi->s_es_lock); list_for_each_entry(ei, &sbi->s_es_list, i_es_list) { inode_cnt++; if (max && max->i_es_all_nr < ei->i_es_all_nr) max = ei; else if (!max) max = ei; } spin_unlock(&sbi->s_es_lock); seq_printf(seq, "stats:\n %lld objects\n %lld reclaimable objects\n", percpu_counter_sum_positive(&es_stats->es_stats_all_cnt), percpu_counter_sum_positive(&es_stats->es_stats_shk_cnt)); seq_printf(seq, " %lld/%lld cache hits/misses\n", percpu_counter_sum_positive(&es_stats->es_stats_cache_hits), percpu_counter_sum_positive(&es_stats->es_stats_cache_misses)); if (inode_cnt) seq_printf(seq, " %d inodes on list\n", inode_cnt); seq_printf(seq, "average:\n %llu us scan time\n", div_u64(es_stats->es_stats_scan_time, 1000)); seq_printf(seq, " %lu shrunk objects\n", es_stats->es_stats_shrunk); if (inode_cnt) seq_printf(seq, "maximum:\n %lu inode (%u objects, %u reclaimable)\n" " %llu us max scan time\n", max->vfs_inode.i_ino, max->i_es_all_nr, max->i_es_shk_nr, div_u64(es_stats->es_stats_max_scan_time, 1000)); return 0; } int ext4_es_register_shrinker(struct ext4_sb_info *sbi) { int err; /* Make sure we have enough bits for physical block number */ BUILD_BUG_ON(ES_SHIFT < 48); INIT_LIST_HEAD(&sbi->s_es_list); sbi->s_es_nr_inode = 0; spin_lock_init(&sbi->s_es_lock); sbi->s_es_stats.es_stats_shrunk = 0; err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_hits, 0, GFP_KERNEL); if (err) return err; err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_misses, 0, GFP_KERNEL); if (err) goto err1; sbi->s_es_stats.es_stats_scan_time = 0; sbi->s_es_stats.es_stats_max_scan_time = 0; err = percpu_counter_init(&sbi->s_es_stats.es_stats_all_cnt, 0, GFP_KERNEL); if (err) goto err2; err = percpu_counter_init(&sbi->s_es_stats.es_stats_shk_cnt, 0, GFP_KERNEL); if (err) goto err3; sbi->s_es_shrinker.scan_objects = ext4_es_scan; sbi->s_es_shrinker.count_objects = ext4_es_count; sbi->s_es_shrinker.seeks = DEFAULT_SEEKS; err = register_shrinker(&sbi->s_es_shrinker, "ext4-es:%s", sbi->s_sb->s_id); if (err) goto err4; return 0; err4: percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); err3: percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); err2: percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); err1: percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits); return err; } void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi) { percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits); percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); unregister_shrinker(&sbi->s_es_shrinker); } /* * Shrink extents in given inode from ei->i_es_shrink_lblk till end. Scan at * most *nr_to_scan extents, update *nr_to_scan accordingly. * * Return 0 if we hit end of tree / interval, 1 if we exhausted nr_to_scan. * Increment *nr_shrunk by the number of reclaimed extents. Also update * ei->i_es_shrink_lblk to where we should continue scanning. */ static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end, int *nr_to_scan, int *nr_shrunk) { struct inode *inode = &ei->vfs_inode; struct ext4_es_tree *tree = &ei->i_es_tree; struct extent_status *es; struct rb_node *node; es = __es_tree_search(&tree->root, ei->i_es_shrink_lblk); if (!es) goto out_wrap; while (*nr_to_scan > 0) { if (es->es_lblk > end) { ei->i_es_shrink_lblk = end + 1; return 0; } (*nr_to_scan)--; node = rb_next(&es->rb_node); /* * We can't reclaim delayed extent from status tree because * fiemap, bigallic, and seek_data/hole need to use it. */ if (ext4_es_is_delayed(es)) goto next; if (ext4_es_is_referenced(es)) { ext4_es_clear_referenced(es); goto next; } rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); (*nr_shrunk)++; next: if (!node) goto out_wrap; es = rb_entry(node, struct extent_status, rb_node); } ei->i_es_shrink_lblk = es->es_lblk; return 1; out_wrap: ei->i_es_shrink_lblk = 0; return 0; } static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan) { struct inode *inode = &ei->vfs_inode; int nr_shrunk = 0; ext4_lblk_t start = ei->i_es_shrink_lblk; static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); if (ei->i_es_shk_nr == 0) return 0; if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED) && __ratelimit(&_rs)) ext4_warning(inode->i_sb, "forced shrink of precached extents"); if (!es_do_reclaim_extents(ei, EXT_MAX_BLOCKS, nr_to_scan, &nr_shrunk) && start != 0) es_do_reclaim_extents(ei, start - 1, nr_to_scan, &nr_shrunk); ei->i_es_tree.cache_es = NULL; return nr_shrunk; } /* * Called to support EXT4_IOC_CLEAR_ES_CACHE. We can only remove * discretionary entries from the extent status cache. (Some entries * must be present for proper operations.) */ void ext4_clear_inode_es(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct extent_status *es; struct ext4_es_tree *tree; struct rb_node *node; write_lock(&ei->i_es_lock); tree = &EXT4_I(inode)->i_es_tree; tree->cache_es = NULL; node = rb_first(&tree->root); while (node) { es = rb_entry(node, struct extent_status, rb_node); node = rb_next(node); if (!ext4_es_is_delayed(es)) { rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); } } ext4_clear_inode_state(inode, EXT4_STATE_EXT_PRECACHED); write_unlock(&ei->i_es_lock); } #ifdef ES_DEBUG__ static void ext4_print_pending_tree(struct inode *inode) { struct ext4_pending_tree *tree; struct rb_node *node; struct pending_reservation *pr; printk(KERN_DEBUG "pending reservations for inode %lu:", inode->i_ino); tree = &EXT4_I(inode)->i_pending_tree; node = rb_first(&tree->root); while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); printk(KERN_DEBUG " %u", pr->lclu); node = rb_next(node); } printk(KERN_DEBUG "\n"); } #else #define ext4_print_pending_tree(inode) #endif int __init ext4_init_pending(void) { ext4_pending_cachep = kmem_cache_create("ext4_pending_reservation", sizeof(struct pending_reservation), 0, (SLAB_RECLAIM_ACCOUNT), NULL); if (ext4_pending_cachep == NULL) return -ENOMEM; return 0; } void ext4_exit_pending(void) { kmem_cache_destroy(ext4_pending_cachep); } void ext4_init_pending_tree(struct ext4_pending_tree *tree) { tree->root = RB_ROOT; } /* * __get_pending - retrieve a pointer to a pending reservation * * @inode - file containing the pending cluster reservation * @lclu - logical cluster of interest * * Returns a pointer to a pending reservation if it's a member of * the set, and NULL if not. Must be called holding i_es_lock. */ static struct pending_reservation *__get_pending(struct inode *inode, ext4_lblk_t lclu) { struct ext4_pending_tree *tree; struct rb_node *node; struct pending_reservation *pr = NULL; tree = &EXT4_I(inode)->i_pending_tree; node = (&tree->root)->rb_node; while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); if (lclu < pr->lclu) node = node->rb_left; else if (lclu > pr->lclu) node = node->rb_right; else if (lclu == pr->lclu) return pr; } return NULL; } /* * __insert_pending - adds a pending cluster reservation to the set of * pending reservations * * @inode - file containing the cluster * @lblk - logical block in the cluster to be added * * Returns 0 on successful insertion and -ENOMEM on failure. If the * pending reservation is already in the set, returns successfully. */ static int __insert_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; struct rb_node **p = &tree->root.rb_node; struct rb_node *parent = NULL; struct pending_reservation *pr; ext4_lblk_t lclu; int ret = 0; lclu = EXT4_B2C(sbi, lblk); /* search to find parent for insertion */ while (*p) { parent = *p; pr = rb_entry(parent, struct pending_reservation, rb_node); if (lclu < pr->lclu) { p = &(*p)->rb_left; } else if (lclu > pr->lclu) { p = &(*p)->rb_right; } else { /* pending reservation already inserted */ goto out; } } pr = kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); if (pr == NULL) { ret = -ENOMEM; goto out; } pr->lclu = lclu; rb_link_node(&pr->rb_node, parent, p); rb_insert_color(&pr->rb_node, &tree->root); out: return ret; } /* * __remove_pending - removes a pending cluster reservation from the set * of pending reservations * * @inode - file containing the cluster * @lblk - logical block in the pending cluster reservation to be removed * * Returns successfully if pending reservation is not a member of the set. */ static void __remove_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct pending_reservation *pr; struct ext4_pending_tree *tree; pr = __get_pending(inode, EXT4_B2C(sbi, lblk)); if (pr != NULL) { tree = &EXT4_I(inode)->i_pending_tree; rb_erase(&pr->rb_node, &tree->root); kmem_cache_free(ext4_pending_cachep, pr); } } /* * ext4_remove_pending - removes a pending cluster reservation from the set * of pending reservations * * @inode - file containing the cluster * @lblk - logical block in the pending cluster reservation to be removed * * Locking for external use of __remove_pending. */ void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_inode_info *ei = EXT4_I(inode); write_lock(&ei->i_es_lock); __remove_pending(inode, lblk); write_unlock(&ei->i_es_lock); } /* * ext4_is_pending - determine whether a cluster has a pending reservation * on it * * @inode - file containing the cluster * @lblk - logical block in the cluster * * Returns true if there's a pending reservation for the cluster in the * set of pending reservations, and false if not. */ bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); bool ret; read_lock(&ei->i_es_lock); ret = (bool)(__get_pending(inode, EXT4_B2C(sbi, lblk)) != NULL); read_unlock(&ei->i_es_lock); return ret; } /* * ext4_es_insert_delayed_block - adds a delayed block to the extents status * tree, adding a pending reservation where * needed * * @inode - file containing the newly added block * @lblk - logical block to be added * @allocated - indicates whether a physical cluster has been allocated for * the logical cluster that contains the block * * Returns 0 on success, negative error code on failure. */ int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, bool allocated) { struct extent_status newes; int err = 0; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return 0; es_debug("add [%u/1) delayed to extent status tree of inode %lu\n", lblk, inode->i_ino); newes.es_lblk = lblk; newes.es_len = 1; ext4_es_store_pblock_status(&newes, ~0, EXTENT_STATUS_DELAYED); trace_ext4_es_insert_delayed_block(inode, &newes, allocated); ext4_es_insert_extent_check(inode, &newes); write_lock(&EXT4_I(inode)->i_es_lock); err = __es_remove_extent(inode, lblk, lblk, NULL); if (err != 0) goto error; retry: err = __es_insert_extent(inode, &newes); if (err == -ENOMEM && __es_shrink(EXT4_SB(inode->i_sb), 128, EXT4_I(inode))) goto retry; if (err != 0) goto error; if (allocated) __insert_pending(inode, lblk); error: write_unlock(&EXT4_I(inode)->i_es_lock); ext4_es_print_tree(inode); ext4_print_pending_tree(inode); return err; } /* * __es_delayed_clu - count number of clusters containing blocks that * are delayed only * * @inode - file containing block range * @start - logical block defining start of range * @end - logical block defining end of range * * Returns the number of clusters containing only delayed (not delayed * and unwritten) blocks in the range specified by @start and @end. Any * cluster or part of a cluster within the range and containing a delayed * and not unwritten block within the range is counted as a whole cluster. */ static unsigned int __es_delayed_clu(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct rb_node *node; ext4_lblk_t first_lclu, last_lclu; unsigned long long last_counted_lclu; unsigned int n = 0; /* guaranteed to be unequal to any ext4_lblk_t value */ last_counted_lclu = ~0ULL; es = __es_tree_search(&tree->root, start); while (es && (es->es_lblk <= end)) { if (ext4_es_is_delonly(es)) { if (es->es_lblk <= start) first_lclu = EXT4_B2C(sbi, start); else first_lclu = EXT4_B2C(sbi, es->es_lblk); if (ext4_es_end(es) >= end) last_lclu = EXT4_B2C(sbi, end); else last_lclu = EXT4_B2C(sbi, ext4_es_end(es)); if (first_lclu == last_counted_lclu) n += last_lclu - first_lclu; else n += last_lclu - first_lclu + 1; last_counted_lclu = last_lclu; } node = rb_next(&es->rb_node); if (!node) break; es = rb_entry(node, struct extent_status, rb_node); } return n; } /* * ext4_es_delayed_clu - count number of clusters containing blocks that * are both delayed and unwritten * * @inode - file containing block range * @lblk - logical block defining start of range * @len - number of blocks in range * * Locking for external use of __es_delayed_clu(). */ unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len) { struct ext4_inode_info *ei = EXT4_I(inode); ext4_lblk_t end; unsigned int n; if (len == 0) return 0; end = lblk + len - 1; WARN_ON(end < lblk); read_lock(&ei->i_es_lock); n = __es_delayed_clu(inode, lblk, end); read_unlock(&ei->i_es_lock); return n; } /* * __revise_pending - makes, cancels, or leaves unchanged pending cluster * reservations for a specified block range depending * upon the presence or absence of delayed blocks * outside the range within clusters at the ends of the * range * * @inode - file containing the range * @lblk - logical block defining the start of range * @len - length of range in blocks * * Used after a newly allocated extent is added to the extents status tree. * Requires that the extents in the range have either written or unwritten * status. Must be called while holding i_es_lock. */ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t end = lblk + len - 1; ext4_lblk_t first, last; bool f_del = false, l_del = false; if (len == 0) return; /* * Two cases - block range within single cluster and block range * spanning two or more clusters. Note that a cluster belonging * to a range starting and/or ending on a cluster boundary is treated * as if it does not contain a delayed extent. The new range may * have allocated space for previously delayed blocks out to the * cluster boundary, requiring that any pre-existing pending * reservation be canceled. Because this code only looks at blocks * outside the range, it should revise pending reservations * correctly even if the extent represented by the range can't be * inserted in the extents status tree due to ENOSPC. */ if (EXT4_B2C(sbi, lblk) == EXT4_B2C(sbi, end)) { first = EXT4_LBLK_CMASK(sbi, lblk); if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); if (f_del) { __insert_pending(inode, first); } else { last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); if (l_del) __insert_pending(inode, last); else __remove_pending(inode, last); } } else { first = EXT4_LBLK_CMASK(sbi, lblk); if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); if (f_del) __insert_pending(inode, first); else __remove_pending(inode, first); last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); if (l_del) __insert_pending(inode, last); else __remove_pending(inode, last); } } |
| 2138 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 | // SPDX-License-Identifier: GPL-2.0 /* * Zoned block device handling * * Copyright (c) 2015, Hannes Reinecke * Copyright (c) 2015, SUSE Linux GmbH * * Copyright (c) 2016, Damien Le Moal * Copyright (c) 2016, Western Digital */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/rbtree.h> #include <linux/blkdev.h> #include <linux/blk-mq.h> #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/sched/mm.h> #include "blk.h" #define ZONE_COND_NAME(name) [BLK_ZONE_COND_##name] = #name static const char *const zone_cond_name[] = { ZONE_COND_NAME(NOT_WP), ZONE_COND_NAME(EMPTY), ZONE_COND_NAME(IMP_OPEN), ZONE_COND_NAME(EXP_OPEN), ZONE_COND_NAME(CLOSED), ZONE_COND_NAME(READONLY), ZONE_COND_NAME(FULL), ZONE_COND_NAME(OFFLINE), }; #undef ZONE_COND_NAME /** * blk_zone_cond_str - Return string XXX in BLK_ZONE_COND_XXX. * @zone_cond: BLK_ZONE_COND_XXX. * * Description: Centralize block layer function to convert BLK_ZONE_COND_XXX * into string format. Useful in the debugging and tracing zone conditions. For * invalid BLK_ZONE_COND_XXX it returns string "UNKNOWN". */ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond) { static const char *zone_cond_str = "UNKNOWN"; if (zone_cond < ARRAY_SIZE(zone_cond_name) && zone_cond_name[zone_cond]) zone_cond_str = zone_cond_name[zone_cond]; return zone_cond_str; } EXPORT_SYMBOL_GPL(blk_zone_cond_str); /* * Return true if a request is a write requests that needs zone write locking. */ bool blk_req_needs_zone_write_lock(struct request *rq) { if (blk_rq_is_passthrough(rq)) return false; if (!rq->q->disk->seq_zones_wlock) return false; if (bdev_op_is_zoned_write(rq->q->disk->part0, req_op(rq))) return blk_rq_zone_is_seq(rq); return false; } EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock); bool blk_req_zone_write_trylock(struct request *rq) { unsigned int zno = blk_rq_zone_no(rq); if (test_and_set_bit(zno, rq->q->disk->seq_zones_wlock)) return false; WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED); rq->rq_flags |= RQF_ZONE_WRITE_LOCKED; return true; } EXPORT_SYMBOL_GPL(blk_req_zone_write_trylock); void __blk_req_zone_write_lock(struct request *rq) { if (WARN_ON_ONCE(test_and_set_bit(blk_rq_zone_no(rq), rq->q->disk->seq_zones_wlock))) return; WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED); rq->rq_flags |= RQF_ZONE_WRITE_LOCKED; } EXPORT_SYMBOL_GPL(__blk_req_zone_write_lock); void __blk_req_zone_write_unlock(struct request *rq) { rq->rq_flags &= ~RQF_ZONE_WRITE_LOCKED; if (rq->q->disk->seq_zones_wlock) WARN_ON_ONCE(!test_and_clear_bit(blk_rq_zone_no(rq), rq->q->disk->seq_zones_wlock)); } EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock); /** * bdev_nr_zones - Get number of zones * @bdev: Target device * * Return the total number of zones of a zoned block device. For a block * device without zone capabilities, the number of zones is always 0. */ unsigned int bdev_nr_zones(struct block_device *bdev) { sector_t zone_sectors = bdev_zone_sectors(bdev); if (!bdev_is_zoned(bdev)) return 0; return (bdev_nr_sectors(bdev) + zone_sectors - 1) >> ilog2(zone_sectors); } EXPORT_SYMBOL_GPL(bdev_nr_zones); /** * blkdev_report_zones - Get zones information * @bdev: Target block device * @sector: Sector from which to report zones * @nr_zones: Maximum number of zones to report * @cb: Callback function called for each reported zone * @data: Private data for the callback * * Description: * Get zone information starting from the zone containing @sector for at most * @nr_zones, and call @cb for each zone reported by the device. * To report all zones in a device starting from @sector, the BLK_ALL_ZONES * constant can be passed to @nr_zones. * Returns the number of zones reported by the device, or a negative errno * value in case of failure. * * Note: The caller must use memalloc_noXX_save/restore() calls to control * memory allocations done within this function. */ int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data) { struct gendisk *disk = bdev->bd_disk; sector_t capacity = get_capacity(disk); if (!bdev_is_zoned(bdev) || WARN_ON_ONCE(!disk->fops->report_zones)) return -EOPNOTSUPP; if (!nr_zones || sector >= capacity) return 0; return disk->fops->report_zones(disk, sector, nr_zones, cb, data); } EXPORT_SYMBOL_GPL(blkdev_report_zones); static inline unsigned long *blk_alloc_zone_bitmap(int node, unsigned int nr_zones) { return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long), GFP_NOIO, node); } static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx, void *data) { /* * For an all-zones reset, ignore conventional, empty, read-only * and offline zones. */ switch (zone->cond) { case BLK_ZONE_COND_NOT_WP: case BLK_ZONE_COND_EMPTY: case BLK_ZONE_COND_READONLY: case BLK_ZONE_COND_OFFLINE: return 0; default: set_bit(idx, (unsigned long *)data); return 0; } } static int blkdev_zone_reset_all_emulated(struct block_device *bdev, gfp_t gfp_mask) { struct gendisk *disk = bdev->bd_disk; sector_t capacity = bdev_nr_sectors(bdev); sector_t zone_sectors = bdev_zone_sectors(bdev); unsigned long *need_reset; struct bio *bio = NULL; sector_t sector = 0; int ret; need_reset = blk_alloc_zone_bitmap(disk->queue->node, disk->nr_zones); if (!need_reset) return -ENOMEM; ret = disk->fops->report_zones(disk, 0, disk->nr_zones, blk_zone_need_reset_cb, need_reset); if (ret < 0) goto out_free_need_reset; ret = 0; while (sector < capacity) { if (!test_bit(disk_zone_no(disk, sector), need_reset)) { sector += zone_sectors; continue; } bio = blk_next_bio(bio, bdev, 0, REQ_OP_ZONE_RESET | REQ_SYNC, gfp_mask); bio->bi_iter.bi_sector = sector; sector += zone_sectors; /* This may take a while, so be nice to others */ cond_resched(); } if (bio) { ret = submit_bio_wait(bio); bio_put(bio); } out_free_need_reset: kfree(need_reset); return ret; } static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask) { struct bio bio; bio_init(&bio, bdev, NULL, 0, REQ_OP_ZONE_RESET_ALL | REQ_SYNC); return submit_bio_wait(&bio); } /** * blkdev_zone_mgmt - Execute a zone management operation on a range of zones * @bdev: Target block device * @op: Operation to be performed on the zones * @sector: Start sector of the first zone to operate on * @nr_sectors: Number of sectors, should be at least the length of one zone and * must be zone size aligned. * @gfp_mask: Memory allocation flags (for bio_alloc) * * Description: * Perform the specified operation on the range of zones specified by * @sector..@sector+@nr_sectors. Specifying the entire disk sector range * is valid, but the specified range should not contain conventional zones. * The operation to execute on each zone can be a zone reset, open, close * or finish request. */ int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, sector_t sector, sector_t nr_sectors, gfp_t gfp_mask) { struct request_queue *q = bdev_get_queue(bdev); sector_t zone_sectors = bdev_zone_sectors(bdev); sector_t capacity = bdev_nr_sectors(bdev); sector_t end_sector = sector + nr_sectors; struct bio *bio = NULL; int ret = 0; if (!bdev_is_zoned(bdev)) return -EOPNOTSUPP; if (bdev_read_only(bdev)) return -EPERM; if (!op_is_zone_mgmt(op)) return -EOPNOTSUPP; if (end_sector <= sector || end_sector > capacity) /* Out of range */ return -EINVAL; /* Check alignment (handle eventual smaller last zone) */ if (sector & (zone_sectors - 1)) return -EINVAL; if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity) return -EINVAL; /* * In the case of a zone reset operation over all zones, * REQ_OP_ZONE_RESET_ALL can be used with devices supporting this * command. For other devices, we emulate this command behavior by * identifying the zones needing a reset. */ if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) { if (!blk_queue_zone_resetall(q)) return blkdev_zone_reset_all_emulated(bdev, gfp_mask); return blkdev_zone_reset_all(bdev, gfp_mask); } while (sector < end_sector) { bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, gfp_mask); bio->bi_iter.bi_sector = sector; sector += zone_sectors; /* This may take a while, so be nice to others */ cond_resched(); } ret = submit_bio_wait(bio); bio_put(bio); return ret; } EXPORT_SYMBOL_GPL(blkdev_zone_mgmt); struct zone_report_args { struct blk_zone __user *zones; }; static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx, void *data) { struct zone_report_args *args = data; if (copy_to_user(&args->zones[idx], zone, sizeof(struct blk_zone))) return -EFAULT; return 0; } /* * BLKREPORTZONE ioctl processing. * Called from blkdev_ioctl. */ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct zone_report_args args; struct request_queue *q; struct blk_zone_report rep; int ret; if (!argp) return -EINVAL; q = bdev_get_queue(bdev); if (!q) return -ENXIO; if (!bdev_is_zoned(bdev)) return -ENOTTY; if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report))) return -EFAULT; if (!rep.nr_zones) return -EINVAL; args.zones = argp + sizeof(struct blk_zone_report); ret = blkdev_report_zones(bdev, rep.sector, rep.nr_zones, blkdev_copy_zone_to_user, &args); if (ret < 0) return ret; rep.nr_zones = ret; rep.flags = BLK_ZONE_REP_CAPACITY; if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) return -EFAULT; return 0; } static int blkdev_truncate_zone_range(struct block_device *bdev, fmode_t mode, const struct blk_zone_range *zrange) { loff_t start, end; if (zrange->sector + zrange->nr_sectors <= zrange->sector || zrange->sector + zrange->nr_sectors > get_capacity(bdev->bd_disk)) /* Out of range */ return -EINVAL; start = zrange->sector << SECTOR_SHIFT; end = ((zrange->sector + zrange->nr_sectors) << SECTOR_SHIFT) - 1; return truncate_bdev_range(bdev, mode, start, end); } /* * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing. * Called from blkdev_ioctl. */ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct request_queue *q; struct blk_zone_range zrange; enum req_op op; int ret; if (!argp) return -EINVAL; q = bdev_get_queue(bdev); if (!q) return -ENXIO; if (!bdev_is_zoned(bdev)) return -ENOTTY; if (!(mode & FMODE_WRITE)) return -EBADF; if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range))) return -EFAULT; switch (cmd) { case BLKRESETZONE: op = REQ_OP_ZONE_RESET; /* Invalidate the page cache, including dirty pages. */ filemap_invalidate_lock(bdev->bd_inode->i_mapping); ret = blkdev_truncate_zone_range(bdev, mode, &zrange); if (ret) goto fail; break; case BLKOPENZONE: op = REQ_OP_ZONE_OPEN; break; case BLKCLOSEZONE: op = REQ_OP_ZONE_CLOSE; break; case BLKFINISHZONE: op = REQ_OP_ZONE_FINISH; break; default: return -ENOTTY; } ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors, GFP_KERNEL); fail: if (cmd == BLKRESETZONE) filemap_invalidate_unlock(bdev->bd_inode->i_mapping); return ret; } void disk_free_zone_bitmaps(struct gendisk *disk) { kfree(disk->conv_zones_bitmap); disk->conv_zones_bitmap = NULL; kfree(disk->seq_zones_wlock); disk->seq_zones_wlock = NULL; } struct blk_revalidate_zone_args { struct gendisk *disk; unsigned long *conv_zones_bitmap; unsigned long *seq_zones_wlock; unsigned int nr_zones; sector_t zone_sectors; sector_t sector; }; /* * Helper function to check the validity of zones of a zoned block device. */ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx, void *data) { struct blk_revalidate_zone_args *args = data; struct gendisk *disk = args->disk; struct request_queue *q = disk->queue; sector_t capacity = get_capacity(disk); /* * All zones must have the same size, with the exception on an eventual * smaller last zone. */ if (zone->start == 0) { if (zone->len == 0 || !is_power_of_2(zone->len)) { pr_warn("%s: Invalid zoned device with non power of two zone size (%llu)\n", disk->disk_name, zone->len); return -ENODEV; } args->zone_sectors = zone->len; args->nr_zones = (capacity + zone->len - 1) >> ilog2(zone->len); } else if (zone->start + args->zone_sectors < capacity) { if (zone->len != args->zone_sectors) { pr_warn("%s: Invalid zoned device with non constant zone size\n", disk->disk_name); return -ENODEV; } } else { if (zone->len > args->zone_sectors) { pr_warn("%s: Invalid zoned device with larger last zone size\n", disk->disk_name); return -ENODEV; } } /* Check for holes in the zone report */ if (zone->start != args->sector) { pr_warn("%s: Zone gap at sectors %llu..%llu\n", disk->disk_name, args->sector, zone->start); return -ENODEV; } /* Check zone type */ switch (zone->type) { case BLK_ZONE_TYPE_CONVENTIONAL: if (!args->conv_zones_bitmap) { args->conv_zones_bitmap = blk_alloc_zone_bitmap(q->node, args->nr_zones); if (!args->conv_zones_bitmap) return -ENOMEM; } set_bit(idx, args->conv_zones_bitmap); break; case BLK_ZONE_TYPE_SEQWRITE_REQ: case BLK_ZONE_TYPE_SEQWRITE_PREF: if (!args->seq_zones_wlock) { args->seq_zones_wlock = blk_alloc_zone_bitmap(q->node, args->nr_zones); if (!args->seq_zones_wlock) return -ENOMEM; } break; default: pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n", disk->disk_name, (int)zone->type, zone->start); return -ENODEV; } args->sector += zone->len; return 0; } /** * blk_revalidate_disk_zones - (re)allocate and initialize zone bitmaps * @disk: Target disk * @update_driver_data: Callback to update driver data on the frozen disk * * Helper function for low-level device drivers to (re) allocate and initialize * a disk request queue zone bitmaps. This functions should normally be called * within the disk ->revalidate method for blk-mq based drivers. For BIO based * drivers only q->nr_zones needs to be updated so that the sysfs exposed value * is correct. * If the @update_driver_data callback function is not NULL, the callback is * executed with the device request queue frozen after all zones have been * checked. */ int blk_revalidate_disk_zones(struct gendisk *disk, void (*update_driver_data)(struct gendisk *disk)) { struct request_queue *q = disk->queue; struct blk_revalidate_zone_args args = { .disk = disk, }; unsigned int noio_flag; int ret; if (WARN_ON_ONCE(!blk_queue_is_zoned(q))) return -EIO; if (WARN_ON_ONCE(!queue_is_mq(q))) return -EIO; if (!get_capacity(disk)) return -EIO; /* * Ensure that all memory allocations in this context are done as if * GFP_NOIO was specified. */ noio_flag = memalloc_noio_save(); ret = disk->fops->report_zones(disk, 0, UINT_MAX, blk_revalidate_zone_cb, &args); if (!ret) { pr_warn("%s: No zones reported\n", disk->disk_name); ret = -ENODEV; } memalloc_noio_restore(noio_flag); /* * If zones where reported, make sure that the entire disk capacity * has been checked. */ if (ret > 0 && args.sector != get_capacity(disk)) { pr_warn("%s: Missing zones from sector %llu\n", disk->disk_name, args.sector); ret = -ENODEV; } /* * Install the new bitmaps and update nr_zones only once the queue is * stopped and all I/Os are completed (i.e. a scheduler is not * referencing the bitmaps). */ blk_mq_freeze_queue(q); if (ret > 0) { blk_queue_chunk_sectors(q, args.zone_sectors); disk->nr_zones = args.nr_zones; swap(disk->seq_zones_wlock, args.seq_zones_wlock); swap(disk->conv_zones_bitmap, args.conv_zones_bitmap); if (update_driver_data) update_driver_data(disk); ret = 0; } else { pr_warn("%s: failed to revalidate zones\n", disk->disk_name); disk_free_zone_bitmaps(disk); } blk_mq_unfreeze_queue(q); kfree(args.seq_zones_wlock); kfree(args.conv_zones_bitmap); return ret; } EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones); void disk_clear_zone_settings(struct gendisk *disk) { struct request_queue *q = disk->queue; blk_mq_freeze_queue(q); disk_free_zone_bitmaps(disk); blk_queue_flag_clear(QUEUE_FLAG_ZONE_RESETALL, q); q->required_elevator_features &= ~ELEVATOR_F_ZBD_SEQ_WRITE; disk->nr_zones = 0; disk->max_open_zones = 0; disk->max_active_zones = 0; q->limits.chunk_sectors = 0; q->limits.zone_write_granularity = 0; q->limits.max_zone_append_sectors = 0; blk_mq_unfreeze_queue(q); } |
| 105 105 79 105 105 105 105 105 105 12 105 105 23 23 23 12 79 79 93 12 105 93 12 12 12 12 12 12 12 93 93 93 105 105 105 105 12 105 23 73 73 79 79 23 79 79 23 23 23 23 23 15 15 18 18 18 15 93 93 93 93 93 93 73 73 73 73 92 173 97 97 97 97 12 12 12 12 12 12 12 12 12 12 12 12 12 23 35 93 73 181 142 181 74 160 160 105 160 105 160 160 160 105 160 160 160 35 142 160 105 160 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <net/switchdev.h> #include "br_private.h" #include "br_private_tunnel.h" static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid); static inline int br_vlan_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct net_bridge_vlan *vle = ptr; u16 vid = *(u16 *)arg->key; return vle->vid != vid; } static const struct rhashtable_params br_vlan_rht_params = { .head_offset = offsetof(struct net_bridge_vlan, vnode), .key_offset = offsetof(struct net_bridge_vlan, vid), .key_len = sizeof(u16), .nelem_hint = 3, .max_size = VLAN_N_VID, .obj_cmpfn = br_vlan_cmp, .automatic_shrinking = true, }; static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid) { return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params); } static void __vlan_add_pvid(struct net_bridge_vlan_group *vg, const struct net_bridge_vlan *v) { if (vg->pvid == v->vid) return; smp_wmb(); br_vlan_set_pvid_state(vg, v->state); vg->pvid = v->vid; } static void __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid) { if (vg->pvid != vid) return; smp_wmb(); vg->pvid = 0; } /* Update the BRIDGE_VLAN_INFO_PVID and BRIDGE_VLAN_INFO_UNTAGGED flags of @v. * If @commit is false, return just whether the BRIDGE_VLAN_INFO_PVID and * BRIDGE_VLAN_INFO_UNTAGGED bits of @flags would produce any change onto @v. */ static bool __vlan_flags_update(struct net_bridge_vlan *v, u16 flags, bool commit) { struct net_bridge_vlan_group *vg; bool change; if (br_vlan_is_master(v)) vg = br_vlan_group(v->br); else vg = nbp_vlan_group(v->port); /* check if anything would be changed on commit */ change = !!(flags & BRIDGE_VLAN_INFO_PVID) == !!(vg->pvid != v->vid) || ((flags ^ v->flags) & BRIDGE_VLAN_INFO_UNTAGGED); if (!commit) goto out; if (flags & BRIDGE_VLAN_INFO_PVID) __vlan_add_pvid(vg, v); else __vlan_delete_pvid(vg, v->vid); if (flags & BRIDGE_VLAN_INFO_UNTAGGED) v->flags |= BRIDGE_VLAN_INFO_UNTAGGED; else v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED; out: return change; } static bool __vlan_flags_would_change(struct net_bridge_vlan *v, u16 flags) { return __vlan_flags_update(v, flags, false); } static void __vlan_flags_commit(struct net_bridge_vlan *v, u16 flags) { __vlan_flags_update(v, flags, true); } static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, struct net_bridge_vlan *v, u16 flags, struct netlink_ext_ack *extack) { int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q add. */ err = br_switchdev_port_vlan_add(dev, v->vid, flags, false, extack); if (err == -EOPNOTSUPP) return vlan_vid_add(dev, br->vlan_proto, v->vid); v->priv_flags |= BR_VLFLAG_ADDED_BY_SWITCHDEV; return err; } static void __vlan_add_list(struct net_bridge_vlan *v) { struct net_bridge_vlan_group *vg; struct list_head *headp, *hpos; struct net_bridge_vlan *vent; if (br_vlan_is_master(v)) vg = br_vlan_group(v->br); else vg = nbp_vlan_group(v->port); headp = &vg->vlan_list; list_for_each_prev(hpos, headp) { vent = list_entry(hpos, struct net_bridge_vlan, vlist); if (v->vid >= vent->vid) break; } list_add_rcu(&v->vlist, hpos); } static void __vlan_del_list(struct net_bridge_vlan *v) { list_del_rcu(&v->vlist); } static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, const struct net_bridge_vlan *v) { int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q del. */ err = br_switchdev_port_vlan_del(dev, v->vid); if (!(v->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV)) vlan_vid_del(dev, br->vlan_proto, v->vid); return err == -EOPNOTSUPP ? 0 : err; } /* Returns a master vlan, if it didn't exist it gets created. In all cases * a reference is taken to the master vlan before returning. */ static struct net_bridge_vlan * br_vlan_get_master(struct net_bridge *br, u16 vid, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *masterv; vg = br_vlan_group(br); masterv = br_vlan_find(vg, vid); if (!masterv) { bool changed; /* missing global ctx, create it now */ if (br_vlan_add(br, vid, 0, &changed, extack)) return NULL; masterv = br_vlan_find(vg, vid); if (WARN_ON(!masterv)) return NULL; refcount_set(&masterv->refcnt, 1); return masterv; } refcount_inc(&masterv->refcnt); return masterv; } static void br_master_vlan_rcu_free(struct rcu_head *rcu) { struct net_bridge_vlan *v; v = container_of(rcu, struct net_bridge_vlan, rcu); WARN_ON(!br_vlan_is_master(v)); free_percpu(v->stats); v->stats = NULL; kfree(v); } static void br_vlan_put_master(struct net_bridge_vlan *masterv) { struct net_bridge_vlan_group *vg; if (!br_vlan_is_master(masterv)) return; vg = br_vlan_group(masterv->br); if (refcount_dec_and_test(&masterv->refcnt)) { rhashtable_remove_fast(&vg->vlan_hash, &masterv->vnode, br_vlan_rht_params); __vlan_del_list(masterv); br_multicast_toggle_one_vlan(masterv, false); br_multicast_ctx_deinit(&masterv->br_mcast_ctx); call_rcu(&masterv->rcu, br_master_vlan_rcu_free); } } static void nbp_vlan_rcu_free(struct rcu_head *rcu) { struct net_bridge_vlan *v; v = container_of(rcu, struct net_bridge_vlan, rcu); WARN_ON(br_vlan_is_master(v)); /* if we had per-port stats configured then free them here */ if (v->priv_flags & BR_VLFLAG_PER_PORT_STATS) free_percpu(v->stats); v->stats = NULL; kfree(v); } static void br_vlan_init_state(struct net_bridge_vlan *v) { struct net_bridge *br; if (br_vlan_is_master(v)) br = v->br; else br = v->port->br; if (br_opt_get(br, BROPT_MST_ENABLED)) { br_mst_vlan_init_state(v); return; } v->state = BR_STATE_FORWARDING; v->msti = 0; } /* This is the shared VLAN add function which works for both ports and bridge * devices. There are four possible calls to this function in terms of the * vlan entry type: * 1. vlan is being added on a port (no master flags, global entry exists) * 2. vlan is being added on a bridge (both master and brentry flags) * 3. vlan is being added on a port, but a global entry didn't exist which * is being created right now (master flag set, brentry flag unset), the * global entry is used for global per-vlan features, but not for filtering * 4. same as 3 but with both master and brentry flags set so the entry * will be used for filtering in both the port and the bridge */ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, struct netlink_ext_ack *extack) { struct net_bridge_vlan *masterv = NULL; struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_device *dev; struct net_bridge *br; int err; if (br_vlan_is_master(v)) { br = v->br; dev = br->dev; vg = br_vlan_group(br); } else { p = v->port; br = p->br; dev = p->dev; vg = nbp_vlan_group(p); } if (p) { /* Add VLAN to the device filter if it is supported. * This ensures tagged traffic enters the bridge when * promiscuous mode is disabled by br_manage_promisc(). */ err = __vlan_vid_add(dev, br, v, flags, extack); if (err) goto out; /* need to work on the master vlan too */ if (flags & BRIDGE_VLAN_INFO_MASTER) { bool changed; err = br_vlan_add(br, v->vid, flags | BRIDGE_VLAN_INFO_BRENTRY, &changed, extack); if (err) goto out_filt; if (changed) br_vlan_notify(br, NULL, v->vid, 0, RTM_NEWVLAN); } masterv = br_vlan_get_master(br, v->vid, extack); if (!masterv) { err = -ENOMEM; goto out_filt; } v->brvlan = masterv; if (br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)) { v->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!v->stats) { err = -ENOMEM; goto out_filt; } v->priv_flags |= BR_VLFLAG_PER_PORT_STATS; } else { v->stats = masterv->stats; } br_multicast_port_ctx_init(p, v, &v->port_mcast_ctx); } else { if (br_vlan_should_use(v)) { err = br_switchdev_port_vlan_add(dev, v->vid, flags, false, extack); if (err && err != -EOPNOTSUPP) goto out; } br_multicast_ctx_init(br, v, &v->br_mcast_ctx); v->priv_flags |= BR_VLFLAG_GLOBAL_MCAST_ENABLED; } /* Add the dev mac and count the vlan only if it's usable */ if (br_vlan_should_use(v)) { err = br_fdb_add_local(br, p, dev->dev_addr, v->vid); if (err) { br_err(br, "failed insert local address into bridge forwarding table\n"); goto out_filt; } vg->num_vlans++; } /* set the state before publishing */ br_vlan_init_state(v); err = rhashtable_lookup_insert_fast(&vg->vlan_hash, &v->vnode, br_vlan_rht_params); if (err) goto out_fdb_insert; __vlan_add_list(v); __vlan_flags_commit(v, flags); br_multicast_toggle_one_vlan(v, true); if (p) nbp_vlan_set_vlan_dev_state(p, v->vid); out: return err; out_fdb_insert: if (br_vlan_should_use(v)) { br_fdb_find_delete_local(br, p, dev->dev_addr, v->vid); vg->num_vlans--; } out_filt: if (p) { __vlan_vid_del(dev, br, v); if (masterv) { if (v->stats && masterv->stats != v->stats) free_percpu(v->stats); v->stats = NULL; br_vlan_put_master(masterv); v->brvlan = NULL; } } else { br_switchdev_port_vlan_del(dev, v->vid); } goto out; } static int __vlan_del(struct net_bridge_vlan *v) { struct net_bridge_vlan *masterv = v; struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; int err = 0; if (br_vlan_is_master(v)) { vg = br_vlan_group(v->br); } else { p = v->port; vg = nbp_vlan_group(v->port); masterv = v->brvlan; } __vlan_delete_pvid(vg, v->vid); if (p) { err = __vlan_vid_del(p->dev, p->br, v); if (err) goto out; } else { err = br_switchdev_port_vlan_del(v->br->dev, v->vid); if (err && err != -EOPNOTSUPP) goto out; err = 0; } if (br_vlan_should_use(v)) { v->flags &= ~BRIDGE_VLAN_INFO_BRENTRY; vg->num_vlans--; } if (masterv != v) { vlan_tunnel_info_del(vg, v); rhashtable_remove_fast(&vg->vlan_hash, &v->vnode, br_vlan_rht_params); __vlan_del_list(v); nbp_vlan_set_vlan_dev_state(p, v->vid); br_multicast_toggle_one_vlan(v, false); br_multicast_port_ctx_deinit(&v->port_mcast_ctx); call_rcu(&v->rcu, nbp_vlan_rcu_free); } br_vlan_put_master(masterv); out: return err; } static void __vlan_group_free(struct net_bridge_vlan_group *vg) { WARN_ON(!list_empty(&vg->vlan_list)); rhashtable_destroy(&vg->vlan_hash); vlan_tunnel_deinit(vg); kfree(vg); } static void __vlan_flush(const struct net_bridge *br, const struct net_bridge_port *p, struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *vlan, *tmp; u16 v_start = 0, v_end = 0; int err; __vlan_delete_pvid(vg, vg->pvid); list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) { /* take care of disjoint ranges */ if (!v_start) { v_start = vlan->vid; } else if (vlan->vid - v_end != 1) { /* found range end, notify and start next one */ br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); v_start = vlan->vid; } v_end = vlan->vid; err = __vlan_del(vlan); if (err) { br_err(br, "port %u(%s) failed to delete vlan %d: %pe\n", (unsigned int) p->port_no, p->dev->name, vlan->vid, ERR_PTR(err)); } } /* notify about the last/whole vlan range */ if (v_start) br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); } struct sk_buff *br_handle_vlan(struct net_bridge *br, const struct net_bridge_port *p, struct net_bridge_vlan_group *vg, struct sk_buff *skb) { struct pcpu_sw_netstats *stats; struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) goto out; /* At this point, we know that the frame was filtered and contains * a valid vlan id. If the vlan id has untagged flag set, * send untagged; otherwise, send tagged. */ br_vlan_get_tag(skb, &vid); v = br_vlan_find(vg, vid); /* Vlan entry must be configured at this point. The * only exception is the bridge is set in promisc mode and the * packet is destined for the bridge device. In this case * pass the packet as is. */ if (!v || !br_vlan_should_use(v)) { if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) { goto out; } else { kfree_skb(skb); return NULL; } } if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { stats = this_cpu_ptr(v->stats); u64_stats_update_begin(&stats->syncp); u64_stats_add(&stats->tx_bytes, skb->len); u64_stats_inc(&stats->tx_packets); u64_stats_update_end(&stats->syncp); } /* If the skb will be sent using forwarding offload, the assumption is * that the switchdev will inject the packet into hardware together * with the bridge VLAN, so that it can be forwarded according to that * VLAN. The switchdev should deal with popping the VLAN header in * hardware on each egress port as appropriate. So only strip the VLAN * header if forwarding offload is not being used. */ if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED && !br_switchdev_frame_uses_tx_fwd_offload(skb)) __vlan_hwaccel_clear_tag(skb); if (p && (p->flags & BR_VLAN_TUNNEL) && br_handle_egress_vlan_tunnel(skb, v)) { kfree_skb(skb); return NULL; } out: return skb; } /* Called under RCU */ static bool __allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, u16 *vid, u8 *state, struct net_bridge_vlan **vlan) { struct pcpu_sw_netstats *stats; struct net_bridge_vlan *v; bool tagged; BR_INPUT_SKB_CB(skb)->vlan_filtered = true; /* If vlan tx offload is disabled on bridge device and frame was * sent from vlan device on the bridge device, it does not have * HW accelerated vlan tag. */ if (unlikely(!skb_vlan_tag_present(skb) && skb->protocol == br->vlan_proto)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) return false; } if (!br_vlan_get_tag(skb, vid)) { /* Tagged frame */ if (skb->vlan_proto != br->vlan_proto) { /* Protocol-mismatch, empty out vlan_tci for new tag */ skb_push(skb, ETH_HLEN); skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (unlikely(!skb)) return false; skb_pull(skb, ETH_HLEN); skb_reset_mac_len(skb); *vid = 0; tagged = false; } else { tagged = true; } } else { /* Untagged frame */ tagged = false; } if (!*vid) { u16 pvid = br_get_pvid(vg); /* Frame had a tag with VID 0 or did not have a tag. * See if pvid is set on this port. That tells us which * vlan untagged or priority-tagged traffic belongs to. */ if (!pvid) goto drop; /* PVID is set on this port. Any untagged or priority-tagged * ingress frame is considered to belong to this vlan. */ *vid = pvid; if (likely(!tagged)) /* Untagged Frame. */ __vlan_hwaccel_put_tag(skb, br->vlan_proto, pvid); else /* Priority-tagged Frame. * At this point, we know that skb->vlan_tci VID * field was 0. * We update only VID field and preserve PCP field. */ skb->vlan_tci |= pvid; /* if snooping and stats are disabled we can avoid the lookup */ if (!br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) && !br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { if (*state == BR_STATE_FORWARDING) { *state = br_vlan_get_pvid_state(vg); if (!br_vlan_state_allowed(*state, true)) goto drop; } return true; } } v = br_vlan_find(vg, *vid); if (!v || !br_vlan_should_use(v)) goto drop; if (*state == BR_STATE_FORWARDING) { *state = br_vlan_get_state(v); if (!br_vlan_state_allowed(*state, true)) goto drop; } if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { stats = this_cpu_ptr(v->stats); u64_stats_update_begin(&stats->syncp); u64_stats_add(&stats->rx_bytes, skb->len); u64_stats_inc(&stats->rx_packets); u64_stats_update_end(&stats->syncp); } *vlan = v; return true; drop: kfree_skb(skb); return false; } bool br_allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, u16 *vid, u8 *state, struct net_bridge_vlan **vlan) { /* If VLAN filtering is disabled on the bridge, all packets are * permitted. */ *vlan = NULL; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) { BR_INPUT_SKB_CB(skb)->vlan_filtered = false; return true; } return __allowed_ingress(br, vg, skb, vid, state, vlan); } /* Called under RCU. */ bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb) { const struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) return true; br_vlan_get_tag(skb, &vid); v = br_vlan_find(vg, vid); if (v && br_vlan_should_use(v) && br_vlan_state_allowed(br_vlan_get_state(v), false)) return true; return false; } /* Called under RCU */ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) { struct net_bridge_vlan_group *vg; struct net_bridge *br = p->br; struct net_bridge_vlan *v; /* If filtering was disabled at input, let it pass. */ if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return true; vg = nbp_vlan_group_rcu(p); if (!vg || !vg->num_vlans) return false; if (!br_vlan_get_tag(skb, vid) && skb->vlan_proto != br->vlan_proto) *vid = 0; if (!*vid) { *vid = br_get_pvid(vg); if (!*vid || !br_vlan_state_allowed(br_vlan_get_pvid_state(vg), true)) return false; return true; } v = br_vlan_find(vg, *vid); if (v && br_vlan_state_allowed(br_vlan_get_state(v), true)) return true; return false; } static int br_vlan_add_existing(struct net_bridge *br, struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan, u16 flags, bool *changed, struct netlink_ext_ack *extack) { bool would_change = __vlan_flags_would_change(vlan, flags); bool becomes_brentry = false; int err; if (!br_vlan_is_brentry(vlan)) { /* Trying to change flags of non-existent bridge vlan */ if (!(flags & BRIDGE_VLAN_INFO_BRENTRY)) return -EINVAL; becomes_brentry = true; } /* Master VLANs that aren't brentries weren't notified before, * time to notify them now. */ if (becomes_brentry || would_change) { err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags, would_change, extack); if (err && err != -EOPNOTSUPP) return err; } if (becomes_brentry) { /* It was only kept for port vlans, now make it real */ err = br_fdb_add_local(br, NULL, br->dev->dev_addr, vlan->vid); if (err) { br_err(br, "failed to insert local address into bridge forwarding table\n"); goto err_fdb_insert; } refcount_inc(&vlan->refcnt); vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; vg->num_vlans++; *changed = true; br_multicast_toggle_one_vlan(vlan, true); } __vlan_flags_commit(vlan, flags); if (would_change) *changed = true; return 0; err_fdb_insert: br_switchdev_port_vlan_del(br->dev, vlan->vid); return err; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. * changed must be true only if the vlan was created or updated */ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; int ret; ASSERT_RTNL(); *changed = false; vg = br_vlan_group(br); vlan = br_vlan_find(vg, vid); if (vlan) return br_vlan_add_existing(br, vg, vlan, flags, changed, extack); vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); if (!vlan) return -ENOMEM; vlan->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!vlan->stats) { kfree(vlan); return -ENOMEM; } vlan->vid = vid; vlan->flags = flags | BRIDGE_VLAN_INFO_MASTER; vlan->flags &= ~BRIDGE_VLAN_INFO_PVID; vlan->br = br; if (flags & BRIDGE_VLAN_INFO_BRENTRY) refcount_set(&vlan->refcnt, 1); ret = __vlan_add(vlan, flags, extack); if (ret) { free_percpu(vlan->stats); kfree(vlan); } else { *changed = true; } return ret; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ int br_vlan_delete(struct net_bridge *br, u16 vid) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; ASSERT_RTNL(); vg = br_vlan_group(br); v = br_vlan_find(vg, vid); if (!v || !br_vlan_is_brentry(v)) return -ENOENT; br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid); br_fdb_delete_by_port(br, NULL, vid, 0); vlan_tunnel_info_del(vg, v); return __vlan_del(v); } void br_vlan_flush(struct net_bridge *br) { struct net_bridge_vlan_group *vg; ASSERT_RTNL(); vg = br_vlan_group(br); __vlan_flush(br, NULL, vg); RCU_INIT_POINTER(br->vlgrp, NULL); synchronize_rcu(); __vlan_group_free(vg); } struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid) { if (!vg) return NULL; return br_vlan_lookup(&vg->vlan_hash, vid); } /* Must be protected by RTNL. */ static void recalculate_group_addr(struct net_bridge *br) { if (br_opt_get(br, BROPT_GROUP_ADDR_SET)) return; spin_lock_bh(&br->lock); if (!br_opt_get(br, BROPT_VLAN_ENABLED) || br->vlan_proto == htons(ETH_P_8021Q)) { /* Bridge Group Address */ br->group_addr[5] = 0x00; } else { /* vlan_enabled && ETH_P_8021AD */ /* Provider Bridge Group Address */ br->group_addr[5] = 0x08; } spin_unlock_bh(&br->lock); } /* Must be protected by RTNL. */ void br_recalculate_fwd_mask(struct net_bridge *br) { if (!br_opt_get(br, BROPT_VLAN_ENABLED) || br->vlan_proto == htons(ETH_P_8021Q)) br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT; else /* vlan_enabled && ETH_P_8021AD */ br->group_fwd_mask_required = BR_GROUPFWD_8021AD & ~(1u << br->group_addr[5]); } int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_filtering = val, }; int err; if (br_opt_get(br, BROPT_VLAN_ENABLED) == !!val) return 0; br_opt_toggle(br, BROPT_VLAN_ENABLED, !!val); err = switchdev_port_attr_set(br->dev, &attr, extack); if (err && err != -EOPNOTSUPP) { br_opt_toggle(br, BROPT_VLAN_ENABLED, !val); return err; } br_manage_promisc(br); recalculate_group_addr(br); br_recalculate_fwd_mask(br); if (!val && br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { br_info(br, "vlan filtering disabled, automatically disabling multicast vlan snooping\n"); br_multicast_toggle_vlan_snooping(br, false, NULL); } return 0; } bool br_vlan_enabled(const struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); return br_opt_get(br, BROPT_VLAN_ENABLED); } EXPORT_SYMBOL_GPL(br_vlan_enabled); int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto) { struct net_bridge *br = netdev_priv(dev); *p_proto = ntohs(br->vlan_proto); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_proto); int __br_vlan_set_proto(struct net_bridge *br, __be16 proto, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_protocol = ntohs(proto), }; int err = 0; struct net_bridge_port *p; struct net_bridge_vlan *vlan; struct net_bridge_vlan_group *vg; __be16 oldproto = br->vlan_proto; if (br->vlan_proto == proto) return 0; err = switchdev_port_attr_set(br->dev, &attr, extack); if (err && err != -EOPNOTSUPP) return err; /* Add VLANs for the new proto to the device filter. */ list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; err = vlan_vid_add(p->dev, proto, vlan->vid); if (err) goto err_filt; } } br->vlan_proto = proto; recalculate_group_addr(br); br_recalculate_fwd_mask(br); /* Delete VLANs for the old proto from the device filter. */ list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, oldproto, vlan->vid); } } return 0; err_filt: attr.u.vlan_protocol = ntohs(oldproto); switchdev_port_attr_set(br->dev, &attr, NULL); list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, proto, vlan->vid); } list_for_each_entry_continue_reverse(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, proto, vlan->vid); } } return err; } int br_vlan_set_proto(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { if (!eth_type_vlan(htons(val))) return -EPROTONOSUPPORT; return __br_vlan_set_proto(br, htons(val), extack); } int br_vlan_set_stats(struct net_bridge *br, unsigned long val) { switch (val) { case 0: case 1: br_opt_toggle(br, BROPT_VLAN_STATS_ENABLED, !!val); break; default: return -EINVAL; } return 0; } int br_vlan_set_stats_per_port(struct net_bridge *br, unsigned long val) { struct net_bridge_port *p; /* allow to change the option if there are no port vlans configured */ list_for_each_entry(p, &br->port_list, list) { struct net_bridge_vlan_group *vg = nbp_vlan_group(p); if (vg->num_vlans) return -EBUSY; } switch (val) { case 0: case 1: br_opt_toggle(br, BROPT_VLAN_STATS_PER_PORT, !!val); break; default: return -EINVAL; } return 0; } static bool vlan_default_pvid(struct net_bridge_vlan_group *vg, u16 vid) { struct net_bridge_vlan *v; if (vid != vg->pvid) return false; v = br_vlan_lookup(&vg->vlan_hash, vid); if (v && br_vlan_should_use(v) && (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) return true; return false; } static void br_vlan_disable_default_pvid(struct net_bridge *br) { struct net_bridge_port *p; u16 pvid = br->default_pvid; /* Disable default_pvid on all ports where it is still * configured. */ if (vlan_default_pvid(br_vlan_group(br), pvid)) { if (!br_vlan_delete(br, pvid)) br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); } list_for_each_entry(p, &br->port_list, list) { if (vlan_default_pvid(nbp_vlan_group(p), pvid) && !nbp_vlan_delete(p, pvid)) br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } br->default_pvid = 0; } int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid, struct netlink_ext_ack *extack) { const struct net_bridge_vlan *pvent; struct net_bridge_vlan_group *vg; struct net_bridge_port *p; unsigned long *changed; bool vlchange; u16 old_pvid; int err = 0; if (!pvid) { br_vlan_disable_default_pvid(br); return 0; } changed = bitmap_zalloc(BR_MAX_PORTS, GFP_KERNEL); if (!changed) return -ENOMEM; old_pvid = br->default_pvid; /* Update default_pvid config only if we do not conflict with * user configuration. */ vg = br_vlan_group(br); pvent = br_vlan_find(vg, pvid); if ((!old_pvid || vlan_default_pvid(vg, old_pvid)) && (!pvent || !br_vlan_should_use(pvent))) { err = br_vlan_add(br, pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &vlchange, extack); if (err) goto out; if (br_vlan_delete(br, old_pvid)) br_vlan_notify(br, NULL, old_pvid, 0, RTM_DELVLAN); br_vlan_notify(br, NULL, pvid, 0, RTM_NEWVLAN); __set_bit(0, changed); } list_for_each_entry(p, &br->port_list, list) { /* Update default_pvid config only if we do not conflict with * user configuration. */ vg = nbp_vlan_group(p); if ((old_pvid && !vlan_default_pvid(vg, old_pvid)) || br_vlan_find(vg, pvid)) continue; err = nbp_vlan_add(p, pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &vlchange, extack); if (err) goto err_port; if (nbp_vlan_delete(p, old_pvid)) br_vlan_notify(br, p, old_pvid, 0, RTM_DELVLAN); br_vlan_notify(p->br, p, pvid, 0, RTM_NEWVLAN); __set_bit(p->port_no, changed); } br->default_pvid = pvid; out: bitmap_free(changed); return err; err_port: list_for_each_entry_continue_reverse(p, &br->port_list, list) { if (!test_bit(p->port_no, changed)) continue; if (old_pvid) { nbp_vlan_add(p, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &vlchange, NULL); br_vlan_notify(p->br, p, old_pvid, 0, RTM_NEWVLAN); } nbp_vlan_delete(p, pvid); br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } if (test_bit(0, changed)) { if (old_pvid) { br_vlan_add(br, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &vlchange, NULL); br_vlan_notify(br, NULL, old_pvid, 0, RTM_NEWVLAN); } br_vlan_delete(br, pvid); br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); } goto out; } int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { u16 pvid = val; int err = 0; if (val >= VLAN_VID_MASK) return -EINVAL; if (pvid == br->default_pvid) goto out; /* Only allow default pvid change when filtering is disabled */ if (br_opt_get(br, BROPT_VLAN_ENABLED)) { pr_info_once("Please disable vlan filtering to change default_pvid\n"); err = -EPERM; goto out; } err = __br_vlan_set_default_pvid(br, pvid, extack); out: return err; } int br_vlan_init(struct net_bridge *br) { struct net_bridge_vlan_group *vg; int ret = -ENOMEM; vg = kzalloc(sizeof(*vg), GFP_KERNEL); if (!vg) goto out; ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); if (ret) goto err_rhtbl; ret = vlan_tunnel_init(vg); if (ret) goto err_tunnel_init; INIT_LIST_HEAD(&vg->vlan_list); br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; rcu_assign_pointer(br->vlgrp, vg); out: return ret; err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: kfree(vg); goto out; } int nbp_vlan_init(struct net_bridge_port *p, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = p->br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_filtering = br_opt_get(p->br, BROPT_VLAN_ENABLED), }; struct net_bridge_vlan_group *vg; int ret = -ENOMEM; vg = kzalloc(sizeof(struct net_bridge_vlan_group), GFP_KERNEL); if (!vg) goto out; ret = switchdev_port_attr_set(p->dev, &attr, extack); if (ret && ret != -EOPNOTSUPP) goto err_vlan_enabled; ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); if (ret) goto err_rhtbl; ret = vlan_tunnel_init(vg); if (ret) goto err_tunnel_init; INIT_LIST_HEAD(&vg->vlan_list); rcu_assign_pointer(p->vlgrp, vg); if (p->br->default_pvid) { bool changed; ret = nbp_vlan_add(p, p->br->default_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &changed, extack); if (ret) goto err_vlan_add; br_vlan_notify(p->br, p, p->br->default_pvid, 0, RTM_NEWVLAN); } out: return ret; err_vlan_add: RCU_INIT_POINTER(p->vlgrp, NULL); synchronize_rcu(); vlan_tunnel_deinit(vg); err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: err_vlan_enabled: kfree(vg); goto out; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. * changed must be true only if the vlan was created or updated */ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags, bool *changed, struct netlink_ext_ack *extack) { struct net_bridge_vlan *vlan; int ret; ASSERT_RTNL(); *changed = false; vlan = br_vlan_find(nbp_vlan_group(port), vid); if (vlan) { bool would_change = __vlan_flags_would_change(vlan, flags); if (would_change) { /* Pass the flags to the hardware bridge */ ret = br_switchdev_port_vlan_add(port->dev, vid, flags, true, extack); if (ret && ret != -EOPNOTSUPP) return ret; } __vlan_flags_commit(vlan, flags); *changed = would_change; return 0; } vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); if (!vlan) return -ENOMEM; vlan->vid = vid; vlan->port = port; ret = __vlan_add(vlan, flags, extack); if (ret) kfree(vlan); else *changed = true; return ret; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) { struct net_bridge_vlan *v; ASSERT_RTNL(); v = br_vlan_find(nbp_vlan_group(port), vid); if (!v) return -ENOENT; br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid); br_fdb_delete_by_port(port->br, port, vid, 0); return __vlan_del(v); } void nbp_vlan_flush(struct net_bridge_port *port) { struct net_bridge_vlan_group *vg; ASSERT_RTNL(); vg = nbp_vlan_group(port); __vlan_flush(port->br, port, vg); RCU_INIT_POINTER(port->vlgrp, NULL); synchronize_rcu(); __vlan_group_free(vg); } void br_vlan_get_stats(const struct net_bridge_vlan *v, struct pcpu_sw_netstats *stats) { int i; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(i) { u64 rxpackets, rxbytes, txpackets, txbytes; struct pcpu_sw_netstats *cpu_stats; unsigned int start; cpu_stats = per_cpu_ptr(v->stats, i); do { start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); rxpackets = u64_stats_read(&cpu_stats->rx_packets); rxbytes = u64_stats_read(&cpu_stats->rx_bytes); txbytes = u64_stats_read(&cpu_stats->tx_bytes); txpackets = u64_stats_read(&cpu_stats->tx_packets); } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); u64_stats_add(&stats->rx_packets, rxpackets); u64_stats_add(&stats->rx_bytes, rxbytes); u64_stats_add(&stats->tx_bytes, txbytes); u64_stats_add(&stats->tx_packets, txpackets); } } int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; struct net_bridge_port *p; ASSERT_RTNL(); p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group(netdev_priv(dev)); else return -EINVAL; *p_pvid = br_get_pvid(vg); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid); int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; struct net_bridge_port *p; p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group_rcu(netdev_priv(dev)); else return -EINVAL; *p_pvid = br_get_pvid(vg); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu); void br_vlan_fill_forward_path_pvid(struct net_bridge *br, struct net_device_path_ctx *ctx, struct net_device_path *path) { struct net_bridge_vlan_group *vg; int idx = ctx->num_vlans - 1; u16 vid; path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return; vg = br_vlan_group(br); if (idx >= 0 && ctx->vlan[idx].proto == br->vlan_proto) { vid = ctx->vlan[idx].id; } else { path->bridge.vlan_mode = DEV_PATH_BR_VLAN_TAG; vid = br_get_pvid(vg); } path->bridge.vlan_id = vid; path->bridge.vlan_proto = br->vlan_proto; } int br_vlan_fill_forward_path_mode(struct net_bridge *br, struct net_bridge_port *dst, struct net_device_path *path) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return 0; vg = nbp_vlan_group_rcu(dst); v = br_vlan_find(vg, path->bridge.vlan_id); if (!v || !br_vlan_should_use(v)) return -EINVAL; if (!(v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) return 0; if (path->bridge.vlan_mode == DEV_PATH_BR_VLAN_TAG) path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP; else if (v->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG_HW; else path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG; return 0; } int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge_port *p; ASSERT_RTNL(); p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group(netdev_priv(dev)); else return -EINVAL; v = br_vlan_find(vg, vid); if (!v) return -ENOENT; p_vinfo->vid = vid; p_vinfo->flags = v->flags; if (vid == br_get_pvid(vg)) p_vinfo->flags |= BRIDGE_VLAN_INFO_PVID; return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_info); int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge_port *p; p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group_rcu(netdev_priv(dev)); else return -EINVAL; v = br_vlan_find(vg, vid); if (!v) return -ENOENT; p_vinfo->vid = vid; p_vinfo->flags = v->flags; if (vid == br_get_pvid(vg)) p_vinfo->flags |= BRIDGE_VLAN_INFO_PVID; return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_info_rcu); static int br_vlan_is_bind_vlan_dev(const struct net_device *dev) { return is_vlan_dev(dev) && !!(vlan_dev_priv(dev)->flags & VLAN_FLAG_BRIDGE_BINDING); } static int br_vlan_is_bind_vlan_dev_fn(struct net_device *dev, __always_unused struct netdev_nested_priv *priv) { return br_vlan_is_bind_vlan_dev(dev); } static bool br_vlan_has_upper_bind_vlan_dev(struct net_device *dev) { int found; rcu_read_lock(); found = netdev_walk_all_upper_dev_rcu(dev, br_vlan_is_bind_vlan_dev_fn, NULL); rcu_read_unlock(); return !!found; } struct br_vlan_bind_walk_data { u16 vid; struct net_device *result; }; static int br_vlan_match_bind_vlan_dev_fn(struct net_device *dev, struct netdev_nested_priv *priv) { struct br_vlan_bind_walk_data *data = priv->data; int found = 0; if (br_vlan_is_bind_vlan_dev(dev) && vlan_dev_priv(dev)->vlan_id == data->vid) { data->result = dev; found = 1; } return found; } static struct net_device * br_vlan_get_upper_bind_vlan_dev(struct net_device *dev, u16 vid) { struct br_vlan_bind_walk_data data = { .vid = vid, }; struct netdev_nested_priv priv = { .data = (void *)&data, }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_match_bind_vlan_dev_fn, &priv); rcu_read_unlock(); return data.result; } static bool br_vlan_is_dev_up(const struct net_device *dev) { return !!(dev->flags & IFF_UP) && netif_oper_up(dev); } static void br_vlan_set_vlan_dev_state(const struct net_bridge *br, struct net_device *vlan_dev) { u16 vid = vlan_dev_priv(vlan_dev)->vlan_id; struct net_bridge_vlan_group *vg; struct net_bridge_port *p; bool has_carrier = false; if (!netif_carrier_ok(br->dev)) { netif_carrier_off(vlan_dev); return; } list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); if (br_vlan_find(vg, vid) && br_vlan_is_dev_up(p->dev)) { has_carrier = true; break; } } if (has_carrier) netif_carrier_on(vlan_dev); else netif_carrier_off(vlan_dev); } static void br_vlan_set_all_vlan_dev_state(struct net_bridge_port *p) { struct net_bridge_vlan_group *vg = nbp_vlan_group(p); struct net_bridge_vlan *vlan; struct net_device *vlan_dev; list_for_each_entry(vlan, &vg->vlan_list, vlist) { vlan_dev = br_vlan_get_upper_bind_vlan_dev(p->br->dev, vlan->vid); if (vlan_dev) { if (br_vlan_is_dev_up(p->dev)) { if (netif_carrier_ok(p->br->dev)) netif_carrier_on(vlan_dev); } else { br_vlan_set_vlan_dev_state(p->br, vlan_dev); } } } } static void br_vlan_upper_change(struct net_device *dev, struct net_device *upper_dev, bool linking) { struct net_bridge *br = netdev_priv(dev); if (!br_vlan_is_bind_vlan_dev(upper_dev)) return; if (linking) { br_vlan_set_vlan_dev_state(br, upper_dev); br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, true); } else { br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, br_vlan_has_upper_bind_vlan_dev(dev)); } } struct br_vlan_link_state_walk_data { struct net_bridge *br; }; static int br_vlan_link_state_change_fn(struct net_device *vlan_dev, struct netdev_nested_priv *priv) { struct br_vlan_link_state_walk_data *data = priv->data; if (br_vlan_is_bind_vlan_dev(vlan_dev)) br_vlan_set_vlan_dev_state(data->br, vlan_dev); return 0; } static void br_vlan_link_state_change(struct net_device *dev, struct net_bridge *br) { struct br_vlan_link_state_walk_data data = { .br = br }; struct netdev_nested_priv priv = { .data = (void *)&data, }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_link_state_change_fn, &priv); rcu_read_unlock(); } /* Must be protected by RTNL. */ static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid) { struct net_device *vlan_dev; if (!br_opt_get(p->br, BROPT_VLAN_BRIDGE_BINDING)) return; vlan_dev = br_vlan_get_upper_bind_vlan_dev(p->br->dev, vid); if (vlan_dev) br_vlan_set_vlan_dev_state(p->br, vlan_dev); } /* Must be protected by RTNL. */ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) { struct netdev_notifier_changeupper_info *info; struct net_bridge *br = netdev_priv(dev); int vlcmd = 0, ret = 0; bool changed = false; switch (event) { case NETDEV_REGISTER: ret = br_vlan_add(br, br->default_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); vlcmd = RTM_NEWVLAN; break; case NETDEV_UNREGISTER: changed = !br_vlan_delete(br, br->default_pvid); vlcmd = RTM_DELVLAN; break; case NETDEV_CHANGEUPPER: info = ptr; br_vlan_upper_change(dev, info->upper_dev, info->linking); break; case NETDEV_CHANGE: case NETDEV_UP: if (!br_opt_get(br, BROPT_VLAN_BRIDGE_BINDING)) break; br_vlan_link_state_change(dev, br); break; } if (changed) br_vlan_notify(br, NULL, br->default_pvid, 0, vlcmd); return ret; } /* Must be protected by RTNL. */ void br_vlan_port_event(struct net_bridge_port *p, unsigned long event) { if (!br_opt_get(p->br, BROPT_VLAN_BRIDGE_BINDING)) return; switch (event) { case NETDEV_CHANGE: case NETDEV_DOWN: case NETDEV_UP: br_vlan_set_all_vlan_dev_state(p); break; } } static bool br_vlan_stats_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) { struct pcpu_sw_netstats stats; struct nlattr *nest; nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY_STATS); if (!nest) return false; br_vlan_get_stats(v, &stats); if (nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_RX_BYTES, u64_stats_read(&stats.rx_bytes), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_RX_PACKETS, u64_stats_read(&stats.rx_packets), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_TX_BYTES, u64_stats_read(&stats.tx_bytes), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_TX_PACKETS, u64_stats_read(&stats.tx_packets), BRIDGE_VLANDB_STATS_PAD)) goto out_err; nla_nest_end(skb, nest); return true; out_err: nla_nest_cancel(skb, nest); return false; } /* v_opts is used to dump the options which must be equal in the whole range */ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, const struct net_bridge_vlan *v_opts, u16 flags, bool dump_stats) { struct bridge_vlan_info info; struct nlattr *nest; nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY); if (!nest) return false; memset(&info, 0, sizeof(info)); info.vid = vid; if (flags & BRIDGE_VLAN_INFO_UNTAGGED) info.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (flags & BRIDGE_VLAN_INFO_PVID) info.flags |= BRIDGE_VLAN_INFO_PVID; if (nla_put(skb, BRIDGE_VLANDB_ENTRY_INFO, sizeof(info), &info)) goto out_err; if (vid_range && vid < vid_range && !(flags & BRIDGE_VLAN_INFO_PVID) && nla_put_u16(skb, BRIDGE_VLANDB_ENTRY_RANGE, vid_range)) goto out_err; if (v_opts) { if (!br_vlan_opts_fill(skb, v_opts)) goto out_err; if (dump_stats && !br_vlan_stats_fill(skb, v_opts)) goto out_err; } nla_nest_end(skb, nest); return true; out_err: nla_nest_cancel(skb, nest); return false; } static size_t rtnl_vlan_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct br_vlan_msg)) + nla_total_size(0) /* BRIDGE_VLANDB_ENTRY */ + nla_total_size(sizeof(u16)) /* BRIDGE_VLANDB_ENTRY_RANGE */ + nla_total_size(sizeof(struct bridge_vlan_info)) /* BRIDGE_VLANDB_ENTRY_INFO */ + br_vlan_opts_nl_size(); /* bridge vlan options */ } void br_vlan_notify(const struct net_bridge *br, const struct net_bridge_port *p, u16 vid, u16 vid_range, int cmd) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v = NULL; struct br_vlan_msg *bvm; struct nlmsghdr *nlh; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; u16 flags = 0; int ifindex; /* right now notifications are done only with rtnl held */ ASSERT_RTNL(); if (p) { ifindex = p->dev->ifindex; vg = nbp_vlan_group(p); net = dev_net(p->dev); } else { ifindex = br->dev->ifindex; vg = br_vlan_group(br); net = dev_net(br->dev); } skb = nlmsg_new(rtnl_vlan_nlmsg_size(), GFP_KERNEL); if (!skb) goto out_err; err = -EMSGSIZE; nlh = nlmsg_put(skb, 0, 0, cmd, sizeof(*bvm), 0); if (!nlh) goto out_err; bvm = nlmsg_data(nlh); memset(bvm, 0, sizeof(*bvm)); bvm->family = AF_BRIDGE; bvm->ifindex = ifindex; switch (cmd) { case RTM_NEWVLAN: /* need to find the vlan due to flags/options */ v = br_vlan_find(vg, vid); if (!v || !br_vlan_should_use(v)) goto out_kfree; flags = v->flags; if (br_get_pvid(vg) == v->vid) flags |= BRIDGE_VLAN_INFO_PVID; break; case RTM_DELVLAN: break; default: goto out_kfree; } if (!br_vlan_fill_vids(skb, vid, vid_range, v, flags, false)) goto out_err; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_BRVLAN, NULL, GFP_KERNEL); return; out_err: rtnl_set_sk_err(net, RTNLGRP_BRVLAN, err); out_kfree: kfree_skb(skb); } /* check if v_curr can enter a range ending in range_end */ bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end) { return v_curr->vid - range_end->vid == 1 && range_end->flags == v_curr->flags && br_vlan_opts_eq_range(v_curr, range_end); } static int br_vlan_dump_dev(const struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb, u32 dump_flags) { struct net_bridge_vlan *v, *range_start = NULL, *range_end = NULL; bool dump_global = !!(dump_flags & BRIDGE_VLANDB_DUMPF_GLOBAL); bool dump_stats = !!(dump_flags & BRIDGE_VLANDB_DUMPF_STATS); struct net_bridge_vlan_group *vg; int idx = 0, s_idx = cb->args[1]; struct nlmsghdr *nlh = NULL; struct net_bridge_port *p; struct br_vlan_msg *bvm; struct net_bridge *br; int err = 0; u16 pvid; if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) return -EINVAL; if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group_rcu(br); p = NULL; } else { /* global options are dumped only for bridge devices */ if (dump_global) return 0; p = br_port_get_rcu(dev); if (WARN_ON(!p)) return -EINVAL; vg = nbp_vlan_group_rcu(p); br = p->br; } if (!vg) return 0; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWVLAN, sizeof(*bvm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; bvm = nlmsg_data(nlh); memset(bvm, 0, sizeof(*bvm)); bvm->family = PF_BRIDGE; bvm->ifindex = dev->ifindex; pvid = br_get_pvid(vg); /* idx must stay at range's beginning until it is filled in */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (!dump_global && !br_vlan_should_use(v)) continue; if (idx < s_idx) { idx++; continue; } if (!range_start) { range_start = v; range_end = v; continue; } if (dump_global) { if (br_vlan_global_opts_can_enter_range(v, range_end)) goto update_end; if (!br_vlan_global_opts_fill(skb, range_start->vid, range_end->vid, range_start)) { err = -EMSGSIZE; break; } /* advance number of filled vlans */ idx += range_end->vid - range_start->vid + 1; range_start = v; } else if (dump_stats || v->vid == pvid || !br_vlan_can_enter_range(v, range_end)) { u16 vlan_flags = br_vlan_flags(range_start, pvid); if (!br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, vlan_flags, dump_stats)) { err = -EMSGSIZE; break; } /* advance number of filled vlans */ idx += range_end->vid - range_start->vid + 1; range_start = v; } update_end: range_end = v; } /* err will be 0 and range_start will be set in 3 cases here: * - first vlan (range_start == range_end) * - last vlan (range_start == range_end, not in range) * - last vlan range (range_start != range_end, in range) */ if (!err && range_start) { if (dump_global && !br_vlan_global_opts_fill(skb, range_start->vid, range_end->vid, range_start)) err = -EMSGSIZE; else if (!dump_global && !br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, br_vlan_flags(range_start, pvid), dump_stats)) err = -EMSGSIZE; } cb->args[1] = err ? idx : 0; nlmsg_end(skb, nlh); return err; } static const struct nla_policy br_vlan_db_dump_pol[BRIDGE_VLANDB_DUMP_MAX + 1] = { [BRIDGE_VLANDB_DUMP_FLAGS] = { .type = NLA_U32 }, }; static int br_vlan_rtm_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *dtb[BRIDGE_VLANDB_DUMP_MAX + 1]; int idx = 0, err = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); struct br_vlan_msg *bvm; struct net_device *dev; u32 dump_flags = 0; err = nlmsg_parse(cb->nlh, sizeof(*bvm), dtb, BRIDGE_VLANDB_DUMP_MAX, br_vlan_db_dump_pol, cb->extack); if (err < 0) return err; bvm = nlmsg_data(cb->nlh); if (dtb[BRIDGE_VLANDB_DUMP_FLAGS]) dump_flags = nla_get_u32(dtb[BRIDGE_VLANDB_DUMP_FLAGS]); rcu_read_lock(); if (bvm->ifindex) { dev = dev_get_by_index_rcu(net, bvm->ifindex); if (!dev) { err = -ENODEV; goto out_err; } err = br_vlan_dump_dev(dev, skb, cb, dump_flags); /* if the dump completed without an error we return 0 here */ if (err != -EMSGSIZE) goto out_err; } else { for_each_netdev_rcu(net, dev) { if (idx < s_idx) goto skip; err = br_vlan_dump_dev(dev, skb, cb, dump_flags); if (err == -EMSGSIZE) break; skip: idx++; } } cb->args[0] = idx; rcu_read_unlock(); return skb->len; out_err: rcu_read_unlock(); return err; } static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = { [BRIDGE_VLANDB_ENTRY_INFO] = NLA_POLICY_EXACT_LEN(sizeof(struct bridge_vlan_info)), [BRIDGE_VLANDB_ENTRY_RANGE] = { .type = NLA_U16 }, [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED }, [BRIDGE_VLANDB_ENTRY_MCAST_ROUTER] = { .type = NLA_U8 }, }; static int br_vlan_rtm_process_one(struct net_device *dev, const struct nlattr *attr, int cmd, struct netlink_ext_ack *extack) { struct bridge_vlan_info *vinfo, vrange_end, *vinfo_last = NULL; struct nlattr *tb[BRIDGE_VLANDB_ENTRY_MAX + 1]; bool changed = false, skip_processing = false; struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; int err = 0, cmdmap = 0; struct net_bridge *br; if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group(br); } else { p = br_port_get_rtnl(dev); if (WARN_ON(!p)) return -ENODEV; br = p->br; vg = nbp_vlan_group(p); } if (WARN_ON(!vg)) return -ENODEV; err = nla_parse_nested(tb, BRIDGE_VLANDB_ENTRY_MAX, attr, br_vlan_db_policy, extack); if (err) return err; if (!tb[BRIDGE_VLANDB_ENTRY_INFO]) { NL_SET_ERR_MSG_MOD(extack, "Missing vlan entry info"); return -EINVAL; } memset(&vrange_end, 0, sizeof(vrange_end)); vinfo = nla_data(tb[BRIDGE_VLANDB_ENTRY_INFO]); if (vinfo->flags & (BRIDGE_VLAN_INFO_RANGE_BEGIN | BRIDGE_VLAN_INFO_RANGE_END)) { NL_SET_ERR_MSG_MOD(extack, "Old-style vlan ranges are not allowed when using RTM vlan calls"); return -EINVAL; } if (!br_vlan_valid_id(vinfo->vid, extack)) return -EINVAL; if (tb[BRIDGE_VLANDB_ENTRY_RANGE]) { vrange_end.vid = nla_get_u16(tb[BRIDGE_VLANDB_ENTRY_RANGE]); /* validate user-provided flags without RANGE_BEGIN */ vrange_end.flags = BRIDGE_VLAN_INFO_RANGE_END | vinfo->flags; vinfo->flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN; /* vinfo_last is the range start, vinfo the range end */ vinfo_last = vinfo; vinfo = &vrange_end; if (!br_vlan_valid_id(vinfo->vid, extack) || !br_vlan_valid_range(vinfo, vinfo_last, extack)) return -EINVAL; } switch (cmd) { case RTM_NEWVLAN: cmdmap = RTM_SETLINK; skip_processing = !!(vinfo->flags & BRIDGE_VLAN_INFO_ONLY_OPTS); break; case RTM_DELVLAN: cmdmap = RTM_DELLINK; break; } if (!skip_processing) { struct bridge_vlan_info *tmp_last = vinfo_last; /* br_process_vlan_info may overwrite vinfo_last */ err = br_process_vlan_info(br, p, cmdmap, vinfo, &tmp_last, &changed, extack); /* notify first if anything changed */ if (changed) br_ifinfo_notify(cmdmap, br, p); if (err) return err; } /* deal with options */ if (cmd == RTM_NEWVLAN) { struct net_bridge_vlan *range_start, *range_end; if (vinfo_last) { range_start = br_vlan_find(vg, vinfo_last->vid); range_end = br_vlan_find(vg, vinfo->vid); } else { range_start = br_vlan_find(vg, vinfo->vid); range_end = range_start; } err = br_vlan_process_options(br, p, range_start, range_end, tb, extack); } return err; } static int br_vlan_rtm_process(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct br_vlan_msg *bvm; struct net_device *dev; struct nlattr *attr; int err, vlans = 0; int rem; /* this should validate the header and check for remaining bytes */ err = nlmsg_parse(nlh, sizeof(*bvm), NULL, BRIDGE_VLANDB_MAX, NULL, extack); if (err < 0) return err; bvm = nlmsg_data(nlh); dev = __dev_get_by_index(net, bvm->ifindex); if (!dev) return -ENODEV; if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) { NL_SET_ERR_MSG_MOD(extack, "The device is not a valid bridge or bridge port"); return -EINVAL; } nlmsg_for_each_attr(attr, nlh, sizeof(*bvm), rem) { switch (nla_type(attr)) { case BRIDGE_VLANDB_ENTRY: err = br_vlan_rtm_process_one(dev, attr, nlh->nlmsg_type, extack); break; case BRIDGE_VLANDB_GLOBAL_OPTIONS: err = br_vlan_rtm_process_global_options(dev, attr, nlh->nlmsg_type, extack); break; default: continue; } vlans++; if (err) break; } if (!vlans) { NL_SET_ERR_MSG_MOD(extack, "No vlans found to process"); err = -EINVAL; } return err; } void br_vlan_rtnl_init(void) { rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_GETVLAN, NULL, br_vlan_rtm_dump, 0); rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_NEWVLAN, br_vlan_rtm_process, NULL, 0); rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_DELVLAN, br_vlan_rtm_process, NULL, 0); } void br_vlan_rtnl_uninit(void) { rtnl_unregister(PF_BRIDGE, RTM_GETVLAN); rtnl_unregister(PF_BRIDGE, RTM_NEWVLAN); rtnl_unregister(PF_BRIDGE, RTM_DELVLAN); } |
| 10 41 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NOTE: * * This header has combined a lot of unrelated to each other stuff. * The process of splitting its content is in progress while keeping * backward compatibility. That's why it's highly recommended NOT to * include this header inside another header file, especially under * generic or architectural include/ directory. */ #ifndef _LINUX_KERNEL_H #define _LINUX_KERNEL_H #include <linux/stdarg.h> #include <linux/align.h> #include <linux/limits.h> #include <linux/linkage.h> #include <linux/stddef.h> #include <linux/types.h> #include <linux/compiler.h> #include <linux/container_of.h> #include <linux/bitops.h> #include <linux/kstrtox.h> #include <linux/log2.h> #include <linux/math.h> #include <linux/minmax.h> #include <linux/typecheck.h> #include <linux/panic.h> #include <linux/printk.h> #include <linux/build_bug.h> #include <linux/static_call_types.h> #include <linux/instruction_pointer.h> #include <asm/byteorder.h> #include <uapi/linux/kernel.h> #define STACK_MAGIC 0xdeadbeef /** * REPEAT_BYTE - repeat the value @x multiple times as an unsigned long value * @x: value to repeat * * NOTE: @x is not checked for > 0xff; larger values produce odd results. */ #define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) /* generic data direction definitions */ #define READ 0 #define WRITE 1 /** * ARRAY_SIZE - get the number of elements in array @arr * @arr: array to be sized */ #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) #define PTR_IF(cond, ptr) ((cond) ? (ptr) : NULL) #define u64_to_user_ptr(x) ( \ { \ typecheck(u64, (x)); \ (void __user *)(uintptr_t)(x); \ } \ ) /** * upper_32_bits - return bits 32-63 of a number * @n: the number we're accessing * * A basic shift-right of a 64- or 32-bit quantity. Use this to suppress * the "right shift count >= width of type" warning when that quantity is * 32-bits. */ #define upper_32_bits(n) ((u32)(((n) >> 16) >> 16)) /** * lower_32_bits - return bits 0-31 of a number * @n: the number we're accessing */ #define lower_32_bits(n) ((u32)((n) & 0xffffffff)) /** * upper_16_bits - return bits 16-31 of a number * @n: the number we're accessing */ #define upper_16_bits(n) ((u16)((n) >> 16)) /** * lower_16_bits - return bits 0-15 of a number * @n: the number we're accessing */ #define lower_16_bits(n) ((u16)((n) & 0xffff)) struct completion; struct user; #ifdef CONFIG_PREEMPT_VOLUNTARY_BUILD extern int __cond_resched(void); # define might_resched() __cond_resched() #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) extern int __cond_resched(void); DECLARE_STATIC_CALL(might_resched, __cond_resched); static __always_inline void might_resched(void) { static_call_mod(might_resched)(); } #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) extern int dynamic_might_resched(void); # define might_resched() dynamic_might_resched() #else # define might_resched() do { } while (0) #endif /* CONFIG_PREEMPT_* */ #ifdef CONFIG_DEBUG_ATOMIC_SLEEP extern void __might_resched(const char *file, int line, unsigned int offsets); extern void __might_sleep(const char *file, int line); extern void __cant_sleep(const char *file, int line, int preempt_offset); extern void __cant_migrate(const char *file, int line); /** * might_sleep - annotation for functions that can sleep * * this macro will print a stack trace if it is executed in an atomic * context (spinlock, irq-handler, ...). Additional sections where blocking is * not allowed can be annotated with non_block_start() and non_block_end() * pairs. * * This is a useful debugging help to be able to catch problems early and not * be bitten later when the calling function happens to sleep when it is not * supposed to. */ # define might_sleep() \ do { __might_sleep(__FILE__, __LINE__); might_resched(); } while (0) /** * cant_sleep - annotation for functions that cannot sleep * * this macro will print a stack trace if it is executed with preemption enabled */ # define cant_sleep() \ do { __cant_sleep(__FILE__, __LINE__, 0); } while (0) # define sched_annotate_sleep() (current->task_state_change = 0) /** * cant_migrate - annotation for functions that cannot migrate * * Will print a stack trace if executed in code which is migratable */ # define cant_migrate() \ do { \ if (IS_ENABLED(CONFIG_SMP)) \ __cant_migrate(__FILE__, __LINE__); \ } while (0) /** * non_block_start - annotate the start of section where sleeping is prohibited * * This is on behalf of the oom reaper, specifically when it is calling the mmu * notifiers. The problem is that if the notifier were to block on, for example, * mutex_lock() and if the process which holds that mutex were to perform a * sleeping memory allocation, the oom reaper is now blocked on completion of * that memory allocation. Other blocking calls like wait_event() pose similar * issues. */ # define non_block_start() (current->non_block_count++) /** * non_block_end - annotate the end of section where sleeping is prohibited * * Closes a section opened by non_block_start(). */ # define non_block_end() WARN_ON(current->non_block_count-- == 0) #else static inline void __might_resched(const char *file, int line, unsigned int offsets) { } static inline void __might_sleep(const char *file, int line) { } # define might_sleep() do { might_resched(); } while (0) # define cant_sleep() do { } while (0) # define cant_migrate() do { } while (0) # define sched_annotate_sleep() do { } while (0) # define non_block_start() do { } while (0) # define non_block_end() do { } while (0) #endif #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0) #if defined(CONFIG_MMU) && \ (defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)) #define might_fault() __might_fault(__FILE__, __LINE__) void __might_fault(const char *file, int line); #else static inline void might_fault(void) { } #endif void do_exit(long error_code) __noreturn; extern int num_to_str(char *buf, int size, unsigned long long num, unsigned int width); /* lib/printf utilities */ extern __printf(2, 3) int sprintf(char *buf, const char * fmt, ...); extern __printf(2, 0) int vsprintf(char *buf, const char *, va_list); extern __printf(3, 4) int snprintf(char *buf, size_t size, const char *fmt, ...); extern __printf(3, 0) int vsnprintf(char *buf, size_t size, const char *fmt, va_list args); extern __printf(3, 4) int scnprintf(char *buf, size_t size, const char *fmt, ...); extern __printf(3, 0) int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); extern __printf(2, 3) __malloc char *kasprintf(gfp_t gfp, const char *fmt, ...); extern __printf(2, 0) __malloc char *kvasprintf(gfp_t gfp, const char *fmt, va_list args); extern __printf(2, 0) const char *kvasprintf_const(gfp_t gfp, const char *fmt, va_list args); extern __scanf(2, 3) int sscanf(const char *, const char *, ...); extern __scanf(2, 0) int vsscanf(const char *, const char *, va_list); extern int no_hash_pointers_enable(char *str); extern int get_option(char **str, int *pint); extern char *get_options(const char *str, int nints, int *ints); extern unsigned long long memparse(const char *ptr, char **retptr); extern bool parse_option_str(const char *str, const char *option); extern char *next_arg(char *args, char **param, char **val); extern int core_kernel_text(unsigned long addr); extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); extern int func_ptr_is_kernel_text(void *ptr); extern void bust_spinlocks(int yes); extern int root_mountflags; extern bool early_boot_irqs_disabled; /* * Values used for system_state. Ordering of the states must not be changed * as code checks for <, <=, >, >= STATE. */ extern enum system_states { SYSTEM_BOOTING, SYSTEM_SCHEDULING, SYSTEM_FREEING_INITMEM, SYSTEM_RUNNING, SYSTEM_HALT, SYSTEM_POWER_OFF, SYSTEM_RESTART, SYSTEM_SUSPEND, } system_state; extern const char hex_asc[]; #define hex_asc_lo(x) hex_asc[((x) & 0x0f)] #define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] static inline char *hex_byte_pack(char *buf, u8 byte) { *buf++ = hex_asc_hi(byte); *buf++ = hex_asc_lo(byte); return buf; } extern const char hex_asc_upper[]; #define hex_asc_upper_lo(x) hex_asc_upper[((x) & 0x0f)] #define hex_asc_upper_hi(x) hex_asc_upper[((x) & 0xf0) >> 4] static inline char *hex_byte_pack_upper(char *buf, u8 byte) { *buf++ = hex_asc_upper_hi(byte); *buf++ = hex_asc_upper_lo(byte); return buf; } extern int hex_to_bin(unsigned char ch); extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); extern char *bin2hex(char *dst, const void *src, size_t count); bool mac_pton(const char *s, u8 *mac); /* * General tracing related utility functions - trace_printk(), * tracing_on/tracing_off and tracing_start()/tracing_stop * * Use tracing_on/tracing_off when you want to quickly turn on or off * tracing. It simply enables or disables the recording of the trace events. * This also corresponds to the user space /sys/kernel/debug/tracing/tracing_on * file, which gives a means for the kernel and userspace to interact. * Place a tracing_off() in the kernel where you want tracing to end. * From user space, examine the trace, and then echo 1 > tracing_on * to continue tracing. * * tracing_stop/tracing_start has slightly more overhead. It is used * by things like suspend to ram where disabling the recording of the * trace is not enough, but tracing must actually stop because things * like calling smp_processor_id() may crash the system. * * Most likely, you want to use tracing_on/tracing_off. */ enum ftrace_dump_mode { DUMP_NONE, DUMP_ALL, DUMP_ORIG, }; #ifdef CONFIG_TRACING void tracing_on(void); void tracing_off(void); int tracing_is_on(void); void tracing_snapshot(void); void tracing_snapshot_alloc(void); extern void tracing_start(void); extern void tracing_stop(void); static inline __printf(1, 2) void ____trace_printk_check_format(const char *fmt, ...) { } #define __trace_printk_check_format(fmt, args...) \ do { \ if (0) \ ____trace_printk_check_format(fmt, ##args); \ } while (0) /** * trace_printk - printf formatting in the ftrace buffer * @fmt: the printf format for printing * * Note: __trace_printk is an internal function for trace_printk() and * the @ip is passed in via the trace_printk() macro. * * This function allows a kernel developer to debug fast path sections * that printk is not appropriate for. By scattering in various * printk like tracing in the code, a developer can quickly see * where problems are occurring. * * This is intended as a debugging tool for the developer only. * Please refrain from leaving trace_printks scattered around in * your code. (Extra memory is used for special buffers that are * allocated when trace_printk() is used.) * * A little optimization trick is done here. If there's only one * argument, there's no need to scan the string for printf formats. * The trace_puts() will suffice. But how can we take advantage of * using trace_puts() when trace_printk() has only one argument? * By stringifying the args and checking the size we can tell * whether or not there are args. __stringify((__VA_ARGS__)) will * turn into "()\0" with a size of 3 when there are no args, anything * else will be bigger. All we need to do is define a string to this, * and then take its size and compare to 3. If it's bigger, use * do_trace_printk() otherwise, optimize it to trace_puts(). Then just * let gcc optimize the rest. */ #define trace_printk(fmt, ...) \ do { \ char _______STR[] = __stringify((__VA_ARGS__)); \ if (sizeof(_______STR) > 3) \ do_trace_printk(fmt, ##__VA_ARGS__); \ else \ trace_puts(fmt); \ } while (0) #define do_trace_printk(fmt, args...) \ do { \ static const char *trace_printk_fmt __used \ __section("__trace_printk_fmt") = \ __builtin_constant_p(fmt) ? fmt : NULL; \ \ __trace_printk_check_format(fmt, ##args); \ \ if (__builtin_constant_p(fmt)) \ __trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args); \ else \ __trace_printk(_THIS_IP_, fmt, ##args); \ } while (0) extern __printf(2, 3) int __trace_bprintk(unsigned long ip, const char *fmt, ...); extern __printf(2, 3) int __trace_printk(unsigned long ip, const char *fmt, ...); /** * trace_puts - write a string into the ftrace buffer * @str: the string to record * * Note: __trace_bputs is an internal function for trace_puts and * the @ip is passed in via the trace_puts macro. * * This is similar to trace_printk() but is made for those really fast * paths that a developer wants the least amount of "Heisenbug" effects, * where the processing of the print format is still too much. * * This function allows a kernel developer to debug fast path sections * that printk is not appropriate for. By scattering in various * printk like tracing in the code, a developer can quickly see * where problems are occurring. * * This is intended as a debugging tool for the developer only. * Please refrain from leaving trace_puts scattered around in * your code. (Extra memory is used for special buffers that are * allocated when trace_puts() is used.) * * Returns: 0 if nothing was written, positive # if string was. * (1 when __trace_bputs is used, strlen(str) when __trace_puts is used) */ #define trace_puts(str) ({ \ static const char *trace_printk_fmt __used \ __section("__trace_printk_fmt") = \ __builtin_constant_p(str) ? str : NULL; \ \ if (__builtin_constant_p(str)) \ __trace_bputs(_THIS_IP_, trace_printk_fmt); \ else \ __trace_puts(_THIS_IP_, str, strlen(str)); \ }) extern int __trace_bputs(unsigned long ip, const char *str); extern int __trace_puts(unsigned long ip, const char *str, int size); extern void trace_dump_stack(int skip); /* * The double __builtin_constant_p is because gcc will give us an error * if we try to allocate the static variable to fmt if it is not a * constant. Even with the outer if statement. */ #define ftrace_vprintk(fmt, vargs) \ do { \ if (__builtin_constant_p(fmt)) { \ static const char *trace_printk_fmt __used \ __section("__trace_printk_fmt") = \ __builtin_constant_p(fmt) ? fmt : NULL; \ \ __ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs); \ } else \ __ftrace_vprintk(_THIS_IP_, fmt, vargs); \ } while (0) extern __printf(2, 0) int __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap); extern __printf(2, 0) int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap); extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode); #else static inline void tracing_start(void) { } static inline void tracing_stop(void) { } static inline void trace_dump_stack(int skip) { } static inline void tracing_on(void) { } static inline void tracing_off(void) { } static inline int tracing_is_on(void) { return 0; } static inline void tracing_snapshot(void) { } static inline void tracing_snapshot_alloc(void) { } static inline __printf(1, 2) int trace_printk(const char *fmt, ...) { return 0; } static __printf(1, 0) inline int ftrace_vprintk(const char *fmt, va_list ap) { return 0; } static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } #endif /* CONFIG_TRACING */ /* This counts to 12. Any more, it will return 13th argument. */ #define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n #define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) #define __CONCAT(a, b) a ## b #define CONCATENATE(a, b) __CONCAT(a, b) /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD #endif /* Permissions on a sysfs file: you didn't miss the 0 prefix did you? */ #define VERIFY_OCTAL_PERMISSIONS(perms) \ (BUILD_BUG_ON_ZERO((perms) < 0) + \ BUILD_BUG_ON_ZERO((perms) > 0777) + \ /* USER_READABLE >= GROUP_READABLE >= OTHER_READABLE */ \ BUILD_BUG_ON_ZERO((((perms) >> 6) & 4) < (((perms) >> 3) & 4)) + \ BUILD_BUG_ON_ZERO((((perms) >> 3) & 4) < ((perms) & 4)) + \ /* USER_WRITABLE >= GROUP_WRITABLE */ \ BUILD_BUG_ON_ZERO((((perms) >> 6) & 2) < (((perms) >> 3) & 2)) + \ /* OTHER_WRITABLE? Generally considered a bad idea. */ \ BUILD_BUG_ON_ZERO((perms) & 2) + \ (perms)) #endif |
| 10883 10888 10883 10885 10880 10885 10884 10882 10722 10726 10622 10623 10614 821 10620 10722 10724 81 81 2 2 132 132 132 131 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 | // SPDX-License-Identifier: GPL-2.0 /* * Lockless hierarchical page accounting & limiting * * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner */ #include <linux/page_counter.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/bug.h> #include <asm/page.h> static void propagate_protected_usage(struct page_counter *c, unsigned long usage) { unsigned long protected, old_protected; long delta; if (!c->parent) return; protected = min(usage, READ_ONCE(c->min)); old_protected = atomic_long_read(&c->min_usage); if (protected != old_protected) { old_protected = atomic_long_xchg(&c->min_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_min_usage); } protected = min(usage, READ_ONCE(c->low)); old_protected = atomic_long_read(&c->low_usage); if (protected != old_protected) { old_protected = atomic_long_xchg(&c->low_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_low_usage); } } /** * page_counter_cancel - take pages out of the local counter * @counter: counter * @nr_pages: number of pages to cancel */ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) { long new; new = atomic_long_sub_return(nr_pages, &counter->usage); /* More uncharges than charges? */ if (WARN_ONCE(new < 0, "page_counter underflow: %ld nr_pages=%lu\n", new, nr_pages)) { new = 0; atomic_long_set(&counter->usage, new); } propagate_protected_usage(counter, new); } /** * page_counter_charge - hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * * NOTE: This does not consider any configured counter limits. */ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) { long new; new = atomic_long_add_return(nr_pages, &c->usage); propagate_protected_usage(c, new); /* * This is indeed racy, but we can live with some * inaccuracy in the watermark. */ if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } } /** * page_counter_try_charge - try to hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * @fail: points first counter to hit its limit, if any * * Returns %true on success, or %false and @fail if the counter or one * of its ancestors has hit its configured limit. */ bool page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail) { struct page_counter *c; for (c = counter; c; c = c->parent) { long new; /* * Charge speculatively to avoid an expensive CAS. If * a bigger charge fails, it might falsely lock out a * racing smaller charge and send it into reclaim * early, but the error is limited to the difference * between the two sizes, which is less than 2M/4M in * case of a THP locking out a regular page charge. * * The atomic_long_add_return() implies a full memory * barrier between incrementing the count and reading * the limit. When racing with page_counter_set_max(), * we either see the new limit or the setter sees the * counter has changed and retries. */ new = atomic_long_add_return(nr_pages, &c->usage); if (new > c->max) { atomic_long_sub(nr_pages, &c->usage); /* * This is racy, but we can live with some * inaccuracy in the failcnt which is only used * to report stats. */ data_race(c->failcnt++); *fail = c; goto failed; } propagate_protected_usage(c, new); /* * Just like with failcnt, we can live with some * inaccuracy in the watermark. */ if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } return true; failed: for (c = counter; c != *fail; c = c->parent) page_counter_cancel(c, nr_pages); return false; } /** * page_counter_uncharge - hierarchically uncharge pages * @counter: counter * @nr_pages: number of pages to uncharge */ void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) page_counter_cancel(c, nr_pages); } /** * page_counter_set_max - set the maximum number of pages allowed * @counter: counter * @nr_pages: limit to set * * Returns 0 on success, -EBUSY if the current number of pages on the * counter already exceeds the specified limit. * * The caller must serialize invocations on the same counter. */ int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages) { for (;;) { unsigned long old; long usage; /* * Update the limit while making sure that it's not * below the concurrently-changing counter value. * * The xchg implies two full memory barriers before * and after, so the read-swap-read is ordered and * ensures coherency with page_counter_try_charge(): * that function modifies the count before checking * the limit, so if it sees the old limit, we see the * modified counter and retry. */ usage = page_counter_read(counter); if (usage > nr_pages) return -EBUSY; old = xchg(&counter->max, nr_pages); if (page_counter_read(counter) <= usage || nr_pages >= old) return 0; counter->max = old; cond_resched(); } } /** * page_counter_set_min - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->min, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_set_low - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->low, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_memparse - memparse() for page counter limits * @buf: string to parse * @max: string meaning maximum possible value * @nr_pages: returns the result in number of pages * * Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be * limited to %PAGE_COUNTER_MAX. */ int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages) { char *end; u64 bytes; if (!strcmp(buf, max)) { *nr_pages = PAGE_COUNTER_MAX; return 0; } bytes = memparse(buf, &end); if (*end != '\0') return -EINVAL; *nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX); return 0; } |
| 1 1 28 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #ifndef _NET_BATMAN_ADV_MAIN_H_ #define _NET_BATMAN_ADV_MAIN_H_ #define BATADV_DRIVER_AUTHOR "Marek Lindner <mareklindner@neomailbox.ch>, " \ "Simon Wunderlich <sw@simonwunderlich.de>" #define BATADV_DRIVER_DESC "B.A.T.M.A.N. advanced" #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION #define BATADV_SOURCE_VERSION "2022.3" #endif /* B.A.T.M.A.N. parameters */ #define BATADV_TQ_MAX_VALUE 255 #define BATADV_THROUGHPUT_MAX_VALUE 0xFFFFFFFF #define BATADV_JITTER 20 /* Time To Live of broadcast messages */ #define BATADV_TTL 50 /* maximum sequence number age of broadcast messages */ #define BATADV_BCAST_MAX_AGE 64 /* purge originators after time in seconds if no valid packet comes in * -> TODO: check influence on BATADV_TQ_LOCAL_WINDOW_SIZE */ #define BATADV_PURGE_TIMEOUT 200000 /* 200 seconds */ #define BATADV_TT_LOCAL_TIMEOUT 600000 /* in milliseconds */ #define BATADV_TT_CLIENT_ROAM_TIMEOUT 600000 /* in milliseconds */ #define BATADV_TT_CLIENT_TEMP_TIMEOUT 600000 /* in milliseconds */ #define BATADV_TT_WORK_PERIOD 5000 /* 5 seconds */ #define BATADV_ORIG_WORK_PERIOD 1000 /* 1 second */ #define BATADV_MCAST_WORK_PERIOD 500 /* 0.5 seconds */ #define BATADV_DAT_ENTRY_TIMEOUT (5 * 60000) /* 5 mins in milliseconds */ /* sliding packet range of received originator messages in sequence numbers * (should be a multiple of our word size) */ #define BATADV_TQ_LOCAL_WINDOW_SIZE 64 /* milliseconds we have to keep pending tt_req */ #define BATADV_TT_REQUEST_TIMEOUT 3000 #define BATADV_TQ_GLOBAL_WINDOW_SIZE 5 #define BATADV_TQ_LOCAL_BIDRECT_SEND_MINIMUM 1 #define BATADV_TQ_LOCAL_BIDRECT_RECV_MINIMUM 1 #define BATADV_TQ_TOTAL_BIDRECT_LIMIT 1 /* B.A.T.M.A.N. V */ #define BATADV_THROUGHPUT_DEFAULT_VALUE 10 /* 1 Mbps */ #define BATADV_ELP_PROBES_PER_NODE 2 #define BATADV_ELP_MIN_PROBE_SIZE 200 /* bytes */ #define BATADV_ELP_PROBE_MAX_TX_DIFF 100 /* milliseconds */ #define BATADV_ELP_MAX_AGE 64 #define BATADV_OGM_MAX_ORIGDIFF 5 #define BATADV_OGM_MAX_AGE 64 /* number of OGMs sent with the last tt diff */ #define BATADV_TT_OGM_APPEND_MAX 3 /* Time in which a client can roam at most ROAMING_MAX_COUNT times in * milliseconds */ #define BATADV_ROAMING_MAX_TIME 20000 #define BATADV_ROAMING_MAX_COUNT 5 #define BATADV_NO_FLAGS 0 #define BATADV_NULL_IFINDEX 0 /* dummy ifindex used to avoid iface checks */ #define BATADV_NO_MARK 0 /* default interface for multi interface operation. The default interface is * used for communication which originated locally (i.e. is not forwarded) * or where special forwarding is not desired/necessary. */ #define BATADV_IF_DEFAULT ((struct batadv_hard_iface *)NULL) #define BATADV_NUM_WORDS BITS_TO_LONGS(BATADV_TQ_LOCAL_WINDOW_SIZE) #define BATADV_LOG_BUF_LEN 8192 /* has to be a power of 2 */ /* number of packets to send for broadcasts on different interface types */ #define BATADV_NUM_BCASTS_DEFAULT 1 #define BATADV_NUM_BCASTS_WIRELESS 3 /* length of the single packet used by the TP meter */ #define BATADV_TP_PACKET_LEN ETH_DATA_LEN /* msecs after which an ARP_REQUEST is sent in broadcast as fallback */ #define ARP_REQ_DELAY 250 /* numbers of originator to contact for any PUT/GET DHT operation */ #define BATADV_DAT_CANDIDATES_NUM 3 /* BATADV_TQ_SIMILARITY_THRESHOLD - TQ points that a secondary metric can differ * at most from the primary one in order to be still considered acceptable */ #define BATADV_TQ_SIMILARITY_THRESHOLD 50 /* should not be bigger than 512 bytes or change the size of * forw_packet->direct_link_flags */ #define BATADV_MAX_AGGREGATION_BYTES 512 #define BATADV_MAX_AGGREGATION_MS 100 #define BATADV_BLA_PERIOD_LENGTH 10000 /* 10 seconds */ #define BATADV_BLA_BACKBONE_TIMEOUT (BATADV_BLA_PERIOD_LENGTH * 6) #define BATADV_BLA_CLAIM_TIMEOUT (BATADV_BLA_PERIOD_LENGTH * 10) #define BATADV_BLA_WAIT_PERIODS 3 #define BATADV_BLA_LOOPDETECT_PERIODS 6 #define BATADV_BLA_LOOPDETECT_TIMEOUT 3000 /* 3 seconds */ #define BATADV_DUPLIST_SIZE 16 #define BATADV_DUPLIST_TIMEOUT 500 /* 500 ms */ /* don't reset again within 30 seconds */ #define BATADV_RESET_PROTECTION_MS 30000 #define BATADV_EXPECTED_SEQNO_RANGE 65536 #define BATADV_NC_NODE_TIMEOUT 10000 /* Milliseconds */ /** * BATADV_TP_MAX_NUM - maximum number of simultaneously active tp sessions */ #define BATADV_TP_MAX_NUM 5 /** * enum batadv_mesh_state - State of a soft interface */ enum batadv_mesh_state { /** @BATADV_MESH_INACTIVE: soft interface is not yet running */ BATADV_MESH_INACTIVE, /** @BATADV_MESH_ACTIVE: interface is up and running */ BATADV_MESH_ACTIVE, /** @BATADV_MESH_DEACTIVATING: interface is getting shut down */ BATADV_MESH_DEACTIVATING, }; #define BATADV_BCAST_QUEUE_LEN 256 #define BATADV_BATMAN_QUEUE_LEN 256 /** * enum batadv_uev_action - action type of uevent */ enum batadv_uev_action { /** @BATADV_UEV_ADD: gateway was selected (after none was selected) */ BATADV_UEV_ADD = 0, /** * @BATADV_UEV_DEL: selected gateway was removed and none is selected * anymore */ BATADV_UEV_DEL, /** * @BATADV_UEV_CHANGE: a different gateway was selected as based gateway */ BATADV_UEV_CHANGE, /** * @BATADV_UEV_LOOPDETECT: loop was detected which cannot be handled by * bridge loop avoidance */ BATADV_UEV_LOOPDETECT, }; /** * enum batadv_uev_type - Type of uevent */ enum batadv_uev_type { /** @BATADV_UEV_GW: selected gateway was modified */ BATADV_UEV_GW = 0, /** @BATADV_UEV_BLA: bridge loop avoidance event */ BATADV_UEV_BLA, }; #define BATADV_GW_THRESHOLD 50 /* Number of fragment chains for each orig_node */ #define BATADV_FRAG_BUFFER_COUNT 8 /* Maximum number of fragments for one packet */ #define BATADV_FRAG_MAX_FRAGMENTS 16 /* Maxumim size of each fragment */ #define BATADV_FRAG_MAX_FRAG_SIZE 1280 /* Time to keep fragments while waiting for rest of the fragments */ #define BATADV_FRAG_TIMEOUT 10000 #define BATADV_DAT_CANDIDATE_NOT_FOUND 0 #define BATADV_DAT_CANDIDATE_ORIG 1 /* Debug Messages */ #ifdef pr_fmt #undef pr_fmt #endif /* Append 'batman-adv: ' before kernel messages */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt /* Kernel headers */ #include <linux/atomic.h> #include <linux/compiler.h> #include <linux/etherdevice.h> #include <linux/if_vlan.h> #include <linux/jiffies.h> #include <linux/netdevice.h> #include <linux/percpu.h> #include <linux/skbuff.h> #include <linux/types.h> #include <uapi/linux/batadv_packet.h> #include "types.h" #include "main.h" /** * batadv_print_vid() - return printable version of vid information * @vid: the VLAN identifier * * Return: -1 when no VLAN is used, VLAN id otherwise */ static inline int batadv_print_vid(unsigned short vid) { if (vid & BATADV_VLAN_HAS_TAG) return (int)(vid & VLAN_VID_MASK); else return -1; } extern struct list_head batadv_hardif_list; extern unsigned int batadv_hardif_generation; extern unsigned char batadv_broadcast_addr[]; extern struct workqueue_struct *batadv_event_workqueue; int batadv_mesh_init(struct net_device *soft_iface); void batadv_mesh_free(struct net_device *soft_iface); bool batadv_is_my_mac(struct batadv_priv *bat_priv, const u8 *addr); int batadv_max_header_len(void); void batadv_skb_set_priority(struct sk_buff *skb, int offset); int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev); int batadv_recv_handler_register(u8 packet_type, int (*recv_handler)(struct sk_buff *, struct batadv_hard_iface *)); void batadv_recv_handler_unregister(u8 packet_type); __be32 batadv_skb_crc32(struct sk_buff *skb, u8 *payload_ptr); /** * batadv_compare_eth() - Compare two not u16 aligned Ethernet addresses * @data1: Pointer to a six-byte array containing the Ethernet address * @data2: Pointer other six-byte array containing the Ethernet address * * note: can't use ether_addr_equal() as it requires aligned memory * * Return: true if they are the same ethernet addr */ static inline bool batadv_compare_eth(const void *data1, const void *data2) { return ether_addr_equal_unaligned(data1, data2); } /** * batadv_has_timed_out() - compares current time (jiffies) and timestamp + * timeout * @timestamp: base value to compare with (in jiffies) * @timeout: added to base value before comparing (in milliseconds) * * Return: true if current time is after timestamp + timeout */ static inline bool batadv_has_timed_out(unsigned long timestamp, unsigned int timeout) { return time_is_before_jiffies(timestamp + msecs_to_jiffies(timeout)); } /** * batadv_atomic_dec_not_zero() - Decrease unless the number is 0 * @v: pointer of type atomic_t * * Return: non-zero if v was not 0, and zero otherwise. */ #define batadv_atomic_dec_not_zero(v) atomic_add_unless((v), -1, 0) /** * batadv_smallest_signed_int() - Returns the smallest signed integer in two's * complement with the sizeof x * @x: type of integer * * Return: smallest signed integer of type */ #define batadv_smallest_signed_int(x) (1u << (7u + 8u * (sizeof(x) - 1u))) /** * batadv_seq_before() - Checks if a sequence number x is a predecessor of y * @x: potential predecessor of @y * @y: value to compare @x against * * It handles overflows/underflows and can correctly check for a predecessor * unless the variable sequence number has grown by more than * 2**(bitwidth(x)-1)-1. * * This means that for a u8 with the maximum value 255, it would think: * * * when adding nothing - it is neither a predecessor nor a successor * * before adding more than 127 to the starting value - it is a predecessor, * * when adding 128 - it is neither a predecessor nor a successor, * * after adding more than 127 to the starting value - it is a successor * * Return: true when x is a predecessor of y, false otherwise */ #define batadv_seq_before(x, y) ({ \ typeof(x)_d1 = (x); \ typeof(y)_d2 = (y); \ typeof(x)_dummy = (_d1 - _d2); \ (void)(&_d1 == &_d2); \ _dummy > batadv_smallest_signed_int(_dummy); \ }) /** * batadv_seq_after() - Checks if a sequence number x is a successor of y * @x: potential successor of @y * @y: value to compare @x against * * It handles overflows/underflows and can correctly check for a successor * unless the variable sequence number has grown by more than * 2**(bitwidth(x)-1)-1. * * This means that for a u8 with the maximum value 255, it would think: * * * when adding nothing - it is neither a predecessor nor a successor * * before adding more than 127 to the starting value - it is a predecessor, * * when adding 128 - it is neither a predecessor nor a successor, * * after adding more than 127 to the starting value - it is a successor * * Return: true when x is a successor of y, false otherwise */ #define batadv_seq_after(x, y) batadv_seq_before(y, x) /** * batadv_add_counter() - Add to per cpu statistics counter of soft interface * @bat_priv: the bat priv with all the soft interface information * @idx: counter index which should be modified * @count: value to increase counter by * * Stop preemption on local cpu while incrementing the counter */ static inline void batadv_add_counter(struct batadv_priv *bat_priv, size_t idx, size_t count) { this_cpu_add(bat_priv->bat_counters[idx], count); } /** * batadv_inc_counter() - Increase per cpu statistics counter of soft interface * @b: the bat priv with all the soft interface information * @i: counter index which should be modified */ #define batadv_inc_counter(b, i) batadv_add_counter(b, i, 1) /** * BATADV_SKB_CB() - Get batadv_skb_cb from skb control buffer * @__skb: skb holding the control buffer * * The members of the control buffer are defined in struct batadv_skb_cb in * types.h. The macro is inspired by the similar macro TCP_SKB_CB() in tcp.h. * * Return: pointer to the batadv_skb_cb of the skb */ #define BATADV_SKB_CB(__skb) ((struct batadv_skb_cb *)&((__skb)->cb[0])) unsigned short batadv_get_vid(struct sk_buff *skb, size_t header_len); bool batadv_vlan_ap_isola_get(struct batadv_priv *bat_priv, unsigned short vid); int batadv_throw_uevent(struct batadv_priv *bat_priv, enum batadv_uev_type type, enum batadv_uev_action action, const char *data); #endif /* _NET_BATMAN_ADV_MAIN_H_ */ |
| 735 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM fib #if !defined(_TRACE_FIB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FIB_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <net/ip_fib.h> #include <linux/tracepoint.h> TRACE_EVENT(fib_table_lookup, TP_PROTO(u32 tb_id, const struct flowi4 *flp, const struct fib_nh_common *nhc, int err), TP_ARGS(tb_id, flp, nhc, err), TP_STRUCT__entry( __field( u32, tb_id ) __field( int, err ) __field( int, oif ) __field( int, iif ) __field( u8, proto ) __field( __u8, tos ) __field( __u8, scope ) __field( __u8, flags ) __array( __u8, src, 4 ) __array( __u8, dst, 4 ) __array( __u8, gw4, 4 ) __array( __u8, gw6, 16 ) __field( u16, sport ) __field( u16, dport ) __array(char, name, IFNAMSIZ ) ), TP_fast_assign( struct in6_addr in6_zero = {}; struct net_device *dev; struct in6_addr *in6; __be32 *p32; __entry->tb_id = tb_id; __entry->err = err; __entry->oif = flp->flowi4_oif; __entry->iif = flp->flowi4_iif; __entry->tos = flp->flowi4_tos; __entry->scope = flp->flowi4_scope; __entry->flags = flp->flowi4_flags; p32 = (__be32 *) __entry->src; *p32 = flp->saddr; p32 = (__be32 *) __entry->dst; *p32 = flp->daddr; __entry->proto = flp->flowi4_proto; if (__entry->proto == IPPROTO_TCP || __entry->proto == IPPROTO_UDP) { __entry->sport = ntohs(flp->fl4_sport); __entry->dport = ntohs(flp->fl4_dport); } else { __entry->sport = 0; __entry->dport = 0; } dev = nhc ? nhc->nhc_dev : NULL; strlcpy(__entry->name, dev ? dev->name : "-", IFNAMSIZ); if (nhc) { if (nhc->nhc_gw_family == AF_INET) { p32 = (__be32 *) __entry->gw4; *p32 = nhc->nhc_gw.ipv4; in6 = (struct in6_addr *)__entry->gw6; *in6 = in6_zero; } else if (nhc->nhc_gw_family == AF_INET6) { p32 = (__be32 *) __entry->gw4; *p32 = 0; in6 = (struct in6_addr *)__entry->gw6; *in6 = nhc->nhc_gw.ipv6; } } else { p32 = (__be32 *) __entry->gw4; *p32 = 0; in6 = (struct in6_addr *)__entry->gw6; *in6 = in6_zero; } ), TP_printk("table %u oif %d iif %d proto %u %pI4/%u -> %pI4/%u tos %d scope %d flags %x ==> dev %s gw %pI4/%pI6c err %d", __entry->tb_id, __entry->oif, __entry->iif, __entry->proto, __entry->src, __entry->sport, __entry->dst, __entry->dport, __entry->tos, __entry->scope, __entry->flags, __entry->name, __entry->gw4, __entry->gw6, __entry->err) ); #endif /* _TRACE_FIB_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "queueing.h" #include <linux/skb_array.h> struct multicore_worker __percpu * wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr) { int cpu; struct multicore_worker __percpu *worker = alloc_percpu(struct multicore_worker); if (!worker) return NULL; for_each_possible_cpu(cpu) { per_cpu_ptr(worker, cpu)->ptr = ptr; INIT_WORK(&per_cpu_ptr(worker, cpu)->work, function); } return worker; } int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, unsigned int len) { int ret; memset(queue, 0, sizeof(*queue)); ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL); if (ret) return ret; queue->worker = wg_packet_percpu_multicore_worker_alloc(function, queue); if (!queue->worker) { ptr_ring_cleanup(&queue->ring, NULL); return -ENOMEM; } return 0; } void wg_packet_queue_free(struct crypt_queue *queue, bool purge) { free_percpu(queue->worker); WARN_ON(!purge && !__ptr_ring_empty(&queue->ring)); ptr_ring_cleanup(&queue->ring, purge ? __skb_array_destroy_skb : NULL); } #define NEXT(skb) ((skb)->prev) #define STUB(queue) ((struct sk_buff *)&queue->empty) void wg_prev_queue_init(struct prev_queue *queue) { NEXT(STUB(queue)) = NULL; queue->head = queue->tail = STUB(queue); queue->peeked = NULL; atomic_set(&queue->count, 0); BUILD_BUG_ON( offsetof(struct sk_buff, next) != offsetof(struct prev_queue, empty.next) - offsetof(struct prev_queue, empty) || offsetof(struct sk_buff, prev) != offsetof(struct prev_queue, empty.prev) - offsetof(struct prev_queue, empty)); } static void __wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb) { WRITE_ONCE(NEXT(skb), NULL); WRITE_ONCE(NEXT(xchg_release(&queue->head, skb)), skb); } bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb) { if (!atomic_add_unless(&queue->count, 1, MAX_QUEUED_PACKETS)) return false; __wg_prev_queue_enqueue(queue, skb); return true; } struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue) { struct sk_buff *tail = queue->tail, *next = smp_load_acquire(&NEXT(tail)); if (tail == STUB(queue)) { if (!next) return NULL; queue->tail = next; tail = next; next = smp_load_acquire(&NEXT(next)); } if (next) { queue->tail = next; atomic_dec(&queue->count); return tail; } if (tail != READ_ONCE(queue->head)) return NULL; __wg_prev_queue_enqueue(queue, STUB(queue)); next = smp_load_acquire(&NEXT(tail)); if (next) { queue->tail = next; atomic_dec(&queue->count); return tail; } return NULL; } #undef NEXT #undef STUB |
| 178 178 178 72 72 72 72 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001 Intel Corp. * Copyright (c) 2001 Nokia, Inc. * * This file is part of the SCTP kernel implementation * * These are the state tables for the SCTP state machine. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Jon Grimm <jgrimm@us.ibm.com> * Hui Huang <hui.huang@nokia.com> * Daisy Chang <daisyc@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> * Sridhar Samudrala <sri@us.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/skbuff.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> static const struct sctp_sm_table_entry primitive_event_table[SCTP_NUM_PRIMITIVE_TYPES][SCTP_STATE_NUM_STATES]; static const struct sctp_sm_table_entry other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_STATE_NUM_STATES]; static const struct sctp_sm_table_entry timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES]; static const struct sctp_sm_table_entry *sctp_chunk_event_lookup( struct net *net, enum sctp_cid cid, enum sctp_state state); static const struct sctp_sm_table_entry bug = { .fn = sctp_sf_bug, .name = "sctp_sf_bug" }; #define DO_LOOKUP(_max, _type, _table) \ ({ \ const struct sctp_sm_table_entry *rtn; \ \ if ((event_subtype._type > (_max))) { \ pr_warn("table %p possible attack: event %d exceeds max %d\n", \ _table, event_subtype._type, _max); \ rtn = &bug; \ } else \ rtn = &_table[event_subtype._type][(int)state]; \ \ rtn; \ }) const struct sctp_sm_table_entry *sctp_sm_lookup_event( struct net *net, enum sctp_event_type event_type, enum sctp_state state, union sctp_subtype event_subtype) { switch (event_type) { case SCTP_EVENT_T_CHUNK: return sctp_chunk_event_lookup(net, event_subtype.chunk, state); case SCTP_EVENT_T_TIMEOUT: return DO_LOOKUP(SCTP_EVENT_TIMEOUT_MAX, timeout, timeout_event_table); case SCTP_EVENT_T_OTHER: return DO_LOOKUP(SCTP_EVENT_OTHER_MAX, other, other_event_table); case SCTP_EVENT_T_PRIMITIVE: return DO_LOOKUP(SCTP_EVENT_PRIMITIVE_MAX, primitive, primitive_event_table); default: /* Yikes! We got an illegal event type. */ return &bug; } } #define TYPE_SCTP_FUNC(func) {.fn = func, .name = #func} #define TYPE_SCTP_DATA { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_data_6_2), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_eat_data_6_2), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_eat_data_fast_4_4), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_DATA */ #define TYPE_SCTP_INIT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1B_init), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_1_siminit), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_1_siminit), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_2_dupinit), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_2_dupinit), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_2_dupinit), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_2_dupinit), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_reshutack), \ } /* TYPE_SCTP_INIT */ #define TYPE_SCTP_INIT_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_3_initack), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1C_ack), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_INIT_ACK */ #define TYPE_SCTP_SACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_sack_6_2), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_sack_6_2), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_eat_sack_6_2), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_sack_6_2), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_SACK */ #define TYPE_SCTP_HEARTBEAT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ /* This should not happen, but we are nice. */ \ TYPE_SCTP_FUNC(sctp_sf_beat_8_3), \ } /* TYPE_SCTP_HEARTBEAT */ #define TYPE_SCTP_HEARTBEAT_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_violation), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_backbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_backbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_backbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_backbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_HEARTBEAT_ACK */ #define TYPE_SCTP_ABORT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_pdiscard), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_wait_abort), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_echoed_abort), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_1_abort), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_pending_abort), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_sent_abort), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_1_abort), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_ack_sent_abort), \ } /* TYPE_SCTP_ABORT */ #define TYPE_SCTP_SHUTDOWN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shutdown), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shutdown), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shutdown_ack), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shut_ctsn), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_SHUTDOWN */ #define TYPE_SCTP_SHUTDOWN_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_8_5_1_E_sa), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_8_5_1_E_sa), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_violation), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_violation), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_final), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_violation), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_final), \ } /* TYPE_SCTP_SHUTDOWN_ACK */ #define TYPE_SCTP_ERROR { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_echoed_err), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_operr_notify), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_operr_notify), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_operr_notify), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ERROR */ #define TYPE_SCTP_COOKIE_ECHO { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1D_ce), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_2_4_dupcook), \ } /* TYPE_SCTP_COOKIE_ECHO */ #define TYPE_SCTP_COOKIE_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_5_1E_ca), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_COOKIE_ACK */ #define TYPE_SCTP_ECN_ECNE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecne), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ECN_ECNE */ #define TYPE_SCTP_ECN_CWR { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecn_cwr), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecn_cwr), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_ecn_cwr), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ECN_CWR */ #define TYPE_SCTP_SHUTDOWN_COMPLETE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_4_C), \ } /* TYPE_SCTP_SHUTDOWN_COMPLETE */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. * * For base protocol (RFC 2960). */ static const struct sctp_sm_table_entry chunk_event_table[SCTP_NUM_BASE_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_DATA, TYPE_SCTP_INIT, TYPE_SCTP_INIT_ACK, TYPE_SCTP_SACK, TYPE_SCTP_HEARTBEAT, TYPE_SCTP_HEARTBEAT_ACK, TYPE_SCTP_ABORT, TYPE_SCTP_SHUTDOWN, TYPE_SCTP_SHUTDOWN_ACK, TYPE_SCTP_ERROR, TYPE_SCTP_COOKIE_ECHO, TYPE_SCTP_COOKIE_ACK, TYPE_SCTP_ECN_ECNE, TYPE_SCTP_ECN_CWR, TYPE_SCTP_SHUTDOWN_COMPLETE, }; /* state_fn_t chunk_event_table[][] */ #define TYPE_SCTP_ASCONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ASCONF */ #define TYPE_SCTP_ASCONF_ACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf_ack), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf_ack), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf_ack), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_asconf_ack), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_ASCONF_ACK */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry addip_chunk_event_table[SCTP_NUM_ADDIP_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_ASCONF, TYPE_SCTP_ASCONF_ACK, }; /*state_fn_t addip_chunk_event_table[][] */ #define TYPE_SCTP_FWD_TSN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_fwd_tsn), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_eat_fwd_tsn), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_eat_fwd_tsn_fast), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_FWD_TSN */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry prsctp_chunk_event_table[SCTP_NUM_PRSCTP_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_FWD_TSN, }; /*state_fn_t prsctp_chunk_event_table[][] */ #define TYPE_SCTP_RECONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_reconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_reconf), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ } /* TYPE_SCTP_RECONF */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry reconf_chunk_event_table[SCTP_NUM_RECONF_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_RECONF, }; /*state_fn_t reconf_chunk_event_table[][] */ #define TYPE_SCTP_AUTH { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_eat_auth), \ } /* TYPE_SCTP_AUTH */ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry auth_chunk_event_table[SCTP_NUM_AUTH_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_AUTH, }; /*state_fn_t auth_chunk_event_table[][] */ static const struct sctp_sm_table_entry pad_chunk_event_table[SCTP_STATE_NUM_STATES] = { /* SCTP_STATE_CLOSED */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_COOKIE_WAIT */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_COOKIE_ECHOED */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_ESTABLISHED */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_SHUTDOWN_PENDING */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_SHUTDOWN_SENT */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_SHUTDOWN_RECEIVED */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), /* SCTP_STATE_SHUTDOWN_ACK_SENT */ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), }; /* chunk pad */ static const struct sctp_sm_table_entry chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { /* SCTP_STATE_CLOSED */ TYPE_SCTP_FUNC(sctp_sf_ootb), /* SCTP_STATE_COOKIE_WAIT */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_COOKIE_ECHOED */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_ESTABLISHED */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_SHUTDOWN_PENDING */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_SHUTDOWN_SENT */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_SHUTDOWN_RECEIVED */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_SHUTDOWN_ACK_SENT */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), }; /* chunk unknown */ #define TYPE_SCTP_PRIMITIVE_ASSOCIATE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asoc), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_not_impl), \ } /* TYPE_SCTP_PRIMITIVE_ASSOCIATE */ #define TYPE_SCTP_PRIMITIVE_SHUTDOWN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_wait_prm_shutdown), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_echoed_prm_shutdown),\ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_prm_shutdown), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_primitive), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_primitive), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_primitive), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_primitive), \ } /* TYPE_SCTP_PRIMITIVE_SHUTDOWN */ #define TYPE_SCTP_PRIMITIVE_ABORT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_wait_prm_abort), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_echoed_prm_abort), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_1_prm_abort), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_pending_prm_abort), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_sent_prm_abort), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_1_prm_abort), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_shutdown_ack_sent_prm_abort), \ } /* TYPE_SCTP_PRIMITIVE_ABORT */ #define TYPE_SCTP_PRIMITIVE_SEND { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_send), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_send), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_send), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ } /* TYPE_SCTP_PRIMITIVE_SEND */ #define TYPE_SCTP_PRIMITIVE_REQUESTHEARTBEAT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_requestheartbeat), \ } /* TYPE_SCTP_PRIMITIVE_REQUESTHEARTBEAT */ #define TYPE_SCTP_PRIMITIVE_ASCONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asconf), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asconf), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_asconf), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ } /* TYPE_SCTP_PRIMITIVE_ASCONF */ #define TYPE_SCTP_PRIMITIVE_RECONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_error_closed), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \ } /* TYPE_SCTP_PRIMITIVE_RECONF */ /* The primary index for this table is the primitive type. * The secondary index for this table is the state. */ static const struct sctp_sm_table_entry primitive_event_table[SCTP_NUM_PRIMITIVE_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_PRIMITIVE_ASSOCIATE, TYPE_SCTP_PRIMITIVE_SHUTDOWN, TYPE_SCTP_PRIMITIVE_ABORT, TYPE_SCTP_PRIMITIVE_SEND, TYPE_SCTP_PRIMITIVE_REQUESTHEARTBEAT, TYPE_SCTP_PRIMITIVE_ASCONF, TYPE_SCTP_PRIMITIVE_RECONF, }; #define TYPE_SCTP_OTHER_NO_PENDING_TSN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_no_pending_tsn), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_start_shutdown), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_9_2_shutdown_ack), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ } #define TYPE_SCTP_OTHER_ICMP_PROTO_UNREACH { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_cookie_wait_icmp_abort), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ } static const struct sctp_sm_table_entry other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_OTHER_NO_PENDING_TSN, TYPE_SCTP_OTHER_ICMP_PROTO_UNREACH, }; #define TYPE_SCTP_EVENT_TIMEOUT_NONE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T1_COOKIE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_bug), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_t1_cookie_timer_expire), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T1_INIT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_t1_init_timer_expire), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T2_SHUTDOWN { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_t2_timer_expire), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_t2_timer_expire), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T3_RTX { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_3_3_rtx), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_3_3_rtx), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_3_3_rtx), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_3_3_rtx), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T4_RTO { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_t4_timer_expire), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_t5_timer_expire), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_t5_timer_expire), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_HEARTBEAT { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_sendbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_sendbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_sendbeat_8_3), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_SACK { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_2_sack), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_2_sack), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_do_6_2_sack), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_AUTOCLOSE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_autoclose_timer_expire), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_RECONF { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_send_reconf), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } #define TYPE_SCTP_EVENT_TIMEOUT_PROBE { \ /* SCTP_STATE_CLOSED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_COOKIE_ECHOED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_send_probe), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } static const struct sctp_sm_table_entry timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_EVENT_TIMEOUT_NONE, TYPE_SCTP_EVENT_TIMEOUT_T1_COOKIE, TYPE_SCTP_EVENT_TIMEOUT_T1_INIT, TYPE_SCTP_EVENT_TIMEOUT_T2_SHUTDOWN, TYPE_SCTP_EVENT_TIMEOUT_T3_RTX, TYPE_SCTP_EVENT_TIMEOUT_T4_RTO, TYPE_SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD, TYPE_SCTP_EVENT_TIMEOUT_HEARTBEAT, TYPE_SCTP_EVENT_TIMEOUT_RECONF, TYPE_SCTP_EVENT_TIMEOUT_PROBE, TYPE_SCTP_EVENT_TIMEOUT_SACK, TYPE_SCTP_EVENT_TIMEOUT_AUTOCLOSE, }; static const struct sctp_sm_table_entry *sctp_chunk_event_lookup( struct net *net, enum sctp_cid cid, enum sctp_state state) { if (state > SCTP_STATE_MAX) return &bug; if (cid == SCTP_CID_I_DATA) cid = SCTP_CID_DATA; if (cid <= SCTP_CID_BASE_MAX) return &chunk_event_table[cid][state]; switch ((u16)cid) { case SCTP_CID_FWD_TSN: case SCTP_CID_I_FWD_TSN: return &prsctp_chunk_event_table[0][state]; case SCTP_CID_ASCONF: return &addip_chunk_event_table[0][state]; case SCTP_CID_ASCONF_ACK: return &addip_chunk_event_table[1][state]; case SCTP_CID_RECONF: return &reconf_chunk_event_table[0][state]; case SCTP_CID_AUTH: return &auth_chunk_event_table[0][state]; case SCTP_CID_PAD: return &pad_chunk_event_table[state]; } return &chunk_event_table_unknown[state]; } |
| 112 102 82 113 175 175 29 29 29 135 135 147 175 175 175 174 175 175 175 175 174 148 61 61 148 148 148 148 148 175 175 175 13 73 258 258 175 175 259 259 259 258 175 259 259 259 175 259 258 174 259 258 175 95 173 175 173 175 175 175 175 175 175 174 175 175 175 175 175 175 175 175 221 222 221 221 222 222 403 79 79 79 66 79 68 79 252 252 252 251 237 237 259 259 258 257 258 256 259 148 14 258 258 259 259 18 17 4 13 13 258 175 259 258 256 259 259 23 259 236 259 142 8 132 27 25 10 10 10 10 10 10 208 207 208 175 208 33 208 207 217 33 217 1 217 11 10 10 10 11 106 98 98 98 106 11 99 99 99 11 85 85 24 4 50 49 49 49 142 142 135 142 142 15 15 4 1 142 134 117 114 57 142 18 16 16 16 16 16 16 5 5 3 1 1 1 141 142 142 1 142 255 91 255 136 259 142 142 142 12 132 11 142 18 15 142 142 142 106 106 128 115 106 1 106 141 115 192 192 105 106 106 95 82 106 43 106 106 17 17 17 5 12 12 12 17 17 141 90 90 148 148 148 148 148 148 143 148 148 11 11 11 11 11 1 12 12 11 12 12 12 1 12 12 12 12 12 12 2 2 2 2 2 2 251 244 245 2 2 8 8 10 174 175 175 175 175 175 175 175 175 175 175 174 175 175 175 175 175 175 175 175 175 175 175 7 7 7 12 12 20 20 20 20 20 10 20 7 20 7 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net> */ /* * Changes: Pedro Roque : Retransmit queue handled by TCP. * : Fragmentation on mtu decrease * : Segment collapse on retransmit * : AF independence * * Linus Torvalds : send_delayed_ack * David S. Miller : Charge memory using the right skb * during syn/ack processing. * David S. Miller : Output engine completely rewritten. * Andrea Arcangeli: SYNACK carry ts_recent in tsecr. * Cacophonix Gaul : draft-minshall-nagle-01 * J Hadi Salim : ECN support * */ #define pr_fmt(fmt) "TCP: " fmt #include <net/tcp.h> #include <net/mptcp.h> #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/module.h> #include <linux/static_key.h> #include <trace/events/tcp.h> /* Refresh clocks of a TCP socket, * ensuring monotically increasing values. */ void tcp_mstamp_refresh(struct tcp_sock *tp) { u64 val = tcp_clock_ns(); tp->tcp_clock_cache = val; tp->tcp_mstamp = div_u64(val, NSEC_PER_USEC); } static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); /* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq); __skb_unlink(skb, &sk->sk_write_queue); tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); if (tp->highest_sack == NULL) tp->highest_sack = skb; tp->packets_out += tcp_skb_pcount(skb); if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, tcp_skb_pcount(skb)); tcp_check_space(sk); } /* SND.NXT, if window was not shrunk or the amount of shrunk was less than one * window scaling factor due to loss of precision. * If window has been shrunk, what should we make? It is not clear at all. * Using SND.UNA we will fail to open window, SND.NXT is out of window. :-( * Anything in between SND.UNA...SND.UNA+SND.WND also can be already * invalid. OK, let's make this for now: */ static inline __u32 tcp_acceptable_seq(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (!before(tcp_wnd_end(tp), tp->snd_nxt) || (tp->rx_opt.wscale_ok && ((tp->snd_nxt - tcp_wnd_end(tp)) < (1 << tp->rx_opt.rcv_wscale)))) return tp->snd_nxt; else return tcp_wnd_end(tp); } /* Calculate mss to advertise in SYN segment. * RFC1122, RFC1063, draft-ietf-tcpimpl-pmtud-01 state that: * * 1. It is independent of path mtu. * 2. Ideally, it is maximal possible segment size i.e. 65535-40. * 3. For IPv4 it is reasonable to calculate it from maximal MTU of * attached devices, because some buggy hosts are confused by * large MSS. * 4. We do not make 3, we advertise MSS, calculated from first * hop device mtu, but allow to raise it to ip_rt_min_advmss. * This may be overridden via information stored in routing table. * 5. Value 65535 for MSS is valid in IPv6 and means "as large as possible, * probably even Jumbo". */ static __u16 tcp_advertise_mss(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); const struct dst_entry *dst = __sk_dst_get(sk); int mss = tp->advmss; if (dst) { unsigned int metric = dst_metric_advmss(dst); if (metric < mss) { mss = metric; tp->advmss = mss; } } return (__u16)mss; } /* RFC2861. Reset CWND after idle period longer RTO to "restart window". * This is the first part of cwnd validation mechanism. */ void tcp_cwnd_restart(struct sock *sk, s32 delta) { struct tcp_sock *tp = tcp_sk(sk); u32 restart_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk)); u32 cwnd = tcp_snd_cwnd(tp); tcp_ca_event(sk, CA_EVENT_CWND_RESTART); tp->snd_ssthresh = tcp_current_ssthresh(sk); restart_cwnd = min(restart_cwnd, cwnd); while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd) cwnd >>= 1; tcp_snd_cwnd_set(tp, max(cwnd, restart_cwnd)); tp->snd_cwnd_stamp = tcp_jiffies32; tp->snd_cwnd_used = 0; } /* Congestion state accounting after a packet has been sent. */ static void tcp_event_data_sent(struct tcp_sock *tp, struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); const u32 now = tcp_jiffies32; if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START); tp->lsndtime = now; /* If it is a reply for ato after last received * packet, enter pingpong mode. */ if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) inet_csk_enter_pingpong_mode(sk); } /* Account for an ACK we sent. */ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); if (unlikely(tp->compressed_ack)) { NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED, tp->compressed_ack); tp->compressed_ack = 0; if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1) __sock_put(sk); } if (unlikely(rcv_nxt != tp->rcv_nxt)) return; /* Special ACK sent by DCTCP to reflect ECN */ tcp_dec_quickack_mode(sk, pkts); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } /* Determine a window scaling and initial window to offer. * Based on the assumption that the given amount of space * will be offered. Store the results in the tp structure. * NOTE: for smooth operation initial space offering should * be a multiple of mss if possible. We assume here that mss >= 1. * This MUST be enforced by all callers. */ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd) { unsigned int space = (__space < 0 ? 0 : __space); /* If no clamp set the clamp to the max possible scaled window */ if (*window_clamp == 0) (*window_clamp) = (U16_MAX << TCP_MAX_WSCALE); space = min(*window_clamp, space); /* Quantize space offering to a multiple of mss if possible. */ if (space > mss) space = rounddown(space, mss); /* NOTE: offering an initial window larger than 32767 * will break some buggy TCP stacks. If the admin tells us * it is likely we could be speaking with such a buggy stack * we will truncate our initial window offering to 32K-1 * unless the remote has sent us a window scaling option, * which we interpret as a sign the remote TCP is not * misinterpreting the window field as a signed quantity. */ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)) (*rcv_wnd) = min(space, MAX_TCP_WINDOW); else (*rcv_wnd) = min_t(u32, space, U16_MAX); if (init_rcv_wnd) *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); *rcv_wscale = 0; if (wscale_ok) { /* Set window scaling on max possible window */ space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); space = max_t(u32, space, READ_ONCE(sysctl_rmem_max)); space = min_t(u32, space, *window_clamp); *rcv_wscale = clamp_t(int, ilog2(space) - 15, 0, TCP_MAX_WSCALE); } /* Set the clamp no higher than max representable value */ (*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp); } EXPORT_SYMBOL(tcp_select_initial_window); /* Chose a new window to advertise, update state in tcp_sock for the * socket, and return result with RFC1323 scaling applied. The return * value can be stuffed directly into th->window for an outgoing * frame. */ static u16 tcp_select_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 old_win = tp->rcv_wnd; u32 cur_win = tcp_receive_window(tp); u32 new_win = __tcp_select_window(sk); /* Never shrink the offered window */ if (new_win < cur_win) { /* Danger Will Robinson! * Don't update rcv_wup/rcv_wnd here or else * we will not be able to advertise a zero * window in time. --DaveM * * Relax Will Robinson. */ if (new_win == 0) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWANTZEROWINDOWADV); new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); } tp->rcv_wnd = new_win; tp->rcv_wup = tp->rcv_nxt; /* Make sure we do not exceed the maximum possible * scaled window. */ if (!tp->rx_opt.rcv_wscale && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)) new_win = min(new_win, MAX_TCP_WINDOW); else new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale)); /* RFC1323 scaling applied */ new_win >>= tp->rx_opt.rcv_wscale; /* If we advertise zero window, disable fast path. */ if (new_win == 0) { tp->pred_flags = 0; if (old_win) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTOZEROWINDOWADV); } else if (old_win == 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV); } return new_win; } /* Packet ECN state for a SYN-ACK */ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) { const struct tcp_sock *tp = tcp_sk(sk); TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR; if (!(tp->ecn_flags & TCP_ECN_OK)) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; else if (tcp_ca_needs_ecn(sk) || tcp_bpf_ca_needs_ecn(sk)) INET_ECN_xmit(sk); } /* Packet ECN state for a SYN. */ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk); bool use_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn) == 1 || tcp_ca_needs_ecn(sk) || bpf_needs_ecn; if (!use_ecn) { const struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst_feature(dst, RTAX_FEATURE_ECN)) use_ecn = true; } tp->ecn_flags = 0; if (use_ecn) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; tp->ecn_flags = TCP_ECN_OK; if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) INET_ECN_xmit(sk); } } static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) { if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)) /* tp->ecn_flags are cleared at a later point in time when * SYN ACK is ultimatively being received. */ TCP_SKB_CB(skb)->tcp_flags &= ~(TCPHDR_ECE | TCPHDR_CWR); } static void tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) { if (inet_rsk(req)->ecn_ok) th->ece = 1; } /* Set up ECN state for a packet on a ESTABLISHED socket that is about to * be sent. */ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, int tcp_header_len) { struct tcp_sock *tp = tcp_sk(sk); if (tp->ecn_flags & TCP_ECN_OK) { /* Not-retransmitted data segment: set ECT and inject CWR. */ if (skb->len != tcp_header_len && !before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) { INET_ECN_xmit(sk); if (tp->ecn_flags & TCP_ECN_QUEUE_CWR) { tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR; th->cwr = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; } } else if (!tcp_ca_needs_ecn(sk)) { /* ACK or retransmitted segment: clear ECT|CE */ INET_ECN_dontxmit(sk); } if (tp->ecn_flags & TCP_ECN_DEMAND_CWR) th->ece = 1; } } /* Constructs common control bits of non-data skb. If SYN/FIN is present, * auto increment end seqno. */ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) { skb->ip_summed = CHECKSUM_PARTIAL; TCP_SKB_CB(skb)->tcp_flags = flags; tcp_skb_pcount_set(skb, 1); TCP_SKB_CB(skb)->seq = seq; if (flags & (TCPHDR_SYN | TCPHDR_FIN)) seq++; TCP_SKB_CB(skb)->end_seq = seq; } static inline bool tcp_urg_mode(const struct tcp_sock *tp) { return tp->snd_una != tp->snd_up; } #define OPTION_SACK_ADVERTISE BIT(0) #define OPTION_TS BIT(1) #define OPTION_MD5 BIT(2) #define OPTION_WSCALE BIT(3) #define OPTION_FAST_OPEN_COOKIE BIT(8) #define OPTION_SMC BIT(9) #define OPTION_MPTCP BIT(10) static void smc_options_write(__be32 *ptr, u16 *options) { #if IS_ENABLED(CONFIG_SMC) if (static_branch_unlikely(&tcp_have_smc)) { if (unlikely(OPTION_SMC & *options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_EXP << 8) | (TCPOLEN_EXP_SMC_BASE)); *ptr++ = htonl(TCPOPT_SMC_MAGIC); } } #endif } struct tcp_out_options { u16 options; /* bit field of OPTION_* */ u16 mss; /* 0 to disable */ u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ u8 hash_size; /* bytes in hash_location */ u8 bpf_opt_len; /* length of BPF hdr option */ __u8 *hash_location; /* temporary pointer, overloaded */ __u32 tsval, tsecr; /* need to include OPTION_TS */ struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ struct mptcp_out_options mptcp; }; static void mptcp_options_write(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, struct tcp_out_options *opts) { #if IS_ENABLED(CONFIG_MPTCP) if (unlikely(OPTION_MPTCP & opts->options)) mptcp_write_options(th, ptr, tp, &opts->mptcp); #endif } #ifdef CONFIG_CGROUP_BPF static int bpf_skops_write_hdr_opt_arg0(struct sk_buff *skb, enum tcp_synack_type synack_type) { if (unlikely(!skb)) return BPF_WRITE_HDR_TCP_CURRENT_MSS; if (unlikely(synack_type == TCP_SYNACK_COOKIE)) return BPF_WRITE_HDR_TCP_SYNACK_COOKIE; return 0; } /* req, syn_skb and synack_type are used when writing synack */ static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts, unsigned int *remaining) { struct bpf_sock_ops_kern sock_ops; int err; if (likely(!BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)) || !*remaining) return; /* *remaining has already been aligned to 4 bytes, so *remaining >= 4 */ /* init sock_ops */ memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); sock_ops.op = BPF_SOCK_OPS_HDR_OPT_LEN_CB; if (req) { /* The listen "sk" cannot be passed here because * it is not locked. It would not make too much * sense to do bpf_setsockopt(listen_sk) based * on individual connection request also. * * Thus, "req" is passed here and the cgroup-bpf-progs * of the listen "sk" will be run. * * "req" is also used here for fastopen even the "sk" here is * a fullsock "child" sk. It is to keep the behavior * consistent between fastopen and non-fastopen on * the bpf programming side. */ sock_ops.sk = (struct sock *)req; sock_ops.syn_skb = syn_skb; } else { sock_owned_by_me(sk); sock_ops.is_fullsock = 1; sock_ops.sk = sk; } sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type); sock_ops.remaining_opt_len = *remaining; /* tcp_current_mss() does not pass a skb */ if (skb) bpf_skops_init_skb(&sock_ops, skb, 0); err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk); if (err || sock_ops.remaining_opt_len == *remaining) return; opts->bpf_opt_len = *remaining - sock_ops.remaining_opt_len; /* round up to 4 bytes */ opts->bpf_opt_len = (opts->bpf_opt_len + 3) & ~3; *remaining -= opts->bpf_opt_len; } static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts) { u8 first_opt_off, nr_written, max_opt_len = opts->bpf_opt_len; struct bpf_sock_ops_kern sock_ops; int err; if (likely(!max_opt_len)) return; memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); sock_ops.op = BPF_SOCK_OPS_WRITE_HDR_OPT_CB; if (req) { sock_ops.sk = (struct sock *)req; sock_ops.syn_skb = syn_skb; } else { sock_owned_by_me(sk); sock_ops.is_fullsock = 1; sock_ops.sk = sk; } sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type); sock_ops.remaining_opt_len = max_opt_len; first_opt_off = tcp_hdrlen(skb) - max_opt_len; bpf_skops_init_skb(&sock_ops, skb, first_opt_off); err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk); if (err) nr_written = 0; else nr_written = max_opt_len - sock_ops.remaining_opt_len; if (nr_written < max_opt_len) memset(skb->data + first_opt_off + nr_written, TCPOPT_NOP, max_opt_len - nr_written); } #else static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts, unsigned int *remaining) { } static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts) { } #endif /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of * TCP options, we learned this through the hard way, so be careful here. * Luckily we can at least blame others for their non-compliance but from * inter-operability perspective it seems that we're somewhat stuck with * the ordering which we have been using if we want to keep working with * those broken things (not that it currently hurts anybody as there isn't * particular reason why the ordering would need to be changed). * * At least SACK_PERM as the first option is known to lead to a disaster * (but it may well be that other scenarios fail similarly). */ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, struct tcp_out_options *opts) { __be32 *ptr = (__be32 *)(th + 1); u16 options = opts->options; /* mungable copy */ if (unlikely(OPTION_MD5 & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); /* overload cookie hash location */ opts->hash_location = (__u8 *)ptr; ptr += 4; } if (unlikely(opts->mss)) { *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | opts->mss); } if (likely(OPTION_TS & options)) { if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); options &= ~OPTION_SACK_ADVERTISE; } else { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); } *ptr++ = htonl(opts->tsval); *ptr++ = htonl(opts->tsecr); } if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM); } if (unlikely(OPTION_WSCALE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | opts->ws); } if (unlikely(opts->num_sack_blocks)) { struct tcp_sack_block *sp = tp->rx_opt.dsack ? tp->duplicate_sack : tp->selective_acks; int this_sack; *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK << 8) | (TCPOLEN_SACK_BASE + (opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK))); for (this_sack = 0; this_sack < opts->num_sack_blocks; ++this_sack) { *ptr++ = htonl(sp[this_sack].start_seq); *ptr++ = htonl(sp[this_sack].end_seq); } tp->rx_opt.dsack = 0; } if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) { struct tcp_fastopen_cookie *foc = opts->fastopen_cookie; u8 *p = (u8 *)ptr; u32 len; /* Fast Open option length */ if (foc->exp) { len = TCPOLEN_EXP_FASTOPEN_BASE + foc->len; *ptr = htonl((TCPOPT_EXP << 24) | (len << 16) | TCPOPT_FASTOPEN_MAGIC); p += TCPOLEN_EXP_FASTOPEN_BASE; } else { len = TCPOLEN_FASTOPEN_BASE + foc->len; *p++ = TCPOPT_FASTOPEN; *p++ = len; } memcpy(p, foc->val, foc->len); if ((len & 3) == 2) { p[foc->len] = TCPOPT_NOP; p[foc->len + 1] = TCPOPT_NOP; } ptr += (len + 3) >> 2; } smc_options_write(ptr, &options); mptcp_options_write(th, ptr, tp, opts); } static void smc_set_option(const struct tcp_sock *tp, struct tcp_out_options *opts, unsigned int *remaining) { #if IS_ENABLED(CONFIG_SMC) if (static_branch_unlikely(&tcp_have_smc)) { if (tp->syn_smc) { if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { opts->options |= OPTION_SMC; *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; } } } #endif } static void smc_set_option_cond(const struct tcp_sock *tp, const struct inet_request_sock *ireq, struct tcp_out_options *opts, unsigned int *remaining) { #if IS_ENABLED(CONFIG_SMC) if (static_branch_unlikely(&tcp_have_smc)) { if (tp->syn_smc && ireq->smc_ok) { if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { opts->options |= OPTION_SMC; *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; } } } #endif } static void mptcp_set_option_cond(const struct request_sock *req, struct tcp_out_options *opts, unsigned int *remaining) { if (rsk_is_mptcp(req)) { unsigned int size; if (mptcp_synack_options(req, &size, &opts->mptcp)) { if (*remaining >= size) { opts->options |= OPTION_MPTCP; *remaining -= size; } } } } /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); unsigned int remaining = MAX_TCP_OPTION_SPACE; struct tcp_fastopen_request *fastopen = tp->fastopen_req; *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG if (static_branch_unlikely(&tcp_md5_needed) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED; } } #endif /* We always get an MSS option. The option bytes which will be seen in * normal data packets should timestamps be used, must be in the MSS * advertised. But we subtract them from tp->mss_cache so that * calculations in tcp_sendmsg are simpler etc. So account for this * fact here if necessary. If we don't do this correctly, as a * receiver we won't recognize data packets as being full sized when we * should, and thus we won't abide by the delayed ACK rules correctly. * SACKs don't matter, we never delay an ACK when we have any of those * going out. */ opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling))) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_sack))) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) remaining -= TCPOLEN_SACKPERM_ALIGNED; } if (fastopen && fastopen->cookie.len >= 0) { u32 need = fastopen->cookie.len; need += fastopen->cookie.exp ? TCPOLEN_EXP_FASTOPEN_BASE : TCPOLEN_FASTOPEN_BASE; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { opts->options |= OPTION_FAST_OPEN_COOKIE; opts->fastopen_cookie = &fastopen->cookie; remaining -= need; tp->syn_fastopen = 1; tp->syn_fastopen_exp = fastopen->cookie.exp ? 1 : 0; } } smc_set_option(tp, opts, &remaining); if (sk_is_mptcp(sk)) { unsigned int size; if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) { opts->options |= OPTION_MPTCP; remaining -= size; } } bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); return MAX_TCP_OPTION_SPACE - remaining; } /* Set up TCP options for SYN-ACKs. */ static unsigned int tcp_synack_options(const struct sock *sk, struct request_sock *req, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, const struct tcp_md5sig_key *md5, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; #ifdef CONFIG_TCP_MD5SIG if (md5) { opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED; /* We can't fit any SACK blocks in a packet with MD5 + TS * options. There was discussion about disabling SACK * rather than TS in order to fit in better with old, * buggy kernels, but that was deemed to be unnecessary. */ if (synack_type != TCP_SYNACK_COOKIE) ireq->tstamp_ok &= !ireq->sack_ok; } #endif /* We always send an MSS option. */ opts->mss = mss; remaining -= TCPOLEN_MSS_ALIGNED; if (likely(ireq->wscale_ok)) { opts->ws = ireq->rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; opts->tsecr = req->ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!ireq->tstamp_ok)) remaining -= TCPOLEN_SACKPERM_ALIGNED; } if (foc != NULL && foc->len >= 0) { u32 need = foc->len; need += foc->exp ? TCPOLEN_EXP_FASTOPEN_BASE : TCPOLEN_FASTOPEN_BASE; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { opts->options |= OPTION_FAST_OPEN_COOKIE; opts->fastopen_cookie = foc; remaining -= need; } } mptcp_set_option_cond(req, opts, &remaining); smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb, synack_type, opts, &remaining); return MAX_TCP_OPTION_SPACE - remaining; } /* Compute TCP options for ESTABLISHED sockets. This is not the * final wire format yet. */ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); unsigned int size = 0; unsigned int eff_sacks; opts->options = 0; *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG if (static_branch_unlikely(&tcp_md5_needed) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { opts->options |= OPTION_MD5; size += TCPOLEN_MD5SIG_ALIGNED; } } #endif if (likely(tp->rx_opt.tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = skb ? tcp_skb_timestamp(skb) + tp->tsoffset : 0; opts->tsecr = tp->rx_opt.ts_recent; size += TCPOLEN_TSTAMP_ALIGNED; } /* MPTCP options have precedence over SACK for the limited TCP * option space because a MPTCP connection would be forced to * fall back to regular TCP if a required multipath option is * missing. SACK still gets a chance to use whatever space is * left. */ if (sk_is_mptcp(sk)) { unsigned int remaining = MAX_TCP_OPTION_SPACE - size; unsigned int opt_size = 0; if (mptcp_established_options(sk, skb, &opt_size, remaining, &opts->mptcp)) { opts->options |= OPTION_MPTCP; size += opt_size; } } eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack; if (unlikely(eff_sacks)) { const unsigned int remaining = MAX_TCP_OPTION_SPACE - size; if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED + TCPOLEN_SACK_PERBLOCK)) return size; opts->num_sack_blocks = min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); size += TCPOLEN_SACK_BASE_ALIGNED + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG))) { unsigned int remaining = MAX_TCP_OPTION_SPACE - size; bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); size = MAX_TCP_OPTION_SPACE - remaining; } return size; } /* TCP SMALL QUEUES (TSQ) * * TSQ goal is to keep small amount of skbs per tcp flow in tx queues (qdisc+dev) * to reduce RTT and bufferbloat. * We do this using a special skb destructor (tcp_wfree). * * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb * needs to be reallocated in a driver. * The invariant being skb->truesize subtracted from sk->sk_wmem_alloc * * Since transmit from skb destructor is forbidden, we use a tasklet * to process all sockets that eventually need to send more skbs. * We use one tasklet per cpu, with its own queue of sockets. */ struct tsq_tasklet { struct tasklet_struct tasklet; struct list_head head; /* queue of tcp sockets */ }; static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); static void tcp_tsq_write(struct sock *sk) { if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) { struct tcp_sock *tp = tcp_sk(sk); if (tp->lost_out > tp->retrans_out && tcp_snd_cwnd(tp) > tcp_packets_in_flight(tp)) { tcp_mstamp_refresh(tp); tcp_xmit_retransmit_queue(sk); } tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle, 0, GFP_ATOMIC); } } static void tcp_tsq_handler(struct sock *sk) { bh_lock_sock(sk); if (!sock_owned_by_user(sk)) tcp_tsq_write(sk); else if (!test_and_set_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); bh_unlock_sock(sk); } /* * One tasklet per cpu tries to send more skbs. * We run in tasklet context but need to disable irqs when * transferring tsq->head because tcp_wfree() might * interrupt us (non NAPI drivers) */ static void tcp_tasklet_func(struct tasklet_struct *t) { struct tsq_tasklet *tsq = from_tasklet(tsq, t, tasklet); LIST_HEAD(list); unsigned long flags; struct list_head *q, *n; struct tcp_sock *tp; struct sock *sk; local_irq_save(flags); list_splice_init(&tsq->head, &list); local_irq_restore(flags); list_for_each_safe(q, n, &list) { tp = list_entry(q, struct tcp_sock, tsq_node); list_del(&tp->tsq_node); sk = (struct sock *)tp; smp_mb__before_atomic(); clear_bit(TSQ_QUEUED, &sk->sk_tsq_flags); tcp_tsq_handler(sk); sk_free(sk); } } #define TCP_DEFERRED_ALL (TCPF_TSQ_DEFERRED | \ TCPF_WRITE_TIMER_DEFERRED | \ TCPF_DELACK_TIMER_DEFERRED | \ TCPF_MTU_REDUCED_DEFERRED) /** * tcp_release_cb - tcp release_sock() callback * @sk: socket * * called from release_sock() to perform protocol dependent * actions before socket release. */ void tcp_release_cb(struct sock *sk) { unsigned long flags, nflags; /* perform an atomic operation only if at least one flag is set */ do { flags = sk->sk_tsq_flags; if (!(flags & TCP_DEFERRED_ALL)) return; nflags = flags & ~TCP_DEFERRED_ALL; } while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags); if (flags & TCPF_TSQ_DEFERRED) { tcp_tsq_write(sk); __sock_put(sk); } /* Here begins the tricky part : * We are called from release_sock() with : * 1) BH disabled * 2) sk_lock.slock spinlock held * 3) socket owned by us (sk->sk_lock.owned == 1) * * But following code is meant to be called from BH handlers, * so we should keep BH disabled, but early release socket ownership */ sock_release_ownership(sk); if (flags & TCPF_WRITE_TIMER_DEFERRED) { tcp_write_timer_handler(sk); __sock_put(sk); } if (flags & TCPF_DELACK_TIMER_DEFERRED) { tcp_delack_timer_handler(sk); __sock_put(sk); } if (flags & TCPF_MTU_REDUCED_DEFERRED) { inet_csk(sk)->icsk_af_ops->mtu_reduced(sk); __sock_put(sk); } } EXPORT_SYMBOL(tcp_release_cb); void __init tcp_tasklet_init(void) { int i; for_each_possible_cpu(i) { struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i); INIT_LIST_HEAD(&tsq->head); tasklet_setup(&tsq->tasklet, tcp_tasklet_func); } } /* * Write buffer destructor automatically called from kfree_skb. * We can't xmit new skbs from this context, as we might already * hold qdisc lock. */ void tcp_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); unsigned long flags, nval, oval; /* Keep one reference on sk_wmem_alloc. * Will be released by sk_free() from here or tcp_tasklet_func() */ WARN_ON(refcount_sub_and_test(skb->truesize - 1, &sk->sk_wmem_alloc)); /* If this softirq is serviced by ksoftirqd, we are likely under stress. * Wait until our queues (qdisc + devices) are drained. * This gives : * - less callbacks to tcp_write_xmit(), reducing stress (batches) * - chance for incoming ACK (processed by another cpu maybe) * to migrate this flow (skb->ooo_okay will be eventually set) */ if (refcount_read(&sk->sk_wmem_alloc) >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current) goto out; for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) { struct tsq_tasklet *tsq; bool empty; if (!(oval & TSQF_THROTTLED) || (oval & TSQF_QUEUED)) goto out; nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED; nval = cmpxchg(&sk->sk_tsq_flags, oval, nval); if (nval != oval) continue; /* queue this socket to tasklet queue */ local_irq_save(flags); tsq = this_cpu_ptr(&tsq_tasklet); empty = list_empty(&tsq->head); list_add(&tp->tsq_node, &tsq->head); if (empty) tasklet_schedule(&tsq->tasklet); local_irq_restore(flags); return; } out: sk_free(sk); } /* Note: Called under soft irq. * We can call TCP stack right away, unless socket is owned by user. */ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) { struct tcp_sock *tp = container_of(timer, struct tcp_sock, pacing_timer); struct sock *sk = (struct sock *)tp; tcp_tsq_handler(sk); sock_put(sk); return HRTIMER_NORESTART; } static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb, u64 prior_wstamp) { struct tcp_sock *tp = tcp_sk(sk); if (sk->sk_pacing_status != SK_PACING_NONE) { unsigned long rate = sk->sk_pacing_rate; /* Original sch_fq does not pace first 10 MSS * Note that tp->data_segs_out overflows after 2^32 packets, * this is a minor annoyance. */ if (rate != ~0UL && rate && tp->data_segs_out >= 10) { u64 len_ns = div64_ul((u64)skb->len * NSEC_PER_SEC, rate); u64 credit = tp->tcp_wstamp_ns - prior_wstamp; /* take into account OS jitter */ len_ns -= min_t(u64, len_ns / 2, credit); tp->tcp_wstamp_ns += len_ns; } } list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); } INDIRECT_CALLABLE_DECLARE(int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)); INDIRECT_CALLABLE_DECLARE(int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)); INDIRECT_CALLABLE_DECLARE(void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)); /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. * All SKB's seen here are completely headerless. It is our * job to build the TCP header, and pass the packet down to * IP so it can do the same plus pass the packet off to the * device. * * We are working here with either a clone of the original * SKB, or a fresh unique copy made by the retransmit engine. */ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, gfp_t gfp_mask, u32 rcv_nxt) { const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet; struct tcp_sock *tp; struct tcp_skb_cb *tcb; struct tcp_out_options opts; unsigned int tcp_options_size, tcp_header_size; struct sk_buff *oskb = NULL; struct tcp_md5sig_key *md5; struct tcphdr *th; u64 prior_wstamp; int err; BUG_ON(!skb || !tcp_skb_pcount(skb)); tp = tcp_sk(sk); prior_wstamp = tp->tcp_wstamp_ns; tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache); skb_set_delivery_time(skb, tp->tcp_wstamp_ns, true); if (clone_it) { oskb = skb; tcp_skb_tsorted_save(oskb) { if (unlikely(skb_cloned(oskb))) skb = pskb_copy(oskb, gfp_mask); else skb = skb_clone(oskb, gfp_mask); } tcp_skb_tsorted_restore(oskb); if (unlikely(!skb)) return -ENOBUFS; /* retransmit skbs might have a non zero value in skb->dev * because skb->dev is aliased with skb->rbnode.rb_left */ skb->dev = NULL; } inet = inet_sk(sk); tcb = TCP_SKB_CB(skb); memset(&opts, 0, sizeof(opts)); if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) { tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5); } else { tcp_options_size = tcp_established_options(sk, skb, &opts, &md5); /* Force a PSH flag on all (GSO) packets to expedite GRO flush * at receiver : This slightly improve GRO performance. * Note that we do not force the PSH flag for non GSO packets, * because they might be sent under high congestion events, * and in this case it is better to delay the delivery of 1-MSS * packets and thus the corresponding ACK packet that would * release the following packet. */ if (tcp_skb_pcount(skb) > 1) tcb->tcp_flags |= TCPHDR_PSH; } tcp_header_size = tcp_options_size + sizeof(struct tcphdr); /* if no packet is in qdisc/device queue, then allow XPS to select * another queue. We can be called from tcp_tsq_handler() * which holds one reference to sk. * * TODO: Ideally, in-flight pure ACK packets should not matter here. * One way to get this would be to set skb->truesize = 2 on them. */ skb->ooo_okay = sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1); /* If we had to use memory reserve to allocate this skb, * this might cause drops if packet is looped back : * Other socket might not have SOCK_MEMALLOC. * Packets not looped back do not care about pfmemalloc. */ skb->pfmemalloc = 0; skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); skb_orphan(skb); skb->sk = sk; skb->destructor = skb_is_tcp_pure_ack(skb) ? __sock_wfree : tcp_wfree; refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm); /* Build TCP header and checksum it. */ th = (struct tcphdr *)skb->data; th->source = inet->inet_sport; th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); th->ack_seq = htonl(rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | tcb->tcp_flags); th->check = 0; th->urg_ptr = 0; /* The urg_mode check is necessary during a below snd_una win probe */ if (unlikely(tcp_urg_mode(tp) && before(tcb->seq, tp->snd_up))) { if (before(tp->snd_up, tcb->seq + 0x10000)) { th->urg_ptr = htons(tp->snd_up - tcb->seq); th->urg = 1; } else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) { th->urg_ptr = htons(0xFFFF); th->urg = 1; } } skb_shinfo(skb)->gso_type = sk->sk_gso_type; if (likely(!(tcb->tcp_flags & TCPHDR_SYN))) { th->window = htons(tcp_select_window(sk)); tcp_ecn_send(sk, skb, th, tcp_header_size); } else { /* RFC1323: The window in SYN & SYN/ACK segments * is never scaled. */ th->window = htons(min(tp->rcv_wnd, 65535U)); } tcp_options_write(th, tp, &opts); #ifdef CONFIG_TCP_MD5SIG /* Calculate the MD5 hash, as we have all we need now */ if (md5) { sk_gso_disable(sk); tp->af_specific->calc_md5_hash(opts.hash_location, md5, sk, skb); } #endif /* BPF prog is the last one writing header option */ bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts); INDIRECT_CALL_INET(icsk->icsk_af_ops->send_check, tcp_v6_send_check, tcp_v4_send_check, sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); tp->data_segs_out += tcp_skb_pcount(skb); tp->bytes_sent += skb->len - tcp_header_size; } if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb)); tp->segs_out += tcp_skb_pcount(skb); skb_set_hash_from_sk(skb, sk); /* OK, its time to fill skb_shinfo(skb)->gso_{segs|size} */ skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb); skb_shinfo(skb)->gso_size = tcp_skb_mss(skb); /* Leave earliest departure time in skb->tstamp (skb->skb_mstamp_ns) */ /* Cleanup our debris for IP stacks */ memset(skb->cb, 0, max(sizeof(struct inet_skb_parm), sizeof(struct inet6_skb_parm))); tcp_add_tx_delay(skb, tp); err = INDIRECT_CALL_INET(icsk->icsk_af_ops->queue_xmit, inet6_csk_xmit, ip_queue_xmit, sk, skb, &inet->cork.fl); if (unlikely(err > 0)) { tcp_enter_cwr(sk); err = net_xmit_eval(err); } if (!err && oskb) { tcp_update_skb_after_send(sk, oskb, prior_wstamp); tcp_rate_skb_sent(sk, oskb); } return err; } static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, gfp_t gfp_mask) { return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask, tcp_sk(sk)->rcv_nxt); } /* This routine just queues the buffer for sending. * * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, * otherwise socket can stall. */ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); /* Advance write_seq and place onto the write_queue. */ WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq); __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); } /* Initialize TSO segments for a packet. */ static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) { if (skb->len <= mss_now) { /* Avoid the costly divide in the normal * non-TSO case. */ tcp_skb_pcount_set(skb, 1); TCP_SKB_CB(skb)->tcp_gso_size = 0; } else { tcp_skb_pcount_set(skb, DIV_ROUND_UP(skb->len, mss_now)); TCP_SKB_CB(skb)->tcp_gso_size = mss_now; } } /* Pcount in the middle of the write queue got changed, we need to do various * tweaks to fix counters */ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int decr) { struct tcp_sock *tp = tcp_sk(sk); tp->packets_out -= decr; if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) tp->sacked_out -= decr; if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) tp->retrans_out -= decr; if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) tp->lost_out -= decr; /* Reno case is special. Sigh... */ if (tcp_is_reno(tp) && decr > 0) tp->sacked_out -= min_t(u32, tp->sacked_out, decr); if (tp->lost_skb_hint && before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) tp->lost_cnt_hint -= decr; tcp_verify_left_out(tp); } static bool tcp_has_tx_tstamp(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->txstamp_ack || (skb_shinfo(skb)->tx_flags & SKBTX_ANY_TSTAMP); } static void tcp_fragment_tstamp(struct sk_buff *skb, struct sk_buff *skb2) { struct skb_shared_info *shinfo = skb_shinfo(skb); if (unlikely(tcp_has_tx_tstamp(skb)) && !before(shinfo->tskey, TCP_SKB_CB(skb2)->seq)) { struct skb_shared_info *shinfo2 = skb_shinfo(skb2); u8 tsflags = shinfo->tx_flags & SKBTX_ANY_TSTAMP; shinfo->tx_flags &= ~tsflags; shinfo2->tx_flags |= tsflags; swap(shinfo->tskey, shinfo2->tskey); TCP_SKB_CB(skb2)->txstamp_ack = TCP_SKB_CB(skb)->txstamp_ack; TCP_SKB_CB(skb)->txstamp_ack = 0; } } static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2) { TCP_SKB_CB(skb2)->eor = TCP_SKB_CB(skb)->eor; TCP_SKB_CB(skb)->eor = 0; } /* Insert buff after skb on the write or rtx queue of sk. */ static void tcp_insert_write_queue_after(struct sk_buff *skb, struct sk_buff *buff, struct sock *sk, enum tcp_queue tcp_queue) { if (tcp_queue == TCP_FRAG_IN_WRITE_QUEUE) __skb_queue_after(&sk->sk_write_queue, skb, buff); else tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); } /* Function to create two new TCP segments. Shrinks the given segment * to the specified size and appends a new segment with the rest of the * packet to the list. This won't be called frequently, I hope. * Remember, these are still headerless SKBs at this point. */ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int nsize, old_factor; long limit; int nlen; u8 flags; if (WARN_ON(len > skb->len)) return -EINVAL; nsize = skb_headlen(skb) - len; if (nsize < 0) nsize = 0; /* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb. * We need some allowance to not penalize applications setting small * SO_SNDBUF values. * Also allow first and last skb in retransmit queue to be split. */ limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_LEGACY_MAX_SIZE); if (unlikely((sk->sk_wmem_queued >> 1) > limit && tcp_queue != TCP_FRAG_IN_WRITE_QUEUE && skb != tcp_rtx_queue_head(sk) && skb != tcp_rtx_queue_tail(sk))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG); return -ENOMEM; } if (skb_unclone_keeptruesize(skb, gfp)) return -ENOMEM; /* Get a new skb... force flag on. */ buff = tcp_stream_alloc_skb(sk, nsize, gfp, true); if (!buff) return -ENOMEM; /* We'll just try again later. */ skb_copy_decrypted(buff, skb); mptcp_skb_ext_copy(buff, skb); sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); nlen = skb->len - len - nsize; buff->truesize += nlen; skb->truesize -= nlen; /* Correct the sequence numbers. */ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len; TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq; TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq; /* PSH and FIN should only be set in the second packet. */ flags = TCP_SKB_CB(skb)->tcp_flags; TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); TCP_SKB_CB(buff)->tcp_flags = flags; TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked; tcp_skb_fragment_eor(skb, buff); skb_split(skb, buff, len); skb_set_delivery_time(buff, skb->tstamp, true); tcp_fragment_tstamp(skb, buff); old_factor = tcp_skb_pcount(skb); /* Fix up tso_factor for both original and new SKB. */ tcp_set_skb_tso_segs(skb, mss_now); tcp_set_skb_tso_segs(buff, mss_now); /* Update delivered info for the new segment */ TCP_SKB_CB(buff)->tx = TCP_SKB_CB(skb)->tx; /* If this packet has been sent out already, we must * adjust the various packet counters. */ if (!before(tp->snd_nxt, TCP_SKB_CB(buff)->end_seq)) { int diff = old_factor - tcp_skb_pcount(skb) - tcp_skb_pcount(buff); if (diff) tcp_adjust_pcount(sk, skb, diff); } /* Link BUFF into the send queue. */ __skb_header_release(buff); tcp_insert_write_queue_after(skb, buff, sk, tcp_queue); if (tcp_queue == TCP_FRAG_IN_RTX_QUEUE) list_add(&buff->tcp_tsorted_anchor, &skb->tcp_tsorted_anchor); return 0; } /* This is similar to __pskb_pull_tail(). The difference is that pulled * data is not copied, but immediately discarded. */ static int __pskb_trim_head(struct sk_buff *skb, int len) { struct skb_shared_info *shinfo; int i, k, eat; eat = min_t(int, len, skb_headlen(skb)); if (eat) { __skb_pull(skb, eat); len -= eat; if (!len) return 0; } eat = len; k = 0; shinfo = skb_shinfo(skb); for (i = 0; i < shinfo->nr_frags; i++) { int size = skb_frag_size(&shinfo->frags[i]); if (size <= eat) { skb_frag_unref(skb, i); eat -= size; } else { shinfo->frags[k] = shinfo->frags[i]; if (eat) { skb_frag_off_add(&shinfo->frags[k], eat); skb_frag_size_sub(&shinfo->frags[k], eat); eat = 0; } k++; } } shinfo->nr_frags = k; skb->data_len -= len; skb->len = skb->data_len; return len; } /* Remove acked data from a packet in the transmit queue. */ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { u32 delta_truesize; if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) return -ENOMEM; delta_truesize = __pskb_trim_head(skb, len); TCP_SKB_CB(skb)->seq += len; if (delta_truesize) { skb->truesize -= delta_truesize; sk_wmem_queued_add(sk, -delta_truesize); if (!skb_zcopy_pure(skb)) sk_mem_uncharge(sk, delta_truesize); } /* Any change of skb->len requires recalculation of tso factor. */ if (tcp_skb_pcount(skb) > 1) tcp_set_skb_tso_segs(skb, tcp_skb_mss(skb)); return 0; } /* Calculate MSS not accounting any TCP options. */ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); int mss_now; /* Calculate base mss without TCP options: It is MMS_S - sizeof(tcphdr) of rfc1122 */ mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ if (icsk->icsk_af_ops->net_frag_header_len) { const struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst_allfrag(dst)) mss_now -= icsk->icsk_af_ops->net_frag_header_len; } /* Clamp it (mss_clamp does not include tcp options) */ if (mss_now > tp->rx_opt.mss_clamp) mss_now = tp->rx_opt.mss_clamp; /* Now subtract optional transport overhead */ mss_now -= icsk->icsk_ext_hdr_len; /* Then reserve room for full set of TCP options and 8 bytes of data */ mss_now = max(mss_now, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss)); return mss_now; } /* Calculate MSS. Not accounting for SACKs here. */ int tcp_mtu_to_mss(struct sock *sk, int pmtu) { /* Subtract TCP options size, not including SACKs */ return __tcp_mtu_to_mss(sk, pmtu) - (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); } EXPORT_SYMBOL(tcp_mtu_to_mss); /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); int mtu; mtu = mss + tp->tcp_header_len + icsk->icsk_ext_hdr_len + icsk->icsk_af_ops->net_header_len; /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ if (icsk->icsk_af_ops->net_frag_header_len) { const struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst_allfrag(dst)) mtu += icsk->icsk_af_ops->net_frag_header_len; } return mtu; } EXPORT_SYMBOL(tcp_mss_to_mtu); /* MTU probing init per socket */ void tcp_mtup_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); icsk->icsk_mtup.enabled = READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing) > 1; icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + icsk->icsk_af_ops->net_header_len; icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, READ_ONCE(net->ipv4.sysctl_tcp_base_mss)); icsk->icsk_mtup.probe_size = 0; if (icsk->icsk_mtup.enabled) icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } EXPORT_SYMBOL(tcp_mtup_init); /* This function synchronize snd mss to current pmtu/exthdr set. tp->rx_opt.user_mss is mss set by user by TCP_MAXSEG. It does NOT counts for TCP options, but includes only bare TCP header. tp->rx_opt.mss_clamp is mss negotiated at connection setup. It is minimum of user_mss and mss received with SYN. It also does not include TCP options. inet_csk(sk)->icsk_pmtu_cookie is last pmtu, seen by this function. tp->mss_cache is current effective sending mss, including all tcp options except for SACKs. It is evaluated, taking into account current pmtu, but never exceeds tp->rx_opt.mss_clamp. NOTE1. rfc1122 clearly states that advertised MSS DOES NOT include either tcp or ip options. NOTE2. inet_csk(sk)->icsk_pmtu_cookie and tp->mss_cache are READ ONLY outside this function. --ANK (980731) */ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); int mss_now; if (icsk->icsk_mtup.search_high > pmtu) icsk->icsk_mtup.search_high = pmtu; mss_now = tcp_mtu_to_mss(sk, pmtu); mss_now = tcp_bound_to_half_wnd(tp, mss_now); /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; if (icsk->icsk_mtup.enabled) mss_now = min(mss_now, tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low)); tp->mss_cache = mss_now; return mss_now; } EXPORT_SYMBOL(tcp_sync_mss); /* Compute the current effective MSS, taking SACKs and IP options, * and even PMTU discovery events into account. */ unsigned int tcp_current_mss(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); const struct dst_entry *dst = __sk_dst_get(sk); u32 mss_now; unsigned int header_len; struct tcp_out_options opts; struct tcp_md5sig_key *md5; mss_now = tp->mss_cache; if (dst) { u32 mtu = dst_mtu(dst); if (mtu != inet_csk(sk)->icsk_pmtu_cookie) mss_now = tcp_sync_mss(sk, mtu); } header_len = tcp_established_options(sk, NULL, &opts, &md5) + sizeof(struct tcphdr); /* The mss_cache is sized based on tp->tcp_header_len, which assumes * some common options. If this is an odd packet (because we have SACK * blocks etc) then our calculated header_len will be different, and * we have to adjust mss_now correspondingly */ if (header_len != tp->tcp_header_len) { int delta = (int) header_len - tp->tcp_header_len; mss_now -= delta; } return mss_now; } /* RFC2861, slow part. Adjust cwnd, after it was not full during one rto. * As additional protections, we do not touch cwnd in retransmission phases, * and if application hit its sndbuf limit recently. */ static void tcp_cwnd_application_limited(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open && sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { /* Limited by application or receiver window. */ u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk)); u32 win_used = max(tp->snd_cwnd_used, init_win); if (win_used < tcp_snd_cwnd(tp)) { tp->snd_ssthresh = tcp_current_ssthresh(sk); tcp_snd_cwnd_set(tp, (tcp_snd_cwnd(tp) + win_used) >> 1); } tp->snd_cwnd_used = 0; } tp->snd_cwnd_stamp = tcp_jiffies32; } static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); /* Track the strongest available signal of the degree to which the cwnd * is fully utilized. If cwnd-limited then remember that fact for the * current window. If not cwnd-limited then track the maximum number of * outstanding packets in the current window. (If cwnd-limited then we * chose to not update tp->max_packets_out to avoid an extra else * clause with no functional impact.) */ if (!before(tp->snd_una, tp->cwnd_usage_seq) || is_cwnd_limited || (!tp->is_cwnd_limited && tp->packets_out > tp->max_packets_out)) { tp->is_cwnd_limited = is_cwnd_limited; tp->max_packets_out = tp->packets_out; tp->cwnd_usage_seq = tp->snd_nxt; } if (tcp_is_cwnd_limited(sk)) { /* Network is feed fully. */ tp->snd_cwnd_used = 0; tp->snd_cwnd_stamp = tcp_jiffies32; } else { /* Network starves. */ if (tp->packets_out > tp->snd_cwnd_used) tp->snd_cwnd_used = tp->packets_out; if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) && (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && !ca_ops->cong_control) tcp_cwnd_application_limited(sk); /* The following conditions together indicate the starvation * is caused by insufficient sender buffer: * 1) just sent some data (see tcp_write_xmit) * 2) not cwnd limited (this else condition) * 3) no more data to send (tcp_write_queue_empty()) * 4) application is hitting buffer limit (SOCK_NOSPACE) */ if (tcp_write_queue_empty(sk) && sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags) && (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) tcp_chrono_start(sk, TCP_CHRONO_SNDBUF_LIMITED); } } /* Minshall's variant of the Nagle send check. */ static bool tcp_minshall_check(const struct tcp_sock *tp) { return after(tp->snd_sml, tp->snd_una) && !after(tp->snd_sml, tp->snd_nxt); } /* Update snd_sml if this skb is under mss * Note that a TSO packet might end with a sub-mss segment * The test is really : * if ((skb->len % mss) != 0) * tp->snd_sml = TCP_SKB_CB(skb)->end_seq; * But we can avoid doing the divide again given we already have * skb_pcount = skb->len / mss_now */ static void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss_now, const struct sk_buff *skb) { if (skb->len < tcp_skb_pcount(skb) * mss_now) tp->snd_sml = TCP_SKB_CB(skb)->end_seq; } /* Return false, if packet can be sent now without violation Nagle's rules: * 1. It is full sized. (provided by caller in %partial bool) * 2. Or it contains FIN. (already checked by caller) * 3. Or TCP_CORK is not set, and TCP_NODELAY is set. * 4. Or TCP_CORK is not set, and all sent packets are ACKed. * With Minshall's modification: all sent small packets are ACKed. */ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, int nonagle) { return partial && ((nonagle & TCP_NAGLE_CORK) || (!nonagle && tp->packets_out && tcp_minshall_check(tp))); } /* Return how many segs we'd like on a TSO packet, * depending on current pacing rate, and how close the peer is. * * Rationale is: * - For close peers, we rather send bigger packets to reduce * cpu costs, because occasional losses will be repaired fast. * - For long distance/rtt flows, we would like to get ACK clocking * with 1 ACK per ms. * * Use min_rtt to help adapt TSO burst size, with smaller min_rtt resulting * in bigger TSO bursts. We we cut the RTT-based allowance in half * for every 2^9 usec (aka 512 us) of RTT, so that the RTT-based allowance * is below 1500 bytes after 6 * ~500 usec = 3ms. */ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, int min_tso_segs) { unsigned long bytes; u32 r; bytes = sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift); r = tcp_min_rtt(tcp_sk(sk)) >> READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log); if (r < BITS_PER_TYPE(sk->sk_gso_max_size)) bytes += sk->sk_gso_max_size >> r; bytes = min_t(unsigned long, bytes, sk->sk_gso_max_size); return max_t(u32, bytes / mss_now, min_tso_segs); } /* Return the number of segments we want in the skb we are transmitting. * See if congestion control module wants to decide; otherwise, autosize. */ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; u32 min_tso, tso_segs; min_tso = ca_ops->min_tso_segs ? ca_ops->min_tso_segs(sk) : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs); tso_segs = tcp_tso_autosize(sk, mss_now, min_tso); return min_t(u32, tso_segs, sk->sk_gso_max_segs); } /* Returns the portion of skb which can be sent right away */ static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb, unsigned int mss_now, unsigned int max_segs, int nonagle) { const struct tcp_sock *tp = tcp_sk(sk); u32 partial, needed, window, max_len; window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; max_len = mss_now * max_segs; if (likely(max_len <= window && skb != tcp_write_queue_tail(sk))) return max_len; needed = min(skb->len, window); if (max_len <= needed) return max_len; partial = needed % mss_now; /* If last segment is not a full MSS, check if Nagle rules allow us * to include this last segment in this skb. * Otherwise, we'll split the skb at last MSS boundary */ if (tcp_nagle_check(partial != 0, tp, nonagle)) return needed - partial; return needed; } /* Can at least one segment of SKB be sent right now, according to the * congestion window rules? If so, return how many segments are allowed. */ static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp, const struct sk_buff *skb) { u32 in_flight, cwnd, halfcwnd; /* Don't be strict about the congestion window for the final FIN. */ if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) && tcp_skb_pcount(skb) == 1) return 1; in_flight = tcp_packets_in_flight(tp); cwnd = tcp_snd_cwnd(tp); if (in_flight >= cwnd) return 0; /* For better scheduling, ensure we have at least * 2 GSO packets in flight. */ halfcwnd = max(cwnd >> 1, 1U); return min(halfcwnd, cwnd - in_flight); } /* Initialize TSO state of a skb. * This must be invoked the first time we consider transmitting * SKB onto the wire. */ static int tcp_init_tso_segs(struct sk_buff *skb, unsigned int mss_now) { int tso_segs = tcp_skb_pcount(skb); if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) { tcp_set_skb_tso_segs(skb, mss_now); tso_segs = tcp_skb_pcount(skb); } return tso_segs; } /* Return true if the Nagle test allows this packet to be * sent now. */ static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned int cur_mss, int nonagle) { /* Nagle rule does not apply to frames, which sit in the middle of the * write_queue (they have no chances to get new data). * * This is implemented in the callers, where they modify the 'nonagle' * argument based upon the location of SKB in the send queue. */ if (nonagle & TCP_NAGLE_PUSH) return true; /* Don't use the nagle rule for urgent data (or for the final FIN). */ if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) return true; if (!tcp_nagle_check(skb->len < cur_mss, tp, nonagle)) return true; return false; } /* Does at least the first segment of SKB fit into the send window? */ static bool tcp_snd_wnd_test(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned int cur_mss) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (skb->len > cur_mss) end_seq = TCP_SKB_CB(skb)->seq + cur_mss; return !after(end_seq, tcp_wnd_end(tp)); } /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet * which is put after SKB on the list. It is very much like * tcp_fragment() except that it may make several kinds of assumptions * in order to speed up the splitting operation. In particular, we * know that all the data is in scatter-gather pages, and that the * packet has never been sent out before (and thus is not cloned). */ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, unsigned int mss_now, gfp_t gfp) { int nlen = skb->len - len; struct sk_buff *buff; u8 flags; /* All of a TSO frame must be composed of paged data. */ if (skb->len != skb->data_len) return tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, skb, len, mss_now, gfp); buff = tcp_stream_alloc_skb(sk, 0, gfp, true); if (unlikely(!buff)) return -ENOMEM; skb_copy_decrypted(buff, skb); mptcp_skb_ext_copy(buff, skb); sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); buff->truesize += nlen; skb->truesize -= nlen; /* Correct the sequence numbers. */ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len; TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq; TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq; /* PSH and FIN should only be set in the second packet. */ flags = TCP_SKB_CB(skb)->tcp_flags; TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); TCP_SKB_CB(buff)->tcp_flags = flags; tcp_skb_fragment_eor(skb, buff); skb_split(skb, buff, len); tcp_fragment_tstamp(skb, buff); /* Fix up tso_factor for both original and new SKB. */ tcp_set_skb_tso_segs(skb, mss_now); tcp_set_skb_tso_segs(buff, mss_now); /* Link BUFF into the send queue. */ __skb_header_release(buff); tcp_insert_write_queue_after(skb, buff, sk, TCP_FRAG_IN_WRITE_QUEUE); return 0; } /* Try to defer sending, if possible, in order to minimize the amount * of TSO splitting we do. View it as a kind of TSO Nagle test. * * This algorithm is from John Heffner. */ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, bool *is_cwnd_limited, bool *is_rwnd_limited, u32 max_segs) { const struct inet_connection_sock *icsk = inet_csk(sk); u32 send_win, cong_win, limit, in_flight; struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *head; int win_divisor; s64 delta; if (icsk->icsk_ca_state >= TCP_CA_Recovery) goto send_now; /* Avoid bursty behavior by allowing defer * only if the last write was recent (1 ms). * Note that tp->tcp_wstamp_ns can be in the future if we have * packets waiting in a qdisc or device for EDT delivery. */ delta = tp->tcp_clock_cache - tp->tcp_wstamp_ns - NSEC_PER_MSEC; if (delta > 0) goto send_now; in_flight = tcp_packets_in_flight(tp); BUG_ON(tcp_skb_pcount(skb) <= 1); BUG_ON(tcp_snd_cwnd(tp) <= in_flight); send_win = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; /* From in_flight test above, we know that cwnd > in_flight. */ cong_win = (tcp_snd_cwnd(tp) - in_flight) * tp->mss_cache; limit = min(send_win, cong_win); /* If a full-sized TSO skb can be sent, do it. */ if (limit >= max_segs * tp->mss_cache) goto send_now; /* Middle in queue won't get any more data, full sendable already? */ if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len)) goto send_now; win_divisor = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_win_divisor); if (win_divisor) { u32 chunk = min(tp->snd_wnd, tcp_snd_cwnd(tp) * tp->mss_cache); /* If at least some fraction of a window is available, * just use it. */ chunk /= win_divisor; if (limit >= chunk) goto send_now; } else { /* Different approach, try not to defer past a single * ACK. Receiver should ACK every other full sized * frame, so if we have space for more than 3 frames * then send now. */ if (limit > tcp_max_tso_deferred_mss(tp) * tp->mss_cache) goto send_now; } /* TODO : use tsorted_sent_queue ? */ head = tcp_rtx_queue_head(sk); if (!head) goto send_now; delta = tp->tcp_clock_cache - head->tstamp; /* If next ACK is likely to come too late (half srtt), do not defer */ if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0) goto send_now; /* Ok, it looks like it is advisable to defer. * Three cases are tracked : * 1) We are cwnd-limited * 2) We are rwnd-limited * 3) We are application limited. */ if (cong_win < send_win) { if (cong_win <= skb->len) { *is_cwnd_limited = true; return true; } } else { if (send_win <= skb->len) { *is_rwnd_limited = true; return true; } } /* If this packet won't get more data, do not wait. */ if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) || TCP_SKB_CB(skb)->eor) goto send_now; return true; send_now: return false; } static inline void tcp_mtu_check_reprobe(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); u32 interval; s32 delta; interval = READ_ONCE(net->ipv4.sysctl_tcp_probe_interval); delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp; if (unlikely(delta >= interval * HZ)) { int mss = tcp_current_mss(sk); /* Update current search range */ icsk->icsk_mtup.probe_size = 0; icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + icsk->icsk_af_ops->net_header_len; icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); /* Update probe time stamp */ icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } } static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) { struct sk_buff *skb, *next; skb = tcp_send_head(sk); tcp_for_write_queue_from_safe(skb, next, sk) { if (len <= skb->len) break; if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb) || !skb_pure_zcopy_same(skb, next)) return false; len -= skb->len; } return true; } /* Create a new MTU probe if we are ready. * MTU probe is regularly attempting to increase the path MTU by * deliberately sending larger packets. This discovers routing * changes resulting in larger path MTUs. * * Returns 0 if we should wait to probe (no cwnd available), * 1 if a probe was sent, * -1 otherwise */ static int tcp_mtu_probe(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb, *nskb, *next; struct net *net = sock_net(sk); int probe_size; int size_needed; int copy, len; int mss_now; int interval; /* Not currently probing/verifying, * not in recovery, * have enough cwnd, and * not SACKing (the variable headers throw things off) */ if (likely(!icsk->icsk_mtup.enabled || icsk->icsk_mtup.probe_size || inet_csk(sk)->icsk_ca_state != TCP_CA_Open || tcp_snd_cwnd(tp) < 11 || tp->rx_opt.num_sacks || tp->rx_opt.dsack)) return -1; /* Use binary search for probe_size between tcp_mss_base, * and current mss_clamp. if (search_high - search_low) * smaller than a threshold, backoff from probing. */ mss_now = tcp_current_mss(sk); probe_size = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high + icsk->icsk_mtup.search_low) >> 1); size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache; interval = icsk->icsk_mtup.search_high - icsk->icsk_mtup.search_low; /* When misfortune happens, we are reprobing actively, * and then reprobe timer has expired. We stick with current * probing process by not resetting search range to its orignal. */ if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) || interval < READ_ONCE(net->ipv4.sysctl_tcp_probe_threshold)) { /* Check whether enough time has elaplased for * another round of probing. */ tcp_mtu_check_reprobe(sk); return -1; } /* Have enough data in the send queue to probe? */ if (tp->write_seq - tp->snd_nxt < size_needed) return -1; if (tp->snd_wnd < size_needed) return -1; if (after(tp->snd_nxt + size_needed, tcp_wnd_end(tp))) return 0; /* Do we need to wait to drain cwnd? With none in flight, don't stall */ if (tcp_packets_in_flight(tp) + 2 > tcp_snd_cwnd(tp)) { if (!tcp_packets_in_flight(tp)) return -1; else return 0; } if (!tcp_can_coalesce_send_queue_head(sk, probe_size)) return -1; /* We're allowed to probe. Build it now. */ nskb = tcp_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); if (!nskb) return -1; sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = tcp_send_head(sk); skb_copy_decrypted(nskb, skb); mptcp_skb_ext_copy(nskb, skb); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq; TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size; TCP_SKB_CB(nskb)->tcp_flags = TCPHDR_ACK; tcp_insert_write_queue_before(nskb, skb, sk); tcp_highest_sack_replace(sk, skb, nskb); len = 0; tcp_for_write_queue_from_safe(skb, next, sk) { copy = min_t(int, skb->len, probe_size - len); skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); if (skb->len <= copy) { /* We've eaten all the data from this skb. * Throw it away. */ TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; /* If this is the last SKB we copy and eor is set * we need to propagate it to the new skb. */ TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; tcp_skb_collapse_tstamp(nskb, skb); tcp_unlink_write_queue(skb, sk); tcp_wmem_free_skb(sk, skb); } else { TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags & ~(TCPHDR_FIN|TCPHDR_PSH); if (!skb_shinfo(skb)->nr_frags) { skb_pull(skb, copy); } else { __pskb_trim_head(skb, copy); tcp_set_skb_tso_segs(skb, mss_now); } TCP_SKB_CB(skb)->seq += copy; } len += copy; if (len >= probe_size) break; } tcp_init_tso_segs(nskb, nskb->len); /* We're ready to send. If this fails, the probe will * be resegmented into mss-sized pieces by tcp_write_xmit(). */ if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) { /* Decrement cwnd here because we are sending * effectively two packets. */ tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) - 1); tcp_event_new_data_sent(sk, nskb); icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len); tp->mtu_probe.probe_seq_start = TCP_SKB_CB(nskb)->seq; tp->mtu_probe.probe_seq_end = TCP_SKB_CB(nskb)->end_seq; return 1; } return -1; } static bool tcp_pacing_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (!tcp_needs_internal_pacing(sk)) return false; if (tp->tcp_wstamp_ns <= tp->tcp_clock_cache) return false; if (!hrtimer_is_queued(&tp->pacing_timer)) { hrtimer_start(&tp->pacing_timer, ns_to_ktime(tp->tcp_wstamp_ns), HRTIMER_MODE_ABS_PINNED_SOFT); sock_hold(sk); } return true; } /* TCP Small Queues : * Control number of packets in qdisc/devices to two packets / or ~1 ms. * (These limits are doubled for retransmits) * This allows for : * - better RTT estimation and ACK scheduling * - faster recovery * - high rates * Alas, some drivers / subsystems require a fair amount * of queued bytes to ensure line rate. * One example is wifi aggregation (802.11 AMPDU) */ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, unsigned int factor) { unsigned long limit; limit = max_t(unsigned long, 2 * skb->truesize, sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift)); if (sk->sk_pacing_status == SK_PACING_NONE) limit = min_t(unsigned long, limit, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes)); limit <<= factor; if (static_branch_unlikely(&tcp_tx_delay_enabled) && tcp_sk(sk)->tcp_tx_delay) { u64 extra_bytes = (u64)sk->sk_pacing_rate * tcp_sk(sk)->tcp_tx_delay; /* TSQ is based on skb truesize sum (sk_wmem_alloc), so we * approximate our needs assuming an ~100% skb->truesize overhead. * USEC_PER_SEC is approximated by 2^20. * do_div(extra_bytes, USEC_PER_SEC/2) is replaced by a right shift. */ extra_bytes >>= (20 - 1); limit += extra_bytes; } if (refcount_read(&sk->sk_wmem_alloc) > limit) { /* Always send skb if rtx queue is empty. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. * This helps when TX completions are delayed too much. */ if (tcp_rtx_queue_empty(sk)) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); /* It is possible TX completion already happened * before we set TSQ_THROTTLED, so we must * test again the condition. */ smp_mb__after_atomic(); if (refcount_read(&sk->sk_wmem_alloc) > limit) return true; } return false; } static void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new) { const u32 now = tcp_jiffies32; enum tcp_chrono old = tp->chrono_type; if (old > TCP_CHRONO_UNSPEC) tp->chrono_stat[old - 1] += now - tp->chrono_start; tp->chrono_start = now; tp->chrono_type = new; } void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type) { struct tcp_sock *tp = tcp_sk(sk); /* If there are multiple conditions worthy of tracking in a * chronograph then the highest priority enum takes precedence * over the other conditions. So that if something "more interesting" * starts happening, stop the previous chrono and start a new one. */ if (type > tp->chrono_type) tcp_chrono_set(tp, type); } void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type) { struct tcp_sock *tp = tcp_sk(sk); /* There are multiple conditions worthy of tracking in a * chronograph, so that the highest priority enum takes * precedence over the other conditions (see tcp_chrono_start). * If a condition stops, we only stop chrono tracking if * it's the "most interesting" or current chrono we are * tracking and starts busy chrono if we have pending data. */ if (tcp_rtx_and_write_queues_empty(sk)) tcp_chrono_set(tp, TCP_CHRONO_UNSPEC); else if (type == tp->chrono_type) tcp_chrono_set(tp, TCP_CHRONO_BUSY); } /* This routine writes packets to the network. It advances the * send_head. This happens as incoming acks open up the remote * window for us. * * LARGESEND note: !tcp_urg_mode is overkill, only frames between * snd_up-64k-mss .. snd_up cannot be large. However, taking into * account rare use of URG, this is not a big flaw. * * Send at most one packet when push_one > 0. Temporarily ignore * cwnd limit to force at most one packet out when push_one == 2. * Returns true, if no segments are in flight and we have queued segments, * but cannot send anything now because of SWS or another problem. */ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; unsigned int tso_segs, sent_pkts; int cwnd_quota; int result; bool is_cwnd_limited = false, is_rwnd_limited = false; u32 max_segs; sent_pkts = 0; tcp_mstamp_refresh(tp); if (!push_one) { /* Do MTU probing. */ result = tcp_mtu_probe(sk); if (!result) { return false; } else if (result > 0) { sent_pkts = 1; } } max_segs = tcp_tso_segs(sk, mss_now); while ((skb = tcp_send_head(sk))) { unsigned int limit; if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp_ns" is used as a start point for the retransmit timer */ tp->tcp_wstamp_ns = tp->tcp_clock_cache; skb_set_delivery_time(skb, tp->tcp_wstamp_ns, true); list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); tcp_init_tso_segs(skb, mss_now); goto repair; /* Skip network transmission */ } if (tcp_pacing_check(sk)) break; tso_segs = tcp_init_tso_segs(skb, mss_now); BUG_ON(!tso_segs); cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) { if (push_one == 2) /* Force out a loss probe pkt. */ cwnd_quota = 1; else break; } if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) { is_rwnd_limited = true; break; } if (tso_segs == 1) { if (unlikely(!tcp_nagle_test(tp, skb, mss_now, (tcp_skb_is_last(sk, skb) ? nonagle : TCP_NAGLE_PUSH)))) break; } else { if (!push_one && tcp_tso_should_defer(sk, skb, &is_cwnd_limited, &is_rwnd_limited, max_segs)) break; } limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, min_t(unsigned int, cwnd_quota, max_segs), nonagle); if (skb->len > limit && unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) break; if (tcp_small_queue_check(sk, skb, 0)) break; /* Argh, we hit an empty skb(), presumably a thread * is sleeping in sendmsg()/sk_stream_wait_memory(). * We do not want to send a pure-ack packet and have * a strange looking rtx queue with empty packet(s). */ if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) break; if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; repair: /* Advance the send_head. This one is sent out. * This call will increment packets_out. */ tcp_event_new_data_sent(sk, skb); tcp_minshall_update(tp, mss_now, skb); sent_pkts += tcp_skb_pcount(skb); if (push_one) break; } if (is_rwnd_limited) tcp_chrono_start(sk, TCP_CHRONO_RWND_LIMITED); else tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED); is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tcp_snd_cwnd(tp)); if (likely(sent_pkts || is_cwnd_limited)) tcp_cwnd_validate(sk, is_cwnd_limited); if (likely(sent_pkts)) { if (tcp_in_cwnd_reduction(sk)) tp->prr_out += sent_pkts; /* Send one loss probe per tail loss episode. */ if (push_one != 2) tcp_schedule_loss_probe(sk, false); return false; } return !tp->packets_out && !tcp_write_queue_empty(sk); } bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 timeout, rto_delta_us; int early_retrans; /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. */ if (rcu_access_pointer(tp->fastopen_rsk)) return false; early_retrans = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_early_retrans); /* Schedule a loss probe in 2*RTT for SACK capable connections * not in loss recovery, that are either limited by cwnd or application. */ if ((early_retrans != 3 && early_retrans != 4) || !tp->packets_out || !tcp_is_sack(tp) || (icsk->icsk_ca_state != TCP_CA_Open && icsk->icsk_ca_state != TCP_CA_CWR)) return false; /* Probe timeout is 2*rtt. Add minimum RTO to account * for delayed ack when there's one outstanding packet. If no RTT * sample is available then probe after TCP_TIMEOUT_INIT. */ if (tp->srtt_us) { timeout = usecs_to_jiffies(tp->srtt_us >> 2); if (tp->packets_out == 1) timeout += TCP_RTO_MIN; else timeout += TCP_TIMEOUT_MIN; } else { timeout = TCP_TIMEOUT_INIT; } /* If the RTO formula yields an earlier time, then use that time. */ rto_delta_us = advancing_rto ? jiffies_to_usecs(inet_csk(sk)->icsk_rto) : tcp_rto_delta_us(sk); /* How far in future is RTO? */ if (rto_delta_us > 0) timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us)); tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, TCP_RTO_MAX); return true; } /* Thanks to skb fast clones, we can detect if a prior transmit of * a packet is still in a qdisc or driver queue. * In this case, there is very little point doing a retransmit ! */ static bool skb_still_in_host_queue(struct sock *sk, const struct sk_buff *skb) { if (unlikely(skb_fclone_busy(sk, skb))) { set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); smp_mb__after_atomic(); if (skb_fclone_busy(sk, skb)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); return true; } } return false; } /* When probe timeout (PTO) fires, try send a new segment if possible, else * retransmit the last segment. */ void tcp_send_loss_probe(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; int pcount; int mss = tcp_current_mss(sk); /* At most one outstanding TLP */ if (tp->tlp_high_seq) goto rearm_timer; tp->tlp_retrans = 0; skb = tcp_send_head(sk); if (skb && tcp_snd_wnd_test(tp, skb, mss)) { pcount = tp->packets_out; tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); if (tp->packets_out > pcount) goto probe_sent; goto rearm_timer; } skb = skb_rb_last(&sk->tcp_rtx_queue); if (unlikely(!skb)) { WARN_ONCE(tp->packets_out, "invalid inflight: %u state %u cwnd %u mss %d\n", tp->packets_out, sk->sk_state, tcp_snd_cwnd(tp), mss); inet_csk(sk)->icsk_pending = 0; return; } if (skb_still_in_host_queue(sk, skb)) goto rearm_timer; pcount = tcp_skb_pcount(skb); if (WARN_ON(!pcount)) goto rearm_timer; if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) { if (unlikely(tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, (pcount - 1) * mss, mss, GFP_ATOMIC))) goto rearm_timer; skb = skb_rb_next(skb); } if (WARN_ON(!skb || !tcp_skb_pcount(skb))) goto rearm_timer; if (__tcp_retransmit_skb(sk, skb, 1)) goto rearm_timer; tp->tlp_retrans = 1; probe_sent: /* Record snd_nxt for loss detection. */ tp->tlp_high_seq = tp->snd_nxt; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); /* Reset s.t. tcp_rearm_rto will restart timer from now */ inet_csk(sk)->icsk_pending = 0; rearm_timer: tcp_rearm_rto(sk); } /* Push out any pending frames which were held back due to * TCP_CORK or attempt at coalescing tiny packets. * The socket must be locked by the caller. */ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle) { /* If we are closed, the bytes will have to remain here. * In time closedown will finish, we empty the write queue and * all will be happy. */ if (unlikely(sk->sk_state == TCP_CLOSE)) return; if (tcp_write_xmit(sk, cur_mss, nonagle, 0, sk_gfp_mask(sk, GFP_ATOMIC))) tcp_check_probe_timer(sk); } /* Send _single_ skb sitting at the send head. This function requires * true push pending frames to setup probe timer etc. */ void tcp_push_one(struct sock *sk, unsigned int mss_now) { struct sk_buff *skb = tcp_send_head(sk); BUG_ON(!skb || skb->len < mss_now); tcp_write_xmit(sk, mss_now, TCP_NAGLE_PUSH, 1, sk->sk_allocation); } /* This function returns the amount that we can raise the * usable window based on the following constraints * * 1. The window can never be shrunk once it is offered (RFC 793) * 2. We limit memory per socket * * RFC 1122: * "the suggested [SWS] avoidance algorithm for the receiver is to keep * RECV.NEXT + RCV.WIN fixed until: * RCV.BUFF - RCV.USER - RCV.WINDOW >= min(1/2 RCV.BUFF, MSS)" * * i.e. don't raise the right edge of the window until you can raise * it at least MSS bytes. * * Unfortunately, the recommended algorithm breaks header prediction, * since header prediction assumes th->window stays fixed. * * Strictly speaking, keeping th->window fixed violates the receiver * side SWS prevention criteria. The problem is that under this rule * a stream of single byte packets will cause the right side of the * window to always advance by a single byte. * * Of course, if the sender implements sender side SWS prevention * then this will not be a problem. * * BSD seems to make the following compromise: * * If the free space is less than the 1/4 of the maximum * space available and the free space is less than 1/2 mss, * then set the window to 0. * [ Actually, bsd uses MSS and 1/4 of maximal _window_ ] * Otherwise, just prevent the window from shrinking * and from being larger than the largest representable value. * * This prevents incremental opening of the window in the regime * where TCP is limited by the speed of the reader side taking * data out of the TCP receive queue. It does nothing about * those cases where the window is constrained on the sender side * because the pipeline is full. * * BSD also seems to "accidentally" limit itself to windows that are a * multiple of MSS, at least until the free space gets quite small. * This would appear to be a side effect of the mbuf implementation. * Combining these two algorithms results in the observed behavior * of having a fixed window size at almost all times. * * Below we obtain similar behavior by forcing the offered window to * a multiple of the mss when it is feasible to do so. * * Note, we don't "adjust" for TIMESTAMP or SACK option bytes. * Regular options like TIMESTAMP are taken into account. */ u32 __tcp_select_window(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); /* MSS for the peer's data. Previous versions used mss_clamp * here. I don't know if the value based on our guesses * of peer's MSS is better for the performance. It's more correct * but may be worse for the performance because of rcv_mss * fluctuations. --SAW 1998/11/1 */ int mss = icsk->icsk_ack.rcv_mss; int free_space = tcp_space(sk); int allowed_space = tcp_full_space(sk); int full_space, window; if (sk_is_mptcp(sk)) mptcp_space(sk, &free_space, &allowed_space); full_space = min_t(int, tp->window_clamp, allowed_space); if (unlikely(mss > full_space)) { mss = full_space; if (mss <= 0) return 0; } if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; if (tcp_under_memory_pressure(sk)) tcp_adjust_rcv_ssthresh(sk); /* free_space might become our new window, make sure we don't * increase it due to wscale. */ free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale); /* if free space is less than mss estimate, or is below 1/16th * of the maximum allowed, try to move to zero-window, else * tcp_clamp_window() will grow rcv buf up to tcp_rmem[2], and * new incoming data is dropped due to memory limits. * With large window, mss test triggers way too late in order * to announce zero window in time before rmem limit kicks in. */ if (free_space < (allowed_space >> 4) || free_space < mss) return 0; } if (free_space > tp->rcv_ssthresh) free_space = tp->rcv_ssthresh; /* Don't do rounding if we are using window scaling, since the * scaled window will not line up with the MSS boundary anyway. */ if (tp->rx_opt.rcv_wscale) { window = free_space; /* Advertise enough space so that it won't get scaled away. * Import case: prevent zero window announcement if * 1<<rcv_wscale > mss. */ window = ALIGN(window, (1 << tp->rx_opt.rcv_wscale)); } else { window = tp->rcv_wnd; /* Get the largest window that is a nice multiple of mss. * Window clamp already applied above. * If our current window offering is within 1 mss of the * free space we just keep it. This prevents the divide * and multiply from happening most of the time. * We also don't do any window rounding when the free space * is too small. */ if (window <= free_space - mss || window > free_space) window = rounddown(free_space, mss); else if (mss == full_space && free_space > window + (full_space >> 1)) window = free_space; } return window; } void tcp_skb_collapse_tstamp(struct sk_buff *skb, const struct sk_buff *next_skb) { if (unlikely(tcp_has_tx_tstamp(next_skb))) { const struct skb_shared_info *next_shinfo = skb_shinfo(next_skb); struct skb_shared_info *shinfo = skb_shinfo(skb); shinfo->tx_flags |= next_shinfo->tx_flags & SKBTX_ANY_TSTAMP; shinfo->tskey = next_shinfo->tskey; TCP_SKB_CB(skb)->txstamp_ack |= TCP_SKB_CB(next_skb)->txstamp_ack; } } /* Collapses two adjacent SKB's during retransmission. */ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *next_skb = skb_rb_next(skb); int next_skb_size; next_skb_size = next_skb->len; BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1); if (next_skb_size && !tcp_skb_shift(skb, next_skb, 1, next_skb_size)) return false; tcp_highest_sack_replace(sk, next_skb, skb); /* Update sequence range on original skb. */ TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; /* Merge over control information. This moves PSH/FIN etc. over */ TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(next_skb)->tcp_flags; /* All done, get rid of second SKB and account for it so * packet counting does not break. */ TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked & TCPCB_EVER_RETRANS; TCP_SKB_CB(skb)->eor = TCP_SKB_CB(next_skb)->eor; /* changed transmit queue under us so clear hints */ tcp_clear_retrans_hints_partial(tp); if (next_skb == tp->retransmit_skb_hint) tp->retransmit_skb_hint = skb; tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb)); tcp_skb_collapse_tstamp(skb, next_skb); tcp_rtx_queue_unlink_and_free(next_skb, sk); return true; } /* Check if coalescing SKBs is legal. */ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) { if (tcp_skb_pcount(skb) > 1) return false; if (skb_cloned(skb)) return false; /* Some heuristics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return false; return true; } /* Collapse packets in the retransmit queue to make to create * less packets on the wire. This is only done on retransmission. */ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, int space) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = to, *tmp; bool first = true; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse)) return; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) return; skb_rbtree_walk_from_safe(skb, tmp) { if (!tcp_can_collapse(sk, skb)) break; if (!tcp_skb_can_collapse(to, skb)) break; space -= skb->len; if (first) { first = false; continue; } if (space < 0) break; if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp))) break; if (!tcp_collapse_retrans(sk, to)) break; } } /* This retransmits one SKB. Policy decisions and retransmit queue * state updates are done by the caller. Returns non-zero if an * error occurred which prevented the send. */ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int cur_mss; int diff, len, err; int avail_wnd; /* Inconclusive MTU probe */ if (icsk->icsk_mtup.probe_size) icsk->icsk_mtup.probe_size = 0; if (skb_still_in_host_queue(sk, skb)) return -EBUSY; if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { WARN_ON_ONCE(1); return -EINVAL; } if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) return -ENOMEM; } if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) return -EHOSTUNREACH; /* Routing failure or similar. */ cur_mss = tcp_current_mss(sk); avail_wnd = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; /* If receiver has shrunk his window, and skb is out of * new window, do not retransmit it. The exception is the * case, when window is shrunk to zero. In this case * our retransmit of one segment serves as a zero window probe. */ if (avail_wnd <= 0) { if (TCP_SKB_CB(skb)->seq != tp->snd_una) return -EAGAIN; avail_wnd = cur_mss; } len = cur_mss * segs; if (len > avail_wnd) { len = rounddown(avail_wnd, cur_mss); if (!len) len = avail_wnd; } if (skb->len > len) { if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len, cur_mss, GFP_ATOMIC)) return -ENOMEM; /* We'll try again later. */ } else { if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) return -ENOMEM; diff = tcp_skb_pcount(skb); tcp_set_skb_tso_segs(skb, cur_mss); diff -= tcp_skb_pcount(skb); if (diff) tcp_adjust_pcount(sk, skb, diff); avail_wnd = min_t(int, avail_wnd, cur_mss); if (skb->len < avail_wnd) tcp_retrans_try_collapse(sk, skb, avail_wnd); } /* RFC3168, section 6.1.1.1. ECN fallback */ if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN) tcp_ecn_clear_syn(sk, skb); /* Update global and local TCP statistics. */ segs = tcp_skb_pcount(skb); TCP_ADD_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS, segs); if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); tp->total_retrans += segs; tp->bytes_retrans += skb->len; /* make sure skb->data is aligned on arches that require it * and check if ack-trimming & collapsing extended the headroom * beyond what csum_start can cover. */ if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb; tcp_skb_tsorted_save(skb) { nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); if (nskb) { nskb->dev = NULL; err = tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC); } else { err = -ENOBUFS; } } tcp_skb_tsorted_restore(skb); if (!err) { tcp_update_skb_after_send(sk, skb, tp->tcp_wstamp_ns); tcp_rate_skb_sent(sk, skb); } } else { err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } /* To avoid taking spuriously low RTT samples based on a timestamp * for a transmit that never happened, always mark EVER_RETRANS */ TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG)) tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB, TCP_SKB_CB(skb)->seq, segs, err); if (likely(!err)) { trace_tcp_retransmit_skb(sk, skb); } else if (err != -EBUSY) { NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs); } return err; } int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) { struct tcp_sock *tp = tcp_sk(sk); int err = __tcp_retransmit_skb(sk, skb, segs); if (err == 0) { #if FASTRETRANS_DEBUG > 0 if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { net_dbg_ratelimited("retrans_out leaked\n"); } #endif TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS; tp->retrans_out += tcp_skb_pcount(skb); } /* Save stamp of the first (attempted) retransmit. */ if (!tp->retrans_stamp) tp->retrans_stamp = tcp_skb_timestamp(skb); if (tp->undo_retrans < 0) tp->undo_retrans = 0; tp->undo_retrans += tcp_skb_pcount(skb); return err; } /* This gets called after a retransmit timeout, and the initially * retransmitted data is acknowledged. It tries to continue * resending the rest of the retransmit queue, until either * we've sent it all or the congestion window limit is reached. */ void tcp_xmit_retransmit_queue(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb, *rtx_head, *hole = NULL; struct tcp_sock *tp = tcp_sk(sk); bool rearm_timer = false; u32 max_segs; int mib_idx; if (!tp->packets_out) return; rtx_head = tcp_rtx_queue_head(sk); skb = tp->retransmit_skb_hint ?: rtx_head; max_segs = tcp_tso_segs(sk, tcp_current_mss(sk)); skb_rbtree_walk_from(skb) { __u8 sacked; int segs; if (tcp_pacing_check(sk)) break; /* we could do better than to assign each time */ if (!hole) tp->retransmit_skb_hint = skb; segs = tcp_snd_cwnd(tp) - tcp_packets_in_flight(tp); if (segs <= 0) break; sacked = TCP_SKB_CB(skb)->sacked; /* In case tcp_shift_skb_data() have aggregated large skbs, * we need to make sure not sending too bigs TSO packets */ segs = min_t(int, segs, max_segs); if (tp->retrans_out >= tp->lost_out) { break; } else if (!(sacked & TCPCB_LOST)) { if (!hole && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED))) hole = skb; continue; } else { if (icsk->icsk_ca_state != TCP_CA_Loss) mib_idx = LINUX_MIB_TCPFASTRETRANS; else mib_idx = LINUX_MIB_TCPSLOWSTARTRETRANS; } if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS)) continue; if (tcp_small_queue_check(sk, skb, 1)) break; if (tcp_retransmit_skb(sk, skb, segs)) break; NET_ADD_STATS(sock_net(sk), mib_idx, tcp_skb_pcount(skb)); if (tcp_in_cwnd_reduction(sk)) tp->prr_out += tcp_skb_pcount(skb); if (skb == rtx_head && icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT) rearm_timer = true; } if (rearm_timer) tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, TCP_RTO_MAX); } /* We allow to exceed memory limits for FIN packets to expedite * connection tear down and (memory) recovery. * Otherwise tcp_send_fin() could be tempted to either delay FIN * or even be forced to close flow without any FIN. * In general, we want to allow one skb per socket to avoid hangs * with edge trigger epoll() */ void sk_forced_mem_schedule(struct sock *sk, int size) { int delta, amt; delta = size - sk->sk_forward_alloc; if (delta <= 0) return; amt = sk_mem_pages(delta); sk->sk_forward_alloc += amt << PAGE_SHIFT; sk_memory_allocated_add(sk, amt); if (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_charge_skmem(sk->sk_memcg, amt, gfp_memcg_charge() | __GFP_NOFAIL); } /* Send a FIN. The caller locks the socket for us. * We should try to send a FIN packet really hard, but eventually give up. */ void tcp_send_fin(struct sock *sk) { struct sk_buff *skb, *tskb, *tail = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); /* Optimization, tack on the FIN if we have one skb in write queue and * this skb was not yet sent, or we are under memory pressure. * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ tskb = tail; if (!tskb && tcp_under_memory_pressure(sk)) tskb = skb_rb_last(&sk->tcp_rtx_queue); if (tskb) { TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; if (!tail) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have * if FIN had been sent. This is because retransmit path * does not change tp->snd_nxt. */ WRITE_ONCE(tp->snd_nxt, tp->snd_nxt + 1); return; } } else { skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); if (unlikely(!skb)) return; INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); skb_reserve(skb, MAX_TCP_HEADER); sk_forced_mem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); tcp_queue_skb(sk, skb); } __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); } /* We get here when a process closes a file descriptor (either due to * an explicit close() or as a byproduct of exit()'ing) and there * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ void tcp_send_active_reset(struct sock *sk, gfp_t priority) { struct sk_buff *skb; TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); /* NOTE: No TCP options attached and we never retransmit this. */ skb = alloc_skb(MAX_TCP_HEADER, priority); if (!skb) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); return; } /* Reserve space for headers and prepare control bits. */ skb_reserve(skb, MAX_TCP_HEADER); tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); tcp_mstamp_refresh(tcp_sk(sk)); /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); /* skb of trace_tcp_send_reset() keeps the skb that caused RST, * skb here is different to the troublesome skb, so use NULL */ trace_tcp_send_reset(sk, NULL); } /* Send a crossed SYN-ACK during socket establishment. * WARNING: This routine must only be called when we have already sent * a SYN packet that crossed the incoming SYN that caused this routine * to get called. If this assumption fails then the initial rcv_wnd * and rcv_wscale values will not be correct. */ int tcp_send_synack(struct sock *sk) { struct sk_buff *skb; skb = tcp_rtx_queue_head(sk); if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_err("%s: wrong queue state\n", __func__); return -EFAULT; } if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { if (skb_cloned(skb)) { struct sk_buff *nskb; tcp_skb_tsorted_save(skb) { nskb = skb_copy(skb, GFP_ATOMIC); } tcp_skb_tsorted_restore(skb); if (!nskb) return -ENOMEM; INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor); tcp_highest_sack_replace(sk, skb, nskb); tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = nskb; } TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ACK; tcp_ecn_send_synack(sk, skb); } return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } /** * tcp_make_synack - Allocate one skb and build a SYNACK packet. * @sk: listener socket * @dst: dst entry attached to the SYNACK. It is consumed and caller * should not use it again. * @req: request_sock pointer * @foc: cookie for tcp fast open * @synack_type: Type of synack to prepare * @syn_skb: SYN packet just received. It could be NULL for rtx case. */ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *md5 = NULL; struct tcp_out_options opts; struct sk_buff *skb; int tcp_header_size; struct tcphdr *th; int mss; u64 now; skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); if (unlikely(!skb)) { dst_release(dst); return NULL; } /* Reserve space for headers. */ skb_reserve(skb, MAX_TCP_HEADER); switch (synack_type) { case TCP_SYNACK_NORMAL: skb_set_owner_w(skb, req_to_sk(req)); break; case TCP_SYNACK_COOKIE: /* Under synflood, we do not attach skb to a socket, * to avoid false sharing. */ break; case TCP_SYNACK_FASTOPEN: /* sk is a const pointer, because we want to express multiple * cpu might call us concurrently. * sk->sk_wmem_alloc in an atomic, we can promote to rw. */ skb_set_owner_w(skb, (struct sock *)sk); break; } skb_dst_set(skb, dst); mss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); memset(&opts, 0, sizeof(opts)); now = tcp_clock_ns(); #ifdef CONFIG_SYN_COOKIES if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok)) skb_set_delivery_time(skb, cookie_init_timestamp(req, now), true); else #endif { skb_set_delivery_time(skb, now, true); if (!tcp_rsk(req)->snt_synack) /* Timestamp first SYNACK */ tcp_rsk(req)->snt_synack = tcp_skb_timestamp_us(skb); } #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); /* bpf program will be interested in the tcp_flags */ TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, foc, synack_type, syn_skb) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); th = (struct tcphdr *)skb->data; memset(th, 0, sizeof(struct tcphdr)); th->syn = 1; th->ack = 1; tcp_ecn_make_synack(req, th); th->source = htons(ireq->ir_num); th->dest = ireq->ir_rmt_port; skb->mark = ireq->ir_mark; skb->ip_summed = CHECKSUM_PARTIAL; th->seq = htonl(tcp_rsk(req)->snt_isn); /* XXX data is queued and acked as is. No buffer/window check */ th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt); /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rsk_rcv_wnd, 65535U)); tcp_options_write(th, NULL, &opts); th->doff = (tcp_header_size >> 2); __TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ if (md5) tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location, md5, req_to_sk(req), skb); rcu_read_unlock(); #endif bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb, synack_type, &opts); skb_set_delivery_time(skb, now, true); tcp_add_tx_delay(skb, tp); return skb; } EXPORT_SYMBOL(tcp_make_synack); static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; u32 ca_key = dst_metric(dst, RTAX_CC_ALGO); if (ca_key == TCP_CA_UNSPEC) return; rcu_read_lock(); ca = tcp_ca_find_key(ca_key); if (likely(ca && bpf_try_module_get(ca, ca->owner))) { bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); icsk->icsk_ca_ops = ca; } rcu_read_unlock(); } /* Do all connect socket setups that can be done AF independent. */ static void tcp_connect_init(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); __u8 rcv_wscale; u32 rcv_wnd; /* We'll fix this up when we get a response from the other end. * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ tp->tcp_header_len = sizeof(struct tcphdr); if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps)) tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG if (tp->af_specific->md5_lookup(sk, sk)) tp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif /* If user gave his TCP_MAXSEG, record it to clamp */ if (tp->rx_opt.user_mss) tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; tp->max_window = 0; tcp_mtup_init(sk); tcp_sync_mss(sk, dst_mtu(dst)); tcp_ca_dst_init(sk, dst); if (!tp->window_clamp) tp->window_clamp = dst_metric(dst, RTAX_WINDOW); tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); tcp_initialize_rcv_mss(sk); /* limit the window selection if the user enforce a smaller rx buffer */ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0)) tp->window_clamp = tcp_full_space(sk); rcv_wnd = tcp_rwnd_init_bpf(sk); if (rcv_wnd == 0) rcv_wnd = dst_metric(dst, RTAX_INITRWND); tcp_select_initial_window(sk, tcp_full_space(sk), tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling), &rcv_wscale, rcv_wnd); tp->rx_opt.rcv_wscale = rcv_wscale; tp->rcv_ssthresh = tp->rcv_wnd; sk->sk_err = 0; sock_reset_flag(sk, SOCK_DONE); tp->snd_wnd = 0; tcp_init_wl(tp, 0); tcp_write_queue_purge(sk); tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; WRITE_ONCE(tp->snd_nxt, tp->write_seq); if (likely(!tp->repair)) tp->rcv_nxt = 0; else tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); inet_csk(sk)->icsk_retransmits = 0; tcp_clear_retrans(tp); } static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); tcb->end_seq += skb->len; __skb_header_release(skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); WRITE_ONCE(tp->write_seq, tcb->end_seq); tp->packets_out += tcp_skb_pcount(skb); } /* Build and send a SYN with data and (cached) Fast Open cookie. However, * queue a data-only packet after the regular SYN, such that regular SYNs * are retransmitted on timeouts. Also if the remote SYN-ACK acknowledges * only the SYN sequence, the data are retransmitted in the first ACK. * If cookie is not cached or other error occurs, falls back to send a * regular SYN with Fast Open cookie request option. */ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; int space, err = 0; struct sk_buff *syn_data; tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */ if (!tcp_fastopen_cookie_check(sk, &tp->rx_opt.mss_clamp, &fo->cookie)) goto fallback; /* MSS for SYN-data is based on cached MSS and bounded by PMTU and * user-MSS. Reserve maximum option space for middleboxes that add * private TCP options. The cost is reduced data space in SYN :( */ tp->rx_opt.mss_clamp = tcp_mss_clamp(tp, tp->rx_opt.mss_clamp); /* Sync mss_cache after updating the mss_clamp */ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); space = __tcp_mtu_to_mss(sk, icsk->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; space = min_t(size_t, space, fo->size); /* limit to order-0 allocations */ space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); syn_data = tcp_stream_alloc_skb(sk, space, sk->sk_allocation, false); if (!syn_data) goto fallback; memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); if (space) { int copied = copy_from_iter(skb_put(syn_data, space), space, &fo->data->msg_iter); if (unlikely(!copied)) { tcp_skb_tsorted_anchor_cleanup(syn_data); kfree_skb(syn_data); goto fallback; } if (copied != space) { skb_trim(syn_data, copied); space = copied; } skb_zcopy_set(syn_data, fo->uarg, NULL); } /* No more data pending in inet_wait_for_connect() */ if (space == fo->size) fo->data = NULL; fo->copied = space; tcp_connect_queue_skb(sk, syn_data); if (syn_data->len) tcp_chrono_start(sk, TCP_CHRONO_BUSY); err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation); skb_set_delivery_time(syn, syn_data->skb_mstamp_ns, true); /* Now full SYN+DATA was cloned and sent (or not), * remove the SYN from the original skb (syn_data) * we keep in write queue in case of a retransmit, as we * also have the SYN packet (with no data) in the same queue. */ TCP_SKB_CB(syn_data)->seq++; TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH; if (!err) { tp->syn_data = (fo->copied > 0); tcp_rbtree_insert(&sk->tcp_rtx_queue, syn_data); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); goto done; } /* data was not sent, put it in write_queue */ __skb_queue_tail(&sk->sk_write_queue, syn_data); tp->packets_out -= tcp_skb_pcount(syn_data); fallback: /* Send a regular SYN with Fast Open cookie request option */ if (fo->cookie.len > 0) fo->cookie.len = 0; err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation); if (err) tp->syn_fastopen = 0; done: fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */ return err; } /* Build a SYN and send it off. */ int tcp_connect(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int err; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL); if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) return -EHOSTUNREACH; /* Routing failure or similar. */ tcp_connect_init(sk); if (unlikely(tp->repair)) { tcp_finish_connect(sk, NULL); return 0; } buff = tcp_stream_alloc_skb(sk, 0, sk->sk_allocation, true); if (unlikely(!buff)) return -ENOBUFS; tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); tcp_mstamp_refresh(tp); tp->retrans_stamp = tcp_time_stamp(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); /* Send off SYN; include data in Fast Open. */ err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) : tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); if (err == -ECONNREFUSED) return err; /* We change tp->snd_nxt after the tcp_transmit_skb() call * in order to make this packet get counted in tcpOutSegs. */ WRITE_ONCE(tp->snd_nxt, tp->write_seq); tp->pushed_seq = tp->write_seq; buff = tcp_send_head(sk); if (unlikely(buff)) { WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(buff)->seq); tp->pushed_seq = TCP_SKB_CB(buff)->seq; } TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); /* Timer for repeating the SYN until an answer. */ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, TCP_RTO_MAX); return 0; } EXPORT_SYMBOL(tcp_connect); /* Send out a delayed ack, the caller does the policy checking * to see if we should even be here. See tcp_input.c:tcp_ack_snd_check() * for details. */ void tcp_send_delayed_ack(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int ato = icsk->icsk_ack.ato; unsigned long timeout; if (ato > TCP_DELACK_MIN) { const struct tcp_sock *tp = tcp_sk(sk); int max_ato = HZ / 2; if (inet_csk_in_pingpong_mode(sk) || (icsk->icsk_ack.pending & ICSK_ACK_PUSHED)) max_ato = TCP_DELACK_MAX; /* Slow path, intersegment interval is "high". */ /* If some rtt estimate is known, use it to bound delayed ack. * Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements * directly. */ if (tp->srtt_us) { int rtt = max_t(int, usecs_to_jiffies(tp->srtt_us >> 3), TCP_DELACK_MIN); if (rtt < max_ato) max_ato = rtt; } ato = min(ato, max_ato); } ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max); /* Stay within the limit we were given */ timeout = jiffies + ato; /* Use new timeout only if there wasn't a older one earlier. */ if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) { /* If delack timer is about to expire, send ACK now. */ if (time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) { tcp_send_ack(sk); return; } if (!time_before(timeout, icsk->icsk_ack.timeout)) timeout = icsk->icsk_ack.timeout; } icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; icsk->icsk_ack.timeout = timeout; sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); } /* This routine sends an ack and also updates the window. */ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) { struct sk_buff *buff; /* If we have been reset, we may not send again. */ if (sk->sk_state == TCP_CLOSE) return; /* We are not putting this on the write queue, so * tcp_transmit_skb() will set the ownership to this * sock. */ buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN)); if (unlikely(!buff)) { struct inet_connection_sock *icsk = inet_csk(sk); unsigned long delay; delay = TCP_DELACK_MAX << icsk->icsk_ack.retry; if (delay < TCP_RTO_MAX) icsk->icsk_ack.retry++; inet_csk_schedule_ack(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, TCP_RTO_MAX); return; } /* Reserve space for headers and prepare control bits. */ skb_reserve(buff, MAX_TCP_HEADER); tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK); /* We do not want pure acks influencing TCP Small Queues or fq/pacing * too much. * SKB_TRUESIZE(max(1 .. 66, MAX_TCP_HEADER)) is unfortunately ~784 */ skb_set_tcp_pure_ack(buff); /* Send it off, this clears delayed acks for us. */ __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt); } EXPORT_SYMBOL_GPL(__tcp_send_ack); void tcp_send_ack(struct sock *sk) { __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); } /* This routine sends a packet with an out of date sequence * number. It assumes the other end will try to ack it. * * Question: what should we make while urgent mode? * 4.4BSD forces sending single byte of data. We cannot send * out of window data, because we have SND.NXT==SND.MAX... * * Current solution: to send TWO zero-length segments in urgent mode: * one is with SEG.SEQ=SND.UNA to deliver urgent pointer, another is * out-of-date with SND.UNA-1 to probe window. */ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; /* We don't queue it, tcp_transmit_skb() sets ownership. */ skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN)); if (!skb) return -1; /* Reserve space for headers and set control bits. */ skb_reserve(skb, MAX_TCP_HEADER); /* Use a previous sequence. This should cause the other * end to send an ack. Don't queue or clone SKB, just * send it. */ tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); NET_INC_STATS(sock_net(sk), mib); return tcp_transmit_skb(sk, skb, 0, (__force gfp_t)0); } /* Called from setsockopt( ... TCP_REPAIR ) */ void tcp_send_window_probe(struct sock *sk) { if (sk->sk_state == TCP_ESTABLISHED) { tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; tcp_mstamp_refresh(tcp_sk(sk)); tcp_xmit_probe_skb(sk, 0, LINUX_MIB_TCPWINPROBE); } } /* Initiate keepalive or window probe from timer. */ int tcp_write_wakeup(struct sock *sk, int mib) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; if (sk->sk_state == TCP_CLOSE) return -1; skb = tcp_send_head(sk); if (skb && before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) { int err; unsigned int mss = tcp_current_mss(sk); unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; if (before(tp->pushed_seq, TCP_SKB_CB(skb)->end_seq)) tp->pushed_seq = TCP_SKB_CB(skb)->end_seq; /* We are probing the opening of a window * but the window size is != 0 * must have been a result SWS avoidance ( sender ) */ if (seg_size < TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq || skb->len > mss) { seg_size = min(seg_size, mss); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; if (tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, skb, seg_size, mss, GFP_ATOMIC)) return -1; } else if (!tcp_skb_pcount(skb)) tcp_set_skb_tso_segs(skb, mss); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); if (!err) tcp_event_new_data_sent(sk, skb); return err; } else { if (between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF)) tcp_xmit_probe_skb(sk, 1, mib); return tcp_xmit_probe_skb(sk, 0, mib); } } /* A window probe timeout has occurred. If window is not closed send * a partial packet else a zero probe. */ void tcp_send_probe0(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); unsigned long timeout; int err; err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE); if (tp->packets_out || tcp_write_queue_empty(sk)) { /* Cancel probe timer, if it is not required. */ icsk->icsk_probes_out = 0; icsk->icsk_backoff = 0; icsk->icsk_probes_tstamp = 0; return; } icsk->icsk_probes_out++; if (err <= 0) { if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2)) icsk->icsk_backoff++; timeout = tcp_probe0_when(sk, TCP_RTO_MAX); } else { /* If packet was not sent due to local congestion, * Let senders fight for local resources conservatively. */ timeout = TCP_RESOURCE_PROBE_INTERVAL; } timeout = tcp_clamp_probe0_to_user_timeout(sk, timeout); tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX); } int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) { const struct tcp_request_sock_ops *af_ops = tcp_rsk(req)->af_specific; struct flowi fl; int res; /* Paired with WRITE_ONCE() in sock_setsockopt() */ if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED) tcp_rsk(req)->txhash = net_tx_rndhash(); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, NULL); if (!res) { TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); if (unlikely(tcp_passive_fastopen(sk))) tcp_sk(sk)->total_retrans++; trace_tcp_retransmit_synack(sk, req); } return res; } EXPORT_SYMBOL(tcp_rtx_synack); |
| 1382 1382 1382 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) ST-Ericsson AB 2010 * Author: Sjur Brendeland */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ #include <linux/stddef.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/rculist.h> #include <net/caif/cfpkt.h> #include <net/caif/cfmuxl.h> #include <net/caif/cfsrvl.h> #include <net/caif/cffrml.h> #define container_obj(layr) container_of(layr, struct cfmuxl, layer) #define CAIF_CTRL_CHANNEL 0 #define UP_CACHE_SIZE 8 #define DN_CACHE_SIZE 8 struct cfmuxl { struct cflayer layer; struct list_head srvl_list; struct list_head frml_list; struct cflayer *up_cache[UP_CACHE_SIZE]; struct cflayer *dn_cache[DN_CACHE_SIZE]; /* * Set when inserting or removing downwards layers. */ spinlock_t transmit_lock; /* * Set when inserting or removing upwards layers. */ spinlock_t receive_lock; }; static int cfmuxl_receive(struct cflayer *layr, struct cfpkt *pkt); static int cfmuxl_transmit(struct cflayer *layr, struct cfpkt *pkt); static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, int phyid); static struct cflayer *get_up(struct cfmuxl *muxl, u16 id); struct cflayer *cfmuxl_create(void) { struct cfmuxl *this = kzalloc(sizeof(struct cfmuxl), GFP_ATOMIC); if (!this) return NULL; this->layer.receive = cfmuxl_receive; this->layer.transmit = cfmuxl_transmit; this->layer.ctrlcmd = cfmuxl_ctrlcmd; INIT_LIST_HEAD(&this->srvl_list); INIT_LIST_HEAD(&this->frml_list); spin_lock_init(&this->transmit_lock); spin_lock_init(&this->receive_lock); snprintf(this->layer.name, CAIF_LAYER_NAME_SZ, "mux"); return &this->layer; } int cfmuxl_set_dnlayer(struct cflayer *layr, struct cflayer *dn, u8 phyid) { struct cfmuxl *muxl = (struct cfmuxl *) layr; spin_lock_bh(&muxl->transmit_lock); list_add_rcu(&dn->node, &muxl->frml_list); spin_unlock_bh(&muxl->transmit_lock); return 0; } static struct cflayer *get_from_id(struct list_head *list, u16 id) { struct cflayer *lyr; list_for_each_entry_rcu(lyr, list, node) { if (lyr->id == id) return lyr; } return NULL; } int cfmuxl_set_uplayer(struct cflayer *layr, struct cflayer *up, u8 linkid) { struct cfmuxl *muxl = container_obj(layr); struct cflayer *old; spin_lock_bh(&muxl->receive_lock); /* Two entries with same id is wrong, so remove old layer from mux */ old = get_from_id(&muxl->srvl_list, linkid); if (old != NULL) list_del_rcu(&old->node); list_add_rcu(&up->node, &muxl->srvl_list); spin_unlock_bh(&muxl->receive_lock); return 0; } struct cflayer *cfmuxl_remove_dnlayer(struct cflayer *layr, u8 phyid) { struct cfmuxl *muxl = container_obj(layr); struct cflayer *dn; int idx = phyid % DN_CACHE_SIZE; spin_lock_bh(&muxl->transmit_lock); RCU_INIT_POINTER(muxl->dn_cache[idx], NULL); dn = get_from_id(&muxl->frml_list, phyid); if (dn == NULL) goto out; list_del_rcu(&dn->node); caif_assert(dn != NULL); out: spin_unlock_bh(&muxl->transmit_lock); return dn; } static struct cflayer *get_up(struct cfmuxl *muxl, u16 id) { struct cflayer *up; int idx = id % UP_CACHE_SIZE; up = rcu_dereference(muxl->up_cache[idx]); if (up == NULL || up->id != id) { spin_lock_bh(&muxl->receive_lock); up = get_from_id(&muxl->srvl_list, id); rcu_assign_pointer(muxl->up_cache[idx], up); spin_unlock_bh(&muxl->receive_lock); } return up; } static struct cflayer *get_dn(struct cfmuxl *muxl, struct dev_info *dev_info) { struct cflayer *dn; int idx = dev_info->id % DN_CACHE_SIZE; dn = rcu_dereference(muxl->dn_cache[idx]); if (dn == NULL || dn->id != dev_info->id) { spin_lock_bh(&muxl->transmit_lock); dn = get_from_id(&muxl->frml_list, dev_info->id); rcu_assign_pointer(muxl->dn_cache[idx], dn); spin_unlock_bh(&muxl->transmit_lock); } return dn; } struct cflayer *cfmuxl_remove_uplayer(struct cflayer *layr, u8 id) { struct cflayer *up; struct cfmuxl *muxl = container_obj(layr); int idx = id % UP_CACHE_SIZE; if (id == 0) { pr_warn("Trying to remove control layer\n"); return NULL; } spin_lock_bh(&muxl->receive_lock); up = get_from_id(&muxl->srvl_list, id); if (up == NULL) goto out; RCU_INIT_POINTER(muxl->up_cache[idx], NULL); list_del_rcu(&up->node); out: spin_unlock_bh(&muxl->receive_lock); return up; } static int cfmuxl_receive(struct cflayer *layr, struct cfpkt *pkt) { int ret; struct cfmuxl *muxl = container_obj(layr); u8 id; struct cflayer *up; if (cfpkt_extr_head(pkt, &id, 1) < 0) { pr_err("erroneous Caif Packet\n"); cfpkt_destroy(pkt); return -EPROTO; } rcu_read_lock(); up = get_up(muxl, id); if (up == NULL) { pr_debug("Received data on unknown link ID = %d (0x%x)" " up == NULL", id, id); cfpkt_destroy(pkt); /* * Don't return ERROR, since modem misbehaves and sends out * flow on before linksetup response. */ rcu_read_unlock(); return /* CFGLU_EPROT; */ 0; } /* We can't hold rcu_lock during receive, so take a ref count instead */ cfsrvl_get(up); rcu_read_unlock(); ret = up->receive(up, pkt); cfsrvl_put(up); return ret; } static int cfmuxl_transmit(struct cflayer *layr, struct cfpkt *pkt) { struct cfmuxl *muxl = container_obj(layr); int err; u8 linkid; struct cflayer *dn; struct caif_payload_info *info = cfpkt_info(pkt); BUG_ON(!info); rcu_read_lock(); dn = get_dn(muxl, info->dev_info); if (dn == NULL) { pr_debug("Send data on unknown phy ID = %d (0x%x)\n", info->dev_info->id, info->dev_info->id); rcu_read_unlock(); cfpkt_destroy(pkt); return -ENOTCONN; } info->hdr_len += 1; linkid = info->channel_id; cfpkt_add_head(pkt, &linkid, 1); /* We can't hold rcu_lock during receive, so take a ref count instead */ cffrml_hold(dn); rcu_read_unlock(); err = dn->transmit(dn, pkt); cffrml_put(dn); return err; } static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, int phyid) { struct cfmuxl *muxl = container_obj(layr); struct cflayer *layer; rcu_read_lock(); list_for_each_entry_rcu(layer, &muxl->srvl_list, node) { if (cfsrvl_phyid_match(layer, phyid) && layer->ctrlcmd) { if ((ctrl == _CAIF_CTRLCMD_PHYIF_DOWN_IND || ctrl == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND) && layer->id != 0) cfmuxl_remove_uplayer(layr, layer->id); /* NOTE: ctrlcmd is not allowed to block */ layer->ctrlcmd(layer, ctrl, phyid); } } rcu_read_unlock(); } |
| 919 648 2 39 39 39 2705 391 641 641 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_INETDEVICE_H #define _LINUX_INETDEVICE_H #ifdef __KERNEL__ #include <linux/bitmap.h> #include <linux/if.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <linux/timer.h> #include <linux/sysctl.h> #include <linux/rtnetlink.h> #include <linux/refcount.h> struct ipv4_devconf { void *sysctl; int data[IPV4_DEVCONF_MAX]; DECLARE_BITMAP(state, IPV4_DEVCONF_MAX); }; #define MC_HASH_SZ_LOG 9 struct in_device { struct net_device *dev; netdevice_tracker dev_tracker; refcount_t refcnt; int dead; struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ struct ip_mc_list __rcu * __rcu *mc_hash; int mc_count; /* Number of installed mcasts */ spinlock_t mc_tomb_lock; struct ip_mc_list *mc_tomb; unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; unsigned long mr_qi; /* Query Interval */ unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ struct neigh_parms *arp_parms; struct ipv4_devconf cnf; struct rcu_head rcu_head; }; #define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1]) #define IPV4_DEVCONF_ALL(net, attr) \ IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr) static inline int ipv4_devconf_get(struct in_device *in_dev, int index) { index--; return in_dev->cnf.data[index]; } static inline void ipv4_devconf_set(struct in_device *in_dev, int index, int val) { index--; set_bit(index, in_dev->cnf.state); in_dev->cnf.data[index] = val; } static inline void ipv4_devconf_setall(struct in_device *in_dev) { bitmap_fill(in_dev->cnf.state, IPV4_DEVCONF_MAX); } #define IN_DEV_CONF_GET(in_dev, attr) \ ipv4_devconf_get((in_dev), IPV4_DEVCONF_ ## attr) #define IN_DEV_CONF_SET(in_dev, attr, val) \ ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_NET_ORCONF(in_dev, net, attr) \ (IPV4_DEVCONF_ALL(net, attr) || \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_ORCONF(in_dev, attr) \ IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr) #define IN_DEV_MAXCONF(in_dev, attr) \ (max(IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) #define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) #define IN_DEV_ACCEPT_LOCAL(in_dev) IN_DEV_ORCONF((in_dev), ACCEPT_LOCAL) #define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY) #define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS) #define IN_DEV_PROXY_ARP(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP) #define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP_PVLAN) #define IN_DEV_SHARED_MEDIA(in_dev) IN_DEV_ORCONF((in_dev), SHARED_MEDIA) #define IN_DEV_TX_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), SEND_REDIRECTS) #define IN_DEV_SEC_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), \ SECURE_REDIRECTS) #define IN_DEV_IDTAG(in_dev) IN_DEV_CONF_GET(in_dev, TAG) #define IN_DEV_MEDIUM_ID(in_dev) IN_DEV_CONF_GET(in_dev, MEDIUM_ID) #define IN_DEV_PROMOTE_SECONDARIES(in_dev) \ IN_DEV_ORCONF((in_dev), \ PROMOTE_SECONDARIES) #define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET) #define IN_DEV_NET_ROUTE_LOCALNET(in_dev, net) \ IN_DEV_NET_ORCONF(in_dev, net, ROUTE_LOCALNET) #define IN_DEV_RX_REDIRECTS(in_dev) \ ((IN_DEV_FORWARD(in_dev) && \ IN_DEV_ANDCONF((in_dev), ACCEPT_REDIRECTS)) \ || (!IN_DEV_FORWARD(in_dev) && \ IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS))) #define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \ IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) #define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) #define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \ ARP_EVICT_NOCARRIER) struct in_ifaddr { struct hlist_node hash; struct in_ifaddr __rcu *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; __be32 ifa_local; __be32 ifa_address; __be32 ifa_mask; __u32 ifa_rt_priority; __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 ifa_valid_lft; __u32 ifa_preferred_lft; unsigned long ifa_cstamp; /* created timestamp */ unsigned long ifa_tstamp; /* updated timestamp */ }; struct in_validator_info { __be32 ivi_addr; struct in_device *ivi_dev; struct netlink_ext_ack *extack; }; int register_inetaddr_notifier(struct notifier_block *nb); int unregister_inetaddr_notifier(struct notifier_block *nb); int register_inetaddr_validator_notifier(struct notifier_block *nb); int unregister_inetaddr_validator_notifier(struct notifier_block *nb); void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf); struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref); static inline struct net_device *ip_dev_find(struct net *net, __be32 addr) { return __ip_dev_find(net, addr, true); } int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *); #ifdef CONFIG_INET int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size); #else static inline int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { return 0; } #endif void devinet_init(void); struct in_device *inetdev_by_index(struct net *, int); __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr); static inline bool inet_ifa_match(__be32 addr, const struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } /* * Check if a mask is acceptable. */ static __inline__ bool bad_mask(__be32 mask, __be32 addr) { __u32 hmask; if (addr & (mask = ~mask)) return true; hmask = ntohl(mask); if (hmask & (hmask+1)) return true; return false; } #define in_dev_for_each_ifa_rtnl(ifa, in_dev) \ for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \ ifa = rtnl_dereference(ifa->ifa_next)) #define in_dev_for_each_ifa_rcu(ifa, in_dev) \ for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \ ifa = rcu_dereference(ifa->ifa_next)) static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->ip_ptr); } static inline struct in_device *in_dev_get(const struct net_device *dev) { struct in_device *in_dev; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) refcount_inc(&in_dev->refcnt); rcu_read_unlock(); return in_dev; } static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->ip_ptr); } /* called with rcu_read_lock or rtnl held */ static inline bool ip_ignore_linkdown(const struct net_device *dev) { struct in_device *in_dev; bool rc = false; in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rc = true; return rc; } static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); return in_dev ? in_dev->arp_parms : NULL; } void in_dev_finish_destroy(struct in_device *idev); static inline void in_dev_put(struct in_device *idev) { if (refcount_dec_and_test(&idev->refcnt)) in_dev_finish_destroy(idev); } #define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) #define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) #endif /* __KERNEL__ */ static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) return htonl(~((1U<<(32-logmask))-1)); return 0; } static __inline__ int inet_mask_len(__be32 mask) { __u32 hmask = ntohl(mask); if (!hmask) return 0; return 32 - ffz(~hmask); } #endif /* _LINUX_INETDEVICE_H */ |
| 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 | /* * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/in.h> #include <linux/ipv6.h> #include "rds.h" #include "loop.h" static char * const rds_trans_modules[] = { [RDS_TRANS_IB] = "rds_rdma", [RDS_TRANS_GAP] = NULL, [RDS_TRANS_TCP] = "rds_tcp", }; static struct rds_transport *transports[RDS_TRANS_COUNT]; static DECLARE_RWSEM(rds_trans_sem); void rds_trans_register(struct rds_transport *trans) { BUG_ON(strlen(trans->t_name) + 1 > TRANSNAMSIZ); down_write(&rds_trans_sem); if (transports[trans->t_type]) printk(KERN_ERR "RDS Transport type %d already registered\n", trans->t_type); else { transports[trans->t_type] = trans; printk(KERN_INFO "Registered RDS/%s transport\n", trans->t_name); } up_write(&rds_trans_sem); } EXPORT_SYMBOL_GPL(rds_trans_register); void rds_trans_unregister(struct rds_transport *trans) { down_write(&rds_trans_sem); transports[trans->t_type] = NULL; printk(KERN_INFO "Unregistered RDS/%s transport\n", trans->t_name); up_write(&rds_trans_sem); } EXPORT_SYMBOL_GPL(rds_trans_unregister); void rds_trans_put(struct rds_transport *trans) { if (trans) module_put(trans->t_owner); } struct rds_transport *rds_trans_get_preferred(struct net *net, const struct in6_addr *addr, __u32 scope_id) { struct rds_transport *ret = NULL; struct rds_transport *trans; unsigned int i; if (ipv6_addr_v4mapped(addr)) { if (*(u_int8_t *)&addr->s6_addr32[3] == IN_LOOPBACKNET) return &rds_loop_transport; } else if (ipv6_addr_loopback(addr)) { return &rds_loop_transport; } down_read(&rds_trans_sem); for (i = 0; i < RDS_TRANS_COUNT; i++) { trans = transports[i]; if (trans && (trans->laddr_check(net, addr, scope_id) == 0) && (!trans->t_owner || try_module_get(trans->t_owner))) { ret = trans; break; } } up_read(&rds_trans_sem); return ret; } struct rds_transport *rds_trans_get(int t_type) { struct rds_transport *ret = NULL; struct rds_transport *trans; down_read(&rds_trans_sem); trans = transports[t_type]; if (!trans) { up_read(&rds_trans_sem); if (rds_trans_modules[t_type]) request_module(rds_trans_modules[t_type]); down_read(&rds_trans_sem); trans = transports[t_type]; } if (trans && trans->t_type == t_type && (!trans->t_owner || try_module_get(trans->t_owner))) ret = trans; up_read(&rds_trans_sem); return ret; } /* * This returns the number of stats entries in the snapshot and only * copies them using the iter if there is enough space for them. The * caller passes in the global stats so that we can size and copy while * holding the lock. */ unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter, unsigned int avail) { struct rds_transport *trans; unsigned int total = 0; unsigned int part; int i; rds_info_iter_unmap(iter); down_read(&rds_trans_sem); for (i = 0; i < RDS_TRANS_COUNT; i++) { trans = transports[i]; if (!trans || !trans->stats_info_copy) continue; part = trans->stats_info_copy(iter, avail); avail -= min(avail, part); total += part; } up_read(&rds_trans_sem); return total; } |
| 1 183 183 183 182 1 1 1 182 182 103 183 183 183 183 1 183 183 1 1 183 183 103 183 183 182 103 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 | #include <linux/export.h> #include <linux/generic-radix-tree.h> #include <linux/gfp.h> #include <linux/kmemleak.h> #define GENRADIX_ARY (PAGE_SIZE / sizeof(struct genradix_node *)) #define GENRADIX_ARY_SHIFT ilog2(GENRADIX_ARY) struct genradix_node { union { /* Interior node: */ struct genradix_node *children[GENRADIX_ARY]; /* Leaf: */ u8 data[PAGE_SIZE]; }; }; static inline int genradix_depth_shift(unsigned depth) { return PAGE_SHIFT + GENRADIX_ARY_SHIFT * depth; } /* * Returns size (of data, in bytes) that a tree of a given depth holds: */ static inline size_t genradix_depth_size(unsigned depth) { return 1UL << genradix_depth_shift(depth); } /* depth that's needed for a genradix that can address up to ULONG_MAX: */ #define GENRADIX_MAX_DEPTH \ DIV_ROUND_UP(BITS_PER_LONG - PAGE_SHIFT, GENRADIX_ARY_SHIFT) #define GENRADIX_DEPTH_MASK \ ((unsigned long) (roundup_pow_of_two(GENRADIX_MAX_DEPTH + 1) - 1)) static inline unsigned genradix_root_to_depth(struct genradix_root *r) { return (unsigned long) r & GENRADIX_DEPTH_MASK; } static inline struct genradix_node *genradix_root_to_node(struct genradix_root *r) { return (void *) ((unsigned long) r & ~GENRADIX_DEPTH_MASK); } /* * Returns pointer to the specified byte @offset within @radix, or NULL if not * allocated */ void *__genradix_ptr(struct __genradix *radix, size_t offset) { struct genradix_root *r = READ_ONCE(radix->root); struct genradix_node *n = genradix_root_to_node(r); unsigned level = genradix_root_to_depth(r); if (ilog2(offset) >= genradix_depth_shift(level)) return NULL; while (1) { if (!n) return NULL; if (!level) break; level--; n = n->children[offset >> genradix_depth_shift(level)]; offset &= genradix_depth_size(level) - 1; } return &n->data[offset]; } EXPORT_SYMBOL(__genradix_ptr); static inline struct genradix_node *genradix_alloc_node(gfp_t gfp_mask) { struct genradix_node *node; node = (struct genradix_node *)__get_free_page(gfp_mask|__GFP_ZERO); /* * We're using pages (not slab allocations) directly for kernel data * structures, so we need to explicitly inform kmemleak of them in order * to avoid false positive memory leak reports. */ kmemleak_alloc(node, PAGE_SIZE, 1, gfp_mask); return node; } static inline void genradix_free_node(struct genradix_node *node) { kmemleak_free(node); free_page((unsigned long)node); } /* * Returns pointer to the specified byte @offset within @radix, allocating it if * necessary - newly allocated slots are always zeroed out: */ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset, gfp_t gfp_mask) { struct genradix_root *v = READ_ONCE(radix->root); struct genradix_node *n, *new_node = NULL; unsigned level; /* Increase tree depth if necessary: */ while (1) { struct genradix_root *r = v, *new_root; n = genradix_root_to_node(r); level = genradix_root_to_depth(r); if (n && ilog2(offset) < genradix_depth_shift(level)) break; if (!new_node) { new_node = genradix_alloc_node(gfp_mask); if (!new_node) return NULL; } new_node->children[0] = n; new_root = ((struct genradix_root *) ((unsigned long) new_node | (n ? level + 1 : 0))); if ((v = cmpxchg_release(&radix->root, r, new_root)) == r) { v = new_root; new_node = NULL; } } while (level--) { struct genradix_node **p = &n->children[offset >> genradix_depth_shift(level)]; offset &= genradix_depth_size(level) - 1; n = READ_ONCE(*p); if (!n) { if (!new_node) { new_node = genradix_alloc_node(gfp_mask); if (!new_node) return NULL; } if (!(n = cmpxchg_release(p, NULL, new_node))) swap(n, new_node); } } if (new_node) genradix_free_node(new_node); return &n->data[offset]; } EXPORT_SYMBOL(__genradix_ptr_alloc); void *__genradix_iter_peek(struct genradix_iter *iter, struct __genradix *radix, size_t objs_per_page) { struct genradix_root *r; struct genradix_node *n; unsigned level, i; restart: r = READ_ONCE(radix->root); if (!r) return NULL; n = genradix_root_to_node(r); level = genradix_root_to_depth(r); if (ilog2(iter->offset) >= genradix_depth_shift(level)) return NULL; while (level) { level--; i = (iter->offset >> genradix_depth_shift(level)) & (GENRADIX_ARY - 1); while (!n->children[i]) { i++; iter->offset = round_down(iter->offset + genradix_depth_size(level), genradix_depth_size(level)); iter->pos = (iter->offset >> PAGE_SHIFT) * objs_per_page; if (i == GENRADIX_ARY) goto restart; } n = n->children[i]; } return &n->data[iter->offset & (PAGE_SIZE - 1)]; } EXPORT_SYMBOL(__genradix_iter_peek); static void genradix_free_recurse(struct genradix_node *n, unsigned level) { if (level) { unsigned i; for (i = 0; i < GENRADIX_ARY; i++) if (n->children[i]) genradix_free_recurse(n->children[i], level - 1); } genradix_free_node(n); } int __genradix_prealloc(struct __genradix *radix, size_t size, gfp_t gfp_mask) { size_t offset; for (offset = 0; offset < size; offset += PAGE_SIZE) if (!__genradix_ptr_alloc(radix, offset, gfp_mask)) return -ENOMEM; return 0; } EXPORT_SYMBOL(__genradix_prealloc); void __genradix_free(struct __genradix *radix) { struct genradix_root *r = xchg(&radix->root, NULL); genradix_free_recurse(genradix_root_to_node(r), genradix_root_to_depth(r)); } EXPORT_SYMBOL(__genradix_free); |
| 2672 2671 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2007-2012 Nicira, Inc. */ #include <linux/netdevice.h> #include <net/genetlink.h> #include <net/netns/generic.h> #include "datapath.h" #include "vport-internal_dev.h" #include "vport-netdev.h" static void dp_detach_port_notify(struct vport *vport) { struct sk_buff *notify; struct datapath *dp; dp = vport->dp; notify = ovs_vport_cmd_build_info(vport, ovs_dp_get_net(dp), 0, 0, OVS_VPORT_CMD_DEL); ovs_dp_detach_port(vport); if (IS_ERR(notify)) { genl_set_err(&dp_vport_genl_family, ovs_dp_get_net(dp), 0, 0, PTR_ERR(notify)); return; } genlmsg_multicast_netns(&dp_vport_genl_family, ovs_dp_get_net(dp), notify, 0, 0, GFP_KERNEL); } void ovs_dp_notify_wq(struct work_struct *work) { struct ovs_net *ovs_net = container_of(work, struct ovs_net, dp_notify_work); struct datapath *dp; ovs_lock(); list_for_each_entry(dp, &ovs_net->dps, list_node) { int i; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { struct vport *vport; struct hlist_node *n; hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) { if (vport->ops->type == OVS_VPORT_TYPE_INTERNAL) continue; if (!(netif_is_ovs_port(vport->dev))) dp_detach_port_notify(vport); } } } ovs_unlock(); } static int dp_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct ovs_net *ovs_net; struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vport *vport = NULL; if (!ovs_is_internal_dev(dev)) vport = ovs_netdev_get_vport(dev); if (!vport) return NOTIFY_DONE; if (event == NETDEV_UNREGISTER) { /* upper_dev_unlink and decrement promisc immediately */ ovs_netdev_detach_dev(vport); /* schedule vport destroy, dev_put and genl notification */ ovs_net = net_generic(dev_net(dev), ovs_net_id); queue_work(system_wq, &ovs_net->dp_notify_work); } return NOTIFY_DONE; } struct notifier_block ovs_dp_device_notifier = { .notifier_call = dp_device_event }; |
| 1548 1544 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 | /* Netfilter messages via netlink socket. Allows for user space * protocol helpers and general trouble making from userspace. * * (C) 2001 by Jay Schulist <jschlst@samba.org>, * (C) 2002-2005 by Harald Welte <laforge@gnumonks.org> * (C) 2005-2017 by Pablo Neira Ayuso <pablo@netfilter.org> * * Initial netfilter messages via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) * * Further development of this code funded by Astaro AG (http://www.astaro.com) * * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. */ #include <linux/module.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/uaccess.h> #include <net/sock.h> #include <linux/init.h> #include <linux/sched/signal.h> #include <net/netlink.h> #include <net/netns/generic.h> #include <linux/netfilter/nfnetlink.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NETFILTER); MODULE_DESCRIPTION("Netfilter messages via netlink socket"); #define nfnl_dereference_protected(id) \ rcu_dereference_protected(table[(id)].subsys, \ lockdep_nfnl_is_held((id))) #define NFNL_MAX_ATTR_COUNT 32 static unsigned int nfnetlink_pernet_id __read_mostly; #ifdef CONFIG_NF_CONNTRACK_EVENTS static DEFINE_SPINLOCK(nfnl_grp_active_lock); #endif struct nfnl_net { struct sock *nfnl; }; static struct { struct mutex mutex; const struct nfnetlink_subsystem __rcu *subsys; } table[NFNL_SUBSYS_COUNT]; static struct lock_class_key nfnl_lockdep_keys[NFNL_SUBSYS_COUNT]; static const char *const nfnl_lockdep_names[NFNL_SUBSYS_COUNT] = { [NFNL_SUBSYS_NONE] = "nfnl_subsys_none", [NFNL_SUBSYS_CTNETLINK] = "nfnl_subsys_ctnetlink", [NFNL_SUBSYS_CTNETLINK_EXP] = "nfnl_subsys_ctnetlink_exp", [NFNL_SUBSYS_QUEUE] = "nfnl_subsys_queue", [NFNL_SUBSYS_ULOG] = "nfnl_subsys_ulog", [NFNL_SUBSYS_OSF] = "nfnl_subsys_osf", [NFNL_SUBSYS_IPSET] = "nfnl_subsys_ipset", [NFNL_SUBSYS_ACCT] = "nfnl_subsys_acct", [NFNL_SUBSYS_CTNETLINK_TIMEOUT] = "nfnl_subsys_cttimeout", [NFNL_SUBSYS_CTHELPER] = "nfnl_subsys_cthelper", [NFNL_SUBSYS_NFTABLES] = "nfnl_subsys_nftables", [NFNL_SUBSYS_NFT_COMPAT] = "nfnl_subsys_nftcompat", [NFNL_SUBSYS_HOOK] = "nfnl_subsys_hook", }; static const int nfnl_group2type[NFNLGRP_MAX+1] = { [NFNLGRP_CONNTRACK_NEW] = NFNL_SUBSYS_CTNETLINK, [NFNLGRP_CONNTRACK_UPDATE] = NFNL_SUBSYS_CTNETLINK, [NFNLGRP_CONNTRACK_DESTROY] = NFNL_SUBSYS_CTNETLINK, [NFNLGRP_CONNTRACK_EXP_NEW] = NFNL_SUBSYS_CTNETLINK_EXP, [NFNLGRP_CONNTRACK_EXP_UPDATE] = NFNL_SUBSYS_CTNETLINK_EXP, [NFNLGRP_CONNTRACK_EXP_DESTROY] = NFNL_SUBSYS_CTNETLINK_EXP, [NFNLGRP_NFTABLES] = NFNL_SUBSYS_NFTABLES, [NFNLGRP_ACCT_QUOTA] = NFNL_SUBSYS_ACCT, [NFNLGRP_NFTRACE] = NFNL_SUBSYS_NFTABLES, }; static struct nfnl_net *nfnl_pernet(struct net *net) { return net_generic(net, nfnetlink_pernet_id); } void nfnl_lock(__u8 subsys_id) { mutex_lock(&table[subsys_id].mutex); } EXPORT_SYMBOL_GPL(nfnl_lock); void nfnl_unlock(__u8 subsys_id) { mutex_unlock(&table[subsys_id].mutex); } EXPORT_SYMBOL_GPL(nfnl_unlock); #ifdef CONFIG_PROVE_LOCKING bool lockdep_nfnl_is_held(u8 subsys_id) { return lockdep_is_held(&table[subsys_id].mutex); } EXPORT_SYMBOL_GPL(lockdep_nfnl_is_held); #endif int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n) { u8 cb_id; /* Sanity-check attr_count size to avoid stack buffer overflow. */ for (cb_id = 0; cb_id < n->cb_count; cb_id++) if (WARN_ON(n->cb[cb_id].attr_count > NFNL_MAX_ATTR_COUNT)) return -EINVAL; nfnl_lock(n->subsys_id); if (table[n->subsys_id].subsys) { nfnl_unlock(n->subsys_id); return -EBUSY; } rcu_assign_pointer(table[n->subsys_id].subsys, n); nfnl_unlock(n->subsys_id); return 0; } EXPORT_SYMBOL_GPL(nfnetlink_subsys_register); int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n) { nfnl_lock(n->subsys_id); table[n->subsys_id].subsys = NULL; nfnl_unlock(n->subsys_id); synchronize_rcu(); return 0; } EXPORT_SYMBOL_GPL(nfnetlink_subsys_unregister); static inline const struct nfnetlink_subsystem *nfnetlink_get_subsys(u16 type) { u8 subsys_id = NFNL_SUBSYS_ID(type); if (subsys_id >= NFNL_SUBSYS_COUNT) return NULL; return rcu_dereference(table[subsys_id].subsys); } static inline const struct nfnl_callback * nfnetlink_find_client(u16 type, const struct nfnetlink_subsystem *ss) { u8 cb_id = NFNL_MSG_TYPE(type); if (cb_id >= ss->cb_count) return NULL; return &ss->cb[cb_id]; } int nfnetlink_has_listeners(struct net *net, unsigned int group) { struct nfnl_net *nfnlnet = nfnl_pernet(net); return netlink_has_listeners(nfnlnet->nfnl, group); } EXPORT_SYMBOL_GPL(nfnetlink_has_listeners); int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags) { struct nfnl_net *nfnlnet = nfnl_pernet(net); return nlmsg_notify(nfnlnet->nfnl, skb, portid, group, echo, flags); } EXPORT_SYMBOL_GPL(nfnetlink_send); int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error) { struct nfnl_net *nfnlnet = nfnl_pernet(net); return netlink_set_err(nfnlnet->nfnl, portid, group, error); } EXPORT_SYMBOL_GPL(nfnetlink_set_err); int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid) { struct nfnl_net *nfnlnet = nfnl_pernet(net); int err; err = nlmsg_unicast(nfnlnet->nfnl, skb, portid); if (err == -EAGAIN) err = -ENOBUFS; return err; } EXPORT_SYMBOL_GPL(nfnetlink_unicast); void nfnetlink_broadcast(struct net *net, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation) { struct nfnl_net *nfnlnet = nfnl_pernet(net); netlink_broadcast(nfnlnet->nfnl, skb, portid, group, allocation); } EXPORT_SYMBOL_GPL(nfnetlink_broadcast); /* Process one complete nfnetlink message. */ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); const struct nfnl_callback *nc; const struct nfnetlink_subsystem *ss; int type, err; /* All the messages must at least contain nfgenmsg */ if (nlmsg_len(nlh) < sizeof(struct nfgenmsg)) return 0; type = nlh->nlmsg_type; replay: rcu_read_lock(); ss = nfnetlink_get_subsys(type); if (!ss) { #ifdef CONFIG_MODULES rcu_read_unlock(); request_module("nfnetlink-subsys-%d", NFNL_SUBSYS_ID(type)); rcu_read_lock(); ss = nfnetlink_get_subsys(type); if (!ss) #endif { rcu_read_unlock(); return -EINVAL; } } nc = nfnetlink_find_client(type, ss); if (!nc) { rcu_read_unlock(); return -EINVAL; } { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); struct nfnl_net *nfnlnet = nfnl_pernet(net); u8 cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); struct nlattr *cda[NFNL_MAX_ATTR_COUNT + 1]; struct nlattr *attr = (void *)nlh + min_len; int attrlen = nlh->nlmsg_len - min_len; __u8 subsys_id = NFNL_SUBSYS_ID(type); struct nfnl_info info = { .net = net, .sk = nfnlnet->nfnl, .nlh = nlh, .nfmsg = nlmsg_data(nlh), .extack = extack, }; /* Sanity-check NFNL_MAX_ATTR_COUNT */ if (ss->cb[cb_id].attr_count > NFNL_MAX_ATTR_COUNT) { rcu_read_unlock(); return -ENOMEM; } err = nla_parse_deprecated(cda, ss->cb[cb_id].attr_count, attr, attrlen, ss->cb[cb_id].policy, extack); if (err < 0) { rcu_read_unlock(); return err; } if (!nc->call) { rcu_read_unlock(); return -EINVAL; } switch (nc->type) { case NFNL_CB_RCU: err = nc->call(skb, &info, (const struct nlattr **)cda); rcu_read_unlock(); break; case NFNL_CB_MUTEX: rcu_read_unlock(); nfnl_lock(subsys_id); if (nfnl_dereference_protected(subsys_id) != ss || nfnetlink_find_client(type, ss) != nc) { nfnl_unlock(subsys_id); err = -EAGAIN; break; } err = nc->call(skb, &info, (const struct nlattr **)cda); nfnl_unlock(subsys_id); break; default: rcu_read_unlock(); err = -EINVAL; break; } if (err == -EAGAIN) goto replay; return err; } } struct nfnl_err { struct list_head head; struct nlmsghdr *nlh; int err; struct netlink_ext_ack extack; }; static int nfnl_err_add(struct list_head *list, struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack) { struct nfnl_err *nfnl_err; nfnl_err = kmalloc(sizeof(struct nfnl_err), GFP_KERNEL); if (nfnl_err == NULL) return -ENOMEM; nfnl_err->nlh = nlh; nfnl_err->err = err; nfnl_err->extack = *extack; list_add_tail(&nfnl_err->head, list); return 0; } static void nfnl_err_del(struct nfnl_err *nfnl_err) { list_del(&nfnl_err->head); kfree(nfnl_err); } static void nfnl_err_reset(struct list_head *err_list) { struct nfnl_err *nfnl_err, *next; list_for_each_entry_safe(nfnl_err, next, err_list, head) nfnl_err_del(nfnl_err); } static void nfnl_err_deliver(struct list_head *err_list, struct sk_buff *skb) { struct nfnl_err *nfnl_err, *next; list_for_each_entry_safe(nfnl_err, next, err_list, head) { netlink_ack(skb, nfnl_err->nlh, nfnl_err->err, &nfnl_err->extack); nfnl_err_del(nfnl_err); } } enum { NFNL_BATCH_FAILURE = (1 << 0), NFNL_BATCH_DONE = (1 << 1), NFNL_BATCH_REPLAY = (1 << 2), }; static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, u16 subsys_id, u32 genid) { struct sk_buff *oskb = skb; struct net *net = sock_net(skb->sk); const struct nfnetlink_subsystem *ss; const struct nfnl_callback *nc; struct netlink_ext_ack extack; LIST_HEAD(err_list); u32 status; int err; if (subsys_id >= NFNL_SUBSYS_COUNT) return netlink_ack(skb, nlh, -EINVAL, NULL); replay: status = 0; replay_abort: skb = netlink_skb_clone(oskb, GFP_KERNEL); if (!skb) return netlink_ack(oskb, nlh, -ENOMEM, NULL); nfnl_lock(subsys_id); ss = nfnl_dereference_protected(subsys_id); if (!ss) { #ifdef CONFIG_MODULES nfnl_unlock(subsys_id); request_module("nfnetlink-subsys-%d", subsys_id); nfnl_lock(subsys_id); ss = nfnl_dereference_protected(subsys_id); if (!ss) #endif { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); return kfree_skb(skb); } } if (!ss->valid_genid || !ss->commit || !ss->abort) { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); return kfree_skb(skb); } if (!try_module_get(ss->owner)) { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); return kfree_skb(skb); } if (!ss->valid_genid(net, genid)) { module_put(ss->owner); nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -ERESTART, NULL); return kfree_skb(skb); } nfnl_unlock(subsys_id); while (skb->len >= nlmsg_total_size(0)) { int msglen, type; if (fatal_signal_pending(current)) { nfnl_err_reset(&err_list); err = -EINTR; status = NFNL_BATCH_FAILURE; goto done; } memset(&extack, 0, sizeof(extack)); nlh = nlmsg_hdr(skb); err = 0; if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len || nlmsg_len(nlh) < sizeof(struct nfgenmsg)) { nfnl_err_reset(&err_list); status |= NFNL_BATCH_FAILURE; goto done; } /* Only requests are handled by the kernel */ if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) { err = -EINVAL; goto ack; } type = nlh->nlmsg_type; if (type == NFNL_MSG_BATCH_BEGIN) { /* Malformed: Batch begin twice */ nfnl_err_reset(&err_list); status |= NFNL_BATCH_FAILURE; goto done; } else if (type == NFNL_MSG_BATCH_END) { status |= NFNL_BATCH_DONE; goto done; } else if (type < NLMSG_MIN_TYPE) { err = -EINVAL; goto ack; } /* We only accept a batch with messages for the same * subsystem. */ if (NFNL_SUBSYS_ID(type) != subsys_id) { err = -EINVAL; goto ack; } nc = nfnetlink_find_client(type, ss); if (!nc) { err = -EINVAL; goto ack; } if (nc->type != NFNL_CB_BATCH) { err = -EINVAL; goto ack; } { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); struct nfnl_net *nfnlnet = nfnl_pernet(net); struct nlattr *cda[NFNL_MAX_ATTR_COUNT + 1]; struct nlattr *attr = (void *)nlh + min_len; u8 cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); int attrlen = nlh->nlmsg_len - min_len; struct nfnl_info info = { .net = net, .sk = nfnlnet->nfnl, .nlh = nlh, .nfmsg = nlmsg_data(nlh), .extack = &extack, }; /* Sanity-check NFTA_MAX_ATTR */ if (ss->cb[cb_id].attr_count > NFNL_MAX_ATTR_COUNT) { err = -ENOMEM; goto ack; } err = nla_parse_deprecated(cda, ss->cb[cb_id].attr_count, attr, attrlen, ss->cb[cb_id].policy, NULL); if (err < 0) goto ack; err = nc->call(skb, &info, (const struct nlattr **)cda); /* The lock was released to autoload some module, we * have to abort and start from scratch using the * original skb. */ if (err == -EAGAIN) { status |= NFNL_BATCH_REPLAY; goto done; } } ack: if (nlh->nlmsg_flags & NLM_F_ACK || err) { /* Errors are delivered once the full batch has been * processed, this avoids that the same error is * reported several times when replaying the batch. */ if (nfnl_err_add(&err_list, nlh, err, &extack) < 0) { /* We failed to enqueue an error, reset the * list of errors and send OOM to userspace * pointing to the batch header. */ nfnl_err_reset(&err_list); netlink_ack(oskb, nlmsg_hdr(oskb), -ENOMEM, NULL); status |= NFNL_BATCH_FAILURE; goto done; } /* We don't stop processing the batch on errors, thus, * userspace gets all the errors that the batch * triggers. */ if (err) status |= NFNL_BATCH_FAILURE; } msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; skb_pull(skb, msglen); } done: if (status & NFNL_BATCH_REPLAY) { ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD); nfnl_err_reset(&err_list); kfree_skb(skb); module_put(ss->owner); goto replay; } else if (status == NFNL_BATCH_DONE) { err = ss->commit(net, oskb); if (err == -EAGAIN) { status |= NFNL_BATCH_REPLAY; goto done; } else if (err) { ss->abort(net, oskb, NFNL_ABORT_NONE); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } } else { enum nfnl_abort_action abort_action; if (status & NFNL_BATCH_FAILURE) abort_action = NFNL_ABORT_NONE; else abort_action = NFNL_ABORT_VALIDATE; err = ss->abort(net, oskb, abort_action); if (err == -EAGAIN) { nfnl_err_reset(&err_list); kfree_skb(skb); module_put(ss->owner); status |= NFNL_BATCH_FAILURE; goto replay_abort; } } if (ss->cleanup) ss->cleanup(net); nfnl_err_deliver(&err_list, oskb); kfree_skb(skb); module_put(ss->owner); } static const struct nla_policy nfnl_batch_policy[NFNL_BATCH_MAX + 1] = { [NFNL_BATCH_GENID] = { .type = NLA_U32 }, }; static void nfnetlink_rcv_skb_batch(struct sk_buff *skb, struct nlmsghdr *nlh) { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); struct nlattr *attr = (void *)nlh + min_len; struct nlattr *cda[NFNL_BATCH_MAX + 1]; int attrlen = nlh->nlmsg_len - min_len; struct nfgenmsg *nfgenmsg; int msglen, err; u32 gen_id = 0; u16 res_id; msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; if (skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg)) return; err = nla_parse_deprecated(cda, NFNL_BATCH_MAX, attr, attrlen, nfnl_batch_policy, NULL); if (err < 0) { netlink_ack(skb, nlh, err, NULL); return; } if (cda[NFNL_BATCH_GENID]) gen_id = ntohl(nla_get_be32(cda[NFNL_BATCH_GENID])); nfgenmsg = nlmsg_data(nlh); skb_pull(skb, msglen); /* Work around old nft using host byte order */ if (nfgenmsg->res_id == (__force __be16)NFNL_SUBSYS_NFTABLES) res_id = NFNL_SUBSYS_NFTABLES; else res_id = ntohs(nfgenmsg->res_id); nfnetlink_rcv_batch(skb, nlh, res_id, gen_id); } static void nfnetlink_rcv(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); if (skb->len < NLMSG_HDRLEN || nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) return; if (!netlink_net_capable(skb, CAP_NET_ADMIN)) { netlink_ack(skb, nlh, -EPERM, NULL); return; } if (nlh->nlmsg_type == NFNL_MSG_BATCH_BEGIN) nfnetlink_rcv_skb_batch(skb, nlh); else netlink_rcv_skb(skb, nfnetlink_rcv_msg); } static void nfnetlink_bind_event(struct net *net, unsigned int group) { #ifdef CONFIG_NF_CONNTRACK_EVENTS int type, group_bit; u8 v; /* All NFNLGRP_CONNTRACK_* group bits fit into u8. * The other groups are not relevant and can be ignored. */ if (group >= 8) return; type = nfnl_group2type[group]; switch (type) { case NFNL_SUBSYS_CTNETLINK: break; case NFNL_SUBSYS_CTNETLINK_EXP: break; default: return; } group_bit = (1 << group); spin_lock(&nfnl_grp_active_lock); v = READ_ONCE(net->ct.ctnetlink_has_listener); if ((v & group_bit) == 0) { v |= group_bit; /* read concurrently without nfnl_grp_active_lock held. */ WRITE_ONCE(net->ct.ctnetlink_has_listener, v); } spin_unlock(&nfnl_grp_active_lock); #endif } static int nfnetlink_bind(struct net *net, int group) { const struct nfnetlink_subsystem *ss; int type; if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX) return 0; type = nfnl_group2type[group]; rcu_read_lock(); ss = nfnetlink_get_subsys(type << 8); rcu_read_unlock(); if (!ss) request_module_nowait("nfnetlink-subsys-%d", type); nfnetlink_bind_event(net, group); return 0; } static void nfnetlink_unbind(struct net *net, int group) { #ifdef CONFIG_NF_CONNTRACK_EVENTS int type, group_bit; if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX) return; type = nfnl_group2type[group]; switch (type) { case NFNL_SUBSYS_CTNETLINK: break; case NFNL_SUBSYS_CTNETLINK_EXP: break; default: return; } /* ctnetlink_has_listener is u8 */ if (group >= 8) return; group_bit = (1 << group); spin_lock(&nfnl_grp_active_lock); if (!nfnetlink_has_listeners(net, group)) { u8 v = READ_ONCE(net->ct.ctnetlink_has_listener); v &= ~group_bit; /* read concurrently without nfnl_grp_active_lock held. */ WRITE_ONCE(net->ct.ctnetlink_has_listener, v); } spin_unlock(&nfnl_grp_active_lock); #endif } static int __net_init nfnetlink_net_init(struct net *net) { struct nfnl_net *nfnlnet = nfnl_pernet(net); struct netlink_kernel_cfg cfg = { .groups = NFNLGRP_MAX, .input = nfnetlink_rcv, .bind = nfnetlink_bind, .unbind = nfnetlink_unbind, }; nfnlnet->nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, &cfg); if (!nfnlnet->nfnl) return -ENOMEM; return 0; } static void __net_exit nfnetlink_net_exit_batch(struct list_head *net_exit_list) { struct nfnl_net *nfnlnet; struct net *net; list_for_each_entry(net, net_exit_list, exit_list) { nfnlnet = nfnl_pernet(net); netlink_kernel_release(nfnlnet->nfnl); } } static struct pernet_operations nfnetlink_net_ops = { .init = nfnetlink_net_init, .exit_batch = nfnetlink_net_exit_batch, .id = &nfnetlink_pernet_id, .size = sizeof(struct nfnl_net), }; static int __init nfnetlink_init(void) { int i; for (i = NFNLGRP_NONE + 1; i <= NFNLGRP_MAX; i++) BUG_ON(nfnl_group2type[i] == NFNL_SUBSYS_NONE); for (i=0; i<NFNL_SUBSYS_COUNT; i++) __mutex_init(&table[i].mutex, nfnl_lockdep_names[i], &nfnl_lockdep_keys[i]); return register_pernet_subsys(&nfnetlink_net_ops); } static void __exit nfnetlink_exit(void) { unregister_pernet_subsys(&nfnetlink_net_ops); } module_init(nfnetlink_init); module_exit(nfnetlink_exit); |
| 293 293 293 293 293 30 293 293 293 293 126 293 103 103 102 102 102 103 103 292 293 102 102 102 92 92 92 21 103 102 103 103 30 30 29 2 30 30 293 293 293 293 293 293 293 292 103 103 103 293 293 293 103 293 293 293 292 284 285 293 293 293 293 293 293 293 103 293 293 293 292 293 293 293 292 293 293 293 293 293 30 102 293 293 293 293 104 292 104 292 293 293 293 293 103 293 293 293 293 293 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 | // SPDX-License-Identifier: GPL-2.0 /* * Generic ring buffer * * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com> */ #include <linux/trace_recursion.h> #include <linux/trace_events.h> #include <linux/ring_buffer.h> #include <linux/trace_clock.h> #include <linux/sched/clock.h> #include <linux/trace_seq.h> #include <linux/spinlock.h> #include <linux/irq_work.h> #include <linux/security.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include <linux/kthread.h> /* for self test */ #include <linux/module.h> #include <linux/percpu.h> #include <linux/mutex.h> #include <linux/delay.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/list.h> #include <linux/cpu.h> #include <linux/oom.h> #include <asm/local.h> /* * The "absolute" timestamp in the buffer is only 59 bits. * If a clock has the 5 MSBs set, it needs to be saved and * reinserted. */ #define TS_MSB (0xf8ULL << 56) #define ABS_TS_MASK (~TS_MSB) static void update_pages_handler(struct work_struct *work); /* * The ring buffer header is special. We must manually up keep it. */ int ring_buffer_print_entry_header(struct trace_seq *s) { trace_seq_puts(s, "# compressed entry header\n"); trace_seq_puts(s, "\ttype_len : 5 bits\n"); trace_seq_puts(s, "\ttime_delta : 27 bits\n"); trace_seq_puts(s, "\tarray : 32 bits\n"); trace_seq_putc(s, '\n'); trace_seq_printf(s, "\tpadding : type == %d\n", RINGBUF_TYPE_PADDING); trace_seq_printf(s, "\ttime_extend : type == %d\n", RINGBUF_TYPE_TIME_EXTEND); trace_seq_printf(s, "\ttime_stamp : type == %d\n", RINGBUF_TYPE_TIME_STAMP); trace_seq_printf(s, "\tdata max type_len == %d\n", RINGBUF_TYPE_DATA_TYPE_LEN_MAX); return !trace_seq_has_overflowed(s); } /* * The ring buffer is made up of a list of pages. A separate list of pages is * allocated for each CPU. A writer may only write to a buffer that is * associated with the CPU it is currently executing on. A reader may read * from any per cpu buffer. * * The reader is special. For each per cpu buffer, the reader has its own * reader page. When a reader has read the entire reader page, this reader * page is swapped with another page in the ring buffer. * * Now, as long as the writer is off the reader page, the reader can do what * ever it wants with that page. The writer will never write to that page * again (as long as it is out of the ring buffer). * * Here's some silly ASCII art. * * +------+ * |reader| RING BUFFER * |page | * +------+ +---+ +---+ +---+ * | |-->| |-->| | * +---+ +---+ +---+ * ^ | * | | * +---------------+ * * * +------+ * |reader| RING BUFFER * |page |------------------v * +------+ +---+ +---+ +---+ * | |-->| |-->| | * +---+ +---+ +---+ * ^ | * | | * +---------------+ * * * +------+ * |reader| RING BUFFER * |page |------------------v * +------+ +---+ +---+ +---+ * ^ | |-->| |-->| | * | +---+ +---+ +---+ * | | * | | * +------------------------------+ * * * +------+ * |buffer| RING BUFFER * |page |------------------v * +------+ +---+ +---+ +---+ * ^ | | | |-->| | * | New +---+ +---+ +---+ * | Reader------^ | * | page | * +------------------------------+ * * * After we make this swap, the reader can hand this page off to the splice * code and be done with it. It can even allocate a new page if it needs to * and swap that into the ring buffer. * * We will be using cmpxchg soon to make all this lockless. * */ /* Used for individual buffers (after the counter) */ #define RB_BUFFER_OFF (1 << 20) #define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data) #define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array)) #define RB_ALIGNMENT 4U #define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX) #define RB_EVNT_MIN_SIZE 8U /* two 32bit words */ #ifndef CONFIG_HAVE_64BIT_ALIGNED_ACCESS # define RB_FORCE_8BYTE_ALIGNMENT 0 # define RB_ARCH_ALIGNMENT RB_ALIGNMENT #else # define RB_FORCE_8BYTE_ALIGNMENT 1 # define RB_ARCH_ALIGNMENT 8U #endif #define RB_ALIGN_DATA __aligned(RB_ARCH_ALIGNMENT) /* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */ #define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX enum { RB_LEN_TIME_EXTEND = 8, RB_LEN_TIME_STAMP = 8, }; #define skip_time_extend(event) \ ((struct ring_buffer_event *)((char *)event + RB_LEN_TIME_EXTEND)) #define extended_time(event) \ (event->type_len >= RINGBUF_TYPE_TIME_EXTEND) static inline int rb_null_event(struct ring_buffer_event *event) { return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta; } static void rb_event_set_padding(struct ring_buffer_event *event) { /* padding has a NULL time_delta */ event->type_len = RINGBUF_TYPE_PADDING; event->time_delta = 0; } static unsigned rb_event_data_length(struct ring_buffer_event *event) { unsigned length; if (event->type_len) length = event->type_len * RB_ALIGNMENT; else length = event->array[0]; return length + RB_EVNT_HDR_SIZE; } /* * Return the length of the given event. Will return * the length of the time extend if the event is a * time extend. */ static inline unsigned rb_event_length(struct ring_buffer_event *event) { switch (event->type_len) { case RINGBUF_TYPE_PADDING: if (rb_null_event(event)) /* undefined */ return -1; return event->array[0] + RB_EVNT_HDR_SIZE; case RINGBUF_TYPE_TIME_EXTEND: return RB_LEN_TIME_EXTEND; case RINGBUF_TYPE_TIME_STAMP: return RB_LEN_TIME_STAMP; case RINGBUF_TYPE_DATA: return rb_event_data_length(event); default: WARN_ON_ONCE(1); } /* not hit */ return 0; } /* * Return total length of time extend and data, * or just the event length for all other events. */ static inline unsigned rb_event_ts_length(struct ring_buffer_event *event) { unsigned len = 0; if (extended_time(event)) { /* time extends include the data event after it */ len = RB_LEN_TIME_EXTEND; event = skip_time_extend(event); } return len + rb_event_length(event); } /** * ring_buffer_event_length - return the length of the event * @event: the event to get the length of * * Returns the size of the data load of a data event. * If the event is something other than a data event, it * returns the size of the event itself. With the exception * of a TIME EXTEND, where it still returns the size of the * data load of the data event after it. */ unsigned ring_buffer_event_length(struct ring_buffer_event *event) { unsigned length; if (extended_time(event)) event = skip_time_extend(event); length = rb_event_length(event); if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX) return length; length -= RB_EVNT_HDR_SIZE; if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0])) length -= sizeof(event->array[0]); return length; } EXPORT_SYMBOL_GPL(ring_buffer_event_length); /* inline for ring buffer fast paths */ static __always_inline void * rb_event_data(struct ring_buffer_event *event) { if (extended_time(event)) event = skip_time_extend(event); WARN_ON_ONCE(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX); /* If length is in len field, then array[0] has the data */ if (event->type_len) return (void *)&event->array[0]; /* Otherwise length is in array[0] and array[1] has the data */ return (void *)&event->array[1]; } /** * ring_buffer_event_data - return the data of the event * @event: the event to get the data from */ void *ring_buffer_event_data(struct ring_buffer_event *event) { return rb_event_data(event); } EXPORT_SYMBOL_GPL(ring_buffer_event_data); #define for_each_buffer_cpu(buffer, cpu) \ for_each_cpu(cpu, buffer->cpumask) #define for_each_online_buffer_cpu(buffer, cpu) \ for_each_cpu_and(cpu, buffer->cpumask, cpu_online_mask) #define TS_SHIFT 27 #define TS_MASK ((1ULL << TS_SHIFT) - 1) #define TS_DELTA_TEST (~TS_MASK) static u64 rb_event_time_stamp(struct ring_buffer_event *event) { u64 ts; ts = event->array[0]; ts <<= TS_SHIFT; ts += event->time_delta; return ts; } /* Flag when events were overwritten */ #define RB_MISSED_EVENTS (1 << 31) /* Missed count stored at end */ #define RB_MISSED_STORED (1 << 30) struct buffer_data_page { u64 time_stamp; /* page time stamp */ local_t commit; /* write committed index */ unsigned char data[] RB_ALIGN_DATA; /* data of buffer page */ }; /* * Note, the buffer_page list must be first. The buffer pages * are allocated in cache lines, which means that each buffer * page will be at the beginning of a cache line, and thus * the least significant bits will be zero. We use this to * add flags in the list struct pointers, to make the ring buffer * lockless. */ struct buffer_page { struct list_head list; /* list of buffer pages */ local_t write; /* index for next write */ unsigned read; /* index for next read */ local_t entries; /* entries on this page */ unsigned long real_end; /* real end of data */ struct buffer_data_page *page; /* Actual data page */ }; /* * The buffer page counters, write and entries, must be reset * atomically when crossing page boundaries. To synchronize this * update, two counters are inserted into the number. One is * the actual counter for the write position or count on the page. * * The other is a counter of updaters. Before an update happens * the update partition of the counter is incremented. This will * allow the updater to update the counter atomically. * * The counter is 20 bits, and the state data is 12. */ #define RB_WRITE_MASK 0xfffff #define RB_WRITE_INTCNT (1 << 20) static void rb_init_page(struct buffer_data_page *bpage) { local_set(&bpage->commit, 0); } /* * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing * this issue out. */ static void free_buffer_page(struct buffer_page *bpage) { free_page((unsigned long)bpage->page); kfree(bpage); } /* * We need to fit the time_stamp delta into 27 bits. */ static inline int test_time_stamp(u64 delta) { if (delta & TS_DELTA_TEST) return 1; return 0; } #define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE) /* Max payload is BUF_PAGE_SIZE - header (8bytes) */ #define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2)) int ring_buffer_print_page_header(struct trace_seq *s) { struct buffer_data_page field; trace_seq_printf(s, "\tfield: u64 timestamp;\t" "offset:0;\tsize:%u;\tsigned:%u;\n", (unsigned int)sizeof(field.time_stamp), (unsigned int)is_signed_type(u64)); trace_seq_printf(s, "\tfield: local_t commit;\t" "offset:%u;\tsize:%u;\tsigned:%u;\n", (unsigned int)offsetof(typeof(field), commit), (unsigned int)sizeof(field.commit), (unsigned int)is_signed_type(long)); trace_seq_printf(s, "\tfield: int overwrite;\t" "offset:%u;\tsize:%u;\tsigned:%u;\n", (unsigned int)offsetof(typeof(field), commit), 1, (unsigned int)is_signed_type(long)); trace_seq_printf(s, "\tfield: char data;\t" "offset:%u;\tsize:%u;\tsigned:%u;\n", (unsigned int)offsetof(typeof(field), data), (unsigned int)BUF_PAGE_SIZE, (unsigned int)is_signed_type(char)); return !trace_seq_has_overflowed(s); } struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; wait_queue_head_t full_waiters; long wait_index; bool waiters_pending; bool full_waiters_pending; bool wakeup_full; }; /* * Structure to hold event state and handle nested events. */ struct rb_event_info { u64 ts; u64 delta; u64 before; u64 after; unsigned long length; struct buffer_page *tail_page; int add_timestamp; }; /* * Used for the add_timestamp * NONE * EXTEND - wants a time extend * ABSOLUTE - the buffer requests all events to have absolute time stamps * FORCE - force a full time stamp. */ enum { RB_ADD_STAMP_NONE = 0, RB_ADD_STAMP_EXTEND = BIT(1), RB_ADD_STAMP_ABSOLUTE = BIT(2), RB_ADD_STAMP_FORCE = BIT(3) }; /* * Used for which event context the event is in. * TRANSITION = 0 * NMI = 1 * IRQ = 2 * SOFTIRQ = 3 * NORMAL = 4 * * See trace_recursive_lock() comment below for more details. */ enum { RB_CTX_TRANSITION, RB_CTX_NMI, RB_CTX_IRQ, RB_CTX_SOFTIRQ, RB_CTX_NORMAL, RB_CTX_MAX }; #if BITS_PER_LONG == 32 #define RB_TIME_32 #endif /* To test on 64 bit machines */ //#define RB_TIME_32 #ifdef RB_TIME_32 struct rb_time_struct { local_t cnt; local_t top; local_t bottom; local_t msb; }; #else #include <asm/local64.h> struct rb_time_struct { local64_t time; }; #endif typedef struct rb_time_struct rb_time_t; #define MAX_NEST 5 /* * head_page == tail_page && head == tail then buffer is empty. */ struct ring_buffer_per_cpu { int cpu; atomic_t record_disabled; atomic_t resize_disabled; struct trace_buffer *buffer; raw_spinlock_t reader_lock; /* serialize readers */ arch_spinlock_t lock; struct lock_class_key lock_key; struct buffer_data_page *free_page; unsigned long nr_pages; unsigned int current_context; struct list_head *pages; struct buffer_page *head_page; /* read from head */ struct buffer_page *tail_page; /* write to tail */ struct buffer_page *commit_page; /* committed pages */ struct buffer_page *reader_page; unsigned long lost_events; unsigned long last_overrun; unsigned long nest; local_t entries_bytes; local_t entries; local_t overrun; local_t commit_overrun; local_t dropped_events; local_t committing; local_t commits; local_t pages_touched; local_t pages_lost; local_t pages_read; long last_pages_touch; size_t shortest_full; unsigned long read; unsigned long read_bytes; rb_time_t write_stamp; rb_time_t before_stamp; u64 event_stamp[MAX_NEST]; u64 read_stamp; /* ring buffer pages to update, > 0 to add, < 0 to remove */ long nr_pages_to_update; struct list_head new_pages; /* new pages to add */ struct work_struct update_pages_work; struct completion update_done; struct rb_irq_work irq_work; }; struct trace_buffer { unsigned flags; int cpus; atomic_t record_disabled; cpumask_var_t cpumask; struct lock_class_key *reader_lock_key; struct mutex mutex; struct ring_buffer_per_cpu **buffers; struct hlist_node node; u64 (*clock)(void); struct rb_irq_work irq_work; bool time_stamp_abs; }; struct ring_buffer_iter { struct ring_buffer_per_cpu *cpu_buffer; unsigned long head; unsigned long next_event; struct buffer_page *head_page; struct buffer_page *cache_reader_page; unsigned long cache_read; u64 read_stamp; u64 page_stamp; struct ring_buffer_event *event; int missed_events; }; #ifdef RB_TIME_32 /* * On 32 bit machines, local64_t is very expensive. As the ring * buffer doesn't need all the features of a true 64 bit atomic, * on 32 bit, it uses these functions (64 still uses local64_t). * * For the ring buffer, 64 bit required operations for the time is * the following: * * - Reads may fail if it interrupted a modification of the time stamp. * It will succeed if it did not interrupt another write even if * the read itself is interrupted by a write. * It returns whether it was successful or not. * * - Writes always succeed and will overwrite other writes and writes * that were done by events interrupting the current write. * * - A write followed by a read of the same time stamp will always succeed, * but may not contain the same value. * * - A cmpxchg will fail if it interrupted another write or cmpxchg. * Other than that, it acts like a normal cmpxchg. * * The 60 bit time stamp is broken up by 30 bits in a top and bottom half * (bottom being the least significant 30 bits of the 60 bit time stamp). * * The two most significant bits of each half holds a 2 bit counter (0-3). * Each update will increment this counter by one. * When reading the top and bottom, if the two counter bits match then the * top and bottom together make a valid 60 bit number. */ #define RB_TIME_SHIFT 30 #define RB_TIME_VAL_MASK ((1 << RB_TIME_SHIFT) - 1) #define RB_TIME_MSB_SHIFT 60 static inline int rb_time_cnt(unsigned long val) { return (val >> RB_TIME_SHIFT) & 3; } static inline u64 rb_time_val(unsigned long top, unsigned long bottom) { u64 val; val = top & RB_TIME_VAL_MASK; val <<= RB_TIME_SHIFT; val |= bottom & RB_TIME_VAL_MASK; return val; } static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt) { unsigned long top, bottom, msb; unsigned long c; /* * If the read is interrupted by a write, then the cnt will * be different. Loop until both top and bottom have been read * without interruption. */ do { c = local_read(&t->cnt); top = local_read(&t->top); bottom = local_read(&t->bottom); msb = local_read(&t->msb); } while (c != local_read(&t->cnt)); *cnt = rb_time_cnt(top); /* If top and bottom counts don't match, this interrupted a write */ if (*cnt != rb_time_cnt(bottom)) return false; /* The shift to msb will lose its cnt bits */ *ret = rb_time_val(top, bottom) | ((u64)msb << RB_TIME_MSB_SHIFT); return true; } static bool rb_time_read(rb_time_t *t, u64 *ret) { unsigned long cnt; return __rb_time_read(t, ret, &cnt); } static inline unsigned long rb_time_val_cnt(unsigned long val, unsigned long cnt) { return (val & RB_TIME_VAL_MASK) | ((cnt & 3) << RB_TIME_SHIFT); } static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom, unsigned long *msb) { *top = (unsigned long)((val >> RB_TIME_SHIFT) & RB_TIME_VAL_MASK); *bottom = (unsigned long)(val & RB_TIME_VAL_MASK); *msb = (unsigned long)(val >> RB_TIME_MSB_SHIFT); } static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long cnt) { val = rb_time_val_cnt(val, cnt); local_set(t, val); } static void rb_time_set(rb_time_t *t, u64 val) { unsigned long cnt, top, bottom, msb; rb_time_split(val, &top, &bottom, &msb); /* Writes always succeed with a valid number even if it gets interrupted. */ do { cnt = local_inc_return(&t->cnt); rb_time_val_set(&t->top, top, cnt); rb_time_val_set(&t->bottom, bottom, cnt); rb_time_val_set(&t->msb, val >> RB_TIME_MSB_SHIFT, cnt); } while (cnt != local_read(&t->cnt)); } static inline bool rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set) { unsigned long ret; ret = local_cmpxchg(l, expect, set); return ret == expect; } static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) { unsigned long cnt, top, bottom, msb; unsigned long cnt2, top2, bottom2, msb2; u64 val; /* The cmpxchg always fails if it interrupted an update */ if (!__rb_time_read(t, &val, &cnt2)) return false; if (val != expect) return false; cnt = local_read(&t->cnt); if ((cnt & 3) != cnt2) return false; cnt2 = cnt + 1; rb_time_split(val, &top, &bottom, &msb); top = rb_time_val_cnt(top, cnt); bottom = rb_time_val_cnt(bottom, cnt); rb_time_split(set, &top2, &bottom2, &msb2); top2 = rb_time_val_cnt(top2, cnt2); bottom2 = rb_time_val_cnt(bottom2, cnt2); if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2)) return false; if (!rb_time_read_cmpxchg(&t->msb, msb, msb2)) return false; if (!rb_time_read_cmpxchg(&t->top, top, top2)) return false; if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2)) return false; return true; } #else /* 64 bits */ /* local64_t always succeeds */ static inline bool rb_time_read(rb_time_t *t, u64 *ret) { *ret = local64_read(&t->time); return true; } static void rb_time_set(rb_time_t *t, u64 val) { local64_set(&t->time, val); } static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) { u64 val; val = local64_cmpxchg(&t->time, expect, set); return val == expect; } #endif /* * Enable this to make sure that the event passed to * ring_buffer_event_time_stamp() is not committed and also * is on the buffer that it passed in. */ //#define RB_VERIFY_EVENT #ifdef RB_VERIFY_EVENT static struct list_head *rb_list_head(struct list_head *list); static void verify_event(struct ring_buffer_per_cpu *cpu_buffer, void *event) { struct buffer_page *page = cpu_buffer->commit_page; struct buffer_page *tail_page = READ_ONCE(cpu_buffer->tail_page); struct list_head *next; long commit, write; unsigned long addr = (unsigned long)event; bool done = false; int stop = 0; /* Make sure the event exists and is not committed yet */ do { if (page == tail_page || WARN_ON_ONCE(stop++ > 100)) done = true; commit = local_read(&page->page->commit); write = local_read(&page->write); if (addr >= (unsigned long)&page->page->data[commit] && addr < (unsigned long)&page->page->data[write]) return; next = rb_list_head(page->list.next); page = list_entry(next, struct buffer_page, list); } while (!done); WARN_ON_ONCE(1); } #else static inline void verify_event(struct ring_buffer_per_cpu *cpu_buffer, void *event) { } #endif /* * The absolute time stamp drops the 5 MSBs and some clocks may * require them. The rb_fix_abs_ts() will take a previous full * time stamp, and add the 5 MSB of that time stamp on to the * saved absolute time stamp. Then they are compared in case of * the unlikely event that the latest time stamp incremented * the 5 MSB. */ static inline u64 rb_fix_abs_ts(u64 abs, u64 save_ts) { if (save_ts & TS_MSB) { abs |= save_ts & TS_MSB; /* Check for overflow */ if (unlikely(abs < save_ts)) abs += 1ULL << 59; } return abs; } static inline u64 rb_time_stamp(struct trace_buffer *buffer); /** * ring_buffer_event_time_stamp - return the event's current time stamp * @buffer: The buffer that the event is on * @event: the event to get the time stamp of * * Note, this must be called after @event is reserved, and before it is * committed to the ring buffer. And must be called from the same * context where the event was reserved (normal, softirq, irq, etc). * * Returns the time stamp associated with the current event. * If the event has an extended time stamp, then that is used as * the time stamp to return. * In the highly unlikely case that the event was nested more than * the max nesting, then the write_stamp of the buffer is returned, * otherwise current time is returned, but that really neither of * the last two cases should ever happen. */ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_event *event) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[smp_processor_id()]; unsigned int nest; u64 ts; /* If the event includes an absolute time, then just use that */ if (event->type_len == RINGBUF_TYPE_TIME_STAMP) { ts = rb_event_time_stamp(event); return rb_fix_abs_ts(ts, cpu_buffer->tail_page->page->time_stamp); } nest = local_read(&cpu_buffer->committing); verify_event(cpu_buffer, event); if (WARN_ON_ONCE(!nest)) goto fail; /* Read the current saved nesting level time stamp */ if (likely(--nest < MAX_NEST)) return cpu_buffer->event_stamp[nest]; /* Shouldn't happen, warn if it does */ WARN_ONCE(1, "nest (%d) greater than max", nest); fail: /* Can only fail on 32 bit */ if (!rb_time_read(&cpu_buffer->write_stamp, &ts)) /* Screw it, just read the current time */ ts = rb_time_stamp(cpu_buffer->buffer); return ts; } /** * ring_buffer_nr_pages - get the number of buffer pages in the ring buffer * @buffer: The ring_buffer to get the number of pages from * @cpu: The cpu of the ring_buffer to get the number of pages from * * Returns the number of pages used by a per_cpu buffer of the ring buffer. */ size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu) { return buffer->buffers[cpu]->nr_pages; } /** * ring_buffer_nr_dirty_pages - get the number of used pages in the ring buffer * @buffer: The ring_buffer to get the number of pages from * @cpu: The cpu of the ring_buffer to get the number of pages from * * Returns the number of pages that have content in the ring buffer. */ size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu) { size_t read; size_t lost; size_t cnt; read = local_read(&buffer->buffers[cpu]->pages_read); lost = local_read(&buffer->buffers[cpu]->pages_lost); cnt = local_read(&buffer->buffers[cpu]->pages_touched); if (WARN_ON_ONCE(cnt < lost)) return 0; cnt -= lost; /* The reader can read an empty page, but not more than that */ if (cnt < read) { WARN_ON_ONCE(read > cnt + 1); return 0; } return cnt - read; } static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int full) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; size_t nr_pages; size_t dirty; nr_pages = cpu_buffer->nr_pages; if (!nr_pages || !full) return true; dirty = ring_buffer_nr_dirty_pages(buffer, cpu); return (dirty * 100) > (full * nr_pages); } /* * rb_wake_up_waiters - wake up tasks waiting for ring buffer input * * Schedules a delayed work to wake up any task that is blocked on the * ring buffer waiters queue. */ static void rb_wake_up_waiters(struct irq_work *work) { struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work); wake_up_all(&rbwork->waiters); if (rbwork->full_waiters_pending || rbwork->wakeup_full) { rbwork->wakeup_full = false; rbwork->full_waiters_pending = false; wake_up_all(&rbwork->full_waiters); } } /** * ring_buffer_wake_waiters - wake up any waiters on this ring buffer * @buffer: The ring buffer to wake waiters on * * In the case of a file that represents a ring buffer is closing, * it is prudent to wake up any waiters that are on this. */ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; struct rb_irq_work *rbwork; if (!buffer) return; if (cpu == RING_BUFFER_ALL_CPUS) { /* Wake up individual ones too. One level recursion */ for_each_buffer_cpu(buffer, cpu) ring_buffer_wake_waiters(buffer, cpu); rbwork = &buffer->irq_work; } else { if (WARN_ON_ONCE(!buffer->buffers)) return; if (WARN_ON_ONCE(cpu >= nr_cpu_ids)) return; cpu_buffer = buffer->buffers[cpu]; /* The CPU buffer may not have been initialized yet */ if (!cpu_buffer) return; rbwork = &cpu_buffer->irq_work; } rbwork->wait_index++; /* make sure the waiters see the new index */ smp_wmb(); rb_wake_up_waiters(&rbwork->work); } /** * ring_buffer_wait - wait for input to the ring buffer * @buffer: buffer to wait on * @cpu: the cpu buffer to wait on * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS * * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon * as data is added to any of the @buffer's cpu buffers. Otherwise * it will wait for data to be added to a specific cpu buffer. */ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) { struct ring_buffer_per_cpu *cpu_buffer; DEFINE_WAIT(wait); struct rb_irq_work *work; long wait_index; int ret = 0; /* * Depending on what the caller is waiting for, either any * data in any cpu buffer, or a specific buffer, put the * caller on the appropriate wait queue. */ if (cpu == RING_BUFFER_ALL_CPUS) { work = &buffer->irq_work; /* Full only makes sense on per cpu reads */ full = 0; } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) return -ENODEV; cpu_buffer = buffer->buffers[cpu]; work = &cpu_buffer->irq_work; } wait_index = READ_ONCE(work->wait_index); while (true) { if (full) prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE); else prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); /* * The events can happen in critical sections where * checking a work queue can cause deadlocks. * After adding a task to the queue, this flag is set * only to notify events to try to wake up the queue * using irq_work. * * We don't clear it even if the buffer is no longer * empty. The flag only causes the next event to run * irq_work to do the work queue wake up. The worse * that can happen if we race with !trace_empty() is that * an event will cause an irq_work to try to wake up * an empty queue. * * There's no reason to protect this flag either, as * the work queue and irq_work logic will do the necessary * synchronization for the wake ups. The only thing * that is necessary is that the wake up happens after * a task has been queued. It's OK for spurious wake ups. */ if (full) work->full_waiters_pending = true; else work->waiters_pending = true; if (signal_pending(current)) { ret = -EINTR; break; } if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) break; if (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)) { unsigned long flags; bool pagebusy; bool done; if (!full) break; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; done = !pagebusy && full_hit(buffer, cpu, full); if (!cpu_buffer->shortest_full || cpu_buffer->shortest_full > full) cpu_buffer->shortest_full = full; raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); if (done) break; } schedule(); /* Make sure to see the new wait index */ smp_rmb(); if (wait_index != work->wait_index) break; } if (full) finish_wait(&work->full_waiters, &wait); else finish_wait(&work->waiters, &wait); return ret; } /** * ring_buffer_poll_wait - poll on buffer input * @buffer: buffer to wait on * @cpu: the cpu buffer to wait on * @filp: the file descriptor * @poll_table: The poll descriptor * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS * * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon * as data is added to any of the @buffer's cpu buffers. Otherwise * it will wait for data to be added to a specific cpu buffer. * * Returns EPOLLIN | EPOLLRDNORM if data exists in the buffers, * zero otherwise. */ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table, int full) { struct ring_buffer_per_cpu *cpu_buffer; struct rb_irq_work *work; if (cpu == RING_BUFFER_ALL_CPUS) { work = &buffer->irq_work; full = 0; } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) return -EINVAL; cpu_buffer = buffer->buffers[cpu]; work = &cpu_buffer->irq_work; } if (full) { poll_wait(filp, &work->full_waiters, poll_table); work->full_waiters_pending = true; } else { poll_wait(filp, &work->waiters, poll_table); work->waiters_pending = true; } /* * There's a tight race between setting the waiters_pending and * checking if the ring buffer is empty. Once the waiters_pending bit * is set, the next event will wake the task up, but we can get stuck * if there's only a single event in. * * FIXME: Ideally, we need a memory barrier on the writer side as well, * but adding a memory barrier to all events will cause too much of a * performance hit in the fast path. We only need a memory barrier when * the buffer goes from empty to having content. But as this race is * extremely small, and it's not a problem if another event comes in, we * will fix it later. */ smp_mb(); if (full) return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0; if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) return EPOLLIN | EPOLLRDNORM; return 0; } /* buffer may be either ring_buffer or ring_buffer_per_cpu */ #define RB_WARN_ON(b, cond) \ ({ \ int _____ret = unlikely(cond); \ if (_____ret) { \ if (__same_type(*(b), struct ring_buffer_per_cpu)) { \ struct ring_buffer_per_cpu *__b = \ (void *)b; \ atomic_inc(&__b->buffer->record_disabled); \ } else \ atomic_inc(&b->record_disabled); \ WARN_ON(1); \ } \ _____ret; \ }) /* Up this if you want to test the TIME_EXTENTS and normalization */ #define DEBUG_SHIFT 0 static inline u64 rb_time_stamp(struct trace_buffer *buffer) { u64 ts; /* Skip retpolines :-( */ if (IS_ENABLED(CONFIG_RETPOLINE) && likely(buffer->clock == trace_clock_local)) ts = trace_clock_local(); else ts = buffer->clock(); /* shift to debug/test normalization and TIME_EXTENTS */ return ts << DEBUG_SHIFT; } u64 ring_buffer_time_stamp(struct trace_buffer *buffer) { u64 time; preempt_disable_notrace(); time = rb_time_stamp(buffer); preempt_enable_notrace(); return time; } EXPORT_SYMBOL_GPL(ring_buffer_time_stamp); void ring_buffer_normalize_time_stamp(struct trace_buffer *buffer, int cpu, u64 *ts) { /* Just stupid testing the normalize function and deltas */ *ts >>= DEBUG_SHIFT; } EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp); /* * Making the ring buffer lockless makes things tricky. * Although writes only happen on the CPU that they are on, * and they only need to worry about interrupts. Reads can * happen on any CPU. * * The reader page is always off the ring buffer, but when the * reader finishes with a page, it needs to swap its page with * a new one from the buffer. The reader needs to take from * the head (writes go to the tail). But if a writer is in overwrite * mode and wraps, it must push the head page forward. * * Here lies the problem. * * The reader must be careful to replace only the head page, and * not another one. As described at the top of the file in the * ASCII art, the reader sets its old page to point to the next * page after head. It then sets the page after head to point to * the old reader page. But if the writer moves the head page * during this operation, the reader could end up with the tail. * * We use cmpxchg to help prevent this race. We also do something * special with the page before head. We set the LSB to 1. * * When the writer must push the page forward, it will clear the * bit that points to the head page, move the head, and then set * the bit that points to the new head page. * * We also don't want an interrupt coming in and moving the head * page on another writer. Thus we use the second LSB to catch * that too. Thus: * * head->list->prev->next bit 1 bit 0 * ------- ------- * Normal page 0 0 * Points to head page 0 1 * New head page 1 0 * * Note we can not trust the prev pointer of the head page, because: * * +----+ +-----+ +-----+ * | |------>| T |---X--->| N | * | |<------| | | | * +----+ +-----+ +-----+ * ^ ^ | * | +-----+ | | * +----------| R |----------+ | * | |<-----------+ * +-----+ * * Key: ---X--> HEAD flag set in pointer * T Tail page * R Reader page * N Next page * * (see __rb_reserve_next() to see where this happens) * * What the above shows is that the reader just swapped out * the reader page with a page in the buffer, but before it * could make the new header point back to the new page added * it was preempted by a writer. The writer moved forward onto * the new page added by the reader and is about to move forward * again. * * You can see, it is legitimate for the previous pointer of * the head (or any page) not to point back to itself. But only * temporarily. */ #define RB_PAGE_NORMAL 0UL #define RB_PAGE_HEAD 1UL #define RB_PAGE_UPDATE 2UL #define RB_FLAG_MASK 3UL /* PAGE_MOVED is not part of the mask */ #define RB_PAGE_MOVED 4UL /* * rb_list_head - remove any bit */ static struct list_head *rb_list_head(struct list_head *list) { unsigned long val = (unsigned long)list; return (struct list_head *)(val & ~RB_FLAG_MASK); } /* * rb_is_head_page - test if the given page is the head page * * Because the reader may move the head_page pointer, we can * not trust what the head page is (it may be pointing to * the reader page). But if the next page is a header page, * its flags will be non zero. */ static inline int rb_is_head_page(struct buffer_page *page, struct list_head *list) { unsigned long val; val = (unsigned long)list->next; if ((val & ~RB_FLAG_MASK) != (unsigned long)&page->list) return RB_PAGE_MOVED; return val & RB_FLAG_MASK; } /* * rb_is_reader_page * * The unique thing about the reader page, is that, if the * writer is ever on it, the previous pointer never points * back to the reader page. */ static bool rb_is_reader_page(struct buffer_page *page) { struct list_head *list = page->list.prev; return rb_list_head(list->next) != &page->list; } /* * rb_set_list_to_head - set a list_head to be pointing to head. */ static void rb_set_list_to_head(struct list_head *list) { unsigned long *ptr; ptr = (unsigned long *)&list->next; *ptr |= RB_PAGE_HEAD; *ptr &= ~RB_PAGE_UPDATE; } /* * rb_head_page_activate - sets up head page */ static void rb_head_page_activate(struct ring_buffer_per_cpu *cpu_buffer) { struct buffer_page *head; head = cpu_buffer->head_page; if (!head) return; /* * Set the previous list pointer to have the HEAD flag. */ rb_set_list_to_head(head->list.prev); } static void rb_list_head_clear(struct list_head *list) { unsigned long *ptr = (unsigned long *)&list->next; *ptr &= ~RB_FLAG_MASK; } /* * rb_head_page_deactivate - clears head page ptr (for free list) */ static void rb_head_page_deactivate(struct ring_buffer_per_cpu *cpu_buffer) { struct list_head *hd; /* Go through the whole list and clear any pointers found. */ rb_list_head_clear(cpu_buffer->pages); list_for_each(hd, cpu_buffer->pages) rb_list_head_clear(hd); } static int rb_head_page_set(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *head, struct buffer_page *prev, int old_flag, int new_flag) { struct list_head *list; unsigned long val = (unsigned long)&head->list; unsigned long ret; list = &prev->list; val &= ~RB_FLAG_MASK; ret = cmpxchg((unsigned long *)&list->next, val | old_flag, val | new_flag); /* check if the reader took the page */ if ((ret & ~RB_FLAG_MASK) != val) return RB_PAGE_MOVED; return ret & RB_FLAG_MASK; } static int rb_head_page_set_update(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *head, struct buffer_page *prev, int old_flag) { return rb_head_page_set(cpu_buffer, head, prev, old_flag, RB_PAGE_UPDATE); } static int rb_head_page_set_head(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *head, struct buffer_page *prev, int old_flag) { return rb_head_page_set(cpu_buffer, head, prev, old_flag, RB_PAGE_HEAD); } static int rb_head_page_set_normal(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *head, struct buffer_page *prev, int old_flag) { return rb_head_page_set(cpu_buffer, head, prev, old_flag, RB_PAGE_NORMAL); } static inline void rb_inc_page(struct buffer_page **bpage) { struct list_head *p = rb_list_head((*bpage)->list.next); *bpage = list_entry(p, struct buffer_page, list); } static struct buffer_page * rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer) { struct buffer_page *head; struct buffer_page *page; struct list_head *list; int i; if (RB_WARN_ON(cpu_buffer, !cpu_buffer->head_page)) return NULL; /* sanity check */ list = cpu_buffer->pages; if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev->next) != list)) return NULL; page = head = cpu_buffer->head_page; /* * It is possible that the writer moves the header behind * where we started, and we miss in one loop. * A second loop should grab the header, but we'll do * three loops just because I'm paranoid. */ for (i = 0; i < 3; i++) { do { if (rb_is_head_page(page, page->list.prev)) { cpu_buffer->head_page = page; return page; } rb_inc_page(&page); } while (page != head); } RB_WARN_ON(cpu_buffer, 1); return NULL; } static int rb_head_page_replace(struct buffer_page *old, struct buffer_page *new) { unsigned long *ptr = (unsigned long *)&old->list.prev->next; unsigned long val; unsigned long ret; val = *ptr & ~RB_FLAG_MASK; val |= RB_PAGE_HEAD; ret = cmpxchg(ptr, val, (unsigned long)&new->list); return ret == val; } /* * rb_tail_page_update - move the tail page forward */ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *tail_page, struct buffer_page *next_page) { unsigned long old_entries; unsigned long old_write; /* * The tail page now needs to be moved forward. * * We need to reset the tail page, but without messing * with possible erasing of data brought in by interrupts * that have moved the tail page and are currently on it. * * We add a counter to the write field to denote this. */ old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write); old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries); local_inc(&cpu_buffer->pages_touched); /* * Just make sure we have seen our old_write and synchronize * with any interrupts that come in. */ barrier(); /* * If the tail page is still the same as what we think * it is, then it is up to us to update the tail * pointer. */ if (tail_page == READ_ONCE(cpu_buffer->tail_page)) { /* Zero the write counter */ unsigned long val = old_write & ~RB_WRITE_MASK; unsigned long eval = old_entries & ~RB_WRITE_MASK; /* * This will only succeed if an interrupt did * not come in and change it. In which case, we * do not want to modify it. * * We add (void) to let the compiler know that we do not care * about the return value of these functions. We use the * cmpxchg to only update if an interrupt did not already * do it for us. If the cmpxchg fails, we don't care. */ (void)local_cmpxchg(&next_page->write, old_write, val); (void)local_cmpxchg(&next_page->entries, old_entries, eval); /* * No need to worry about races with clearing out the commit. * it only can increment when a commit takes place. But that * only happens in the outer most nested commit. */ local_set(&next_page->page->commit, 0); /* Again, either we update tail_page or an interrupt does */ (void)cmpxchg(&cpu_buffer->tail_page, tail_page, next_page); } } static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *bpage) { unsigned long val = (unsigned long)bpage; if (RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK)) return 1; return 0; } /** * rb_check_list - make sure a pointer to a list has the last bits zero */ static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer, struct list_head *list) { if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev) != list->prev)) return 1; if (RB_WARN_ON(cpu_buffer, rb_list_head(list->next) != list->next)) return 1; return 0; } /** * rb_check_pages - integrity check of buffer pages * @cpu_buffer: CPU buffer with pages to test * * As a safety measure we check to make sure the data pages have not * been corrupted. */ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) { struct list_head *head = cpu_buffer->pages; struct buffer_page *bpage, *tmp; /* Reset the head page if it exists */ if (cpu_buffer->head_page) rb_set_head_page(cpu_buffer); rb_head_page_deactivate(cpu_buffer); if (RB_WARN_ON(cpu_buffer, head->next->prev != head)) return -1; if (RB_WARN_ON(cpu_buffer, head->prev->next != head)) return -1; if (rb_check_list(cpu_buffer, head)) return -1; list_for_each_entry_safe(bpage, tmp, head, list) { if (RB_WARN_ON(cpu_buffer, bpage->list.next->prev != &bpage->list)) return -1; if (RB_WARN_ON(cpu_buffer, bpage->list.prev->next != &bpage->list)) return -1; if (rb_check_list(cpu_buffer, &bpage->list)) return -1; } rb_head_page_activate(cpu_buffer); return 0; } static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, long nr_pages, struct list_head *pages) { struct buffer_page *bpage, *tmp; bool user_thread = current->mm != NULL; gfp_t mflags; long i; /* * Check if the available memory is there first. * Note, si_mem_available() only gives us a rough estimate of available * memory. It may not be accurate. But we don't care, we just want * to prevent doing any allocation when it is obvious that it is * not going to succeed. */ i = si_mem_available(); if (i < nr_pages) return -ENOMEM; /* * __GFP_RETRY_MAYFAIL flag makes sure that the allocation fails * gracefully without invoking oom-killer and the system is not * destabilized. */ mflags = GFP_KERNEL | __GFP_RETRY_MAYFAIL; /* * If a user thread allocates too much, and si_mem_available() * reports there's enough memory, even though there is not. * Make sure the OOM killer kills this thread. This can happen * even with RETRY_MAYFAIL because another task may be doing * an allocation after this task has taken all memory. * This is the task the OOM killer needs to take out during this * loop, even if it was triggered by an allocation somewhere else. */ if (user_thread) set_current_oom_origin(); for (i = 0; i < nr_pages; i++) { struct page *page; bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), mflags, cpu_to_node(cpu_buffer->cpu)); if (!bpage) goto free_pages; rb_check_bpage(cpu_buffer, bpage); list_add(&bpage->list, pages); page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags, 0); if (!page) goto free_pages; bpage->page = page_address(page); rb_init_page(bpage->page); if (user_thread && fatal_signal_pending(current)) goto free_pages; } if (user_thread) clear_current_oom_origin(); return 0; free_pages: list_for_each_entry_safe(bpage, tmp, pages, list) { list_del_init(&bpage->list); free_buffer_page(bpage); } if (user_thread) clear_current_oom_origin(); return -ENOMEM; } static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) { LIST_HEAD(pages); WARN_ON(!nr_pages); if (__rb_allocate_pages(cpu_buffer, nr_pages, &pages)) return -ENOMEM; /* * The ring buffer page list is a circular list that does not * start and end with a list head. All page list items point to * other pages. */ cpu_buffer->pages = pages.next; list_del(&pages); cpu_buffer->nr_pages = nr_pages; rb_check_pages(cpu_buffer); return 0; } static struct ring_buffer_per_cpu * rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; struct buffer_page *bpage; struct page *page; int ret; cpu_buffer = kzalloc_node(ALIGN(sizeof(*cpu_buffer), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); if (!cpu_buffer) return NULL; cpu_buffer->cpu = cpu; cpu_buffer->buffer = buffer; raw_spin_lock_init(&cpu_buffer->reader_lock); lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key); cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; INIT_WORK(&cpu_buffer->update_pages_work, update_pages_handler); init_completion(&cpu_buffer->update_done); init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters); init_waitqueue_head(&cpu_buffer->irq_work.waiters); init_waitqueue_head(&cpu_buffer->irq_work.full_waiters); bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); if (!bpage) goto fail_free_buffer; rb_check_bpage(cpu_buffer, bpage); cpu_buffer->reader_page = bpage; page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0); if (!page) goto fail_free_reader; bpage->page = page_address(page); rb_init_page(bpage->page); INIT_LIST_HEAD(&cpu_buffer->reader_page->list); INIT_LIST_HEAD(&cpu_buffer->new_pages); ret = rb_allocate_pages(cpu_buffer, nr_pages); if (ret < 0) goto fail_free_reader; cpu_buffer->head_page = list_entry(cpu_buffer->pages, struct buffer_page, list); cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page; rb_head_page_activate(cpu_buffer); return cpu_buffer; fail_free_reader: free_buffer_page(cpu_buffer->reader_page); fail_free_buffer: kfree(cpu_buffer); return NULL; } static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) { struct list_head *head = cpu_buffer->pages; struct buffer_page *bpage, *tmp; free_buffer_page(cpu_buffer->reader_page); if (head) { rb_head_page_deactivate(cpu_buffer); list_for_each_entry_safe(bpage, tmp, head, list) { list_del_init(&bpage->list); free_buffer_page(bpage); } bpage = list_entry(head, struct buffer_page, list); free_buffer_page(bpage); } kfree(cpu_buffer); } /** * __ring_buffer_alloc - allocate a new ring_buffer * @size: the size in bytes per cpu that is needed. * @flags: attributes to set for the ring buffer. * @key: ring buffer reader_lock_key. * * Currently the only flag that is available is the RB_FL_OVERWRITE * flag. This flag means that the buffer will overwrite old data * when the buffer wraps. If this flag is not set, the buffer will * drop data when the tail hits the head. */ struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *key) { struct trace_buffer *buffer; long nr_pages; int bsize; int cpu; int ret; /* keep it in its own cache line */ buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()), GFP_KERNEL); if (!buffer) return NULL; if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL)) goto fail_free_buffer; nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); buffer->flags = flags; buffer->clock = trace_clock_local; buffer->reader_lock_key = key; init_irq_work(&buffer->irq_work.work, rb_wake_up_waiters); init_waitqueue_head(&buffer->irq_work.waiters); /* need at least two pages */ if (nr_pages < 2) nr_pages = 2; buffer->cpus = nr_cpu_ids; bsize = sizeof(void *) * nr_cpu_ids; buffer->buffers = kzalloc(ALIGN(bsize, cache_line_size()), GFP_KERNEL); if (!buffer->buffers) goto fail_free_cpumask; cpu = raw_smp_processor_id(); cpumask_set_cpu(cpu, buffer->cpumask); buffer->buffers[cpu] = rb_allocate_cpu_buffer(buffer, nr_pages, cpu); if (!buffer->buffers[cpu]) goto fail_free_buffers; ret = cpuhp_state_add_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node); if (ret < 0) goto fail_free_buffers; mutex_init(&buffer->mutex); return buffer; fail_free_buffers: for_each_buffer_cpu(buffer, cpu) { if (buffer->buffers[cpu]) rb_free_cpu_buffer(buffer->buffers[cpu]); } kfree(buffer->buffers); fail_free_cpumask: free_cpumask_var(buffer->cpumask); fail_free_buffer: kfree(buffer); return NULL; } EXPORT_SYMBOL_GPL(__ring_buffer_alloc); /** * ring_buffer_free - free a ring buffer. * @buffer: the buffer to free. */ void ring_buffer_free(struct trace_buffer *buffer) { int cpu; cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node); for_each_buffer_cpu(buffer, cpu) rb_free_cpu_buffer(buffer->buffers[cpu]); kfree(buffer->buffers); free_cpumask_var(buffer->cpumask); kfree(buffer); } EXPORT_SYMBOL_GPL(ring_buffer_free); void ring_buffer_set_clock(struct trace_buffer *buffer, u64 (*clock)(void)) { buffer->clock = clock; } void ring_buffer_set_time_stamp_abs(struct trace_buffer *buffer, bool abs) { buffer->time_stamp_abs = abs; } bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer) { return buffer->time_stamp_abs; } static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer); static inline unsigned long rb_page_entries(struct buffer_page *bpage) { return local_read(&bpage->entries) & RB_WRITE_MASK; } static inline unsigned long rb_page_write(struct buffer_page *bpage) { return local_read(&bpage->write) & RB_WRITE_MASK; } static int rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) { struct list_head *tail_page, *to_remove, *next_page; struct buffer_page *to_remove_page, *tmp_iter_page; struct buffer_page *last_page, *first_page; unsigned long nr_removed; unsigned long head_bit; int page_entries; head_bit = 0; raw_spin_lock_irq(&cpu_buffer->reader_lock); atomic_inc(&cpu_buffer->record_disabled); /* * We don't race with the readers since we have acquired the reader * lock. We also don't race with writers after disabling recording. * This makes it easy to figure out the first and the last page to be * removed from the list. We unlink all the pages in between including * the first and last pages. This is done in a busy loop so that we * lose the least number of traces. * The pages are freed after we restart recording and unlock readers. */ tail_page = &cpu_buffer->tail_page->list; /* * tail page might be on reader page, we remove the next page * from the ring buffer */ if (cpu_buffer->tail_page == cpu_buffer->reader_page) tail_page = rb_list_head(tail_page->next); to_remove = tail_page; /* start of pages to remove */ first_page = list_entry(rb_list_head(to_remove->next), struct buffer_page, list); for (nr_removed = 0; nr_removed < nr_pages; nr_removed++) { to_remove = rb_list_head(to_remove)->next; head_bit |= (unsigned long)to_remove & RB_PAGE_HEAD; } next_page = rb_list_head(to_remove)->next; /* * Now we remove all pages between tail_page and next_page. * Make sure that we have head_bit value preserved for the * next page */ tail_page->next = (struct list_head *)((unsigned long)next_page | head_bit); next_page = rb_list_head(next_page); next_page->prev = tail_page; /* make sure pages points to a valid page in the ring buffer */ cpu_buffer->pages = next_page; /* update head page */ if (head_bit) cpu_buffer->head_page = list_entry(next_page, struct buffer_page, list); /* * change read pointer to make sure any read iterators reset * themselves */ cpu_buffer->read = 0; /* pages are removed, resume tracing and then free the pages */ atomic_dec(&cpu_buffer->record_disabled); raw_spin_unlock_irq(&cpu_buffer->reader_lock); RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)); /* last buffer page to remove */ last_page = list_entry(rb_list_head(to_remove), struct buffer_page, list); tmp_iter_page = first_page; do { cond_resched(); to_remove_page = tmp_iter_page; rb_inc_page(&tmp_iter_page); /* update the counters */ page_entries = rb_page_entries(to_remove_page); if (page_entries) { /* * If something was added to this page, it was full * since it is not the tail page. So we deduct the * bytes consumed in ring buffer from here. * Increment overrun to account for the lost events. */ local_add(page_entries, &cpu_buffer->overrun); local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); } /* * We have already removed references to this list item, just * free up the buffer_page and its page */ free_buffer_page(to_remove_page); nr_removed--; } while (to_remove_page != last_page); RB_WARN_ON(cpu_buffer, nr_removed); return nr_removed == 0; } static int rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer) { struct list_head *pages = &cpu_buffer->new_pages; int retries, success; raw_spin_lock_irq(&cpu_buffer->reader_lock); /* * We are holding the reader lock, so the reader page won't be swapped * in the ring buffer. Now we are racing with the writer trying to * move head page and the tail page. * We are going to adapt the reader page update process where: * 1. We first splice the start and end of list of new pages between * the head page and its previous page. * 2. We cmpxchg the prev_page->next to point from head page to the * start of new pages list. * 3. Finally, we update the head->prev to the end of new list. * * We will try this process 10 times, to make sure that we don't keep * spinning. */ retries = 10; success = 0; while (retries--) { struct list_head *head_page, *prev_page, *r; struct list_head *last_page, *first_page; struct list_head *head_page_with_bit; head_page = &rb_set_head_page(cpu_buffer)->list; if (!head_page) break; prev_page = head_page->prev; first_page = pages->next; last_page = pages->prev; head_page_with_bit = (struct list_head *) ((unsigned long)head_page | RB_PAGE_HEAD); last_page->next = head_page_with_bit; first_page->prev = prev_page; r = cmpxchg(&prev_page->next, head_page_with_bit, first_page); if (r == head_page_with_bit) { /* * yay, we replaced the page pointer to our new list, * now, we just have to update to head page's prev * pointer to point to end of list */ head_page->prev = last_page; success = 1; break; } } if (success) INIT_LIST_HEAD(pages); /* * If we weren't successful in adding in new pages, warn and stop * tracing */ RB_WARN_ON(cpu_buffer, !success); raw_spin_unlock_irq(&cpu_buffer->reader_lock); /* free pages if they weren't inserted */ if (!success) { struct buffer_page *bpage, *tmp; list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages, list) { list_del_init(&bpage->list); free_buffer_page(bpage); } } return success; } static void rb_update_pages(struct ring_buffer_per_cpu *cpu_buffer) { int success; if (cpu_buffer->nr_pages_to_update > 0) success = rb_insert_pages(cpu_buffer); else success = rb_remove_pages(cpu_buffer, -cpu_buffer->nr_pages_to_update); if (success) cpu_buffer->nr_pages += cpu_buffer->nr_pages_to_update; } static void update_pages_handler(struct work_struct *work) { struct ring_buffer_per_cpu *cpu_buffer = container_of(work, struct ring_buffer_per_cpu, update_pages_work); rb_update_pages(cpu_buffer); complete(&cpu_buffer->update_done); } /** * ring_buffer_resize - resize the ring buffer * @buffer: the buffer to resize. * @size: the new size. * @cpu_id: the cpu buffer to resize * * Minimum size is 2 * BUF_PAGE_SIZE. * * Returns 0 on success and < 0 on failure. */ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, int cpu_id) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long nr_pages; int cpu, err; /* * Always succeed at resizing a non-existent buffer: */ if (!buffer) return 0; /* Make sure the requested buffer exists */ if (cpu_id != RING_BUFFER_ALL_CPUS && !cpumask_test_cpu(cpu_id, buffer->cpumask)) return 0; nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); /* we need a minimum of two pages */ if (nr_pages < 2) nr_pages = 2; /* prevent another thread from changing buffer sizes */ mutex_lock(&buffer->mutex); if (cpu_id == RING_BUFFER_ALL_CPUS) { /* * Don't succeed if resizing is disabled, as a reader might be * manipulating the ring buffer and is expecting a sane state while * this is true. */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; if (atomic_read(&cpu_buffer->resize_disabled)) { err = -EBUSY; goto out_err_unlock; } } /* calculate the pages to update */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; cpu_buffer->nr_pages_to_update = nr_pages - cpu_buffer->nr_pages; /* * nothing more to do for removing pages or no update */ if (cpu_buffer->nr_pages_to_update <= 0) continue; /* * to add pages, make sure all new pages can be * allocated without receiving ENOMEM */ INIT_LIST_HEAD(&cpu_buffer->new_pages); if (__rb_allocate_pages(cpu_buffer, cpu_buffer->nr_pages_to_update, &cpu_buffer->new_pages)) { /* not enough memory for new pages */ err = -ENOMEM; goto out_err; } } cpus_read_lock(); /* * Fire off all the required work handlers * We can't schedule on offline CPUs, but it's not necessary * since we can change their buffer sizes without any race. */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; if (!cpu_buffer->nr_pages_to_update) continue; /* Can't run something on an offline CPU. */ if (!cpu_online(cpu)) { rb_update_pages(cpu_buffer); cpu_buffer->nr_pages_to_update = 0; } else { schedule_work_on(cpu, &cpu_buffer->update_pages_work); } } /* wait for all the updates to complete */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; if (!cpu_buffer->nr_pages_to_update) continue; if (cpu_online(cpu)) wait_for_completion(&cpu_buffer->update_done); cpu_buffer->nr_pages_to_update = 0; } cpus_read_unlock(); } else { cpu_buffer = buffer->buffers[cpu_id]; if (nr_pages == cpu_buffer->nr_pages) goto out; /* * Don't succeed if resizing is disabled, as a reader might be * manipulating the ring buffer and is expecting a sane state while * this is true. */ if (atomic_read(&cpu_buffer->resize_disabled)) { err = -EBUSY; goto out_err_unlock; } cpu_buffer->nr_pages_to_update = nr_pages - cpu_buffer->nr_pages; INIT_LIST_HEAD(&cpu_buffer->new_pages); if (cpu_buffer->nr_pages_to_update > 0 && __rb_allocate_pages(cpu_buffer, cpu_buffer->nr_pages_to_update, &cpu_buffer->new_pages)) { err = -ENOMEM; goto out_err; } cpus_read_lock(); /* Can't run something on an offline CPU. */ if (!cpu_online(cpu_id)) rb_update_pages(cpu_buffer); else { schedule_work_on(cpu_id, &cpu_buffer->update_pages_work); wait_for_completion(&cpu_buffer->update_done); } cpu_buffer->nr_pages_to_update = 0; cpus_read_unlock(); } out: /* * The ring buffer resize can happen with the ring buffer * enabled, so that the update disturbs the tracing as little * as possible. But if the buffer is disabled, we do not need * to worry about that, and we can take the time to verify * that the buffer is not corrupt. */ if (atomic_read(&buffer->record_disabled)) { atomic_inc(&buffer->record_disabled); /* * Even though the buffer was disabled, we must make sure * that it is truly disabled before calling rb_check_pages. * There could have been a race between checking * record_disable and incrementing it. */ synchronize_rcu(); for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; rb_check_pages(cpu_buffer); } atomic_dec(&buffer->record_disabled); } mutex_unlock(&buffer->mutex); return 0; out_err: for_each_buffer_cpu(buffer, cpu) { struct buffer_page *bpage, *tmp; cpu_buffer = buffer->buffers[cpu]; cpu_buffer->nr_pages_to_update = 0; if (list_empty(&cpu_buffer->new_pages)) continue; list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages, list) { list_del_init(&bpage->list); free_buffer_page(bpage); } } out_err_unlock: mutex_unlock(&buffer->mutex); return err; } EXPORT_SYMBOL_GPL(ring_buffer_resize); void ring_buffer_change_overwrite(struct trace_buffer *buffer, int val) { mutex_lock(&buffer->mutex); if (val) buffer->flags |= RB_FL_OVERWRITE; else buffer->flags &= ~RB_FL_OVERWRITE; mutex_unlock(&buffer->mutex); } EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite); static __always_inline void *__rb_page_index(struct buffer_page *bpage, unsigned index) { return bpage->page->data + index; } static __always_inline struct ring_buffer_event * rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) { return __rb_page_index(cpu_buffer->reader_page, cpu_buffer->reader_page->read); } static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) { return local_read(&bpage->page->commit); } static struct ring_buffer_event * rb_iter_head_event(struct ring_buffer_iter *iter) { struct ring_buffer_event *event; struct buffer_page *iter_head_page = iter->head_page; unsigned long commit; unsigned length; if (iter->head != iter->next_event) return iter->event; /* * When the writer goes across pages, it issues a cmpxchg which * is a mb(), which will synchronize with the rmb here. * (see rb_tail_page_update() and __rb_reserve_next()) */ commit = rb_page_commit(iter_head_page); smp_rmb(); event = __rb_page_index(iter_head_page, iter->head); length = rb_event_length(event); /* * READ_ONCE() doesn't work on functions and we don't want the * compiler doing any crazy optimizations with length. */ barrier(); if ((iter->head + length) > commit || length > BUF_MAX_DATA_SIZE) /* Writer corrupted the read? */ goto reset; memcpy(iter->event, event, length); /* * If the page stamp is still the same after this rmb() then the * event was safely copied without the writer entering the page. */ smp_rmb(); /* Make sure the page didn't change since we read this */ if (iter->page_stamp != iter_head_page->page->time_stamp || commit > rb_page_commit(iter_head_page)) goto reset; iter->next_event = iter->head + length; return iter->event; reset: /* Reset to the beginning */ iter->page_stamp = iter->read_stamp = iter->head_page->page->time_stamp; iter->head = 0; iter->next_event = 0; iter->missed_events = 1; return NULL; } /* Size is determined by what has been committed */ static __always_inline unsigned rb_page_size(struct buffer_page *bpage) { return rb_page_commit(bpage); } static __always_inline unsigned rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer) { return rb_page_commit(cpu_buffer->commit_page); } static __always_inline unsigned rb_event_index(struct ring_buffer_event *event) { unsigned long addr = (unsigned long)event; return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE; } static void rb_inc_iter(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; /* * The iterator could be on the reader page (it starts there). * But the head could have moved, since the reader was * found. Check for this case and assign the iterator * to the head page instead of next. */ if (iter->head_page == cpu_buffer->reader_page) iter->head_page = rb_set_head_page(cpu_buffer); else rb_inc_page(&iter->head_page); iter->page_stamp = iter->read_stamp = iter->head_page->page->time_stamp; iter->head = 0; iter->next_event = 0; } /* * rb_handle_head_page - writer hit the head page * * Returns: +1 to retry page * 0 to continue * -1 on error */ static int rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *tail_page, struct buffer_page *next_page) { struct buffer_page *new_head; int entries; int type; int ret; entries = rb_page_entries(next_page); /* * The hard part is here. We need to move the head * forward, and protect against both readers on * other CPUs and writers coming in via interrupts. */ type = rb_head_page_set_update(cpu_buffer, next_page, tail_page, RB_PAGE_HEAD); /* * type can be one of four: * NORMAL - an interrupt already moved it for us * HEAD - we are the first to get here. * UPDATE - we are the interrupt interrupting * a current move. * MOVED - a reader on another CPU moved the next * pointer to its reader page. Give up * and try again. */ switch (type) { case RB_PAGE_HEAD: /* * We changed the head to UPDATE, thus * it is our responsibility to update * the counters. */ local_add(entries, &cpu_buffer->overrun); local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); /* * The entries will be zeroed out when we move the * tail page. */ /* still more to do */ break; case RB_PAGE_UPDATE: /* * This is an interrupt that interrupt the * previous update. Still more to do. */ break; case RB_PAGE_NORMAL: /* * An interrupt came in before the update * and processed this for us. * Nothing left to do. */ return 1; case RB_PAGE_MOVED: /* * The reader is on another CPU and just did * a swap with our next_page. * Try again. */ return 1; default: RB_WARN_ON(cpu_buffer, 1); /* WTF??? */ return -1; } /* * Now that we are here, the old head pointer is * set to UPDATE. This will keep the reader from * swapping the head page with the reader page. * The reader (on another CPU) will spin till * we are finished. * * We just need to protect against interrupts * doing the job. We will set the next pointer * to HEAD. After that, we set the old pointer * to NORMAL, but only if it was HEAD before. * otherwise we are an interrupt, and only * want the outer most commit to reset it. */ new_head = next_page; rb_inc_page(&new_head); ret = rb_head_page_set_head(cpu_buffer, new_head, next_page, RB_PAGE_NORMAL); /* * Valid returns are: * HEAD - an interrupt came in and already set it. * NORMAL - One of two things: * 1) We really set it. * 2) A bunch of interrupts came in and moved * the page forward again. */ switch (ret) { case RB_PAGE_HEAD: case RB_PAGE_NORMAL: /* OK */ break; default: RB_WARN_ON(cpu_buffer, 1); return -1; } /* * It is possible that an interrupt came in, * set the head up, then more interrupts came in * and moved it again. When we get back here, * the page would have been set to NORMAL but we * just set it back to HEAD. * * How do you detect this? Well, if that happened * the tail page would have moved. */ if (ret == RB_PAGE_NORMAL) { struct buffer_page *buffer_tail_page; buffer_tail_page = READ_ONCE(cpu_buffer->tail_page); /* * If the tail had moved passed next, then we need * to reset the pointer. */ if (buffer_tail_page != tail_page && buffer_tail_page != next_page) rb_head_page_set_normal(cpu_buffer, new_head, next_page, RB_PAGE_HEAD); } /* * If this was the outer most commit (the one that * changed the original pointer from HEAD to UPDATE), * then it is up to us to reset it to NORMAL. */ if (type == RB_PAGE_HEAD) { ret = rb_head_page_set_normal(cpu_buffer, next_page, tail_page, RB_PAGE_UPDATE); if (RB_WARN_ON(cpu_buffer, ret != RB_PAGE_UPDATE)) return -1; } return 0; } static inline void rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, unsigned long tail, struct rb_event_info *info) { struct buffer_page *tail_page = info->tail_page; struct ring_buffer_event *event; unsigned long length = info->length; /* * Only the event that crossed the page boundary * must fill the old tail_page with padding. */ if (tail >= BUF_PAGE_SIZE) { /* * If the page was filled, then we still need * to update the real_end. Reset it to zero * and the reader will ignore it. */ if (tail == BUF_PAGE_SIZE) tail_page->real_end = 0; local_sub(length, &tail_page->write); return; } event = __rb_page_index(tail_page, tail); /* account for padding bytes */ local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); /* * Save the original length to the meta data. * This will be used by the reader to add lost event * counter. */ tail_page->real_end = tail; /* * If this event is bigger than the minimum size, then * we need to be careful that we don't subtract the * write counter enough to allow another writer to slip * in on this page. * We put in a discarded commit instead, to make sure * that this space is not used again. * * If we are less than the minimum size, we don't need to * worry about it. */ if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) { /* No room for any events */ /* Mark the rest of the page with padding */ rb_event_set_padding(event); /* Make sure the padding is visible before the write update */ smp_wmb(); /* Set the write back to the previous setting */ local_sub(length, &tail_page->write); return; } /* Put in a discarded event */ event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE; event->type_len = RINGBUF_TYPE_PADDING; /* time delta must be non zero */ event->time_delta = 1; /* Make sure the padding is visible before the tail_page->write update */ smp_wmb(); /* Set write to end of buffer */ length = (tail + length) - BUF_PAGE_SIZE; local_sub(length, &tail_page->write); } static inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer); /* * This is the slow path, force gcc not to inline it. */ static noinline struct ring_buffer_event * rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, unsigned long tail, struct rb_event_info *info) { struct buffer_page *tail_page = info->tail_page; struct buffer_page *commit_page = cpu_buffer->commit_page; struct trace_buffer *buffer = cpu_buffer->buffer; struct buffer_page *next_page; int ret; next_page = tail_page; rb_inc_page(&next_page); /* * If for some reason, we had an interrupt storm that made * it all the way around the buffer, bail, and warn * about it. */ if (unlikely(next_page == commit_page)) { local_inc(&cpu_buffer->commit_overrun); goto out_reset; } /* * This is where the fun begins! * * We are fighting against races between a reader that * could be on another CPU trying to swap its reader * page with the buffer head. * * We are also fighting against interrupts coming in and * moving the head or tail on us as well. * * If the next page is the head page then we have filled * the buffer, unless the commit page is still on the * reader page. */ if (rb_is_head_page(next_page, &tail_page->list)) { /* * If the commit is not on the reader page, then * move the header page. */ if (!rb_is_reader_page(cpu_buffer->commit_page)) { /* * If we are not in overwrite mode, * this is easy, just stop here. */ if (!(buffer->flags & RB_FL_OVERWRITE)) { local_inc(&cpu_buffer->dropped_events); goto out_reset; } ret = rb_handle_head_page(cpu_buffer, tail_page, next_page); if (ret < 0) goto out_reset; if (ret) goto out_again; } else { /* * We need to be careful here too. The * commit page could still be on the reader * page. We could have a small buffer, and * have filled up the buffer with events * from interrupts and such, and wrapped. * * Note, if the tail page is also on the * reader_page, we let it move out. */ if (unlikely((cpu_buffer->commit_page != cpu_buffer->tail_page) && (cpu_buffer->commit_page == cpu_buffer->reader_page))) { local_inc(&cpu_buffer->commit_overrun); goto out_reset; } } } rb_tail_page_update(cpu_buffer, tail_page, next_page); out_again: rb_reset_tail(cpu_buffer, tail, info); /* Commit what we have for now. */ rb_end_commit(cpu_buffer); /* rb_end_commit() decs committing */ local_inc(&cpu_buffer->committing); /* fail and let the caller try again */ return ERR_PTR(-EAGAIN); out_reset: /* reset write */ rb_reset_tail(cpu_buffer, tail, info); return NULL; } /* Slow path */ static struct ring_buffer_event * rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs) { if (abs) event->type_len = RINGBUF_TYPE_TIME_STAMP; else event->type_len = RINGBUF_TYPE_TIME_EXTEND; /* Not the first event on the page, or not delta? */ if (abs || rb_event_index(event)) { event->time_delta = delta & TS_MASK; event->array[0] = delta >> TS_SHIFT; } else { /* nope, just zero it */ event->time_delta = 0; event->array[0] = 0; } return skip_time_extend(event); } #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK static inline bool sched_clock_stable(void) { return true; } #endif static void rb_check_timestamp(struct ring_buffer_per_cpu *cpu_buffer, struct rb_event_info *info) { u64 write_stamp; WARN_ONCE(1, "Delta way too big! %llu ts=%llu before=%llu after=%llu write stamp=%llu\n%s", (unsigned long long)info->delta, (unsigned long long)info->ts, (unsigned long long)info->before, (unsigned long long)info->after, (unsigned long long)(rb_time_read(&cpu_buffer->write_stamp, &write_stamp) ? write_stamp : 0), sched_clock_stable() ? "" : "If you just came from a suspend/resume,\n" "please switch to the trace global clock:\n" " echo global > /sys/kernel/debug/tracing/trace_clock\n" "or add trace_clock=global to the kernel command line\n"); } static void rb_add_timestamp(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event **event, struct rb_event_info *info, u64 *delta, unsigned int *length) { bool abs = info->add_timestamp & (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE); if (unlikely(info->delta > (1ULL << 59))) { /* * Some timers can use more than 59 bits, and when a timestamp * is added to the buffer, it will lose those bits. */ if (abs && (info->ts & TS_MSB)) { info->delta &= ABS_TS_MASK; /* did the clock go backwards */ } else if (info->before == info->after && info->before > info->ts) { /* not interrupted */ static int once; /* * This is possible with a recalibrating of the TSC. * Do not produce a call stack, but just report it. */ if (!once) { once++; pr_warn("Ring buffer clock went backwards: %llu -> %llu\n", info->before, info->ts); } } else rb_check_timestamp(cpu_buffer, info); if (!abs) info->delta = 0; } *event = rb_add_time_stamp(*event, info->delta, abs); *length -= RB_LEN_TIME_EXTEND; *delta = 0; } /** * rb_update_event - update event type and data * @cpu_buffer: The per cpu buffer of the @event * @event: the event to update * @info: The info to update the @event with (contains length and delta) * * Update the type and data fields of the @event. The length * is the actual size that is written to the ring buffer, * and with this, we can determine what to place into the * data field. */ static void rb_update_event(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event, struct rb_event_info *info) { unsigned length = info->length; u64 delta = info->delta; unsigned int nest = local_read(&cpu_buffer->committing) - 1; if (!WARN_ON_ONCE(nest >= MAX_NEST)) cpu_buffer->event_stamp[nest] = info->ts; /* * If we need to add a timestamp, then we * add it to the start of the reserved space. */ if (unlikely(info->add_timestamp)) rb_add_timestamp(cpu_buffer, &event, info, &delta, &length); event->time_delta = delta; length -= RB_EVNT_HDR_SIZE; if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) { event->type_len = 0; event->array[0] = length; } else event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT); } static unsigned rb_calculate_event_length(unsigned length) { struct ring_buffer_event event; /* Used only for sizeof array */ /* zero length can cause confusions */ if (!length) length++; if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) length += sizeof(event.array[0]); length += RB_EVNT_HDR_SIZE; length = ALIGN(length, RB_ARCH_ALIGNMENT); /* * In case the time delta is larger than the 27 bits for it * in the header, we need to add a timestamp. If another * event comes in when trying to discard this one to increase * the length, then the timestamp will be added in the allocated * space of this event. If length is bigger than the size needed * for the TIME_EXTEND, then padding has to be used. The events * length must be either RB_LEN_TIME_EXTEND, or greater than or equal * to RB_LEN_TIME_EXTEND + 8, as 8 is the minimum size for padding. * As length is a multiple of 4, we only need to worry if it * is 12 (RB_LEN_TIME_EXTEND + 4). */ if (length == RB_LEN_TIME_EXTEND + RB_ALIGNMENT) length += RB_ALIGNMENT; return length; } static u64 rb_time_delta(struct ring_buffer_event *event) { switch (event->type_len) { case RINGBUF_TYPE_PADDING: return 0; case RINGBUF_TYPE_TIME_EXTEND: return rb_event_time_stamp(event); case RINGBUF_TYPE_TIME_STAMP: return 0; case RINGBUF_TYPE_DATA: return event->time_delta; default: return 0; } } static inline int rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) { unsigned long new_index, old_index; struct buffer_page *bpage; unsigned long index; unsigned long addr; u64 write_stamp; u64 delta; new_index = rb_event_index(event); old_index = new_index + rb_event_ts_length(event); addr = (unsigned long)event; addr &= PAGE_MASK; bpage = READ_ONCE(cpu_buffer->tail_page); delta = rb_time_delta(event); if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp)) return 0; /* Make sure the write stamp is read before testing the location */ barrier(); if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) { unsigned long write_mask = local_read(&bpage->write) & ~RB_WRITE_MASK; unsigned long event_length = rb_event_length(event); /* Something came in, can't discard */ if (!rb_time_cmpxchg(&cpu_buffer->write_stamp, write_stamp, write_stamp - delta)) return 0; /* * It's possible that the event time delta is zero * (has the same time stamp as the previous event) * in which case write_stamp and before_stamp could * be the same. In such a case, force before_stamp * to be different than write_stamp. It doesn't * matter what it is, as long as its different. */ if (!delta) rb_time_set(&cpu_buffer->before_stamp, 0); /* * If an event were to come in now, it would see that the * write_stamp and the before_stamp are different, and assume * that this event just added itself before updating * the write stamp. The interrupting event will fix the * write stamp for us, and use the before stamp as its delta. */ /* * This is on the tail page. It is possible that * a write could come in and move the tail page * and write to the next page. That is fine * because we just shorten what is on this page. */ old_index += write_mask; new_index += write_mask; index = local_cmpxchg(&bpage->write, old_index, new_index); if (index == old_index) { /* update counters */ local_sub(event_length, &cpu_buffer->entries_bytes); return 1; } } /* could not discard */ return 0; } static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer) { local_inc(&cpu_buffer->committing); local_inc(&cpu_buffer->commits); } static __always_inline void rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) { unsigned long max_count; /* * We only race with interrupts and NMIs on this CPU. * If we own the commit event, then we can commit * all others that interrupted us, since the interruptions * are in stack format (they finish before they come * back to us). This allows us to do a simple loop to * assign the commit to the tail. */ again: max_count = cpu_buffer->nr_pages * 100; while (cpu_buffer->commit_page != READ_ONCE(cpu_buffer->tail_page)) { if (RB_WARN_ON(cpu_buffer, !(--max_count))) return; if (RB_WARN_ON(cpu_buffer, rb_is_reader_page(cpu_buffer->tail_page))) return; local_set(&cpu_buffer->commit_page->page->commit, rb_page_write(cpu_buffer->commit_page)); rb_inc_page(&cpu_buffer->commit_page); /* add barrier to keep gcc from optimizing too much */ barrier(); } while (rb_commit_index(cpu_buffer) != rb_page_write(cpu_buffer->commit_page)) { local_set(&cpu_buffer->commit_page->page->commit, rb_page_write(cpu_buffer->commit_page)); RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->commit_page->page->commit) & ~RB_WRITE_MASK); barrier(); } /* again, keep gcc from optimizing */ barrier(); /* * If an interrupt came in just after the first while loop * and pushed the tail page forward, we will be left with * a dangling commit that will never go forward. */ if (unlikely(cpu_buffer->commit_page != READ_ONCE(cpu_buffer->tail_page))) goto again; } static __always_inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer) { unsigned long commits; if (RB_WARN_ON(cpu_buffer, !local_read(&cpu_buffer->committing))) return; again: commits = local_read(&cpu_buffer->commits); /* synchronize with interrupts */ barrier(); if (local_read(&cpu_buffer->committing) == 1) rb_set_commit_to_write(cpu_buffer); local_dec(&cpu_buffer->committing); /* synchronize with interrupts */ barrier(); /* * Need to account for interrupts coming in between the * updating of the commit page and the clearing of the * committing counter. */ if (unlikely(local_read(&cpu_buffer->commits) != commits) && !local_read(&cpu_buffer->committing)) { local_inc(&cpu_buffer->committing); goto again; } } static inline void rb_event_discard(struct ring_buffer_event *event) { if (extended_time(event)) event = skip_time_extend(event); /* array[0] holds the actual length for the discarded event */ event->array[0] = rb_event_data_length(event) - RB_EVNT_HDR_SIZE; event->type_len = RINGBUF_TYPE_PADDING; /* time delta must be non zero */ if (!event->time_delta) event->time_delta = 1; } static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) { local_inc(&cpu_buffer->entries); rb_end_commit(cpu_buffer); } static __always_inline void rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) { if (buffer->irq_work.waiters_pending) { buffer->irq_work.waiters_pending = false; /* irq_work_queue() supplies it's own memory barriers */ irq_work_queue(&buffer->irq_work.work); } if (cpu_buffer->irq_work.waiters_pending) { cpu_buffer->irq_work.waiters_pending = false; /* irq_work_queue() supplies it's own memory barriers */ irq_work_queue(&cpu_buffer->irq_work.work); } if (cpu_buffer->last_pages_touch == local_read(&cpu_buffer->pages_touched)) return; if (cpu_buffer->reader_page == cpu_buffer->commit_page) return; if (!cpu_buffer->irq_work.full_waiters_pending) return; cpu_buffer->last_pages_touch = local_read(&cpu_buffer->pages_touched); if (!full_hit(buffer, cpu_buffer->cpu, cpu_buffer->shortest_full)) return; cpu_buffer->irq_work.wakeup_full = true; cpu_buffer->irq_work.full_waiters_pending = false; /* irq_work_queue() supplies it's own memory barriers */ irq_work_queue(&cpu_buffer->irq_work.work); } #ifdef CONFIG_RING_BUFFER_RECORD_RECURSION # define do_ring_buffer_record_recursion() \ do_ftrace_record_recursion(_THIS_IP_, _RET_IP_) #else # define do_ring_buffer_record_recursion() do { } while (0) #endif /* * The lock and unlock are done within a preempt disable section. * The current_context per_cpu variable can only be modified * by the current task between lock and unlock. But it can * be modified more than once via an interrupt. To pass this * information from the lock to the unlock without having to * access the 'in_interrupt()' functions again (which do show * a bit of overhead in something as critical as function tracing, * we use a bitmask trick. * * bit 1 = NMI context * bit 2 = IRQ context * bit 3 = SoftIRQ context * bit 4 = normal context. * * This works because this is the order of contexts that can * preempt other contexts. A SoftIRQ never preempts an IRQ * context. * * When the context is determined, the corresponding bit is * checked and set (if it was set, then a recursion of that context * happened). * * On unlock, we need to clear this bit. To do so, just subtract * 1 from the current_context and AND it to itself. * * (binary) * 101 - 1 = 100 * 101 & 100 = 100 (clearing bit zero) * * 1010 - 1 = 1001 * 1010 & 1001 = 1000 (clearing bit 1) * * The least significant bit can be cleared this way, and it * just so happens that it is the same bit corresponding to * the current context. * * Now the TRANSITION bit breaks the above slightly. The TRANSITION bit * is set when a recursion is detected at the current context, and if * the TRANSITION bit is already set, it will fail the recursion. * This is needed because there's a lag between the changing of * interrupt context and updating the preempt count. In this case, * a false positive will be found. To handle this, one extra recursion * is allowed, and this is done by the TRANSITION bit. If the TRANSITION * bit is already set, then it is considered a recursion and the function * ends. Otherwise, the TRANSITION bit is set, and that bit is returned. * * On the trace_recursive_unlock(), the TRANSITION bit will be the first * to be cleared. Even if it wasn't the context that set it. That is, * if an interrupt comes in while NORMAL bit is set and the ring buffer * is called before preempt_count() is updated, since the check will * be on the NORMAL bit, the TRANSITION bit will then be set. If an * NMI then comes in, it will set the NMI bit, but when the NMI code * does the trace_recursive_unlock() it will clear the TRANSITION bit * and leave the NMI bit set. But this is fine, because the interrupt * code that set the TRANSITION bit will then clear the NMI bit when it * calls trace_recursive_unlock(). If another NMI comes in, it will * set the TRANSITION bit and continue. * * Note: The TRANSITION bit only handles a single transition between context. */ static __always_inline int trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) { unsigned int val = cpu_buffer->current_context; int bit = interrupt_context_level(); bit = RB_CTX_NORMAL - bit; if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) { /* * It is possible that this was called by transitioning * between interrupt context, and preempt_count() has not * been updated yet. In this case, use the TRANSITION bit. */ bit = RB_CTX_TRANSITION; if (val & (1 << (bit + cpu_buffer->nest))) { do_ring_buffer_record_recursion(); return 1; } } val |= (1 << (bit + cpu_buffer->nest)); cpu_buffer->current_context = val; return 0; } static __always_inline void trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer) { cpu_buffer->current_context &= cpu_buffer->current_context - (1 << cpu_buffer->nest); } /* The recursive locking above uses 5 bits */ #define NESTED_BITS 5 /** * ring_buffer_nest_start - Allow to trace while nested * @buffer: The ring buffer to modify * * The ring buffer has a safety mechanism to prevent recursion. * But there may be a case where a trace needs to be done while * tracing something else. In this case, calling this function * will allow this function to nest within a currently active * ring_buffer_lock_reserve(). * * Call this function before calling another ring_buffer_lock_reserve() and * call ring_buffer_nest_end() after the nested ring_buffer_unlock_commit(). */ void ring_buffer_nest_start(struct trace_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; int cpu; /* Enabled by ring_buffer_nest_end() */ preempt_disable_notrace(); cpu = raw_smp_processor_id(); cpu_buffer = buffer->buffers[cpu]; /* This is the shift value for the above recursive locking */ cpu_buffer->nest += NESTED_BITS; } /** * ring_buffer_nest_end - Allow to trace while nested * @buffer: The ring buffer to modify * * Must be called after ring_buffer_nest_start() and after the * ring_buffer_unlock_commit(). */ void ring_buffer_nest_end(struct trace_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; int cpu; /* disabled by ring_buffer_nest_start() */ cpu = raw_smp_processor_id(); cpu_buffer = buffer->buffers[cpu]; /* This is the shift value for the above recursive locking */ cpu_buffer->nest -= NESTED_BITS; preempt_enable_notrace(); } /** * ring_buffer_unlock_commit - commit a reserved * @buffer: The buffer to commit to * @event: The event pointer to commit. * * This commits the data to the ring buffer, and releases any locks held. * * Must be paired with ring_buffer_lock_reserve. */ int ring_buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) { struct ring_buffer_per_cpu *cpu_buffer; int cpu = raw_smp_processor_id(); cpu_buffer = buffer->buffers[cpu]; rb_commit(cpu_buffer, event); rb_wakeups(buffer, cpu_buffer); trace_recursive_unlock(cpu_buffer); preempt_enable_notrace(); return 0; } EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit); /* Special value to validate all deltas on a page. */ #define CHECK_FULL_PAGE 1L #ifdef CONFIG_RING_BUFFER_VALIDATE_TIME_DELTAS static void dump_buffer_page(struct buffer_data_page *bpage, struct rb_event_info *info, unsigned long tail) { struct ring_buffer_event *event; u64 ts, delta; int e; ts = bpage->time_stamp; pr_warn(" [%lld] PAGE TIME STAMP\n", ts); for (e = 0; e < tail; e += rb_event_length(event)) { event = (struct ring_buffer_event *)(bpage->data + e); switch (event->type_len) { case RINGBUF_TYPE_TIME_EXTEND: delta = rb_event_time_stamp(event); ts += delta; pr_warn(" [%lld] delta:%lld TIME EXTEND\n", ts, delta); break; case RINGBUF_TYPE_TIME_STAMP: delta = rb_event_time_stamp(event); ts = rb_fix_abs_ts(delta, ts); pr_warn(" [%lld] absolute:%lld TIME STAMP\n", ts, delta); break; case RINGBUF_TYPE_PADDING: ts += event->time_delta; pr_warn(" [%lld] delta:%d PADDING\n", ts, event->time_delta); break; case RINGBUF_TYPE_DATA: ts += event->time_delta; pr_warn(" [%lld] delta:%d\n", ts, event->time_delta); break; default: break; } } } static DEFINE_PER_CPU(atomic_t, checking); static atomic_t ts_dump; /* * Check if the current event time stamp matches the deltas on * the buffer page. */ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, struct rb_event_info *info, unsigned long tail) { struct ring_buffer_event *event; struct buffer_data_page *bpage; u64 ts, delta; bool full = false; int e; bpage = info->tail_page->page; if (tail == CHECK_FULL_PAGE) { full = true; tail = local_read(&bpage->commit); } else if (info->add_timestamp & (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE)) { /* Ignore events with absolute time stamps */ return; } /* * Do not check the first event (skip possible extends too). * Also do not check if previous events have not been committed. */ if (tail <= 8 || tail > local_read(&bpage->commit)) return; /* * If this interrupted another event, */ if (atomic_inc_return(this_cpu_ptr(&checking)) != 1) goto out; ts = bpage->time_stamp; for (e = 0; e < tail; e += rb_event_length(event)) { event = (struct ring_buffer_event *)(bpage->data + e); switch (event->type_len) { case RINGBUF_TYPE_TIME_EXTEND: delta = rb_event_time_stamp(event); ts += delta; break; case RINGBUF_TYPE_TIME_STAMP: delta = rb_event_time_stamp(event); ts = rb_fix_abs_ts(delta, ts); break; case RINGBUF_TYPE_PADDING: if (event->time_delta == 1) break; fallthrough; case RINGBUF_TYPE_DATA: ts += event->time_delta; break; default: RB_WARN_ON(cpu_buffer, 1); } } if ((full && ts > info->ts) || (!full && ts + info->delta != info->ts)) { /* If another report is happening, ignore this one */ if (atomic_inc_return(&ts_dump) != 1) { atomic_dec(&ts_dump); goto out; } atomic_inc(&cpu_buffer->record_disabled); /* There's some cases in boot up that this can happen */ WARN_ON_ONCE(system_state != SYSTEM_BOOTING); pr_warn("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s\n", cpu_buffer->cpu, ts + info->delta, info->ts, info->delta, info->before, info->after, full ? " (full)" : ""); dump_buffer_page(bpage, info, tail); atomic_dec(&ts_dump); /* Do not re-enable checking */ return; } out: atomic_dec(this_cpu_ptr(&checking)); } #else static inline void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, struct rb_event_info *info, unsigned long tail) { } #endif /* CONFIG_RING_BUFFER_VALIDATE_TIME_DELTAS */ static struct ring_buffer_event * __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, struct rb_event_info *info) { struct ring_buffer_event *event; struct buffer_page *tail_page; unsigned long tail, write, w; bool a_ok; bool b_ok; /* Don't let the compiler play games with cpu_buffer->tail_page */ tail_page = info->tail_page = READ_ONCE(cpu_buffer->tail_page); /*A*/ w = local_read(&tail_page->write) & RB_WRITE_MASK; barrier(); b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); barrier(); info->ts = rb_time_stamp(cpu_buffer->buffer); if ((info->add_timestamp & RB_ADD_STAMP_ABSOLUTE)) { info->delta = info->ts; } else { /* * If interrupting an event time update, we may need an * absolute timestamp. * Don't bother if this is the start of a new page (w == 0). */ if (unlikely(!a_ok || !b_ok || (info->before != info->after && w))) { info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND; info->length += RB_LEN_TIME_EXTEND; } else { info->delta = info->ts - info->after; if (unlikely(test_time_stamp(info->delta))) { info->add_timestamp |= RB_ADD_STAMP_EXTEND; info->length += RB_LEN_TIME_EXTEND; } } } /*B*/ rb_time_set(&cpu_buffer->before_stamp, info->ts); /*C*/ write = local_add_return(info->length, &tail_page->write); /* set write to only the index of the write */ write &= RB_WRITE_MASK; tail = write - info->length; /* See if we shot pass the end of this buffer page */ if (unlikely(write > BUF_PAGE_SIZE)) { /* before and after may now different, fix it up*/ b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); if (a_ok && b_ok && info->before != info->after) (void)rb_time_cmpxchg(&cpu_buffer->before_stamp, info->before, info->after); if (a_ok && b_ok) check_buffer(cpu_buffer, info, CHECK_FULL_PAGE); return rb_move_tail(cpu_buffer, tail, info); } if (likely(tail == w)) { u64 save_before; bool s_ok; /* Nothing interrupted us between A and C */ /*D*/ rb_time_set(&cpu_buffer->write_stamp, info->ts); barrier(); /*E*/ s_ok = rb_time_read(&cpu_buffer->before_stamp, &save_before); RB_WARN_ON(cpu_buffer, !s_ok); if (likely(!(info->add_timestamp & (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE)))) /* This did not interrupt any time update */ info->delta = info->ts - info->after; else /* Just use full timestamp for interrupting event */ info->delta = info->ts; barrier(); check_buffer(cpu_buffer, info, tail); if (unlikely(info->ts != save_before)) { /* SLOW PATH - Interrupted between C and E */ a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); RB_WARN_ON(cpu_buffer, !a_ok); /* Write stamp must only go forward */ if (save_before > info->after) { /* * We do not care about the result, only that * it gets updated atomically. */ (void)rb_time_cmpxchg(&cpu_buffer->write_stamp, info->after, save_before); } } } else { u64 ts; /* SLOW PATH - Interrupted between A and C */ a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); /* Was interrupted before here, write_stamp must be valid */ RB_WARN_ON(cpu_buffer, !a_ok); ts = rb_time_stamp(cpu_buffer->buffer); barrier(); /*E*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) && info->after < ts && rb_time_cmpxchg(&cpu_buffer->write_stamp, info->after, ts)) { /* Nothing came after this event between C and E */ info->delta = ts - info->after; } else { /* * Interrupted between C and E: * Lost the previous events time stamp. Just set the * delta to zero, and this will be the same time as * the event this event interrupted. And the events that * came after this will still be correct (as they would * have built their delta on the previous event. */ info->delta = 0; } info->ts = ts; info->add_timestamp &= ~RB_ADD_STAMP_FORCE; } /* * If this is the first commit on the page, then it has the same * timestamp as the page itself. */ if (unlikely(!tail && !(info->add_timestamp & (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE)))) info->delta = 0; /* We reserved something on the buffer */ event = __rb_page_index(tail_page, tail); rb_update_event(cpu_buffer, event, info); local_inc(&tail_page->entries); /* * If this is the first commit on the page, then update * its timestamp. */ if (unlikely(!tail)) tail_page->page->time_stamp = info->ts; /* account for these added bytes */ local_add(info->length, &cpu_buffer->entries_bytes); return event; } static __always_inline struct ring_buffer_event * rb_reserve_next_event(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer, unsigned long length) { struct ring_buffer_event *event; struct rb_event_info info; int nr_loops = 0; int add_ts_default; rb_start_commit(cpu_buffer); /* The commit page can not change after this */ #ifdef CONFIG_RING_BUFFER_ALLOW_SWAP /* * Due to the ability to swap a cpu buffer from a buffer * it is possible it was swapped before we committed. * (committing stops a swap). We check for it here and * if it happened, we have to fail the write. */ barrier(); if (unlikely(READ_ONCE(cpu_buffer->buffer) != buffer)) { local_dec(&cpu_buffer->committing); local_dec(&cpu_buffer->commits); return NULL; } #endif info.length = rb_calculate_event_length(length); if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) { add_ts_default = RB_ADD_STAMP_ABSOLUTE; info.length += RB_LEN_TIME_EXTEND; } else { add_ts_default = RB_ADD_STAMP_NONE; } again: info.add_timestamp = add_ts_default; info.delta = 0; /* * We allow for interrupts to reenter here and do a trace. * If one does, it will cause this original code to loop * back here. Even with heavy interrupts happening, this * should only happen a few times in a row. If this happens * 1000 times in a row, there must be either an interrupt * storm or we have something buggy. * Bail! */ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000)) goto out_fail; event = __rb_reserve_next(cpu_buffer, &info); if (unlikely(PTR_ERR(event) == -EAGAIN)) { if (info.add_timestamp & (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND)) info.length -= RB_LEN_TIME_EXTEND; goto again; } if (likely(event)) return event; out_fail: rb_end_commit(cpu_buffer); return NULL; } /** * ring_buffer_lock_reserve - reserve a part of the buffer * @buffer: the ring buffer to reserve from * @length: the length of the data to reserve (excluding event header) * * Returns a reserved event on the ring buffer to copy directly to. * The user of this interface will need to get the body to write into * and can use the ring_buffer_event_data() interface. * * The length is the length of the data needed, not the event length * which also includes the event header. * * Must be paired with ring_buffer_unlock_commit, unless NULL is returned. * If NULL is returned, then nothing has been allocated or locked. */ struct ring_buffer_event * ring_buffer_lock_reserve(struct trace_buffer *buffer, unsigned long length) { struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; int cpu; /* If we are tracing schedule, we don't want to recurse */ preempt_disable_notrace(); if (unlikely(atomic_read(&buffer->record_disabled))) goto out; cpu = raw_smp_processor_id(); if (unlikely(!cpumask_test_cpu(cpu, buffer->cpumask))) goto out; cpu_buffer = buffer->buffers[cpu]; if (unlikely(atomic_read(&cpu_buffer->record_disabled))) goto out; if (unlikely(length > BUF_MAX_DATA_SIZE)) goto out; if (unlikely(trace_recursive_lock(cpu_buffer))) goto out; event = rb_reserve_next_event(buffer, cpu_buffer, length); if (!event) goto out_unlock; return event; out_unlock: trace_recursive_unlock(cpu_buffer); out: preempt_enable_notrace(); return NULL; } EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve); /* * Decrement the entries to the page that an event is on. * The event does not even need to exist, only the pointer * to the page it is on. This may only be called before the commit * takes place. */ static inline void rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) { unsigned long addr = (unsigned long)event; struct buffer_page *bpage = cpu_buffer->commit_page; struct buffer_page *start; addr &= PAGE_MASK; /* Do the likely case first */ if (likely(bpage->page == (void *)addr)) { local_dec(&bpage->entries); return; } /* * Because the commit page may be on the reader page we * start with the next page and check the end loop there. */ rb_inc_page(&bpage); start = bpage; do { if (bpage->page == (void *)addr) { local_dec(&bpage->entries); return; } rb_inc_page(&bpage); } while (bpage != start); /* commit not part of this buffer?? */ RB_WARN_ON(cpu_buffer, 1); } /** * ring_buffer_discard_commit - discard an event that has not been committed * @buffer: the ring buffer * @event: non committed event to discard * * Sometimes an event that is in the ring buffer needs to be ignored. * This function lets the user discard an event in the ring buffer * and then that event will not be read later. * * This function only works if it is called before the item has been * committed. It will try to free the event from the ring buffer * if another event has not been added behind it. * * If another event has been added behind it, it will set the event * up as discarded, and perform the commit. * * If this function is called, do not call ring_buffer_unlock_commit on * the event. */ void ring_buffer_discard_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) { struct ring_buffer_per_cpu *cpu_buffer; int cpu; /* The event is discarded regardless */ rb_event_discard(event); cpu = smp_processor_id(); cpu_buffer = buffer->buffers[cpu]; /* * This must only be called if the event has not been * committed yet. Thus we can assume that preemption * is still disabled. */ RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing)); rb_decrement_entry(cpu_buffer, event); if (rb_try_to_discard(cpu_buffer, event)) goto out; out: rb_end_commit(cpu_buffer); trace_recursive_unlock(cpu_buffer); preempt_enable_notrace(); } EXPORT_SYMBOL_GPL(ring_buffer_discard_commit); /** * ring_buffer_write - write data to the buffer without reserving * @buffer: The ring buffer to write to. * @length: The length of the data being written (excluding the event header) * @data: The data to write to the buffer. * * This is like ring_buffer_lock_reserve and ring_buffer_unlock_commit as * one function. If you already have the data to write to the buffer, it * may be easier to simply call this function. * * Note, like ring_buffer_lock_reserve, the length is the length of the data * and not the length of the event which would hold the header. */ int ring_buffer_write(struct trace_buffer *buffer, unsigned long length, void *data) { struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; void *body; int ret = -EBUSY; int cpu; preempt_disable_notrace(); if (atomic_read(&buffer->record_disabled)) goto out; cpu = raw_smp_processor_id(); if (!cpumask_test_cpu(cpu, buffer->cpumask)) goto out; cpu_buffer = buffer->buffers[cpu]; if (atomic_read(&cpu_buffer->record_disabled)) goto out; if (length > BUF_MAX_DATA_SIZE) goto out; if (unlikely(trace_recursive_lock(cpu_buffer))) goto out; event = rb_reserve_next_event(buffer, cpu_buffer, length); if (!event) goto out_unlock; body = rb_event_data(event); memcpy(body, data, length); rb_commit(cpu_buffer, event); rb_wakeups(buffer, cpu_buffer); ret = 0; out_unlock: trace_recursive_unlock(cpu_buffer); out: preempt_enable_notrace(); return ret; } EXPORT_SYMBOL_GPL(ring_buffer_write); static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) { struct buffer_page *reader = cpu_buffer->reader_page; struct buffer_page *head = rb_set_head_page(cpu_buffer); struct buffer_page *commit = cpu_buffer->commit_page; /* In case of error, head will be NULL */ if (unlikely(!head)) return true; /* Reader should exhaust content in reader page */ if (reader->read != rb_page_commit(reader)) return false; /* * If writers are committing on the reader page, knowing all * committed content has been read, the ring buffer is empty. */ if (commit == reader) return true; /* * If writers are committing on a page other than reader page * and head page, there should always be content to read. */ if (commit != head) return false; /* * Writers are committing on the head page, we just need * to care about there're committed data, and the reader will * swap reader page with head page when it is to read data. */ return rb_page_commit(commit) == 0; } /** * ring_buffer_record_disable - stop all writes into the buffer * @buffer: The ring buffer to stop writes to. * * This prevents all writes to the buffer. Any attempt to write * to the buffer after this will fail and return NULL. * * The caller should call synchronize_rcu() after this. */ void ring_buffer_record_disable(struct trace_buffer *buffer) { atomic_inc(&buffer->record_disabled); } EXPORT_SYMBOL_GPL(ring_buffer_record_disable); /** * ring_buffer_record_enable - enable writes to the buffer * @buffer: The ring buffer to enable writes * * Note, multiple disables will need the same number of enables * to truly enable the writing (much like preempt_disable). */ void ring_buffer_record_enable(struct trace_buffer *buffer) { atomic_dec(&buffer->record_disabled); } EXPORT_SYMBOL_GPL(ring_buffer_record_enable); /** * ring_buffer_record_off - stop all writes into the buffer * @buffer: The ring buffer to stop writes to. * * This prevents all writes to the buffer. Any attempt to write * to the buffer after this will fail and return NULL. * * This is different than ring_buffer_record_disable() as * it works like an on/off switch, where as the disable() version * must be paired with a enable(). */ void ring_buffer_record_off(struct trace_buffer *buffer) { unsigned int rd; unsigned int new_rd; do { rd = atomic_read(&buffer->record_disabled); new_rd = rd | RB_BUFFER_OFF; } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); } EXPORT_SYMBOL_GPL(ring_buffer_record_off); /** * ring_buffer_record_on - restart writes into the buffer * @buffer: The ring buffer to start writes to. * * This enables all writes to the buffer that was disabled by * ring_buffer_record_off(). * * This is different than ring_buffer_record_enable() as * it works like an on/off switch, where as the enable() version * must be paired with a disable(). */ void ring_buffer_record_on(struct trace_buffer *buffer) { unsigned int rd; unsigned int new_rd; do { rd = atomic_read(&buffer->record_disabled); new_rd = rd & ~RB_BUFFER_OFF; } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); } EXPORT_SYMBOL_GPL(ring_buffer_record_on); /** * ring_buffer_record_is_on - return true if the ring buffer can write * @buffer: The ring buffer to see if write is enabled * * Returns true if the ring buffer is in a state that it accepts writes. */ bool ring_buffer_record_is_on(struct trace_buffer *buffer) { return !atomic_read(&buffer->record_disabled); } /** * ring_buffer_record_is_set_on - return true if the ring buffer is set writable * @buffer: The ring buffer to see if write is set enabled * * Returns true if the ring buffer is set writable by ring_buffer_record_on(). * Note that this does NOT mean it is in a writable state. * * It may return true when the ring buffer has been disabled by * ring_buffer_record_disable(), as that is a temporary disabling of * the ring buffer. */ bool ring_buffer_record_is_set_on(struct trace_buffer *buffer) { return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF); } /** * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer * @buffer: The ring buffer to stop writes to. * @cpu: The CPU buffer to stop * * This prevents all writes to the buffer. Any attempt to write * to the buffer after this will fail and return NULL. * * The caller should call synchronize_rcu() after this. */ void ring_buffer_record_disable_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return; cpu_buffer = buffer->buffers[cpu]; atomic_inc(&cpu_buffer->record_disabled); } EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu); /** * ring_buffer_record_enable_cpu - enable writes to the buffer * @buffer: The ring buffer to enable writes * @cpu: The CPU to enable. * * Note, multiple disables will need the same number of enables * to truly enable the writing (much like preempt_disable). */ void ring_buffer_record_enable_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return; cpu_buffer = buffer->buffers[cpu]; atomic_dec(&cpu_buffer->record_disabled); } EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu); /* * The total entries in the ring buffer is the running counter * of entries entered into the ring buffer, minus the sum of * the entries read from the ring buffer and the number of * entries that were overwritten. */ static inline unsigned long rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer) { return local_read(&cpu_buffer->entries) - (local_read(&cpu_buffer->overrun) + cpu_buffer->read); } /** * ring_buffer_oldest_event_ts - get the oldest event timestamp from the buffer * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu) { unsigned long flags; struct ring_buffer_per_cpu *cpu_buffer; struct buffer_page *bpage; u64 ret = 0; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; cpu_buffer = buffer->buffers[cpu]; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); /* * if the tail is on reader_page, oldest time stamp is on the reader * page */ if (cpu_buffer->tail_page == cpu_buffer->reader_page) bpage = cpu_buffer->reader_page; else bpage = rb_set_head_page(cpu_buffer); if (bpage) ret = bpage->page->time_stamp; raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); return ret; } EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts); /** * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ unsigned long ring_buffer_bytes_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long ret; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; cpu_buffer = buffer->buffers[cpu]; ret = local_read(&cpu_buffer->entries_bytes) - cpu_buffer->read_bytes; return ret; } EXPORT_SYMBOL_GPL(ring_buffer_bytes_cpu); /** * ring_buffer_entries_cpu - get the number of entries in a cpu buffer * @buffer: The ring buffer * @cpu: The per CPU buffer to get the entries from. */ unsigned long ring_buffer_entries_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; cpu_buffer = buffer->buffers[cpu]; return rb_num_of_entries(cpu_buffer); } EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu); /** * ring_buffer_overrun_cpu - get the number of overruns caused by the ring * buffer wrapping around (only if RB_FL_OVERWRITE is on). * @buffer: The ring buffer * @cpu: The per CPU buffer to get the number of overruns from */ unsigned long ring_buffer_overrun_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long ret; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; cpu_buffer = buffer->buffers[cpu]; ret = local_read(&cpu_buffer->overrun); return ret; } EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu); /** * ring_buffer_commit_overrun_cpu - get the number of overruns caused by * commits failing due to the buffer wrapping around while there are uncommitted * events, such as during an interrupt storm. * @buffer: The ring buffer * @cpu: The per CPU buffer to get the number of overruns from */ unsigned long ring_buffer_commit_overrun_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long ret; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; cpu_buffer = buffer->buffers[cpu]; ret = local_read(&cpu_buffer->commit_overrun); return ret; } EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu); /** * ring_buffer_dropped_events_cpu - get the number of dropped events caused by * the ring buffer filling up (only if RB_FL_OVERWRITE is off). * @buffer: The ring buffer * @cpu: The per CPU buffer to get the number of overruns from */ unsigned long ring_buffer_dropped_events_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long ret; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; cpu_buffer = buffer->buffers[cpu]; ret = local_read(&cpu_buffer->dropped_events); return ret; } EXPORT_SYMBOL_GPL(ring_buffer_dropped_events_cpu); /** * ring_buffer_read_events_cpu - get the number of events successfully read * @buffer: The ring buffer * @cpu: The per CPU buffer to get the number of events read */ unsigned long ring_buffer_read_events_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; cpu_buffer = buffer->buffers[cpu]; return cpu_buffer->read; } EXPORT_SYMBOL_GPL(ring_buffer_read_events_cpu); /** * ring_buffer_entries - get the number of entries in a buffer * @buffer: The ring buffer * * Returns the total number of entries in the ring buffer * (all CPU entries) */ unsigned long ring_buffer_entries(struct trace_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long entries = 0; int cpu; /* if you care about this being correct, lock the buffer */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; entries += rb_num_of_entries(cpu_buffer); } return entries; } EXPORT_SYMBOL_GPL(ring_buffer_entries); /** * ring_buffer_overruns - get the number of overruns in buffer * @buffer: The ring buffer * * Returns the total number of overruns in the ring buffer * (all CPU entries) */ unsigned long ring_buffer_overruns(struct trace_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long overruns = 0; int cpu; /* if you care about this being correct, lock the buffer */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; overruns += local_read(&cpu_buffer->overrun); } return overruns; } EXPORT_SYMBOL_GPL(ring_buffer_overruns); static void rb_iter_reset(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; /* Iterator usage is expected to have record disabled */ iter->head_page = cpu_buffer->reader_page; iter->head = cpu_buffer->reader_page->read; iter->next_event = iter->head; iter->cache_reader_page = iter->head_page; iter->cache_read = cpu_buffer->read; if (iter->head) { iter->read_stamp = cpu_buffer->read_stamp; iter->page_stamp = cpu_buffer->reader_page->page->time_stamp; } else { iter->read_stamp = iter->head_page->page->time_stamp; iter->page_stamp = iter->read_stamp; } } /** * ring_buffer_iter_reset - reset an iterator * @iter: The iterator to reset * * Resets the iterator, so that it will start from the beginning * again. */ void ring_buffer_iter_reset(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; if (!iter) return; cpu_buffer = iter->cpu_buffer; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); rb_iter_reset(iter); raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); /** * ring_buffer_iter_empty - check if an iterator has no more to read * @iter: The iterator to check */ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; struct buffer_page *reader; struct buffer_page *head_page; struct buffer_page *commit_page; struct buffer_page *curr_commit_page; unsigned commit; u64 curr_commit_ts; u64 commit_ts; cpu_buffer = iter->cpu_buffer; reader = cpu_buffer->reader_page; head_page = cpu_buffer->head_page; commit_page = cpu_buffer->commit_page; commit_ts = commit_page->page->time_stamp; /* * When the writer goes across pages, it issues a cmpxchg which * is a mb(), which will synchronize with the rmb here. * (see rb_tail_page_update()) */ smp_rmb(); commit = rb_page_commit(commit_page); /* We want to make sure that the commit page doesn't change */ smp_rmb(); /* Make sure commit page didn't change */ curr_commit_page = READ_ONCE(cpu_buffer->commit_page); curr_commit_ts = READ_ONCE(curr_commit_page->page->time_stamp); /* If the commit page changed, then there's more data */ if (curr_commit_page != commit_page || curr_commit_ts != commit_ts) return 0; /* Still racy, as it may return a false positive, but that's OK */ return ((iter->head_page == commit_page && iter->head >= commit) || (iter->head_page == reader && commit_page == head_page && head_page->read == commit && iter->head == rb_page_commit(cpu_buffer->reader_page))); } EXPORT_SYMBOL_GPL(ring_buffer_iter_empty); static void rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) { u64 delta; switch (event->type_len) { case RINGBUF_TYPE_PADDING: return; case RINGBUF_TYPE_TIME_EXTEND: delta = rb_event_time_stamp(event); cpu_buffer->read_stamp += delta; return; case RINGBUF_TYPE_TIME_STAMP: delta = rb_event_time_stamp(event); delta = rb_fix_abs_ts(delta, cpu_buffer->read_stamp); cpu_buffer->read_stamp = delta; return; case RINGBUF_TYPE_DATA: cpu_buffer->read_stamp += event->time_delta; return; default: RB_WARN_ON(cpu_buffer, 1); } return; } static void rb_update_iter_read_stamp(struct ring_buffer_iter *iter, struct ring_buffer_event *event) { u64 delta; switch (event->type_len) { case RINGBUF_TYPE_PADDING: return; case RINGBUF_TYPE_TIME_EXTEND: delta = rb_event_time_stamp(event); iter->read_stamp += delta; return; case RINGBUF_TYPE_TIME_STAMP: delta = rb_event_time_stamp(event); delta = rb_fix_abs_ts(delta, iter->read_stamp); iter->read_stamp = delta; return; case RINGBUF_TYPE_DATA: iter->read_stamp += event->time_delta; return; default: RB_WARN_ON(iter->cpu_buffer, 1); } return; } static struct buffer_page * rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) { struct buffer_page *reader = NULL; unsigned long overwrite; unsigned long flags; int nr_loops = 0; int ret; local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); again: /* * This should normally only loop twice. But because the * start of the reader inserts an empty page, it causes * a case where we will loop three times. There should be no * reason to loop four times (that I know of). */ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) { reader = NULL; goto out; } reader = cpu_buffer->reader_page; /* If there's more to read, return this page */ if (cpu_buffer->reader_page->read < rb_page_size(reader)) goto out; /* Never should we have an index greater than the size */ if (RB_WARN_ON(cpu_buffer, cpu_buffer->reader_page->read > rb_page_size(reader))) goto out; /* check if we caught up to the tail */ reader = NULL; if (cpu_buffer->commit_page == cpu_buffer->reader_page) goto out; /* Don't bother swapping if the ring buffer is empty */ if (rb_num_of_entries(cpu_buffer) == 0) goto out; /* * Reset the reader page to size zero. */ local_set(&cpu_buffer->reader_page->write, 0); local_set(&cpu_buffer->reader_page->entries, 0); local_set(&cpu_buffer->reader_page->page->commit, 0); cpu_buffer->reader_page->real_end = 0; spin: /* * Splice the empty reader page into the list around the head. */ reader = rb_set_head_page(cpu_buffer); if (!reader) goto out; cpu_buffer->reader_page->list.next = rb_list_head(reader->list.next); cpu_buffer->reader_page->list.prev = reader->list.prev; /* * cpu_buffer->pages just needs to point to the buffer, it * has no specific buffer page to point to. Lets move it out * of our way so we don't accidentally swap it. */ cpu_buffer->pages = reader->list.prev; /* The reader page will be pointing to the new head */ rb_set_list_to_head(&cpu_buffer->reader_page->list); /* * We want to make sure we read the overruns after we set up our * pointers to the next object. The writer side does a * cmpxchg to cross pages which acts as the mb on the writer * side. Note, the reader will constantly fail the swap * while the writer is updating the pointers, so this * guarantees that the overwrite recorded here is the one we * want to compare with the last_overrun. */ smp_mb(); overwrite = local_read(&(cpu_buffer->overrun)); /* * Here's the tricky part. * * We need to move the pointer past the header page. * But we can only do that if a writer is not currently * moving it. The page before the header page has the * flag bit '1' set if it is pointing to the page we want. * but if the writer is in the process of moving it * than it will be '2' or already moved '0'. */ ret = rb_head_page_replace(reader, cpu_buffer->reader_page); /* * If we did not convert it, then we must try again. */ if (!ret) goto spin; /* * Yay! We succeeded in replacing the page. * * Now make the new head point back to the reader page. */ rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list; rb_inc_page(&cpu_buffer->head_page); local_inc(&cpu_buffer->pages_read); /* Finally update the reader page to the new head */ cpu_buffer->reader_page = reader; cpu_buffer->reader_page->read = 0; if (overwrite != cpu_buffer->last_overrun) { cpu_buffer->lost_events = overwrite - cpu_buffer->last_overrun; cpu_buffer->last_overrun = overwrite; } goto again; out: /* Update the read_stamp on the first event */ if (reader && reader->read == 0) cpu_buffer->read_stamp = reader->page->time_stamp; arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); /* * The writer has preempt disable, wait for it. But not forever * Although, 1 second is pretty much "forever" */ #define USECS_WAIT 1000000 for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) { /* If the write is past the end of page, a writer is still updating it */ if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE)) break; udelay(1); /* Get the latest version of the reader write value */ smp_rmb(); } /* The writer is not moving forward? Something is wrong */ if (RB_WARN_ON(cpu_buffer, nr_loops == USECS_WAIT)) reader = NULL; /* * Make sure we see any padding after the write update * (see rb_reset_tail()) */ smp_rmb(); return reader; } static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) { struct ring_buffer_event *event; struct buffer_page *reader; unsigned length; reader = rb_get_reader_page(cpu_buffer); /* This function should not be called when buffer is empty */ if (RB_WARN_ON(cpu_buffer, !reader)) return; event = rb_reader_event(cpu_buffer); if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX) cpu_buffer->read++; rb_update_read_stamp(cpu_buffer, event); length = rb_event_length(event); cpu_buffer->reader_page->read += length; } static void rb_advance_iter(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; cpu_buffer = iter->cpu_buffer; /* If head == next_event then we need to jump to the next event */ if (iter->head == iter->next_event) { /* If the event gets overwritten again, there's nothing to do */ if (rb_iter_head_event(iter) == NULL) return; } iter->head = iter->next_event; /* * Check if we are at the end of the buffer. */ if (iter->next_event >= rb_page_size(iter->head_page)) { /* discarded commits can make the page empty */ if (iter->head_page == cpu_buffer->commit_page) return; rb_inc_iter(iter); return; } rb_update_iter_read_stamp(iter, iter->event); } static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer) { return cpu_buffer->lost_events; } static struct ring_buffer_event * rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts, unsigned long *lost_events) { struct ring_buffer_event *event; struct buffer_page *reader; int nr_loops = 0; if (ts) *ts = 0; again: /* * We repeat when a time extend is encountered. * Since the time extend is always attached to a data event, * we should never loop more than once. * (We never hit the following condition more than twice). */ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2)) return NULL; reader = rb_get_reader_page(cpu_buffer); if (!reader) return NULL; event = rb_reader_event(cpu_buffer); switch (event->type_len) { case RINGBUF_TYPE_PADDING: if (rb_null_event(event)) RB_WARN_ON(cpu_buffer, 1); /* * Because the writer could be discarding every * event it creates (which would probably be bad) * if we were to go back to "again" then we may never * catch up, and will trigger the warn on, or lock * the box. Return the padding, and we will release * the current locks, and try again. */ return event; case RINGBUF_TYPE_TIME_EXTEND: /* Internal data, OK to advance */ rb_advance_reader(cpu_buffer); goto again; case RINGBUF_TYPE_TIME_STAMP: if (ts) { *ts = rb_event_time_stamp(event); *ts = rb_fix_abs_ts(*ts, reader->page->time_stamp); ring_buffer_normalize_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu, ts); } /* Internal data, OK to advance */ rb_advance_reader(cpu_buffer); goto again; case RINGBUF_TYPE_DATA: if (ts && !(*ts)) { *ts = cpu_buffer->read_stamp + event->time_delta; ring_buffer_normalize_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu, ts); } if (lost_events) *lost_events = rb_lost_events(cpu_buffer); return event; default: RB_WARN_ON(cpu_buffer, 1); } return NULL; } EXPORT_SYMBOL_GPL(ring_buffer_peek); static struct ring_buffer_event * rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) { struct trace_buffer *buffer; struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; int nr_loops = 0; if (ts) *ts = 0; cpu_buffer = iter->cpu_buffer; buffer = cpu_buffer->buffer; /* * Check if someone performed a consuming read to * the buffer. A consuming read invalidates the iterator * and we need to reset the iterator in this case. */ if (unlikely(iter->cache_read != cpu_buffer->read || iter->cache_reader_page != cpu_buffer->reader_page)) rb_iter_reset(iter); again: if (ring_buffer_iter_empty(iter)) return NULL; /* * As the writer can mess with what the iterator is trying * to read, just give up if we fail to get an event after * three tries. The iterator is not as reliable when reading * the ring buffer with an active write as the consumer is. * Do not warn if the three failures is reached. */ if (++nr_loops > 3) return NULL; if (rb_per_cpu_empty(cpu_buffer)) return NULL; if (iter->head >= rb_page_size(iter->head_page)) { rb_inc_iter(iter); goto again; } event = rb_iter_head_event(iter); if (!event) goto again; switch (event->type_len) { case RINGBUF_TYPE_PADDING: if (rb_null_event(event)) { rb_inc_iter(iter); goto again; } rb_advance_iter(iter); return event; case RINGBUF_TYPE_TIME_EXTEND: /* Internal data, OK to advance */ rb_advance_iter(iter); goto again; case RINGBUF_TYPE_TIME_STAMP: if (ts) { *ts = rb_event_time_stamp(event); *ts = rb_fix_abs_ts(*ts, iter->head_page->page->time_stamp); ring_buffer_normalize_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu, ts); } /* Internal data, OK to advance */ rb_advance_iter(iter); goto again; case RINGBUF_TYPE_DATA: if (ts && !(*ts)) { *ts = iter->read_stamp + event->time_delta; ring_buffer_normalize_time_stamp(buffer, cpu_buffer->cpu, ts); } return event; default: RB_WARN_ON(cpu_buffer, 1); } return NULL; } EXPORT_SYMBOL_GPL(ring_buffer_iter_peek); static inline bool rb_reader_lock(struct ring_buffer_per_cpu *cpu_buffer) { if (likely(!in_nmi())) { raw_spin_lock(&cpu_buffer->reader_lock); return true; } /* * If an NMI die dumps out the content of the ring buffer * trylock must be used to prevent a deadlock if the NMI * preempted a task that holds the ring buffer locks. If * we get the lock then all is fine, if not, then continue * to do the read, but this can corrupt the ring buffer, * so it must be permanently disabled from future writes. * Reading from NMI is a oneshot deal. */ if (raw_spin_trylock(&cpu_buffer->reader_lock)) return true; /* Continue without locking, but disable the ring buffer */ atomic_inc(&cpu_buffer->record_disabled); return false; } static inline void rb_reader_unlock(struct ring_buffer_per_cpu *cpu_buffer, bool locked) { if (likely(locked)) raw_spin_unlock(&cpu_buffer->reader_lock); return; } /** * ring_buffer_peek - peek at the next event to be read * @buffer: The ring buffer to read * @cpu: The cpu to peak at * @ts: The timestamp counter of this event. * @lost_events: a variable to store if events were lost (may be NULL) * * This will return the event that will be read next, but does * not consume the data. */ struct ring_buffer_event * ring_buffer_peek(struct trace_buffer *buffer, int cpu, u64 *ts, unsigned long *lost_events) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; struct ring_buffer_event *event; unsigned long flags; bool dolock; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return NULL; again: local_irq_save(flags); dolock = rb_reader_lock(cpu_buffer); event = rb_buffer_peek(cpu_buffer, ts, lost_events); if (event && event->type_len == RINGBUF_TYPE_PADDING) rb_advance_reader(cpu_buffer); rb_reader_unlock(cpu_buffer, dolock); local_irq_restore(flags); if (event && event->type_len == RINGBUF_TYPE_PADDING) goto again; return event; } /** ring_buffer_iter_dropped - report if there are dropped events * @iter: The ring buffer iterator * * Returns true if there was dropped events since the last peek. */ bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter) { bool ret = iter->missed_events != 0; iter->missed_events = 0; return ret; } EXPORT_SYMBOL_GPL(ring_buffer_iter_dropped); /** * ring_buffer_iter_peek - peek at the next event to be read * @iter: The ring buffer iterator * @ts: The timestamp counter of this event. * * This will return the event that will be read next, but does * not increment the iterator. */ struct ring_buffer_event * ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) { struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; struct ring_buffer_event *event; unsigned long flags; again: raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); event = rb_iter_peek(iter, ts); raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); if (event && event->type_len == RINGBUF_TYPE_PADDING) goto again; return event; } /** * ring_buffer_consume - return an event and consume it * @buffer: The ring buffer to get the next event from * @cpu: the cpu to read the buffer from * @ts: a variable to store the timestamp (may be NULL) * @lost_events: a variable to store if events were lost (may be NULL) * * Returns the next event in the ring buffer, and that event is consumed. * Meaning, that sequential reads will keep returning a different event, * and eventually empty the ring buffer if the producer is slower. */ struct ring_buffer_event * ring_buffer_consume(struct trace_buffer *buffer, int cpu, u64 *ts, unsigned long *lost_events) { struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event = NULL; unsigned long flags; bool dolock; again: /* might be called in atomic */ preempt_disable(); if (!cpumask_test_cpu(cpu, buffer->cpumask)) goto out; cpu_buffer = buffer->buffers[cpu]; local_irq_save(flags); dolock = rb_reader_lock(cpu_buffer); event = rb_buffer_peek(cpu_buffer, ts, lost_events); if (event) { cpu_buffer->lost_events = 0; rb_advance_reader(cpu_buffer); } rb_reader_unlock(cpu_buffer, dolock); local_irq_restore(flags); out: preempt_enable(); if (event && event->type_len == RINGBUF_TYPE_PADDING) goto again; return event; } EXPORT_SYMBOL_GPL(ring_buffer_consume); /** * ring_buffer_read_prepare - Prepare for a non consuming read of the buffer * @buffer: The ring buffer to read from * @cpu: The cpu buffer to iterate over * @flags: gfp flags to use for memory allocation * * This performs the initial preparations necessary to iterate * through the buffer. Memory is allocated, buffer recording * is disabled, and the iterator pointer is returned to the caller. * * Disabling buffer recording prevents the reading from being * corrupted. This is not a consuming read, so a producer is not * expected. * * After a sequence of ring_buffer_read_prepare calls, the user is * expected to make at least one call to ring_buffer_read_prepare_sync. * Afterwards, ring_buffer_read_start is invoked to get things going * for real. * * This overall must be paired with ring_buffer_read_finish. */ struct ring_buffer_iter * ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags) { struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_iter *iter; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return NULL; iter = kzalloc(sizeof(*iter), flags); if (!iter) return NULL; iter->event = kmalloc(BUF_MAX_DATA_SIZE, flags); if (!iter->event) { kfree(iter); return NULL; } cpu_buffer = buffer->buffers[cpu]; iter->cpu_buffer = cpu_buffer; atomic_inc(&cpu_buffer->resize_disabled); return iter; } EXPORT_SYMBOL_GPL(ring_buffer_read_prepare); /** * ring_buffer_read_prepare_sync - Synchronize a set of prepare calls * * All previously invoked ring_buffer_read_prepare calls to prepare * iterators will be synchronized. Afterwards, read_buffer_read_start * calls on those iterators are allowed. */ void ring_buffer_read_prepare_sync(void) { synchronize_rcu(); } EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync); /** * ring_buffer_read_start - start a non consuming read of the buffer * @iter: The iterator returned by ring_buffer_read_prepare * * This finalizes the startup of an iteration through the buffer. * The iterator comes from a call to ring_buffer_read_prepare and * an intervening ring_buffer_read_prepare_sync must have been * performed. * * Must be paired with ring_buffer_read_finish. */ void ring_buffer_read_start(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; if (!iter) return; cpu_buffer = iter->cpu_buffer; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); arch_spin_lock(&cpu_buffer->lock); rb_iter_reset(iter); arch_spin_unlock(&cpu_buffer->lock); raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } EXPORT_SYMBOL_GPL(ring_buffer_read_start); /** * ring_buffer_read_finish - finish reading the iterator of the buffer * @iter: The iterator retrieved by ring_buffer_start * * This re-enables the recording to the buffer, and frees the * iterator. */ void ring_buffer_read_finish(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; unsigned long flags; /* * Ring buffer is disabled from recording, here's a good place * to check the integrity of the ring buffer. * Must prevent readers from trying to read, as the check * clears the HEAD page and readers require it. */ raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); rb_check_pages(cpu_buffer); raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); atomic_dec(&cpu_buffer->resize_disabled); kfree(iter->event); kfree(iter); } EXPORT_SYMBOL_GPL(ring_buffer_read_finish); /** * ring_buffer_iter_advance - advance the iterator to the next location * @iter: The ring buffer iterator * * Move the location of the iterator such that the next read will * be the next location of the iterator. */ void ring_buffer_iter_advance(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; unsigned long flags; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); rb_advance_iter(iter); raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } EXPORT_SYMBOL_GPL(ring_buffer_iter_advance); /** * ring_buffer_size - return the size of the ring buffer (in bytes) * @buffer: The ring buffer. * @cpu: The CPU to get ring buffer size from. */ unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu) { /* * Earlier, this method returned * BUF_PAGE_SIZE * buffer->nr_pages * Since the nr_pages field is now removed, we have converted this to * return the per cpu buffer value. */ if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; return BUF_PAGE_SIZE * buffer->buffers[cpu]->nr_pages; } EXPORT_SYMBOL_GPL(ring_buffer_size); static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) { rb_head_page_deactivate(cpu_buffer); cpu_buffer->head_page = list_entry(cpu_buffer->pages, struct buffer_page, list); local_set(&cpu_buffer->head_page->write, 0); local_set(&cpu_buffer->head_page->entries, 0); local_set(&cpu_buffer->head_page->page->commit, 0); cpu_buffer->head_page->read = 0; cpu_buffer->tail_page = cpu_buffer->head_page; cpu_buffer->commit_page = cpu_buffer->head_page; INIT_LIST_HEAD(&cpu_buffer->reader_page->list); INIT_LIST_HEAD(&cpu_buffer->new_pages); local_set(&cpu_buffer->reader_page->write, 0); local_set(&cpu_buffer->reader_page->entries, 0); local_set(&cpu_buffer->reader_page->page->commit, 0); cpu_buffer->reader_page->read = 0; local_set(&cpu_buffer->entries_bytes, 0); local_set(&cpu_buffer->overrun, 0); local_set(&cpu_buffer->commit_overrun, 0); local_set(&cpu_buffer->dropped_events, 0); local_set(&cpu_buffer->entries, 0); local_set(&cpu_buffer->committing, 0); local_set(&cpu_buffer->commits, 0); local_set(&cpu_buffer->pages_touched, 0); local_set(&cpu_buffer->pages_lost, 0); local_set(&cpu_buffer->pages_read, 0); cpu_buffer->last_pages_touch = 0; cpu_buffer->shortest_full = 0; cpu_buffer->read = 0; cpu_buffer->read_bytes = 0; rb_time_set(&cpu_buffer->write_stamp, 0); rb_time_set(&cpu_buffer->before_stamp, 0); memset(cpu_buffer->event_stamp, 0, sizeof(cpu_buffer->event_stamp)); cpu_buffer->lost_events = 0; cpu_buffer->last_overrun = 0; rb_head_page_activate(cpu_buffer); } /* Must have disabled the cpu buffer then done a synchronize_rcu */ static void reset_disabled_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) { unsigned long flags; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing))) goto out; arch_spin_lock(&cpu_buffer->lock); rb_reset_cpu(cpu_buffer); arch_spin_unlock(&cpu_buffer->lock); out: raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } /** * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer * @buffer: The ring buffer to reset a per cpu buffer of * @cpu: The CPU buffer to be reset */ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return; /* prevent another thread from changing buffer sizes */ mutex_lock(&buffer->mutex); atomic_inc(&cpu_buffer->resize_disabled); atomic_inc(&cpu_buffer->record_disabled); /* Make sure all commits have finished */ synchronize_rcu(); reset_disabled_cpu_buffer(cpu_buffer); atomic_dec(&cpu_buffer->record_disabled); atomic_dec(&cpu_buffer->resize_disabled); mutex_unlock(&buffer->mutex); } EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu); /** * ring_buffer_reset_online_cpus - reset a ring buffer per CPU buffer * @buffer: The ring buffer to reset a per cpu buffer of * @cpu: The CPU buffer to be reset */ void ring_buffer_reset_online_cpus(struct trace_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; int cpu; /* prevent another thread from changing buffer sizes */ mutex_lock(&buffer->mutex); for_each_online_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; atomic_inc(&cpu_buffer->resize_disabled); atomic_inc(&cpu_buffer->record_disabled); } /* Make sure all commits have finished */ synchronize_rcu(); for_each_online_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; reset_disabled_cpu_buffer(cpu_buffer); atomic_dec(&cpu_buffer->record_disabled); atomic_dec(&cpu_buffer->resize_disabled); } mutex_unlock(&buffer->mutex); } /** * ring_buffer_reset - reset a ring buffer * @buffer: The ring buffer to reset all cpu buffers */ void ring_buffer_reset(struct trace_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; int cpu; /* prevent another thread from changing buffer sizes */ mutex_lock(&buffer->mutex); for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; atomic_inc(&cpu_buffer->resize_disabled); atomic_inc(&cpu_buffer->record_disabled); } /* Make sure all commits have finished */ synchronize_rcu(); for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; reset_disabled_cpu_buffer(cpu_buffer); atomic_dec(&cpu_buffer->record_disabled); atomic_dec(&cpu_buffer->resize_disabled); } mutex_unlock(&buffer->mutex); } EXPORT_SYMBOL_GPL(ring_buffer_reset); /** * ring_buffer_empty - is the ring buffer empty? * @buffer: The ring buffer to test */ bool ring_buffer_empty(struct trace_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; bool dolock; int cpu; int ret; /* yes this is racy, but if you don't like the race, lock the buffer */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; local_irq_save(flags); dolock = rb_reader_lock(cpu_buffer); ret = rb_per_cpu_empty(cpu_buffer); rb_reader_unlock(cpu_buffer, dolock); local_irq_restore(flags); if (!ret) return false; } return true; } EXPORT_SYMBOL_GPL(ring_buffer_empty); /** * ring_buffer_empty_cpu - is a cpu buffer of a ring buffer empty? * @buffer: The ring buffer * @cpu: The CPU buffer to test */ bool ring_buffer_empty_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; bool dolock; int ret; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return true; cpu_buffer = buffer->buffers[cpu]; local_irq_save(flags); dolock = rb_reader_lock(cpu_buffer); ret = rb_per_cpu_empty(cpu_buffer); rb_reader_unlock(cpu_buffer, dolock); local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu); #ifdef CONFIG_RING_BUFFER_ALLOW_SWAP /** * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers * @buffer_a: One buffer to swap with * @buffer_b: The other buffer to swap with * @cpu: the CPU of the buffers to swap * * This function is useful for tracers that want to take a "snapshot" * of a CPU buffer and has another back up buffer lying around. * it is expected that the tracer handles the cpu buffer not being * used at the moment. */ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, struct trace_buffer *buffer_b, int cpu) { struct ring_buffer_per_cpu *cpu_buffer_a; struct ring_buffer_per_cpu *cpu_buffer_b; int ret = -EINVAL; if (!cpumask_test_cpu(cpu, buffer_a->cpumask) || !cpumask_test_cpu(cpu, buffer_b->cpumask)) goto out; cpu_buffer_a = buffer_a->buffers[cpu]; cpu_buffer_b = buffer_b->buffers[cpu]; /* At least make sure the two buffers are somewhat the same */ if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages) goto out; ret = -EAGAIN; if (atomic_read(&buffer_a->record_disabled)) goto out; if (atomic_read(&buffer_b->record_disabled)) goto out; if (atomic_read(&cpu_buffer_a->record_disabled)) goto out; if (atomic_read(&cpu_buffer_b->record_disabled)) goto out; /* * We can't do a synchronize_rcu here because this * function can be called in atomic context. * Normally this will be called from the same CPU as cpu. * If not it's up to the caller to protect this. */ atomic_inc(&cpu_buffer_a->record_disabled); atomic_inc(&cpu_buffer_b->record_disabled); ret = -EBUSY; if (local_read(&cpu_buffer_a->committing)) goto out_dec; if (local_read(&cpu_buffer_b->committing)) goto out_dec; buffer_a->buffers[cpu] = cpu_buffer_b; buffer_b->buffers[cpu] = cpu_buffer_a; cpu_buffer_b->buffer = buffer_a; cpu_buffer_a->buffer = buffer_b; ret = 0; out_dec: atomic_dec(&cpu_buffer_a->record_disabled); atomic_dec(&cpu_buffer_b->record_disabled); out: return ret; } EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); #endif /* CONFIG_RING_BUFFER_ALLOW_SWAP */ /** * ring_buffer_alloc_read_page - allocate a page to read from buffer * @buffer: the buffer to allocate for. * @cpu: the cpu buffer to allocate. * * This function is used in conjunction with ring_buffer_read_page. * When reading a full page from the ring buffer, these functions * can be used to speed up the process. The calling function should * allocate a few pages first with this function. Then when it * needs to get pages from the ring buffer, it passes the result * of this function into ring_buffer_read_page, which will swap * the page that was allocated, with the read page of the buffer. * * Returns: * The page allocated, or ERR_PTR */ void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; struct buffer_data_page *bpage = NULL; unsigned long flags; struct page *page; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return ERR_PTR(-ENODEV); cpu_buffer = buffer->buffers[cpu]; local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); if (cpu_buffer->free_page) { bpage = cpu_buffer->free_page; cpu_buffer->free_page = NULL; } arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); if (bpage) goto out; page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, 0); if (!page) return ERR_PTR(-ENOMEM); bpage = page_address(page); out: rb_init_page(bpage); return bpage; } EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page); /** * ring_buffer_free_read_page - free an allocated read page * @buffer: the buffer the page was allocate for * @cpu: the cpu buffer the page came from * @data: the page to free * * Free a page allocated from ring_buffer_alloc_read_page. */ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; struct buffer_data_page *bpage = data; struct page *page = virt_to_page(bpage); unsigned long flags; /* If the page is still in use someplace else, we can't reuse it */ if (page_ref_count(page) > 1) goto out; local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); if (!cpu_buffer->free_page) { cpu_buffer->free_page = bpage; bpage = NULL; } arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); out: free_page((unsigned long)bpage); } EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); /** * ring_buffer_read_page - extract a page from the ring buffer * @buffer: buffer to extract from * @data_page: the page to use allocated from ring_buffer_alloc_read_page * @len: amount to extract * @cpu: the cpu of the buffer to extract * @full: should the extraction only happen when the page is full. * * This function will pull out a page from the ring buffer and consume it. * @data_page must be the address of the variable that was returned * from ring_buffer_alloc_read_page. This is because the page might be used * to swap with a page in the ring buffer. * * for example: * rpage = ring_buffer_alloc_read_page(buffer, cpu); * if (IS_ERR(rpage)) * return PTR_ERR(rpage); * ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0); * if (ret >= 0) * process_page(rpage, ret); * * When @full is set, the function will not return true unless * the writer is off the reader page. * * Note: it is up to the calling functions to handle sleeps and wakeups. * The ring buffer can be used anywhere in the kernel and can not * blindly call wake_up. The layer that uses the ring buffer must be * responsible for that. * * Returns: * >=0 if data has been transferred, returns the offset of consumed data. * <0 if no data has been transferred. */ int ring_buffer_read_page(struct trace_buffer *buffer, void **data_page, size_t len, int cpu, int full) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; struct ring_buffer_event *event; struct buffer_data_page *bpage; struct buffer_page *reader; unsigned long missed_events; unsigned long flags; unsigned int commit; unsigned int read; u64 save_timestamp; int ret = -1; if (!cpumask_test_cpu(cpu, buffer->cpumask)) goto out; /* * If len is not big enough to hold the page header, then * we can not copy anything. */ if (len <= BUF_PAGE_HDR_SIZE) goto out; len -= BUF_PAGE_HDR_SIZE; if (!data_page) goto out; bpage = *data_page; if (!bpage) goto out; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); reader = rb_get_reader_page(cpu_buffer); if (!reader) goto out_unlock; event = rb_reader_event(cpu_buffer); read = reader->read; commit = rb_page_commit(reader); /* Check if any events were dropped */ missed_events = cpu_buffer->lost_events; /* * If this page has been partially read or * if len is not big enough to read the rest of the page or * a writer is still on the page, then * we must copy the data from the page to the buffer. * Otherwise, we can simply swap the page with the one passed in. */ if (read || (len < (commit - read)) || cpu_buffer->reader_page == cpu_buffer->commit_page) { struct buffer_data_page *rpage = cpu_buffer->reader_page->page; unsigned int rpos = read; unsigned int pos = 0; unsigned int size; /* * If a full page is expected, this can still be returned * if there's been a previous partial read and the * rest of the page can be read and the commit page is off * the reader page. */ if (full && (!read || (len < (commit - read)) || cpu_buffer->reader_page == cpu_buffer->commit_page)) goto out_unlock; if (len > (commit - read)) len = (commit - read); /* Always keep the time extend and data together */ size = rb_event_ts_length(event); if (len < size) goto out_unlock; /* save the current timestamp, since the user will need it */ save_timestamp = cpu_buffer->read_stamp; /* Need to copy one event at a time */ do { /* We need the size of one event, because * rb_advance_reader only advances by one event, * whereas rb_event_ts_length may include the size of * one or two events. * We have already ensured there's enough space if this * is a time extend. */ size = rb_event_length(event); memcpy(bpage->data + pos, rpage->data + rpos, size); len -= size; rb_advance_reader(cpu_buffer); rpos = reader->read; pos += size; if (rpos >= commit) break; event = rb_reader_event(cpu_buffer); /* Always keep the time extend and data together */ size = rb_event_ts_length(event); } while (len >= size); /* update bpage */ local_set(&bpage->commit, pos); bpage->time_stamp = save_timestamp; /* we copied everything to the beginning */ read = 0; } else { /* update the entry counter */ cpu_buffer->read += rb_page_entries(reader); cpu_buffer->read_bytes += BUF_PAGE_SIZE; /* swap the pages */ rb_init_page(bpage); bpage = reader->page; reader->page = *data_page; local_set(&reader->write, 0); local_set(&reader->entries, 0); reader->read = 0; *data_page = bpage; /* * Use the real_end for the data size, * This gives us a chance to store the lost events * on the page. */ if (reader->real_end) local_set(&bpage->commit, reader->real_end); } ret = read; cpu_buffer->lost_events = 0; commit = local_read(&bpage->commit); /* * Set a flag in the commit field if we lost events */ if (missed_events) { /* If there is room at the end of the page to save the * missed events, then record it there. */ if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) { memcpy(&bpage->data[commit], &missed_events, sizeof(missed_events)); local_add(RB_MISSED_STORED, &bpage->commit); commit += sizeof(missed_events); } local_add(RB_MISSED_EVENTS, &bpage->commit); } /* * This page may be off to user land. Zero it out here. */ if (commit < BUF_PAGE_SIZE) memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit); out_unlock: raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); out: return ret; } EXPORT_SYMBOL_GPL(ring_buffer_read_page); /* * We only allocate new buffers, never free them if the CPU goes down. * If we were to free the buffer, then the user would lose any trace that was in * the buffer. */ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node) { struct trace_buffer *buffer; long nr_pages_same; int cpu_i; unsigned long nr_pages; buffer = container_of(node, struct trace_buffer, node); if (cpumask_test_cpu(cpu, buffer->cpumask)) return 0; nr_pages = 0; nr_pages_same = 1; /* check if all cpu sizes are same */ for_each_buffer_cpu(buffer, cpu_i) { /* fill in the size from first enabled cpu */ if (nr_pages == 0) nr_pages = buffer->buffers[cpu_i]->nr_pages; if (nr_pages != buffer->buffers[cpu_i]->nr_pages) { nr_pages_same = 0; break; } } /* allocate minimum pages, user can later expand it */ if (!nr_pages_same) nr_pages = 2; buffer->buffers[cpu] = rb_allocate_cpu_buffer(buffer, nr_pages, cpu); if (!buffer->buffers[cpu]) { WARN(1, "failed to allocate ring buffer on CPU %u\n", cpu); return -ENOMEM; } smp_wmb(); cpumask_set_cpu(cpu, buffer->cpumask); return 0; } #ifdef CONFIG_RING_BUFFER_STARTUP_TEST /* * This is a basic integrity check of the ring buffer. * Late in the boot cycle this test will run when configured in. * It will kick off a thread per CPU that will go into a loop * writing to the per cpu ring buffer various sizes of data. * Some of the data will be large items, some small. * * Another thread is created that goes into a spin, sending out * IPIs to the other CPUs to also write into the ring buffer. * this is to test the nesting ability of the buffer. * * Basic stats are recorded and reported. If something in the * ring buffer should happen that's not expected, a big warning * is displayed and all ring buffers are disabled. */ static struct task_struct *rb_threads[NR_CPUS] __initdata; struct rb_test_data { struct trace_buffer *buffer; unsigned long events; unsigned long bytes_written; unsigned long bytes_alloc; unsigned long bytes_dropped; unsigned long events_nested; unsigned long bytes_written_nested; unsigned long bytes_alloc_nested; unsigned long bytes_dropped_nested; int min_size_nested; int max_size_nested; int max_size; int min_size; int cpu; int cnt; }; static struct rb_test_data rb_data[NR_CPUS] __initdata; /* 1 meg per cpu */ #define RB_TEST_BUFFER_SIZE 1048576 static char rb_string[] __initdata = "abcdefghijklmnopqrstuvwxyz1234567890!@#$%^&*()?+\\" "?+|:';\",.<>/?abcdefghijklmnopqrstuvwxyz1234567890" "!@#$%^&*()?+\\?+|:';\",.<>/?abcdefghijklmnopqrstuv"; static bool rb_test_started __initdata; struct rb_item { int size; char str[]; }; static __init int rb_write_something(struct rb_test_data *data, bool nested) { struct ring_buffer_event *event; struct rb_item *item; bool started; int event_len; int size; int len; int cnt; /* Have nested writes different that what is written */ cnt = data->cnt + (nested ? 27 : 0); /* Multiply cnt by ~e, to make some unique increment */ size = (cnt * 68 / 25) % (sizeof(rb_string) - 1); len = size + sizeof(struct rb_item); started = rb_test_started; /* read rb_test_started before checking buffer enabled */ smp_rmb(); event = ring_buffer_lock_reserve(data->buffer, len); if (!event) { /* Ignore dropped events before test starts. */ if (started) { if (nested) data->bytes_dropped += len; else data->bytes_dropped_nested += len; } return len; } event_len = ring_buffer_event_length(event); if (RB_WARN_ON(data->buffer, event_len < len)) goto out; item = ring_buffer_event_data(event); item->size = size; memcpy(item->str, rb_string, size); if (nested) { data->bytes_alloc_nested += event_len; data->bytes_written_nested += len; data->events_nested++; if (!data->min_size_nested || len < data->min_size_nested) data->min_size_nested = len; if (len > data->max_size_nested) data->max_size_nested = len; } else { data->bytes_alloc += event_len; data->bytes_written += len; data->events++; if (!data->min_size || len < data->min_size) data->max_size = len; if (len > data->max_size) data->max_size = len; } out: ring_buffer_unlock_commit(data->buffer, event); return 0; } static __init int rb_test(void *arg) { struct rb_test_data *data = arg; while (!kthread_should_stop()) { rb_write_something(data, false); data->cnt++; set_current_state(TASK_INTERRUPTIBLE); /* Now sleep between a min of 100-300us and a max of 1ms */ usleep_range(((data->cnt % 3) + 1) * 100, 1000); } return 0; } static __init void rb_ipi(void *ignore) { struct rb_test_data *data; int cpu = smp_processor_id(); data = &rb_data[cpu]; rb_write_something(data, true); } static __init int rb_hammer_test(void *arg) { while (!kthread_should_stop()) { /* Send an IPI to all cpus to write data! */ smp_call_function(rb_ipi, NULL, 1); /* No sleep, but for non preempt, let others run */ schedule(); } return 0; } static __init int test_ringbuffer(void) { struct task_struct *rb_hammer; struct trace_buffer *buffer; int cpu; int ret = 0; if (security_locked_down(LOCKDOWN_TRACEFS)) { pr_warn("Lockdown is enabled, skipping ring buffer tests\n"); return 0; } pr_info("Running ring buffer tests...\n"); buffer = ring_buffer_alloc(RB_TEST_BUFFER_SIZE, RB_FL_OVERWRITE); if (WARN_ON(!buffer)) return 0; /* Disable buffer so that threads can't write to it yet */ ring_buffer_record_off(buffer); for_each_online_cpu(cpu) { rb_data[cpu].buffer = buffer; rb_data[cpu].cpu = cpu; rb_data[cpu].cnt = cpu; rb_threads[cpu] = kthread_run_on_cpu(rb_test, &rb_data[cpu], cpu, "rbtester/%u"); if (WARN_ON(IS_ERR(rb_threads[cpu]))) { pr_cont("FAILED\n"); ret = PTR_ERR(rb_threads[cpu]); goto out_free; } } /* Now create the rb hammer! */ rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer"); if (WARN_ON(IS_ERR(rb_hammer))) { pr_cont("FAILED\n"); ret = PTR_ERR(rb_hammer); goto out_free; } ring_buffer_record_on(buffer); /* * Show buffer is enabled before setting rb_test_started. * Yes there's a small race window where events could be * dropped and the thread wont catch it. But when a ring * buffer gets enabled, there will always be some kind of * delay before other CPUs see it. Thus, we don't care about * those dropped events. We care about events dropped after * the threads see that the buffer is active. */ smp_wmb(); rb_test_started = true; set_current_state(TASK_INTERRUPTIBLE); /* Just run for 10 seconds */; schedule_timeout(10 * HZ); kthread_stop(rb_hammer); out_free: for_each_online_cpu(cpu) { if (!rb_threads[cpu]) break; kthread_stop(rb_threads[cpu]); } if (ret) { ring_buffer_free(buffer); return ret; } /* Report! */ pr_info("finished\n"); for_each_online_cpu(cpu) { struct ring_buffer_event *event; struct rb_test_data *data = &rb_data[cpu]; struct rb_item *item; unsigned long total_events; unsigned long total_dropped; unsigned long total_written; unsigned long total_alloc; unsigned long total_read = 0; unsigned long total_size = 0; unsigned long total_len = 0; unsigned long total_lost = 0; unsigned long lost; int big_event_size; int small_event_size; ret = -1; total_events = data->events + data->events_nested; total_written = data->bytes_written + data->bytes_written_nested; total_alloc = data->bytes_alloc + data->bytes_alloc_nested; total_dropped = data->bytes_dropped + data->bytes_dropped_nested; big_event_size = data->max_size + data->max_size_nested; small_event_size = data->min_size + data->min_size_nested; pr_info("CPU %d:\n", cpu); pr_info(" events: %ld\n", total_events); pr_info(" dropped bytes: %ld\n", total_dropped); pr_info(" alloced bytes: %ld\n", total_alloc); pr_info(" written bytes: %ld\n", total_written); pr_info(" biggest event: %d\n", big_event_size); pr_info(" smallest event: %d\n", small_event_size); if (RB_WARN_ON(buffer, total_dropped)) break; ret = 0; while ((event = ring_buffer_consume(buffer, cpu, NULL, &lost))) { total_lost += lost; item = ring_buffer_event_data(event); total_len += ring_buffer_event_length(event); total_size += item->size + sizeof(struct rb_item); if (memcmp(&item->str[0], rb_string, item->size) != 0) { pr_info("FAILED!\n"); pr_info("buffer had: %.*s\n", item->size, item->str); pr_info("expected: %.*s\n", item->size, rb_string); RB_WARN_ON(buffer, 1); ret = -1; break; } total_read++; } if (ret) break; ret = -1; pr_info(" read events: %ld\n", total_read); pr_info(" lost events: %ld\n", total_lost); pr_info(" total events: %ld\n", total_lost + total_read); pr_info(" recorded len bytes: %ld\n", total_len); pr_info(" recorded size bytes: %ld\n", total_size); if (total_lost) { pr_info(" With dropped events, record len and size may not match\n" " alloced and written from above\n"); } else { if (RB_WARN_ON(buffer, total_len != total_alloc || total_size != total_written)) break; } if (RB_WARN_ON(buffer, total_lost + total_read != total_events)) break; ret = 0; } if (!ret) pr_info("Ring buffer PASSED!\n"); ring_buffer_free(buffer); return 0; } late_initcall(test_ringbuffer); #endif /* CONFIG_RING_BUFFER_STARTUP_TEST */ |
| 1459 1459 1458 1458 1456 1456 1452 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 | // SPDX-License-Identifier: GPL-2.0 /* * sysctl_net_ipv6.c: sysctl interface to net IPV6 subsystem. * * Changes: * YOSHIFUJI Hideaki @USAGI: added icmp sysctl table. */ #include <linux/mm.h> #include <linux/sysctl.h> #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/slab.h> #include <linux/export.h> #include <net/ndisc.h> #include <net/ipv6.h> #include <net/addrconf.h> #include <net/inet_frag.h> #include <net/netevent.h> #include <net/ip_fib.h> #ifdef CONFIG_NETLABEL #include <net/calipso.h> #endif #include <linux/ioam6.h> static int flowlabel_reflect_max = 0x7; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; static u32 rt6_multipath_hash_fields_all_mask = FIB_MULTIPATH_HASH_FIELD_ALL_MASK; static u32 ioam6_id_max = IOAM6_DEFAULT_ID; static u64 ioam6_id_wide_max = IOAM6_DEFAULT_ID_WIDE; static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; net = container_of(table->data, struct net, ipv6.sysctl.multipath_hash_policy); ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net); return ret; } static int proc_rt6_multipath_hash_fields(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; net = container_of(table->data, struct net, ipv6.sysctl.multipath_hash_fields); ret = proc_douintvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net); return ret; } static struct ctl_table ipv6_table_template[] = { { .procname = "bindv6only", .data = &init_net.ipv6.sysctl.bindv6only, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "anycast_src_echo_reply", .data = &init_net.ipv6.sysctl.anycast_src_echo_reply, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "flowlabel_consistency", .data = &init_net.ipv6.sysctl.flowlabel_consistency, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "auto_flowlabels", .data = &init_net.ipv6.sysctl.auto_flowlabels, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra2 = &auto_flowlabels_max }, { .procname = "fwmark_reflect", .data = &init_net.ipv6.sysctl.fwmark_reflect, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "idgen_retries", .data = &init_net.ipv6.sysctl.idgen_retries, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "idgen_delay", .data = &init_net.ipv6.sysctl.idgen_delay, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "flowlabel_state_ranges", .data = &init_net.ipv6.sysctl.flowlabel_state_ranges, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_nonlocal_bind", .data = &init_net.ipv6.sysctl.ip_nonlocal_bind, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "flowlabel_reflect", .data = &init_net.ipv6.sysctl.flowlabel_reflect, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &flowlabel_reflect_max, }, { .procname = "max_dst_opts_number", .data = &init_net.ipv6.sysctl.max_dst_opts_cnt, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_hbh_opts_number", .data = &init_net.ipv6.sysctl.max_hbh_opts_cnt, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_dst_opts_length", .data = &init_net.ipv6.sysctl.max_dst_opts_len, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_hbh_length", .data = &init_net.ipv6.sysctl.max_hbh_opts_len, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "fib_multipath_hash_policy", .data = &init_net.ipv6.sysctl.multipath_hash_policy, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_rt6_multipath_hash_policy, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_THREE, }, { .procname = "fib_multipath_hash_fields", .data = &init_net.ipv6.sysctl.multipath_hash_fields, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_rt6_multipath_hash_fields, .extra1 = SYSCTL_ONE, .extra2 = &rt6_multipath_hash_fields_all_mask, }, { .procname = "seg6_flowlabel", .data = &init_net.ipv6.sysctl.seg6_flowlabel, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "fib_notify_on_flag_change", .data = &init_net.ipv6.sysctl.fib_notify_on_flag_change, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "ioam6_id", .data = &init_net.ipv6.sysctl.ioam6_id, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra2 = &ioam6_id_max, }, { .procname = "ioam6_id_wide", .data = &init_net.ipv6.sysctl.ioam6_id_wide, .maxlen = sizeof(u64), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra2 = &ioam6_id_wide_max, }, { } }; static struct ctl_table ipv6_rotable[] = { { .procname = "mld_max_msf", .data = &sysctl_mld_max_msf, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "mld_qrv", .data = &sysctl_mld_qrv, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE }, #ifdef CONFIG_NETLABEL { .procname = "calipso_cache_enable", .data = &calipso_cache_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "calipso_cache_bucket_size", .data = &calipso_cache_bucketsize, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif /* CONFIG_NETLABEL */ { } }; static int __net_init ipv6_sysctl_net_init(struct net *net) { struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; struct ctl_table *ipv6_icmp_table; int err, i; err = -ENOMEM; ipv6_table = kmemdup(ipv6_table_template, sizeof(ipv6_table_template), GFP_KERNEL); if (!ipv6_table) goto out; /* Update the variables to point into the current struct net */ for (i = 0; i < ARRAY_SIZE(ipv6_table_template) - 1; i++) ipv6_table[i].data += (void *)net - (void *)&init_net; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) goto out_ipv6_table; ipv6_icmp_table = ipv6_icmp_sysctl_init(net); if (!ipv6_icmp_table) goto out_ipv6_route_table; net->ipv6.sysctl.hdr = register_net_sysctl(net, "net/ipv6", ipv6_table); if (!net->ipv6.sysctl.hdr) goto out_ipv6_icmp_table; net->ipv6.sysctl.route_hdr = register_net_sysctl(net, "net/ipv6/route", ipv6_route_table); if (!net->ipv6.sysctl.route_hdr) goto out_unregister_ipv6_table; net->ipv6.sysctl.icmp_hdr = register_net_sysctl(net, "net/ipv6/icmp", ipv6_icmp_table); if (!net->ipv6.sysctl.icmp_hdr) goto out_unregister_route_table; err = 0; out: return err; out_unregister_route_table: unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); out_unregister_ipv6_table: unregister_net_sysctl_table(net->ipv6.sysctl.hdr); out_ipv6_icmp_table: kfree(ipv6_icmp_table); out_ipv6_route_table: kfree(ipv6_route_table); out_ipv6_table: kfree(ipv6_table); goto out; } static void __net_exit ipv6_sysctl_net_exit(struct net *net) { struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; struct ctl_table *ipv6_icmp_table; ipv6_table = net->ipv6.sysctl.hdr->ctl_table_arg; ipv6_route_table = net->ipv6.sysctl.route_hdr->ctl_table_arg; ipv6_icmp_table = net->ipv6.sysctl.icmp_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv6.sysctl.icmp_hdr); unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); unregister_net_sysctl_table(net->ipv6.sysctl.hdr); kfree(ipv6_table); kfree(ipv6_route_table); kfree(ipv6_icmp_table); } static struct pernet_operations ipv6_sysctl_net_ops = { .init = ipv6_sysctl_net_init, .exit = ipv6_sysctl_net_exit, }; static struct ctl_table_header *ip6_header; int ipv6_sysctl_register(void) { int err = -ENOMEM; ip6_header = register_net_sysctl(&init_net, "net/ipv6", ipv6_rotable); if (!ip6_header) goto out; err = register_pernet_subsys(&ipv6_sysctl_net_ops); if (err) goto err_pernet; out: return err; err_pernet: unregister_net_sysctl_table(ip6_header); goto out; } void ipv6_sysctl_unregister(void) { unregister_net_sysctl_table(ip6_header); unregister_pernet_subsys(&ipv6_sysctl_net_ops); } |
| 553 50 41 24 20 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __SOCK_DIAG_H__ #define __SOCK_DIAG_H__ #include <linux/netlink.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> struct sk_buff; struct nlmsghdr; struct sock; struct sock_diag_handler { __u8 family; int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh); int (*get_info)(struct sk_buff *skb, struct sock *sk); int (*destroy)(struct sk_buff *skb, struct nlmsghdr *nlh); }; int sock_diag_register(const struct sock_diag_handler *h); void sock_diag_unregister(const struct sock_diag_handler *h); void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); u64 __sock_gen_cookie(struct sock *sk); static inline u64 sock_gen_cookie(struct sock *sk) { u64 cookie; preempt_disable(); cookie = __sock_gen_cookie(sk); preempt_enable(); return cookie; } int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype); static inline enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk) { switch (sk->sk_family) { case AF_INET: if (sk->sk_type == SOCK_RAW) return SKNLGRP_NONE; switch (sk->sk_protocol) { case IPPROTO_TCP: return SKNLGRP_INET_TCP_DESTROY; case IPPROTO_UDP: return SKNLGRP_INET_UDP_DESTROY; default: return SKNLGRP_NONE; } case AF_INET6: if (sk->sk_type == SOCK_RAW) return SKNLGRP_NONE; switch (sk->sk_protocol) { case IPPROTO_TCP: return SKNLGRP_INET6_TCP_DESTROY; case IPPROTO_UDP: return SKNLGRP_INET6_UDP_DESTROY; default: return SKNLGRP_NONE; } default: return SKNLGRP_NONE; } } static inline bool sock_diag_has_destroy_listeners(const struct sock *sk) { const struct net *n = sock_net(sk); const enum sknetlink_groups group = sock_diag_destroy_group(sk); return group != SKNLGRP_NONE && n->diag_nlsk && netlink_has_listeners(n->diag_nlsk, group); } void sock_diag_broadcast_destroy(struct sock *sk); int sock_diag_destroy(struct sock *sk, int err); #endif |
| 210 137 137 10 45 14 14 13 10 10 15 10 9 15 15 139 139 172 142 259 222 189 44 44 1 1 1 181 183 2 611 613 42 43 43 43 43 43 43 43 43 43 613 612 43 613 43 1 612 613 613 613 44 44 88 87 2 2 2 2 2 2 13 8 9 9 9 9 9 9 9 9 9 44 44 44 13 42 42 42 42 42 42 44 42 42 42 42 42 45 45 9 37 37 37 45 45 45 45 9 137 111 111 111 111 111 131 137 137 137 137 137 137 137 137 137 130 77 196 132 78 197 14 184 198 2 2 2 2 2 2 2 137 137 137 30 30 106 136 111 137 137 132 132 132 45 38 51 44 44 44 44 43 43 43 43 43 43 43 43 43 43 43 43 29 43 43 43 49 43 29 43 43 43 43 43 43 49 43 9 9 49 43 49 43 44 44 44 44 44 44 44 44 44 44 49 49 44 44 44 1 43 43 43 43 49 44 44 44 44 44 46 46 46 46 2 45 37 45 1 45 45 5 5 5 5 5 14 14 14 14 14 14 5 5 137 137 137 137 35 137 137 137 137 137 137 137 5 5 5 5 5 2 5 5 5 6 6 6 15 15 15 12 12 11 8 8 6 5 5 15 13 13 8 2 7 13 5 2 3 2 12 5 9 12 1 1 2 1 1 2 1 1 1 2 12 12 12 11 12 1 7 4 7 30 4 3 3 5 1 1 1 1 1 1 1 1 1 3 142 142 7 11 11 310 315 310 315 48 43 47 5 4 3 47 137 137 137 137 137 137 30 137 137 137 137 137 137 137 137 137 245 210 210 156 183 492 492 129 129 491 492 492 473 473 473 473 471 42 42 14 14 14 14 14 8 8 3 1 50 49 50 50 47 47 47 50 47 47 46 3 3 50 47 47 50 50 47 47 47 47 47 47 47 50 50 47 21 4 26 51 48 2 50 50 47 50 47 47 50 50 50 9 9 9 9 9 9 9 9 9 11 11 9 8 9 11 11 9 9 2 137 137 137 137 32 137 137 137 137 137 137 137 137 137 137 137 137 137 132 132 131 132 132 132 132 132 132 132 1 75 132 132 106 132 132 132 132 132 132 132 132 132 132 130 130 130 2 2 2 2 2271 37 578 578 578 578 578 1 1 1 577 577 577 577 577 577 577 66 66 577 577 48 48 36 37 52 45 9 43 9 3566 3567 3565 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 | /* * Generic process-grouping system. * * Based originally on the cpuset system, extracted by Paul Menage * Copyright (C) 2006 Google, Inc * * Notifications support * Copyright (C) 2009 Nokia Corporation * Author: Kirill A. Shutemov * * Copyright notices from the original cpuset code: * -------------------------------------------------- * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2006 Silicon Graphics, Inc. * * Portions derived from Patrick Mochel's sysfs code. * sysfs is Copyright (c) 2001-3 Patrick Mochel * * 2003-10-10 Written by Simon Derr. * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * --------------------------------------------------- * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of the Linux * distribution for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "cgroup-internal.h" #include <linux/bpf-cgroup.h> #include <linux/cred.h> #include <linux/errno.h> #include <linux/init_task.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/mutex.h> #include <linux/mount.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/percpu-rwsem.h> #include <linux/string.h> #include <linux/hashtable.h> #include <linux/idr.h> #include <linux/kthread.h> #include <linux/atomic.h> #include <linux/cpuset.h> #include <linux/proc_ns.h> #include <linux/nsproxy.h> #include <linux/file.h> #include <linux/fs_parser.h> #include <linux/sched/cputime.h> #include <linux/psi.h> #include <net/sock.h> #define CREATE_TRACE_POINTS #include <trace/events/cgroup.h> #define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \ MAX_CFTYPE_NAME + 2) /* let's not notify more than 100 times per second */ #define CGROUP_FILE_NOTIFY_MIN_INTV DIV_ROUND_UP(HZ, 100) /* * To avoid confusing the compiler (and generating warnings) with code * that attempts to access what would be a 0-element array (i.e. sized * to a potentially empty array when CGROUP_SUBSYS_COUNT == 0), this * constant expression can be added. */ #define CGROUP_HAS_SUBSYS_CONFIG (CGROUP_SUBSYS_COUNT > 0) /* * cgroup_mutex is the master lock. Any modification to cgroup or its * hierarchy must be performed while holding it. * * css_set_lock protects task->cgroups pointer, the list of css_set * objects, and the chain of tasks off each css_set. * * These locks are exported if CONFIG_PROVE_RCU so that accessors in * cgroup.h can use them for lockdep annotations. */ DEFINE_MUTEX(cgroup_mutex); DEFINE_SPINLOCK(css_set_lock); #ifdef CONFIG_PROVE_RCU EXPORT_SYMBOL_GPL(cgroup_mutex); EXPORT_SYMBOL_GPL(css_set_lock); #endif DEFINE_SPINLOCK(trace_cgroup_path_lock); char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; static bool cgroup_debug __read_mostly; /* * Protects cgroup_idr and css_idr so that IDs can be released without * grabbing cgroup_mutex. */ static DEFINE_SPINLOCK(cgroup_idr_lock); /* * Protects cgroup_file->kn for !self csses. It synchronizes notifications * against file removal/re-creation across css hiding. */ static DEFINE_SPINLOCK(cgroup_file_kn_lock); DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem); #define cgroup_assert_mutex_or_rcu_locked() \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&cgroup_mutex), \ "cgroup_mutex or RCU read lock required"); /* * cgroup destruction makes heavy use of work items and there can be a lot * of concurrent destructions. Use a separate workqueue so that cgroup * destruction work items don't end up filling up max_active of system_wq * which may lead to deadlock. */ static struct workqueue_struct *cgroup_destroy_wq; /* generate an array of cgroup subsystem pointers */ #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys, struct cgroup_subsys *cgroup_subsys[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS /* array of cgroup subsystem names */ #define SUBSYS(_x) [_x ## _cgrp_id] = #_x, static const char *cgroup_subsys_name[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS /* array of static_keys for cgroup_subsys_enabled() and cgroup_subsys_on_dfl() */ #define SUBSYS(_x) \ DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_enabled_key); \ DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_on_dfl_key); \ EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_enabled_key); \ EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_on_dfl_key); #include <linux/cgroup_subsys.h> #undef SUBSYS #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_enabled_key, static struct static_key_true *cgroup_subsys_enabled_key[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_on_dfl_key, static struct static_key_true *cgroup_subsys_on_dfl_key[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu); /* the default hierarchy */ struct cgroup_root cgrp_dfl_root = { .cgrp.rstat_cpu = &cgrp_dfl_root_rstat_cpu }; EXPORT_SYMBOL_GPL(cgrp_dfl_root); /* * The default hierarchy always exists but is hidden until mounted for the * first time. This is for backward compatibility. */ static bool cgrp_dfl_visible; /* some controllers are not supported in the default hierarchy */ static u16 cgrp_dfl_inhibit_ss_mask; /* some controllers are implicitly enabled on the default hierarchy */ static u16 cgrp_dfl_implicit_ss_mask; /* some controllers can be threaded on the default hierarchy */ static u16 cgrp_dfl_threaded_ss_mask; /* The list of hierarchy roots */ LIST_HEAD(cgroup_roots); static int cgroup_root_count; /* hierarchy ID allocation and mapping, protected by cgroup_mutex */ static DEFINE_IDR(cgroup_hierarchy_idr); /* * Assign a monotonically increasing serial number to csses. It guarantees * cgroups with bigger numbers are newer than those with smaller numbers. * Also, as csses are always appended to the parent's ->children list, it * guarantees that sibling csses are always sorted in the ascending serial * number order on the list. Protected by cgroup_mutex. */ static u64 css_serial_nr_next = 1; /* * These bitmasks identify subsystems with specific features to avoid * having to do iterative checks repeatedly. */ static u16 have_fork_callback __read_mostly; static u16 have_exit_callback __read_mostly; static u16 have_release_callback __read_mostly; static u16 have_canfork_callback __read_mostly; /* cgroup namespace for init task */ struct cgroup_namespace init_cgroup_ns = { .ns.count = REFCOUNT_INIT(2), .user_ns = &init_user_ns, .ns.ops = &cgroupns_operations, .ns.inum = PROC_CGROUP_INIT_INO, .root_cset = &init_css_set, }; static struct file_system_type cgroup2_fs_type; static struct cftype cgroup_base_files[]; static struct cftype cgroup_psi_files[]; /* cgroup optional features */ enum cgroup_opt_features { #ifdef CONFIG_PSI OPT_FEATURE_PRESSURE, #endif OPT_FEATURE_COUNT }; static const char *cgroup_opt_feature_names[OPT_FEATURE_COUNT] = { #ifdef CONFIG_PSI "pressure", #endif }; static u16 cgroup_feature_disable_mask __read_mostly; static int cgroup_apply_control(struct cgroup *cgrp); static void cgroup_finalize_control(struct cgroup *cgrp, int ret); static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task); static int cgroup_destroy_locked(struct cgroup *cgrp); static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss); static void css_release(struct percpu_ref *ref); static void kill_css(struct cgroup_subsys_state *css); static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add); /** * cgroup_ssid_enabled - cgroup subsys enabled test by subsys ID * @ssid: subsys ID of interest * * cgroup_subsys_enabled() can only be used with literal subsys names which * is fine for individual subsystems but unsuitable for cgroup core. This * is slower static_key_enabled() based test indexed by @ssid. */ bool cgroup_ssid_enabled(int ssid) { if (!CGROUP_HAS_SUBSYS_CONFIG) return false; return static_key_enabled(cgroup_subsys_enabled_key[ssid]); } /** * cgroup_on_dfl - test whether a cgroup is on the default hierarchy * @cgrp: the cgroup of interest * * The default hierarchy is the v2 interface of cgroup and this function * can be used to test whether a cgroup is on the default hierarchy for * cases where a subsystem should behave differently depending on the * interface version. * * List of changed behaviors: * * - Mount options "noprefix", "xattr", "clone_children", "release_agent" * and "name" are disallowed. * * - When mounting an existing superblock, mount options should match. * * - rename(2) is disallowed. * * - "tasks" is removed. Everything should be at process granularity. Use * "cgroup.procs" instead. * * - "cgroup.procs" is not sorted. pids will be unique unless they got * recycled in-between reads. * * - "release_agent" and "notify_on_release" are removed. Replacement * notification mechanism will be implemented. * * - "cgroup.clone_children" is removed. * * - "cgroup.subtree_populated" is available. Its value is 0 if the cgroup * and its descendants contain no task; otherwise, 1. The file also * generates kernfs notification which can be monitored through poll and * [di]notify when the value of the file changes. * * - cpuset: tasks will be kept in empty cpusets when hotplug happens and * take masks of ancestors with non-empty cpus/mems, instead of being * moved to an ancestor. * * - cpuset: a task can be moved into an empty cpuset, and again it takes * masks of ancestors. * * - blkcg: blk-throttle becomes properly hierarchical. * * - debug: disallowed on the default hierarchy. */ bool cgroup_on_dfl(const struct cgroup *cgrp) { return cgrp->root == &cgrp_dfl_root; } /* IDR wrappers which synchronize using cgroup_idr_lock */ static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask) { int ret; idr_preload(gfp_mask); spin_lock_bh(&cgroup_idr_lock); ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_DIRECT_RECLAIM); spin_unlock_bh(&cgroup_idr_lock); idr_preload_end(); return ret; } static void *cgroup_idr_replace(struct idr *idr, void *ptr, int id) { void *ret; spin_lock_bh(&cgroup_idr_lock); ret = idr_replace(idr, ptr, id); spin_unlock_bh(&cgroup_idr_lock); return ret; } static void cgroup_idr_remove(struct idr *idr, int id) { spin_lock_bh(&cgroup_idr_lock); idr_remove(idr, id); spin_unlock_bh(&cgroup_idr_lock); } static bool cgroup_has_tasks(struct cgroup *cgrp) { return cgrp->nr_populated_csets; } bool cgroup_is_threaded(struct cgroup *cgrp) { return cgrp->dom_cgrp != cgrp; } /* can @cgrp host both domain and threaded children? */ static bool cgroup_is_mixable(struct cgroup *cgrp) { /* * Root isn't under domain level resource control exempting it from * the no-internal-process constraint, so it can serve as a thread * root and a parent of resource domains at the same time. */ return !cgroup_parent(cgrp); } /* can @cgrp become a thread root? Should always be true for a thread root */ static bool cgroup_can_be_thread_root(struct cgroup *cgrp) { /* mixables don't care */ if (cgroup_is_mixable(cgrp)) return true; /* domain roots can't be nested under threaded */ if (cgroup_is_threaded(cgrp)) return false; /* can only have either domain or threaded children */ if (cgrp->nr_populated_domain_children) return false; /* and no domain controllers can be enabled */ if (cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) return false; return true; } /* is @cgrp root of a threaded subtree? */ bool cgroup_is_thread_root(struct cgroup *cgrp) { /* thread root should be a domain */ if (cgroup_is_threaded(cgrp)) return false; /* a domain w/ threaded children is a thread root */ if (cgrp->nr_threaded_children) return true; /* * A domain which has tasks and explicit threaded controllers * enabled is a thread root. */ if (cgroup_has_tasks(cgrp) && (cgrp->subtree_control & cgrp_dfl_threaded_ss_mask)) return true; return false; } /* a domain which isn't connected to the root w/o brekage can't be used */ static bool cgroup_is_valid_domain(struct cgroup *cgrp) { /* the cgroup itself can be a thread root */ if (cgroup_is_threaded(cgrp)) return false; /* but the ancestors can't be unless mixable */ while ((cgrp = cgroup_parent(cgrp))) { if (!cgroup_is_mixable(cgrp) && cgroup_is_thread_root(cgrp)) return false; if (cgroup_is_threaded(cgrp)) return false; } return true; } /* subsystems visibly enabled on a cgroup */ static u16 cgroup_control(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); u16 root_ss_mask = cgrp->root->subsys_mask; if (parent) { u16 ss_mask = parent->subtree_control; /* threaded cgroups can only have threaded controllers */ if (cgroup_is_threaded(cgrp)) ss_mask &= cgrp_dfl_threaded_ss_mask; return ss_mask; } if (cgroup_on_dfl(cgrp)) root_ss_mask &= ~(cgrp_dfl_inhibit_ss_mask | cgrp_dfl_implicit_ss_mask); return root_ss_mask; } /* subsystems enabled on a cgroup */ static u16 cgroup_ss_mask(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); if (parent) { u16 ss_mask = parent->subtree_ss_mask; /* threaded cgroups can only have threaded controllers */ if (cgroup_is_threaded(cgrp)) ss_mask &= cgrp_dfl_threaded_ss_mask; return ss_mask; } return cgrp->root->subsys_mask; } /** * cgroup_css - obtain a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Return @cgrp's css (cgroup_subsys_state) associated with @ss. This * function must be called either under cgroup_mutex or rcu_read_lock() and * the caller is responsible for pinning the returned css if it wants to * keep accessing it outside the said locks. This function may return * %NULL if @cgrp doesn't have @subsys_id enabled. */ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { if (CGROUP_HAS_SUBSYS_CONFIG && ss) return rcu_dereference_check(cgrp->subsys[ss->id], lockdep_is_held(&cgroup_mutex)); else return &cgrp->self; } /** * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get @cgrp's css associated with @ss. If the css doesn't exist * or is offline, %NULL is returned. */ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; rcu_read_lock(); css = cgroup_css(cgrp, ss); if (css && !css_tryget_online(css)) css = NULL; rcu_read_unlock(); return css; } /** * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Similar to cgroup_css() but returns the effective css, which is defined * as the matching css of the nearest ancestor including self which has @ss * enabled. If @ss is associated with the hierarchy @cgrp is on, this * function is guaranteed to return non-NULL css. */ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, struct cgroup_subsys *ss) { lockdep_assert_held(&cgroup_mutex); if (!ss) return &cgrp->self; /* * This function is used while updating css associations and thus * can't test the csses directly. Test ss_mask. */ while (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) { cgrp = cgroup_parent(cgrp); if (!cgrp) return NULL; } return cgroup_css(cgrp, ss); } /** * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * * The returned css is not guaranteed to be online, and therefore it is the * callers responsibility to try get a reference for it. */ struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; if (!CGROUP_HAS_SUBSYS_CONFIG) return NULL; do { css = cgroup_css(cgrp, ss); if (css) return css; cgrp = cgroup_parent(cgrp); } while (cgrp); return init_css_set.subsys[ss->id]; } /** * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * The returned css must be put using css_put(). */ struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; if (!CGROUP_HAS_SUBSYS_CONFIG) return NULL; rcu_read_lock(); do { css = cgroup_css(cgrp, ss); if (css && css_tryget_online(css)) goto out_unlock; cgrp = cgroup_parent(cgrp); } while (cgrp); css = init_css_set.subsys[ss->id]; css_get(css); out_unlock: rcu_read_unlock(); return css; } EXPORT_SYMBOL_GPL(cgroup_get_e_css); static void cgroup_get_live(struct cgroup *cgrp) { WARN_ON_ONCE(cgroup_is_dead(cgrp)); css_get(&cgrp->self); } /** * __cgroup_task_count - count the number of tasks in a cgroup. The caller * is responsible for taking the css_set_lock. * @cgrp: the cgroup in question */ int __cgroup_task_count(const struct cgroup *cgrp) { int count = 0; struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) count += link->cset->nr_tasks; return count; } /** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question */ int cgroup_task_count(const struct cgroup *cgrp) { int count; spin_lock_irq(&css_set_lock); count = __cgroup_task_count(cgrp); spin_unlock_irq(&css_set_lock); return count; } struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) { struct cgroup *cgrp = of->kn->parent->priv; struct cftype *cft = of_cft(of); /* * This is open and unprotected implementation of cgroup_css(). * seq_css() is only called from a kernfs file operation which has * an active reference on the file. Because all the subsystem * files are drained before a css is disassociated with a cgroup, * the matching css from the cgroup's subsys table is guaranteed to * be and stay valid until the enclosing operation is complete. */ if (CGROUP_HAS_SUBSYS_CONFIG && cft->ss) return rcu_dereference_raw(cgrp->subsys[cft->ss->id]); else return &cgrp->self; } EXPORT_SYMBOL_GPL(of_css); /** * for_each_css - iterate all css's of a cgroup * @css: the iteration cursor * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end * @cgrp: the target cgroup to iterate css's of * * Should be called under cgroup_[tree_]mutex. */ #define for_each_css(css, ssid, cgrp) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ if (!((css) = rcu_dereference_check( \ (cgrp)->subsys[(ssid)], \ lockdep_is_held(&cgroup_mutex)))) { } \ else /** * for_each_e_css - iterate all effective css's of a cgroup * @css: the iteration cursor * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end * @cgrp: the target cgroup to iterate css's of * * Should be called under cgroup_[tree_]mutex. */ #define for_each_e_css(css, ssid, cgrp) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ if (!((css) = cgroup_e_css_by_mask(cgrp, \ cgroup_subsys[(ssid)]))) \ ; \ else /** * do_each_subsys_mask - filter for_each_subsys with a bitmask * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end * @ss_mask: the bitmask * * The block will only run for cases where the ssid-th bit (1 << ssid) of * @ss_mask is set. */ #define do_each_subsys_mask(ss, ssid, ss_mask) do { \ unsigned long __ss_mask = (ss_mask); \ if (!CGROUP_HAS_SUBSYS_CONFIG) { \ (ssid) = 0; \ break; \ } \ for_each_set_bit(ssid, &__ss_mask, CGROUP_SUBSYS_COUNT) { \ (ss) = cgroup_subsys[ssid]; \ { #define while_each_subsys_mask() \ } \ } \ } while (false) /* iterate over child cgrps, lock should be held throughout iteration */ #define cgroup_for_each_live_child(child, cgrp) \ list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \ if (({ lockdep_assert_held(&cgroup_mutex); \ cgroup_is_dead(child); })) \ ; \ else /* walk live descendants in pre order */ #define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \ css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else /* walk live descendants in postorder */ #define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) \ css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else /* * The default css_set - used by init and its children prior to any * hierarchies being mounted. It contains a pointer to the root state * for each subsystem. Also used to anchor the list of css_sets. Not * reference-counted, to improve performance when child cgroups * haven't been created. */ struct css_set init_css_set = { .refcount = REFCOUNT_INIT(1), .dom_cset = &init_css_set, .tasks = LIST_HEAD_INIT(init_css_set.tasks), .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks), .dying_tasks = LIST_HEAD_INIT(init_css_set.dying_tasks), .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), .threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node), .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node), .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), /* * The following field is re-initialized when this cset gets linked * in cgroup_init(). However, let's initialize the field * statically too so that the default cgroup can be accessed safely * early during boot. */ .dfl_cgrp = &cgrp_dfl_root.cgrp, }; static int css_set_count = 1; /* 1 for init_css_set */ static bool css_set_threaded(struct css_set *cset) { return cset->dom_cset != cset; } /** * css_set_populated - does a css_set contain any tasks? * @cset: target css_set * * css_set_populated() should be the same as !!cset->nr_tasks at steady * state. However, css_set_populated() can be called while a task is being * added to or removed from the linked list before the nr_tasks is * properly updated. Hence, we can't just look at ->nr_tasks here. */ static bool css_set_populated(struct css_set *cset) { lockdep_assert_held(&css_set_lock); return !list_empty(&cset->tasks) || !list_empty(&cset->mg_tasks); } /** * cgroup_update_populated - update the populated count of a cgroup * @cgrp: the target cgroup * @populated: inc or dec populated count * * One of the css_sets associated with @cgrp is either getting its first * task or losing the last. Update @cgrp->nr_populated_* accordingly. The * count is propagated towards root so that a given cgroup's * nr_populated_children is zero iff none of its descendants contain any * tasks. * * @cgrp's interface file "cgroup.populated" is zero if both * @cgrp->nr_populated_csets and @cgrp->nr_populated_children are zero and * 1 otherwise. When the sum changes from or to zero, userland is notified * that the content of the interface file has changed. This can be used to * detect when @cgrp and its descendants become populated or empty. */ static void cgroup_update_populated(struct cgroup *cgrp, bool populated) { struct cgroup *child = NULL; int adj = populated ? 1 : -1; lockdep_assert_held(&css_set_lock); do { bool was_populated = cgroup_is_populated(cgrp); if (!child) { cgrp->nr_populated_csets += adj; } else { if (cgroup_is_threaded(child)) cgrp->nr_populated_threaded_children += adj; else cgrp->nr_populated_domain_children += adj; } if (was_populated == cgroup_is_populated(cgrp)) break; cgroup1_check_for_release(cgrp); TRACE_CGROUP_PATH(notify_populated, cgrp, cgroup_is_populated(cgrp)); cgroup_file_notify(&cgrp->events_file); child = cgrp; cgrp = cgroup_parent(cgrp); } while (cgrp); } /** * css_set_update_populated - update populated state of a css_set * @cset: target css_set * @populated: whether @cset is populated or depopulated * * @cset is either getting the first task or losing the last. Update the * populated counters of all associated cgroups accordingly. */ static void css_set_update_populated(struct css_set *cset, bool populated) { struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) cgroup_update_populated(link->cgrp, populated); } /* * @task is leaving, advance task iterators which are pointing to it so * that they can resume at the next position. Advancing an iterator might * remove it from the list, use safe walk. See css_task_iter_skip() for * details. */ static void css_set_skip_task_iters(struct css_set *cset, struct task_struct *task) { struct css_task_iter *it, *pos; list_for_each_entry_safe(it, pos, &cset->task_iters, iters_node) css_task_iter_skip(it, task); } /** * css_set_move_task - move a task from one css_set to another * @task: task being moved * @from_cset: css_set @task currently belongs to (may be NULL) * @to_cset: new css_set @task is being moved to (may be NULL) * @use_mg_tasks: move to @to_cset->mg_tasks instead of ->tasks * * Move @task from @from_cset to @to_cset. If @task didn't belong to any * css_set, @from_cset can be NULL. If @task is being disassociated * instead of moved, @to_cset can be NULL. * * This function automatically handles populated counter updates and * css_task_iter adjustments but the caller is responsible for managing * @from_cset and @to_cset's reference counts. */ static void css_set_move_task(struct task_struct *task, struct css_set *from_cset, struct css_set *to_cset, bool use_mg_tasks) { lockdep_assert_held(&css_set_lock); if (to_cset && !css_set_populated(to_cset)) css_set_update_populated(to_cset, true); if (from_cset) { WARN_ON_ONCE(list_empty(&task->cg_list)); css_set_skip_task_iters(from_cset, task); list_del_init(&task->cg_list); if (!css_set_populated(from_cset)) css_set_update_populated(from_cset, false); } else { WARN_ON_ONCE(!list_empty(&task->cg_list)); } if (to_cset) { /* * We are synchronized through cgroup_threadgroup_rwsem * against PF_EXITING setting such that we can't race * against cgroup_exit()/cgroup_free() dropping the css_set. */ WARN_ON_ONCE(task->flags & PF_EXITING); cgroup_move_task(task, to_cset); list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : &to_cset->tasks); } } /* * hash table for cgroup groups. This improves the performance to find * an existing css_set. This hash doesn't (currently) take into * account cgroups in empty hierarchies. */ #define CSS_SET_HASH_BITS 7 static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS); static unsigned long css_set_hash(struct cgroup_subsys_state *css[]) { unsigned long key = 0UL; struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) key += (unsigned long)css[i]; key = (key >> 16) ^ key; return key; } void put_css_set_locked(struct css_set *cset) { struct cgrp_cset_link *link, *tmp_link; struct cgroup_subsys *ss; int ssid; lockdep_assert_held(&css_set_lock); if (!refcount_dec_and_test(&cset->refcount)) return; WARN_ON_ONCE(!list_empty(&cset->threaded_csets)); /* This css_set is dead. Unlink it and release cgroup and css refs */ for_each_subsys(ss, ssid) { list_del(&cset->e_cset_node[ssid]); css_put(cset->subsys[ssid]); } hash_del(&cset->hlist); css_set_count--; list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); if (cgroup_parent(link->cgrp)) cgroup_put(link->cgrp); kfree(link); } if (css_set_threaded(cset)) { list_del(&cset->threaded_csets_node); put_css_set_locked(cset->dom_cset); } kfree_rcu(cset, rcu_head); } /** * compare_css_sets - helper function for find_existing_css_set(). * @cset: candidate css_set being tested * @old_cset: existing css_set for a task * @new_cgrp: cgroup that's being entered by the task * @template: desired set of css pointers in css_set (pre-calculated) * * Returns true if "cset" matches "old_cset" except for the hierarchy * which "new_cgrp" belongs to, for which it should match "new_cgrp". */ static bool compare_css_sets(struct css_set *cset, struct css_set *old_cset, struct cgroup *new_cgrp, struct cgroup_subsys_state *template[]) { struct cgroup *new_dfl_cgrp; struct list_head *l1, *l2; /* * On the default hierarchy, there can be csets which are * associated with the same set of cgroups but different csses. * Let's first ensure that csses match. */ if (memcmp(template, cset->subsys, sizeof(cset->subsys))) return false; /* @cset's domain should match the default cgroup's */ if (cgroup_on_dfl(new_cgrp)) new_dfl_cgrp = new_cgrp; else new_dfl_cgrp = old_cset->dfl_cgrp; if (new_dfl_cgrp->dom_cgrp != cset->dom_cset->dfl_cgrp) return false; /* * Compare cgroup pointers in order to distinguish between * different cgroups in hierarchies. As different cgroups may * share the same effective css, this comparison is always * necessary. */ l1 = &cset->cgrp_links; l2 = &old_cset->cgrp_links; while (1) { struct cgrp_cset_link *link1, *link2; struct cgroup *cgrp1, *cgrp2; l1 = l1->next; l2 = l2->next; /* See if we reached the end - both lists are equal length. */ if (l1 == &cset->cgrp_links) { BUG_ON(l2 != &old_cset->cgrp_links); break; } else { BUG_ON(l2 == &old_cset->cgrp_links); } /* Locate the cgroups associated with these links. */ link1 = list_entry(l1, struct cgrp_cset_link, cgrp_link); link2 = list_entry(l2, struct cgrp_cset_link, cgrp_link); cgrp1 = link1->cgrp; cgrp2 = link2->cgrp; /* Hierarchies should be linked in the same order. */ BUG_ON(cgrp1->root != cgrp2->root); /* * If this hierarchy is the hierarchy of the cgroup * that's changing, then we need to check that this * css_set points to the new cgroup; if it's any other * hierarchy, then this css_set should point to the * same cgroup as the old css_set. */ if (cgrp1->root == new_cgrp->root) { if (cgrp1 != new_cgrp) return false; } else { if (cgrp1 != cgrp2) return false; } } return true; } /** * find_existing_css_set - init css array and find the matching css_set * @old_cset: the css_set that we're using before the cgroup transition * @cgrp: the cgroup that we're moving into * @template: out param for the new set of csses, should be clear on entry */ static struct css_set *find_existing_css_set(struct css_set *old_cset, struct cgroup *cgrp, struct cgroup_subsys_state *template[]) { struct cgroup_root *root = cgrp->root; struct cgroup_subsys *ss; struct css_set *cset; unsigned long key; int i; /* * Build the set of subsystem state objects that we want to see in the * new css_set. While subsystems can change globally, the entries here * won't change, so no need for locking. */ for_each_subsys(ss, i) { if (root->subsys_mask & (1UL << i)) { /* * @ss is in this hierarchy, so we want the * effective css from @cgrp. */ template[i] = cgroup_e_css_by_mask(cgrp, ss); } else { /* * @ss is not in this hierarchy, so we don't want * to change the css. */ template[i] = old_cset->subsys[i]; } } key = css_set_hash(template); hash_for_each_possible(css_set_table, cset, hlist, key) { if (!compare_css_sets(cset, old_cset, cgrp, template)) continue; /* This css_set matches what we need */ return cset; } /* No existing cgroup group matched */ return NULL; } static void free_cgrp_cset_links(struct list_head *links_to_free) { struct cgrp_cset_link *link, *tmp_link; list_for_each_entry_safe(link, tmp_link, links_to_free, cset_link) { list_del(&link->cset_link); kfree(link); } } /** * allocate_cgrp_cset_links - allocate cgrp_cset_links * @count: the number of links to allocate * @tmp_links: list_head the allocated links are put on * * Allocate @count cgrp_cset_link structures and chain them on @tmp_links * through ->cset_link. Returns 0 on success or -errno. */ static int allocate_cgrp_cset_links(int count, struct list_head *tmp_links) { struct cgrp_cset_link *link; int i; INIT_LIST_HEAD(tmp_links); for (i = 0; i < count; i++) { link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { free_cgrp_cset_links(tmp_links); return -ENOMEM; } list_add(&link->cset_link, tmp_links); } return 0; } /** * link_css_set - a helper function to link a css_set to a cgroup * @tmp_links: cgrp_cset_link objects allocated by allocate_cgrp_cset_links() * @cset: the css_set to be linked * @cgrp: the destination cgroup */ static void link_css_set(struct list_head *tmp_links, struct css_set *cset, struct cgroup *cgrp) { struct cgrp_cset_link *link; BUG_ON(list_empty(tmp_links)); if (cgroup_on_dfl(cgrp)) cset->dfl_cgrp = cgrp; link = list_first_entry(tmp_links, struct cgrp_cset_link, cset_link); link->cset = cset; link->cgrp = cgrp; /* * Always add links to the tail of the lists so that the lists are * in chronological order. */ list_move_tail(&link->cset_link, &cgrp->cset_links); list_add_tail(&link->cgrp_link, &cset->cgrp_links); if (cgroup_parent(cgrp)) cgroup_get_live(cgrp); } /** * find_css_set - return a new css_set with one cgroup updated * @old_cset: the baseline css_set * @cgrp: the cgroup to be updated * * Return a new css_set that's equivalent to @old_cset, but with @cgrp * substituted into the appropriate hierarchy. */ static struct css_set *find_css_set(struct css_set *old_cset, struct cgroup *cgrp) { struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT] = { }; struct css_set *cset; struct list_head tmp_links; struct cgrp_cset_link *link; struct cgroup_subsys *ss; unsigned long key; int ssid; lockdep_assert_held(&cgroup_mutex); /* First see if we already have a cgroup group that matches * the desired set */ spin_lock_irq(&css_set_lock); cset = find_existing_css_set(old_cset, cgrp, template); if (cset) get_css_set(cset); spin_unlock_irq(&css_set_lock); if (cset) return cset; cset = kzalloc(sizeof(*cset), GFP_KERNEL); if (!cset) return NULL; /* Allocate all the cgrp_cset_link objects that we'll need */ if (allocate_cgrp_cset_links(cgroup_root_count, &tmp_links) < 0) { kfree(cset); return NULL; } refcount_set(&cset->refcount, 1); cset->dom_cset = cset; INIT_LIST_HEAD(&cset->tasks); INIT_LIST_HEAD(&cset->mg_tasks); INIT_LIST_HEAD(&cset->dying_tasks); INIT_LIST_HEAD(&cset->task_iters); INIT_LIST_HEAD(&cset->threaded_csets); INIT_HLIST_NODE(&cset->hlist); INIT_LIST_HEAD(&cset->cgrp_links); INIT_LIST_HEAD(&cset->mg_src_preload_node); INIT_LIST_HEAD(&cset->mg_dst_preload_node); INIT_LIST_HEAD(&cset->mg_node); /* Copy the set of subsystem state objects generated in * find_existing_css_set() */ memcpy(cset->subsys, template, sizeof(cset->subsys)); spin_lock_irq(&css_set_lock); /* Add reference counts and links from the new css_set. */ list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == cgrp->root) c = cgrp; link_css_set(&tmp_links, cset, c); } BUG_ON(!list_empty(&tmp_links)); css_set_count++; /* Add @cset to the hash table */ key = css_set_hash(cset->subsys); hash_add(css_set_table, &cset->hlist, key); for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cset->subsys[ssid]; list_add_tail(&cset->e_cset_node[ssid], &css->cgroup->e_csets[ssid]); css_get(css); } spin_unlock_irq(&css_set_lock); /* * If @cset should be threaded, look up the matching dom_cset and * link them up. We first fully initialize @cset then look for the * dom_cset. It's simpler this way and safe as @cset is guaranteed * to stay empty until we return. */ if (cgroup_is_threaded(cset->dfl_cgrp)) { struct css_set *dcset; dcset = find_css_set(cset, cset->dfl_cgrp->dom_cgrp); if (!dcset) { put_css_set(cset); return NULL; } spin_lock_irq(&css_set_lock); cset->dom_cset = dcset; list_add_tail(&cset->threaded_csets_node, &dcset->threaded_csets); spin_unlock_irq(&css_set_lock); } return cset; } struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) { struct cgroup *root_cgrp = kernfs_root_to_node(kf_root)->priv; return root_cgrp->root; } void cgroup_favor_dynmods(struct cgroup_root *root, bool favor) { bool favoring = root->flags & CGRP_ROOT_FAVOR_DYNMODS; /* see the comment above CGRP_ROOT_FAVOR_DYNMODS definition */ if (favor && !favoring) { rcu_sync_enter(&cgroup_threadgroup_rwsem.rss); root->flags |= CGRP_ROOT_FAVOR_DYNMODS; } else if (!favor && favoring) { rcu_sync_exit(&cgroup_threadgroup_rwsem.rss); root->flags &= ~CGRP_ROOT_FAVOR_DYNMODS; } } static int cgroup_init_root_id(struct cgroup_root *root) { int id; lockdep_assert_held(&cgroup_mutex); id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL); if (id < 0) return id; root->hierarchy_id = id; return 0; } static void cgroup_exit_root_id(struct cgroup_root *root) { lockdep_assert_held(&cgroup_mutex); idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); } void cgroup_free_root(struct cgroup_root *root) { kfree(root); } static void cgroup_destroy_root(struct cgroup_root *root) { struct cgroup *cgrp = &root->cgrp; struct cgrp_cset_link *link, *tmp_link; trace_cgroup_destroy_root(root); cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); BUG_ON(atomic_read(&root->nr_cgrps)); BUG_ON(!list_empty(&cgrp->self.children)); /* Rebind all subsystems back to the default hierarchy */ WARN_ON(rebind_subsystems(&cgrp_dfl_root, root->subsys_mask)); /* * Release all the links from cset_links to this hierarchy's * root cgroup */ spin_lock_irq(&css_set_lock); list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); kfree(link); } spin_unlock_irq(&css_set_lock); if (!list_empty(&root->root_list)) { list_del(&root->root_list); cgroup_root_count--; } cgroup_favor_dynmods(root, false); cgroup_exit_root_id(root); mutex_unlock(&cgroup_mutex); cgroup_rstat_exit(cgrp); kernfs_destroy_root(root->kf_root); cgroup_free_root(root); } /* * Returned cgroup is without refcount but it's valid as long as cset pins it. */ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { struct cgroup *res_cgroup = NULL; if (cset == &init_css_set) { res_cgroup = &root->cgrp; } else if (root == &cgrp_dfl_root) { res_cgroup = cset->dfl_cgrp; } else { struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == root) { res_cgroup = c; break; } } } BUG_ON(!res_cgroup); return res_cgroup; } /* * look up cgroup associated with current task's cgroup namespace on the * specified hierarchy */ static struct cgroup * current_cgns_cgroup_from_root(struct cgroup_root *root) { struct cgroup *res = NULL; struct css_set *cset; lockdep_assert_held(&css_set_lock); rcu_read_lock(); cset = current->nsproxy->cgroup_ns->root_cset; res = __cset_cgroup_from_root(cset, root); rcu_read_unlock(); return res; } /* * Look up cgroup associated with current task's cgroup namespace on the default * hierarchy. * * Unlike current_cgns_cgroup_from_root(), this doesn't need locks: * - Internal rcu_read_lock is unnecessary because we don't dereference any rcu * pointers. * - css_set_lock is not needed because we just read cset->dfl_cgrp. * - As a bonus returned cgrp is pinned with the current because it cannot * switch cgroup_ns asynchronously. */ static struct cgroup *current_cgns_cgroup_dfl(void) { struct css_set *cset; cset = current->nsproxy->cgroup_ns->root_cset; return __cset_cgroup_from_root(cset, &cgrp_dfl_root); } /* look up cgroup associated with given css_set on the specified hierarchy */ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); return __cset_cgroup_from_root(cset, root); } /* * Return the cgroup for "task" from the given hierarchy. Must be * called with cgroup_mutex and css_set_lock held. */ struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root) { /* * No need to lock the task - since we hold css_set_lock the * task can't change groups. */ return cset_cgroup_from_root(task_css_set(task), root); } /* * A task must hold cgroup_mutex to modify cgroups. * * Any task can increment and decrement the count field without lock. * So in general, code holding cgroup_mutex can't rely on the count * field not changing. However, if the count goes to zero, then only * cgroup_attach_task() can increment it again. Because a count of zero * means that no tasks are currently attached, therefore there is no * way a task attached to that cgroup can fork (the other way to * increment the count). So code holding cgroup_mutex can safely * assume that if the count is zero, it will stay zero. Similarly, if * a task holds cgroup_mutex on a cgroup with zero count, it * knows that the cgroup won't be removed, as cgroup_rmdir() * needs that mutex. * * A cgroup can only be deleted if both its 'count' of using tasks * is zero, and its list of 'children' cgroups is empty. Since all * tasks in the system use _some_ cgroup, and since there is always at * least one task in the system (init, pid == 1), therefore, root cgroup * always has either children cgroups and/or using tasks. So we don't * need a special hack to ensure that root cgroup cannot be deleted. * * P.S. One more locking exception. RCU is used to guard the * update of a tasks cgroup pointer by cgroup_attach_task() */ static struct kernfs_syscall_ops cgroup_kf_syscall_ops; static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft, char *buf) { struct cgroup_subsys *ss = cft->ss; if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) && !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) { const char *dbg = (cft->flags & CFTYPE_DEBUG) ? ".__DEBUG__." : ""; snprintf(buf, CGROUP_FILE_NAME_MAX, "%s%s.%s", dbg, cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name, cft->name); } else { strscpy(buf, cft->name, CGROUP_FILE_NAME_MAX); } return buf; } /** * cgroup_file_mode - deduce file mode of a control file * @cft: the control file in question * * S_IRUGO for read, S_IWUSR for write. */ static umode_t cgroup_file_mode(const struct cftype *cft) { umode_t mode = 0; if (cft->read_u64 || cft->read_s64 || cft->seq_show) mode |= S_IRUGO; if (cft->write_u64 || cft->write_s64 || cft->write) { if (cft->flags & CFTYPE_WORLD_WRITABLE) mode |= S_IWUGO; else mode |= S_IWUSR; } return mode; } /** * cgroup_calc_subtree_ss_mask - calculate subtree_ss_mask * @subtree_control: the new subtree_control mask to consider * @this_ss_mask: available subsystems * * On the default hierarchy, a subsystem may request other subsystems to be * enabled together through its ->depends_on mask. In such cases, more * subsystems than specified in "cgroup.subtree_control" may be enabled. * * This function calculates which subsystems need to be enabled if * @subtree_control is to be applied while restricted to @this_ss_mask. */ static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask) { u16 cur_ss_mask = subtree_control; struct cgroup_subsys *ss; int ssid; lockdep_assert_held(&cgroup_mutex); cur_ss_mask |= cgrp_dfl_implicit_ss_mask; while (true) { u16 new_ss_mask = cur_ss_mask; do_each_subsys_mask(ss, ssid, cur_ss_mask) { new_ss_mask |= ss->depends_on; } while_each_subsys_mask(); /* * Mask out subsystems which aren't available. This can * happen only if some depended-upon subsystems were bound * to non-default hierarchies. */ new_ss_mask &= this_ss_mask; if (new_ss_mask == cur_ss_mask) break; cur_ss_mask = new_ss_mask; } return cur_ss_mask; } /** * cgroup_kn_unlock - unlocking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * * This helper undoes cgroup_kn_lock_live() and should be invoked before * the method finishes if locking succeeded. Note that once this function * returns the cgroup returned by cgroup_kn_lock_live() may become * inaccessible any time. If the caller intends to continue to access the * cgroup, it should pin it before invoking this function. */ void cgroup_kn_unlock(struct kernfs_node *kn) { struct cgroup *cgrp; if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn->parent->priv; mutex_unlock(&cgroup_mutex); kernfs_unbreak_active_protection(kn); cgroup_put(cgrp); } /** * cgroup_kn_lock_live - locking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * @drain_offline: perform offline draining on the cgroup * * This helper is to be used by a cgroup kernfs method currently servicing * @kn. It breaks the active protection, performs cgroup locking and * verifies that the associated cgroup is alive. Returns the cgroup if * alive; otherwise, %NULL. A successful return should be undone by a * matching cgroup_kn_unlock() invocation. If @drain_offline is %true, the * cgroup is drained of offlining csses before return. * * Any cgroup kernfs method implementation which requires locking the * associated cgroup should use this helper. It avoids nesting cgroup * locking under kernfs active protection and allows all kernfs operations * including self-removal. */ struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline) { struct cgroup *cgrp; if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn->parent->priv; /* * We're gonna grab cgroup_mutex which nests outside kernfs * active_ref. cgroup liveliness check alone provides enough * protection against removal. Ensure @cgrp stays accessible and * break the active_ref protection. */ if (!cgroup_tryget(cgrp)) return NULL; kernfs_break_active_protection(kn); if (drain_offline) cgroup_lock_and_drain_offline(cgrp); else mutex_lock(&cgroup_mutex); if (!cgroup_is_dead(cgrp)) return cgrp; cgroup_kn_unlock(kn); return NULL; } static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) { char name[CGROUP_FILE_NAME_MAX]; lockdep_assert_held(&cgroup_mutex); if (cft->file_offset) { struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss); struct cgroup_file *cfile = (void *)css + cft->file_offset; spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = NULL; spin_unlock_irq(&cgroup_file_kn_lock); del_timer_sync(&cfile->notify_timer); } kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); } /** * css_clear_dir - remove subsys files in a cgroup directory * @css: target css */ static void css_clear_dir(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; struct cftype *cfts; if (!(css->flags & CSS_VISIBLE)) return; css->flags &= ~CSS_VISIBLE; if (!css->ss) { if (cgroup_on_dfl(cgrp)) { cgroup_addrm_files(css, cgrp, cgroup_base_files, false); if (cgroup_psi_enabled()) cgroup_addrm_files(css, cgrp, cgroup_psi_files, false); } else { cgroup_addrm_files(css, cgrp, cgroup1_base_files, false); } } else { list_for_each_entry(cfts, &css->ss->cfts, node) cgroup_addrm_files(css, cgrp, cfts, false); } } /** * css_populate_dir - create subsys files in a cgroup directory * @css: target css * * On failure, no file is added. */ static int css_populate_dir(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; struct cftype *cfts, *failed_cfts; int ret; if ((css->flags & CSS_VISIBLE) || !cgrp->kn) return 0; if (!css->ss) { if (cgroup_on_dfl(cgrp)) { ret = cgroup_addrm_files(&cgrp->self, cgrp, cgroup_base_files, true); if (ret < 0) return ret; if (cgroup_psi_enabled()) { ret = cgroup_addrm_files(&cgrp->self, cgrp, cgroup_psi_files, true); if (ret < 0) return ret; } } else { cgroup_addrm_files(css, cgrp, cgroup1_base_files, true); } } else { list_for_each_entry(cfts, &css->ss->cfts, node) { ret = cgroup_addrm_files(css, cgrp, cfts, true); if (ret < 0) { failed_cfts = cfts; goto err; } } } css->flags |= CSS_VISIBLE; return 0; err: list_for_each_entry(cfts, &css->ss->cfts, node) { if (cfts == failed_cfts) break; cgroup_addrm_files(css, cgrp, cfts, false); } return ret; } int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) { struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; int ssid, i, ret; u16 dfl_disable_ss_mask = 0; lockdep_assert_held(&cgroup_mutex); do_each_subsys_mask(ss, ssid, ss_mask) { /* * If @ss has non-root csses attached to it, can't move. * If @ss is an implicit controller, it is exempt from this * rule and can be stolen. */ if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)) && !ss->implicit_on_dfl) return -EBUSY; /* can't move between two non-dummy roots either */ if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root) return -EBUSY; /* * Collect ssid's that need to be disabled from default * hierarchy. */ if (ss->root == &cgrp_dfl_root) dfl_disable_ss_mask |= 1 << ssid; } while_each_subsys_mask(); if (dfl_disable_ss_mask) { struct cgroup *scgrp = &cgrp_dfl_root.cgrp; /* * Controllers from default hierarchy that need to be rebound * are all disabled together in one go. */ cgrp_dfl_root.subsys_mask &= ~dfl_disable_ss_mask; WARN_ON(cgroup_apply_control(scgrp)); cgroup_finalize_control(scgrp, 0); } do_each_subsys_mask(ss, ssid, ss_mask) { struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; struct cgroup_subsys_state *css = cgroup_css(scgrp, ss); struct css_set *cset; WARN_ON(!css || cgroup_css(dcgrp, ss)); if (src_root != &cgrp_dfl_root) { /* disable from the source */ src_root->subsys_mask &= ~(1 << ssid); WARN_ON(cgroup_apply_control(scgrp)); cgroup_finalize_control(scgrp, 0); } /* rebind */ RCU_INIT_POINTER(scgrp->subsys[ssid], NULL); rcu_assign_pointer(dcgrp->subsys[ssid], css); ss->root = dst_root; css->cgroup = dcgrp; spin_lock_irq(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) list_move_tail(&cset->e_cset_node[ss->id], &dcgrp->e_csets[ss->id]); spin_unlock_irq(&css_set_lock); if (ss->css_rstat_flush) { list_del_rcu(&css->rstat_css_node); synchronize_rcu(); list_add_rcu(&css->rstat_css_node, &dcgrp->rstat_css_list); } /* default hierarchy doesn't enable controllers by default */ dst_root->subsys_mask |= 1 << ssid; if (dst_root == &cgrp_dfl_root) { static_branch_enable(cgroup_subsys_on_dfl_key[ssid]); } else { dcgrp->subtree_control |= 1 << ssid; static_branch_disable(cgroup_subsys_on_dfl_key[ssid]); } ret = cgroup_apply_control(dcgrp); if (ret) pr_warn("partial failure to rebind %s controller (err=%d)\n", ss->name, ret); if (ss->bind) ss->bind(css); } while_each_subsys_mask(); kernfs_activate(dcgrp->kn); return 0; } int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root) { int len = 0; char *buf = NULL; struct cgroup_root *kf_cgroot = cgroup_root_from_kf(kf_root); struct cgroup *ns_cgroup; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) return -ENOMEM; spin_lock_irq(&css_set_lock); ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot); len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX); spin_unlock_irq(&css_set_lock); if (len >= PATH_MAX) len = -ERANGE; else if (len > 0) { seq_escape(sf, buf, " \t\n\\"); len = 0; } kfree(buf); return len; } enum cgroup2_param { Opt_nsdelegate, Opt_favordynmods, Opt_memory_localevents, Opt_memory_recursiveprot, nr__cgroup2_params }; static const struct fs_parameter_spec cgroup2_fs_parameters[] = { fsparam_flag("nsdelegate", Opt_nsdelegate), fsparam_flag("favordynmods", Opt_favordynmods), fsparam_flag("memory_localevents", Opt_memory_localevents), fsparam_flag("memory_recursiveprot", Opt_memory_recursiveprot), {} }; static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct fs_parse_result result; int opt; opt = fs_parse(fc, cgroup2_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_nsdelegate: ctx->flags |= CGRP_ROOT_NS_DELEGATE; return 0; case Opt_favordynmods: ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; return 0; case Opt_memory_localevents: ctx->flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; return 0; case Opt_memory_recursiveprot: ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; return 0; } return -EINVAL; } static void apply_cgroup_root_flags(unsigned int root_flags) { if (current->nsproxy->cgroup_ns == &init_cgroup_ns) { if (root_flags & CGRP_ROOT_NS_DELEGATE) cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE; else cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE; cgroup_favor_dynmods(&cgrp_dfl_root, root_flags & CGRP_ROOT_FAVOR_DYNMODS); if (root_flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_LOCAL_EVENTS; if (root_flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT; } } static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root) { if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) seq_puts(seq, ",nsdelegate"); if (cgrp_dfl_root.flags & CGRP_ROOT_FAVOR_DYNMODS) seq_puts(seq, ",favordynmods"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) seq_puts(seq, ",memory_localevents"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) seq_puts(seq, ",memory_recursiveprot"); return 0; } static int cgroup_reconfigure(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); apply_cgroup_root_flags(ctx->flags); return 0; } static void init_cgroup_housekeeping(struct cgroup *cgrp) { struct cgroup_subsys *ss; int ssid; INIT_LIST_HEAD(&cgrp->self.sibling); INIT_LIST_HEAD(&cgrp->self.children); INIT_LIST_HEAD(&cgrp->cset_links); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); cgrp->self.cgroup = cgrp; cgrp->self.flags |= CSS_ONLINE; cgrp->dom_cgrp = cgrp; cgrp->max_descendants = INT_MAX; cgrp->max_depth = INT_MAX; INIT_LIST_HEAD(&cgrp->rstat_css_list); prev_cputime_init(&cgrp->prev_cputime); for_each_subsys(ss, ssid) INIT_LIST_HEAD(&cgrp->e_csets[ssid]); init_waitqueue_head(&cgrp->offline_waitq); INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent); } void init_cgroup_root(struct cgroup_fs_context *ctx) { struct cgroup_root *root = ctx->root; struct cgroup *cgrp = &root->cgrp; INIT_LIST_HEAD(&root->root_list); atomic_set(&root->nr_cgrps, 1); cgrp->root = root; init_cgroup_housekeeping(cgrp); /* DYNMODS must be modified through cgroup_favor_dynmods() */ root->flags = ctx->flags & ~CGRP_ROOT_FAVOR_DYNMODS; if (ctx->release_agent) strscpy(root->release_agent_path, ctx->release_agent, PATH_MAX); if (ctx->name) strscpy(root->name, ctx->name, MAX_CGROUP_ROOT_NAMELEN); if (ctx->cpuset_clone_children) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags); } int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) { LIST_HEAD(tmp_links); struct cgroup *root_cgrp = &root->cgrp; struct kernfs_syscall_ops *kf_sops; struct css_set *cset; int i, ret; lockdep_assert_held(&cgroup_mutex); ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out; /* * We're accessing css_set_count without locking css_set_lock here, * but that's OK - it can only be increased by someone holding * cgroup_lock, and that's us. Later rebinding may disable * controllers on the default hierarchy and thus create new csets, * which can't be more than the existing ones. Allocate 2x. */ ret = allocate_cgrp_cset_links(2 * css_set_count, &tmp_links); if (ret) goto cancel_ref; ret = cgroup_init_root_id(root); if (ret) goto cancel_ref; kf_sops = root == &cgrp_dfl_root ? &cgroup_kf_syscall_ops : &cgroup1_kf_syscall_ops; root->kf_root = kernfs_create_root(kf_sops, KERNFS_ROOT_CREATE_DEACTIVATED | KERNFS_ROOT_SUPPORT_EXPORTOP | KERNFS_ROOT_SUPPORT_USER_XATTR, root_cgrp); if (IS_ERR(root->kf_root)) { ret = PTR_ERR(root->kf_root); goto exit_root_id; } root_cgrp->kn = kernfs_root_to_node(root->kf_root); WARN_ON_ONCE(cgroup_ino(root_cgrp) != 1); root_cgrp->ancestors[0] = root_cgrp; ret = css_populate_dir(&root_cgrp->self); if (ret) goto destroy_root; ret = cgroup_rstat_init(root_cgrp); if (ret) goto destroy_root; ret = rebind_subsystems(root, ss_mask); if (ret) goto exit_stats; ret = cgroup_bpf_inherit(root_cgrp); WARN_ON_ONCE(ret); trace_cgroup_setup_root(root); /* * There must be no failure case after here, since rebinding takes * care of subsystems' refcounts, which are explicitly dropped in * the failure exit path. */ list_add(&root->root_list, &cgroup_roots); cgroup_root_count++; /* * Link the root cgroup in this hierarchy into all the css_set * objects. */ spin_lock_irq(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) { link_css_set(&tmp_links, cset, root_cgrp); if (css_set_populated(cset)) cgroup_update_populated(root_cgrp, true); } spin_unlock_irq(&css_set_lock); BUG_ON(!list_empty(&root_cgrp->self.children)); BUG_ON(atomic_read(&root->nr_cgrps) != 1); ret = 0; goto out; exit_stats: cgroup_rstat_exit(root_cgrp); destroy_root: kernfs_destroy_root(root->kf_root); root->kf_root = NULL; exit_root_id: cgroup_exit_root_id(root); cancel_ref: percpu_ref_exit(&root_cgrp->self.refcnt); out: free_cgrp_cset_links(&tmp_links); return ret; } int cgroup_do_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; ctx->kfc.root = ctx->root->kf_root; if (fc->fs_type == &cgroup2_fs_type) ctx->kfc.magic = CGROUP2_SUPER_MAGIC; else ctx->kfc.magic = CGROUP_SUPER_MAGIC; ret = kernfs_get_tree(fc); /* * In non-init cgroup namespace, instead of root cgroup's dentry, * we return the dentry corresponding to the cgroupns->root_cgrp. */ if (!ret && ctx->ns != &init_cgroup_ns) { struct dentry *nsdentry; struct super_block *sb = fc->root->d_sb; struct cgroup *cgrp; mutex_lock(&cgroup_mutex); spin_lock_irq(&css_set_lock); cgrp = cset_cgroup_from_root(ctx->ns->root_cset, ctx->root); spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); nsdentry = kernfs_node_dentry(cgrp->kn, sb); dput(fc->root); if (IS_ERR(nsdentry)) { deactivate_locked_super(sb); ret = PTR_ERR(nsdentry); nsdentry = NULL; } fc->root = nsdentry; } if (!ctx->kfc.new_sb_created) cgroup_put(&ctx->root->cgrp); return ret; } /* * Destroy a cgroup filesystem context. */ static void cgroup_fs_context_free(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); kfree(ctx->name); kfree(ctx->release_agent); put_cgroup_ns(ctx->ns); kernfs_free_fs_context(fc); kfree(ctx); } static int cgroup_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; WRITE_ONCE(cgrp_dfl_visible, true); cgroup_get_live(&cgrp_dfl_root.cgrp); ctx->root = &cgrp_dfl_root; ret = cgroup_do_get_tree(fc); if (!ret) apply_cgroup_root_flags(ctx->flags); return ret; } static const struct fs_context_operations cgroup_fs_context_ops = { .free = cgroup_fs_context_free, .parse_param = cgroup2_parse_param, .get_tree = cgroup_get_tree, .reconfigure = cgroup_reconfigure, }; static const struct fs_context_operations cgroup1_fs_context_ops = { .free = cgroup_fs_context_free, .parse_param = cgroup1_parse_param, .get_tree = cgroup1_get_tree, .reconfigure = cgroup1_reconfigure, }; /* * Initialise the cgroup filesystem creation/reconfiguration context. Notably, * we select the namespace we're going to use. */ static int cgroup_init_fs_context(struct fs_context *fc) { struct cgroup_fs_context *ctx; ctx = kzalloc(sizeof(struct cgroup_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->ns = current->nsproxy->cgroup_ns; get_cgroup_ns(ctx->ns); fc->fs_private = &ctx->kfc; if (fc->fs_type == &cgroup2_fs_type) fc->ops = &cgroup_fs_context_ops; else fc->ops = &cgroup1_fs_context_ops; put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->ns->user_ns); fc->global = true; #ifdef CONFIG_CGROUP_FAVOR_DYNMODS ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; #endif return 0; } static void cgroup_kill_sb(struct super_block *sb) { struct kernfs_root *kf_root = kernfs_root_from_sb(sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root); /* * If @root doesn't have any children, start killing it. * This prevents new mounts by disabling percpu_ref_tryget_live(). * * And don't kill the default root. */ if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root && !percpu_ref_is_dying(&root->cgrp.self.refcnt)) { cgroup_bpf_offline(&root->cgrp); percpu_ref_kill(&root->cgrp.self.refcnt); } cgroup_put(&root->cgrp); kernfs_kill_sb(sb); } struct file_system_type cgroup_fs_type = { .name = "cgroup", .init_fs_context = cgroup_init_fs_context, .parameters = cgroup1_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; static struct file_system_type cgroup2_fs_type = { .name = "cgroup2", .init_fs_context = cgroup_init_fs_context, .parameters = cgroup2_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; #ifdef CONFIG_CPUSETS static const struct fs_context_operations cpuset_fs_context_ops = { .get_tree = cgroup1_get_tree, .free = cgroup_fs_context_free, }; /* * This is ugly, but preserves the userspace API for existing cpuset * users. If someone tries to mount the "cpuset" filesystem, we * silently switch it to mount "cgroup" instead */ static int cpuset_init_fs_context(struct fs_context *fc) { char *agent = kstrdup("/sbin/cpuset_release_agent", GFP_USER); struct cgroup_fs_context *ctx; int err; err = cgroup_init_fs_context(fc); if (err) { kfree(agent); return err; } fc->ops = &cpuset_fs_context_ops; ctx = cgroup_fc2context(fc); ctx->subsys_mask = 1 << cpuset_cgrp_id; ctx->flags |= CGRP_ROOT_NOPREFIX; ctx->release_agent = agent; get_filesystem(&cgroup_fs_type); put_filesystem(fc->fs_type); fc->fs_type = &cgroup_fs_type; return 0; } static struct file_system_type cpuset_fs_type = { .name = "cpuset", .init_fs_context = cpuset_init_fs_context, .fs_flags = FS_USERNS_MOUNT, }; #endif int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root); return kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen); } int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { int ret; mutex_lock(&cgroup_mutex); spin_lock_irq(&css_set_lock); ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns); spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); return ret; } EXPORT_SYMBOL_GPL(cgroup_path_ns); /** * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy * @task: target task * @buf: the buffer to write the path into * @buflen: the length of the buffer * * Determine @task's cgroup on the first (the one with the lowest non-zero * hierarchy_id) cgroup hierarchy and copy its path into @buf. This * function grabs cgroup_mutex and shouldn't be used inside locks used by * cgroup controller callbacks. * * Return value is the same as kernfs_path(). */ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) { struct cgroup_root *root; struct cgroup *cgrp; int hierarchy_id = 1; int ret; mutex_lock(&cgroup_mutex); spin_lock_irq(&css_set_lock); root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id); if (root) { cgrp = task_cgroup_from_root(task, root); ret = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns); } else { /* if no hierarchy exists, everyone is in "/" */ ret = strscpy(buf, "/", buflen); } spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); return ret; } EXPORT_SYMBOL_GPL(task_cgroup_path); /** * cgroup_attach_lock - Lock for ->attach() * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem * * cgroup migration sometimes needs to stabilize threadgroups against forks and * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach() * implementations (e.g. cpuset), also need to disable CPU hotplug. * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can * lead to deadlocks. * * Bringing up a CPU may involve creating and destroying tasks which requires * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while * write-locking threadgroup_rwsem, the locking order is reversed and we end up * waiting for an on-going CPU hotplug operation which in turn is waiting for * the threadgroup_rwsem to be released to create new tasks. For more details: * * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu * * Resolve the situation by always acquiring cpus_read_lock() before optionally * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that * CPU hotplug is disabled on entry. */ void cgroup_attach_lock(bool lock_threadgroup) { cpus_read_lock(); if (lock_threadgroup) percpu_down_write(&cgroup_threadgroup_rwsem); } /** * cgroup_attach_unlock - Undo cgroup_attach_lock() * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem */ void cgroup_attach_unlock(bool lock_threadgroup) { if (lock_threadgroup) percpu_up_write(&cgroup_threadgroup_rwsem); cpus_read_unlock(); } /** * cgroup_migrate_add_task - add a migration target task to a migration context * @task: target task * @mgctx: target migration context * * Add @task, which is a migration target, to @mgctx->tset. This function * becomes noop if @task doesn't need to be migrated. @task's css_set * should have been added as a migration source and @task->cg_list will be * moved from the css_set's tasks list to mg_tasks one. */ static void cgroup_migrate_add_task(struct task_struct *task, struct cgroup_mgctx *mgctx) { struct css_set *cset; lockdep_assert_held(&css_set_lock); /* @task either already exited or can't exit until the end */ if (task->flags & PF_EXITING) return; /* cgroup_threadgroup_rwsem protects racing against forks */ WARN_ON_ONCE(list_empty(&task->cg_list)); cset = task_css_set(task); if (!cset->mg_src_cgrp) return; mgctx->tset.nr_tasks++; list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) list_add_tail(&cset->mg_node, &mgctx->tset.src_csets); if (list_empty(&cset->mg_dst_cset->mg_node)) list_add_tail(&cset->mg_dst_cset->mg_node, &mgctx->tset.dst_csets); } /** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * @tset iteration is initialized and the first task is returned. */ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp) { tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); tset->cur_task = NULL; return cgroup_taskset_next(tset, dst_cssp); } /** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * Return the next task in @tset. Iteration must have been initialized * with cgroup_taskset_first(). */ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp) { struct css_set *cset = tset->cur_cset; struct task_struct *task = tset->cur_task; while (CGROUP_HAS_SUBSYS_CONFIG && &cset->mg_node != tset->csets) { if (!task) task = list_first_entry(&cset->mg_tasks, struct task_struct, cg_list); else task = list_next_entry(task, cg_list); if (&task->cg_list != &cset->mg_tasks) { tset->cur_cset = cset; tset->cur_task = task; /* * This function may be called both before and * after cgroup_taskset_migrate(). The two cases * can be distinguished by looking at whether @cset * has its ->mg_dst_cset set. */ if (cset->mg_dst_cset) *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid]; else *dst_cssp = cset->subsys[tset->ssid]; return task; } cset = list_next_entry(cset, mg_node); task = NULL; } return NULL; } /** * cgroup_migrate_execute - migrate a taskset * @mgctx: migration context * * Migrate tasks in @mgctx as setup by migration preparation functions. * This function fails iff one of the ->can_attach callbacks fails and * guarantees that either all or none of the tasks in @mgctx are migrated. * @mgctx is consumed regardless of success. */ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx) { struct cgroup_taskset *tset = &mgctx->tset; struct cgroup_subsys *ss; struct task_struct *task, *tmp_task; struct css_set *cset, *tmp_cset; int ssid, failed_ssid, ret; /* check that we can legitimately attach to the cgroup */ if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->can_attach) { tset->ssid = ssid; ret = ss->can_attach(tset); if (ret) { failed_ssid = ssid; goto out_cancel_attach; } } } while_each_subsys_mask(); } /* * Now that we're guaranteed success, proceed to move all tasks to * the new cgroup. There are no failure cases after here, so this * is the commit point. */ spin_lock_irq(&css_set_lock); list_for_each_entry(cset, &tset->src_csets, mg_node) { list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) { struct css_set *from_cset = task_css_set(task); struct css_set *to_cset = cset->mg_dst_cset; get_css_set(to_cset); to_cset->nr_tasks++; css_set_move_task(task, from_cset, to_cset, true); from_cset->nr_tasks--; /* * If the source or destination cgroup is frozen, * the task might require to change its state. */ cgroup_freezer_migrate_task(task, from_cset->dfl_cgrp, to_cset->dfl_cgrp); put_css_set_locked(from_cset); } } spin_unlock_irq(&css_set_lock); /* * Migration is committed, all target tasks are now on dst_csets. * Nothing is sensitive to fork() after this point. Notify * controllers that migration is complete. */ tset->csets = &tset->dst_csets; if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->attach) { tset->ssid = ssid; ss->attach(tset); } } while_each_subsys_mask(); } ret = 0; goto out_release_tset; out_cancel_attach: if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ssid == failed_ssid) break; if (ss->cancel_attach) { tset->ssid = ssid; ss->cancel_attach(tset); } } while_each_subsys_mask(); } out_release_tset: spin_lock_irq(&css_set_lock); list_splice_init(&tset->dst_csets, &tset->src_csets); list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) { list_splice_tail_init(&cset->mg_tasks, &cset->tasks); list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock); /* * Re-initialize the cgroup_taskset structure in case it is reused * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() * iteration. */ tset->nr_tasks = 0; tset->csets = &tset->src_csets; return ret; } /** * cgroup_migrate_vet_dst - verify whether a cgroup can be migration destination * @dst_cgrp: destination cgroup to test * * On the default hierarchy, except for the mixable, (possible) thread root * and threaded cgroups, subtree_control must be zero for migration * destination cgroups with tasks so that child cgroups don't compete * against tasks. */ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp) { /* v1 doesn't have any restriction */ if (!cgroup_on_dfl(dst_cgrp)) return 0; /* verify @dst_cgrp can host resources */ if (!cgroup_is_valid_domain(dst_cgrp->dom_cgrp)) return -EOPNOTSUPP; /* * If @dst_cgrp is already or can become a thread root or is * threaded, it doesn't matter. */ if (cgroup_can_be_thread_root(dst_cgrp) || cgroup_is_threaded(dst_cgrp)) return 0; /* apply no-internal-process constraint */ if (dst_cgrp->subtree_control) return -EBUSY; return 0; } /** * cgroup_migrate_finish - cleanup after attach * @mgctx: migration context * * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See * those functions for details. */ void cgroup_migrate_finish(struct cgroup_mgctx *mgctx) { struct css_set *cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets, mg_src_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_src_preload_node); put_css_set_locked(cset); } list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets, mg_dst_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_dst_preload_node); put_css_set_locked(cset); } spin_unlock_irq(&css_set_lock); } /** * cgroup_migrate_add_src - add a migration source css_set * @src_cset: the source css_set to add * @dst_cgrp: the destination cgroup * @mgctx: migration context * * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin * @src_cset and add it to @mgctx->src_csets, which should later be cleaned * up by cgroup_migrate_finish(). * * This function may be called without holding cgroup_threadgroup_rwsem * even if the target is a process. Threads may be created and destroyed * but as long as cgroup_mutex is not dropped, no new css_set can be put * into play and the preloaded css_sets are guaranteed to cover all * migrations. */ void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, struct cgroup_mgctx *mgctx) { struct cgroup *src_cgrp; lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); /* * If ->dead, @src_set is associated with one or more dead cgroups * and doesn't contain any migratable tasks. Ignore it early so * that the rest of migration path doesn't get confused by it. */ if (src_cset->dead) return; if (!list_empty(&src_cset->mg_src_preload_node)) return; src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); WARN_ON(src_cset->mg_src_cgrp); WARN_ON(src_cset->mg_dst_cgrp); WARN_ON(!list_empty(&src_cset->mg_tasks)); WARN_ON(!list_empty(&src_cset->mg_node)); src_cset->mg_src_cgrp = src_cgrp; src_cset->mg_dst_cgrp = dst_cgrp; get_css_set(src_cset); list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets); } /** * cgroup_migrate_prepare_dst - prepare destination css_sets for migration * @mgctx: migration context * * Tasks are about to be moved and all the source css_sets have been * preloaded to @mgctx->preloaded_src_csets. This function looks up and * pins all destination css_sets, links each to its source, and append them * to @mgctx->preloaded_dst_csets. * * This function must be called after cgroup_migrate_add_src() has been * called on each migration source css_set. After migration is performed * using cgroup_migrate(), cgroup_migrate_finish() must be called on * @mgctx. */ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) { struct css_set *src_cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); /* look up the dst cset for each src cset and link it to src */ list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets, mg_src_preload_node) { struct css_set *dst_cset; struct cgroup_subsys *ss; int ssid; dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp); if (!dst_cset) return -ENOMEM; WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset); /* * If src cset equals dst, it's noop. Drop the src. * cgroup_migrate() will skip the cset too. Note that we * can't handle src == dst as some nodes are used by both. */ if (src_cset == dst_cset) { src_cset->mg_src_cgrp = NULL; src_cset->mg_dst_cgrp = NULL; list_del_init(&src_cset->mg_src_preload_node); put_css_set(src_cset); put_css_set(dst_cset); continue; } src_cset->mg_dst_cset = dst_cset; if (list_empty(&dst_cset->mg_dst_preload_node)) list_add_tail(&dst_cset->mg_dst_preload_node, &mgctx->preloaded_dst_csets); else put_css_set(dst_cset); for_each_subsys(ss, ssid) if (src_cset->subsys[ssid] != dst_cset->subsys[ssid]) mgctx->ss_mask |= 1 << ssid; } return 0; } /** * cgroup_migrate - migrate a process or task to a cgroup * @leader: the leader of the process or the task to migrate * @threadgroup: whether @leader points to the whole process or a single task * @mgctx: migration context * * Migrate a process or task denoted by @leader. If migrating a process, * the caller must be holding cgroup_threadgroup_rwsem. The caller is also * responsible for invoking cgroup_migrate_add_src() and * cgroup_migrate_prepare_dst() on the targets before invoking this * function and following up with cgroup_migrate_finish(). * * As long as a controller's ->can_attach() doesn't fail, this function is * guaranteed to succeed. This means that, excluding ->can_attach() * failure, when migrating multiple targets, the success or failure can be * decided for all targets by invoking group_migrate_prepare_dst() before * actually starting migrating. */ int cgroup_migrate(struct task_struct *leader, bool threadgroup, struct cgroup_mgctx *mgctx) { struct task_struct *task; /* * Prevent freeing of tasks while we take a snapshot. Tasks that are * already PF_EXITING could be freed from underneath us unless we * take an rcu_read_lock. */ spin_lock_irq(&css_set_lock); rcu_read_lock(); task = leader; do { cgroup_migrate_add_task(task, mgctx); if (!threadgroup) break; } while_each_thread(leader, task); rcu_read_unlock(); spin_unlock_irq(&css_set_lock); return cgroup_migrate_execute(mgctx); } /** * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup * @dst_cgrp: the cgroup to attach to * @leader: the task or the leader of the threadgroup to be attached * @threadgroup: attach the whole threadgroup? * * Call holding cgroup_mutex and cgroup_threadgroup_rwsem. */ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup) { DEFINE_CGROUP_MGCTX(mgctx); struct task_struct *task; int ret = 0; /* look up all src csets */ spin_lock_irq(&css_set_lock); rcu_read_lock(); task = leader; do { cgroup_migrate_add_src(task_css_set(task), dst_cgrp, &mgctx); if (!threadgroup) break; } while_each_thread(leader, task); rcu_read_unlock(); spin_unlock_irq(&css_set_lock); /* prepare dst csets and commit */ ret = cgroup_migrate_prepare_dst(&mgctx); if (!ret) ret = cgroup_migrate(leader, threadgroup, &mgctx); cgroup_migrate_finish(&mgctx); if (!ret) TRACE_CGROUP_PATH(attach_task, dst_cgrp, leader, threadgroup); return ret; } struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, bool *threadgroup_locked) { struct task_struct *tsk; pid_t pid; if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return ERR_PTR(-EINVAL); /* * If we migrate a single thread, we don't care about threadgroup * stability. If the thread is `current`, it won't exit(2) under our * hands or change PID through exec(2). We exclude * cgroup_update_dfl_csses and other cgroup_{proc,thread}s_write * callers by cgroup_mutex. * Therefore, we can skip the global lock. */ lockdep_assert_held(&cgroup_mutex); *threadgroup_locked = pid || threadgroup; cgroup_attach_lock(*threadgroup_locked); rcu_read_lock(); if (pid) { tsk = find_task_by_vpid(pid); if (!tsk) { tsk = ERR_PTR(-ESRCH); goto out_unlock_threadgroup; } } else { tsk = current; } if (threadgroup) tsk = tsk->group_leader; /* * kthreads may acquire PF_NO_SETAFFINITY during initialization. * If userland migrates such a kthread to a non-root cgroup, it can * become trapped in a cpuset, or RT kthread may be born in a * cgroup with no rt_runtime allocated. Just say no. */ if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) { tsk = ERR_PTR(-EINVAL); goto out_unlock_threadgroup; } get_task_struct(tsk); goto out_unlock_rcu; out_unlock_threadgroup: cgroup_attach_unlock(*threadgroup_locked); *threadgroup_locked = false; out_unlock_rcu: rcu_read_unlock(); return tsk; } void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked) { struct cgroup_subsys *ss; int ssid; /* release reference from cgroup_procs_write_start() */ put_task_struct(task); cgroup_attach_unlock(threadgroup_locked); for_each_subsys(ss, ssid) if (ss->post_attach) ss->post_attach(); } static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask) { struct cgroup_subsys *ss; bool printed = false; int ssid; do_each_subsys_mask(ss, ssid, ss_mask) { if (printed) seq_putc(seq, ' '); seq_puts(seq, ss->name); printed = true; } while_each_subsys_mask(); if (printed) seq_putc(seq, '\n'); } /* show controllers which are enabled from the parent */ static int cgroup_controllers_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; cgroup_print_ss_mask(seq, cgroup_control(cgrp)); return 0; } /* show controllers which are enabled for a given cgroup's children */ static int cgroup_subtree_control_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; cgroup_print_ss_mask(seq, cgrp->subtree_control); return 0; } /** * cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy * @cgrp: root of the subtree to update csses for * * @cgrp's control masks have changed and its subtree's css associations * need to be updated accordingly. This function looks up all css_sets * which are attached to the subtree, creates the matching updated css_sets * and migrates the tasks to the new ones. */ static int cgroup_update_dfl_csses(struct cgroup *cgrp) { DEFINE_CGROUP_MGCTX(mgctx); struct cgroup_subsys_state *d_css; struct cgroup *dsct; struct css_set *src_cset; bool has_tasks; int ret; lockdep_assert_held(&cgroup_mutex); /* look up all csses currently attached to @cgrp's subtree */ spin_lock_irq(&css_set_lock); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { struct cgrp_cset_link *link; /* * As cgroup_update_dfl_csses() is only called by * cgroup_apply_control(). The csses associated with the * given cgrp will not be affected by changes made to * its subtree_control file. We can skip them. */ if (dsct == cgrp) continue; list_for_each_entry(link, &dsct->cset_links, cset_link) cgroup_migrate_add_src(link->cset, dsct, &mgctx); } spin_unlock_irq(&css_set_lock); /* * We need to write-lock threadgroup_rwsem while migrating tasks. * However, if there are no source csets for @cgrp, changing its * controllers isn't gonna produce any task migrations and the * write-locking can be skipped safely. */ has_tasks = !list_empty(&mgctx.preloaded_src_csets); cgroup_attach_lock(has_tasks); /* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&mgctx); if (ret) goto out_finish; spin_lock_irq(&css_set_lock); list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_src_preload_node) { struct task_struct *task, *ntask; /* all tasks in src_csets need to be migrated */ list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list) cgroup_migrate_add_task(task, &mgctx); } spin_unlock_irq(&css_set_lock); ret = cgroup_migrate_execute(&mgctx); out_finish: cgroup_migrate_finish(&mgctx); cgroup_attach_unlock(has_tasks); return ret; } /** * cgroup_lock_and_drain_offline - lock cgroup_mutex and drain offlined csses * @cgrp: root of the target subtree * * Because css offlining is asynchronous, userland may try to re-enable a * controller while the previous css is still around. This function grabs * cgroup_mutex and drains the previous css instances of @cgrp's subtree. */ void cgroup_lock_and_drain_offline(struct cgroup *cgrp) __acquires(&cgroup_mutex) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; restart: mutex_lock(&cgroup_mutex); cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); DEFINE_WAIT(wait); if (!css || !percpu_ref_is_dying(&css->refcnt)) continue; cgroup_get_live(dsct); prepare_to_wait(&dsct->offline_waitq, &wait, TASK_UNINTERRUPTIBLE); mutex_unlock(&cgroup_mutex); schedule(); finish_wait(&dsct->offline_waitq, &wait); cgroup_put(dsct); goto restart; } } } /** * cgroup_save_control - save control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Save ->subtree_control, ->subtree_ss_mask and ->dom_cgrp to the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */ static void cgroup_save_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->old_subtree_control = dsct->subtree_control; dsct->old_subtree_ss_mask = dsct->subtree_ss_mask; dsct->old_dom_cgrp = dsct->dom_cgrp; } } /** * cgroup_propagate_control - refresh control masks of a subtree * @cgrp: root of the target subtree * * For @cgrp and its subtree, ensure ->subtree_ss_mask matches * ->subtree_control and propagate controller availability through the * subtree so that descendants don't have unavailable controllers enabled. */ static void cgroup_propagate_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->subtree_control &= cgroup_control(dsct); dsct->subtree_ss_mask = cgroup_calc_subtree_ss_mask(dsct->subtree_control, cgroup_ss_mask(dsct)); } } /** * cgroup_restore_control - restore control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Restore ->subtree_control, ->subtree_ss_mask and ->dom_cgrp from the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */ static void cgroup_restore_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { dsct->subtree_control = dsct->old_subtree_control; dsct->subtree_ss_mask = dsct->old_subtree_ss_mask; dsct->dom_cgrp = dsct->old_dom_cgrp; } } static bool css_visible(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; if (cgroup_control(cgrp) & (1 << ss->id)) return true; if (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) return false; return cgroup_on_dfl(cgrp) && ss->implicit_on_dfl; } /** * cgroup_apply_control_enable - enable or show csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and create new csses or make the existing ones * visible. A css is created invisible if it's being implicitly enabled * through dependency. An invisible css is made visible when the userland * explicitly enables it. * * Returns 0 on success, -errno on failure. On failure, csses which have * been processed already aren't cleaned up. The caller is responsible for * cleaning up with cgroup_apply_control_disable(). */ static int cgroup_apply_control_enable(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid, ret; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) continue; if (!css) { css = css_create(dsct, ss); if (IS_ERR(css)) return PTR_ERR(css); } WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); if (css_visible(css)) { ret = css_populate_dir(css); if (ret) return ret; } } } return 0; } /** * cgroup_apply_control_disable - kill or hide csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and kill and hide csses so that they match * cgroup_ss_mask() and cgroup_visible_mask(). * * A css is hidden when the userland requests it to be disabled while other * subsystems are still depending on it. The css must not actively control * resources and be in the vanilla state if it's made visible again later. * Controllers which may be depended upon should provide ->css_reset() for * this purpose. */ static void cgroup_apply_control_disable(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); if (!css) continue; WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); if (css->parent && !(cgroup_ss_mask(dsct) & (1 << ss->id))) { kill_css(css); } else if (!css_visible(css)) { css_clear_dir(css); if (ss->css_reset) ss->css_reset(css); } } } } /** * cgroup_apply_control - apply control mask updates to the subtree * @cgrp: root of the target subtree * * subsystems can be enabled and disabled in a subtree using the following * steps. * * 1. Call cgroup_save_control() to stash the current state. * 2. Update ->subtree_control masks in the subtree as desired. * 3. Call cgroup_apply_control() to apply the changes. * 4. Optionally perform other related operations. * 5. Call cgroup_finalize_control() to finish up. * * This function implements step 3 and propagates the mask changes * throughout @cgrp's subtree, updates csses accordingly and perform * process migrations. */ static int cgroup_apply_control(struct cgroup *cgrp) { int ret; cgroup_propagate_control(cgrp); ret = cgroup_apply_control_enable(cgrp); if (ret) return ret; /* * At this point, cgroup_e_css_by_mask() results reflect the new csses * making the following cgroup_update_dfl_csses() properly update * css associations of all tasks in the subtree. */ return cgroup_update_dfl_csses(cgrp); } /** * cgroup_finalize_control - finalize control mask update * @cgrp: root of the target subtree * @ret: the result of the update * * Finalize control mask update. See cgroup_apply_control() for more info. */ static void cgroup_finalize_control(struct cgroup *cgrp, int ret) { if (ret) { cgroup_restore_control(cgrp); cgroup_propagate_control(cgrp); } cgroup_apply_control_disable(cgrp); } static int cgroup_vet_subtree_control_enable(struct cgroup *cgrp, u16 enable) { u16 domain_enable = enable & ~cgrp_dfl_threaded_ss_mask; /* if nothing is getting enabled, nothing to worry about */ if (!enable) return 0; /* can @cgrp host any resources? */ if (!cgroup_is_valid_domain(cgrp->dom_cgrp)) return -EOPNOTSUPP; /* mixables don't care */ if (cgroup_is_mixable(cgrp)) return 0; if (domain_enable) { /* can't enable domain controllers inside a thread subtree */ if (cgroup_is_thread_root(cgrp) || cgroup_is_threaded(cgrp)) return -EOPNOTSUPP; } else { /* * Threaded controllers can handle internal competitions * and are always allowed inside a (prospective) thread * subtree. */ if (cgroup_can_be_thread_root(cgrp) || cgroup_is_threaded(cgrp)) return 0; } /* * Controllers can't be enabled for a cgroup with tasks to avoid * child cgroups competing against tasks. */ if (cgroup_has_tasks(cgrp)) return -EBUSY; return 0; } /* change the enabled child controllers for a cgroup in the default hierarchy */ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { u16 enable = 0, disable = 0; struct cgroup *cgrp, *child; struct cgroup_subsys *ss; char *tok; int ssid, ret; /* * Parse input - space separated list of subsystem names prefixed * with either + or -. */ buf = strstrip(buf); while ((tok = strsep(&buf, " "))) { if (tok[0] == '\0') continue; do_each_subsys_mask(ss, ssid, ~cgrp_dfl_inhibit_ss_mask) { if (!cgroup_ssid_enabled(ssid) || strcmp(tok + 1, ss->name)) continue; if (*tok == '+') { enable |= 1 << ssid; disable &= ~(1 << ssid); } else if (*tok == '-') { disable |= 1 << ssid; enable &= ~(1 << ssid); } else { return -EINVAL; } break; } while_each_subsys_mask(); if (ssid == CGROUP_SUBSYS_COUNT) return -EINVAL; } cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENODEV; for_each_subsys(ss, ssid) { if (enable & (1 << ssid)) { if (cgrp->subtree_control & (1 << ssid)) { enable &= ~(1 << ssid); continue; } if (!(cgroup_control(cgrp) & (1 << ssid))) { ret = -ENOENT; goto out_unlock; } } else if (disable & (1 << ssid)) { if (!(cgrp->subtree_control & (1 << ssid))) { disable &= ~(1 << ssid); continue; } /* a child has it enabled? */ cgroup_for_each_live_child(child, cgrp) { if (child->subtree_control & (1 << ssid)) { ret = -EBUSY; goto out_unlock; } } } } if (!enable && !disable) { ret = 0; goto out_unlock; } ret = cgroup_vet_subtree_control_enable(cgrp, enable); if (ret) goto out_unlock; /* save and update control masks and prepare csses */ cgroup_save_control(cgrp); cgrp->subtree_control |= enable; cgrp->subtree_control &= ~disable; ret = cgroup_apply_control(cgrp); cgroup_finalize_control(cgrp, ret); if (ret) goto out_unlock; kernfs_activate(cgrp->kn); out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; } /** * cgroup_enable_threaded - make @cgrp threaded * @cgrp: the target cgroup * * Called when "threaded" is written to the cgroup.type interface file and * tries to make @cgrp threaded and join the parent's resource domain. * This function is never called on the root cgroup as cgroup.type doesn't * exist on it. */ static int cgroup_enable_threaded(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup *dom_cgrp = parent->dom_cgrp; struct cgroup *dsct; struct cgroup_subsys_state *d_css; int ret; lockdep_assert_held(&cgroup_mutex); /* noop if already threaded */ if (cgroup_is_threaded(cgrp)) return 0; /* * If @cgroup is populated or has domain controllers enabled, it * can't be switched. While the below cgroup_can_be_thread_root() * test can catch the same conditions, that's only when @parent is * not mixable, so let's check it explicitly. */ if (cgroup_is_populated(cgrp) || cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) return -EOPNOTSUPP; /* we're joining the parent's domain, ensure its validity */ if (!cgroup_is_valid_domain(dom_cgrp) || !cgroup_can_be_thread_root(dom_cgrp)) return -EOPNOTSUPP; /* * The following shouldn't cause actual migrations and should * always succeed. */ cgroup_save_control(cgrp); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) if (dsct == cgrp || cgroup_is_threaded(dsct)) dsct->dom_cgrp = dom_cgrp; ret = cgroup_apply_control(cgrp); if (!ret) parent->nr_threaded_children++; cgroup_finalize_control(cgrp, ret); return ret; } static int cgroup_type_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; if (cgroup_is_threaded(cgrp)) seq_puts(seq, "threaded\n"); else if (!cgroup_is_valid_domain(cgrp)) seq_puts(seq, "domain invalid\n"); else if (cgroup_is_thread_root(cgrp)) seq_puts(seq, "domain threaded\n"); else seq_puts(seq, "domain\n"); return 0; } static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; int ret; /* only switching to threaded mode is supported */ if (strcmp(strstrip(buf), "threaded")) return -EINVAL; /* drain dying csses before we re-apply (threaded) subtree control */ cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENOENT; /* threaded can only be enabled */ ret = cgroup_enable_threaded(cgrp); cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static int cgroup_max_descendants_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; int descendants = READ_ONCE(cgrp->max_descendants); if (descendants == INT_MAX) seq_puts(seq, "max\n"); else seq_printf(seq, "%d\n", descendants); return 0; } static ssize_t cgroup_max_descendants_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; int descendants; ssize_t ret; buf = strstrip(buf); if (!strcmp(buf, "max")) { descendants = INT_MAX; } else { ret = kstrtoint(buf, 0, &descendants); if (ret) return ret; } if (descendants < 0) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgrp->max_descendants = descendants; cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_max_depth_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; int depth = READ_ONCE(cgrp->max_depth); if (depth == INT_MAX) seq_puts(seq, "max\n"); else seq_printf(seq, "%d\n", depth); return 0; } static ssize_t cgroup_max_depth_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; ssize_t ret; int depth; buf = strstrip(buf); if (!strcmp(buf, "max")) { depth = INT_MAX; } else { ret = kstrtoint(buf, 0, &depth); if (ret) return ret; } if (depth < 0) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgrp->max_depth = depth; cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_events_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; seq_printf(seq, "populated %d\n", cgroup_is_populated(cgrp)); seq_printf(seq, "frozen %d\n", test_bit(CGRP_FROZEN, &cgrp->flags)); return 0; } static int cgroup_stat_show(struct seq_file *seq, void *v) { struct cgroup *cgroup = seq_css(seq)->cgroup; seq_printf(seq, "nr_descendants %d\n", cgroup->nr_descendants); seq_printf(seq, "nr_dying_descendants %d\n", cgroup->nr_dying_descendants); return 0; } static int __maybe_unused cgroup_extra_stat_show(struct seq_file *seq, struct cgroup *cgrp, int ssid) { struct cgroup_subsys *ss = cgroup_subsys[ssid]; struct cgroup_subsys_state *css; int ret; if (!ss->css_extra_stat_show) return 0; css = cgroup_tryget_css(cgrp, ss); if (!css) return 0; ret = ss->css_extra_stat_show(seq, css); css_put(css); return ret; } static int cpu_stat_show(struct seq_file *seq, void *v) { struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup; int ret = 0; cgroup_base_stat_cputime_show(seq); #ifdef CONFIG_CGROUP_SCHED ret = cgroup_extra_stat_show(seq, cgrp, cpu_cgrp_id); #endif return ret; } #ifdef CONFIG_PSI static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IO); } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_MEM); } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_CPU); } static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, enum psi_res res) { struct cgroup_file_ctx *ctx = of->priv; struct psi_trigger *new; struct cgroup *cgrp; struct psi_group *psi; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; cgroup_get(cgrp); cgroup_kn_unlock(of->kn); /* Allow only one trigger per file descriptor */ if (ctx->psi.trigger) { cgroup_put(cgrp); return -EBUSY; } psi = cgroup_psi(cgrp); new = psi_trigger_create(psi, buf, res); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); } smp_store_release(&ctx->psi.trigger, new); cgroup_put(cgrp); return nbytes; } static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_IO); } static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_MEM); } static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_CPU); } #ifdef CONFIG_IRQ_TIME_ACCOUNTING static int cgroup_irq_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IRQ); } static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_IRQ); } #endif static int cgroup_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); seq_printf(seq, "%d\n", psi->enabled); return 0; } static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { ssize_t ret; int enable; struct cgroup *cgrp; struct psi_group *psi; ret = kstrtoint(strstrip(buf), 0, &enable); if (ret) return ret; if (enable < 0 || enable > 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; psi = cgroup_psi(cgrp); if (psi->enabled != enable) { int i; /* show or hide {cpu,memory,io,irq}.pressure files */ for (i = 0; i < NR_PSI_RESOURCES; i++) cgroup_file_show(&cgrp->psi_files[i], enable); psi->enabled = enable; if (enable) psi_cgroup_restart(psi); } cgroup_kn_unlock(of->kn); return nbytes; } static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, poll_table *pt) { struct cgroup_file_ctx *ctx = of->priv; return psi_trigger_poll(&ctx->psi.trigger, of->file, pt); } static void cgroup_pressure_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; psi_trigger_destroy(ctx->psi.trigger); } bool cgroup_psi_enabled(void) { if (static_branch_likely(&psi_disabled)) return false; return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0; } #else /* CONFIG_PSI */ bool cgroup_psi_enabled(void) { return false; } #endif /* CONFIG_PSI */ static int cgroup_freeze_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; seq_printf(seq, "%d\n", cgrp->freezer.freeze); return 0; } static ssize_t cgroup_freeze_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; ssize_t ret; int freeze; ret = kstrtoint(strstrip(buf), 0, &freeze); if (ret) return ret; if (freeze < 0 || freeze > 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgroup_freeze(cgrp, freeze); cgroup_kn_unlock(of->kn); return nbytes; } static void __cgroup_kill(struct cgroup *cgrp) { struct css_task_iter it; struct task_struct *task; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); set_bit(CGRP_KILL, &cgrp->flags); spin_unlock_irq(&css_set_lock); css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it); while ((task = css_task_iter_next(&it))) { /* Ignore kernel threads here. */ if (task->flags & PF_KTHREAD) continue; /* Skip tasks that are already dying. */ if (__fatal_signal_pending(task)) continue; send_sig(SIGKILL, task, 0); } css_task_iter_end(&it); spin_lock_irq(&css_set_lock); clear_bit(CGRP_KILL, &cgrp->flags); spin_unlock_irq(&css_set_lock); } static void cgroup_kill(struct cgroup *cgrp) { struct cgroup_subsys_state *css; struct cgroup *dsct; lockdep_assert_held(&cgroup_mutex); cgroup_for_each_live_descendant_pre(dsct, css, cgrp) __cgroup_kill(dsct); } static ssize_t cgroup_kill_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { ssize_t ret = 0; int kill; struct cgroup *cgrp; ret = kstrtoint(strstrip(buf), 0, &kill); if (ret) return ret; if (kill != 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; /* * Killing is a process directed operation, i.e. the whole thread-group * is taken down so act like we do for cgroup.procs and only make this * writable in non-threaded cgroups. */ if (cgroup_is_threaded(cgrp)) ret = -EOPNOTSUPP; else cgroup_kill(cgrp); cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); struct cgroup_file_ctx *ctx; int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->ns = current->nsproxy->cgroup_ns; get_cgroup_ns(ctx->ns); of->priv = ctx; if (!cft->open) return 0; ret = cft->open(of); if (ret) { put_cgroup_ns(ctx->ns); kfree(ctx); } return ret; } static void cgroup_file_release(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); struct cgroup_file_ctx *ctx = of->priv; if (cft->release) cft->release(of); put_cgroup_ns(ctx->ns); kfree(ctx); } static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = of->kn->parent->priv; struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; int ret; if (!nbytes) return 0; /* * If namespaces are delegation boundaries, disallow writes to * files in an non-init namespace root from inside the namespace * except for the files explicitly marked delegatable - * cgroup.procs and cgroup.subtree_control. */ if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) && !(cft->flags & CFTYPE_NS_DELEGATABLE) && ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp) return -EPERM; if (cft->write) return cft->write(of, buf, nbytes, off); /* * kernfs guarantees that a file isn't deleted with operations in * flight, which means that the matching css is and stays alive and * doesn't need to be pinned. The RCU locking is not necessary * either. It's just for the convenience of using cgroup_css(). */ rcu_read_lock(); css = cgroup_css(cgrp, cft->ss); rcu_read_unlock(); if (cft->write_u64) { unsigned long long v; ret = kstrtoull(buf, 0, &v); if (!ret) ret = cft->write_u64(css, cft, v); } else if (cft->write_s64) { long long v; ret = kstrtoll(buf, 0, &v); if (!ret) ret = cft->write_s64(css, cft, v); } else { ret = -EINVAL; } return ret ?: nbytes; } static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt) { struct cftype *cft = of_cft(of); if (cft->poll) return cft->poll(of, pt); return kernfs_generic_poll(of, pt); } static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) { return seq_cft(seq)->seq_start(seq, ppos); } static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos) { return seq_cft(seq)->seq_next(seq, v, ppos); } static void cgroup_seqfile_stop(struct seq_file *seq, void *v) { if (seq_cft(seq)->seq_stop) seq_cft(seq)->seq_stop(seq, v); } static int cgroup_seqfile_show(struct seq_file *m, void *arg) { struct cftype *cft = seq_cft(m); struct cgroup_subsys_state *css = seq_css(m); if (cft->seq_show) return cft->seq_show(m, arg); if (cft->read_u64) seq_printf(m, "%llu\n", cft->read_u64(css, cft)); else if (cft->read_s64) seq_printf(m, "%lld\n", cft->read_s64(css, cft)); else return -EINVAL; return 0; } static struct kernfs_ops cgroup_kf_single_ops = { .atomic_write_len = PAGE_SIZE, .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, .poll = cgroup_file_poll, .seq_show = cgroup_seqfile_show, }; static struct kernfs_ops cgroup_kf_ops = { .atomic_write_len = PAGE_SIZE, .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, .poll = cgroup_file_poll, .seq_start = cgroup_seqfile_start, .seq_next = cgroup_seqfile_next, .seq_stop = cgroup_seqfile_stop, .seq_show = cgroup_seqfile_show, }; /* set uid and gid of cgroup dirs and files to that of the creator */ static int cgroup_kn_set_ugid(struct kernfs_node *kn) { struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, .ia_uid = current_fsuid(), .ia_gid = current_fsgid(), }; if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) && gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID)) return 0; return kernfs_setattr(kn, &iattr); } static void cgroup_file_notify_timer(struct timer_list *timer) { cgroup_file_notify(container_of(timer, struct cgroup_file, notify_timer)); } static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype *cft) { char name[CGROUP_FILE_NAME_MAX]; struct kernfs_node *kn; struct lock_class_key *key = NULL; int ret; #ifdef CONFIG_DEBUG_LOCK_ALLOC key = &cft->lockdep_key; #endif kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), cgroup_file_mode(cft), GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0, cft->kf_ops, cft, NULL, key); if (IS_ERR(kn)) return PTR_ERR(kn); ret = cgroup_kn_set_ugid(kn); if (ret) { kernfs_remove(kn); return ret; } if (cft->file_offset) { struct cgroup_file *cfile = (void *)css + cft->file_offset; timer_setup(&cfile->notify_timer, cgroup_file_notify_timer, 0); spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = kn; spin_unlock_irq(&cgroup_file_kn_lock); } return 0; } /** * cgroup_addrm_files - add or remove files to a cgroup directory * @css: the target css * @cgrp: the target cgroup (usually css->cgroup) * @cfts: array of cftypes to be added * @is_add: whether to add or remove * * Depending on @is_add, add or remove files defined by @cfts on @cgrp. * For removals, this function never fails. */ static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add) { struct cftype *cft, *cft_end = NULL; int ret = 0; lockdep_assert_held(&cgroup_mutex); restart: for (cft = cfts; cft != cft_end && cft->name[0] != '\0'; cft++) { /* does cft->flags tell us to skip this file on @cgrp? */ if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp)) continue; if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp)) continue; if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgroup_parent(cgrp)) continue; if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp)) continue; if ((cft->flags & CFTYPE_DEBUG) && !cgroup_debug) continue; if (is_add) { ret = cgroup_add_file(css, cgrp, cft); if (ret) { pr_warn("%s: failed to add %s, err=%d\n", __func__, cft->name, ret); cft_end = cft; is_add = false; goto restart; } } else { cgroup_rm_file(cgrp, cft); } } return ret; } static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add) { struct cgroup_subsys *ss = cfts[0].ss; struct cgroup *root = &ss->root->cgrp; struct cgroup_subsys_state *css; int ret = 0; lockdep_assert_held(&cgroup_mutex); /* add/rm files for all cgroups created before */ css_for_each_descendant_pre(css, cgroup_css(root, ss)) { struct cgroup *cgrp = css->cgroup; if (!(css->flags & CSS_VISIBLE)) continue; ret = cgroup_addrm_files(css, cgrp, cfts, is_add); if (ret) break; } if (is_add && !ret) kernfs_activate(root->kn); return ret; } static void cgroup_exit_cftypes(struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft->name[0] != '\0'; cft++) { /* free copy for custom atomic_write_len, see init_cftypes() */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) kfree(cft->kf_ops); cft->kf_ops = NULL; cft->ss = NULL; /* revert flags set by cgroup core while adding @cfts */ cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL | __CFTYPE_ADDED); } } static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; int ret = 0; for (cft = cfts; cft->name[0] != '\0'; cft++) { struct kernfs_ops *kf_ops; WARN_ON(cft->ss || cft->kf_ops); if (cft->flags & __CFTYPE_ADDED) { ret = -EBUSY; break; } if (cft->seq_start) kf_ops = &cgroup_kf_ops; else kf_ops = &cgroup_kf_single_ops; /* * Ugh... if @cft wants a custom max_write_len, we need to * make a copy of kf_ops to set its atomic_write_len. */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) { kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL); if (!kf_ops) { ret = -ENOMEM; break; } kf_ops->atomic_write_len = cft->max_write_len; } cft->kf_ops = kf_ops; cft->ss = ss; cft->flags |= __CFTYPE_ADDED; } if (ret) cgroup_exit_cftypes(cfts); return ret; } static int cgroup_rm_cftypes_locked(struct cftype *cfts) { lockdep_assert_held(&cgroup_mutex); list_del(&cfts->node); cgroup_apply_cftypes(cfts, false); cgroup_exit_cftypes(cfts); return 0; } /** * cgroup_rm_cftypes - remove an array of cftypes from a subsystem * @cfts: zero-length name terminated array of cftypes * * Unregister @cfts. Files described by @cfts are removed from all * existing cgroups and all future cgroups won't have them either. This * function can be called anytime whether @cfts' subsys is attached or not. * * Returns 0 on successful unregistration, -ENOENT if @cfts is not * registered. */ int cgroup_rm_cftypes(struct cftype *cfts) { int ret; if (!cfts || cfts[0].name[0] == '\0') return 0; if (!(cfts[0].flags & __CFTYPE_ADDED)) return -ENOENT; mutex_lock(&cgroup_mutex); ret = cgroup_rm_cftypes_locked(cfts); mutex_unlock(&cgroup_mutex); return ret; } /** * cgroup_add_cftypes - add an array of cftypes to a subsystem * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Register @cfts to @ss. Files described by @cfts are created for all * existing cgroups to which @ss is attached and all future cgroups will * have them too. This function can be called anytime whether @ss is * attached or not. * * Returns 0 on successful registration, -errno on failure. Note that this * function currently returns 0 as long as @cfts registration is successful * even if some file creation attempts on existing cgroups fail. */ static int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { int ret; if (!cgroup_ssid_enabled(ss->id)) return 0; if (!cfts || cfts[0].name[0] == '\0') return 0; ret = cgroup_init_cftypes(ss, cfts); if (ret) return ret; mutex_lock(&cgroup_mutex); list_add_tail(&cfts->node, &ss->cfts); ret = cgroup_apply_cftypes(cfts, true); if (ret) cgroup_rm_cftypes_locked(cfts); mutex_unlock(&cgroup_mutex); return ret; } /** * cgroup_add_dfl_cftypes - add an array of cftypes for default hierarchy * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the default hierarchy. */ int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_ONLY_ON_DFL; return cgroup_add_cftypes(ss, cfts); } /** * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the legacy hierarchies. */ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_NOT_ON_DFL; return cgroup_add_cftypes(ss, cfts); } /** * cgroup_file_notify - generate a file modified event for a cgroup_file * @cfile: target cgroup_file * * @cfile must have been obtained by setting cftype->file_offset. */ void cgroup_file_notify(struct cgroup_file *cfile) { unsigned long flags; spin_lock_irqsave(&cgroup_file_kn_lock, flags); if (cfile->kn) { unsigned long last = cfile->notified_at; unsigned long next = last + CGROUP_FILE_NOTIFY_MIN_INTV; if (time_in_range(jiffies, last, next)) { timer_reduce(&cfile->notify_timer, next); } else { kernfs_notify(cfile->kn); cfile->notified_at = jiffies; } } spin_unlock_irqrestore(&cgroup_file_kn_lock, flags); } /** * cgroup_file_show - show or hide a hidden cgroup file * @cfile: target cgroup_file obtained by setting cftype->file_offset * @show: whether to show or hide */ void cgroup_file_show(struct cgroup_file *cfile, bool show) { struct kernfs_node *kn; spin_lock_irq(&cgroup_file_kn_lock); kn = cfile->kn; kernfs_get(kn); spin_unlock_irq(&cgroup_file_kn_lock); if (kn) kernfs_show(kn, show); kernfs_put(kn); } /** * css_next_child - find the next child of a given css * @pos: the current position (%NULL to initiate traversal) * @parent: css whose children to walk * * This function returns the next child of @parent and should be called * under either cgroup_mutex or RCU read lock. The only requirement is * that @parent and @pos are accessible. The next sibling is guaranteed to * be returned regardless of their states. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* * @pos could already have been unlinked from the sibling list. * Once a cgroup is removed, its ->sibling.next is no longer * updated when its next sibling changes. CSS_RELEASED is set when * @pos is taken off list, at which time its next pointer is valid, * and, as releases are serialized, the one pointed to by the next * pointer is guaranteed to not have started release yet. This * implies that if we observe !CSS_RELEASED on @pos in this RCU * critical section, the one pointed to by its next pointer is * guaranteed to not have finished its RCU grace period even if we * have dropped rcu_read_lock() in-between iterations. * * If @pos has CSS_RELEASED set, its next pointer can't be * dereferenced; however, as each css is given a monotonically * increasing unique serial number and always appended to the * sibling list, the next one can be found by walking the parent's * children until the first css with higher serial number than * @pos's. While this path can be slower, it happens iff iteration * races against release and the race window is very small. */ if (!pos) { next = list_entry_rcu(parent->children.next, struct cgroup_subsys_state, sibling); } else if (likely(!(pos->flags & CSS_RELEASED))) { next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling); } else { list_for_each_entry_rcu(next, &parent->children, sibling, lockdep_is_held(&cgroup_mutex)) if (next->serial_nr > pos->serial_nr) break; } /* * @next, if not pointing to the head, can be dereferenced and is * the next sibling. */ if (&next->sibling != &parent->children) return next; return NULL; } /** * css_next_descendant_pre - find the next descendant for pre-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_pre(). Find the next descendant * to visit for pre-order traversal of @root's descendants. @root is * included in the iteration and the first node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. This function will return the correct next descendant as long * as both @pos and @root are accessible and @pos is a descendant of @root. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state * css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* if first iteration, visit @root */ if (!pos) return root; /* visit the first child if exists */ next = css_next_child(NULL, pos); if (next) return next; /* no child, visit my or the closest ancestor's next sibling */ while (pos != root) { next = css_next_child(pos, pos->parent); if (next) return next; pos = pos->parent; } return NULL; } EXPORT_SYMBOL_GPL(css_next_descendant_pre); /** * css_rightmost_descendant - return the rightmost descendant of a css * @pos: css of interest * * Return the rightmost descendant of @pos. If there's no descendant, @pos * is returned. This can be used during pre-order traversal to skip * subtree of @pos. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. This function will return the correct rightmost descendant as * long as @pos is accessible. */ struct cgroup_subsys_state * css_rightmost_descendant(struct cgroup_subsys_state *pos) { struct cgroup_subsys_state *last, *tmp; cgroup_assert_mutex_or_rcu_locked(); do { last = pos; /* ->prev isn't RCU safe, walk ->next till the end */ pos = NULL; css_for_each_child(tmp, last) pos = tmp; } while (pos); return last; } static struct cgroup_subsys_state * css_leftmost_descendant(struct cgroup_subsys_state *pos) { struct cgroup_subsys_state *last; do { last = pos; pos = css_next_child(NULL, pos); } while (pos); return last; } /** * css_next_descendant_post - find the next descendant for post-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_post(). Find the next descendant * to visit for post-order traversal of @root's descendants. @root is * included in the iteration and the last node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. This function will return the correct next descendant as long * as both @pos and @cgroup are accessible and @pos is a descendant of * @cgroup. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state * css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* if first iteration, visit leftmost descendant which may be @root */ if (!pos) return css_leftmost_descendant(root); /* if we visited @root, we're done */ if (pos == root) return NULL; /* if there's an unvisited sibling, visit its leftmost descendant */ next = css_next_child(pos, pos->parent); if (next) return css_leftmost_descendant(next); /* no sibling left, visit parent */ return pos->parent; } /** * css_has_online_children - does a css have online children * @css: the target css * * Returns %true if @css has any online children; otherwise, %false. This * function can be called from any context but the caller is responsible * for synchronizing against on/offlining as necessary. */ bool css_has_online_children(struct cgroup_subsys_state *css) { struct cgroup_subsys_state *child; bool ret = false; rcu_read_lock(); css_for_each_child(child, css) { if (child->flags & CSS_ONLINE) { ret = true; break; } } rcu_read_unlock(); return ret; } static struct css_set *css_task_iter_next_css_set(struct css_task_iter *it) { struct list_head *l; struct cgrp_cset_link *link; struct css_set *cset; lockdep_assert_held(&css_set_lock); /* find the next threaded cset */ if (it->tcset_pos) { l = it->tcset_pos->next; if (l != it->tcset_head) { it->tcset_pos = l; return container_of(l, struct css_set, threaded_csets_node); } it->tcset_pos = NULL; } /* find the next cset */ l = it->cset_pos; l = l->next; if (l == it->cset_head) { it->cset_pos = NULL; return NULL; } if (it->ss) { cset = container_of(l, struct css_set, e_cset_node[it->ss->id]); } else { link = list_entry(l, struct cgrp_cset_link, cset_link); cset = link->cset; } it->cset_pos = l; /* initialize threaded css_set walking */ if (it->flags & CSS_TASK_ITER_THREADED) { if (it->cur_dcset) put_css_set_locked(it->cur_dcset); it->cur_dcset = cset; get_css_set(cset); it->tcset_head = &cset->threaded_csets; it->tcset_pos = &cset->threaded_csets; } return cset; } /** * css_task_iter_advance_css_set - advance a task iterator to the next css_set * @it: the iterator to advance * * Advance @it to the next css_set to walk. */ static void css_task_iter_advance_css_set(struct css_task_iter *it) { struct css_set *cset; lockdep_assert_held(&css_set_lock); /* Advance to the next non-empty css_set and find first non-empty tasks list*/ while ((cset = css_task_iter_next_css_set(it))) { if (!list_empty(&cset->tasks)) { it->cur_tasks_head = &cset->tasks; break; } else if (!list_empty(&cset->mg_tasks)) { it->cur_tasks_head = &cset->mg_tasks; break; } else if (!list_empty(&cset->dying_tasks)) { it->cur_tasks_head = &cset->dying_tasks; break; } } if (!cset) { it->task_pos = NULL; return; } it->task_pos = it->cur_tasks_head->next; /* * We don't keep css_sets locked across iteration steps and thus * need to take steps to ensure that iteration can be resumed after * the lock is re-acquired. Iteration is performed at two levels - * css_sets and tasks in them. * * Once created, a css_set never leaves its cgroup lists, so a * pinned css_set is guaranteed to stay put and we can resume * iteration afterwards. * * Tasks may leave @cset across iteration steps. This is resolved * by registering each iterator with the css_set currently being * walked and making css_set_move_task() advance iterators whose * next task is leaving. */ if (it->cur_cset) { list_del(&it->iters_node); put_css_set_locked(it->cur_cset); } get_css_set(cset); it->cur_cset = cset; list_add(&it->iters_node, &cset->task_iters); } static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task) { lockdep_assert_held(&css_set_lock); if (it->task_pos == &task->cg_list) { it->task_pos = it->task_pos->next; it->flags |= CSS_TASK_ITER_SKIPPED; } } static void css_task_iter_advance(struct css_task_iter *it) { struct task_struct *task; lockdep_assert_held(&css_set_lock); repeat: if (it->task_pos) { /* * Advance iterator to find next entry. We go through cset * tasks, mg_tasks and dying_tasks, when consumed we move onto * the next cset. */ if (it->flags & CSS_TASK_ITER_SKIPPED) it->flags &= ~CSS_TASK_ITER_SKIPPED; else it->task_pos = it->task_pos->next; if (it->task_pos == &it->cur_cset->tasks) { it->cur_tasks_head = &it->cur_cset->mg_tasks; it->task_pos = it->cur_tasks_head->next; } if (it->task_pos == &it->cur_cset->mg_tasks) { it->cur_tasks_head = &it->cur_cset->dying_tasks; it->task_pos = it->cur_tasks_head->next; } if (it->task_pos == &it->cur_cset->dying_tasks) css_task_iter_advance_css_set(it); } else { /* called from start, proceed to the first cset */ css_task_iter_advance_css_set(it); } if (!it->task_pos) return; task = list_entry(it->task_pos, struct task_struct, cg_list); if (it->flags & CSS_TASK_ITER_PROCS) { /* if PROCS, skip over tasks which aren't group leaders */ if (!thread_group_leader(task)) goto repeat; /* and dying leaders w/o live member threads */ if (it->cur_tasks_head == &it->cur_cset->dying_tasks && !atomic_read(&task->signal->live)) goto repeat; } else { /* skip all dying ones */ if (it->cur_tasks_head == &it->cur_cset->dying_tasks) goto repeat; } } /** * css_task_iter_start - initiate task iteration * @css: the css to walk tasks of * @flags: CSS_TASK_ITER_* flags * @it: the task iterator to use * * Initiate iteration through the tasks of @css. The caller can call * css_task_iter_next() to walk through the tasks until the function * returns NULL. On completion of iteration, css_task_iter_end() must be * called. */ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it) { memset(it, 0, sizeof(*it)); spin_lock_irq(&css_set_lock); it->ss = css->ss; it->flags = flags; if (CGROUP_HAS_SUBSYS_CONFIG && it->ss) it->cset_pos = &css->cgroup->e_csets[css->ss->id]; else it->cset_pos = &css->cgroup->cset_links; it->cset_head = it->cset_pos; css_task_iter_advance(it); spin_unlock_irq(&css_set_lock); } /** * css_task_iter_next - return the next task for the iterator * @it: the task iterator being iterated * * The "next" function for task iteration. @it should have been * initialized via css_task_iter_start(). Returns NULL when the iteration * reaches the end. */ struct task_struct *css_task_iter_next(struct css_task_iter *it) { if (it->cur_task) { put_task_struct(it->cur_task); it->cur_task = NULL; } spin_lock_irq(&css_set_lock); /* @it may be half-advanced by skips, finish advancing */ if (it->flags & CSS_TASK_ITER_SKIPPED) css_task_iter_advance(it); if (it->task_pos) { it->cur_task = list_entry(it->task_pos, struct task_struct, cg_list); get_task_struct(it->cur_task); css_task_iter_advance(it); } spin_unlock_irq(&css_set_lock); return it->cur_task; } /** * css_task_iter_end - finish task iteration * @it: the task iterator to finish * * Finish task iteration started by css_task_iter_start(). */ void css_task_iter_end(struct css_task_iter *it) { if (it->cur_cset) { spin_lock_irq(&css_set_lock); list_del(&it->iters_node); put_css_set_locked(it->cur_cset); spin_unlock_irq(&css_set_lock); } if (it->cur_dcset) put_css_set(it->cur_dcset); if (it->cur_task) put_task_struct(it->cur_task); } static void cgroup_procs_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; if (ctx->procs.started) css_task_iter_end(&ctx->procs.iter); } static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; if (pos) (*pos)++; return css_task_iter_next(&ctx->procs.iter); } static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, unsigned int iter_flags) { struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_file_ctx *ctx = of->priv; struct css_task_iter *it = &ctx->procs.iter; /* * When a seq_file is seeked, it's always traversed sequentially * from position 0, so we can simply keep iterating on !0 *pos. */ if (!ctx->procs.started) { if (WARN_ON_ONCE((*pos))) return ERR_PTR(-EINVAL); css_task_iter_start(&cgrp->self, iter_flags, it); ctx->procs.started = true; } else if (!(*pos)) { css_task_iter_end(it); css_task_iter_start(&cgrp->self, iter_flags, it); } else return it->cur_task; return cgroup_procs_next(s, NULL, NULL); } static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) { struct cgroup *cgrp = seq_css(s)->cgroup; /* * All processes of a threaded subtree belong to the domain cgroup * of the subtree. Only threads can be distributed across the * subtree. Reject reads on cgroup.procs in the subtree proper. * They're always empty anyway. */ if (cgroup_is_threaded(cgrp)) return ERR_PTR(-EOPNOTSUPP); return __cgroup_procs_start(s, pos, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED); } static int cgroup_procs_show(struct seq_file *s, void *v) { seq_printf(s, "%d\n", task_pid_vnr(v)); return 0; } static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb) { int ret; struct inode *inode; lockdep_assert_held(&cgroup_mutex); inode = kernfs_get_inode(sb, cgrp->procs_file.kn); if (!inode) return -ENOMEM; ret = inode_permission(&init_user_ns, inode, MAY_WRITE); iput(inode); return ret; } static int cgroup_procs_write_permission(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, struct cgroup_namespace *ns) { struct cgroup *com_cgrp = src_cgrp; int ret; lockdep_assert_held(&cgroup_mutex); /* find the common ancestor */ while (!cgroup_is_descendant(dst_cgrp, com_cgrp)) com_cgrp = cgroup_parent(com_cgrp); /* %current should be authorized to migrate to the common ancestor */ ret = cgroup_may_write(com_cgrp, sb); if (ret) return ret; /* * If namespaces are delegation boundaries, %current must be able * to see both source and destination cgroups from its namespace. */ if ((cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) && (!cgroup_is_descendant(src_cgrp, ns->root_cset->dfl_cgrp) || !cgroup_is_descendant(dst_cgrp, ns->root_cset->dfl_cgrp))) return -ENOENT; return 0; } static int cgroup_attach_permissions(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, bool threadgroup, struct cgroup_namespace *ns) { int ret = 0; ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb, ns); if (ret) return ret; ret = cgroup_migrate_vet_dst(dst_cgrp); if (ret) return ret; if (!threadgroup && (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp)) ret = -EOPNOTSUPP; return ret; } static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, bool threadgroup) { struct cgroup_file_ctx *ctx = of->priv; struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; const struct cred *saved_cred; ssize_t ret; bool threadgroup_locked; dst_cgrp = cgroup_kn_lock_live(of->kn, false); if (!dst_cgrp) return -ENODEV; task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; /* find the source cgroup */ spin_lock_irq(&css_set_lock); src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); spin_unlock_irq(&css_set_lock); /* * Process and thread migrations follow same delegation rule. Check * permissions using the credentials from file open to protect against * inherited fd attacks. */ saved_cred = override_creds(of->file->f_cred); ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, of->file->f_path.dentry->d_sb, threadgroup, ctx->ns); revert_creds(saved_cred); if (ret) goto out_finish; ret = cgroup_attach_task(dst_cgrp, task, threadgroup); out_finish: cgroup_procs_write_finish(task, threadgroup_locked); out_unlock: cgroup_kn_unlock(of->kn); return ret; } static ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup_procs_write(of, buf, true) ?: nbytes; } static void *cgroup_threads_start(struct seq_file *s, loff_t *pos) { return __cgroup_procs_start(s, pos, 0); } static ssize_t cgroup_threads_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup_procs_write(of, buf, false) ?: nbytes; } /* cgroup core interface files for the default hierarchy */ static struct cftype cgroup_base_files[] = { { .name = "cgroup.type", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_type_show, .write = cgroup_type_write, }, { .name = "cgroup.procs", .flags = CFTYPE_NS_DELEGATABLE, .file_offset = offsetof(struct cgroup, procs_file), .release = cgroup_procs_release, .seq_start = cgroup_procs_start, .seq_next = cgroup_procs_next, .seq_show = cgroup_procs_show, .write = cgroup_procs_write, }, { .name = "cgroup.threads", .flags = CFTYPE_NS_DELEGATABLE, .release = cgroup_procs_release, .seq_start = cgroup_threads_start, .seq_next = cgroup_procs_next, .seq_show = cgroup_procs_show, .write = cgroup_threads_write, }, { .name = "cgroup.controllers", .seq_show = cgroup_controllers_show, }, { .name = "cgroup.subtree_control", .flags = CFTYPE_NS_DELEGATABLE, .seq_show = cgroup_subtree_control_show, .write = cgroup_subtree_control_write, }, { .name = "cgroup.events", .flags = CFTYPE_NOT_ON_ROOT, .file_offset = offsetof(struct cgroup, events_file), .seq_show = cgroup_events_show, }, { .name = "cgroup.max.descendants", .seq_show = cgroup_max_descendants_show, .write = cgroup_max_descendants_write, }, { .name = "cgroup.max.depth", .seq_show = cgroup_max_depth_show, .write = cgroup_max_depth_write, }, { .name = "cgroup.stat", .seq_show = cgroup_stat_show, }, { .name = "cgroup.freeze", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_freeze_show, .write = cgroup_freeze_write, }, { .name = "cgroup.kill", .flags = CFTYPE_NOT_ON_ROOT, .write = cgroup_kill_write, }, { .name = "cpu.stat", .seq_show = cpu_stat_show, }, { } /* terminate */ }; static struct cftype cgroup_psi_files[] = { #ifdef CONFIG_PSI { .name = "io.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]), .seq_show = cgroup_io_pressure_show, .write = cgroup_io_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, { .name = "memory.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]), .seq_show = cgroup_memory_pressure_show, .write = cgroup_memory_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, { .name = "cpu.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]), .seq_show = cgroup_cpu_pressure_show, .write = cgroup_cpu_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, #ifdef CONFIG_IRQ_TIME_ACCOUNTING { .name = "irq.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]), .seq_show = cgroup_irq_pressure_show, .write = cgroup_irq_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, #endif { .name = "cgroup.pressure", .seq_show = cgroup_pressure_show, .write = cgroup_pressure_write, }, #endif /* CONFIG_PSI */ { } /* terminate */ }; /* * css destruction is four-stage process. * * 1. Destruction starts. Killing of the percpu_ref is initiated. * Implemented in kill_css(). * * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs * and thus css_tryget_online() is guaranteed to fail, the css can be * offlined by invoking offline_css(). After offlining, the base ref is * put. Implemented in css_killed_work_fn(). * * 3. When the percpu_ref reaches zero, the only possible remaining * accessors are inside RCU read sections. css_release() schedules the * RCU callback. * * 4. After the grace period, the css can be freed. Implemented in * css_free_work_fn(). * * It is actually hairier because both step 2 and 4 require process context * and thus involve punting to css->destroy_work adding two additional * steps to the already complex sequence. */ static void css_free_rwork_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(to_rcu_work(work), struct cgroup_subsys_state, destroy_rwork); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; percpu_ref_exit(&css->refcnt); if (ss) { /* css free path */ struct cgroup_subsys_state *parent = css->parent; int id = css->id; ss->css_free(css); cgroup_idr_remove(&ss->css_idr, id); cgroup_put(cgrp); if (parent) css_put(parent); } else { /* cgroup free path */ atomic_dec(&cgrp->root->nr_cgrps); cgroup1_pidlist_destroy_all(cgrp); cancel_work_sync(&cgrp->release_agent_work); if (cgroup_parent(cgrp)) { /* * We get a ref to the parent, and put the ref when * this cgroup is being freed, so it's guaranteed * that the parent won't be destroyed before its * children. */ cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); psi_cgroup_free(cgrp); cgroup_rstat_exit(cgrp); kfree(cgrp); } else { /* * This is root cgroup's refcnt reaching zero, * which indicates that the root should be * released. */ cgroup_destroy_root(cgrp->root); } } } static void css_release_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; mutex_lock(&cgroup_mutex); css->flags |= CSS_RELEASED; list_del_rcu(&css->sibling); if (ss) { /* css release path */ if (!list_empty(&css->rstat_css_node)) { cgroup_rstat_flush(cgrp); list_del_rcu(&css->rstat_css_node); } cgroup_idr_replace(&ss->css_idr, NULL, css->id); if (ss->css_released) ss->css_released(css); } else { struct cgroup *tcgrp; /* cgroup release path */ TRACE_CGROUP_PATH(release, cgrp); cgroup_rstat_flush(cgrp); spin_lock_irq(&css_set_lock); for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) tcgrp->nr_dying_descendants--; spin_unlock_irq(&css_set_lock); /* * There are two control paths which try to determine * cgroup from dentry without going through kernfs - * cgroupstats_build() and css_tryget_online_from_dir(). * Those are supported by RCU protecting clearing of * cgrp->kn->priv backpointer. */ if (cgrp->kn) RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL); } mutex_unlock(&cgroup_mutex); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); } static void css_release(struct percpu_ref *ref) { struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); INIT_WORK(&css->destroy_work, css_release_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); } static void init_and_link_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss, struct cgroup *cgrp) { lockdep_assert_held(&cgroup_mutex); cgroup_get_live(cgrp); memset(css, 0, sizeof(*css)); css->cgroup = cgrp; css->ss = ss; css->id = -1; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); INIT_LIST_HEAD(&css->rstat_css_node); css->serial_nr = css_serial_nr_next++; atomic_set(&css->online_cnt, 0); if (cgroup_parent(cgrp)) { css->parent = cgroup_css(cgroup_parent(cgrp), ss); css_get(css->parent); } if (ss->css_rstat_flush) list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list); BUG_ON(cgroup_css(cgrp, ss)); } /* invoke ->css_online() on a new CSS and mark it online if successful */ static int online_css(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; int ret = 0; lockdep_assert_held(&cgroup_mutex); if (ss->css_online) ret = ss->css_online(css); if (!ret) { css->flags |= CSS_ONLINE; rcu_assign_pointer(css->cgroup->subsys[ss->id], css); atomic_inc(&css->online_cnt); if (css->parent) atomic_inc(&css->parent->online_cnt); } return ret; } /* if the CSS is online, invoke ->css_offline() on it and mark it offline */ static void offline_css(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; lockdep_assert_held(&cgroup_mutex); if (!(css->flags & CSS_ONLINE)) return; if (ss->css_offline) ss->css_offline(css); css->flags &= ~CSS_ONLINE; RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL); wake_up_all(&css->cgroup->offline_waitq); } /** * css_create - create a cgroup_subsys_state * @cgrp: the cgroup new css will be associated with * @ss: the subsys of new css * * Create a new css associated with @cgrp - @ss pair. On success, the new * css is online and installed in @cgrp. This function doesn't create the * interface files. Returns 0 on success, -errno on failure. */ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss); struct cgroup_subsys_state *css; int err; lockdep_assert_held(&cgroup_mutex); css = ss->css_alloc(parent_css); if (!css) css = ERR_PTR(-ENOMEM); if (IS_ERR(css)) return css; init_and_link_css(css, ss, cgrp); err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL); if (err) goto err_free_css; err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL); if (err < 0) goto err_free_css; css->id = err; /* @css is ready to be brought online now, make it visible */ list_add_tail_rcu(&css->sibling, &parent_css->children); cgroup_idr_replace(&ss->css_idr, css, css->id); err = online_css(css); if (err) goto err_list_del; return css; err_list_del: list_del_rcu(&css->sibling); err_free_css: list_del_rcu(&css->rstat_css_node); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); return ERR_PTR(err); } /* * The returned cgroup is fully initialized including its control mask, but * it isn't associated with its kernfs_node and doesn't have the control * mask applied. */ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, umode_t mode) { struct cgroup_root *root = parent->root; struct cgroup *cgrp, *tcgrp; struct kernfs_node *kn; int level = parent->level + 1; int ret; /* allocate the cgroup and its ID, 0 is reserved for the root */ cgrp = kzalloc(struct_size(cgrp, ancestors, (level + 1)), GFP_KERNEL); if (!cgrp) return ERR_PTR(-ENOMEM); ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out_free_cgrp; ret = cgroup_rstat_init(cgrp); if (ret) goto out_cancel_ref; /* create the directory */ kn = kernfs_create_dir(parent->kn, name, mode, cgrp); if (IS_ERR(kn)) { ret = PTR_ERR(kn); goto out_stat_exit; } cgrp->kn = kn; init_cgroup_housekeeping(cgrp); cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; ret = psi_cgroup_alloc(cgrp); if (ret) goto out_kernfs_remove; ret = cgroup_bpf_inherit(cgrp); if (ret) goto out_psi_free; /* * New cgroup inherits effective freeze counter, and * if the parent has to be frozen, the child has too. */ cgrp->freezer.e_freeze = parent->freezer.e_freeze; if (cgrp->freezer.e_freeze) { /* * Set the CGRP_FREEZE flag, so when a process will be * attached to the child cgroup, it will become frozen. * At this point the new cgroup is unpopulated, so we can * consider it frozen immediately. */ set_bit(CGRP_FREEZE, &cgrp->flags); set_bit(CGRP_FROZEN, &cgrp->flags); } spin_lock_irq(&css_set_lock); for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestors[tcgrp->level] = tcgrp; if (tcgrp != cgrp) { tcgrp->nr_descendants++; /* * If the new cgroup is frozen, all ancestor cgroups * get a new frozen descendant, but their state can't * change because of this. */ if (cgrp->freezer.e_freeze) tcgrp->freezer.nr_frozen_descendants++; } } spin_unlock_irq(&css_set_lock); if (notify_on_release(parent)) set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags)) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags); cgrp->self.serial_nr = css_serial_nr_next++; /* allocation complete, commit to creation */ list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children); atomic_inc(&root->nr_cgrps); cgroup_get_live(parent); /* * On the default hierarchy, a child doesn't automatically inherit * subtree_control from the parent. Each is configured manually. */ if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); cgroup_propagate_control(cgrp); return cgrp; out_psi_free: psi_cgroup_free(cgrp); out_kernfs_remove: kernfs_remove(cgrp->kn); out_stat_exit: cgroup_rstat_exit(cgrp); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: kfree(cgrp); return ERR_PTR(ret); } static bool cgroup_check_hierarchy_limits(struct cgroup *parent) { struct cgroup *cgroup; int ret = false; int level = 1; lockdep_assert_held(&cgroup_mutex); for (cgroup = parent; cgroup; cgroup = cgroup_parent(cgroup)) { if (cgroup->nr_descendants >= cgroup->max_descendants) goto fail; if (level > cgroup->max_depth) goto fail; level++; } ret = true; fail: return ret; } int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) { struct cgroup *parent, *cgrp; int ret; /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ if (strchr(name, '\n')) return -EINVAL; parent = cgroup_kn_lock_live(parent_kn, false); if (!parent) return -ENODEV; if (!cgroup_check_hierarchy_limits(parent)) { ret = -EAGAIN; goto out_unlock; } cgrp = cgroup_create(parent, name, mode); if (IS_ERR(cgrp)) { ret = PTR_ERR(cgrp); goto out_unlock; } /* * This extra ref will be put in cgroup_free_fn() and guarantees * that @cgrp->kn is always accessible. */ kernfs_get(cgrp->kn); ret = cgroup_kn_set_ugid(cgrp->kn); if (ret) goto out_destroy; ret = css_populate_dir(&cgrp->self); if (ret) goto out_destroy; ret = cgroup_apply_control_enable(cgrp); if (ret) goto out_destroy; TRACE_CGROUP_PATH(mkdir, cgrp); /* let's create and online css's */ kernfs_activate(cgrp->kn); ret = 0; goto out_unlock; out_destroy: cgroup_destroy_locked(cgrp); out_unlock: cgroup_kn_unlock(parent_kn); return ret; } /* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to * initiate destruction and put the css ref from kill_css(). */ static void css_killed_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); mutex_lock(&cgroup_mutex); do { offline_css(css); css_put(css); /* @css can't go away while we're holding cgroup_mutex */ css = css->parent; } while (css && atomic_dec_and_test(&css->online_cnt)); mutex_unlock(&cgroup_mutex); } /* css kill confirmation processing requires process context, bounce */ static void css_killed_ref_fn(struct percpu_ref *ref) { struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); if (atomic_dec_and_test(&css->online_cnt)) { INIT_WORK(&css->destroy_work, css_killed_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); } } /** * kill_css - destroy a css * @css: css to destroy * * This function initiates destruction of @css by removing cgroup interface * files and putting its base reference. ->css_offline() will be invoked * asynchronously once css_tryget_online() is guaranteed to fail and when * the reference count reaches zero, @css will be released. */ static void kill_css(struct cgroup_subsys_state *css) { lockdep_assert_held(&cgroup_mutex); if (css->flags & CSS_DYING) return; css->flags |= CSS_DYING; /* * This must happen before css is disassociated with its cgroup. * See seq_css() for details. */ css_clear_dir(css); /* * Killing would put the base ref, but we need to keep it alive * until after ->css_offline(). */ css_get(css); /* * cgroup core guarantees that, by the time ->css_offline() is * invoked, no new css reference will be given out via * css_tryget_online(). We can't simply call percpu_ref_kill() and * proceed to offlining css's because percpu_ref_kill() doesn't * guarantee that the ref is seen as killed on all CPUs on return. * * Use percpu_ref_kill_and_confirm() to get notifications as each * css is confirmed to be seen as killed on all CPUs. */ percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn); } /** * cgroup_destroy_locked - the first stage of cgroup destruction * @cgrp: cgroup to be destroyed * * css's make use of percpu refcnts whose killing latency shouldn't be * exposed to userland and are RCU protected. Also, cgroup core needs to * guarantee that css_tryget_online() won't succeed by the time * ->css_offline() is invoked. To satisfy all the requirements, * destruction is implemented in the following two steps. * * s1. Verify @cgrp can be destroyed and mark it dying. Remove all * userland visible parts and start killing the percpu refcnts of * css's. Set up so that the next stage will be kicked off once all * the percpu refcnts are confirmed to be killed. * * s2. Invoke ->css_offline(), mark the cgroup dead and proceed with the * rest of destruction. Once all cgroup references are gone, the * cgroup is RCU-freed. * * This function implements s1. After this step, @cgrp is gone as far as * the userland is concerned and a new cgroup with the same name may be * created. As cgroup doesn't care about the names internally, this * doesn't cause any problem. */ static int cgroup_destroy_locked(struct cgroup *cgrp) __releases(&cgroup_mutex) __acquires(&cgroup_mutex) { struct cgroup *tcgrp, *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *css; struct cgrp_cset_link *link; int ssid; lockdep_assert_held(&cgroup_mutex); /* * Only migration can raise populated from zero and we're already * holding cgroup_mutex. */ if (cgroup_is_populated(cgrp)) return -EBUSY; /* * Make sure there's no live children. We can't test emptiness of * ->self.children as dead children linger on it while being * drained; otherwise, "rmdir parent/child parent" may fail. */ if (css_has_online_children(&cgrp->self)) return -EBUSY; /* * Mark @cgrp and the associated csets dead. The former prevents * further task migration and child creation by disabling * cgroup_lock_live_group(). The latter makes the csets ignored by * the migration path. */ cgrp->self.flags &= ~CSS_ONLINE; spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) link->cset->dead = true; spin_unlock_irq(&css_set_lock); /* initiate massacre of all css's */ for_each_css(css, ssid, cgrp) kill_css(css); /* clear and remove @cgrp dir, @cgrp has an extra ref on its kn */ css_clear_dir(&cgrp->self); kernfs_remove(cgrp->kn); if (cgroup_is_threaded(cgrp)) parent->nr_threaded_children--; spin_lock_irq(&css_set_lock); for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) { tcgrp->nr_descendants--; tcgrp->nr_dying_descendants++; /* * If the dying cgroup is frozen, decrease frozen descendants * counters of ancestor cgroups. */ if (test_bit(CGRP_FROZEN, &cgrp->flags)) tcgrp->freezer.nr_frozen_descendants--; } spin_unlock_irq(&css_set_lock); cgroup1_check_for_release(parent); cgroup_bpf_offline(cgrp); /* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt); return 0; }; int cgroup_rmdir(struct kernfs_node *kn) { struct cgroup *cgrp; int ret = 0; cgrp = cgroup_kn_lock_live(kn, false); if (!cgrp) return 0; ret = cgroup_destroy_locked(cgrp); if (!ret) TRACE_CGROUP_PATH(rmdir, cgrp); cgroup_kn_unlock(kn); return ret; } static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { .show_options = cgroup_show_options, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .show_path = cgroup_show_path, }; static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) { struct cgroup_subsys_state *css; pr_debug("Initializing cgroup subsys %s\n", ss->name); mutex_lock(&cgroup_mutex); idr_init(&ss->css_idr); INIT_LIST_HEAD(&ss->cfts); /* Create the root cgroup state for this subsystem */ ss->root = &cgrp_dfl_root; css = ss->css_alloc(NULL); /* We don't handle early failures gracefully */ BUG_ON(IS_ERR(css)); init_and_link_css(css, ss, &cgrp_dfl_root.cgrp); /* * Root csses are never destroyed and we can't initialize * percpu_ref during early init. Disable refcnting. */ css->flags |= CSS_NO_REF; if (early) { /* allocation can't be done safely during early init */ css->id = 1; } else { css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0); } /* Update the init_css_set to contain a subsys * pointer to this state - since the subsystem is * newly registered, all tasks and hence the * init_css_set is in the subsystem's root cgroup. */ init_css_set.subsys[ss->id] = css; have_fork_callback |= (bool)ss->fork << ss->id; have_exit_callback |= (bool)ss->exit << ss->id; have_release_callback |= (bool)ss->release << ss->id; have_canfork_callback |= (bool)ss->can_fork << ss->id; /* At system boot, before all subsystems have been * registered, no tasks have been forked, so we don't * need to invoke fork callbacks here. */ BUG_ON(!list_empty(&init_task.tasks)); BUG_ON(online_css(css)); mutex_unlock(&cgroup_mutex); } /** * cgroup_init_early - cgroup initialization at system boot * * Initialize cgroups at system boot, and initialize any * subsystems that request early init. */ int __init cgroup_init_early(void) { static struct cgroup_fs_context __initdata ctx; struct cgroup_subsys *ss; int i; ctx.root = &cgrp_dfl_root; init_cgroup_root(&ctx); cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF; RCU_INIT_POINTER(init_task.cgroups, &init_css_set); for_each_subsys(ss, i) { WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id, "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p id:name=%d:%s\n", i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free, ss->id, ss->name); WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN, "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]); ss->id = i; ss->name = cgroup_subsys_name[i]; if (!ss->legacy_name) ss->legacy_name = cgroup_subsys_name[i]; if (ss->early_init) cgroup_init_subsys(ss, true); } return 0; } /** * cgroup_init - cgroup initialization * * Register cgroup filesystem and /proc file, and initialize * any subsystems that didn't request early init. */ int __init cgroup_init(void) { struct cgroup_subsys *ss; int ssid; BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16); BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_psi_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files)); cgroup_rstat_boot(); get_user_ns(init_cgroup_ns.user_ns); mutex_lock(&cgroup_mutex); /* * Add init_css_set to the hash table so that dfl_root can link to * it during init. */ hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys)); BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0)); mutex_unlock(&cgroup_mutex); for_each_subsys(ss, ssid) { if (ss->early_init) { struct cgroup_subsys_state *css = init_css_set.subsys[ss->id]; css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0); } else { cgroup_init_subsys(ss, false); } list_add_tail(&init_css_set.e_cset_node[ssid], &cgrp_dfl_root.cgrp.e_csets[ssid]); /* * Setting dfl_root subsys_mask needs to consider the * disabled flag and cftype registration needs kmalloc, * both of which aren't available during early_init. */ if (!cgroup_ssid_enabled(ssid)) continue; if (cgroup1_ssid_disabled(ssid)) printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n", ss->name); cgrp_dfl_root.subsys_mask |= 1 << ss->id; /* implicit controllers must be threaded too */ WARN_ON(ss->implicit_on_dfl && !ss->threaded); if (ss->implicit_on_dfl) cgrp_dfl_implicit_ss_mask |= 1 << ss->id; else if (!ss->dfl_cftypes) cgrp_dfl_inhibit_ss_mask |= 1 << ss->id; if (ss->threaded) cgrp_dfl_threaded_ss_mask |= 1 << ss->id; if (ss->dfl_cftypes == ss->legacy_cftypes) { WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes)); } else { WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes)); WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes)); } if (ss->bind) ss->bind(init_css_set.subsys[ssid]); mutex_lock(&cgroup_mutex); css_populate_dir(init_css_set.subsys[ssid]); mutex_unlock(&cgroup_mutex); } /* init_css_set.subsys[] has been updated, re-hash */ hash_del(&init_css_set.hlist); hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys)); WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup")); WARN_ON(register_filesystem(&cgroup_fs_type)); WARN_ON(register_filesystem(&cgroup2_fs_type)); WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show)); #ifdef CONFIG_CPUSETS WARN_ON(register_filesystem(&cpuset_fs_type)); #endif return 0; } static int __init cgroup_wq_init(void) { /* * There isn't much point in executing destruction path in * parallel. Good chunk is serialized with cgroup_mutex anyway. * Use 1 for @max_active. * * We would prefer to do this in cgroup_init() above, but that * is called before init_workqueues(): so leave this until after. */ cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); BUG_ON(!cgroup_destroy_wq); return 0; } core_initcall(cgroup_wq_init); void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) { struct kernfs_node *kn; kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) return; kernfs_path(kn, buf, buflen); kernfs_put(kn); } /* * cgroup_get_from_id : get the cgroup associated with cgroup id * @id: cgroup id * On success return the cgrp or ERR_PTR on failure * Only cgroups within current task's cgroup NS are valid. */ struct cgroup *cgroup_get_from_id(u64 id) { struct kernfs_node *kn; struct cgroup *cgrp, *root_cgrp; kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) return ERR_PTR(-ENOENT); if (kernfs_type(kn) != KERNFS_DIR) { kernfs_put(kn); return ERR_PTR(-ENOENT); } rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (cgrp && !cgroup_tryget(cgrp)) cgrp = NULL; rcu_read_unlock(); kernfs_put(kn); if (!cgrp) return ERR_PTR(-ENOENT); root_cgrp = current_cgns_cgroup_dfl(); if (!cgroup_is_descendant(cgrp, root_cgrp)) { cgroup_put(cgrp); return ERR_PTR(-ENOENT); } return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_id); /* * proc_cgroup_show() * - Print task's cgroup paths into seq_file, one line for each hierarchy * - Used for /proc/<pid>/cgroup. */ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { char *buf; int retval; struct cgroup_root *root; retval = -ENOMEM; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; mutex_lock(&cgroup_mutex); spin_lock_irq(&css_set_lock); for_each_root(root) { struct cgroup_subsys *ss; struct cgroup *cgrp; int ssid, count = 0; if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible)) continue; seq_printf(m, "%d:", root->hierarchy_id); if (root != &cgrp_dfl_root) for_each_subsys(ss, ssid) if (root->subsys_mask & (1 << ssid)) seq_printf(m, "%s%s", count++ ? "," : "", ss->legacy_name); if (strlen(root->name)) seq_printf(m, "%sname=%s", count ? "," : "", root->name); seq_putc(m, ':'); cgrp = task_cgroup_from_root(tsk, root); /* * On traditional hierarchies, all zombie tasks show up as * belonging to the root cgroup. On the default hierarchy, * while a zombie doesn't show up in "cgroup.procs" and * thus can't be migrated, its /proc/PID/cgroup keeps * reporting the cgroup it belonged to before exiting. If * the cgroup is removed before the zombie is reaped, * " (deleted)" is appended to the cgroup path. */ if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) { retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX, current->nsproxy->cgroup_ns); if (retval >= PATH_MAX) retval = -ENAMETOOLONG; if (retval < 0) goto out_unlock; seq_puts(m, buf); } else { seq_puts(m, "/"); } if (cgroup_on_dfl(cgrp) && cgroup_is_dead(cgrp)) seq_puts(m, " (deleted)\n"); else seq_putc(m, '\n'); } retval = 0; out_unlock: spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); kfree(buf); out: return retval; } /** * cgroup_fork - initialize cgroup related fields during copy_process() * @child: pointer to task_struct of forking parent process. * * A task is associated with the init_css_set until cgroup_post_fork() * attaches it to the target css_set. */ void cgroup_fork(struct task_struct *child) { RCU_INIT_POINTER(child->cgroups, &init_css_set); INIT_LIST_HEAD(&child->cg_list); } /** * cgroup_v1v2_get_from_file - get a cgroup pointer from a file pointer * @f: file corresponding to cgroup_dir * * Find the cgroup from a file pointer associated with a cgroup directory. * Returns a pointer to the cgroup on success. ERR_PTR is returned if the * cgroup cannot be found. */ static struct cgroup *cgroup_v1v2_get_from_file(struct file *f) { struct cgroup_subsys_state *css; css = css_tryget_online_from_dir(f->f_path.dentry, NULL); if (IS_ERR(css)) return ERR_CAST(css); return css->cgroup; } /** * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports * cgroup2. * @f: file corresponding to cgroup2_dir */ static struct cgroup *cgroup_get_from_file(struct file *f) { struct cgroup *cgrp = cgroup_v1v2_get_from_file(f); if (IS_ERR(cgrp)) return ERR_CAST(cgrp); if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); } return cgrp; } /** * cgroup_css_set_fork - find or create a css_set for a child process * @kargs: the arguments passed to create the child process * * This functions finds or creates a new css_set which the child * process will be attached to in cgroup_post_fork(). By default, * the child process will be given the same css_set as its parent. * * If CLONE_INTO_CGROUP is specified this function will try to find an * existing css_set which includes the requested cgroup and if not create * a new css_set that the child will be attached to later. If this function * succeeds it will hold cgroup_threadgroup_rwsem on return. If * CLONE_INTO_CGROUP is requested this function will grab cgroup mutex * before grabbing cgroup_threadgroup_rwsem and will hold a reference * to the target cgroup. */ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) __acquires(&cgroup_mutex) __acquires(&cgroup_threadgroup_rwsem) { int ret; struct cgroup *dst_cgrp = NULL; struct css_set *cset; struct super_block *sb; struct file *f; if (kargs->flags & CLONE_INTO_CGROUP) mutex_lock(&cgroup_mutex); cgroup_threadgroup_change_begin(current); spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); spin_unlock_irq(&css_set_lock); if (!(kargs->flags & CLONE_INTO_CGROUP)) { kargs->cset = cset; return 0; } f = fget_raw(kargs->cgroup); if (!f) { ret = -EBADF; goto err; } sb = f->f_path.dentry->d_sb; dst_cgrp = cgroup_get_from_file(f); if (IS_ERR(dst_cgrp)) { ret = PTR_ERR(dst_cgrp); dst_cgrp = NULL; goto err; } if (cgroup_is_dead(dst_cgrp)) { ret = -ENODEV; goto err; } /* * Verify that we the target cgroup is writable for us. This is * usually done by the vfs layer but since we're not going through * the vfs layer here we need to do it "manually". */ ret = cgroup_may_write(dst_cgrp, sb); if (ret) goto err; /* * Spawning a task directly into a cgroup works by passing a file * descriptor to the target cgroup directory. This can even be an O_PATH * file descriptor. But it can never be a cgroup.procs file descriptor. * This was done on purpose so spawning into a cgroup could be * conceptualized as an atomic * * fd = openat(dfd_cgroup, "cgroup.procs", ...); * write(fd, <child-pid>, ...); * * sequence, i.e. it's a shorthand for the caller opening and writing * cgroup.procs of the cgroup indicated by @dfd_cgroup. This allows us * to always use the caller's credentials. */ ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb, !(kargs->flags & CLONE_THREAD), current->nsproxy->cgroup_ns); if (ret) goto err; kargs->cset = find_css_set(cset, dst_cgrp); if (!kargs->cset) { ret = -ENOMEM; goto err; } put_css_set(cset); fput(f); kargs->cgrp = dst_cgrp; return ret; err: cgroup_threadgroup_change_end(current); mutex_unlock(&cgroup_mutex); if (f) fput(f); if (dst_cgrp) cgroup_put(dst_cgrp); put_css_set(cset); if (kargs->cset) put_css_set(kargs->cset); return ret; } /** * cgroup_css_set_put_fork - drop references we took during fork * @kargs: the arguments passed to create the child process * * Drop references to the prepared css_set and target cgroup if * CLONE_INTO_CGROUP was requested. */ static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { cgroup_threadgroup_change_end(current); if (kargs->flags & CLONE_INTO_CGROUP) { struct cgroup *cgrp = kargs->cgrp; struct css_set *cset = kargs->cset; mutex_unlock(&cgroup_mutex); if (cset) { put_css_set(cset); kargs->cset = NULL; } if (cgrp) { cgroup_put(cgrp); kargs->cgrp = NULL; } } } /** * cgroup_can_fork - called on a new task before the process is exposed * @child: the child process * @kargs: the arguments passed to create the child process * * This prepares a new css_set for the child process which the child will * be attached to in cgroup_post_fork(). * This calls the subsystem can_fork() callbacks. If the cgroup_can_fork() * callback returns an error, the fork aborts with that error code. This * allows for a cgroup subsystem to conditionally allow or deny new forks. */ int cgroup_can_fork(struct task_struct *child, struct kernel_clone_args *kargs) { struct cgroup_subsys *ss; int i, j, ret; ret = cgroup_css_set_fork(kargs); if (ret) return ret; do_each_subsys_mask(ss, i, have_canfork_callback) { ret = ss->can_fork(child, kargs->cset); if (ret) goto out_revert; } while_each_subsys_mask(); return 0; out_revert: for_each_subsys(ss, j) { if (j >= i) break; if (ss->cancel_fork) ss->cancel_fork(child, kargs->cset); } cgroup_css_set_put_fork(kargs); return ret; } /** * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork() * @child: the child process * @kargs: the arguments passed to create the child process * * This calls the cancel_fork() callbacks if a fork failed *after* * cgroup_can_fork() succeeded and cleans up references we took to * prepare a new css_set for the child process in cgroup_can_fork(). */ void cgroup_cancel_fork(struct task_struct *child, struct kernel_clone_args *kargs) { struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) if (ss->cancel_fork) ss->cancel_fork(child, kargs->cset); cgroup_css_set_put_fork(kargs); } /** * cgroup_post_fork - finalize cgroup setup for the child process * @child: the child process * @kargs: the arguments passed to create the child process * * Attach the child process to its css_set calling the subsystem fork() * callbacks. */ void cgroup_post_fork(struct task_struct *child, struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { unsigned long cgrp_flags = 0; bool kill = false; struct cgroup_subsys *ss; struct css_set *cset; int i; cset = kargs->cset; kargs->cset = NULL; spin_lock_irq(&css_set_lock); /* init tasks are special, only link regular threads */ if (likely(child->pid)) { if (kargs->cgrp) cgrp_flags = kargs->cgrp->flags; else cgrp_flags = cset->dfl_cgrp->flags; WARN_ON_ONCE(!list_empty(&child->cg_list)); cset->nr_tasks++; css_set_move_task(child, NULL, cset, false); } else { put_css_set(cset); cset = NULL; } if (!(child->flags & PF_KTHREAD)) { if (unlikely(test_bit(CGRP_FREEZE, &cgrp_flags))) { /* * If the cgroup has to be frozen, the new task has * too. Let's set the JOBCTL_TRAP_FREEZE jobctl bit to * get the task into the frozen state. */ spin_lock(&child->sighand->siglock); WARN_ON_ONCE(child->frozen); child->jobctl |= JOBCTL_TRAP_FREEZE; spin_unlock(&child->sighand->siglock); /* * Calling cgroup_update_frozen() isn't required here, * because it will be called anyway a bit later from * do_freezer_trap(). So we avoid cgroup's transient * switch from the frozen state and back. */ } /* * If the cgroup is to be killed notice it now and take the * child down right after we finished preparing it for * userspace. */ kill = test_bit(CGRP_KILL, &cgrp_flags); } spin_unlock_irq(&css_set_lock); /* * Call ss->fork(). This must happen after @child is linked on * css_set; otherwise, @child might change state between ->fork() * and addition to css_set. */ do_each_subsys_mask(ss, i, have_fork_callback) { ss->fork(child); } while_each_subsys_mask(); /* Make the new cset the root_cset of the new cgroup namespace. */ if (kargs->flags & CLONE_NEWCGROUP) { struct css_set *rcset = child->nsproxy->cgroup_ns->root_cset; get_css_set(cset); child->nsproxy->cgroup_ns->root_cset = cset; put_css_set(rcset); } /* Cgroup has to be killed so take down child immediately. */ if (unlikely(kill)) do_send_sig_info(SIGKILL, SEND_SIG_NOINFO, child, PIDTYPE_TGID); cgroup_css_set_put_fork(kargs); } /** * cgroup_exit - detach cgroup from exiting task * @tsk: pointer to task_struct of exiting process * * Description: Detach cgroup from @tsk. * */ void cgroup_exit(struct task_struct *tsk) { struct cgroup_subsys *ss; struct css_set *cset; int i; spin_lock_irq(&css_set_lock); WARN_ON_ONCE(list_empty(&tsk->cg_list)); cset = task_css_set(tsk); css_set_move_task(tsk, cset, NULL, false); list_add_tail(&tsk->cg_list, &cset->dying_tasks); cset->nr_tasks--; WARN_ON_ONCE(cgroup_task_frozen(tsk)); if (unlikely(!(tsk->flags & PF_KTHREAD) && test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags))) cgroup_update_frozen(task_dfl_cgroup(tsk)); spin_unlock_irq(&css_set_lock); /* see cgroup_post_fork() for details */ do_each_subsys_mask(ss, i, have_exit_callback) { ss->exit(tsk); } while_each_subsys_mask(); } void cgroup_release(struct task_struct *task) { struct cgroup_subsys *ss; int ssid; do_each_subsys_mask(ss, ssid, have_release_callback) { ss->release(task); } while_each_subsys_mask(); spin_lock_irq(&css_set_lock); css_set_skip_task_iters(task_css_set(task), task); list_del_init(&task->cg_list); spin_unlock_irq(&css_set_lock); } void cgroup_free(struct task_struct *task) { struct css_set *cset = task_css_set(task); put_css_set(cset); } static int __init cgroup_disable(char *str) { struct cgroup_subsys *ss; char *token; int i; while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; for_each_subsys(ss, i) { if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; static_branch_disable(cgroup_subsys_enabled_key[i]); pr_info("Disabling %s control group subsystem\n", ss->name); } for (i = 0; i < OPT_FEATURE_COUNT; i++) { if (strcmp(token, cgroup_opt_feature_names[i])) continue; cgroup_feature_disable_mask |= 1 << i; pr_info("Disabling %s control group feature\n", cgroup_opt_feature_names[i]); break; } } return 1; } __setup("cgroup_disable=", cgroup_disable); void __init __weak enable_debug_cgroup(void) { } static int __init enable_cgroup_debug(char *str) { cgroup_debug = true; enable_debug_cgroup(); return 1; } __setup("cgroup_debug", enable_cgroup_debug); /** * css_tryget_online_from_dir - get corresponding css from a cgroup dentry * @dentry: directory dentry of interest * @ss: subsystem of interest * * If @dentry is a directory for a cgroup which has @ss enabled on it, try * to get the corresponding css and return it. If such css doesn't exist * or can't be pinned, an ERR_PTR value is returned. */ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss) { struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct file_system_type *s_type = dentry->d_sb->s_type; struct cgroup_subsys_state *css = NULL; struct cgroup *cgrp; /* is @dentry a cgroup dir? */ if ((s_type != &cgroup_fs_type && s_type != &cgroup2_fs_type) || !kn || kernfs_type(kn) != KERNFS_DIR) return ERR_PTR(-EBADF); rcu_read_lock(); /* * This path doesn't originate from kernfs and @kn could already * have been or be removed at any point. @kn->priv is RCU * protected for this access. See css_release_work_fn() for details. */ cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (cgrp) css = cgroup_css(cgrp, ss); if (!css || !css_tryget_online(css)) css = ERR_PTR(-ENOENT); rcu_read_unlock(); return css; } /** * css_from_id - lookup css by id * @id: the cgroup id * @ss: cgroup subsys to be looked into * * Returns the css if there's valid one with @id, otherwise returns NULL. * Should be called under rcu_read_lock(). */ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) { WARN_ON_ONCE(!rcu_read_lock_held()); return idr_find(&ss->css_idr, id); } /** * cgroup_get_from_path - lookup and get a cgroup from its default hierarchy path * @path: path on the default hierarchy * * Find the cgroup at @path on the default hierarchy, increment its * reference count and return it. Returns pointer to the found cgroup on * success, ERR_PTR(-ENOENT) if @path doesn't exist or if the cgroup has already * been released and ERR_PTR(-ENOTDIR) if @path points to a non-directory. */ struct cgroup *cgroup_get_from_path(const char *path) { struct kernfs_node *kn; struct cgroup *cgrp = ERR_PTR(-ENOENT); struct cgroup *root_cgrp; root_cgrp = current_cgns_cgroup_dfl(); kn = kernfs_walk_and_get(root_cgrp->kn, path); if (!kn) goto out; if (kernfs_type(kn) != KERNFS_DIR) { cgrp = ERR_PTR(-ENOTDIR); goto out_kernfs; } rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (!cgrp || !cgroup_tryget(cgrp)) cgrp = ERR_PTR(-ENOENT); rcu_read_unlock(); out_kernfs: kernfs_put(kn); out: return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_path); /** * cgroup_v1v2_get_from_fd - get a cgroup pointer from a fd * @fd: fd obtained by open(cgroup_dir) * * Find the cgroup from a fd which should be obtained * by opening a cgroup directory. Returns a pointer to the * cgroup on success. ERR_PTR is returned if the cgroup * cannot be found. */ struct cgroup *cgroup_v1v2_get_from_fd(int fd) { struct cgroup *cgrp; struct file *f; f = fget_raw(fd); if (!f) return ERR_PTR(-EBADF); cgrp = cgroup_v1v2_get_from_file(f); fput(f); return cgrp; } /** * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports * cgroup2. * @fd: fd obtained by open(cgroup2_dir) */ struct cgroup *cgroup_get_from_fd(int fd) { struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgrp)) return ERR_CAST(cgrp); if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); } return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_fd); static u64 power_of_ten(int power) { u64 v = 1; while (power--) v *= 10; return v; } /** * cgroup_parse_float - parse a floating number * @input: input string * @dec_shift: number of decimal digits to shift * @v: output * * Parse a decimal floating point number in @input and store the result in * @v with decimal point right shifted @dec_shift times. For example, if * @input is "12.3456" and @dec_shift is 3, *@v will be set to 12345. * Returns 0 on success, -errno otherwise. * * There's nothing cgroup specific about this function except that it's * currently the only user. */ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) { s64 whole, frac = 0; int fstart = 0, fend = 0, flen; if (!sscanf(input, "%lld.%n%lld%n", &whole, &fstart, &frac, &fend)) return -EINVAL; if (frac < 0) return -EINVAL; flen = fend > fstart ? fend - fstart : 0; if (flen < dec_shift) frac *= power_of_ten(dec_shift - flen); else frac = DIV_ROUND_CLOSEST_ULL(frac, power_of_ten(flen - dec_shift)); *v = whole * power_of_ten(dec_shift) + frac; return 0; } /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */ #ifdef CONFIG_SOCK_CGROUP_DATA void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { struct cgroup *cgroup; rcu_read_lock(); /* Don't associate the sock with unrelated interrupted task's cgroup. */ if (in_interrupt()) { cgroup = &cgrp_dfl_root.cgrp; cgroup_get(cgroup); goto out; } while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { cgroup = cset->dfl_cgrp; break; } cpu_relax(); } out: skcd->cgroup = cgroup; cgroup_bpf_get(cgroup); rcu_read_unlock(); } void cgroup_sk_clone(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); /* * We might be cloning a socket which is left in an empty * cgroup and the cgroup might have already been rmdir'd. * Don't use cgroup_get_live(). */ cgroup_get(cgrp); cgroup_bpf_get(cgrp); } void cgroup_sk_free(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); cgroup_bpf_put(cgrp); cgroup_put(cgrp); } #endif /* CONFIG_SOCK_CGROUP_DATA */ #ifdef CONFIG_SYSFS static ssize_t show_delegatable_files(struct cftype *files, char *buf, ssize_t size, const char *prefix) { struct cftype *cft; ssize_t ret = 0; for (cft = files; cft && cft->name[0] != '\0'; cft++) { if (!(cft->flags & CFTYPE_NS_DELEGATABLE)) continue; if (prefix) ret += snprintf(buf + ret, size - ret, "%s.", prefix); ret += snprintf(buf + ret, size - ret, "%s\n", cft->name); if (WARN_ON(ret >= size)) break; } return ret; } static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct cgroup_subsys *ss; int ssid; ssize_t ret = 0; ret = show_delegatable_files(cgroup_base_files, buf + ret, PAGE_SIZE - ret, NULL); if (cgroup_psi_enabled()) ret += show_delegatable_files(cgroup_psi_files, buf + ret, PAGE_SIZE - ret, NULL); for_each_subsys(ss, ssid) ret += show_delegatable_files(ss->dfl_cftypes, buf + ret, PAGE_SIZE - ret, cgroup_subsys_name[ssid]); return ret; } static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate); static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE, "nsdelegate\n" "favordynmods\n" "memory_localevents\n" "memory_recursiveprot\n"); } static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features); static struct attribute *cgroup_sysfs_attrs[] = { &cgroup_delegate_attr.attr, &cgroup_features_attr.attr, NULL, }; static const struct attribute_group cgroup_sysfs_attr_group = { .attrs = cgroup_sysfs_attrs, .name = "cgroup", }; static int __init cgroup_sysfs_init(void) { return sysfs_create_group(kernel_kobj, &cgroup_sysfs_attr_group); } subsys_initcall(cgroup_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 5424 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_KASAN_H #define _LINUX_KASAN_H #include <linux/bug.h> #include <linux/kasan-enabled.h> #include <linux/kernel.h> #include <linux/static_key.h> #include <linux/types.h> struct kmem_cache; struct page; struct slab; struct vm_struct; struct task_struct; #ifdef CONFIG_KASAN #include <linux/linkage.h> #include <asm/kasan.h> #endif typedef unsigned int __bitwise kasan_vmalloc_flags_t; #define KASAN_VMALLOC_NONE ((__force kasan_vmalloc_flags_t)0x00u) #define KASAN_VMALLOC_INIT ((__force kasan_vmalloc_flags_t)0x01u) #define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u) #define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u) #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) #include <linux/pgtable.h> /* Software KASAN implementations use shadow memory. */ #ifdef CONFIG_KASAN_SW_TAGS /* This matches KASAN_TAG_INVALID. */ #define KASAN_SHADOW_INIT 0xFE #else #define KASAN_SHADOW_INIT 0 #endif #ifndef PTE_HWTABLE_PTRS #define PTE_HWTABLE_PTRS 0 #endif extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; extern pte_t kasan_early_shadow_pte[MAX_PTRS_PER_PTE + PTE_HWTABLE_PTRS]; extern pmd_t kasan_early_shadow_pmd[MAX_PTRS_PER_PMD]; extern pud_t kasan_early_shadow_pud[MAX_PTRS_PER_PUD]; extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D]; int kasan_populate_early_shadow(const void *shadow_start, const void *shadow_end); static inline void *kasan_mem_to_shadow(const void *addr) { return (void *)((unsigned long)addr >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET; } int kasan_add_zero_shadow(void *start, unsigned long size); void kasan_remove_zero_shadow(void *start, unsigned long size); /* Enable reporting bugs after kasan_disable_current() */ extern void kasan_enable_current(void); /* Disable reporting bugs for current task */ extern void kasan_disable_current(void); #else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ static inline int kasan_add_zero_shadow(void *start, unsigned long size) { return 0; } static inline void kasan_remove_zero_shadow(void *start, unsigned long size) {} static inline void kasan_enable_current(void) {} static inline void kasan_disable_current(void) {} #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ #ifdef CONFIG_KASAN_HW_TAGS #else /* CONFIG_KASAN_HW_TAGS */ #endif /* CONFIG_KASAN_HW_TAGS */ static inline bool kasan_has_integrated_init(void) { return kasan_hw_tags_enabled(); } #ifdef CONFIG_KASAN struct kasan_cache { #ifdef CONFIG_KASAN_GENERIC int alloc_meta_offset; int free_meta_offset; #endif bool is_kmalloc; }; void __kasan_unpoison_range(const void *addr, size_t size); static __always_inline void kasan_unpoison_range(const void *addr, size_t size) { if (kasan_enabled()) __kasan_unpoison_range(addr, size); } void __kasan_poison_pages(struct page *page, unsigned int order, bool init); static __always_inline void kasan_poison_pages(struct page *page, unsigned int order, bool init) { if (kasan_enabled()) __kasan_poison_pages(page, order, init); } void __kasan_unpoison_pages(struct page *page, unsigned int order, bool init); static __always_inline void kasan_unpoison_pages(struct page *page, unsigned int order, bool init) { if (kasan_enabled()) __kasan_unpoison_pages(page, order, init); } void __kasan_cache_create_kmalloc(struct kmem_cache *cache); static __always_inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) { if (kasan_enabled()) __kasan_cache_create_kmalloc(cache); } void __kasan_poison_slab(struct slab *slab); static __always_inline void kasan_poison_slab(struct slab *slab) { if (kasan_enabled()) __kasan_poison_slab(slab); } void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object); static __always_inline void kasan_unpoison_object_data(struct kmem_cache *cache, void *object) { if (kasan_enabled()) __kasan_unpoison_object_data(cache, object); } void __kasan_poison_object_data(struct kmem_cache *cache, void *object); static __always_inline void kasan_poison_object_data(struct kmem_cache *cache, void *object) { if (kasan_enabled()) __kasan_poison_object_data(cache, object); } void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache, const void *object); static __always_inline void * __must_check kasan_init_slab_obj( struct kmem_cache *cache, const void *object) { if (kasan_enabled()) return __kasan_init_slab_obj(cache, object); return (void *)object; } bool __kasan_slab_free(struct kmem_cache *s, void *object, unsigned long ip, bool init); static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init) { if (kasan_enabled()) return __kasan_slab_free(s, object, _RET_IP_, init); return false; } void __kasan_kfree_large(void *ptr, unsigned long ip); static __always_inline void kasan_kfree_large(void *ptr) { if (kasan_enabled()) __kasan_kfree_large(ptr, _RET_IP_); } void __kasan_slab_free_mempool(void *ptr, unsigned long ip); static __always_inline void kasan_slab_free_mempool(void *ptr) { if (kasan_enabled()) __kasan_slab_free_mempool(ptr, _RET_IP_); } void * __must_check __kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags, bool init); static __always_inline void * __must_check kasan_slab_alloc( struct kmem_cache *s, void *object, gfp_t flags, bool init) { if (kasan_enabled()) return __kasan_slab_alloc(s, object, flags, init); return object; } void * __must_check __kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size, gfp_t flags); static __always_inline void * __must_check kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size, gfp_t flags) { if (kasan_enabled()) return __kasan_kmalloc(s, object, size, flags); return (void *)object; } void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags); static __always_inline void * __must_check kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags) { if (kasan_enabled()) return __kasan_kmalloc_large(ptr, size, flags); return (void *)ptr; } void * __must_check __kasan_krealloc(const void *object, size_t new_size, gfp_t flags); static __always_inline void * __must_check kasan_krealloc(const void *object, size_t new_size, gfp_t flags) { if (kasan_enabled()) return __kasan_krealloc(object, new_size, flags); return (void *)object; } /* * Unlike kasan_check_read/write(), kasan_check_byte() is performed even for * the hardware tag-based mode that doesn't rely on compiler instrumentation. */ bool __kasan_check_byte(const void *addr, unsigned long ip); static __always_inline bool kasan_check_byte(const void *addr) { if (kasan_enabled()) return __kasan_check_byte(addr, _RET_IP_); return true; } #else /* CONFIG_KASAN */ static inline void kasan_unpoison_range(const void *address, size_t size) {} static inline void kasan_poison_pages(struct page *page, unsigned int order, bool init) {} static inline void kasan_unpoison_pages(struct page *page, unsigned int order, bool init) {} static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {} static inline void kasan_poison_slab(struct slab *slab) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, void *object) {} static inline void kasan_poison_object_data(struct kmem_cache *cache, void *object) {} static inline void *kasan_init_slab_obj(struct kmem_cache *cache, const void *object) { return (void *)object; } static inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init) { return false; } static inline void kasan_kfree_large(void *ptr) {} static inline void kasan_slab_free_mempool(void *ptr) {} static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags, bool init) { return object; } static inline void *kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size, gfp_t flags) { return (void *)object; } static inline void *kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags) { return (void *)ptr; } static inline void *kasan_krealloc(const void *object, size_t new_size, gfp_t flags) { return (void *)object; } static inline bool kasan_check_byte(const void *address) { return true; } #endif /* CONFIG_KASAN */ #if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) void kasan_unpoison_task_stack(struct task_struct *task); #else static inline void kasan_unpoison_task_stack(struct task_struct *task) {} #endif #ifdef CONFIG_KASAN_GENERIC size_t kasan_metadata_size(struct kmem_cache *cache); slab_flags_t kasan_never_merge(void); void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, slab_flags_t *flags); void kasan_cache_shrink(struct kmem_cache *cache); void kasan_cache_shutdown(struct kmem_cache *cache); void kasan_record_aux_stack(void *ptr); void kasan_record_aux_stack_noalloc(void *ptr); #else /* CONFIG_KASAN_GENERIC */ /* Tag-based KASAN modes do not use per-object metadata. */ static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } /* And thus nothing prevents cache merging. */ static inline slab_flags_t kasan_never_merge(void) { return 0; } /* And no cache-related metadata initialization is required. */ static inline void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, slab_flags_t *flags) {} static inline void kasan_cache_shrink(struct kmem_cache *cache) {} static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} static inline void kasan_record_aux_stack(void *ptr) {} static inline void kasan_record_aux_stack_noalloc(void *ptr) {} #endif /* CONFIG_KASAN_GENERIC */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) static inline void *kasan_reset_tag(const void *addr) { return (void *)arch_kasan_reset_tag(addr); } /** * kasan_report - print a report about a bad memory access detected by KASAN * @addr: address of the bad access * @size: size of the bad access * @is_write: whether the bad access is a write or a read * @ip: instruction pointer for the accessibility check or the bad access itself */ bool kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip); #else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline void *kasan_reset_tag(const void *addr) { return (void *)addr; } #endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS*/ #ifdef CONFIG_KASAN_HW_TAGS void kasan_report_async(void); #endif /* CONFIG_KASAN_HW_TAGS */ #ifdef CONFIG_KASAN_SW_TAGS void __init kasan_init_sw_tags(void); #else static inline void kasan_init_sw_tags(void) { } #endif #ifdef CONFIG_KASAN_HW_TAGS void kasan_init_hw_tags_cpu(void); void __init kasan_init_hw_tags(void); #else static inline void kasan_init_hw_tags_cpu(void) { } static inline void kasan_init_hw_tags(void) { } #endif #ifdef CONFIG_KASAN_VMALLOC #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); int kasan_populate_vmalloc(unsigned long addr, unsigned long size); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end); #else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, unsigned long size) { return 0; } static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end) { } #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, kasan_vmalloc_flags_t flags); static __always_inline void *kasan_unpoison_vmalloc(const void *start, unsigned long size, kasan_vmalloc_flags_t flags) { if (kasan_enabled()) return __kasan_unpoison_vmalloc(start, size, flags); return (void *)start; } void __kasan_poison_vmalloc(const void *start, unsigned long size); static __always_inline void kasan_poison_vmalloc(const void *start, unsigned long size) { if (kasan_enabled()) __kasan_poison_vmalloc(start, size); } #else /* CONFIG_KASAN_VMALLOC */ static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, unsigned long size) { return 0; } static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end) { } static inline void *kasan_unpoison_vmalloc(const void *start, unsigned long size, kasan_vmalloc_flags_t flags) { return (void *)start; } static inline void kasan_poison_vmalloc(const void *start, unsigned long size) { } #endif /* CONFIG_KASAN_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) /* * These functions allocate and free shadow memory for kernel modules. * They are only required when KASAN_VMALLOC is not supported, as otherwise * shadow memory is allocated by the generic vmalloc handlers. */ int kasan_alloc_module_shadow(void *addr, size_t size, gfp_t gfp_mask); void kasan_free_module_shadow(const struct vm_struct *vm); #else /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ static inline int kasan_alloc_module_shadow(void *addr, size_t size, gfp_t gfp_mask) { return 0; } static inline void kasan_free_module_shadow(const struct vm_struct *vm) {} #endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ #ifdef CONFIG_KASAN_INLINE void kasan_non_canonical_hook(unsigned long addr); #else /* CONFIG_KASAN_INLINE */ static inline void kasan_non_canonical_hook(unsigned long addr) { } #endif /* CONFIG_KASAN_INLINE */ #endif /* LINUX_KASAN_H */ |
| 1 1 1 1 1 2 2 2 2 2 2 2 14 4 10 9 9 9 9 9 14 1620 1620 1619 1618 1618 1618 1618 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 | // SPDX-License-Identifier: GPL-2.0-only /* * xfrm_state.c * * Changes: * Mitsuru KANDA @USAGI * Kazunori MIYAZAWA @USAGI * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * IPv6 support * YOSHIFUJI Hideaki @USAGI * Split up af-specific functions * Derek Atkins <derek@ihtfp.com> * Add UDP Encapsulation * */ #include <linux/compat.h> #include <linux/workqueue.h> #include <net/xfrm.h> #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <linux/module.h> #include <linux/cache.h> #include <linux/audit.h> #include <linux/uaccess.h> #include <linux/ktime.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <crypto/aead.h> #include "xfrm_hash.h" #define xfrm_state_deref_prot(table, net) \ rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock)) static void xfrm_state_gc_task(struct work_struct *work); /* Each xfrm_state may be linked to two tables: 1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl) 2. Hash table by (daddr,family,reqid) to find what SAs exist for given destination/tunnel endpoint. (output) */ static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; static struct kmem_cache *xfrm_state_cache __ro_after_init; static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); static HLIST_HEAD(xfrm_state_gc_list); static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x) { return refcount_inc_not_zero(&x->refcnt); } static inline unsigned int xfrm_dst_hash(struct net *net, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u32 reqid, unsigned short family) { return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask); } static inline unsigned int xfrm_src_hash(struct net *net, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask); } static inline unsigned int xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask); } static unsigned int xfrm_seq_hash(struct net *net, u32 seq) { return __xfrm_seq_hash(seq, net->xfrm.state_hmask); } static void xfrm_hash_transfer(struct hlist_head *list, struct hlist_head *ndsttable, struct hlist_head *nsrctable, struct hlist_head *nspitable, struct hlist_head *nseqtable, unsigned int nhashmask) { struct hlist_node *tmp; struct xfrm_state *x; hlist_for_each_entry_safe(x, tmp, list, bydst) { unsigned int h; h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family, nhashmask); hlist_add_head_rcu(&x->bydst, ndsttable + h); h = __xfrm_src_hash(&x->id.daddr, &x->props.saddr, x->props.family, nhashmask); hlist_add_head_rcu(&x->bysrc, nsrctable + h); if (x->id.spi) { h = __xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, x->props.family, nhashmask); hlist_add_head_rcu(&x->byspi, nspitable + h); } if (x->km.seq) { h = __xfrm_seq_hash(x->km.seq, nhashmask); hlist_add_head_rcu(&x->byseq, nseqtable + h); } } } static unsigned long xfrm_hash_new_size(unsigned int state_hmask) { return ((state_hmask + 1) << 1) * sizeof(struct hlist_head); } static void xfrm_hash_resize(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.state_hash_work); struct hlist_head *ndst, *nsrc, *nspi, *nseq, *odst, *osrc, *ospi, *oseq; unsigned long nsize, osize; unsigned int nhashmask, ohashmask; int i; nsize = xfrm_hash_new_size(net->xfrm.state_hmask); ndst = xfrm_hash_alloc(nsize); if (!ndst) return; nsrc = xfrm_hash_alloc(nsize); if (!nsrc) { xfrm_hash_free(ndst, nsize); return; } nspi = xfrm_hash_alloc(nsize); if (!nspi) { xfrm_hash_free(ndst, nsize); xfrm_hash_free(nsrc, nsize); return; } nseq = xfrm_hash_alloc(nsize); if (!nseq) { xfrm_hash_free(ndst, nsize); xfrm_hash_free(nsrc, nsize); xfrm_hash_free(nspi, nsize); return; } spin_lock_bh(&net->xfrm.xfrm_state_lock); write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net); for (i = net->xfrm.state_hmask; i >= 0; i--) xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nseq, nhashmask); osrc = xfrm_state_deref_prot(net->xfrm.state_bysrc, net); ospi = xfrm_state_deref_prot(net->xfrm.state_byspi, net); oseq = xfrm_state_deref_prot(net->xfrm.state_byseq, net); ohashmask = net->xfrm.state_hmask; rcu_assign_pointer(net->xfrm.state_bydst, ndst); rcu_assign_pointer(net->xfrm.state_bysrc, nsrc); rcu_assign_pointer(net->xfrm.state_byspi, nspi); rcu_assign_pointer(net->xfrm.state_byseq, nseq); net->xfrm.state_hmask = nhashmask; write_seqcount_end(&net->xfrm.xfrm_state_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_state_lock); osize = (ohashmask + 1) * sizeof(struct hlist_head); synchronize_rcu(); xfrm_hash_free(odst, osize); xfrm_hash_free(osrc, osize); xfrm_hash_free(ospi, osize); xfrm_hash_free(oseq, osize); } static DEFINE_SPINLOCK(xfrm_state_afinfo_lock); static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO]; static DEFINE_SPINLOCK(xfrm_state_gc_lock); int __xfrm_state_delete(struct xfrm_state *x); int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); static bool km_is_alive(const struct km_event *c); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); int xfrm_register_type(const struct xfrm_type *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); int err = 0; if (!afinfo) return -EAFNOSUPPORT; #define X(afi, T, name) do { \ WARN_ON((afi)->type_ ## name); \ (afi)->type_ ## name = (T); \ } while (0) switch (type->proto) { case IPPROTO_COMP: X(afinfo, type, comp); break; case IPPROTO_AH: X(afinfo, type, ah); break; case IPPROTO_ESP: X(afinfo, type, esp); break; case IPPROTO_IPIP: X(afinfo, type, ipip); break; case IPPROTO_DSTOPTS: X(afinfo, type, dstopts); break; case IPPROTO_ROUTING: X(afinfo, type, routing); break; case IPPROTO_IPV6: X(afinfo, type, ipip6); break; default: WARN_ON(1); err = -EPROTONOSUPPORT; break; } #undef X rcu_read_unlock(); return err; } EXPORT_SYMBOL(xfrm_register_type); void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return; #define X(afi, T, name) do { \ WARN_ON((afi)->type_ ## name != (T)); \ (afi)->type_ ## name = NULL; \ } while (0) switch (type->proto) { case IPPROTO_COMP: X(afinfo, type, comp); break; case IPPROTO_AH: X(afinfo, type, ah); break; case IPPROTO_ESP: X(afinfo, type, esp); break; case IPPROTO_IPIP: X(afinfo, type, ipip); break; case IPPROTO_DSTOPTS: X(afinfo, type, dstopts); break; case IPPROTO_ROUTING: X(afinfo, type, routing); break; case IPPROTO_IPV6: X(afinfo, type, ipip6); break; default: WARN_ON(1); break; } #undef X rcu_read_unlock(); } EXPORT_SYMBOL(xfrm_unregister_type); static const struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family) { const struct xfrm_type *type = NULL; struct xfrm_state_afinfo *afinfo; int modload_attempted = 0; retry: afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return NULL; switch (proto) { case IPPROTO_COMP: type = afinfo->type_comp; break; case IPPROTO_AH: type = afinfo->type_ah; break; case IPPROTO_ESP: type = afinfo->type_esp; break; case IPPROTO_IPIP: type = afinfo->type_ipip; break; case IPPROTO_DSTOPTS: type = afinfo->type_dstopts; break; case IPPROTO_ROUTING: type = afinfo->type_routing; break; case IPPROTO_IPV6: type = afinfo->type_ipip6; break; default: break; } if (unlikely(type && !try_module_get(type->owner))) type = NULL; rcu_read_unlock(); if (!type && !modload_attempted) { request_module("xfrm-type-%d-%d", family, proto); modload_attempted = 1; goto retry; } return type; } static void xfrm_put_type(const struct xfrm_type *type) { module_put(type->owner); } int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); int err = 0; if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; switch (type->proto) { case IPPROTO_ESP: WARN_ON(afinfo->type_offload_esp); afinfo->type_offload_esp = type; break; default: WARN_ON(1); err = -EPROTONOSUPPORT; break; } rcu_read_unlock(); return err; } EXPORT_SYMBOL(xfrm_register_type_offload); void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return; switch (type->proto) { case IPPROTO_ESP: WARN_ON(afinfo->type_offload_esp != type); afinfo->type_offload_esp = NULL; break; default: WARN_ON(1); break; } rcu_read_unlock(); } EXPORT_SYMBOL(xfrm_unregister_type_offload); static const struct xfrm_type_offload * xfrm_get_type_offload(u8 proto, unsigned short family, bool try_load) { const struct xfrm_type_offload *type = NULL; struct xfrm_state_afinfo *afinfo; retry: afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return NULL; switch (proto) { case IPPROTO_ESP: type = afinfo->type_offload_esp; break; default: break; } if ((type && !try_module_get(type->owner))) type = NULL; rcu_read_unlock(); if (!type && try_load) { request_module("xfrm-offload-%d-%d", family, proto); try_load = false; goto retry; } return type; } static void xfrm_put_type_offload(const struct xfrm_type_offload *type) { module_put(type->owner); } static const struct xfrm_mode xfrm4_mode_map[XFRM_MODE_MAX] = { [XFRM_MODE_BEET] = { .encap = XFRM_MODE_BEET, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET, }, [XFRM_MODE_TRANSPORT] = { .encap = XFRM_MODE_TRANSPORT, .family = AF_INET, }, [XFRM_MODE_TUNNEL] = { .encap = XFRM_MODE_TUNNEL, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET, }, }; static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = { [XFRM_MODE_BEET] = { .encap = XFRM_MODE_BEET, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET6, }, [XFRM_MODE_ROUTEOPTIMIZATION] = { .encap = XFRM_MODE_ROUTEOPTIMIZATION, .family = AF_INET6, }, [XFRM_MODE_TRANSPORT] = { .encap = XFRM_MODE_TRANSPORT, .family = AF_INET6, }, [XFRM_MODE_TUNNEL] = { .encap = XFRM_MODE_TUNNEL, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET6, }, }; static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family) { const struct xfrm_mode *mode; if (unlikely(encap >= XFRM_MODE_MAX)) return NULL; switch (family) { case AF_INET: mode = &xfrm4_mode_map[encap]; if (mode->family == family) return mode; break; case AF_INET6: mode = &xfrm6_mode_map[encap]; if (mode->family == family) return mode; break; default: break; } return NULL; } void xfrm_state_free(struct xfrm_state *x) { kmem_cache_free(xfrm_state_cache, x); } EXPORT_SYMBOL(xfrm_state_free); static void ___xfrm_state_destroy(struct xfrm_state *x) { hrtimer_cancel(&x->mtimer); del_timer_sync(&x->rtimer); kfree(x->aead); kfree(x->aalg); kfree(x->ealg); kfree(x->calg); kfree(x->encap); kfree(x->coaddr); kfree(x->replay_esn); kfree(x->preplay_esn); if (x->type_offload) xfrm_put_type_offload(x->type_offload); if (x->type) { x->type->destructor(x); xfrm_put_type(x->type); } if (x->xfrag.page) put_page(x->xfrag.page); xfrm_dev_state_free(x); security_xfrm_state_free(x); xfrm_state_free(x); } static void xfrm_state_gc_task(struct work_struct *work) { struct xfrm_state *x; struct hlist_node *tmp; struct hlist_head gc_list; spin_lock_bh(&xfrm_state_gc_lock); hlist_move_list(&xfrm_state_gc_list, &gc_list); spin_unlock_bh(&xfrm_state_gc_lock); synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) ___xfrm_state_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) { struct xfrm_state *x = container_of(me, struct xfrm_state, mtimer); enum hrtimer_restart ret = HRTIMER_NORESTART; time64_t now = ktime_get_real_seconds(); time64_t next = TIME64_MAX; int warn = 0; int err = 0; spin_lock(&x->lock); if (x->km.state == XFRM_STATE_DEAD) goto out; if (x->km.state == XFRM_STATE_EXPIRED) goto expired; if (x->lft.hard_add_expires_seconds) { long tmo = x->lft.hard_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { if (x->xflags & XFRM_SOFT_EXPIRE) { /* enter hard expire without soft expire first?! * setting a new date could trigger this. * workaround: fix x->curflt.add_time by below: */ x->curlft.add_time = now - x->saved_tmo - 1; tmo = x->lft.hard_add_expires_seconds - x->saved_tmo; } else goto expired; } if (tmo < next) next = tmo; } if (x->lft.hard_use_expires_seconds) { long tmo = x->lft.hard_use_expires_seconds + (x->curlft.use_time ? : now) - now; if (tmo <= 0) goto expired; if (tmo < next) next = tmo; } if (x->km.dying) goto resched; if (x->lft.soft_add_expires_seconds) { long tmo = x->lft.soft_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { warn = 1; x->xflags &= ~XFRM_SOFT_EXPIRE; } else if (tmo < next) { next = tmo; x->xflags |= XFRM_SOFT_EXPIRE; x->saved_tmo = tmo; } } if (x->lft.soft_use_expires_seconds) { long tmo = x->lft.soft_use_expires_seconds + (x->curlft.use_time ? : now) - now; if (tmo <= 0) warn = 1; else if (tmo < next) next = tmo; } x->km.dying = warn; if (warn) km_state_expired(x, 0, 0); resched: if (next != TIME64_MAX) { hrtimer_forward_now(&x->mtimer, ktime_set(next, 0)); ret = HRTIMER_RESTART; } goto out; expired: if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) x->km.state = XFRM_STATE_EXPIRED; err = __xfrm_state_delete(x); if (!err) km_state_expired(x, 1, 0); xfrm_audit_state_delete(x, err ? 0 : 1, true); out: spin_unlock(&x->lock); return ret; } static void xfrm_replay_timer_handler(struct timer_list *t); struct xfrm_state *xfrm_state_alloc(struct net *net) { struct xfrm_state *x; x = kmem_cache_zalloc(xfrm_state_cache, GFP_ATOMIC); if (x) { write_pnet(&x->xs_net, net); refcount_set(&x->refcnt, 1); atomic_set(&x->tunnel_users, 0); INIT_LIST_HEAD(&x->km.all); INIT_HLIST_NODE(&x->bydst); INIT_HLIST_NODE(&x->bysrc); INIT_HLIST_NODE(&x->byspi); INIT_HLIST_NODE(&x->byseq); hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT); x->mtimer.function = xfrm_timer_handler; timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0); x->curlft.add_time = ktime_get_real_seconds(); x->lft.soft_byte_limit = XFRM_INF; x->lft.soft_packet_limit = XFRM_INF; x->lft.hard_byte_limit = XFRM_INF; x->lft.hard_packet_limit = XFRM_INF; x->replay_maxage = 0; x->replay_maxdiff = 0; spin_lock_init(&x->lock); } return x; } EXPORT_SYMBOL(xfrm_state_alloc); void __xfrm_state_destroy(struct xfrm_state *x, bool sync) { WARN_ON(x->km.state != XFRM_STATE_DEAD); if (sync) { synchronize_rcu(); ___xfrm_state_destroy(x); } else { spin_lock_bh(&xfrm_state_gc_lock); hlist_add_head(&x->gclist, &xfrm_state_gc_list); spin_unlock_bh(&xfrm_state_gc_lock); schedule_work(&xfrm_state_gc_work); } } EXPORT_SYMBOL(__xfrm_state_destroy); int __xfrm_state_delete(struct xfrm_state *x) { struct net *net = xs_net(x); int err = -ESRCH; if (x->km.state != XFRM_STATE_DEAD) { x->km.state = XFRM_STATE_DEAD; spin_lock(&net->xfrm.xfrm_state_lock); list_del(&x->km.all); hlist_del_rcu(&x->bydst); hlist_del_rcu(&x->bysrc); if (x->km.seq) hlist_del_rcu(&x->byseq); if (x->id.spi) hlist_del_rcu(&x->byspi); net->xfrm.state_num--; spin_unlock(&net->xfrm.xfrm_state_lock); if (x->encap_sk) sock_put(rcu_dereference_raw(x->encap_sk)); xfrm_dev_state_delete(x); /* All xfrm_state objects are created by xfrm_state_alloc. * The xfrm_state_alloc call gives a reference, and that * is what we are dropping here. */ xfrm_state_put(x); err = 0; } return err; } EXPORT_SYMBOL(__xfrm_state_delete); int xfrm_state_delete(struct xfrm_state *x) { int err; spin_lock_bh(&x->lock); err = __xfrm_state_delete(x); spin_unlock_bh(&x->lock); return err; } EXPORT_SYMBOL(xfrm_state_delete); #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) { int i, err = 0; for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { if (xfrm_id_proto_match(x->id.proto, proto) && (err = security_xfrm_state_delete(x)) != 0) { xfrm_audit_state_delete(x, 0, task_valid); return err; } } } return err; } static inline int xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) { int i, err = 0; for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; struct xfrm_dev_offload *xso; hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { xso = &x->xso; if (xso->dev == dev && (err = security_xfrm_state_delete(x)) != 0) { xfrm_audit_state_delete(x, 0, task_valid); return err; } } } return err; } #else static inline int xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) { return 0; } static inline int xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) { return 0; } #endif int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) { int i, err = 0, cnt = 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_flush_secctx_check(net, proto, task_valid); if (err) goto out; err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; restart: hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { if (!xfrm_state_kern(x) && xfrm_id_proto_match(x->id.proto, proto)) { xfrm_state_hold(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); if (sync) xfrm_state_put_sync(x); else xfrm_state_put(x); if (!err) cnt++; spin_lock_bh(&net->xfrm.xfrm_state_lock); goto restart; } } } out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (cnt) err = 0; return err; } EXPORT_SYMBOL(xfrm_state_flush); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid) { int i, err = 0, cnt = 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_dev_state_flush_secctx_check(net, dev, task_valid); if (err) goto out; err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; struct xfrm_dev_offload *xso; restart: hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { xso = &x->xso; if (!xfrm_state_kern(x) && xso->dev == dev) { xfrm_state_hold(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); xfrm_state_put(x); if (!err) cnt++; spin_lock_bh(&net->xfrm.xfrm_state_lock); goto restart; } } } if (cnt) err = 0; out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); return err; } EXPORT_SYMBOL(xfrm_dev_state_flush); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { spin_lock_bh(&net->xfrm.xfrm_state_lock); si->sadcnt = net->xfrm.state_num; si->sadhcnt = net->xfrm.state_hmask + 1; si->sadhmcnt = xfrm_state_hashmax; spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_sad_getinfo); static void __xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi4 *fl4 = &fl->u.ip4; sel->daddr.a4 = fl4->daddr; sel->saddr.a4 = fl4->saddr; sel->dport = xfrm_flowi_dport(fl, &fl4->uli); sel->dport_mask = htons(0xffff); sel->sport = xfrm_flowi_sport(fl, &fl4->uli); sel->sport_mask = htons(0xffff); sel->family = AF_INET; sel->prefixlen_d = 32; sel->prefixlen_s = 32; sel->proto = fl4->flowi4_proto; sel->ifindex = fl4->flowi4_oif; } static void __xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi6 *fl6 = &fl->u.ip6; /* Initialize temporary selector matching only to current session. */ *(struct in6_addr *)&sel->daddr = fl6->daddr; *(struct in6_addr *)&sel->saddr = fl6->saddr; sel->dport = xfrm_flowi_dport(fl, &fl6->uli); sel->dport_mask = htons(0xffff); sel->sport = xfrm_flowi_sport(fl, &fl6->uli); sel->sport_mask = htons(0xffff); sel->family = AF_INET6; sel->prefixlen_d = 128; sel->prefixlen_s = 128; sel->proto = fl6->flowi6_proto; sel->ifindex = fl6->flowi6_oif; } static void xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl, const struct xfrm_tmpl *tmpl, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { switch (family) { case AF_INET: __xfrm4_init_tempsel(&x->sel, fl); break; case AF_INET6: __xfrm6_init_tempsel(&x->sel, fl); break; } x->id = tmpl->id; switch (tmpl->encap_family) { case AF_INET: if (x->id.daddr.a4 == 0) x->id.daddr.a4 = daddr->a4; x->props.saddr = tmpl->saddr; if (x->props.saddr.a4 == 0) x->props.saddr.a4 = saddr->a4; break; case AF_INET6: if (ipv6_addr_any((struct in6_addr *)&x->id.daddr)) memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr)); memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr)); if (ipv6_addr_any((struct in6_addr *)&x->props.saddr)) memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr)); break; } x->props.mode = tmpl->mode; x->props.reqid = tmpl->reqid; x->props.family = tmpl->encap_family; } static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family); struct xfrm_state *x; hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) { if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) continue; if (!xfrm_state_hold_rcu(x)) continue; return x; } return NULL; } static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family) { unsigned int h = xfrm_src_hash(net, daddr, saddr, family); struct xfrm_state *x; hlist_for_each_entry_rcu(x, net->xfrm.state_bysrc + h, bysrc) { if (x->props.family != family || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family) || !xfrm_addr_equal(&x->props.saddr, saddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) continue; if (!xfrm_state_hold_rcu(x)) continue; return x; } return NULL; } static inline struct xfrm_state * __xfrm_state_locate(struct xfrm_state *x, int use_spi, int family) { struct net *net = xs_net(x); u32 mark = x->mark.v & x->mark.m; if (use_spi) return __xfrm_state_lookup(net, mark, &x->id.daddr, x->id.spi, x->id.proto, family); else return __xfrm_state_lookup_byaddr(net, mark, &x->id.daddr, &x->props.saddr, x->id.proto, family); } static void xfrm_hash_grow_check(struct net *net, int have_hash_collision) { if (have_hash_collision && (net->xfrm.state_hmask + 1) < xfrm_state_hashmax && net->xfrm.state_num > net->xfrm.state_hmask) schedule_work(&net->xfrm.state_hash_work); } static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, const struct flowi *fl, unsigned short family, struct xfrm_state **best, int *acq_in_progress, int *error) { /* Resolution logic: * 1. There is a valid state with matching selector. Done. * 2. Valid state with inappropriate selector. Skip. * * Entering area of "sysdeps". * * 3. If state is not valid, selector is temporary, it selects * only session which triggered previous resolution. Key * manager will do something to install a state with proper * selector. */ if (x->km.state == XFRM_STATE_VALID) { if ((x->sel.family && (x->sel.family != family || !xfrm_selector_match(&x->sel, fl, family))) || !security_xfrm_state_pol_flow_match(x, pol, &fl->u.__fl_common)) return; if (!*best || (*best)->km.dying > x->km.dying || ((*best)->km.dying == x->km.dying && (*best)->curlft.add_time < x->curlft.add_time)) *best = x; } else if (x->km.state == XFRM_STATE_ACQ) { *acq_in_progress = 1; } else if (x->km.state == XFRM_STATE_ERROR || x->km.state == XFRM_STATE_EXPIRED) { if ((!x->sel.family || (x->sel.family == family && xfrm_selector_match(&x->sel, fl, family))) && security_xfrm_state_pol_flow_match(x, pol, &fl->u.__fl_common)) *error = -ESRCH; } } struct xfrm_state * xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family, u32 if_id) { static xfrm_address_t saddr_wildcard = { }; struct net *net = xp_net(pol); unsigned int h, h_wildcard; struct xfrm_state *x, *x0, *to_put; int acquire_in_progress = 0; int error = 0; struct xfrm_state *best = NULL; u32 mark = pol->mark.v & pol->mark.m; unsigned short encap_family = tmpl->encap_family; unsigned int sequence; struct km_event c; to_put = NULL; sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); rcu_read_lock(); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error); } if (best || acquire_in_progress) goto found; h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family); hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_addr_equal(&x->id.daddr, daddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error); } found: x = best; if (!x && !error && !acquire_in_progress) { if (tmpl->id.spi && (x0 = __xfrm_state_lookup(net, mark, daddr, tmpl->id.spi, tmpl->id.proto, encap_family)) != NULL) { to_put = x0; error = -EEXIST; goto out; } c.net = net; /* If the KMs have no listeners (yet...), avoid allocating an SA * for each and every packet - garbage collection might not * handle the flood. */ if (!km_is_alive(&c)) { error = -ESRCH; goto out; } x = xfrm_state_alloc(net); if (x == NULL) { error = -ENOMEM; goto out; } /* Initialize temporary state matching only * to current session. */ xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family); memcpy(&x->mark, &pol->mark, sizeof(x->mark)); x->if_id = if_id; error = security_xfrm_state_alloc_acquire(x, pol->security, fl->flowi_secid); if (error) { x->km.state = XFRM_STATE_DEAD; to_put = x; x = NULL; goto out; } if (km_query(x, tmpl, pol) == 0) { spin_lock_bh(&net->xfrm.xfrm_state_lock); x->km.state = XFRM_STATE_ACQ; list_add(&x->km.all, &net->xfrm.state_all); hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h); h = xfrm_src_hash(net, daddr, saddr, encap_family); hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family); hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); hlist_add_head_rcu(&x->byseq, net->xfrm.state_byseq + h); } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL_SOFT); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } else { x->km.state = XFRM_STATE_DEAD; to_put = x; x = NULL; error = -ESRCH; } } out: if (x) { if (!xfrm_state_hold_rcu(x)) { *err = -EAGAIN; x = NULL; } } else { *err = acquire_in_progress ? -EAGAIN : error; } rcu_read_unlock(); if (to_put) xfrm_state_put(to_put); if (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)) { *err = -EAGAIN; if (x) { xfrm_state_put(x); x = NULL; } } return x; } struct xfrm_state * xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, u8 mode, u8 proto, u32 reqid) { unsigned int h; struct xfrm_state *rx = NULL, *x = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, reqid, family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, family) && mode == x->props.mode && proto == x->id.proto && x->km.state == XFRM_STATE_VALID) { rx = x; break; } } if (rx) xfrm_state_hold(rx); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return rx; } EXPORT_SYMBOL(xfrm_stateonly_find); struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, unsigned short family) { struct xfrm_state *x; struct xfrm_state_walk *w; spin_lock_bh(&net->xfrm.xfrm_state_lock); list_for_each_entry(w, &net->xfrm.state_all, all) { x = container_of(w, struct xfrm_state, km); if (x->props.family != family || x->id.spi != spi) continue; xfrm_state_hold(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } spin_unlock_bh(&net->xfrm.xfrm_state_lock); return NULL; } EXPORT_SYMBOL(xfrm_state_lookup_byspi); static void __xfrm_state_insert(struct xfrm_state *x) { struct net *net = xs_net(x); unsigned int h; list_add(&x->km.all, &net->xfrm.state_all); h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family); hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h); h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family); hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); hlist_add_head_rcu(&x->byseq, net->xfrm.state_byseq + h); } hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); if (x->replay_maxage) mod_timer(&x->rtimer, jiffies + x->replay_maxage); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); } /* net->xfrm.xfrm_state_lock is held */ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) { struct net *net = xs_net(xnew); unsigned short family = xnew->props.family; u32 reqid = xnew->props.reqid; struct xfrm_state *x; unsigned int h; u32 mark = xnew->mark.v & xnew->mark.m; u32 if_id = xnew->if_id; h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && x->if_id == if_id && (mark & x->mark.m) == x->mark.v && xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) && xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family)) x->genid++; } } void xfrm_state_insert(struct xfrm_state *x) { struct net *net = xs_net(x); spin_lock_bh(&net->xfrm.xfrm_state_lock); __xfrm_state_bump_genids(x); __xfrm_state_insert(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_state_insert); /* net->xfrm.xfrm_state_lock is held */ static struct xfrm_state *__find_acq_core(struct net *net, const struct xfrm_mark *m, unsigned short family, u8 mode, u32 reqid, u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create) { unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family); struct xfrm_state *x; u32 mark = m->v & m->m; hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.reqid != reqid || x->props.mode != mode || x->props.family != family || x->km.state != XFRM_STATE_ACQ || x->id.spi != 0 || x->id.proto != proto || (mark & x->mark.m) != x->mark.v || !xfrm_addr_equal(&x->id.daddr, daddr, family) || !xfrm_addr_equal(&x->props.saddr, saddr, family)) continue; xfrm_state_hold(x); return x; } if (!create) return NULL; x = xfrm_state_alloc(net); if (likely(x)) { switch (family) { case AF_INET: x->sel.daddr.a4 = daddr->a4; x->sel.saddr.a4 = saddr->a4; x->sel.prefixlen_d = 32; x->sel.prefixlen_s = 32; x->props.saddr.a4 = saddr->a4; x->id.daddr.a4 = daddr->a4; break; case AF_INET6: x->sel.daddr.in6 = daddr->in6; x->sel.saddr.in6 = saddr->in6; x->sel.prefixlen_d = 128; x->sel.prefixlen_s = 128; x->props.saddr.in6 = saddr->in6; x->id.daddr.in6 = daddr->in6; break; } x->km.state = XFRM_STATE_ACQ; x->id.proto = proto; x->props.family = family; x->props.mode = mode; x->props.reqid = reqid; x->if_id = if_id; x->mark.v = m->v; x->mark.m = m->m; x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; xfrm_state_hold(x); hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL_SOFT); list_add(&x->km.all, &net->xfrm.state_all); hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h); h = xfrm_src_hash(net, daddr, saddr, family); hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); } return x; } static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq); int xfrm_state_add(struct xfrm_state *x) { struct net *net = xs_net(x); struct xfrm_state *x1, *to_put; int family; int err; u32 mark = x->mark.v & x->mark.m; int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY); family = x->props.family; to_put = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); x1 = __xfrm_state_locate(x, use_spi, family); if (x1) { to_put = x1; x1 = NULL; err = -EEXIST; goto out; } if (use_spi && x->km.seq) { x1 = __xfrm_find_acq_byseq(net, mark, x->km.seq); if (x1 && ((x1->id.proto != x->id.proto) || !xfrm_addr_equal(&x1->id.daddr, &x->id.daddr, family))) { to_put = x1; x1 = NULL; } } if (use_spi && !x1) x1 = __find_acq_core(net, &x->mark, family, x->props.mode, x->props.reqid, x->if_id, x->id.proto, &x->id.daddr, &x->props.saddr, 0); __xfrm_state_bump_genids(x); __xfrm_state_insert(x); err = 0; out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (x1) { xfrm_state_delete(x1); xfrm_state_put(x1); } if (to_put) xfrm_state_put(to_put); return err; } EXPORT_SYMBOL(xfrm_state_add); #ifdef CONFIG_XFRM_MIGRATE static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *security) { struct xfrm_user_sec_ctx *uctx; int size = sizeof(*uctx) + security->ctx_len; int err; uctx = kmalloc(size, GFP_KERNEL); if (!uctx) return -ENOMEM; uctx->exttype = XFRMA_SEC_CTX; uctx->len = size; uctx->ctx_doi = security->ctx_doi; uctx->ctx_alg = security->ctx_alg; uctx->ctx_len = security->ctx_len; memcpy(uctx + 1, security->ctx_str, security->ctx_len); err = security_xfrm_state_alloc(x, uctx); kfree(uctx); if (err) return err; return 0; } static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, struct xfrm_encap_tmpl *encap) { struct net *net = xs_net(orig); struct xfrm_state *x = xfrm_state_alloc(net); if (!x) goto out; memcpy(&x->id, &orig->id, sizeof(x->id)); memcpy(&x->sel, &orig->sel, sizeof(x->sel)); memcpy(&x->lft, &orig->lft, sizeof(x->lft)); x->props.mode = orig->props.mode; x->props.replay_window = orig->props.replay_window; x->props.reqid = orig->props.reqid; x->props.family = orig->props.family; x->props.saddr = orig->props.saddr; if (orig->aalg) { x->aalg = xfrm_algo_auth_clone(orig->aalg); if (!x->aalg) goto error; } x->props.aalgo = orig->props.aalgo; if (orig->aead) { x->aead = xfrm_algo_aead_clone(orig->aead); x->geniv = orig->geniv; if (!x->aead) goto error; } if (orig->ealg) { x->ealg = xfrm_algo_clone(orig->ealg); if (!x->ealg) goto error; } x->props.ealgo = orig->props.ealgo; if (orig->calg) { x->calg = xfrm_algo_clone(orig->calg); if (!x->calg) goto error; } x->props.calgo = orig->props.calgo; if (encap || orig->encap) { if (encap) x->encap = kmemdup(encap, sizeof(*x->encap), GFP_KERNEL); else x->encap = kmemdup(orig->encap, sizeof(*x->encap), GFP_KERNEL); if (!x->encap) goto error; } if (orig->security) if (clone_security(x, orig->security)) goto error; if (orig->coaddr) { x->coaddr = kmemdup(orig->coaddr, sizeof(*x->coaddr), GFP_KERNEL); if (!x->coaddr) goto error; } if (orig->replay_esn) { if (xfrm_replay_clone(x, orig)) goto error; } memcpy(&x->mark, &orig->mark, sizeof(x->mark)); memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark)); x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; x->if_id = orig->if_id; x->tfcpad = orig->tfcpad; x->replay_maxdiff = orig->replay_maxdiff; x->replay_maxage = orig->replay_maxage; memcpy(&x->curlft, &orig->curlft, sizeof(x->curlft)); x->km.state = orig->km.state; x->km.seq = orig->km.seq; x->replay = orig->replay; x->preplay = orig->preplay; x->mapping_maxage = orig->mapping_maxage; x->lastused = orig->lastused; x->new_mapping = 0; x->new_mapping_sport = 0; return x; error: xfrm_state_put(x); out: return NULL; } struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net, u32 if_id) { unsigned int h; struct xfrm_state *x = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); if (m->reqid) { h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr, m->reqid, m->old_family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; if (m->reqid && x->props.reqid != m->reqid) continue; if (if_id != 0 && x->if_id != if_id) continue; if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, m->old_family) || !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, m->old_family)) continue; xfrm_state_hold(x); break; } } else { h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr, m->old_family); hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; if (if_id != 0 && x->if_id != if_id) continue; if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, m->old_family) || !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, m->old_family)) continue; xfrm_state_hold(x); break; } } spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_migrate_state_find); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m, struct xfrm_encap_tmpl *encap) { struct xfrm_state *xc; xc = xfrm_state_clone(x, encap); if (!xc) return NULL; xc->props.family = m->new_family; if (xfrm_init_state(xc) < 0) goto error; memcpy(&xc->id.daddr, &m->new_daddr, sizeof(xc->id.daddr)); memcpy(&xc->props.saddr, &m->new_saddr, sizeof(xc->props.saddr)); /* add state */ if (xfrm_addr_equal(&x->id.daddr, &m->new_daddr, m->new_family)) { /* a care is needed when the destination address of the state is to be updated as it is a part of triplet */ xfrm_state_insert(xc); } else { if (xfrm_state_add(xc) < 0) goto error; } return xc; error: xfrm_state_put(xc); return NULL; } EXPORT_SYMBOL(xfrm_state_migrate); #endif int xfrm_state_update(struct xfrm_state *x) { struct xfrm_state *x1, *to_put; int err; int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY); struct net *net = xs_net(x); to_put = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); x1 = __xfrm_state_locate(x, use_spi, x->props.family); err = -ESRCH; if (!x1) goto out; if (xfrm_state_kern(x1)) { to_put = x1; err = -EEXIST; goto out; } if (x1->km.state == XFRM_STATE_ACQ) { __xfrm_state_insert(x); x = NULL; } err = 0; out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (to_put) xfrm_state_put(to_put); if (err) return err; if (!x) { xfrm_state_delete(x1); xfrm_state_put(x1); return 0; } err = -EINVAL; spin_lock_bh(&x1->lock); if (likely(x1->km.state == XFRM_STATE_VALID)) { if (x->encap && x1->encap && x->encap->encap_type == x1->encap->encap_type) memcpy(x1->encap, x->encap, sizeof(*x1->encap)); else if (x->encap || x1->encap) goto fail; if (x->coaddr && x1->coaddr) { memcpy(x1->coaddr, x->coaddr, sizeof(*x1->coaddr)); } if (!use_spi && memcmp(&x1->sel, &x->sel, sizeof(x1->sel))) memcpy(&x1->sel, &x->sel, sizeof(x1->sel)); memcpy(&x1->lft, &x->lft, sizeof(x1->lft)); x1->km.dying = 0; hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); if (x1->curlft.use_time) xfrm_state_check_expire(x1); if (x->props.smark.m || x->props.smark.v || x->if_id) { spin_lock_bh(&net->xfrm.xfrm_state_lock); if (x->props.smark.m || x->props.smark.v) x1->props.smark = x->props.smark; if (x->if_id) x1->if_id = x->if_id; __xfrm_state_bump_genids(x1); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } err = 0; x->km.state = XFRM_STATE_DEAD; __xfrm_state_put(x); } fail: spin_unlock_bh(&x1->lock); xfrm_state_put(x1); return err; } EXPORT_SYMBOL(xfrm_state_update); int xfrm_state_check_expire(struct xfrm_state *x) { if (!x->curlft.use_time) x->curlft.use_time = ktime_get_real_seconds(); if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { x->km.state = XFRM_STATE_EXPIRED; hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL_SOFT); return -EINVAL; } if (!x->km.dying && (x->curlft.bytes >= x->lft.soft_byte_limit || x->curlft.packets >= x->lft.soft_packet_limit)) { x->km.dying = 1; km_state_expired(x, 0, 0); } return 0; } EXPORT_SYMBOL(xfrm_state_check_expire); struct xfrm_state * xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { struct xfrm_state *x; rcu_read_lock(); x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family); rcu_read_unlock(); return x; } EXPORT_SYMBOL(xfrm_state_lookup); struct xfrm_state * xfrm_state_lookup_byaddr(struct net *net, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family) { struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_state_lookup_byaddr); struct xfrm_state * xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family) { struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __find_acq_core(net, mark, family, mode, reqid, if_id, proto, daddr, saddr, create); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_find_acq); #ifdef CONFIG_XFRM_SUB_POLICY #if IS_ENABLED(CONFIG_IPV6) /* distribution counting sort function for xfrm_state and xfrm_tmpl */ static void __xfrm6_sort(void **dst, void **src, int n, int (*cmp)(const void *p), int maxclass) { int count[XFRM_MAX_DEPTH] = { }; int class[XFRM_MAX_DEPTH]; int i; for (i = 0; i < n; i++) { int c = cmp(src[i]); class[i] = c; count[c]++; } for (i = 2; i < maxclass; i++) count[i] += count[i - 1]; for (i = 0; i < n; i++) { dst[count[class[i] - 1]++] = src[i]; src[i] = NULL; } } /* Rule for xfrm_state: * * rule 1: select IPsec transport except AH * rule 2: select MIPv6 RO or inbound trigger * rule 3: select IPsec transport AH * rule 4: select IPsec tunnel * rule 5: others */ static int __xfrm6_state_sort_cmp(const void *p) { const struct xfrm_state *v = p; switch (v->props.mode) { case XFRM_MODE_TRANSPORT: if (v->id.proto != IPPROTO_AH) return 1; else return 3; #if IS_ENABLED(CONFIG_IPV6_MIP6) case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: return 2; #endif case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: return 4; } return 5; } /* Rule for xfrm_tmpl: * * rule 1: select IPsec transport * rule 2: select MIPv6 RO or inbound trigger * rule 3: select IPsec tunnel * rule 4: others */ static int __xfrm6_tmpl_sort_cmp(const void *p) { const struct xfrm_tmpl *v = p; switch (v->mode) { case XFRM_MODE_TRANSPORT: return 1; #if IS_ENABLED(CONFIG_IPV6_MIP6) case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: return 2; #endif case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: return 3; } return 4; } #else static inline int __xfrm6_state_sort_cmp(const void *p) { return 5; } static inline int __xfrm6_tmpl_sort_cmp(const void *p) { return 4; } static inline void __xfrm6_sort(void **dst, void **src, int n, int (*cmp)(const void *p), int maxclass) { int i; for (i = 0; i < n; i++) dst[i] = src[i]; } #endif /* CONFIG_IPV6 */ void xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, unsigned short family) { int i; if (family == AF_INET6) __xfrm6_sort((void **)dst, (void **)src, n, __xfrm6_tmpl_sort_cmp, 5); else for (i = 0; i < n; i++) dst[i] = src[i]; } void xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, unsigned short family) { int i; if (family == AF_INET6) __xfrm6_sort((void **)dst, (void **)src, n, __xfrm6_state_sort_cmp, 6); else for (i = 0; i < n; i++) dst[i] = src[i]; } #endif /* Silly enough, but I'm lazy to build resolution list */ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq) { unsigned int h = xfrm_seq_hash(net, seq); struct xfrm_state *x; hlist_for_each_entry_rcu(x, net->xfrm.state_byseq + h, byseq) { if (x->km.seq == seq && (mark & x->mark.m) == x->mark.v && x->km.state == XFRM_STATE_ACQ) { xfrm_state_hold(x); return x; } } return NULL; } struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq) { struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __xfrm_find_acq_byseq(net, mark, seq); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_find_acq_byseq); u32 xfrm_get_acqseq(void) { u32 res; static atomic_t acqseq; do { res = atomic_inc_return(&acqseq); } while (!res); return res; } EXPORT_SYMBOL(xfrm_get_acqseq); int verify_spi_info(u8 proto, u32 min, u32 max) { switch (proto) { case IPPROTO_AH: case IPPROTO_ESP: break; case IPPROTO_COMP: /* IPCOMP spi is 16-bits. */ if (max >= 0x10000) return -EINVAL; break; default: return -EINVAL; } if (min > max) return -EINVAL; return 0; } EXPORT_SYMBOL(verify_spi_info); int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) { struct net *net = xs_net(x); unsigned int h; struct xfrm_state *x0; int err = -ENOENT; __be32 minspi = htonl(low); __be32 maxspi = htonl(high); __be32 newspi = 0; u32 mark = x->mark.v & x->mark.m; spin_lock_bh(&x->lock); if (x->km.state == XFRM_STATE_DEAD) goto unlock; err = 0; if (x->id.spi) goto unlock; err = -ENOENT; if (minspi == maxspi) { x0 = xfrm_state_lookup(net, mark, &x->id.daddr, minspi, x->id.proto, x->props.family); if (x0) { xfrm_state_put(x0); goto unlock; } newspi = minspi; } else { u32 spi = 0; for (h = 0; h < high-low+1; h++) { spi = low + prandom_u32_max(high - low + 1); x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family); if (x0 == NULL) { newspi = htonl(spi); break; } xfrm_state_put(x0); } } if (newspi) { spin_lock_bh(&net->xfrm.xfrm_state_lock); x->id.spi = newspi; h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = 0; } unlock: spin_unlock_bh(&x->lock); return err; } EXPORT_SYMBOL(xfrm_alloc_spi); static bool __xfrm_state_filter_match(struct xfrm_state *x, struct xfrm_address_filter *filter) { if (filter) { if ((filter->family == AF_INET || filter->family == AF_INET6) && x->props.family != filter->family) return false; return addr_match(&x->props.saddr, &filter->saddr, filter->splen) && addr_match(&x->id.daddr, &filter->daddr, filter->dplen); } return true; } int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *data) { struct xfrm_state *state; struct xfrm_state_walk *x; int err = 0; if (walk->seq != 0 && list_empty(&walk->all)) return 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); if (list_empty(&walk->all)) x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all); else x = list_first_entry(&walk->all, struct xfrm_state_walk, all); list_for_each_entry_from(x, &net->xfrm.state_all, all) { if (x->state == XFRM_STATE_DEAD) continue; state = container_of(x, struct xfrm_state, km); if (!xfrm_id_proto_match(state->id.proto, walk->proto)) continue; if (!__xfrm_state_filter_match(state, walk->filter)) continue; err = func(state, walk->seq, data); if (err) { list_move_tail(&walk->all, &x->all); goto out; } walk->seq++; } if (walk->seq == 0) { err = -ENOENT; goto out; } list_del_init(&walk->all); out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); return err; } EXPORT_SYMBOL(xfrm_state_walk); void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto, struct xfrm_address_filter *filter) { INIT_LIST_HEAD(&walk->all); walk->proto = proto; walk->state = XFRM_STATE_DEAD; walk->seq = 0; walk->filter = filter; } EXPORT_SYMBOL(xfrm_state_walk_init); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net) { kfree(walk->filter); if (list_empty(&walk->all)) return; spin_lock_bh(&net->xfrm.xfrm_state_lock); list_del(&walk->all); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_state_walk_done); static void xfrm_replay_timer_handler(struct timer_list *t) { struct xfrm_state *x = from_timer(x, t, rtimer); spin_lock(&x->lock); if (x->km.state == XFRM_STATE_VALID) { if (xfrm_aevent_is_on(xs_net(x))) xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT); else x->xflags |= XFRM_TIME_DEFER; } spin_unlock(&x->lock); } static LIST_HEAD(xfrm_km_list); void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) if (km->notify_policy) km->notify_policy(xp, dir, c); rcu_read_unlock(); } void km_state_notify(struct xfrm_state *x, const struct km_event *c) { struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) if (km->notify) km->notify(x, c); rcu_read_unlock(); } EXPORT_SYMBOL(km_policy_notify); EXPORT_SYMBOL(km_state_notify); void km_state_expired(struct xfrm_state *x, int hard, u32 portid) { struct km_event c; c.data.hard = hard; c.portid = portid; c.event = XFRM_MSG_EXPIRE; km_state_notify(x, &c); } EXPORT_SYMBOL(km_state_expired); /* * We send to all registered managers regardless of failure * We are happy with one success */ int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol) { int err = -EINVAL, acqret; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { acqret = km->acquire(x, t, pol); if (!acqret) err = acqret; } rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_query); static int __km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { int err = -EINVAL; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->new_mapping) err = km->new_mapping(x, ipaddr, sport); if (!err) break; } rcu_read_unlock(); return err; } int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { int ret = 0; if (x->mapping_maxage) { if ((jiffies / HZ - x->new_mapping) > x->mapping_maxage || x->new_mapping_sport != sport) { x->new_mapping_sport = sport; x->new_mapping = jiffies / HZ; ret = __km_new_mapping(x, ipaddr, sport); } } else { ret = __km_new_mapping(x, ipaddr, sport); } return ret; } EXPORT_SYMBOL(km_new_mapping); void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid) { struct km_event c; c.data.hard = hard; c.portid = portid; c.event = XFRM_MSG_POLEXPIRE; km_policy_notify(pol, dir, &c); } EXPORT_SYMBOL(km_policy_expired); #ifdef CONFIG_XFRM_MIGRATE int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap) { int err = -EINVAL; int ret; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->migrate) { ret = km->migrate(sel, dir, type, m, num_migrate, k, encap); if (!ret) err = ret; } } rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_migrate); #endif int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr) { int err = -EINVAL; int ret; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->report) { ret = km->report(net, proto, sel, addr); if (!ret) err = ret; } } rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_report); static bool km_is_alive(const struct km_event *c) { struct xfrm_mgr *km; bool is_alive = false; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->is_alive && km->is_alive(c)) { is_alive = true; break; } } rcu_read_unlock(); return is_alive; } #if IS_ENABLED(CONFIG_XFRM_USER_COMPAT) static DEFINE_SPINLOCK(xfrm_translator_lock); static struct xfrm_translator __rcu *xfrm_translator; struct xfrm_translator *xfrm_get_translator(void) { struct xfrm_translator *xtr; rcu_read_lock(); xtr = rcu_dereference(xfrm_translator); if (unlikely(!xtr)) goto out; if (!try_module_get(xtr->owner)) xtr = NULL; out: rcu_read_unlock(); return xtr; } EXPORT_SYMBOL_GPL(xfrm_get_translator); void xfrm_put_translator(struct xfrm_translator *xtr) { module_put(xtr->owner); } EXPORT_SYMBOL_GPL(xfrm_put_translator); int xfrm_register_translator(struct xfrm_translator *xtr) { int err = 0; spin_lock_bh(&xfrm_translator_lock); if (unlikely(xfrm_translator != NULL)) err = -EEXIST; else rcu_assign_pointer(xfrm_translator, xtr); spin_unlock_bh(&xfrm_translator_lock); return err; } EXPORT_SYMBOL_GPL(xfrm_register_translator); int xfrm_unregister_translator(struct xfrm_translator *xtr) { int err = 0; spin_lock_bh(&xfrm_translator_lock); if (likely(xfrm_translator != NULL)) { if (rcu_access_pointer(xfrm_translator) != xtr) err = -EINVAL; else RCU_INIT_POINTER(xfrm_translator, NULL); } spin_unlock_bh(&xfrm_translator_lock); synchronize_rcu(); return err; } EXPORT_SYMBOL_GPL(xfrm_unregister_translator); #endif int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) { int err; u8 *data; struct xfrm_mgr *km; struct xfrm_policy *pol = NULL; if (sockptr_is_null(optval) && !optlen) { xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL); xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL); __sk_dst_reset(sk); return 0; } if (optlen <= 0 || optlen > PAGE_SIZE) return -EMSGSIZE; data = memdup_sockptr(optval, optlen); if (IS_ERR(data)) return PTR_ERR(data); if (in_compat_syscall()) { struct xfrm_translator *xtr = xfrm_get_translator(); if (!xtr) { kfree(data); return -EOPNOTSUPP; } err = xtr->xlate_user_policy_sockptr(&data, optlen); xfrm_put_translator(xtr); if (err) { kfree(data); return err; } } err = -EINVAL; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { pol = km->compile_policy(sk, optname, data, optlen, &err); if (err >= 0) break; } rcu_read_unlock(); if (err >= 0) { xfrm_sk_policy_insert(sk, err, pol); xfrm_pol_put(pol); __sk_dst_reset(sk); err = 0; } kfree(data); return err; } EXPORT_SYMBOL(xfrm_user_policy); static DEFINE_SPINLOCK(xfrm_km_lock); void xfrm_register_km(struct xfrm_mgr *km) { spin_lock_bh(&xfrm_km_lock); list_add_tail_rcu(&km->list, &xfrm_km_list); spin_unlock_bh(&xfrm_km_lock); } EXPORT_SYMBOL(xfrm_register_km); void xfrm_unregister_km(struct xfrm_mgr *km) { spin_lock_bh(&xfrm_km_lock); list_del_rcu(&km->list); spin_unlock_bh(&xfrm_km_lock); synchronize_rcu(); } EXPORT_SYMBOL(xfrm_unregister_km); int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo) { int err = 0; if (WARN_ON(afinfo->family >= NPROTO)) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_state_afinfo_lock); if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL)) err = -EEXIST; else rcu_assign_pointer(xfrm_state_afinfo[afinfo->family], afinfo); spin_unlock_bh(&xfrm_state_afinfo_lock); return err; } EXPORT_SYMBOL(xfrm_state_register_afinfo); int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo) { int err = 0, family = afinfo->family; if (WARN_ON(family >= NPROTO)) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_state_afinfo_lock); if (likely(xfrm_state_afinfo[afinfo->family] != NULL)) { if (rcu_access_pointer(xfrm_state_afinfo[family]) != afinfo) err = -EINVAL; else RCU_INIT_POINTER(xfrm_state_afinfo[afinfo->family], NULL); } spin_unlock_bh(&xfrm_state_afinfo_lock); synchronize_rcu(); return err; } EXPORT_SYMBOL(xfrm_state_unregister_afinfo); struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family) { if (unlikely(family >= NPROTO)) return NULL; return rcu_dereference(xfrm_state_afinfo[family]); } EXPORT_SYMBOL_GPL(xfrm_state_afinfo_get_rcu); struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family) { struct xfrm_state_afinfo *afinfo; if (unlikely(family >= NPROTO)) return NULL; rcu_read_lock(); afinfo = rcu_dereference(xfrm_state_afinfo[family]); if (unlikely(!afinfo)) rcu_read_unlock(); return afinfo; } void xfrm_flush_gc(void) { flush_work(&xfrm_state_gc_work); } EXPORT_SYMBOL(xfrm_flush_gc); /* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */ void xfrm_state_delete_tunnel(struct xfrm_state *x) { if (x->tunnel) { struct xfrm_state *t = x->tunnel; if (atomic_read(&t->tunnel_users) == 2) xfrm_state_delete(t); atomic_dec(&t->tunnel_users); xfrm_state_put_sync(t); x->tunnel = NULL; } } EXPORT_SYMBOL(xfrm_state_delete_tunnel); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) { const struct xfrm_type *type = READ_ONCE(x->type); struct crypto_aead *aead; u32 blksize, net_adj = 0; if (x->km.state != XFRM_STATE_VALID || !type || type->proto != IPPROTO_ESP) return mtu - x->props.header_len; aead = x->data; blksize = ALIGN(crypto_aead_blocksize(aead), 4); switch (x->props.mode) { case XFRM_MODE_TRANSPORT: case XFRM_MODE_BEET: if (x->props.family == AF_INET) net_adj = sizeof(struct iphdr); else if (x->props.family == AF_INET6) net_adj = sizeof(struct ipv6hdr); break; case XFRM_MODE_TUNNEL: break; default: WARN_ON_ONCE(1); break; } return ((mtu - x->props.header_len - crypto_aead_authsize(aead) - net_adj) & ~(blksize - 1)) + net_adj - 2; } EXPORT_SYMBOL_GPL(xfrm_state_mtu); int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload, struct netlink_ext_ack *extack) { const struct xfrm_mode *inner_mode; const struct xfrm_mode *outer_mode; int family = x->props.family; int err; if (family == AF_INET && READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)) x->props.flags |= XFRM_STATE_NOPMTUDISC; err = -EPROTONOSUPPORT; if (x->sel.family != AF_UNSPEC) { inner_mode = xfrm_get_mode(x->props.mode, x->sel.family); if (inner_mode == NULL) { NL_SET_ERR_MSG(extack, "Requested mode not found"); goto error; } if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL) && family != x->sel.family) { NL_SET_ERR_MSG(extack, "Only tunnel modes can accommodate a change of family"); goto error; } x->inner_mode = *inner_mode; } else { const struct xfrm_mode *inner_mode_iaf; int iafamily = AF_INET; inner_mode = xfrm_get_mode(x->props.mode, x->props.family); if (inner_mode == NULL) { NL_SET_ERR_MSG(extack, "Requested mode not found"); goto error; } if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL)) { NL_SET_ERR_MSG(extack, "Only tunnel modes can accommodate an AF_UNSPEC selector"); goto error; } x->inner_mode = *inner_mode; if (x->props.family == AF_INET) iafamily = AF_INET6; inner_mode_iaf = xfrm_get_mode(x->props.mode, iafamily); if (inner_mode_iaf) { if (inner_mode_iaf->flags & XFRM_MODE_FLAG_TUNNEL) x->inner_mode_iaf = *inner_mode_iaf; } } x->type = xfrm_get_type(x->id.proto, family); if (x->type == NULL) { NL_SET_ERR_MSG(extack, "Requested type not found"); goto error; } x->type_offload = xfrm_get_type_offload(x->id.proto, family, offload); err = x->type->init_state(x, extack); if (err) goto error; outer_mode = xfrm_get_mode(x->props.mode, family); if (!outer_mode) { NL_SET_ERR_MSG(extack, "Requested mode not found"); err = -EPROTONOSUPPORT; goto error; } x->outer_mode = *outer_mode; if (init_replay) { err = xfrm_init_replay(x, extack); if (err) goto error; } error: return err; } EXPORT_SYMBOL(__xfrm_init_state); int xfrm_init_state(struct xfrm_state *x) { int err; err = __xfrm_init_state(x, true, false, NULL); if (!err) x->km.state = XFRM_STATE_VALID; return err; } EXPORT_SYMBOL(xfrm_init_state); int __net_init xfrm_state_init(struct net *net) { unsigned int sz; if (net_eq(net, &init_net)) xfrm_state_cache = KMEM_CACHE(xfrm_state, SLAB_HWCACHE_ALIGN | SLAB_PANIC); INIT_LIST_HEAD(&net->xfrm.state_all); sz = sizeof(struct hlist_head) * 8; net->xfrm.state_bydst = xfrm_hash_alloc(sz); if (!net->xfrm.state_bydst) goto out_bydst; net->xfrm.state_bysrc = xfrm_hash_alloc(sz); if (!net->xfrm.state_bysrc) goto out_bysrc; net->xfrm.state_byspi = xfrm_hash_alloc(sz); if (!net->xfrm.state_byspi) goto out_byspi; net->xfrm.state_byseq = xfrm_hash_alloc(sz); if (!net->xfrm.state_byseq) goto out_byseq; net->xfrm.state_hmask = ((sz / sizeof(struct hlist_head)) - 1); net->xfrm.state_num = 0; INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize); spin_lock_init(&net->xfrm.xfrm_state_lock); seqcount_spinlock_init(&net->xfrm.xfrm_state_hash_generation, &net->xfrm.xfrm_state_lock); return 0; out_byseq: xfrm_hash_free(net->xfrm.state_byspi, sz); out_byspi: xfrm_hash_free(net->xfrm.state_bysrc, sz); out_bysrc: xfrm_hash_free(net->xfrm.state_bydst, sz); out_bydst: return -ENOMEM; } void xfrm_state_fini(struct net *net) { unsigned int sz; flush_work(&net->xfrm.state_hash_work); flush_work(&xfrm_state_gc_work); xfrm_state_flush(net, 0, false, true); WARN_ON(!list_empty(&net->xfrm.state_all)); sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head); WARN_ON(!hlist_empty(net->xfrm.state_byseq)); xfrm_hash_free(net->xfrm.state_byseq, sz); WARN_ON(!hlist_empty(net->xfrm.state_byspi)); xfrm_hash_free(net->xfrm.state_byspi, sz); WARN_ON(!hlist_empty(net->xfrm.state_bysrc)); xfrm_hash_free(net->xfrm.state_bysrc, sz); WARN_ON(!hlist_empty(net->xfrm.state_bydst)); xfrm_hash_free(net->xfrm.state_bydst, sz); } #ifdef CONFIG_AUDITSYSCALL static void xfrm_audit_helper_sainfo(struct xfrm_state *x, struct audit_buffer *audit_buf) { struct xfrm_sec_ctx *ctx = x->security; u32 spi = ntohl(x->id.spi); if (ctx) audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); switch (x->props.family) { case AF_INET: audit_log_format(audit_buf, " src=%pI4 dst=%pI4", &x->props.saddr.a4, &x->id.daddr.a4); break; case AF_INET6: audit_log_format(audit_buf, " src=%pI6 dst=%pI6", x->props.saddr.a6, x->id.daddr.a6); break; } audit_log_format(audit_buf, " spi=%u(0x%x)", spi, spi); } static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family, struct audit_buffer *audit_buf) { const struct iphdr *iph4; const struct ipv6hdr *iph6; switch (family) { case AF_INET: iph4 = ip_hdr(skb); audit_log_format(audit_buf, " src=%pI4 dst=%pI4", &iph4->saddr, &iph4->daddr); break; case AF_INET6: iph6 = ipv6_hdr(skb); audit_log_format(audit_buf, " src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x", &iph6->saddr, &iph6->daddr, iph6->flow_lbl[0] & 0x0f, iph6->flow_lbl[1], iph6->flow_lbl[2]); break; } } void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SAD-add"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); xfrm_audit_helper_sainfo(x, audit_buf); audit_log_format(audit_buf, " res=%u", result); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_add); void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SAD-delete"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); xfrm_audit_helper_sainfo(x, audit_buf); audit_log_format(audit_buf, " res=%u", result); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_delete); void xfrm_audit_state_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) { struct audit_buffer *audit_buf; u32 spi; audit_buf = xfrm_audit_start("SA-replay-overflow"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf); /* don't record the sequence number because it's inherent in this kind * of audit message */ spi = ntohl(x->id.spi); audit_log_format(audit_buf, " spi=%u(0x%x)", spi, spi); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_replay_overflow); void xfrm_audit_state_replay(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq) { struct audit_buffer *audit_buf; u32 spi; audit_buf = xfrm_audit_start("SA-replayed-pkt"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf); spi = ntohl(x->id.spi); audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u", spi, spi, ntohl(net_seq)); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_replay); void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SA-notfound"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, family, audit_buf); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_notfound_simple); void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family, __be32 net_spi, __be32 net_seq) { struct audit_buffer *audit_buf; u32 spi; audit_buf = xfrm_audit_start("SA-notfound"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, family, audit_buf); spi = ntohl(net_spi); audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u", spi, spi, ntohl(net_seq)); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_notfound); void xfrm_audit_state_icvfail(struct xfrm_state *x, struct sk_buff *skb, u8 proto) { struct audit_buffer *audit_buf; __be32 net_spi; __be32 net_seq; audit_buf = xfrm_audit_start("SA-icv-failure"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf); if (xfrm_parse_spi(skb, proto, &net_spi, &net_seq) == 0) { u32 spi = ntohl(net_spi); audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u", spi, spi, ntohl(net_seq)); } audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_icvfail); #endif /* CONFIG_AUDITSYSCALL */ |
| 1 2 1 1 2 22 10 1491 1491 1460 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * TCP over IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on: * linux/net/ipv4/tcp.c * linux/net/ipv4/tcp_input.c * linux/net/ipv4/tcp_output.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind * a single port at the same time. * YOSHIFUJI Hideaki @USAGI: convert /proc/net/tcp6 to seq_file. */ #include <linux/bottom_half.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/jiffies.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/init.h> #include <linux/jhash.h> #include <linux/ipsec.h> #include <linux/times.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/random.h> #include <linux/indirect_call_wrapper.h> #include <net/tcp.h> #include <net/ndisc.h> #include <net/inet6_hashtables.h> #include <net/inet6_connection_sock.h> #include <net/ipv6.h> #include <net/transp_v6.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <net/inet_ecn.h> #include <net/protocol.h> #include <net/xfrm.h> #include <net/snmp.h> #include <net/dsfield.h> #include <net/timewait_sock.h> #include <net/inet_common.h> #include <net/secure_seq.h> #include <net/busy_poll.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <crypto/hash.h> #include <linux/scatterlist.h> #include <trace/events/tcp.h> static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb); static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); INDIRECT_CALLABLE_SCOPE int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); static const struct inet_connection_sock_af_ops ipv6_mapped; const struct inet_connection_sock_af_ops ipv6_specific; #ifdef CONFIG_TCP_MD5SIG static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; #else static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, const struct in6_addr *addr, int l3index) { return NULL; } #endif /* Helper returning the inet6 address from a given tcp socket. * It can be used in TCP stack instead of inet6_sk(sk). * This avoids a dereference and allow compiler optimizations. * It is a specialized version of inet6_sk_generic(). */ static struct ipv6_pinfo *tcp_inet6_sk(const struct sock *sk) { unsigned int offset = sizeof(struct tcp6_sock) - sizeof(struct ipv6_pinfo); return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { const struct rt6_info *rt = (const struct rt6_info *)dst; rcu_assign_pointer(sk->sk_rx_dst, dst); sk->sk_rx_dst_ifindex = skb->skb_iif; sk->sk_rx_dst_cookie = rt6_get_cookie(rt); } } static u32 tcp_v6_init_seq(const struct sk_buff *skb) { return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, tcp_hdr(skb)->dest, tcp_hdr(skb)->source); } static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb) { return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32); } static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { /* This check is replicated from tcp_v6_connect() and intended to * prevent BPF program called below from accessing bytes that are out * of the bound specified by user in addr_len. */ if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; sock_owned_by_me(sk); return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr); } static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_connection_sock *icsk = inet_csk(sk); struct in6_addr *saddr = NULL, *final_p, final; struct inet_timewait_death_row *tcp_death_row; struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct ipv6_txoptions *opt; struct dst_entry *dst; struct flowi6 fl6; int addr_type; int err; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; memset(&fl6, 0, sizeof(fl6)); if (np->sndflow) { fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; IP6_ECN_flow_init(fl6.flowlabel); if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { struct ip6_flowlabel *flowlabel; flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; fl6_sock_release(flowlabel); } } /* * connect() to INADDR_ANY means loopback (BSD'ism). */ if (ipv6_addr_any(&usin->sin6_addr)) { if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), &usin->sin6_addr); else usin->sin6_addr = in6addr_loopback; } addr_type = ipv6_addr_type(&usin->sin6_addr); if (addr_type & IPV6_ADDR_MULTICAST) return -ENETUNREACH; if (addr_type&IPV6_ADDR_LINKLOCAL) { if (addr_len >= sizeof(struct sockaddr_in6) && usin->sin6_scope_id) { /* If interface is set while binding, indices * must coincide. */ if (!sk_dev_equal_l3scope(sk, usin->sin6_scope_id)) return -EINVAL; sk->sk_bound_dev_if = usin->sin6_scope_id; } /* Connect to link-local address requires an interface */ if (!sk->sk_bound_dev_if) return -EINVAL; } if (tp->rx_opt.ts_recent_stamp && !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; WRITE_ONCE(tp->write_seq, 0); } sk->sk_v6_daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; /* * TCP over IPv4 */ if (addr_type & IPV6_ADDR_MAPPED) { u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; if (ipv6_only_sock(sk)) return -ENETUNREACH; sin.sin_family = AF_INET; sin.sin_port = usin->sin6_port; sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3]; /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */ WRITE_ONCE(icsk->icsk_af_ops, &ipv6_mapped); if (sk_is_mptcp(sk)) mptcpv6_handle_mapped(sk, true); sk->sk_backlog_rcv = tcp_v4_do_rcv; #ifdef CONFIG_TCP_MD5SIG tp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin)); if (err) { icsk->icsk_ext_hdr_len = exthdrlen; /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */ WRITE_ONCE(icsk->icsk_af_ops, &ipv6_specific); if (sk_is_mptcp(sk)) mptcpv6_handle_mapped(sk, false); sk->sk_backlog_rcv = tcp_v6_do_rcv; #ifdef CONFIG_TCP_MD5SIG tp->af_specific = &tcp_sock_ipv6_specific; #endif goto failure; } np->saddr = sk->sk_v6_rcv_saddr; return err; } if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) saddr = &sk->sk_v6_rcv_saddr; fl6.flowi6_proto = IPPROTO_TCP; fl6.daddr = sk->sk_v6_daddr; fl6.saddr = saddr ? *saddr : np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = usin->sin6_port; fl6.fl6_sport = inet->inet_sport; fl6.flowi6_uid = sk->sk_uid; opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(&fl6, opt, &final); security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); dst = ip6_dst_lookup_flow(net, sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; } tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!saddr) { saddr = &fl6.saddr; err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); if (err) goto failure; } /* set the source address */ np->saddr = *saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; ip6_dst_store(sk, dst, NULL, NULL); icsk->icsk_ext_hdr_len = 0; if (opt) icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen; tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); inet->inet_dport = usin->sin6_port; tcp_set_state(sk, TCP_SYN_SENT); err = inet6_hash_connect(tcp_death_row, sk); if (err) goto late_failure; sk_set_txhash(sk); if (likely(!tp->repair)) { if (!tp->write_seq) WRITE_ONCE(tp->write_seq, secure_tcpv6_seq(np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport)); tp->tsoffset = secure_tcpv6_ts_off(net, np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32); } if (tcp_fastopen_defer_connect(sk, &err)) return err; if (err) goto late_failure; err = tcp_connect(sk); if (err) goto late_failure; return 0; late_failure: tcp_set_state(sk, TCP_CLOSE); inet_bhash2_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } static void tcp_v6_mtu_reduced(struct sock *sk) { struct dst_entry *dst; u32 mtu; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; mtu = READ_ONCE(tcp_sk(sk)->mtu_info); /* Drop requests trying to increase our current mss. * Check done in __ip6_rt_update_pmtu() is too late. */ if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache) return; dst = inet6_csk_update_pmtu(sk, mtu); if (!dst) return; if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { tcp_sync_mss(sk, dst_mtu(dst)); tcp_simple_retransmit(sk); } } static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); struct net *net = dev_net(skb->dev); struct request_sock *fastopen; struct ipv6_pinfo *np; struct tcp_sock *tp; __u32 seq, snd_una; struct sock *sk; bool fatal; int err; sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &hdr->daddr, th->dest, &hdr->saddr, ntohs(th->source), skb->dev->ifindex, inet6_sdif(skb)); if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return -ENOENT; } if (sk->sk_state == TCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return 0; } seq = ntohl(th->seq); fatal = icmpv6_err_convert(type, code, &err); if (sk->sk_state == TCP_NEW_SYN_RECV) { tcp_req_err(sk, seq, fatal); return 0; } bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) goto out; if (static_branch_unlikely(&ip6_min_hopcount)) { /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */ if (ipv6_hdr(skb)->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount)) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); goto out; } } tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } np = tcp_inet6_sk(sk); if (type == NDISC_REDIRECT) { if (!sock_owned_by_user(sk)) { struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); if (dst) dst->ops->redirect(dst, sk, skb); } goto out; } if (type == ICMPV6_PKT_TOOBIG) { u32 mtu = ntohl(info); /* We are not interested in TCP_LISTEN and open_requests * (SYN-ACKs send out by Linux are always <576bytes so * they should go through unfragmented). */ if (sk->sk_state == TCP_LISTEN) goto out; if (!ip6_sk_accept_pmtu(sk)) goto out; if (mtu < IPV6_MIN_MTU) goto out; WRITE_ONCE(tp->mtu_info, mtu); if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); goto out; } /* Might be for an request_sock */ switch (sk->sk_state) { case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is * already accepted it is treated as a connected one below. */ if (fastopen && !fastopen->sk) break; ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th); if (!sock_owned_by_user(sk)) { sk->sk_err = err; sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ tcp_done(sk); } else sk->sk_err_soft = err; goto out; case TCP_LISTEN: break; default: /* check if this ICMP message allows revert of backoff. * (see RFC 6069) */ if (!fastopen && type == ICMPV6_DEST_UNREACH && code == ICMPV6_NOROUTE) tcp_ld_RTO_revert(sk, seq); } if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; sk_error_report(sk); } else sk->sk_err_soft = err; out: bh_unlock_sock(sk); sock_put(sk); return 0; } static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct ipv6_txoptions *opt; struct flowi6 *fl6 = &fl->u.ip6; struct sk_buff *skb; int err = -ENOMEM; u8 tclass; /* First, grab a route. */ if (!dst && (dst = inet6_csk_route_req(sk, fl6, req, IPPROTO_TCP)) == NULL) goto done; skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); if (skb) { __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, &ireq->ir_v6_rmt_addr); fl6->daddr = ireq->ir_v6_rmt_addr; if (np->repflow && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ? (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | (np->tclass & INET_ECN_MASK) : np->tclass; if (!INET_ECN_is_capable(tclass) && tcp_bpf_ca_needs_ecn((struct sock *)req)) tclass |= INET_ECN_ECT_0; rcu_read_lock(); opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt, tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } done: return err; } static void tcp_v6_reqsk_destructor(struct request_sock *req) { kfree(inet_rsk(req)->ipv6_opt); consume_skb(inet_rsk(req)->pktopts); } #ifdef CONFIG_TCP_MD5SIG static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, const struct in6_addr *addr, int l3index) { return tcp_md5_do_lookup(sk, l3index, (union tcp_md5_addr *)addr, AF_INET6); } static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { int l3index; l3index = l3mdev_master_ifindex_by_index(sock_net(sk), addr_sk->sk_bound_dev_if); return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr, l3index); } static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; int l3index = 0; u8 prefixlen; u8 flags; if (optlen < sizeof(cmd)) return -EINVAL; if (copy_from_sockptr(&cmd, optval, sizeof(cmd))) return -EFAULT; if (sin6->sin6_family != AF_INET6) return -EINVAL; flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; if (optname == TCP_MD5SIG_EXT && cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { prefixlen = cmd.tcpm_prefixlen; if (prefixlen > 128 || (ipv6_addr_v4mapped(&sin6->sin6_addr) && prefixlen > 32)) return -EINVAL; } else { prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128; } if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex && cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex); if (dev && netif_is_l3_master(dev)) l3index = dev->ifindex; rcu_read_unlock(); /* ok to reference set/not set outside of rcu; * right now device MUST be an L3 master */ if (!dev || !l3index) return -EINVAL; } if (!cmd.tcpm_keylen) { if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], AF_INET, prefixlen, l3index, flags); return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr, AF_INET6, prefixlen, l3index, flags); } if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], AF_INET, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr, AF_INET6, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp, const struct in6_addr *daddr, const struct in6_addr *saddr, const struct tcphdr *th, int nbytes) { struct tcp6_pseudohdr *bp; struct scatterlist sg; struct tcphdr *_th; bp = hp->scratch; /* 1. TCP pseudo-header (RFC2460) */ bp->saddr = *saddr; bp->daddr = *daddr; bp->protocol = cpu_to_be32(IPPROTO_TCP); bp->len = cpu_to_be32(nbytes); _th = (struct tcphdr *)(bp + 1); memcpy(_th, th, sizeof(*th)); _th->check = 0; sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th)); ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(*bp) + sizeof(*th)); return crypto_ahash_update(hp->md5_req); } static int tcp_v6_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, const struct in6_addr *daddr, struct in6_addr *saddr, const struct tcphdr *th) { struct tcp_md5sig_pool *hp; struct ahash_request *req; hp = tcp_get_md5sig_pool(); if (!hp) goto clear_hash_noput; req = hp->md5_req; if (crypto_ahash_init(req)) goto clear_hash; if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(hp, key)) goto clear_hash; ahash_request_set_crypt(req, NULL, md5_hash, 0); if (crypto_ahash_final(req)) goto clear_hash; tcp_put_md5sig_pool(); return 0; clear_hash: tcp_put_md5sig_pool(); clear_hash_noput: memset(md5_hash, 0, 16); return 1; } static int tcp_v6_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb) { const struct in6_addr *saddr, *daddr; struct tcp_md5sig_pool *hp; struct ahash_request *req; const struct tcphdr *th = tcp_hdr(skb); if (sk) { /* valid for establish/request sockets */ saddr = &sk->sk_v6_rcv_saddr; daddr = &sk->sk_v6_daddr; } else { const struct ipv6hdr *ip6h = ipv6_hdr(skb); saddr = &ip6h->saddr; daddr = &ip6h->daddr; } hp = tcp_get_md5sig_pool(); if (!hp) goto clear_hash_noput; req = hp->md5_req; if (crypto_ahash_init(req)) goto clear_hash; if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, skb->len)) goto clear_hash; if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(hp, key)) goto clear_hash; ahash_request_set_crypt(req, NULL, md5_hash, 0); if (crypto_ahash_final(req)) goto clear_hash; tcp_put_md5sig_pool(); return 0; clear_hash: tcp_put_md5sig_pool(); clear_hash_noput: memset(md5_hash, 0, 16); return 1; } #endif static void tcp_v6_init_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb) { bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); struct inet_request_sock *ireq = inet_rsk(req); const struct ipv6_pinfo *np = tcp_inet6_sk(sk_listener); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; /* So that link locals have meaning */ if ((!sk_listener->sk_bound_dev_if || l3_slave) && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = tcp_v6_iif(skb); if (!TCP_SKB_CB(skb)->tcp_tw_isn && (ipv6_opt_accepted(sk_listener, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || np->repflow)) { refcount_inc(&skb->users); ireq->pktopts = skb; } } static struct dst_entry *tcp_v6_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct request_sock *req) { tcp_v6_init_req(req, sk, skb); if (security_inet_conn_request(sk, skb, req)) return NULL; return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP); } struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .family = AF_INET6, .obj_size = sizeof(struct tcp6_request_sock), .rtx_syn_ack = tcp_rtx_synack, .send_ack = tcp_v6_reqsk_send_ack, .destructor = tcp_v6_reqsk_destructor, .send_reset = tcp_v6_send_reset, .syn_ack_timeout = tcp_syn_ack_timeout, }; const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr), #ifdef CONFIG_TCP_MD5SIG .req_md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, #endif #ifdef CONFIG_SYN_COOKIES .cookie_init_seq = cookie_v6_init_sequence, #endif .route_req = tcp_v6_route_req, .init_seq = tcp_v6_init_seq, .init_ts_off = tcp_v6_init_ts_off, .send_synack = tcp_v6_send_synack, }; static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int rst, u8 tclass, __be32 label, u32 priority, u32 txhash) { const struct tcphdr *th = tcp_hdr(skb); struct tcphdr *t1; struct sk_buff *buff; struct flowi6 fl6; struct net *net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); struct sock *ctl_sk = net->ipv6.tcp_sk; unsigned int tot_len = sizeof(struct tcphdr); __be32 mrst = 0, *topt; struct dst_entry *dst; __u32 mark = 0; if (tsecr) tot_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG if (key) tot_len += TCPOLEN_MD5SIG_ALIGNED; #endif #ifdef CONFIG_MPTCP if (rst && !key) { mrst = mptcp_reset_option(skb); if (mrst) tot_len += sizeof(__be32); } #endif buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); if (!buff) return; skb_reserve(buff, MAX_TCP_HEADER); t1 = skb_push(buff, tot_len); skb_reset_transport_header(buff); /* Swap the send and the receive. */ memset(t1, 0, sizeof(*t1)); t1->dest = th->source; t1->source = th->dest; t1->doff = tot_len / 4; t1->seq = htonl(seq); t1->ack_seq = htonl(ack); t1->ack = !rst || !th->ack; t1->rst = rst; t1->window = htons(win); topt = (__be32 *)(t1 + 1); if (tsecr) { *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); *topt++ = htonl(tsval); *topt++ = htonl(tsecr); } if (mrst) *topt++ = mrst; #ifdef CONFIG_TCP_MD5SIG if (key) { *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); tcp_v6_md5_hash_hdr((__u8 *)topt, key, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, t1); } #endif memset(&fl6, 0, sizeof(fl6)); fl6.daddr = ipv6_hdr(skb)->saddr; fl6.saddr = ipv6_hdr(skb)->daddr; fl6.flowlabel = label; buff->ip_summed = CHECKSUM_PARTIAL; __tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr); fl6.flowi6_proto = IPPROTO_TCP; if (rt6_need_strict(&fl6.daddr) && !oif) fl6.flowi6_oif = tcp_v6_iif(skb); else { if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) oif = skb->skb_iif; fl6.flowi6_oif = oif; } if (sk) { if (sk->sk_state == TCP_TIME_WAIT) mark = inet_twsk(sk)->tw_mark; else mark = sk->sk_mark; skb_set_delivery_time(buff, tcp_transmit_time(sk), true); } if (txhash) { /* autoflowlabel/skb_get_hash_flowi6 rely on buff->hash */ skb_set_hash(buff, txhash, PKT_HASH_TYPE_L4); } fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark) ?: mark; fl6.fl6_dport = t1->dest; fl6.fl6_sport = t1->source; fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6)); /* Pass a socket to ip6_dst_lookup either it is for RST * Underlying function will use this to retrieve the network * namespace */ if (sk && sk->sk_state != TCP_TIME_WAIT) dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL); /*sk's xfrm_policy can be referred*/ else dst = ip6_dst_lookup_flow(net, ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass & ~INET_ECN_MASK, priority); TCP_INC_STATS(net, TCP_MIB_OUTSEGS); if (rst) TCP_INC_STATS(net, TCP_MIB_OUTRSTS); return; } kfree_skb(buff); } static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); struct ipv6hdr *ipv6h = ipv6_hdr(skb); u32 seq = 0, ack_seq = 0; struct tcp_md5sig_key *key = NULL; #ifdef CONFIG_TCP_MD5SIG const __u8 *hash_location = NULL; unsigned char newhash[16]; int genhash; struct sock *sk1 = NULL; #endif __be32 label = 0; u32 priority = 0; struct net *net; u32 txhash = 0; int oif = 0; if (th->rst) return; /* If sk not NULL, it means we did a successful lookup and incoming * route had to be correct. prequeue might have dropped our dst. */ if (!sk && !ipv6_unicast_destination(skb)) return; net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); hash_location = tcp_parse_md5sig_option(th); if (sk && sk_fullsock(sk)) { int l3index; /* sdif set, means packet ingressed via a device * in an L3 domain and inet_iif is set to it. */ l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr, l3index); } else if (hash_location) { int dif = tcp_v6_iif_l3_slave(skb); int sdif = tcp_v6_sdif(skb); int l3index; /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. * we are not loose security here: * Incoming packet is checked with md5 hash with finding key, * no RST generated if md5 hash doesn't match. */ sk1 = inet6_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, NULL, 0, &ipv6h->saddr, th->source, &ipv6h->daddr, ntohs(th->source), dif, sdif); if (!sk1) goto out; /* sdif set, means packet ingressed via a device * in an L3 domain and dif is set to it. */ l3index = tcp_v6_sdif(skb) ? dif : 0; key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr, l3index); if (!key) goto out; genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto out; } #endif if (th->ack) seq = ntohl(th->ack_seq); else ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); if (sk) { oif = sk->sk_bound_dev_if; if (sk_fullsock(sk)) { const struct ipv6_pinfo *np = tcp_inet6_sk(sk); trace_tcp_send_reset(sk, skb); if (np->repflow) label = ip6_flowlabel(ipv6h); priority = sk->sk_priority; txhash = sk->sk_hash; } if (sk->sk_state == TCP_TIME_WAIT) { label = cpu_to_be32(inet_twsk(sk)->tw_flowlabel); priority = inet_twsk(sk)->tw_priority; txhash = inet_twsk(sk)->tw_txhash; } } else { if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_TCP_RESET) label = ip6_flowlabel(ipv6h); } tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, ipv6_get_dsfield(ipv6h), label, priority, txhash); #ifdef CONFIG_TCP_MD5SIG out: rcu_read_unlock(); #endif } static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, u8 tclass, __be32 label, u32 priority, u32 txhash) { tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0, tclass, label, priority, txhash); } static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) { struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp_raw() + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority, tw->tw_txhash); inet_twsk_put(tw); } static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { int l3index; l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ /* RFC 7323 2.3 * The window field (SEG.WND) of every outgoing segment, with the * exception of <SYN> segments, MUST be right-shifted by * Rcv.Wind.Shift bits: */ tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority, tcp_rsk(req)->txhash); } static struct sock *tcp_v6_cookie_check(struct sock *sk, struct sk_buff *skb) { #ifdef CONFIG_SYN_COOKIES const struct tcphdr *th = tcp_hdr(skb); if (!th->syn) sk = cookie_v6_check(sk, skb); #endif return sk; } u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie) { u16 mss = 0; #ifdef CONFIG_SYN_COOKIES mss = tcp_get_syncookie_mss(&tcp6_request_sock_ops, &tcp_request_sock_ipv6_ops, sk, th); if (mss) { *cookie = __cookie_v6_init_sequence(iph, th, &mss); tcp_synq_overflow(sk); } #endif return mss; } static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_conn_request(sk, skb); if (!ipv6_unicast_destination(skb)) goto drop; if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); return 0; } return tcp_conn_request(&tcp6_request_sock_ops, &tcp_request_sock_ipv6_ops, sk, skb); drop: tcp_listendrop(sk); return 0; /* don't send reset */ } static void tcp_v6_restore_cb(struct sk_buff *skb) { /* We need to move header back to the beginning if xfrm6_policy_check() * and tcp_v6_fill_cb() are going to be called again. * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there. */ memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6, sizeof(struct inet6_skb_parm)); } static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req) { struct inet_request_sock *ireq; struct ipv6_pinfo *newnp; const struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct ipv6_txoptions *opt; struct inet_sock *newinet; bool found_dup_sk = false; struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; int l3index; #endif struct flowi6 fl6; if (skb->protocol == htons(ETH_P_IP)) { /* * v6 mapped */ newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst, req_unhash, own_req); if (!newsk) return NULL; inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk); newnp = tcp_inet6_sk(newsk); newtp = tcp_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); newnp->saddr = newsk->sk_v6_rcv_saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; if (sk_is_mptcp(newsk)) mptcpv6_handle_mapped(newsk, true); newsk->sk_backlog_rcv = tcp_v4_do_rcv; #ifdef CONFIG_TCP_MD5SIG newtp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = inet_iif(skb); newnp->mcast_hops = ip_hdr(skb)->ttl; newnp->rcv_flowinfo = 0; if (np->repflow) newnp->flow_label = 0; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count * here, tcp_create_openreq_child now does this for us, see the comment in * that function for the gory details. -acme */ /* It is tricky place. Until this moment IPv4 tcp worked with IPv6 icsk.icsk_af_ops. Sync it now. */ tcp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie); return newsk; } ireq = inet_rsk(req); if (sk_acceptq_is_full(sk)) goto out_overflow; if (!dst) { dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_TCP); if (!dst) goto out; } newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) goto out_nonewsk; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks * count here, tcp_create_openreq_child now does this for us, see the * comment in that function for the gory details. -acme */ newsk->sk_gso_type = SKB_GSO_TCPV6; ip6_dst_store(newsk, dst, NULL, NULL); inet6_sk_rx_dst_set(newsk, skb); inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk); newtp = tcp_sk(newsk); newinet = inet_sk(newsk); newnp = tcp_inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr; newnp->saddr = ireq->ir_v6_loc_addr; newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; newsk->sk_bound_dev_if = ireq->ir_iif; /* Now IPv6 options... First: no IPv4 options. */ newinet->inet_opt = NULL; newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = tcp_v6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); if (np->repflow) newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). */ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)) newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; /* Clone native IPv6 options from listening socket (if any) Yes, keeping reference count would be much more clever, but we make one more one thing there: reattach optmem to newsk. */ opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); if (opt) { opt = ipv6_dup_options(newsk, opt); RCU_INIT_POINTER(newnp->opt, opt); } inet_csk(newsk)->icsk_ext_hdr_len = 0; if (opt) inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen + opt->opt_flen; tcp_ca_openreq_child(newsk, dst); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst)); tcp_initialize_rcv_mss(newsk); newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; newinet->inet_rcv_saddr = LOOPBACK4_IPV6; #ifdef CONFIG_TCP_MD5SIG l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); /* Copy over the MD5 key from the original socket */ key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr, l3index); if (key) { /* We're using one, so create a matching key * on the newsk structure. If we fail to get * memory, then we end up not copying the key * across. Shucks. */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, AF_INET6, 128, l3index, key->flags, key->key, key->keylen, sk_gfp_mask(sk, GFP_ATOMIC)); } #endif if (__inet_inherit_port(sk, newsk) < 0) { inet_csk_prepare_forced_close(newsk); tcp_done(newsk); goto out; } *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), &found_dup_sk); if (*own_req) { tcp_move_syn(newtp, req); /* Clone pktoptions received with SYN, if we own the req */ if (ireq->pktopts) { newnp->pktoptions = skb_clone(ireq->pktopts, sk_gfp_mask(sk, GFP_ATOMIC)); consume_skb(ireq->pktopts); ireq->pktopts = NULL; if (newnp->pktoptions) { tcp_v6_restore_cb(newnp->pktoptions); skb_set_owner_r(newnp->pktoptions, newsk); } } } else { if (!req_unhash && found_dup_sk) { /* This code path should only be executed in the * syncookie case only */ bh_unlock_sock(newsk); sock_put(newsk); newsk = NULL; } } return newsk; out_overflow: __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); out_nonewsk: dst_release(dst); out: tcp_listendrop(sk); return NULL; } INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * * We have a potential double-lock case here, so even when * doing backlog processing we use the BH locking scheme. * This is because we cannot sleep with the original spinlock * held. */ INDIRECT_CALLABLE_SCOPE int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct sk_buff *opt_skb = NULL; enum skb_drop_reason reason; struct tcp_sock *tp; /* Imagine: socket is IPv6. IPv4 packet arrives, goes to IPv4 receive handler and backlogged. From backlog it always goes here. Kerboom... Fortunately, tcp_rcv_established and rcv_established handle them correctly, but it is not case with tcp_v6_hnd_req and tcp_v6_send_reset(). --ANK */ if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); /* * socket locking is here for SMP purposes as backlog rcv * is currently called with bh processing disabled. */ /* Do Stevens' IPV6_PKTOPTIONS. Yes, guys, it is the only place in our code, where we may make it not affecting IPv4. The rest of code is protocol independent, and I do not like idea to uglify IPv4. Actually, all the idea behind IPV6_PKTOPTIONS looks not very well thought. For now we latch options, received in the last packet, enqueued by tcp. Feel free to propose better solution. --ANK (980728) */ if (np->rxopt.all) opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); reason = SKB_DROP_REASON_NOT_SPECIFIED; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; dst = rcu_dereference_protected(sk->sk_rx_dst, lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (sk->sk_rx_dst_ifindex != skb->skb_iif || INDIRECT_CALL_1(dst->ops->check, ip6_dst_check, dst, sk->sk_rx_dst_cookie) == NULL) { RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); } } tcp_rcv_established(sk, skb); if (opt_skb) goto ipv6_pktoptions; return 0; } if (tcp_checksum_complete(skb)) goto csum_err; if (sk->sk_state == TCP_LISTEN) { struct sock *nsk = tcp_v6_cookie_check(sk, skb); if (!nsk) goto discard; if (nsk != sk) { if (tcp_child_process(sk, nsk, skb)) goto reset; if (opt_skb) __kfree_skb(opt_skb); return 0; } } else sock_rps_save_rxhash(sk, skb); if (tcp_rcv_state_process(sk, skb)) goto reset; if (opt_skb) goto ipv6_pktoptions; return 0; reset: tcp_v6_send_reset(sk, skb); discard: if (opt_skb) __kfree_skb(opt_skb); kfree_skb_reason(skb, reason); return 0; csum_err: reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; ipv6_pktoptions: /* Do you ask, what is it? 1. skb was enqueued by tcp. 2. skb is added to tail of read queue, rather than out of order. 3. socket is not in passive state. 4. Finally, it really contains options, which user wants to receive. */ tp = tcp_sk(sk); if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo) np->mcast_oif = tcp_v6_iif(opt_skb); if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit; if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass) np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb)); if (np->repflow) np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) { skb_set_owner_r(opt_skb, sk); tcp_v6_restore_cb(opt_skb); opt_skb = xchg(&np->pktoptions, opt_skb); } else { __kfree_skb(opt_skb); opt_skb = xchg(&np->pktoptions, NULL); } } consume_skb(opt_skb); return 0; } static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr, const struct tcphdr *th) { /* This is tricky: we move IP6CB at its correct location into * TCP_SKB_CB(). It must be done after xfrm6_policy_check(), because * _decode_session6() uses IP6CB(). * barrier() makes sure compiler won't play aliasing games. */ memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb), sizeof(struct inet6_skb_parm)); barrier(); TCP_SKB_CB(skb)->seq = ntohl(th->seq); TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + skb->len - th->doff*4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); TCP_SKB_CB(skb)->tcp_tw_isn = 0; TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr); TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = skb->tstamp || skb_hwtstamps(skb)->hwtstamp; } INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) { enum skb_drop_reason drop_reason; int sdif = inet6_sdif(skb); int dif = inet6_iif(skb); const struct tcphdr *th; const struct ipv6hdr *hdr; bool refcounted; struct sock *sk; int ret; struct net *net = dev_net(skb->dev); drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (skb->pkt_type != PACKET_HOST) goto discard_it; /* * Count it even if it's bad. */ __TCP_INC_STATS(net, TCP_MIB_INSEGS); if (!pskb_may_pull(skb, sizeof(struct tcphdr))) goto discard_it; th = (const struct tcphdr *)skb->data; if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) { drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; goto bad_packet; } if (!pskb_may_pull(skb, th->doff*4)) goto discard_it; if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo)) goto csum_error; th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); lookup: sk = __inet6_lookup_skb(net->ipv4.tcp_death_row.hashinfo, skb, __tcp_hdrlen(th), th->source, th->dest, inet6_iif(skb), sdif, &refcounted); if (!sk) goto no_tcp_socket; process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; drop_reason = tcp_inbound_md5_hash(sk, skb, &hdr->saddr, &hdr->daddr, AF_INET6, dif, sdif); if (drop_reason) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; } if (tcp_checksum_complete(skb)) { reqsk_put(req); goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb); if (!nsk) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } sk = nsk; /* reuseport_migrate_sock() has already held one sk_refcnt * before returning. */ } else { sock_hold(sk); } refcounted = true; nsk = NULL; if (!tcp_filter(sk, skb)) { th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); nsk = tcp_check_req(sk, skb, req, false, &req_stolen); } else { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; } if (!nsk) { reqsk_put(req); if (req_stolen) { /* Another cpu got exclusive access to req * and created a full blown socket. * Try to feed this packet to this socket * instead of discarding it. */ tcp_v6_restore_cb(skb); sock_put(sk); goto lookup; } goto discard_and_relse; } if (nsk == sk) { reqsk_put(req); tcp_v6_restore_cb(skb); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v6_send_reset(nsk, skb); goto discard_and_relse; } else { sock_put(sk); return 0; } } if (static_branch_unlikely(&ip6_min_hopcount)) { /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */ if (hdr->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount)) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); goto discard_and_relse; } } if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto discard_and_relse; } drop_reason = tcp_inbound_md5_hash(sk, skb, &hdr->saddr, &hdr->daddr, AF_INET6, dif, sdif); if (drop_reason) goto discard_and_relse; if (tcp_filter(sk, skb)) { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto discard_and_relse; } th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); skb->dev = NULL; if (sk->sk_state == TCP_LISTEN) { ret = tcp_v6_do_rcv(sk, skb); goto put_and_return; } sk_incoming_cpu_update(sk); bh_lock_sock_nested(sk); tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { ret = tcp_v6_do_rcv(sk, skb); } else { if (tcp_add_backlog(sk, skb, &drop_reason)) goto discard_and_relse; } bh_unlock_sock(sk); put_and_return: if (refcounted) sock_put(sk); return ret ? -1 : 0; no_tcp_socket: drop_reason = SKB_DROP_REASON_NO_SOCKET; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; tcp_v6_fill_cb(skb, hdr, th); if (tcp_checksum_complete(skb)) { csum_error: drop_reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); } else { tcp_v6_send_reset(NULL, skb); } discard_it: SKB_DR_OR(drop_reason, NOT_SPECIFIED); kfree_skb_reason(skb, drop_reason); return 0; discard_and_relse: sk_drops_add(sk, skb); if (refcounted) sock_put(sk); goto discard_it; do_time_wait: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; inet_twsk_put(inet_twsk(sk)); goto discard_it; } tcp_v6_fill_cb(skb, hdr, th); if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; } switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { case TCP_TW_SYN: { struct sock *sk2; sk2 = inet6_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, skb, __tcp_hdrlen(th), &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, ntohs(th->dest), tcp_v6_iif_l3_slave(skb), sdif); if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); inet_twsk_deschedule_put(tw); sk = sk2; tcp_v6_restore_cb(skb); refcounted = false; goto process; } } /* to ACK */ fallthrough; case TCP_TW_ACK: tcp_v6_timewait_ack(sk, skb); break; case TCP_TW_RST: tcp_v6_send_reset(sk, skb); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it; case TCP_TW_SUCCESS: ; } goto discard_it; } void tcp_v6_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); const struct ipv6hdr *hdr; const struct tcphdr *th; struct sock *sk; if (skb->pkt_type != PACKET_HOST) return; if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) return; hdr = ipv6_hdr(skb); th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) return; /* Note : We use inet6_iif() here, not tcp_v6_iif() */ sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &hdr->saddr, th->source, &hdr->daddr, ntohs(th->dest), inet6_iif(skb), inet6_sdif(skb)); if (sk) { skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, sk->sk_rx_dst_cookie); if (dst && sk->sk_rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } } static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), .twsk_unique = tcp_twsk_unique, .twsk_destructor = tcp_twsk_destructor, }; INDIRECT_CALLABLE_SCOPE void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) { __tcp_v6_send_check(skb, &sk->sk_v6_rcv_saddr, &sk->sk_v6_daddr); } const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, .sk_rx_dst_set = inet6_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct ipv6hdr), .net_frag_header_len = sizeof(struct frag_hdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6), .mtu_reduced = tcp_v6_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = { .md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, .md5_parse = tcp_v6_parse_md5_keys, }; #endif /* * TCP over IPv4 via INET6 API */ static const struct inet_connection_sock_af_ops ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct iphdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6), .mtu_reduced = tcp_v4_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_parse = tcp_v6_parse_md5_keys, }; #endif /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ static int tcp_v6_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_init_sock(sk); icsk->icsk_af_ops = &ipv6_specific; #ifdef CONFIG_TCP_MD5SIG tcp_sk(sk)->af_specific = &tcp_sock_ipv6_specific; #endif return 0; } static void tcp_v6_destroy_sock(struct sock *sk) { tcp_v4_destroy_sock(sk); inet6_destroy_sock(sk); } #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, const struct request_sock *req, int i) { long ttd = req->rsk_timer.expires - jiffies; const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr; const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr; if (ttd < 0) ttd = 0; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], inet_rsk(req)->ir_num, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], ntohs(inet_rsk(req)->ir_rmt_port), TCP_SYN_RECV, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_to_clock_t(ttd), req->num_timeout, from_kuid_munged(seq_user_ns(seq), sock_i_uid(req->rsk_listener)), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); } static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) { const struct in6_addr *dest, *src; __u16 destp, srcp; int timer_active; unsigned long timer_expires; const struct inet_sock *inet = inet_sk(sp); const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; int rx_queue; int state; dest = &sp->sk_v6_daddr; src = &sp->sk_v6_rcv_saddr; destp = ntohs(inet->inet_dport); srcp = ntohs(inet->inet_sport); if (icsk->icsk_pending == ICSK_TIME_RETRANS || icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; timer_expires = icsk->icsk_timeout; } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; timer_expires = icsk->icsk_timeout; } else if (timer_pending(&sp->sk_timer)) { timer_active = 2; timer_expires = sp->sk_timer.expires; } else { timer_active = 0; timer_expires = jiffies; } state = inet_sk_state_load(sp); if (state == TCP_LISTEN) rx_queue = READ_ONCE(sp->sk_ack_backlog); else /* Because we don't lock the socket, * we might find a transient negative value. */ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq), 0); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %lu %lu %u %u %d\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, state, READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), icsk->icsk_probes_out, sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sp), tcp_snd_cwnd(tp), state == TCP_LISTEN ? fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) ); } static void get_timewait6_sock(struct seq_file *seq, struct inet_timewait_sock *tw, int i) { long delta = tw->tw_timer.expires - jiffies; const struct in6_addr *dest, *src; __u16 destp, srcp; dest = &tw->tw_v6_daddr; src = &tw->tw_v6_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, tw->tw_substate, 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, refcount_read(&tw->tw_refcnt), tw); } static int tcp6_seq_show(struct seq_file *seq, void *v) { struct tcp_iter_state *st; struct sock *sk = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, " sl " "local_address " "remote_address " "st tx_queue rx_queue tr tm->when retrnsmt" " uid timeout inode\n"); goto out; } st = seq->private; if (sk->sk_state == TCP_TIME_WAIT) get_timewait6_sock(seq, v, st->num); else if (sk->sk_state == TCP_NEW_SYN_RECV) get_openreq6(seq, v, st->num); else get_tcp6_sock(seq, v, st->num); out: return 0; } static const struct seq_operations tcp6_seq_ops = { .show = tcp6_seq_show, .start = tcp_seq_start, .next = tcp_seq_next, .stop = tcp_seq_stop, }; static struct tcp_seq_afinfo tcp6_seq_afinfo = { .family = AF_INET6, }; int __net_init tcp6_proc_init(struct net *net) { if (!proc_create_net_data("tcp6", 0444, net->proc_net, &tcp6_seq_ops, sizeof(struct tcp_iter_state), &tcp6_seq_afinfo)) return -ENOMEM; return 0; } void tcp6_proc_exit(struct net *net) { remove_proc_entry("tcp6", net->proc_net); } #endif struct proto tcpv6_prot = { .name = "TCPv6", .owner = THIS_MODULE, .close = tcp_close, .pre_connect = tcp_v6_pre_connect, .connect = tcp_v6_connect, .disconnect = tcp_disconnect, .accept = inet_csk_accept, .ioctl = tcp_ioctl, .init = tcp_v6_init_sock, .destroy = tcp_v6_destroy_sock, .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, .hash = inet6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .put_port = inet_put_port, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = tcp_bpf_update_proto, #endif .enter_memory_pressure = tcp_enter_memory_pressure, .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, .memory_pressure = &tcp_memory_pressure, .orphan_count = &tcp_orphan_count, .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, .twsk_prot = &tcp6_timewait_sock_ops, .rsk_prot = &tcp6_request_sock_ops, .h.hashinfo = NULL, .no_autobind = true, .diag_destroy = tcp_abort, }; EXPORT_SYMBOL_GPL(tcpv6_prot); static const struct inet6_protocol tcpv6_protocol = { .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; static struct inet_protosw tcpv6_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_TCP, .prot = &tcpv6_prot, .ops = &inet6_stream_ops, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, }; static int __net_init tcpv6_net_init(struct net *net) { return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, SOCK_RAW, IPPROTO_TCP, net); } static void __net_exit tcpv6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.tcp_sk); } static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) { tcp_twsk_purge(net_exit_list, AF_INET6); } static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, .exit_batch = tcpv6_net_exit_batch, }; int __init tcpv6_init(void) { int ret; ret = inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP); if (ret) goto out; /* register inet6 protocol */ ret = inet6_register_protosw(&tcpv6_protosw); if (ret) goto out_tcpv6_protocol; ret = register_pernet_subsys(&tcpv6_net_ops); if (ret) goto out_tcpv6_protosw; ret = mptcpv6_init(); if (ret) goto out_tcpv6_pernet_subsys; out: return ret; out_tcpv6_pernet_subsys: unregister_pernet_subsys(&tcpv6_net_ops); out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); out_tcpv6_protocol: inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); goto out; } void tcpv6_exit(void) { unregister_pernet_subsys(&tcpv6_net_ops); inet6_unregister_protosw(&tcpv6_protosw); inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); } |
| 12 12 12 12 12 12 12 12 18 18 18 18 18 12 12 12 56 56 56 50 50 56 56 50 56 56 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 | // SPDX-License-Identifier: GPL-2.0 #define CREATE_TRACE_POINTS #include <trace/events/mmap_lock.h> #include <linux/mm.h> #include <linux/cgroup.h> #include <linux/memcontrol.h> #include <linux/mmap_lock.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/smp.h> #include <linux/trace_events.h> #include <linux/local_lock.h> EXPORT_TRACEPOINT_SYMBOL(mmap_lock_start_locking); EXPORT_TRACEPOINT_SYMBOL(mmap_lock_acquire_returned); EXPORT_TRACEPOINT_SYMBOL(mmap_lock_released); #ifdef CONFIG_MEMCG /* * Our various events all share the same buffer (because we don't want or need * to allocate a set of buffers *per event type*), so we need to protect against * concurrent _reg() and _unreg() calls, and count how many _reg() calls have * been made. */ static DEFINE_MUTEX(reg_lock); static int reg_refcount; /* Protected by reg_lock. */ /* * Size of the buffer for memcg path names. Ignoring stack trace support, * trace_events_hist.c uses MAX_FILTER_STR_VAL for this, so we also use it. */ #define MEMCG_PATH_BUF_SIZE MAX_FILTER_STR_VAL /* * How many contexts our trace events might be called in: normal, softirq, irq, * and NMI. */ #define CONTEXT_COUNT 4 struct memcg_path { local_lock_t lock; char __rcu *buf; local_t buf_idx; }; static DEFINE_PER_CPU(struct memcg_path, memcg_paths) = { .lock = INIT_LOCAL_LOCK(lock), .buf_idx = LOCAL_INIT(0), }; static char **tmp_bufs; /* Called with reg_lock held. */ static void free_memcg_path_bufs(void) { struct memcg_path *memcg_path; int cpu; char **old = tmp_bufs; for_each_possible_cpu(cpu) { memcg_path = per_cpu_ptr(&memcg_paths, cpu); *(old++) = rcu_dereference_protected(memcg_path->buf, lockdep_is_held(®_lock)); rcu_assign_pointer(memcg_path->buf, NULL); } /* Wait for inflight memcg_path_buf users to finish. */ synchronize_rcu(); old = tmp_bufs; for_each_possible_cpu(cpu) { kfree(*(old++)); } kfree(tmp_bufs); tmp_bufs = NULL; } int trace_mmap_lock_reg(void) { int cpu; char *new; mutex_lock(®_lock); /* If the refcount is going 0->1, proceed with allocating buffers. */ if (reg_refcount++) goto out; tmp_bufs = kmalloc_array(num_possible_cpus(), sizeof(*tmp_bufs), GFP_KERNEL); if (tmp_bufs == NULL) goto out_fail; for_each_possible_cpu(cpu) { new = kmalloc(MEMCG_PATH_BUF_SIZE * CONTEXT_COUNT, GFP_KERNEL); if (new == NULL) goto out_fail_free; rcu_assign_pointer(per_cpu_ptr(&memcg_paths, cpu)->buf, new); /* Don't need to wait for inflights, they'd have gotten NULL. */ } out: mutex_unlock(®_lock); return 0; out_fail_free: free_memcg_path_bufs(); out_fail: /* Since we failed, undo the earlier ref increment. */ --reg_refcount; mutex_unlock(®_lock); return -ENOMEM; } void trace_mmap_lock_unreg(void) { mutex_lock(®_lock); /* If the refcount is going 1->0, proceed with freeing buffers. */ if (--reg_refcount) goto out; free_memcg_path_bufs(); out: mutex_unlock(®_lock); } static inline char *get_memcg_path_buf(void) { struct memcg_path *memcg_path = this_cpu_ptr(&memcg_paths); char *buf; int idx; rcu_read_lock(); buf = rcu_dereference(memcg_path->buf); if (buf == NULL) { rcu_read_unlock(); return NULL; } idx = local_add_return(MEMCG_PATH_BUF_SIZE, &memcg_path->buf_idx) - MEMCG_PATH_BUF_SIZE; return &buf[idx]; } static inline void put_memcg_path_buf(void) { local_sub(MEMCG_PATH_BUF_SIZE, &this_cpu_ptr(&memcg_paths)->buf_idx); rcu_read_unlock(); } #define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ do { \ const char *memcg_path; \ local_lock(&memcg_paths.lock); \ memcg_path = get_mm_memcg_path(mm); \ trace_mmap_lock_##type(mm, \ memcg_path != NULL ? memcg_path : "", \ ##__VA_ARGS__); \ if (likely(memcg_path != NULL)) \ put_memcg_path_buf(); \ local_unlock(&memcg_paths.lock); \ } while (0) #else /* !CONFIG_MEMCG */ int trace_mmap_lock_reg(void) { return 0; } void trace_mmap_lock_unreg(void) { } #define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ trace_mmap_lock_##type(mm, "", ##__VA_ARGS__) #endif /* CONFIG_MEMCG */ #ifdef CONFIG_TRACING #ifdef CONFIG_MEMCG /* * Write the given mm_struct's memcg path to a percpu buffer, and return a * pointer to it. If the path cannot be determined, or no buffer was available * (because the trace event is being unregistered), NULL is returned. * * Note: buffers are allocated per-cpu to avoid locking, so preemption must be * disabled by the caller before calling us, and re-enabled only after the * caller is done with the pointer. * * The caller must call put_memcg_path_buf() once the buffer is no longer * needed. This must be done while preemption is still disabled. */ static const char *get_mm_memcg_path(struct mm_struct *mm) { char *buf = NULL; struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm); if (memcg == NULL) goto out; if (unlikely(memcg->css.cgroup == NULL)) goto out_put; buf = get_memcg_path_buf(); if (buf == NULL) goto out_put; cgroup_path(memcg->css.cgroup, buf, MEMCG_PATH_BUF_SIZE); out_put: css_put(&memcg->css); out: return buf; } #endif /* CONFIG_MEMCG */ /* * Trace calls must be in a separate file, as otherwise there's a circular * dependency between linux/mmap_lock.h and trace/events/mmap_lock.h. */ void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write) { TRACE_MMAP_LOCK_EVENT(start_locking, mm, write); } EXPORT_SYMBOL(__mmap_lock_do_trace_start_locking); void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write, bool success) { TRACE_MMAP_LOCK_EVENT(acquire_returned, mm, write, success); } EXPORT_SYMBOL(__mmap_lock_do_trace_acquire_returned); void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write) { TRACE_MMAP_LOCK_EVENT(released, mm, write); } EXPORT_SYMBOL(__mmap_lock_do_trace_released); #endif /* CONFIG_TRACING */ |
| 133 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Because linux/module.h has tracepoints in the header, and ftrace.h * used to include this file, define_trace.h includes linux/module.h * But we do not want the module.h to override the TRACE_SYSTEM macro * variable that define_trace.h is processing, so we only set it * when module events are being processed, which would happen when * CREATE_TRACE_POINTS is defined. */ #ifdef CREATE_TRACE_POINTS #undef TRACE_SYSTEM #define TRACE_SYSTEM module #endif #if !defined(_TRACE_MODULE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MODULE_H #include <linux/tracepoint.h> #ifdef CONFIG_MODULES struct module; #define show_module_flags(flags) __print_flags(flags, "", \ { (1UL << TAINT_PROPRIETARY_MODULE), "P" }, \ { (1UL << TAINT_OOT_MODULE), "O" }, \ { (1UL << TAINT_FORCED_MODULE), "F" }, \ { (1UL << TAINT_CRAP), "C" }, \ { (1UL << TAINT_UNSIGNED_MODULE), "E" }) TRACE_EVENT(module_load, TP_PROTO(struct module *mod), TP_ARGS(mod), TP_STRUCT__entry( __field( unsigned int, taints ) __string( name, mod->name ) ), TP_fast_assign( __entry->taints = mod->taints; __assign_str(name, mod->name); ), TP_printk("%s %s", __get_str(name), show_module_flags(__entry->taints)) ); TRACE_EVENT(module_free, TP_PROTO(struct module *mod), TP_ARGS(mod), TP_STRUCT__entry( __string( name, mod->name ) ), TP_fast_assign( __assign_str(name, mod->name); ), TP_printk("%s", __get_str(name)) ); #ifdef CONFIG_MODULE_UNLOAD /* trace_module_get/put are only used if CONFIG_MODULE_UNLOAD is defined */ DECLARE_EVENT_CLASS(module_refcnt, TP_PROTO(struct module *mod, unsigned long ip), TP_ARGS(mod, ip), TP_STRUCT__entry( __field( unsigned long, ip ) __field( int, refcnt ) __string( name, mod->name ) ), TP_fast_assign( __entry->ip = ip; __entry->refcnt = atomic_read(&mod->refcnt); __assign_str(name, mod->name); ), TP_printk("%s call_site=%ps refcnt=%d", __get_str(name), (void *)__entry->ip, __entry->refcnt) ); DEFINE_EVENT(module_refcnt, module_get, TP_PROTO(struct module *mod, unsigned long ip), TP_ARGS(mod, ip) ); DEFINE_EVENT(module_refcnt, module_put, TP_PROTO(struct module *mod, unsigned long ip), TP_ARGS(mod, ip) ); #endif /* CONFIG_MODULE_UNLOAD */ TRACE_EVENT(module_request, TP_PROTO(char *name, bool wait, unsigned long ip), TP_ARGS(name, wait, ip), TP_STRUCT__entry( __field( unsigned long, ip ) __field( bool, wait ) __string( name, name ) ), TP_fast_assign( __entry->ip = ip; __entry->wait = wait; __assign_str(name, name); ), TP_printk("%s wait=%d call_site=%ps", __get_str(name), (int)__entry->wait, (void *)__entry->ip) ); #endif /* CONFIG_MODULES */ #endif /* _TRACE_MODULE_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 3 3 2 2 2 5 5 5 2 2 2 2 2 2 3 3 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "queueing.h" #include "timers.h" #include "device.h" #include "peer.h" #include "socket.h" #include "messages.h" #include "cookie.h" #include <linux/uio.h> #include <linux/inetdevice.h> #include <linux/socket.h> #include <net/ip_tunnels.h> #include <net/udp.h> #include <net/sock.h> static void wg_packet_send_handshake_initiation(struct wg_peer *peer) { struct message_handshake_initiation packet; if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake), REKEY_TIMEOUT)) return; /* This function is rate limited. */ atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); net_dbg_ratelimited("%s: Sending handshake initiation to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); if (wg_noise_handshake_create_initiation(&packet, &peer->handshake)) { wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer); wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); wg_socket_send_buffer_to_peer(peer, &packet, sizeof(packet), HANDSHAKE_DSCP); wg_timers_handshake_initiated(peer); } } void wg_packet_handshake_send_worker(struct work_struct *work) { struct wg_peer *peer = container_of(work, struct wg_peer, transmit_handshake_work); wg_packet_send_handshake_initiation(peer); wg_peer_put(peer); } void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer, bool is_retry) { if (!is_retry) peer->timer_handshake_attempts = 0; rcu_read_lock_bh(); /* We check last_sent_handshake here in addition to the actual function * we're queueing up, so that we don't queue things if not strictly * necessary: */ if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake), REKEY_TIMEOUT) || unlikely(READ_ONCE(peer->is_dead))) goto out; wg_peer_get(peer); /* Queues up calling packet_send_queued_handshakes(peer), where we do a * peer_put(peer) after: */ if (!queue_work(peer->device->handshake_send_wq, &peer->transmit_handshake_work)) /* If the work was already queued, we want to drop the * extra reference: */ wg_peer_put(peer); out: rcu_read_unlock_bh(); } void wg_packet_send_handshake_response(struct wg_peer *peer) { struct message_handshake_response packet; atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); net_dbg_ratelimited("%s: Sending handshake response to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); if (wg_noise_handshake_create_response(&packet, &peer->handshake)) { wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer); if (wg_noise_handshake_begin_session(&peer->handshake, &peer->keypairs)) { wg_timers_session_derived(peer); wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); wg_socket_send_buffer_to_peer(peer, &packet, sizeof(packet), HANDSHAKE_DSCP); } } } void wg_packet_send_handshake_cookie(struct wg_device *wg, struct sk_buff *initiating_skb, __le32 sender_index) { struct message_handshake_cookie packet; net_dbg_skb_ratelimited("%s: Sending cookie response for denied handshake message for %pISpfsc\n", wg->dev->name, initiating_skb); wg_cookie_message_create(&packet, initiating_skb, sender_index, &wg->cookie_checker); wg_socket_send_buffer_as_reply_to_skb(wg, initiating_skb, &packet, sizeof(packet)); } static void keep_key_fresh(struct wg_peer *peer) { struct noise_keypair *keypair; bool send; rcu_read_lock_bh(); keypair = rcu_dereference_bh(peer->keypairs.current_keypair); send = keypair && READ_ONCE(keypair->sending.is_valid) && (atomic64_read(&keypair->sending_counter) > REKEY_AFTER_MESSAGES || (keypair->i_am_the_initiator && wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME))); rcu_read_unlock_bh(); if (unlikely(send)) wg_packet_send_queued_handshake_initiation(peer, false); } static unsigned int calculate_skb_padding(struct sk_buff *skb) { unsigned int padded_size, last_unit = skb->len; if (unlikely(!PACKET_CB(skb)->mtu)) return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit; /* We do this modulo business with the MTU, just in case the networking * layer gives us a packet that's bigger than the MTU. In that case, we * wouldn't want the final subtraction to overflow in the case of the * padded_size being clamped. Fortunately, that's very rarely the case, * so we optimize for that not happening. */ if (unlikely(last_unit > PACKET_CB(skb)->mtu)) last_unit %= PACKET_CB(skb)->mtu; padded_size = min(PACKET_CB(skb)->mtu, ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE)); return padded_size - last_unit; } static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) { unsigned int padding_len, plaintext_len, trailer_len; struct scatterlist sg[MAX_SKB_FRAGS + 8]; struct message_data *header; struct sk_buff *trailer; int num_frags; /* Force hash calculation before encryption so that flow analysis is * consistent over the inner packet. */ skb_get_hash(skb); /* Calculate lengths. */ padding_len = calculate_skb_padding(skb); trailer_len = padding_len + noise_encrypted_len(0); plaintext_len = skb->len + padding_len; /* Expand data section to have room for padding and auth tag. */ num_frags = skb_cow_data(skb, trailer_len, &trailer); if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg))) return false; /* Set the padding to zeros, and make sure it and the auth tag are part * of the skb. */ memset(skb_tail_pointer(trailer), 0, padding_len); /* Expand head section to have room for our header and the network * stack's headers. */ if (unlikely(skb_cow_head(skb, DATA_PACKET_HEAD_ROOM) < 0)) return false; /* Finalize checksum calculation for the inner packet, if required. */ if (unlikely(skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))) return false; /* Only after checksumming can we safely add on the padding at the end * and the header. */ skb_set_inner_network_header(skb, 0); header = (struct message_data *)skb_push(skb, sizeof(*header)); header->header.type = cpu_to_le32(MESSAGE_DATA); header->key_idx = keypair->remote_index; header->counter = cpu_to_le64(PACKET_CB(skb)->nonce); pskb_put(skb, trailer, trailer_len); /* Now we can encrypt the scattergather segments */ sg_init_table(sg, num_frags); if (skb_to_sgvec(skb, sg, sizeof(struct message_data), noise_encrypted_len(plaintext_len)) <= 0) return false; return chacha20poly1305_encrypt_sg_inplace(sg, plaintext_len, NULL, 0, PACKET_CB(skb)->nonce, keypair->sending.key); } void wg_packet_send_keepalive(struct wg_peer *peer) { struct sk_buff *skb; if (skb_queue_empty(&peer->staged_packet_queue)) { skb = alloc_skb(DATA_PACKET_HEAD_ROOM + MESSAGE_MINIMUM_LENGTH, GFP_ATOMIC); if (unlikely(!skb)) return; skb_reserve(skb, DATA_PACKET_HEAD_ROOM); skb->dev = peer->device->dev; PACKET_CB(skb)->mtu = skb->dev->mtu; skb_queue_tail(&peer->staged_packet_queue, skb); net_dbg_ratelimited("%s: Sending keepalive packet to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); } wg_packet_send_staged_packets(peer); } static void wg_packet_create_data_done(struct wg_peer *peer, struct sk_buff *first) { struct sk_buff *skb, *next; bool is_keepalive, data_sent = false; wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); skb_list_walk_safe(first, skb, next) { is_keepalive = skb->len == message_data_len(0); if (likely(!wg_socket_send_skb_to_peer(peer, skb, PACKET_CB(skb)->ds) && !is_keepalive)) data_sent = true; } if (likely(data_sent)) wg_timers_data_sent(peer); keep_key_fresh(peer); } void wg_packet_tx_worker(struct work_struct *work) { struct wg_peer *peer = container_of(work, struct wg_peer, transmit_packet_work); struct noise_keypair *keypair; enum packet_state state; struct sk_buff *first; while ((first = wg_prev_queue_peek(&peer->tx_queue)) != NULL && (state = atomic_read_acquire(&PACKET_CB(first)->state)) != PACKET_STATE_UNCRYPTED) { wg_prev_queue_drop_peeked(&peer->tx_queue); keypair = PACKET_CB(first)->keypair; if (likely(state == PACKET_STATE_CRYPTED)) wg_packet_create_data_done(peer, first); else kfree_skb_list(first); wg_noise_keypair_put(keypair, false); wg_peer_put(peer); if (need_resched()) cond_resched(); } } void wg_packet_encrypt_worker(struct work_struct *work) { struct crypt_queue *queue = container_of(work, struct multicore_worker, work)->ptr; struct sk_buff *first, *skb, *next; while ((first = ptr_ring_consume_bh(&queue->ring)) != NULL) { enum packet_state state = PACKET_STATE_CRYPTED; skb_list_walk_safe(first, skb, next) { if (likely(encrypt_packet(skb, PACKET_CB(first)->keypair))) { wg_reset_packet(skb, true); } else { state = PACKET_STATE_DEAD; break; } } wg_queue_enqueue_per_peer_tx(first, state); if (need_resched()) cond_resched(); } } static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first) { struct wg_device *wg = peer->device; int ret = -EINVAL; rcu_read_lock_bh(); if (unlikely(READ_ONCE(peer->is_dead))) goto err; ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first, wg->packet_crypt_wq, &wg->encrypt_queue.last_cpu); if (unlikely(ret == -EPIPE)) wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD); err: rcu_read_unlock_bh(); if (likely(!ret || ret == -EPIPE)) return; wg_noise_keypair_put(PACKET_CB(first)->keypair, false); wg_peer_put(peer); kfree_skb_list(first); } void wg_packet_purge_staged_packets(struct wg_peer *peer) { spin_lock_bh(&peer->staged_packet_queue.lock); peer->device->dev->stats.tx_dropped += peer->staged_packet_queue.qlen; __skb_queue_purge(&peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); } void wg_packet_send_staged_packets(struct wg_peer *peer) { struct noise_keypair *keypair; struct sk_buff_head packets; struct sk_buff *skb; /* Steal the current queue into our local one. */ __skb_queue_head_init(&packets); spin_lock_bh(&peer->staged_packet_queue.lock); skb_queue_splice_init(&peer->staged_packet_queue, &packets); spin_unlock_bh(&peer->staged_packet_queue.lock); if (unlikely(skb_queue_empty(&packets))) return; /* First we make sure we have a valid reference to a valid key. */ rcu_read_lock_bh(); keypair = wg_noise_keypair_get( rcu_dereference_bh(peer->keypairs.current_keypair)); rcu_read_unlock_bh(); if (unlikely(!keypair)) goto out_nokey; if (unlikely(!READ_ONCE(keypair->sending.is_valid))) goto out_nokey; if (unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, REJECT_AFTER_TIME))) goto out_invalid; /* After we know we have a somewhat valid key, we now try to assign * nonces to all of the packets in the queue. If we can't assign nonces * for all of them, we just consider it a failure and wait for the next * handshake. */ skb_queue_walk(&packets, skb) { /* 0 for no outer TOS: no leak. TODO: at some later point, we * might consider using flowi->tos as outer instead. */ PACKET_CB(skb)->ds = ip_tunnel_ecn_encap(0, ip_hdr(skb), skb); PACKET_CB(skb)->nonce = atomic64_inc_return(&keypair->sending_counter) - 1; if (unlikely(PACKET_CB(skb)->nonce >= REJECT_AFTER_MESSAGES)) goto out_invalid; } packets.prev->next = NULL; wg_peer_get(keypair->entry.peer); PACKET_CB(packets.next)->keypair = keypair; wg_packet_create_data(peer, packets.next); return; out_invalid: WRITE_ONCE(keypair->sending.is_valid, false); out_nokey: wg_noise_keypair_put(keypair, false); /* We orphan the packets if we're waiting on a handshake, so that they * don't block a socket's pool. */ skb_queue_walk(&packets, skb) skb_orphan(skb); /* Then we put them back on the top of the queue. We're not too * concerned about accidentally getting things a little out of order if * packets are being added really fast, because this queue is for before * packets can even be sent and it's small anyway. */ spin_lock_bh(&peer->staged_packet_queue.lock); skb_queue_splice(&packets, &peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); /* If we're exiting because there's something wrong with the key, it * means we should initiate a new handshake. */ wg_packet_send_queued_handshake_initiation(peer, false); } |
| 2202 2202 2203 71 24 69 69 24 41 24 24 1 23 20 3 2194 2193 2201 462 462 24 24 462 462 460 460 460 474 463 463 462 462 101 101 462 91 474 462 22 20 3 22 24 24 20 20 20 20 28 28 2 26 28 24 24 24 460 425 425 424 460 2147 1064 425 2148 2146 2147 703 2 2 3 3 3 20 20 20 631 460 3 3 3 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/dev_addr_lists.c - Functions for handling net device lists * Copyright (c) 2010 Jiri Pirko <jpirko@redhat.com> * * This file contains functions for working with unicast, multicast and device * addresses lists. */ #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/export.h> #include <linux/list.h> #include "dev.h" /* * General list handling functions */ static int __hw_addr_insert(struct netdev_hw_addr_list *list, struct netdev_hw_addr *new, int addr_len) { struct rb_node **ins_point = &list->tree.rb_node, *parent = NULL; struct netdev_hw_addr *ha; while (*ins_point) { int diff; ha = rb_entry(*ins_point, struct netdev_hw_addr, node); diff = memcmp(new->addr, ha->addr, addr_len); if (diff == 0) diff = memcmp(&new->type, &ha->type, sizeof(new->type)); parent = *ins_point; if (diff < 0) ins_point = &parent->rb_left; else if (diff > 0) ins_point = &parent->rb_right; else return -EEXIST; } rb_link_node_rcu(&new->node, parent, ins_point); rb_insert_color(&new->node, &list->tree); return 0; } static struct netdev_hw_addr* __hw_addr_create(const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha; int alloc_size; alloc_size = sizeof(*ha); if (alloc_size < L1_CACHE_BYTES) alloc_size = L1_CACHE_BYTES; ha = kmalloc(alloc_size, GFP_ATOMIC); if (!ha) return NULL; memcpy(ha->addr, addr, addr_len); ha->type = addr_type; ha->refcount = 1; ha->global_use = global; ha->synced = sync ? 1 : 0; ha->sync_cnt = 0; return ha; } static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync, int sync_count, bool exclusive) { struct rb_node **ins_point = &list->tree.rb_node, *parent = NULL; struct netdev_hw_addr *ha; if (addr_len > MAX_ADDR_LEN) return -EINVAL; while (*ins_point) { int diff; ha = rb_entry(*ins_point, struct netdev_hw_addr, node); diff = memcmp(addr, ha->addr, addr_len); if (diff == 0) diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); parent = *ins_point; if (diff < 0) { ins_point = &parent->rb_left; } else if (diff > 0) { ins_point = &parent->rb_right; } else { if (exclusive) return -EEXIST; if (global) { /* check if addr is already used as global */ if (ha->global_use) return 0; else ha->global_use = true; } if (sync) { if (ha->synced && sync_count) return -EEXIST; else ha->synced++; } ha->refcount++; return 0; } } ha = __hw_addr_create(addr, addr_len, addr_type, global, sync); if (!ha) return -ENOMEM; rb_link_node(&ha->node, parent, ins_point); rb_insert_color(&ha->node, &list->tree); list_add_tail_rcu(&ha->list, &list->list); list->count++; return 0; } static int __hw_addr_add(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false, 0, false); } static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, struct netdev_hw_addr *ha, bool global, bool sync) { if (global && !ha->global_use) return -ENOENT; if (sync && !ha->synced) return -ENOENT; if (global) ha->global_use = false; if (sync) ha->synced--; if (--ha->refcount) return 0; rb_erase(&ha->node, &list->tree); list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); list->count--; return 0; } static struct netdev_hw_addr *__hw_addr_lookup(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { struct rb_node *node; node = list->tree.rb_node; while (node) { struct netdev_hw_addr *ha = rb_entry(node, struct netdev_hw_addr, node); int diff = memcmp(addr, ha->addr, addr_len); if (diff == 0 && addr_type) diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); if (diff < 0) node = node->rb_left; else if (diff > 0) node = node->rb_right; else return ha; } return NULL; } static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha = __hw_addr_lookup(list, addr, addr_len, addr_type); if (!ha) return -ENOENT; return __hw_addr_del_entry(list, ha, global, sync); } static int __hw_addr_del(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { return __hw_addr_del_ex(list, addr, addr_len, addr_type, false, false); } static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr *ha, int addr_len) { int err; err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type, false, true, ha->sync_cnt, false); if (err && err != -EEXIST) return err; if (!err) { ha->sync_cnt++; ha->refcount++; } return 0; } static void __hw_addr_unsync_one(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, struct netdev_hw_addr *ha, int addr_len) { int err; err = __hw_addr_del_ex(to_list, ha->addr, addr_len, ha->type, false, true); if (err) return; ha->sync_cnt--; /* address on from list is not marked synced */ __hw_addr_del_entry(from_list, ha, false, false); } static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { int err = 0; struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (ha->sync_cnt == ha->refcount) { __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } else { err = __hw_addr_sync_one(to_list, ha, addr_len); if (err) break; } } return err; } /* This function only works where there is a strict 1-1 relationship * between source and destionation of they synch. If you ever need to * sync addresses to more then 1 destination, you need to use * __hw_addr_sync_multiple(). */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { int err = 0; struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (!ha->sync_cnt) { err = __hw_addr_sync_one(to_list, ha, addr_len); if (err) break; } else if (ha->refcount == 1) __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } return err; } EXPORT_SYMBOL(__hw_addr_sync); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (ha->sync_cnt) __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } } EXPORT_SYMBOL(__hw_addr_unsync); /** * __hw_addr_sync_dev - Synchonize device's multicast list * @list: address list to syncronize * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed * * This function is intended to be called from the ndo_set_rx_mode * function of devices that require explicit address add/remove * notifications. The unsync function may be NULL in which case * the addresses requiring removal will simply be removed without * any notification to the device. **/ int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)) { struct netdev_hw_addr *ha, *tmp; int err; /* first go through and flush out any stale entries */ list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt || ha->refcount != 1) continue; /* if unsync is defined and fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr)) continue; ha->sync_cnt--; __hw_addr_del_entry(list, ha, false, false); } /* go through and sync new entries to the list */ list_for_each_entry_safe(ha, tmp, &list->list, list) { if (ha->sync_cnt) continue; err = sync(dev, ha->addr); if (err) return err; ha->sync_cnt++; ha->refcount++; } return 0; } EXPORT_SYMBOL(__hw_addr_sync_dev); /** * __hw_addr_ref_sync_dev - Synchronize device's multicast address list taking * into account references * @list: address list to synchronize * @dev: device to sync * @sync: function to call if address or reference on it should be added * @unsync: function to call if address or some reference on it should removed * * This function is intended to be called from the ndo_set_rx_mode * function of devices that require explicit address or references on it * add/remove notifications. The unsync function may be NULL in which case * the addresses or references on it requiring removal will simply be * removed without any notification to the device. That is responsibility of * the driver to identify and distribute address or references on it between * internal address tables. **/ int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *, int), int (*unsync)(struct net_device *, const unsigned char *, int)) { struct netdev_hw_addr *ha, *tmp; int err, ref_cnt; /* first go through and flush out any unsynced/stale entries */ list_for_each_entry_safe(ha, tmp, &list->list, list) { /* sync if address is not used */ if ((ha->sync_cnt << 1) <= ha->refcount) continue; /* if fails defer unsyncing address */ ref_cnt = ha->refcount - ha->sync_cnt; if (unsync && unsync(dev, ha->addr, ref_cnt)) continue; ha->refcount = (ref_cnt << 1) + 1; ha->sync_cnt = ref_cnt; __hw_addr_del_entry(list, ha, false, false); } /* go through and sync updated/new entries to the list */ list_for_each_entry_safe(ha, tmp, &list->list, list) { /* sync if address added or reused */ if ((ha->sync_cnt << 1) >= ha->refcount) continue; ref_cnt = ha->refcount - ha->sync_cnt; err = sync(dev, ha->addr, ref_cnt); if (err) return err; ha->refcount = ref_cnt << 1; ha->sync_cnt = ref_cnt; } return 0; } EXPORT_SYMBOL(__hw_addr_ref_sync_dev); /** * __hw_addr_ref_unsync_dev - Remove synchronized addresses and references on * it from device * @list: address list to remove synchronized addresses (references on it) from * @dev: device to sync * @unsync: function to call if address and references on it should be removed * * Remove all addresses that were added to the device by * __hw_addr_ref_sync_dev(). This function is intended to be called from the * ndo_stop or ndo_open functions on devices that require explicit address (or * references on it) add/remove notifications. If the unsync function pointer * is NULL then this function can be used to just reset the sync_cnt for the * addresses in the list. **/ void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *, int)) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt) continue; /* if fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr, ha->sync_cnt)) continue; ha->refcount -= ha->sync_cnt - 1; ha->sync_cnt = 0; __hw_addr_del_entry(list, ha, false, false); } } EXPORT_SYMBOL(__hw_addr_ref_unsync_dev); /** * __hw_addr_unsync_dev - Remove synchronized addresses from device * @list: address list to remove synchronized addresses from * @dev: device to sync * @unsync: function to call if address should be removed * * Remove all addresses that were added to the device by __hw_addr_sync_dev(). * This function is intended to be called from the ndo_stop or ndo_open * functions on devices that require explicit address add/remove * notifications. If the unsync function pointer is NULL then this function * can be used to just reset the sync_cnt for the addresses in the list. **/ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt) continue; /* if unsync is defined and fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr)) continue; ha->sync_cnt--; __hw_addr_del_entry(list, ha, false, false); } } EXPORT_SYMBOL(__hw_addr_unsync_dev); static void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; list->tree = RB_ROOT; list_for_each_entry_safe(ha, tmp, &list->list, list) { list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); } list->count = 0; } void __hw_addr_init(struct netdev_hw_addr_list *list) { INIT_LIST_HEAD(&list->list); list->count = 0; list->tree = RB_ROOT; } EXPORT_SYMBOL(__hw_addr_init); /* * Device addresses handling functions */ /* Check that netdev->dev_addr is not written to directly as this would * break the rbtree layout. All changes should go thru dev_addr_set() and co. * Remove this check in mid-2024. */ void dev_addr_check(struct net_device *dev) { if (!memcmp(dev->dev_addr, dev->dev_addr_shadow, MAX_ADDR_LEN)) return; netdev_warn(dev, "Current addr: %*ph\n", MAX_ADDR_LEN, dev->dev_addr); netdev_warn(dev, "Expected addr: %*ph\n", MAX_ADDR_LEN, dev->dev_addr_shadow); netdev_WARN(dev, "Incorrect netdev->dev_addr\n"); } /** * dev_addr_flush - Flush device address list * @dev: device * * Flush device address list and reset ->dev_addr. * * The caller must hold the rtnl_mutex. */ void dev_addr_flush(struct net_device *dev) { /* rtnl_mutex must be held here */ dev_addr_check(dev); __hw_addr_flush(&dev->dev_addrs); dev->dev_addr = NULL; } /** * dev_addr_init - Init device address list * @dev: device * * Init device address list and create the first element, * used by ->dev_addr. * * The caller must hold the rtnl_mutex. */ int dev_addr_init(struct net_device *dev) { unsigned char addr[MAX_ADDR_LEN]; struct netdev_hw_addr *ha; int err; /* rtnl_mutex must be held here */ __hw_addr_init(&dev->dev_addrs); memset(addr, 0, sizeof(addr)); err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr), NETDEV_HW_ADDR_T_LAN); if (!err) { /* * Get the first (previously created) address from the list * and set dev_addr pointer to this location. */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); dev->dev_addr = ha->addr; } return err; } void dev_addr_mod(struct net_device *dev, unsigned int offset, const void *addr, size_t len) { struct netdev_hw_addr *ha; dev_addr_check(dev); ha = container_of(dev->dev_addr, struct netdev_hw_addr, addr[0]); rb_erase(&ha->node, &dev->dev_addrs.tree); memcpy(&ha->addr[offset], addr, len); memcpy(&dev->dev_addr_shadow[offset], addr, len); WARN_ON(__hw_addr_insert(&dev->dev_addrs, ha, dev->addr_len)); } EXPORT_SYMBOL(dev_addr_mod); /** * dev_addr_add - Add a device address * @dev: device * @addr: address to add * @addr_type: address type * * Add a device address to the device or increase the reference count if * it already exists. * * The caller must hold the rtnl_mutex. */ int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; ASSERT_RTNL(); err = dev_pre_changeaddr_notify(dev, addr, NULL); if (err) return err; err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; } EXPORT_SYMBOL(dev_addr_add); /** * dev_addr_del - Release a device address. * @dev: device * @addr: address to delete * @addr_type: address type * * Release reference to a device address and remove it from the device * if the reference count drops to zero. * * The caller must hold the rtnl_mutex. */ int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; struct netdev_hw_addr *ha; ASSERT_RTNL(); /* * We can not remove the first address from the list because * dev->dev_addr points to that. */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); if (!memcmp(ha->addr, addr, dev->addr_len) && ha->type == addr_type && ha->refcount == 1) return -ENOENT; err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, addr_type); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; } EXPORT_SYMBOL(dev_addr_del); /* * Unicast list handling functions */ /** * dev_uc_add_excl - Add a global secondary unicast address * @dev: device * @addr: address to add */ int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST, true, false, 0, true); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_add_excl); /** * dev_uc_add - Add a secondary unicast address * @dev: device * @addr: address to add * * Add a secondary unicast address to the device or increase * the reference count if it already exists. */ int dev_uc_add(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_add); /** * dev_uc_del - Release secondary unicast address. * @dev: device * @addr: address to delete * * Release reference to a secondary unicast address and remove it * from the device if the reference count drops to zero. */ int dev_uc_del(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_del(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_del); /** * dev_uc_sync - Synchronize device's unicast list to another device * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. This function assumes that * addresses will only ever be synced to the @to devices and no other. */ int dev_uc_sync(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_uc_sync); /** * dev_uc_sync_multiple - Synchronize device's unicast list to another * device, but allow for multiple calls to sync to multiple devices. * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have been deleted from the source. The source device * must be locked by netif_addr_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. It allows for a single source * device to be synced to multiple destination devices. */ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_uc_sync_multiple); /** * dev_uc_unsync - Remove synchronized addresses from the destination device * @to: destination device * @from: source device * * Remove all addresses that were added to the destination device by * dev_uc_sync(). This function is intended to be called from the * dev->stop function of layered software devices. */ void dev_uc_unsync(struct net_device *to, struct net_device *from) { if (to->addr_len != from->addr_len) return; /* netif_addr_lock_bh() uses lockdep subclass 0, this is okay for two * reasons: * 1) This is always called without any addr_list_lock, so as the * outermost one here, it must be 0. * 2) This is called by some callers after unlinking the upper device, * so the dev->lower_level becomes 1 again. * Therefore, the subclass for 'from' is 0, for 'to' is either 1 or * larger. */ netif_addr_lock_bh(from); netif_addr_lock(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_uc_unsync); /** * dev_uc_flush - Flush unicast addresses * @dev: device * * Flush unicast addresses. */ void dev_uc_flush(struct net_device *dev) { netif_addr_lock_bh(dev); __hw_addr_flush(&dev->uc); netif_addr_unlock_bh(dev); } EXPORT_SYMBOL(dev_uc_flush); /** * dev_uc_init - Init unicast address list * @dev: device * * Init unicast address list. */ void dev_uc_init(struct net_device *dev) { __hw_addr_init(&dev->uc); } EXPORT_SYMBOL(dev_uc_init); /* * Multicast list handling functions */ /** * dev_mc_add_excl - Add a global secondary multicast address * @dev: device * @addr: address to add */ int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, true, false, 0, true); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_mc_add_excl); static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, bool global) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, global, false, 0, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } /** * dev_mc_add - Add a multicast address * @dev: device * @addr: address to add * * Add a multicast address to the device or increase * the reference count if it already exists. */ int dev_mc_add(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, false); } EXPORT_SYMBOL(dev_mc_add); /** * dev_mc_add_global - Add a global multicast address * @dev: device * @addr: address to add * * Add a global multicast address to the device. */ int dev_mc_add_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, true); } EXPORT_SYMBOL(dev_mc_add_global); static int __dev_mc_del(struct net_device *dev, const unsigned char *addr, bool global) { int err; netif_addr_lock_bh(dev); err = __hw_addr_del_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, global, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } /** * dev_mc_del - Delete a multicast address. * @dev: device * @addr: address to delete * * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ int dev_mc_del(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, false); } EXPORT_SYMBOL(dev_mc_del); /** * dev_mc_del_global - Delete a global multicast address. * @dev: device * @addr: address to delete * * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ int dev_mc_del_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, true); } EXPORT_SYMBOL(dev_mc_del_global); /** * dev_mc_sync - Synchronize device's multicast list to another device * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the ndo_set_rx_mode * function of layered software devices. */ int dev_mc_sync(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_mc_sync); /** * dev_mc_sync_multiple - Synchronize device's multicast list to another * device, but allow for multiple calls to sync to multiple devices. * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the ndo_set_rx_mode * function of layered software devices. It allows for a single * source device to be synced to multiple destination devices. */ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_mc_sync_multiple); /** * dev_mc_unsync - Remove synchronized addresses from the destination device * @to: destination device * @from: source device * * Remove all addresses that were added to the destination device by * dev_mc_sync(). This function is intended to be called from the * dev->stop function of layered software devices. */ void dev_mc_unsync(struct net_device *to, struct net_device *from) { if (to->addr_len != from->addr_len) return; /* See the above comments inside dev_uc_unsync(). */ netif_addr_lock_bh(from); netif_addr_lock(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_mc_unsync); /** * dev_mc_flush - Flush multicast addresses * @dev: device * * Flush multicast addresses. */ void dev_mc_flush(struct net_device *dev) { netif_addr_lock_bh(dev); __hw_addr_flush(&dev->mc); netif_addr_unlock_bh(dev); } EXPORT_SYMBOL(dev_mc_flush); /** * dev_mc_init - Init multicast address list * @dev: device * * Init multicast address list. */ void dev_mc_init(struct net_device *dev) { __hw_addr_init(&dev->mc); } EXPORT_SYMBOL(dev_mc_init); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 | // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */ #include <crypto/aead.h> #include <linux/debugfs.h> #include <net/xfrm.h> #include "netdevsim.h" #define NSIM_IPSEC_AUTH_BITS 128 static ssize_t nsim_dbg_netdev_ops_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { struct netdevsim *ns = filp->private_data; struct nsim_ipsec *ipsec = &ns->ipsec; size_t bufsize; char *buf, *p; int len; int i; /* the buffer needed is * (num SAs * 3 lines each * ~60 bytes per line) + one more line */ bufsize = (ipsec->count * 4 * 60) + 60; buf = kzalloc(bufsize, GFP_KERNEL); if (!buf) return -ENOMEM; p = buf; p += scnprintf(p, bufsize - (p - buf), "SA count=%u tx=%u\n", ipsec->count, ipsec->tx); for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) { struct nsim_sa *sap = &ipsec->sa[i]; if (!sap->used) continue; p += scnprintf(p, bufsize - (p - buf), "sa[%i] %cx ipaddr=0x%08x %08x %08x %08x\n", i, (sap->rx ? 'r' : 't'), sap->ipaddr[0], sap->ipaddr[1], sap->ipaddr[2], sap->ipaddr[3]); p += scnprintf(p, bufsize - (p - buf), "sa[%i] spi=0x%08x proto=0x%x salt=0x%08x crypt=%d\n", i, be32_to_cpu(sap->xs->id.spi), sap->xs->id.proto, sap->salt, sap->crypt); p += scnprintf(p, bufsize - (p - buf), "sa[%i] key=0x%08x %08x %08x %08x\n", i, sap->key[0], sap->key[1], sap->key[2], sap->key[3]); } len = simple_read_from_buffer(buffer, count, ppos, buf, p - buf); kfree(buf); return len; } static const struct file_operations ipsec_dbg_fops = { .owner = THIS_MODULE, .open = simple_open, .read = nsim_dbg_netdev_ops_read, }; static int nsim_ipsec_find_empty_idx(struct nsim_ipsec *ipsec) { u32 i; if (ipsec->count == NSIM_IPSEC_MAX_SA_COUNT) return -ENOSPC; /* search sa table */ for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) { if (!ipsec->sa[i].used) return i; } return -ENOSPC; } static int nsim_ipsec_parse_proto_keys(struct xfrm_state *xs, u32 *mykey, u32 *mysalt) { const char aes_gcm_name[] = "rfc4106(gcm(aes))"; struct net_device *dev = xs->xso.real_dev; unsigned char *key_data; char *alg_name = NULL; int key_len; if (!xs->aead) { netdev_err(dev, "Unsupported IPsec algorithm\n"); return -EINVAL; } if (xs->aead->alg_icv_len != NSIM_IPSEC_AUTH_BITS) { netdev_err(dev, "IPsec offload requires %d bit authentication\n", NSIM_IPSEC_AUTH_BITS); return -EINVAL; } key_data = &xs->aead->alg_key[0]; key_len = xs->aead->alg_key_len; alg_name = xs->aead->alg_name; if (strcmp(alg_name, aes_gcm_name)) { netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n", aes_gcm_name); return -EINVAL; } /* 160 accounts for 16 byte key and 4 byte salt */ if (key_len > NSIM_IPSEC_AUTH_BITS) { *mysalt = ((u32 *)key_data)[4]; } else if (key_len == NSIM_IPSEC_AUTH_BITS) { *mysalt = 0; } else { netdev_err(dev, "IPsec hw offload only supports 128 bit keys with optional 32 bit salt\n"); return -EINVAL; } memcpy(mykey, key_data, 16); return 0; } static int nsim_ipsec_add_sa(struct xfrm_state *xs) { struct nsim_ipsec *ipsec; struct net_device *dev; struct netdevsim *ns; struct nsim_sa sa; u16 sa_idx; int ret; dev = xs->xso.real_dev; ns = netdev_priv(dev); ipsec = &ns->ipsec; if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) { netdev_err(dev, "Unsupported protocol 0x%04x for ipsec offload\n", xs->id.proto); return -EINVAL; } if (xs->calg) { netdev_err(dev, "Compression offload not supported\n"); return -EINVAL; } /* find the first unused index */ ret = nsim_ipsec_find_empty_idx(ipsec); if (ret < 0) { netdev_err(dev, "No space for SA in Rx table!\n"); return ret; } sa_idx = (u16)ret; memset(&sa, 0, sizeof(sa)); sa.used = true; sa.xs = xs; if (sa.xs->id.proto & IPPROTO_ESP) sa.crypt = xs->ealg || xs->aead; /* get the key and salt */ ret = nsim_ipsec_parse_proto_keys(xs, sa.key, &sa.salt); if (ret) { netdev_err(dev, "Failed to get key data for SA table\n"); return ret; } if (xs->xso.dir == XFRM_DEV_OFFLOAD_IN) { sa.rx = true; if (xs->props.family == AF_INET6) memcpy(sa.ipaddr, &xs->id.daddr.a6, 16); else memcpy(&sa.ipaddr[3], &xs->id.daddr.a4, 4); } /* the preparations worked, so save the info */ memcpy(&ipsec->sa[sa_idx], &sa, sizeof(sa)); /* the XFRM stack doesn't like offload_handle == 0, * so add a bitflag in case our array index is 0 */ xs->xso.offload_handle = sa_idx | NSIM_IPSEC_VALID; ipsec->count++; return 0; } static void nsim_ipsec_del_sa(struct xfrm_state *xs) { struct netdevsim *ns = netdev_priv(xs->xso.real_dev); struct nsim_ipsec *ipsec = &ns->ipsec; u16 sa_idx; sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID; if (!ipsec->sa[sa_idx].used) { netdev_err(ns->netdev, "Invalid SA for delete sa_idx=%d\n", sa_idx); return; } memset(&ipsec->sa[sa_idx], 0, sizeof(struct nsim_sa)); ipsec->count--; } static bool nsim_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) { struct netdevsim *ns = netdev_priv(xs->xso.real_dev); struct nsim_ipsec *ipsec = &ns->ipsec; ipsec->ok++; return true; } static const struct xfrmdev_ops nsim_xfrmdev_ops = { .xdo_dev_state_add = nsim_ipsec_add_sa, .xdo_dev_state_delete = nsim_ipsec_del_sa, .xdo_dev_offload_ok = nsim_ipsec_offload_ok, }; bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb) { struct sec_path *sp = skb_sec_path(skb); struct nsim_ipsec *ipsec = &ns->ipsec; struct xfrm_state *xs; struct nsim_sa *tsa; u32 sa_idx; /* do we even need to check this packet? */ if (!sp) return true; if (unlikely(!sp->len)) { netdev_err(ns->netdev, "no xfrm state len = %d\n", sp->len); return false; } xs = xfrm_input_state(skb); if (unlikely(!xs)) { netdev_err(ns->netdev, "no xfrm_input_state() xs = %p\n", xs); return false; } sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID; if (unlikely(sa_idx >= NSIM_IPSEC_MAX_SA_COUNT)) { netdev_err(ns->netdev, "bad sa_idx=%d max=%d\n", sa_idx, NSIM_IPSEC_MAX_SA_COUNT); return false; } tsa = &ipsec->sa[sa_idx]; if (unlikely(!tsa->used)) { netdev_err(ns->netdev, "unused sa_idx=%d\n", sa_idx); return false; } if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) { netdev_err(ns->netdev, "unexpected proto=%d\n", xs->id.proto); return false; } ipsec->tx++; return true; } void nsim_ipsec_init(struct netdevsim *ns) { ns->netdev->xfrmdev_ops = &nsim_xfrmdev_ops; #define NSIM_ESP_FEATURES (NETIF_F_HW_ESP | \ NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) ns->netdev->features |= NSIM_ESP_FEATURES; ns->netdev->hw_enc_features |= NSIM_ESP_FEATURES; ns->ipsec.pfile = debugfs_create_file("ipsec", 0400, ns->nsim_dev_port->ddir, ns, &ipsec_dbg_fops); } void nsim_ipsec_teardown(struct netdevsim *ns) { struct nsim_ipsec *ipsec = &ns->ipsec; if (ipsec->count) netdev_err(ns->netdev, "tearing down IPsec offload with %d SAs left\n", ipsec->count); debugfs_remove_recursive(ipsec->pfile); } |
| 809 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright 2019 Google LLC */ #ifndef __LINUX_BLK_CRYPTO_H #define __LINUX_BLK_CRYPTO_H #include <linux/types.h> enum blk_crypto_mode_num { BLK_ENCRYPTION_MODE_INVALID, BLK_ENCRYPTION_MODE_AES_256_XTS, BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV, BLK_ENCRYPTION_MODE_ADIANTUM, BLK_ENCRYPTION_MODE_MAX, }; #define BLK_CRYPTO_MAX_KEY_SIZE 64 /** * struct blk_crypto_config - an inline encryption key's crypto configuration * @crypto_mode: encryption algorithm this key is for * @data_unit_size: the data unit size for all encryption/decryptions with this * key. This is the size in bytes of each individual plaintext and * ciphertext. This is always a power of 2. It might be e.g. the * filesystem block size or the disk sector size. * @dun_bytes: the maximum number of bytes of DUN used when using this key */ struct blk_crypto_config { enum blk_crypto_mode_num crypto_mode; unsigned int data_unit_size; unsigned int dun_bytes; }; /** * struct blk_crypto_key - an inline encryption key * @crypto_cfg: the crypto configuration (like crypto_mode, key size) for this * key * @data_unit_size_bits: log2 of data_unit_size * @size: size of this key in bytes (determined by @crypto_cfg.crypto_mode) * @raw: the raw bytes of this key. Only the first @size bytes are used. * * A blk_crypto_key is immutable once created, and many bios can reference it at * the same time. It must not be freed until all bios using it have completed * and it has been evicted from all devices on which it may have been used. */ struct blk_crypto_key { struct blk_crypto_config crypto_cfg; unsigned int data_unit_size_bits; unsigned int size; u8 raw[BLK_CRYPTO_MAX_KEY_SIZE]; }; #define BLK_CRYPTO_MAX_IV_SIZE 32 #define BLK_CRYPTO_DUN_ARRAY_SIZE (BLK_CRYPTO_MAX_IV_SIZE / sizeof(u64)) /** * struct bio_crypt_ctx - an inline encryption context * @bc_key: the key, algorithm, and data unit size to use * @bc_dun: the data unit number (starting IV) to use * * A bio_crypt_ctx specifies that the contents of the bio will be encrypted (for * write requests) or decrypted (for read requests) inline by the storage device * or controller, or by the crypto API fallback. */ struct bio_crypt_ctx { const struct blk_crypto_key *bc_key; u64 bc_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]; }; #include <linux/blk_types.h> #include <linux/blkdev.h> struct request; struct request_queue; #ifdef CONFIG_BLK_INLINE_ENCRYPTION static inline bool bio_has_crypt_ctx(struct bio *bio) { return bio->bi_crypt_context; } void bio_crypt_set_ctx(struct bio *bio, const struct blk_crypto_key *key, const u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE], gfp_t gfp_mask); bool bio_crypt_dun_is_contiguous(const struct bio_crypt_ctx *bc, unsigned int bytes, const u64 next_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]); int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, enum blk_crypto_mode_num crypto_mode, unsigned int dun_bytes, unsigned int data_unit_size); int blk_crypto_start_using_key(const struct blk_crypto_key *key, struct request_queue *q); int blk_crypto_evict_key(struct request_queue *q, const struct blk_crypto_key *key); bool blk_crypto_config_supported(struct request_queue *q, const struct blk_crypto_config *cfg); #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool bio_has_crypt_ctx(struct bio *bio) { return false; } #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ int __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask); /** * bio_crypt_clone - clone bio encryption context * @dst: destination bio * @src: source bio * @gfp_mask: memory allocation flags * * If @src has an encryption context, clone it to @dst. * * Return: 0 on success, -ENOMEM if out of memory. -ENOMEM is only possible if * @gfp_mask doesn't include %__GFP_DIRECT_RECLAIM. */ static inline int bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask) { if (bio_has_crypt_ctx(src)) return __bio_crypt_clone(dst, src, gfp_mask); return 0; } #endif /* __LINUX_BLK_CRYPTO_H */ |
| 2738 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Kernel Electric-Fence (KFENCE). Public interface for allocator and fault * handler integration. For more info see Documentation/dev-tools/kfence.rst. * * Copyright (C) 2020, Google LLC. */ #ifndef _LINUX_KFENCE_H #define _LINUX_KFENCE_H #include <linux/mm.h> #include <linux/types.h> #ifdef CONFIG_KFENCE #include <linux/atomic.h> #include <linux/static_key.h> extern unsigned long kfence_sample_interval; /* * We allocate an even number of pages, as it simplifies calculations to map * address to metadata indices; effectively, the very first page serves as an * extended guard page, but otherwise has no special purpose. */ #define KFENCE_POOL_SIZE ((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 * PAGE_SIZE) extern char *__kfence_pool; DECLARE_STATIC_KEY_FALSE(kfence_allocation_key); extern atomic_t kfence_allocation_gate; /** * is_kfence_address() - check if an address belongs to KFENCE pool * @addr: address to check * * Return: true or false depending on whether the address is within the KFENCE * object range. * * KFENCE objects live in a separate page range and are not to be intermixed * with regular heap objects (e.g. KFENCE objects must never be added to the * allocator freelists). Failing to do so may and will result in heap * corruptions, therefore is_kfence_address() must be used to check whether * an object requires specific handling. * * Note: This function may be used in fast-paths, and is performance critical. * Future changes should take this into account; for instance, we want to avoid * introducing another load and therefore need to keep KFENCE_POOL_SIZE a * constant (until immediate patching support is added to the kernel). */ static __always_inline bool is_kfence_address(const void *addr) { /* * The __kfence_pool != NULL check is required to deal with the case * where __kfence_pool == NULL && addr < KFENCE_POOL_SIZE. Keep it in * the slow-path after the range-check! */ return unlikely((unsigned long)((char *)addr - __kfence_pool) < KFENCE_POOL_SIZE && __kfence_pool); } /** * kfence_alloc_pool() - allocate the KFENCE pool via memblock */ void __init kfence_alloc_pool(void); /** * kfence_init() - perform KFENCE initialization at boot time * * Requires that kfence_alloc_pool() was called before. This sets up the * allocation gate timer, and requires that workqueues are available. */ void __init kfence_init(void); /** * kfence_shutdown_cache() - handle shutdown_cache() for KFENCE objects * @s: cache being shut down * * Before shutting down a cache, one must ensure there are no remaining objects * allocated from it. Because KFENCE objects are not referenced from the cache * directly, we need to check them here. * * Note that shutdown_cache() is internal to SL*B, and kmem_cache_destroy() does * not return if allocated objects still exist: it prints an error message and * simply aborts destruction of a cache, leaking memory. * * If the only such objects are KFENCE objects, we will not leak the entire * cache, but instead try to provide more useful debug info by making allocated * objects "zombie allocations". Objects may then still be used or freed (which * is handled gracefully), but usage will result in showing KFENCE error reports * which include stack traces to the user of the object, the original allocation * site, and caller to shutdown_cache(). */ void kfence_shutdown_cache(struct kmem_cache *s); /* * Allocate a KFENCE object. Allocators must not call this function directly, * use kfence_alloc() instead. */ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags); /** * kfence_alloc() - allocate a KFENCE object with a low probability * @s: struct kmem_cache with object requirements * @size: exact size of the object to allocate (can be less than @s->size * e.g. for kmalloc caches) * @flags: GFP flags * * Return: * * NULL - must proceed with allocating as usual, * * non-NULL - pointer to a KFENCE object. * * kfence_alloc() should be inserted into the heap allocation fast path, * allowing it to transparently return KFENCE-allocated objects with a low * probability using a static branch (the probability is controlled by the * kfence.sample_interval boot parameter). */ static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { #if defined(CONFIG_KFENCE_STATIC_KEYS) || CONFIG_KFENCE_SAMPLE_INTERVAL == 0 if (!static_branch_unlikely(&kfence_allocation_key)) return NULL; #else if (!static_branch_likely(&kfence_allocation_key)) return NULL; #endif if (likely(atomic_read(&kfence_allocation_gate))) return NULL; return __kfence_alloc(s, size, flags); } /** * kfence_ksize() - get actual amount of memory allocated for a KFENCE object * @addr: pointer to a heap object * * Return: * * 0 - not a KFENCE object, must call __ksize() instead, * * non-0 - this many bytes can be accessed without causing a memory error. * * kfence_ksize() returns the number of bytes requested for a KFENCE object at * allocation time. This number may be less than the object size of the * corresponding struct kmem_cache. */ size_t kfence_ksize(const void *addr); /** * kfence_object_start() - find the beginning of a KFENCE object * @addr: address within a KFENCE-allocated object * * Return: address of the beginning of the object. * * SL[AU]B-allocated objects are laid out within a page one by one, so it is * easy to calculate the beginning of an object given a pointer inside it and * the object size. The same is not true for KFENCE, which places a single * object at either end of the page. This helper function is used to find the * beginning of a KFENCE-allocated object. */ void *kfence_object_start(const void *addr); /** * __kfence_free() - release a KFENCE heap object to KFENCE pool * @addr: object to be freed * * Requires: is_kfence_address(addr) * * Release a KFENCE object and mark it as freed. */ void __kfence_free(void *addr); /** * kfence_free() - try to release an arbitrary heap object to KFENCE pool * @addr: object to be freed * * Return: * * false - object doesn't belong to KFENCE pool and was ignored, * * true - object was released to KFENCE pool. * * Release a KFENCE object and mark it as freed. May be called on any object, * even non-KFENCE objects, to simplify integration of the hooks into the * allocator's free codepath. The allocator must check the return value to * determine if it was a KFENCE object or not. */ static __always_inline __must_check bool kfence_free(void *addr) { if (!is_kfence_address(addr)) return false; __kfence_free(addr); return true; } /** * kfence_handle_page_fault() - perform page fault handling for KFENCE pages * @addr: faulting address * @is_write: is access a write * @regs: current struct pt_regs (can be NULL, but shows full stack trace) * * Return: * * false - address outside KFENCE pool, * * true - page fault handled by KFENCE, no additional handling required. * * A page fault inside KFENCE pool indicates a memory error, such as an * out-of-bounds access, a use-after-free or an invalid memory access. In these * cases KFENCE prints an error message and marks the offending page as * present, so that the kernel can proceed. */ bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs); #ifdef CONFIG_PRINTK struct kmem_obj_info; /** * __kfence_obj_info() - fill kmem_obj_info struct * @kpp: kmem_obj_info to be filled * @object: the object * * Return: * * false - not a KFENCE object * * true - a KFENCE object, filled @kpp * * Copies information to @kpp for KFENCE objects. */ bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); #endif #else /* CONFIG_KFENCE */ static inline bool is_kfence_address(const void *addr) { return false; } static inline void kfence_alloc_pool(void) { } static inline void kfence_init(void) { } static inline void kfence_shutdown_cache(struct kmem_cache *s) { } static inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { return NULL; } static inline size_t kfence_ksize(const void *addr) { return 0; } static inline void *kfence_object_start(const void *addr) { return NULL; } static inline void __kfence_free(void *addr) { } static inline bool __must_check kfence_free(void *addr) { return false; } static inline bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs) { return false; } #ifdef CONFIG_PRINTK struct kmem_obj_info; static inline bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) { return false; } #endif #endif #endif /* _LINUX_KFENCE_H */ |
| 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 | /* 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), }; /* 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 */ 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; }; /* * 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_rwsem, 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 }; /* * 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; /* * 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? */ int 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]; 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; /* 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; /* If there is block congestion on this cgroup. */ atomic_t congestion_count; /* Used to store internal freezer state */ struct cgroup_freezer_state freezer; /* 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; /* * 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; /* A list running through the active hierarchies */ struct list_head root_list; /* 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); #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lockdep_key; #endif }; /* * 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 (*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; /** * 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 */ |
| 11 12 11 11 11 11 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 | // SPDX-License-Identifier: GPL-2.0-or-later /** -*- linux-c -*- *********************************************************** * Linux PPP over X/Ethernet (PPPoX/PPPoE) Sockets * * PPPoX --- Generic PPP encapsulation socket family * PPPoE --- PPP over Ethernet (RFC 2516) * * Version: 0.5.2 * * Author: Michal Ostrowski <mostrows@speakeasy.net> * * 051000 : Initialization cleanup * * License: */ #include <linux/string.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/compat.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/net.h> #include <linux/init.h> #include <linux/if_pppox.h> #include <linux/ppp_defs.h> #include <linux/ppp-ioctl.h> #include <linux/ppp_channel.h> #include <linux/kmod.h> #include <net/sock.h> #include <linux/uaccess.h> static const struct pppox_proto *pppox_protos[PX_MAX_PROTO + 1]; int register_pppox_proto(int proto_num, const struct pppox_proto *pp) { if (proto_num < 0 || proto_num > PX_MAX_PROTO) return -EINVAL; if (pppox_protos[proto_num]) return -EALREADY; pppox_protos[proto_num] = pp; return 0; } void unregister_pppox_proto(int proto_num) { if (proto_num >= 0 && proto_num <= PX_MAX_PROTO) pppox_protos[proto_num] = NULL; } void pppox_unbind_sock(struct sock *sk) { /* Clear connection to ppp device, if attached. */ if (sk->sk_state & (PPPOX_BOUND | PPPOX_CONNECTED)) { ppp_unregister_channel(&pppox_sk(sk)->chan); sk->sk_state = PPPOX_DEAD; } } EXPORT_SYMBOL(register_pppox_proto); EXPORT_SYMBOL(unregister_pppox_proto); EXPORT_SYMBOL(pppox_unbind_sock); int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; struct pppox_sock *po = pppox_sk(sk); int rc; lock_sock(sk); switch (cmd) { case PPPIOCGCHAN: { int index; rc = -ENOTCONN; if (!(sk->sk_state & PPPOX_CONNECTED)) break; rc = -EINVAL; index = ppp_channel_index(&po->chan); if (put_user(index , (int __user *) arg)) break; rc = 0; sk->sk_state |= PPPOX_BOUND; break; } default: rc = pppox_protos[sk->sk_protocol]->ioctl ? pppox_protos[sk->sk_protocol]->ioctl(sock, cmd, arg) : -ENOTTY; } release_sock(sk); return rc; } EXPORT_SYMBOL(pppox_ioctl); #ifdef CONFIG_COMPAT int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { if (cmd == PPPOEIOCSFWD32) cmd = PPPOEIOCSFWD; return pppox_ioctl(sock, cmd, (unsigned long)compat_ptr(arg)); } EXPORT_SYMBOL(pppox_compat_ioctl); #endif static int pppox_create(struct net *net, struct socket *sock, int protocol, int kern) { int rc = -EPROTOTYPE; if (protocol < 0 || protocol > PX_MAX_PROTO) goto out; rc = -EPROTONOSUPPORT; if (!pppox_protos[protocol]) request_module("net-pf-%d-proto-%d", PF_PPPOX, protocol); if (!pppox_protos[protocol] || !try_module_get(pppox_protos[protocol]->owner)) goto out; rc = pppox_protos[protocol]->create(net, sock, kern); module_put(pppox_protos[protocol]->owner); out: return rc; } static const struct net_proto_family pppox_proto_family = { .family = PF_PPPOX, .create = pppox_create, .owner = THIS_MODULE, }; static int __init pppox_init(void) { return sock_register(&pppox_proto_family); } static void __exit pppox_exit(void) { sock_unregister(PF_PPPOX); } module_init(pppox_init); module_exit(pppox_exit); MODULE_AUTHOR("Michal Ostrowski <mostrows@speakeasy.net>"); MODULE_DESCRIPTION("PPP over Ethernet driver (generic socket layer)"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_PPPOX); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __IEEE802154_CORE_H #define __IEEE802154_CORE_H #include <net/cfg802154.h> struct cfg802154_registered_device { const struct cfg802154_ops *ops; struct list_head list; /* wpan_phy index, internal only */ int wpan_phy_idx; /* also protected by devlist_mtx */ int opencount; wait_queue_head_t dev_wait; /* protected by RTNL only */ int num_running_ifaces; /* associated wpan interfaces, protected by rtnl or RCU */ struct list_head wpan_dev_list; int devlist_generation, wpan_dev_id; /* must be last because of the way we do wpan_phy_priv(), * and it should at least be aligned to NETDEV_ALIGN */ struct wpan_phy wpan_phy __aligned(NETDEV_ALIGN); }; static inline struct cfg802154_registered_device * wpan_phy_to_rdev(struct wpan_phy *wpan_phy) { BUG_ON(!wpan_phy); return container_of(wpan_phy, struct cfg802154_registered_device, wpan_phy); } extern struct list_head cfg802154_rdev_list; extern int cfg802154_rdev_list_generation; int cfg802154_switch_netns(struct cfg802154_registered_device *rdev, struct net *net); /* free object */ void cfg802154_dev_free(struct cfg802154_registered_device *rdev); struct cfg802154_registered_device * cfg802154_rdev_by_wpan_phy_idx(int wpan_phy_idx); struct wpan_phy *wpan_phy_idx_to_wpan_phy(int wpan_phy_idx); #endif /* __IEEE802154_CORE_H */ |
| 2272 1622 1129 2272 2272 2272 2272 2272 1671 1671 2084 2085 2085 2497 2497 2270 2269 2270 2272 2272 3 3 3 2497 2270 2268 2270 2268 2270 2269 2270 2270 2270 2270 2268 2270 2270 2270 2269 2270 2269 2270 2270 2269 2269 2270 2269 2252 2251 2270 433 432 431 433 432 432 2272 2272 2272 2272 95 94 2270 2269 95 95 95 122 95 2268 2270 27 39 2270 2270 2270 2251 2270 2270 2251 139 2142 2270 2270 1011 1290 1290 2270 2270 2270 2270 2269 2269 577 577 577 577 1 577 2279 588 2281 2280 2276 2273 2272 2273 636 2271 2271 2272 2272 2268 2272 2272 2272 2272 2272 2272 2270 2272 2272 2270 2269 2270 2251 636 633 631 633 84 84 84 578 578 578 578 578 577 577 577 577 577 63 577 576 577 577 577 577 25 577 577 1 59 59 60 60 63 63 95 95 3 3 3 2282 2 2281 1335 1259 2281 577 42 577 39 577 37 37 575 589 2283 2283 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also entry.S and others). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/user.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> #include <linux/unistd.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/mempolicy.h> #include <linux/sem.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/kmsan.h> #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/cgroup.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/seccomp.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/jiffies.h> #include <linux/futex.h> #include <linux/compat.h> #include <linux/kthread.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/proc_fs.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/ksm.h> #include <linux/acct.h> #include <linux/userfaultfd_k.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/random.h> #include <linux/tty.h> #include <linux/fs_struct.h> #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> #include <linux/user-return-notifier.h> #include <linux/oom.h> #include <linux/khugepaged.h> #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> #include <linux/stackleak.h> #include <linux/kasan.h> #include <linux/scs.h> #include <linux/io_uring.h> #include <linux/bpf.h> #include <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> /* * 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) { } #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node) { return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); } static inline void free_task_struct(struct task_struct *tsk) { kmem_cache_free(task_struct_cachep, tsk); } #endif #ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ # if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) # ifdef CONFIG_VMAP_STACK /* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. */ #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); struct vm_stack { struct rcu_head rcu; struct vm_struct *stack_vm_area; }; static bool try_release_thread_stack_to_cache(struct vm_struct *vm) { unsigned int i; for (i = 0; i < NR_CACHED_STACKS; i++) { if (this_cpu_cmpxchg(cached_stacks[i], NULL, vm) != NULL) continue; return true; } return false; } static void thread_stack_free_rcu(struct rcu_head *rh) { struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu); if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area)) return; vfree(vm_stack); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct vm_stack *vm_stack = tsk->stack; vm_stack->stack_vm_area = tsk->stack_vm_area; call_rcu(&vm_stack->rcu, thread_stack_free_rcu); } static int free_vm_stack_cache(unsigned int cpu) { struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_stack = cached_vm_stacks[i]; if (!vm_stack) continue; vfree(vm_stack->addr); cached_vm_stacks[i] = NULL; } return 0; } static int memcg_charge_kernel_stack(struct vm_struct *vm) { int i; int ret; BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0); BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0); if (ret) goto err; } return 0; err: /* * If memcg_kmem_charge_page() fails, page's memory cgroup pointer is * NULL, and memcg_kmem_uncharge_page() in free_thread_stack() will * ignore this page. */ for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) memcg_kmem_uncharge_page(vm->pages[i], 0); return ret; } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct vm_struct *vm; void *stack; int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *s; s = this_cpu_xchg(cached_stacks[i], NULL); if (!s) continue; /* Reset stack metadata. */ kasan_unpoison_range(s->addr, THREAD_SIZE); stack = kasan_reset_tag(s->addr); /* Clear stale pointers from reused stack. */ memset(stack, 0, THREAD_SIZE); if (memcg_charge_kernel_stack(s)) { vfree(s->addr); return -ENOMEM; } tsk->stack_vm_area = s; tsk->stack = stack; return 0; } /* * Allocated stacks are cached and later reused by new threads, * so memcg accounting is performed manually on assigning/releasing * stacks to tasks. Drop __GFP_ACCOUNT. */ stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START, VMALLOC_END, THREADINFO_GFP & ~__GFP_ACCOUNT, PAGE_KERNEL, 0, node, __builtin_return_address(0)); if (!stack) return -ENOMEM; vm = find_vm_area(stack); if (memcg_charge_kernel_stack(vm)) { vfree(stack); return -ENOMEM; } /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ tsk->stack_vm_area = vm; stack = kasan_reset_tag(stack); tsk->stack = stack; return 0; } static void free_thread_stack(struct task_struct *tsk) { if (!try_release_thread_stack_to_cache(tsk->stack_vm_area)) thread_stack_delayed_free(tsk); tsk->stack = NULL; tsk->stack_vm_area = NULL; } # else /* !CONFIG_VMAP_STACK */ static void thread_stack_free_rcu(struct rcu_head *rh) { __free_pages(virt_to_page(rh), THREAD_SIZE_ORDER); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); return 0; } return -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } # endif /* CONFIG_VMAP_STACK */ # else /* !(THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)) */ static struct kmem_cache *thread_stack_cache; static void thread_stack_free_rcu(struct rcu_head *rh) { kmem_cache_free(thread_stack_cache, rh); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; return stack ? 0 : -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } void thread_stack_cache_init(void) { thread_stack_cache = kmem_cache_create_usercopy("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, 0, THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL); } # endif /* THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) */ #else /* CONFIG_ARCH_THREAD_STACK_ALLOCATOR */ static int alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = arch_alloc_thread_stack_node(tsk, node); tsk->stack = stack; return stack ? 0 : -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { arch_free_thread_stack(tsk); tsk->stack = NULL; } #endif /* !CONFIG_ARCH_THREAD_STACK_ALLOCATOR */ /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */ struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */ struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */ struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; 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) vma_init(vma, mm); 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) { 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. */ *new = data_race(*orig); INIT_LIST_HEAD(&new->anon_vma_chain); dup_anon_vma_name(orig, new); } return new; } void vm_area_free(struct vm_area_struct *vma) { free_anon_vma_name(vma); kmem_cache_free(vm_area_cachep, vma); } 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) { 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); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) { struct file *exe_file; exe_file = get_mm_exe_file(oldmm); RCU_INIT_POINTER(mm->exe_file, exe_file); /* * We depend on the oldmm having properly denied write access to the * exe_file already. */ if (exe_file && deny_write_access(exe_file)) pr_warn_once("deny_write_access() failed in %s\n", __func__); } #ifdef CONFIG_MMU static __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { struct vm_area_struct *mpnt, *tmp; int retval; unsigned long charge = 0; LIST_HEAD(uf); MA_STATE(old_mas, &oldmm->mm_mt, 0, 0); MA_STATE(mas, &mm->mm_mt, 0, 0); uprobe_start_dup_mmap(); if (mmap_write_lock_killable(oldmm)) { retval = -EINTR; goto fail_uprobe_end; } flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* * Not linked in yet - no deadlock potential: */ mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING); /* No ordering required: file already has been exposed. */ dup_mm_exe_file(mm, oldmm); mm->total_vm = oldmm->total_vm; mm->data_vm = oldmm->data_vm; mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; retval = ksm_fork(mm, oldmm); if (retval) goto out; khugepaged_fork(mm, oldmm); retval = mas_expected_entries(&mas, oldmm->map_count); if (retval) goto out; mas_for_each(&old_mas, mpnt, ULONG_MAX) { struct file *file; if (mpnt->vm_flags & VM_DONTCOPY) { 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; tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT); file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; get_file(file); i_mmap_lock_write(mapping); if (tmp->vm_flags & VM_SHARED) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ vma_interval_tree_insert_after(tmp, mpnt, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); i_mmap_unlock_write(mapping); } /* * Copy/update hugetlb private vma information. */ if (is_vm_hugetlb_page(tmp)) hugetlb_dup_vma_private(tmp); /* Link the vma into the MT */ mas.index = tmp->vm_start; mas.last = tmp->vm_end - 1; mas_store(&mas, tmp); if (mas_is_err(&mas)) goto fail_nomem_mas_store; mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); if (retval) goto loop_out; } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); loop_out: mas_destroy(&mas); out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); dup_userfaultfd_complete(&uf); fail_uprobe_end: uprobe_end_dup_mmap(); return retval; fail_nomem_mas_store: unlink_anon_vmas(tmp); fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); goto loop_out; } static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) return -ENOMEM; return 0; } static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } #else static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { mmap_write_lock(oldmm); dup_mm_exe_file(mm, oldmm); mmap_write_unlock(oldmm); return 0; } #define mm_alloc_pgd(mm) (0) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ static void check_mm(struct mm_struct *mm) { int i; BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS, "Please make sure 'struct resident_page_types[]' is updated as well"); for (i = 0; i < NR_MM_COUNTERS; i++) { long x = atomic_long_read(&mm->rss_stat.count[i]); if (unlikely(x)) pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n", mm, resident_page_types[i], x); } if (mm_pgtables_bytes(mm)) pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n", mm_pgtables_bytes(mm)); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by * mmput. Free the page directory and the mm. */ void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); WARN_ON_ONCE(mm == current->mm); WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); mm_pasid_drop(mm); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); static void mmdrop_async_fn(struct work_struct *work) { struct mm_struct *mm; mm = container_of(work, struct mm_struct, async_put_work); __mmdrop(mm); } static void mmdrop_async(struct mm_struct *mm) { if (unlikely(atomic_dec_and_test(&mm->mm_count))) { INIT_WORK(&mm->async_put_work, mmdrop_async_fn); schedule_work(&mm->async_put_work); } } static inline void free_signal_struct(struct signal_struct *sig) { taskstats_tgid_free(sig); sched_autogroup_exit(sig); /* * __mmdrop is not safe to call from softirq context on x86 due to * pgd_dtor so postpone it to the async context */ if (sig->oom_mm) mmdrop_async(sig->oom_mm); kmem_cache_free(signal_cachep, sig); } static inline void put_signal_struct(struct signal_struct *sig) { if (refcount_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); io_uring_free(tsk); cgroup_free(tsk); task_numa_free(tsk, true); security_task_free(tsk); bpf_task_storage_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 __init __weak arch_task_cache_init(void) { } /* * set_max_threads */ static void set_max_threads(unsigned int max_threads_suggested) { u64 threads; unsigned long nr_pages = totalram_pages(); /* * The number of threads shall be limited such that the thread * structures may only consume a small part of the available memory. */ if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64) threads = MAX_THREADS; else threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE, (u64) THREAD_SIZE * 8UL); if (threads > max_threads_suggested) threads = max_threads_suggested; max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); } #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT /* Initialized by the architecture: */ int arch_task_struct_size __read_mostly; #endif #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR static void task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ arch_thread_struct_whitelist(offset, size); /* * Handle zero-sized whitelist or empty thread_struct, otherwise * adjust offset to position of thread_struct in task_struct. */ if (unlikely(*size == 0)) *offset = 0; else *offset += offsetof(struct task_struct, thread); } #endif /* CONFIG_ARCH_TASK_STRUCT_ALLOCATOR */ void __init fork_init(void) { int i; #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN 0 #endif int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN); unsigned long useroffset, usersize; /* create a slab on which task_structs can be allocated */ task_struct_whitelist(&useroffset, &usersize); task_struct_cachep = kmem_cache_create_usercopy("task_struct", arch_task_struct_size, align, SLAB_PANIC|SLAB_ACCOUNT, useroffset, usersize, NULL); #endif /* do the arch specific task caches init */ arch_task_cache_init(); set_max_threads(MAX_THREADS); init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2; init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", NULL, free_vm_stack_cache); #endif scs_init(); lockdep_init_task(&init_task); uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; return 0; } void set_task_stack_end_magic(struct task_struct *tsk) { unsigned long *stackend; stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ } static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; int err; if (node == NUMA_NO_NODE) node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; err = arch_dup_task_struct(tsk, orig); if (err) goto free_tsk; err = alloc_thread_stack_node(tsk, node); if (err) goto free_tsk; #ifdef CONFIG_THREAD_INFO_IN_TASK refcount_set(&tsk->stack_refcount, 1); #endif account_kernel_stack(tsk, 1); err = scs_prepare(tsk, node); if (err) goto free_stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under * the sighand lock in case orig has changed between now and * then. Until then, filter must be NULL to avoid messing up * the usage counts on the error path calling free_task. */ tsk->seccomp.filter = NULL; #endif setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); set_task_stack_end_magic(tsk); clear_syscall_work_syscall_user_dispatch(tsk); #ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif if (orig->cpus_ptr == &orig->cpus_mask) tsk->cpus_ptr = &tsk->cpus_mask; dup_user_cpus_ptr(tsk, orig, node); /* * One for the user space visible state that goes away when reaped. * One for the scheduler. */ refcount_set(&tsk->rcu_users, 2); /* One for the rcu users */ refcount_set(&tsk->usage, 1); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; tsk->worker_private = NULL; kcov_task_init(tsk); kmsan_task_create(tsk); kmap_local_fork(tsk); #ifdef CONFIG_FAULT_INJECTION tsk->fail_nth = 0; #endif #ifdef CONFIG_BLK_CGROUP tsk->throttle_queue = NULL; tsk->use_memdelay = 0; #endif #ifdef CONFIG_IOMMU_SVA tsk->pasid_activated = 0; #endif #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif #ifdef CONFIG_CPU_SUP_INTEL tsk->reported_split_lock = 0; #endif 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); mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); mm_pasid_init(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); hugetlb_count_init(mm); if (current->mm) { mm->flags = current->mm->flags & MMF_INIT_MASK; mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { mm->flags = default_dump_filter; mm->def_flags = 0; } if (mm_alloc_pgd(mm)) goto fail_nopgd; if (init_new_context(p, mm)) goto fail_nocontext; mm->user_ns = get_user_ns(user_ns); lru_gen_init_mm(mm); return mm; fail_nocontext: mm_free_pgd(mm); fail_nopgd: free_mm(mm); return NULL; } /* * Allocate and initialize an mm_struct. */ struct mm_struct *mm_alloc(void) { struct mm_struct *mm; mm = allocate_mm(); if (!mm) return NULL; memset(mm, 0, sizeof(*mm)); return mm_init(mm, current, current_user_ns()); } static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); mm_put_huge_zero_page(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); list_del(&mm->mmlist); spin_unlock(&mmlist_lock); } if (mm->binfmt) module_put(mm->binfmt->module); lru_gen_del_mm(mm); mmdrop(mm); } /* * Decrement the use count and release all resources for an mm. */ void mmput(struct mm_struct *mm) { might_sleep(); if (atomic_dec_and_test(&mm->mm_users)) __mmput(mm); } EXPORT_SYMBOL_GPL(mmput); #ifdef CONFIG_MMU static void mmput_async_fn(struct work_struct *work) { struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); __mmput(mm); } void mmput_async(struct mm_struct *mm) { if (atomic_dec_and_test(&mm->mm_users)) { INIT_WORK(&mm->async_put_work, mmput_async_fn); schedule_work(&mm->async_put_work); } } EXPORT_SYMBOL_GPL(mmput_async); #endif /** * set_mm_exe_file - change a reference to the mm's executable file * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main users are mmput() and sys_execve(). Callers prevent concurrent * invocations: in mmput() nobody alive left, in execve task is single * threaded. * * Can only fail if new_exe_file != NULL. */ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct file *old_exe_file; /* * It is safe to dereference the exe_file without RCU as * this function is only called if nobody else can access * this mm -- see comment above for justification. */ old_exe_file = rcu_dereference_raw(mm->exe_file); if (new_exe_file) { /* * We expect the caller (i.e., sys_execve) to already denied * write access, so this is unlikely to fail. */ if (unlikely(deny_write_access(new_exe_file))) return -EACCES; get_file(new_exe_file); } rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) { allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * replace_mm_exe_file - replace a reference to the mm's executable file * * This changes mm's executable file (shown as symlink /proc/[pid]/exe), * dealing with concurrent invocation and without grabbing the mmap lock in * write mode. * * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE). */ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct vm_area_struct *vma; struct file *old_exe_file; int ret = 0; /* Forbid mm->exe_file change if old file still mapped. */ old_exe_file = get_mm_exe_file(mm); if (old_exe_file) { VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (path_equal(&vma->vm_file->f_path, &old_exe_file->f_path)) { ret = -EBUSY; break; } } mmap_read_unlock(mm); fput(old_exe_file); if (ret) return ret; } /* set the new file, lockless */ ret = deny_write_access(new_exe_file); if (ret) return -EACCES; get_file(new_exe_file); old_exe_file = xchg(&mm->exe_file, new_exe_file); if (old_exe_file) { /* * Don't race with dup_mmap() getting the file and disallowing * write access while someone might open the file writable. */ mmap_read_lock(mm); allow_write_access(old_exe_file); fput(old_exe_file); mmap_read_unlock(mm); } return 0; } /** * get_mm_exe_file - acquire a reference to the mm's executable file * * Returns %NULL if mm has no associated executable file. * User must release file via fput(). */ struct file *get_mm_exe_file(struct mm_struct *mm) { struct file *exe_file; rcu_read_lock(); exe_file = rcu_dereference(mm->exe_file); if (exe_file && !get_file_rcu(exe_file)) exe_file = NULL; rcu_read_unlock(); return exe_file; } /** * get_task_exe_file - acquire a reference to the task's executable file * * Returns %NULL if task's mm (if any) has no associated executable file or * this is a kernel thread with borrowed mm (see the comment above get_task_mm). * User must release file via fput(). */ struct file *get_task_exe_file(struct task_struct *task) { struct file *exe_file = NULL; struct mm_struct *mm; task_lock(task); mm = task->mm; if (mm) { if (!(task->flags & PF_KTHREAD)) exe_file = get_mm_exe_file(mm); } task_unlock(task); return exe_file; } /** * get_task_mm - acquire a reference to the task's mm * * Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning * this kernel workthread has transiently adopted a user mm with use_mm, * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() * after use. Typically used by /proc and ptrace. */ struct mm_struct *get_task_mm(struct task_struct *task) { struct mm_struct *mm; task_lock(task); mm = task->mm; if (mm) { if (task->flags & PF_KTHREAD) mm = NULL; else mmget(mm); } task_unlock(task); return mm; } EXPORT_SYMBOL_GPL(get_task_mm); struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) { struct mm_struct *mm; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return ERR_PTR(err); mm = get_task_mm(task); if (mm && mm != current->mm && !ptrace_may_access(task, mode)) { mmput(mm); mm = ERR_PTR(-EACCES); } up_read(&task->signal->exec_update_lock); return mm; } static void complete_vfork_done(struct task_struct *tsk) { struct completion *vfork; task_lock(tsk); vfork = tsk->vfork_done; if (likely(vfork)) { tsk->vfork_done = NULL; complete(vfork); } task_unlock(tsk); } static int wait_for_vfork_done(struct task_struct *child, struct completion *vfork) { unsigned int state = TASK_UNINTERRUPTIBLE|TASK_KILLABLE|TASK_FREEZABLE; int killed; cgroup_enter_frozen(); killed = wait_for_completion_state(vfork, state); cgroup_leave_frozen(false); if (killed) { task_lock(child); child->vfork_done = NULL; task_unlock(child); } put_task_struct(child); return killed; } /* Please note the differences between mmput and mm_release. * mmput is called whenever we stop holding onto a mm_struct, * error success whatever. * * mm_release is called after a mm_struct has been removed * from the current process. * * This difference is important for error handling, when we * only half set up a mm_struct for a new process and need to restore * the old one. Because we mmput the new mm_struct before * restoring the old one. . . * Eric Biederman 10 January 1998 */ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { uprobe_free_utask(tsk); /* Get rid of any cached register state */ deactivate_mm(tsk, mm); /* * Signal userspace if we're not exiting with a core dump * because we want to leave the value intact for debugging * purposes. */ if (tsk->clear_child_tid) { if (atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. */ put_user(0, tsk->clear_child_tid); do_futex(tsk->clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0, 0); } tsk->clear_child_tid = NULL; } /* * All done, finally we can wake up parent and return this mm to him. * Also kthread_stop() uses this completion for synchronization. */ if (tsk->vfork_done) complete_vfork_done(tsk); } void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exit_release(tsk); mm_release(tsk, mm); } void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exec_release(tsk); mm_release(tsk, mm); } /** * dup_mm() - duplicates an existing mm structure * @tsk: the task_struct with which the new mm will be associated. * @oldmm: the mm to duplicate. * * Allocates a new mm structure and duplicates the provided @oldmm structure * content into it. * * Return: the duplicated mm or NULL on failure. */ static struct mm_struct *dup_mm(struct task_struct *tsk, struct mm_struct *oldmm) { struct mm_struct *mm; int err; mm = allocate_mm(); if (!mm) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; err = dup_mmap(mm, oldmm); if (err) goto free_pt; mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; if (mm->binfmt && !try_module_get(mm->binfmt->module)) goto free_pt; return mm; free_pt: /* don't put binfmt in mmput, we haven't got module yet */ mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); fail_nomem: return NULL; } static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) { struct mm_struct *mm, *oldmm; tsk->min_flt = tsk->maj_flt = 0; tsk->nvcsw = tsk->nivcsw = 0; #ifdef CONFIG_DETECT_HUNG_TASK tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; tsk->last_switch_time = 0; #endif tsk->mm = NULL; tsk->active_mm = NULL; /* * Are we cloning a kernel thread? * * We need to steal a active VM for that.. */ oldmm = current->mm; if (!oldmm) return 0; if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; } else { mm = dup_mm(tsk, current->mm); if (!mm) return -ENOMEM; } tsk->mm = mm; tsk->active_mm = mm; return 0; } static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) { struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ spin_lock(&fs->lock); if (fs->in_exec) { spin_unlock(&fs->lock); return -EAGAIN; } fs->users++; spin_unlock(&fs->lock); return 0; } tsk->fs = copy_fs_struct(fs); if (!tsk->fs) return -ENOMEM; return 0; } static int copy_files(unsigned long clone_flags, struct task_struct *tsk) { struct files_struct *oldf, *newf; int error = 0; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) goto out; if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); goto out; } newf = dup_fd(oldf, NR_OPEN_MAX, &error); if (!newf) goto out; tsk->files = newf; error = 0; out: return error; } static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) { struct sighand_struct *sig; if (clone_flags & CLONE_SIGHAND) { refcount_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; refcount_set(&sig->count, 1); spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); spin_unlock_irq(¤t->sighand->siglock); /* Reset all signal handler not set to SIG_IGN to SIG_DFL. */ if (clone_flags & CLONE_CLEAR_SIGHAND) flush_signal_handlers(tsk, 0); return 0; } void __cleanup_sighand(struct sighand_struct *sighand) { if (refcount_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); /* * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it * without an RCU grace period, see __lock_task_sighand(). */ kmem_cache_free(sighand_cachep, sighand); } } /* * Initialize POSIX timer handling for a thread group. */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { struct posix_cputimers *pct = &sig->posix_cputimers; unsigned long cpu_limit; cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); posix_cputimers_group_init(pct, cpu_limit); } static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; if (clone_flags & CLONE_THREAD) return 0; sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; if (!sig) return -ENOMEM; sig->nr_threads = 1; sig->quick_threads = 1; atomic_set(&sig->live, 1); refcount_set(&sig->sigcnt, 1); /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head); init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_HLIST_HEAD(&sig->multiprocess); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS INIT_LIST_HEAD(&sig->posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; #endif task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); posix_cpu_timers_init_group(sig); tty_audit_fork(sig); sched_autogroup_fork(sig); sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); init_rwsem(&sig->exec_update_lock); return 0; } static void copy_seccomp(struct task_struct *p) { #ifdef CONFIG_SECCOMP /* * Must be called with sighand->lock held, which is common to * all threads in the group. Holding cred_guard_mutex is not * needed because this new task is not yet running and cannot * be racing exec. */ assert_spin_locked(¤t->sighand->siglock); /* Ref-count the new filter user, and assign it. */ get_seccomp_filter(current); p->seccomp = current->seccomp; /* * Explicitly enable no_new_privs here in case it got set * between the task_struct being duplicated and holding the * sighand lock. The seccomp state and nnp must be in sync. */ if (task_no_new_privs(current)) task_set_no_new_privs(p); /* * If the parent gained a seccomp mode after copying thread * flags and between before we held the sighand lock, we have * to manually enable the seccomp thread flag here. */ if (p->seccomp.mode != SECCOMP_MODE_DISABLED) set_task_syscall_work(p, SECCOMP); #endif } SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) { current->clear_child_tid = tidptr; return task_pid_vnr(current); } static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES p->pi_waiters = RB_ROOT_CACHED; p->pi_top_task = NULL; p->pi_blocked_on = NULL; #endif } static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); } static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { if (type == PIDTYPE_PID) task->thread_pid = pid; else task->signal->pids[type] = pid; } static inline void rcu_copy_process(struct task_struct *p) { #ifdef CONFIG_PREEMPT_RCU p->rcu_read_lock_nesting = 0; p->rcu_read_unlock_special.s = 0; p->rcu_blocked_node = NULL; INIT_LIST_HEAD(&p->rcu_node_entry); #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); p->rcu_tasks_idle_cpu = -1; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; p->trc_reader_special.s = 0; INIT_LIST_HEAD(&p->trc_holdout_list); INIT_LIST_HEAD(&p->trc_blkd_node); #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } struct pid *pidfd_pid(const struct file *file) { if (file->f_op == &pidfd_fops) return file->private_data; return ERR_PTR(-EBADF); } static int pidfd_release(struct inode *inode, struct file *file) { struct pid *pid = file->private_data; file->private_data = NULL; put_pid(pid); return 0; } #ifdef CONFIG_PROC_FS /** * pidfd_show_fdinfo - print information about a pidfd * @m: proc fdinfo file * @f: file referencing a pidfd * * Pid: * This function will print the pid that a given pidfd refers to in the * pid namespace of the procfs instance. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its pid. This is * similar to calling getppid() on a process whose parent is outside of * its pid namespace. * * NSpid: * If pid namespaces are supported then this function will also print * the pid of a given pidfd refers to for all descendant pid namespaces * starting from the current pid namespace of the instance, i.e. the * Pid field and the first entry in the NSpid field will be identical. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its first NSpid * entry and no others will be shown. * Note that this differs from the Pid and NSpid fields in * /proc/<pid>/status where Pid and NSpid are always shown relative to * the pid namespace of the procfs instance. The difference becomes * obvious when sending around a pidfd between pid namespaces from a * different branch of the tree, i.e. where no ancestral relation is * present between the pid namespaces: * - create two new pid namespaces ns1 and ns2 in the initial pid * namespace (also take care to create new mount namespaces in the * new pid namespace and mount procfs) * - create a process with a pidfd in ns1 * - send pidfd from ns1 to ns2 * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid * have exactly one entry, which is 0 */ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) { struct pid *pid = f->private_data; struct pid_namespace *ns; pid_t nr = -1; if (likely(pid_has_task(pid, PIDTYPE_PID))) { ns = proc_pid_ns(file_inode(m->file)->i_sb); nr = pid_nr_ns(pid, ns); } seq_put_decimal_ll(m, "Pid:\t", nr); #ifdef CONFIG_PID_NS seq_put_decimal_ll(m, "\nNSpid:\t", nr); if (nr > 0) { int i; /* If nr is non-zero it means that 'pid' is valid and that * ns, i.e. the pid namespace associated with the procfs * instance, is in the pid namespace hierarchy of pid. * Start at one below the already printed level. */ for (i = ns->level + 1; i <= pid->level; i++) seq_put_decimal_ll(m, "\t", pid->numbers[i].nr); } #endif seq_putc(m, '\n'); } #endif /* * Poll support for process exit notification. */ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { struct pid *pid = file->private_data; __poll_t poll_flags = 0; poll_wait(file, &pid->wait_pidfd, pts); /* * Inform pollers only when the whole thread group exits. * If the thread group leader exits before all other threads in the * group, then poll(2) should block, similar to the wait(2) family. */ if (thread_group_exited(pid)) poll_flags = EPOLLIN | EPOLLRDNORM; return poll_flags; } const struct file_operations pidfd_fops = { .release = pidfd_release, .poll = pidfd_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = pidfd_show_fdinfo, #endif }; static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); free_task(tsk); } static __always_inline void delayed_free_task(struct task_struct *tsk) { if (IS_ENABLED(CONFIG_MEMCG)) call_rcu(&tsk->rcu, __delayed_free_task); else free_task(tsk); } static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) { /* Skip if kernel thread */ if (!tsk->mm) return; /* Skip if spawning a thread or using vfork */ if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) return; /* We need to synchronize with __set_oom_adj */ mutex_lock(&oom_adj_mutex); set_bit(MMF_MULTIPROCESS, &tsk->mm->flags); /* Update the values in case they were changed after copy_signal */ tsk->signal->oom_score_adj = current->signal->oom_score_adj; tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_unlock(&oom_adj_mutex); } #ifdef CONFIG_RV static void rv_task_fork(struct task_struct *p) { int i; for (i = 0; i < RV_PER_TASK_MONITORS; i++) p->rv[i].da_mon.monitoring = false; } #else #define rv_task_fork(p) do {} while (0) #endif /* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ static __latent_entropy struct task_struct *copy_process( struct pid *pid, int trace, int node, struct kernel_clone_args *args) { int pidfd = -1, retval; struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; const u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different * namespace */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); /* * Siblings of global init remain as zombies on exit since they are * not reaped by their parent (swapper). To solve this and to avoid * multi-rooted process trees, prevent global and container-inits * from creating siblings. */ if ((clone_flags & CLONE_PARENT) && current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); /* * If the new process will be in a different pid or user namespace * do not allow it to share a thread group with the forking task. */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != nsp->pid_ns_for_children)) return ERR_PTR(-EINVAL); } /* * If the new process will be in a different time namespace * do not allow it to share VM or a thread group with the forking task. */ if (clone_flags & (CLONE_THREAD | CLONE_VM)) { if (nsp->time_ns != nsp->time_ns_for_children) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. * - CLONE_THREAD is blocked until someone really needs it. */ if (clone_flags & (CLONE_DETACHED | CLONE_THREAD)) return ERR_PTR(-EINVAL); } /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple * processes that happen during the fork and delay them so that * they appear to happen after the fork. */ sigemptyset(&delayed.signal); INIT_HLIST_NODE(&delayed.node); spin_lock_irq(¤t->sighand->siglock); if (!(clone_flags & CLONE_THREAD)) hlist_add_head(&delayed.node, ¤t->signal->multiprocess); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; if (args->io_thread) { /* * Mark us an IO worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_IO_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; ftrace_graph_init_task(p); rt_mutex_init_task(p); lockdep_assert_irqs_enabled(); #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; retval = -EAGAIN; if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_cleanup_count; } current->flags &= ~PF_NPROC_EXCEEDED; /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ retval = -EAGAIN; if (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY); p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); p->utime = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME p->utimescaled = p->stimescaled = 0; #endif prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_init(&p->vtime.seqcount); p->vtime.starttime = 0; p->vtime.state = VTIME_INACTIVE; #endif #ifdef CONFIG_IO_URING p->io_uring = NULL; #endif #if defined(SPLIT_RSS_COUNTING) memset(&p->rss_stat, 0, sizeof(p->rss_stat)); #endif p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI p->psi_flags = 0; #endif task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); if (args->kthread) { if (!set_kthread_struct(p)) goto bad_fork_cleanup_delayacct; } #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup_delayacct; } #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; p->cpuset_slab_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock); #endif #ifdef CONFIG_TRACE_IRQFLAGS memset(&p->irqtrace, 0, sizeof(p->irqtrace)); p->irqtrace.hardirq_disable_ip = _THIS_IP_; p->irqtrace.softirq_enable_ip = _THIS_IP_; p->softirqs_enabled = 1; p->softirq_context = 0; #endif p->pagefault_disabled = 0; #ifdef CONFIG_LOCKDEP lockdep_init_task(p); #endif #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; #endif #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(p->bpf_storage, NULL); p->bpf_ctx = NULL; #endif /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) goto bad_fork_cleanup_policy; retval = perf_event_init_task(p, clone_flags); if (retval) goto bad_fork_cleanup_policy; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = security_task_alloc(p, clone_flags); if (retval) goto bad_fork_cleanup_audit; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_security; retval = copy_files(clone_flags, p); if (retval) goto bad_fork_cleanup_semundo; retval = copy_fs(clone_flags, p); if (retval) goto bad_fork_cleanup_files; retval = copy_sighand(clone_flags, p); if (retval) goto bad_fork_cleanup_fs; retval = copy_signal(clone_flags, p); if (retval) goto bad_fork_cleanup_sighand; retval = copy_mm(clone_flags, p); if (retval) goto bad_fork_cleanup_signal; retval = copy_namespaces(clone_flags, p); if (retval) goto bad_fork_cleanup_mm; retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(p, args); if (retval) goto bad_fork_cleanup_io; stackleak_task_init(p); if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; } } /* * This has to happen after we've potentially unshared the file * descriptor table (so that the pidfd doesn't leak into the child * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { retval = get_unused_fd_flags(O_RDWR | O_CLOEXEC); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; pidfile = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, O_RDWR | O_CLOEXEC); if (IS_ERR(pidfile)) { put_unused_fd(pidfd); retval = PTR_ERR(pidfile); goto bad_fork_free_pid; } get_pid(pid); /* held by pidfile now */ retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; } #ifdef CONFIG_BLOCK p->plug = NULL; #endif futex_init_task(p); /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); clear_task_syscall_work(p, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(p, SYSCALL_EMU); #endif clear_tsk_latency_tracing(p); /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; p->tgid = current->tgid; } else { p->group_leader = p; p->tgid = p->pid; } p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->pdeath_signal = 0; INIT_LIST_HEAD(&p->thread_group); p->task_works = NULL; clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL; #endif #ifdef CONFIG_RETHOOK p->rethooks.first = NULL; #endif /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted that the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ retval = cgroup_can_fork(p, args); if (retval) goto bad_fork_put_pidfd; /* * Now that the cgroups are pinned, re-clone the parent cgroup and put * the new task on the correct runqueue. All this *before* the task * becomes visible. * * This isn't part of ->can_fork() because while the re-cloning is * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ sched_cgroup_fork(p, args); /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by * stalling fork(2) after we recorded the start_time but before it is * visible to the system. */ p->start_time = ktime_get_ns(); p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; p->exit_signal = args->exit_signal; } klp_copy_process(p); sched_core_fork(p); spin_lock(¤t->sighand->siglock); /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); rv_task_fork(p); rseq_fork(p, clone_flags); /* Don't start children in a dying pid namespace */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; goto bad_fork_cancel_cgroup; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_cancel_cgroup; } init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); init_task_pid(p, PIDTYPE_PID, pid); if (thread_group_leader(p)) { init_task_pid(p, PIDTYPE_TGID, pid); init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) { ns_of_pid(pid)->child_reaper = p; p->signal->flags |= SIGNAL_UNKILLABLE; } p->signal->shared_pending.signal = delayed.signal; p->signal->tty = tty_kref_get(current->signal->tty); /* * Inherit has_child_subreaper flag under the same * tasklist_lock with adding child to the process tree * for propagate_has_child_subreaper optimization. */ p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper || p->real_parent->signal->is_child_subreaper; list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_TGID); attach_pid(p, PIDTYPE_PGID); attach_pid(p, PIDTYPE_SID); __this_cpu_inc(process_counts); } else { current->signal->nr_threads++; current->signal->quick_threads++; atomic_inc(¤t->signal->live); refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); list_add_tail_rcu(&p->thread_node, &p->signal->thread_head); } attach_pid(p, PIDTYPE_PID); nr_threads++; } total_forks++; hlist_del_init(&delayed.node); spin_unlock(¤t->sighand->siglock); syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); if (pidfile) fd_install(pidfd, pidfile); proc_fork_connector(p); sched_post_fork(p); cgroup_post_fork(p, args); perf_event_fork(p); trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); copy_oom_score_adj(clone_flags, p); return p; bad_fork_cancel_cgroup: sched_core_free(p); spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { fput(pidfile); put_unused_fd(pidfd); } bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: exit_thread(p); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { mm_clear_owner(p->mm, p); mmput(p->mm); } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_security: security_task_free(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_perf: perf_event_free_task(p); bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); #endif bad_fork_cleanup_delayacct: delayacct_tsk_free(p); bad_fork_cleanup_count: dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); exit_creds(p); bad_fork_free: WRITE_ONCE(p->__state, TASK_DEAD); exit_task_stack_account(p); put_task_stack(p); delayed_free_task(p); fork_out: spin_lock_irq(¤t->sighand->siglock); hlist_del_init(&delayed.node); spin_unlock_irq(¤t->sighand->siglock); return ERR_PTR(retval); } static inline void init_idle_pids(struct task_struct *idle) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */ init_task_pid(idle, type, &init_struct_pid); } } static int idle_dummy(void *dummy) { /* This function is never called */ return 0; } struct task_struct * __init fork_idle(int cpu) { struct task_struct *task; struct kernel_clone_args args = { .flags = CLONE_VM, .fn = &idle_dummy, .fn_arg = NULL, .kthread = 1, .idle = 1, }; task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args); if (!IS_ERR(task)) { init_idle_pids(task); init_idle(task, cpu); } return task; } struct mm_struct *copy_init_mm(void) { return dup_mm(NULL, &init_mm); } /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. * The returned task is inactive, and the caller must fire it up through * wake_up_new_task(p). All signals are blocked in the created task. */ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) { unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| CLONE_IO; struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, .io_thread = 1, }; return copy_process(NULL, 0, node, &args); } /* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. * * args->exit_signal is expected to be checked for sanity by the caller. */ pid_t kernel_clone(struct kernel_clone_args *args) { u64 clone_flags = args->flags; struct completion vfork; struct pid *pid; struct task_struct *p; int trace = 0; pid_t nr; /* * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate * field in struct clone_args and it still doesn't make sense to have * them both point at the same memory location. Performing this check * here has the advantage that we don't need to have a separate helper * to check for legacy clone(). */ if ((args->flags & CLONE_PIDFD) && (args->flags & CLONE_PARENT_SETTID) && (args->pidfd == args->parent_tid)) return -EINVAL; /* * Determine whether and which event to report to ptracer. When * called from kernel_thread or CLONE_UNTRACED is explicitly * requested, no event is reported; otherwise, report if the event * for the type of forking is enabled. */ if (!(clone_flags & CLONE_UNTRACED)) { if (clone_flags & CLONE_VFORK) trace = PTRACE_EVENT_VFORK; else if (args->exit_signal != SIGCHLD) trace = PTRACE_EVENT_CLONE; else trace = PTRACE_EVENT_FORK; if (likely(!ptrace_event_enabled(current, trace))) trace = 0; } p = copy_process(NULL, trace, NUMA_NO_NODE, args); add_latent_entropy(); if (IS_ERR(p)) return PTR_ERR(p); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ trace_sched_process_fork(current, p); pid = get_task_pid(p, PIDTYPE_PID); nr = pid_vnr(pid); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, args->parent_tid); if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); get_task_struct(p); } if (IS_ENABLED(CONFIG_LRU_GEN) && !(clone_flags & CLONE_VM)) { /* lock the task to synchronize with memcg migration */ task_lock(p); lru_gen_add_mm(p->mm); task_unlock(p); } wake_up_new_task(p); /* forking complete and child started to run, tell ptracer */ if (unlikely(trace)) ptrace_event_pid(trace, pid); if (clone_flags & CLONE_VFORK) { if (!wait_for_vfork_done(p, &vfork)) ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } put_pid(pid); return nr; } /* * Create a kernel thread. */ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, .kthread = 1, }; return kernel_clone(&args); } /* * Create a user mode thread. */ pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, }; return kernel_clone(&args); } #ifdef __ARCH_WANT_SYS_FORK SYSCALL_DEFINE0(fork) { #ifdef CONFIG_MMU struct kernel_clone_args args = { .exit_signal = SIGCHLD, }; return kernel_clone(&args); #else /* can not support in nommu mode */ return -EINVAL; #endif } #endif #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { struct kernel_clone_args args = { .flags = CLONE_VFORK | CLONE_VM, .exit_signal = SIGCHLD, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE #ifdef CONFIG_CLONE_BACKWARDS SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, unsigned long, tls, int __user *, child_tidptr) #elif defined(CONFIG_CLONE_BACKWARDS2) SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #elif defined(CONFIG_CLONE_BACKWARDS3) SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, int, stack_size, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #endif { struct kernel_clone_args args = { .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE3 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) { int err; struct clone_args args; pid_t *kset_tid = kargs->set_tid; BUILD_BUG_ON(offsetofend(struct clone_args, tls) != CLONE_ARGS_SIZE_VER0); BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) != CLONE_ARGS_SIZE_VER1); BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) != CLONE_ARGS_SIZE_VER2); BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2); if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; err = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (err) return err; if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL)) return -EINVAL; if (unlikely(!args.set_tid && args.set_tid_size > 0)) return -EINVAL; if (unlikely(args.set_tid && args.set_tid_size == 0)) return -EINVAL; /* * Verify that higher 32bits of exit_signal are unset and that * it is a valid signal */ if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) || !valid_signal(args.exit_signal))) return -EINVAL; if ((args.flags & CLONE_INTO_CGROUP) && (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2)) return -EINVAL; *kargs = (struct kernel_clone_args){ .flags = args.flags, .pidfd = u64_to_user_ptr(args.pidfd), .child_tid = u64_to_user_ptr(args.child_tid), .parent_tid = u64_to_user_ptr(args.parent_tid), .exit_signal = args.exit_signal, .stack = args.stack, .stack_size = args.stack_size, .tls = args.tls, .set_tid_size = args.set_tid_size, .cgroup = args.cgroup, }; if (args.set_tid && copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid), (kargs->set_tid_size * sizeof(pid_t)))) return -EFAULT; kargs->set_tid = kset_tid; return 0; } /** * clone3_stack_valid - check and prepare stack * @kargs: kernel clone args * * Verify that the stack arguments userspace gave us are sane. * In addition, set the stack direction for userspace since it's easy for us to * determine. */ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) { if (kargs->stack == 0) { if (kargs->stack_size > 0) return false; } else { if (kargs->stack_size == 0) return false; if (!access_ok((void __user *)kargs->stack, kargs->stack_size)) return false; #if !defined(CONFIG_STACK_GROWSUP) && !defined(CONFIG_IA64) kargs->stack += kargs->stack_size; #endif } return true; } static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP)) return false; /* * - make the CLONE_DETACHED bit reusable for clone3 * - make the CSIGNAL bits reusable for clone3 */ if (kargs->flags & (CLONE_DETACHED | CSIGNAL)) return false; if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) == (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) return false; if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) && kargs->exit_signal) return false; if (!clone3_stack_valid(kargs)) return false; return true; } /** * clone3 - create a new process with specific properties * @uargs: argument structure * @size: size of @uargs * * clone3() is the extensible successor to clone()/clone2(). * It takes a struct as argument that is versioned by its size. * * Return: On success, a positive PID for the child process. * On error, a negative errno number. */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; struct kernel_clone_args kargs; pid_t set_tid[MAX_PID_NS_LEVEL]; kargs.set_tid = set_tid; err = copy_clone_args_from_user(&kargs, uargs, size); if (err) return err; if (!clone3_args_valid(&kargs)) return -EINVAL; return kernel_clone(&kargs); } #endif void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data) { struct task_struct *leader, *parent, *child; int res; read_lock(&tasklist_lock); leader = top = top->group_leader; down: for_each_thread(leader, parent) { list_for_each_entry(child, &parent->children, sibling) { res = visitor(child, data); if (res) { if (res < 0) goto out; leader = child; goto down; } up: ; } } if (leader != top) { child = leader; parent = child->real_parent; leader = parent->group_leader; goto up; } out: read_unlock(&tasklist_lock); } #ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; spin_lock_init(&sighand->siglock); init_waitqueue_head(&sighand->signalfd_wqh); } void __init proc_caches_init(void) { unsigned int mm_size; 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); /* * The mm_cpumask is located at the end of mm_struct, and is * dynamically sized based on the maximum CPU number this system * can have, taking hotplug into account (nr_cpu_ids). */ mm_size = sizeof(struct mm_struct) + cpumask_size(); mm_cachep = kmem_cache_create_usercopy("mm_struct", mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); mmap_init(); nsproxy_cache_init(); } /* * Check constraints on flags passed to the unshare system call. */ static int check_unshare_flags(unsigned long unshare_flags) { if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP| CLONE_NEWTIME)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing * to unshare. Note that unsharing the address space or the * signal handlers also need to unshare the signal queues (aka * CLONE_THREAD). */ if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) { if (!thread_group_empty(current)) return -EINVAL; } if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) { if (refcount_read(¤t->sighand->count) > 1) return -EINVAL; } if (unshare_flags & CLONE_VM) { if (!current_is_single_threaded()) return -EINVAL; } return 0; } /* * Unshare the filesystem structure if it is being shared */ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; if (!(unshare_flags & CLONE_FS) || !fs) return 0; /* don't need lock here; in the worst case we'll do useless copy */ if (fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); if (!*new_fsp) return -ENOMEM; return 0; } /* * Unshare file descriptor table if it is being shared */ int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp) { struct files_struct *fd = current->files; int error = 0; if ((unshare_flags & CLONE_FILES) && (fd && atomic_read(&fd->count) > 1)) { *new_fdp = dup_fd(fd, max_fds, &error); if (!*new_fdp) return error; } return 0; } /* * unshare allows a process to 'unshare' part of the process * context which was originally shared using clone. copy_* * functions used by kernel_clone() cannot be used here directly * because they modify an inactive task_struct that is being * constructed. Here we are modifying the current, active, * task_struct. */ int ksys_unshare(unsigned long unshare_flags) { struct fs_struct *fs, *new_fs = NULL; struct files_struct *new_fd = NULL; struct cred *new_cred = NULL; struct nsproxy *new_nsproxy = NULL; int do_sysvsem = 0; int err; /* * If unsharing a user namespace must also unshare the thread group * and unshare the filesystem root and working directories. */ if (unshare_flags & CLONE_NEWUSER) unshare_flags |= CLONE_THREAD | CLONE_FS; /* * If unsharing vm, must also unshare signal handlers. */ if (unshare_flags & CLONE_VM) unshare_flags |= CLONE_SIGHAND; /* * If unsharing a signal handlers, must also unshare the signal queues. */ if (unshare_flags & CLONE_SIGHAND) unshare_flags |= CLONE_THREAD; /* * If unsharing namespace, must also unshare filesystem information. */ if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; err = check_unshare_flags(unshare_flags); if (err) goto bad_unshare_out; /* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; err = unshare_fs(unshare_flags, &new_fs); if (err) goto bad_unshare_out; err = unshare_fd(unshare_flags, NR_OPEN_MAX, &new_fd); if (err) goto bad_unshare_cleanup_fs; err = unshare_userns(unshare_flags, &new_cred); if (err) goto bad_unshare_cleanup_fd; err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_cred, new_fs); if (err) goto bad_unshare_cleanup_cred; if (new_cred) { err = set_cred_ucounts(new_cred); if (err) goto bad_unshare_cleanup_cred; } if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* * CLONE_SYSVSEM is equivalent to sys_exit(). */ exit_sem(current); } if (unshare_flags & CLONE_NEWIPC) { /* Orphan segments in old ns (see sem above). */ exit_shm(current); shm_init_task(current); } if (new_nsproxy) switch_task_namespaces(current, new_nsproxy); task_lock(current); if (new_fs) { fs = current->fs; spin_lock(&fs->lock); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; spin_unlock(&fs->lock); } if (new_fd) swap(current->files, new_fd); task_unlock(current); if (new_cred) { /* Install the new user namespace */ commit_creds(new_cred); new_cred = NULL; } } perf_event_namespaces(current); bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); bad_unshare_cleanup_fs: if (new_fs) free_fs_struct(new_fs); bad_unshare_out: return err; } SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) { return ksys_unshare(unshare_flags); } /* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to * the exec layer of the kernel. */ int unshare_files(void) { struct task_struct *task = current; struct files_struct *old, *copy = NULL; int error; error = unshare_fd(CLONE_FILES, NR_OPEN_MAX, ©); if (error || !copy) return error; old = task->files; task_lock(task); task->files = copy; task_unlock(task); put_files_struct(old); return 0; } int sysctl_max_threads(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int ret; int threads = max_threads; int min = 1; int max = MAX_THREADS; t = *table; t.data = &threads; t.extra1 = &min; t.extra2 = &max; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || !write) return ret; max_threads = threads; return 0; } |
| 38 13 14 12 38 1 2 12 12 12 5 10 7 3 6 1 1 3 5 9 3 9 6 1 1 3 3 3 1 1 3 8 2 1 3 33 21 4 184 185 185 184 184 184 184 185 185 185 184 49 49 19 17 24 3 14 14 13 14 14 14 56 3 1 1 1 13 43 13 5 3 3 2 1 2 5 5 1 1 1 42 41 42 43 185 10 185 64 228 64 48 31 47 7 64 178 37 76 1 5 55 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/export.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/if_vlan.h> #include <linux/filter.h> #include <net/dsa.h> #include <net/dst_metadata.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/gre.h> #include <net/pptp.h> #include <net/tipc.h> #include <linux/igmp.h> #include <linux/icmp.h> #include <linux/sctp.h> #include <linux/dccp.h> #include <linux/if_tunnel.h> #include <linux/if_pppox.h> #include <linux/ppp_defs.h> #include <linux/stddef.h> #include <linux/if_ether.h> #include <linux/if_hsr.h> #include <linux/mpls.h> #include <linux/tcp.h> #include <linux/ptp_classify.h> #include <net/flow_dissector.h> #include <scsi/fc/fc_fcoe.h> #include <uapi/linux/batadv_packet.h> #include <linux/bpf.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_labels.h> #endif #include <linux/bpf-netns.h> static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { flow_dissector->used_keys |= (1 << key_id); } void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count) { unsigned int i; memset(flow_dissector, 0, sizeof(*flow_dissector)); for (i = 0; i < key_count; i++, key++) { /* User should make sure that every key target offset is within * boundaries of unsigned short. */ BUG_ON(key->offset > USHRT_MAX); BUG_ON(dissector_uses_key(flow_dissector, key->key_id)); dissector_set_key(flow_dissector, key->key_id); flow_dissector->offset[key->key_id] = key->offset; } /* Ensure that the dissector always includes control and basic key. * That way we are able to avoid handling lack of these in fast path. */ BUG_ON(!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL)); BUG_ON(!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_BASIC)); } EXPORT_SYMBOL(skb_flow_dissector_init); #ifdef CONFIG_BPF_SYSCALL int flow_dissector_bpf_prog_attach_check(struct net *net, struct bpf_prog *prog) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; if (net == &init_net) { /* BPF flow dissector in the root namespace overrides * any per-net-namespace one. When attaching to root, * make sure we don't have any BPF program attached * to the non-root namespaces. */ struct net *ns; for_each_net(ns) { if (ns == &init_net) continue; if (rcu_access_pointer(ns->bpf.run_array[type])) return -EEXIST; } } else { /* Make sure root flow dissector is not attached * when attaching to the non-root namespace. */ if (rcu_access_pointer(init_net.bpf.run_array[type])) return -EEXIST; } return 0; } #endif /* CONFIG_BPF_SYSCALL */ /** * __skb_flow_get_ports - extract the upper layer ports and return them * @skb: sk_buff to extract the ports from * @thoff: transport header offset * @ip_proto: protocol for which to get port offset * @data: raw buffer pointer to the packet, if NULL use skb->data * @hlen: packet header length, if @data is NULL use skb_headlen(skb) * * The function will try to retrieve the ports at offset thoff + poff where poff * is the protocol port offset returned from proto_ports_offset */ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, const void *data, int hlen) { int poff = proto_ports_offset(ip_proto); if (!data) { data = skb->data; hlen = skb_headlen(skb); } if (poff >= 0) { __be32 *ports, _ports; ports = __skb_header_pointer(skb, thoff + poff, sizeof(_ports), data, hlen, &_ports); if (ports) return *ports; } return 0; } EXPORT_SYMBOL(__skb_flow_get_ports); static bool icmp_has_id(u8 type) { switch (type) { case ICMP_ECHO: case ICMP_ECHOREPLY: case ICMP_TIMESTAMP: case ICMP_TIMESTAMPREPLY: case ICMPV6_ECHO_REQUEST: case ICMPV6_ECHO_REPLY: return true; } return false; } /** * skb_flow_get_icmp_tci - extract ICMP(6) Type, Code and Identifier fields * @skb: sk_buff to extract from * @key_icmp: struct flow_dissector_key_icmp to fill * @data: raw buffer pointer to the packet * @thoff: offset to extract at * @hlen: packet header length */ void skb_flow_get_icmp_tci(const struct sk_buff *skb, struct flow_dissector_key_icmp *key_icmp, const void *data, int thoff, int hlen) { struct icmphdr *ih, _ih; ih = __skb_header_pointer(skb, thoff, sizeof(_ih), data, hlen, &_ih); if (!ih) return; key_icmp->type = ih->type; key_icmp->code = ih->code; /* As we use 0 to signal that the Id field is not present, * avoid confusion with packets without such field */ if (icmp_has_id(ih->type)) key_icmp->id = ih->un.echo.id ? ntohs(ih->un.echo.id) : 1; else key_icmp->id = 0; } EXPORT_SYMBOL(skb_flow_get_icmp_tci); /* If FLOW_DISSECTOR_KEY_ICMP is set, dissect an ICMP packet * using skb_flow_get_icmp_tci(). */ static void __skb_flow_dissect_icmp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int thoff, int hlen) { struct flow_dissector_key_icmp *key_icmp; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ICMP)) return; key_icmp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ICMP, target_container); skb_flow_get_icmp_tci(skb, key_icmp, data, thoff, hlen); } static void __skb_flow_dissect_l2tpv3(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_l2tpv3 *key_l2tpv3; struct { __be32 session_id; } *hdr, _hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_L2TPV3)) return; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return; key_l2tpv3 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_L2TPV3, target_container); key_l2tpv3->session_id = hdr->session_id; } void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_meta *meta; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_META)) return; meta = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_META, target_container); meta->ingress_ifindex = skb->skb_iif; } EXPORT_SYMBOL(skb_flow_dissect_meta); static void skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_control *ctrl; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) return; ctrl = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL, target_container); ctrl->addr_type = type; } void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, bool post_ct, u16 zone) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct flow_dissector_key_ct *key; enum ip_conntrack_info ctinfo; struct nf_conn_labels *cl; struct nf_conn *ct; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CT)) return; ct = nf_ct_get(skb, &ctinfo); if (!ct && !post_ct) return; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CT, target_container); if (!ct) { key->ct_state = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_INVALID; key->ct_zone = zone; return; } if (ctinfo < mapsize) key->ct_state = ctinfo_map[ctinfo]; #if IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) key->ct_zone = ct->zone.id; #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) key->ct_mark = READ_ONCE(ct->mark); #endif cl = nf_ct_labels_find(ct); if (cl) memcpy(key->ct_labels, cl->bits, sizeof(key->ct_labels)); #endif /* CONFIG_NF_CONNTRACK */ } EXPORT_SYMBOL(skb_flow_dissect_ct); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct ip_tunnel_info *info; struct ip_tunnel_key *key; /* A quick check to see if there might be something to do. */ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) return; info = skb_tunnel_info(skb); if (!info) return; key = &info->key; switch (ip_tunnel_info_af(info)) { case AF_INET: skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV4_ADDRS, flow_dissector, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { struct flow_dissector_key_ipv4_addrs *ipv4; ipv4 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, target_container); ipv4->src = key->u.ipv4.src; ipv4->dst = key->u.ipv4.dst; } break; case AF_INET6: skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV6_ADDRS, flow_dissector, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { struct flow_dissector_key_ipv6_addrs *ipv6; ipv6 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, target_container); ipv6->src = key->u.ipv6.src; ipv6->dst = key->u.ipv6.dst; } break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { struct flow_dissector_key_keyid *keyid; keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID, target_container); keyid->keyid = tunnel_id_to_key32(key->tun_id); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) { struct flow_dissector_key_ports *tp; tp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS, target_container); tp->src = key->tp_src; tp->dst = key->tp_dst; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP)) { struct flow_dissector_key_ip *ip; ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP, target_container); ip->tos = key->tos; ip->ttl = key->ttl; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) { struct flow_dissector_key_enc_opts *enc_opt; enc_opt = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS, target_container); if (info->options_len) { enc_opt->len = info->options_len; ip_tunnel_info_opts_get(enc_opt->data, info); enc_opt->dst_opt_type = info->key.tun_flags & TUNNEL_OPTIONS_PRESENT; } } } EXPORT_SYMBOL(skb_flow_dissect_tunnel_info); void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_hash *key; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_HASH)) return; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_HASH, target_container); key->hash = skb_get_hash_raw(skb); } EXPORT_SYMBOL(skb_flow_dissect_hash); static enum flow_dissect_ret __skb_flow_dissect_mpls(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen, int lse_index, bool *entropy_label) { struct mpls_label *hdr, _hdr; u32 entry, label, bos; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) return FLOW_DISSECT_RET_OUT_GOOD; if (lse_index >= FLOW_DIS_MPLS_MAX) return FLOW_DISSECT_RET_OUT_GOOD; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; entry = ntohl(hdr->entry); label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT; bos = (entry & MPLS_LS_S_MASK) >> MPLS_LS_S_SHIFT; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) { struct flow_dissector_key_mpls *key_mpls; struct flow_dissector_mpls_lse *lse; key_mpls = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_MPLS, target_container); lse = &key_mpls->ls[lse_index]; lse->mpls_ttl = (entry & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; lse->mpls_bos = bos; lse->mpls_tc = (entry & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT; lse->mpls_label = label; dissector_set_mpls_lse(key_mpls, lse_index); } if (*entropy_label && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) { struct flow_dissector_key_keyid *key_keyid; key_keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY, target_container); key_keyid->keyid = cpu_to_be32(label); } *entropy_label = label == MPLS_LABEL_ENTROPY; return bos ? FLOW_DISSECT_RET_OUT_GOOD : FLOW_DISSECT_RET_PROTO_AGAIN; } static enum flow_dissect_ret __skb_flow_dissect_arp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_arp *key_arp; struct { unsigned char ar_sha[ETH_ALEN]; unsigned char ar_sip[4]; unsigned char ar_tha[ETH_ALEN]; unsigned char ar_tip[4]; } *arp_eth, _arp_eth; const struct arphdr *arp; struct arphdr _arp; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ARP)) return FLOW_DISSECT_RET_OUT_GOOD; arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data, hlen, &_arp); if (!arp) return FLOW_DISSECT_RET_OUT_BAD; if (arp->ar_hrd != htons(ARPHRD_ETHER) || arp->ar_pro != htons(ETH_P_IP) || arp->ar_hln != ETH_ALEN || arp->ar_pln != 4 || (arp->ar_op != htons(ARPOP_REPLY) && arp->ar_op != htons(ARPOP_REQUEST))) return FLOW_DISSECT_RET_OUT_BAD; arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp), sizeof(_arp_eth), data, hlen, &_arp_eth); if (!arp_eth) return FLOW_DISSECT_RET_OUT_BAD; key_arp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ARP, target_container); memcpy(&key_arp->sip, arp_eth->ar_sip, sizeof(key_arp->sip)); memcpy(&key_arp->tip, arp_eth->ar_tip, sizeof(key_arp->tip)); /* Only store the lower byte of the opcode; * this covers ARPOP_REPLY and ARPOP_REQUEST. */ key_arp->op = ntohs(arp->ar_op) & 0xff; ether_addr_copy(key_arp->sha, arp_eth->ar_sha); ether_addr_copy(key_arp->tha, arp_eth->ar_tha); return FLOW_DISSECT_RET_OUT_GOOD; } static enum flow_dissect_ret __skb_flow_dissect_gre(const struct sk_buff *skb, struct flow_dissector_key_control *key_control, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 *p_proto, int *p_nhoff, int *p_hlen, unsigned int flags) { struct flow_dissector_key_keyid *key_keyid; struct gre_base_hdr *hdr, _hdr; int offset = 0; u16 gre_ver; hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), data, *p_hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; /* Only look inside GRE without routing */ if (hdr->flags & GRE_ROUTING) return FLOW_DISSECT_RET_OUT_GOOD; /* Only look inside GRE for version 0 and 1 */ gre_ver = ntohs(hdr->flags & GRE_VERSION); if (gre_ver > 1) return FLOW_DISSECT_RET_OUT_GOOD; *p_proto = hdr->protocol; if (gre_ver) { /* Version1 must be PPTP, and check the flags */ if (!(*p_proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY))) return FLOW_DISSECT_RET_OUT_GOOD; } offset += sizeof(struct gre_base_hdr); if (hdr->flags & GRE_CSUM) offset += sizeof_field(struct gre_full_hdr, csum) + sizeof_field(struct gre_full_hdr, reserved1); if (hdr->flags & GRE_KEY) { const __be32 *keyid; __be32 _keyid; keyid = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_keyid), data, *p_hlen, &_keyid); if (!keyid) return FLOW_DISSECT_RET_OUT_BAD; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_GRE_KEYID)) { key_keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_GRE_KEYID, target_container); if (gre_ver == 0) key_keyid->keyid = *keyid; else key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; } offset += sizeof_field(struct gre_full_hdr, key); } if (hdr->flags & GRE_SEQ) offset += sizeof_field(struct pptp_gre_header, seq); if (gre_ver == 0) { if (*p_proto == htons(ETH_P_TEB)) { const struct ethhdr *eth; struct ethhdr _eth; eth = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_eth), data, *p_hlen, &_eth); if (!eth) return FLOW_DISSECT_RET_OUT_BAD; *p_proto = eth->h_proto; offset += sizeof(*eth); /* Cap headers that we access via pointers at the * end of the Ethernet header as our maximum alignment * at that point is only 2 bytes. */ if (NET_IP_ALIGN) *p_hlen = *p_nhoff + offset; } } else { /* version 1, must be PPTP */ u8 _ppp_hdr[PPP_HDRLEN]; u8 *ppp_hdr; if (hdr->flags & GRE_ACK) offset += sizeof_field(struct pptp_gre_header, ack); ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_ppp_hdr), data, *p_hlen, _ppp_hdr); if (!ppp_hdr) return FLOW_DISSECT_RET_OUT_BAD; switch (PPP_PROTOCOL(ppp_hdr)) { case PPP_IP: *p_proto = htons(ETH_P_IP); break; case PPP_IPV6: *p_proto = htons(ETH_P_IPV6); break; default: /* Could probably catch some more like MPLS */ break; } offset += PPP_HDRLEN; } *p_nhoff += offset; key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) return FLOW_DISSECT_RET_OUT_GOOD; return FLOW_DISSECT_RET_PROTO_AGAIN; } /** * __skb_flow_dissect_batadv() - dissect batman-adv header * @skb: sk_buff to with the batman-adv header * @key_control: flow dissectors control key * @data: raw buffer pointer to the packet, if NULL use skb->data * @p_proto: pointer used to update the protocol to process next * @p_nhoff: pointer used to update inner network header offset * @hlen: packet header length * @flags: any combination of FLOW_DISSECTOR_F_* * * ETH_P_BATMAN packets are tried to be dissected. Only * &struct batadv_unicast packets are actually processed because they contain an * inner ethernet header and are usually followed by actual network header. This * allows the flow dissector to continue processing the packet. * * Return: FLOW_DISSECT_RET_PROTO_AGAIN when &struct batadv_unicast was found, * FLOW_DISSECT_RET_OUT_GOOD when dissector should stop after encapsulation, * otherwise FLOW_DISSECT_RET_OUT_BAD */ static enum flow_dissect_ret __skb_flow_dissect_batadv(const struct sk_buff *skb, struct flow_dissector_key_control *key_control, const void *data, __be16 *p_proto, int *p_nhoff, int hlen, unsigned int flags) { struct { struct batadv_unicast_packet batadv_unicast; struct ethhdr eth; } *hdr, _hdr; hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; if (hdr->batadv_unicast.version != BATADV_COMPAT_VERSION) return FLOW_DISSECT_RET_OUT_BAD; if (hdr->batadv_unicast.packet_type != BATADV_UNICAST) return FLOW_DISSECT_RET_OUT_BAD; *p_proto = hdr->eth.h_proto; *p_nhoff += sizeof(*hdr); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) return FLOW_DISSECT_RET_OUT_GOOD; return FLOW_DISSECT_RET_PROTO_AGAIN; } static void __skb_flow_dissect_tcp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int thoff, int hlen) { struct flow_dissector_key_tcp *key_tcp; struct tcphdr *th, _th; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TCP)) return; th = __skb_header_pointer(skb, thoff, sizeof(_th), data, hlen, &_th); if (!th) return; if (unlikely(__tcp_hdrlen(th) < sizeof(_th))) return; key_tcp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_TCP, target_container); key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF)); } static void __skb_flow_dissect_ports(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, u8 ip_proto, int hlen) { enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX; struct flow_dissector_key_ports *key_ports; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) dissector_ports = FLOW_DISSECTOR_KEY_PORTS; else if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) dissector_ports = FLOW_DISSECTOR_KEY_PORTS_RANGE; if (dissector_ports == FLOW_DISSECTOR_KEY_MAX) return; key_ports = skb_flow_dissector_target(flow_dissector, dissector_ports, target_container); key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen); } static void __skb_flow_dissect_ipv4(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, const struct iphdr *iph) { struct flow_dissector_key_ip *key_ip; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) return; key_ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IP, target_container); key_ip->tos = iph->tos; key_ip->ttl = iph->ttl; } static void __skb_flow_dissect_ipv6(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, const struct ipv6hdr *iph) { struct flow_dissector_key_ip *key_ip; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) return; key_ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IP, target_container); key_ip->tos = ipv6_get_dsfield(iph); key_ip->ttl = iph->hop_limit; } /* Maximum number of protocol headers that can be parsed in * __skb_flow_dissect */ #define MAX_FLOW_DISSECT_HDRS 15 static bool skb_flow_dissect_allowed(int *num_hdrs) { ++*num_hdrs; return (*num_hdrs <= MAX_FLOW_DISSECT_HDRS); } static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_ports *key_ports = NULL; struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_tags *key_tags; key_control = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL, target_container); key_control->thoff = flow_keys->thoff; if (flow_keys->is_frag) key_control->flags |= FLOW_DIS_IS_FRAGMENT; if (flow_keys->is_first_frag) key_control->flags |= FLOW_DIS_FIRST_FRAG; if (flow_keys->is_encap) key_control->flags |= FLOW_DIS_ENCAPSULATION; key_basic = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_BASIC, target_container); key_basic->n_proto = flow_keys->n_proto; key_basic->ip_proto = flow_keys->ip_proto; if (flow_keys->addr_proto == ETH_P_IP && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); key_addrs->v4addrs.src = flow_keys->ipv4_src; key_addrs->v4addrs.dst = flow_keys->ipv4_dst; key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } else if (flow_keys->addr_proto == ETH_P_IPV6 && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS, target_container); memcpy(&key_addrs->v6addrs.src, &flow_keys->ipv6_src, sizeof(key_addrs->v6addrs.src)); memcpy(&key_addrs->v6addrs.dst, &flow_keys->ipv6_dst, sizeof(key_addrs->v6addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); else if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE, target_container); if (key_ports) { key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL, target_container); key_tags->flow_label = ntohl(flow_keys->flow_label); } } u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags) { struct bpf_flow_keys *flow_keys = ctx->flow_keys; u32 result; /* Pass parameters to the BPF program */ memset(flow_keys, 0, sizeof(*flow_keys)); flow_keys->n_proto = proto; flow_keys->nhoff = nhoff; flow_keys->thoff = flow_keys->nhoff; BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG != (int)FLOW_DISSECTOR_F_PARSE_1ST_FRAG); BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL != (int)FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP != (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP); flow_keys->flags = flags; result = bpf_prog_run_pin_on_cpu(prog, ctx); flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen); flow_keys->thoff = clamp_t(u16, flow_keys->thoff, flow_keys->nhoff, hlen); return result; } static bool is_pppoe_ses_hdr_valid(const struct pppoe_hdr *hdr) { return hdr->ver == 1 && hdr->type == 1 && hdr->code == 0; } /** * __skb_flow_dissect - extract the flow_keys struct and return it * @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified * @flow_dissector: list of keys to dissect * @target_container: target structure to put dissected values into * @data: raw buffer pointer to the packet, if NULL use skb->data * @proto: protocol for which to get the flow, if @data is NULL use skb->protocol * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb) * @hlen: packet header length, if @data is NULL use skb_headlen(skb) * @flags: flags that control the dissection process, e.g. * FLOW_DISSECTOR_F_STOP_AT_ENCAP. * * The function will try to retrieve individual keys into target specified * by flow_dissector from either the skbuff or a raw buffer specified by the * rest parameters. * * Caller must take care of zeroing target container memory. */ bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; bool mpls_el = false; int mpls_lse = 0; int num_hdrs = 0; u8 ip_proto = 0; bool ret; if (!data) { data = skb->data; proto = skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol; nhoff = skb_network_offset(skb); hlen = skb_headlen(skb); #if IS_ENABLED(CONFIG_NET_DSA) if (unlikely(skb->dev && netdev_uses_dsa(skb->dev) && proto == htons(ETH_P_XDSA))) { const struct dsa_device_ops *ops; int offset = 0; ops = skb->dev->dsa_ptr->tag_ops; /* Only DSA header taggers break flow dissection */ if (ops->needed_headroom) { if (ops->flow_dissect) ops->flow_dissect(skb, &proto, &offset); else dsa_tag_generic_flow_dissect(skb, &proto, &offset); hlen -= offset; nhoff += offset; } } #endif } /* It is ensured by skb_flow_dissector_init() that control key will * be always present. */ key_control = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL, target_container); /* It is ensured by skb_flow_dissector_init() that basic key will * be always present. */ key_basic = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_BASIC, target_container); if (skb) { if (!net) { if (skb->dev) net = dev_net(skb->dev); else if (skb->sk) net = sock_net(skb->sk); } } WARN_ON_ONCE(!net); if (net) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog_array *run_array; rcu_read_lock(); run_array = rcu_dereference(init_net.bpf.run_array[type]); if (!run_array) run_array = rcu_dereference(net->bpf.run_array[type]); if (run_array) { struct bpf_flow_keys flow_keys; struct bpf_flow_dissector ctx = { .flow_keys = &flow_keys, .data = data, .data_end = data + hlen, }; __be16 n_proto = proto; struct bpf_prog *prog; u32 result; if (skb) { ctx.skb = skb; /* we can't use 'proto' in the skb case * because it might be set to skb->vlan_proto * which has been pulled from the data */ n_proto = skb->protocol; } prog = READ_ONCE(run_array->items[0].prog); result = bpf_flow_dissect(prog, &ctx, n_proto, nhoff, hlen, flags); if (result == BPF_FLOW_DISSECTOR_CONTINUE) goto dissect_continue; __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); return result == BPF_OK; } dissect_continue: rcu_read_unlock(); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct ethhdr *eth = eth_hdr(skb); struct flow_dissector_key_eth_addrs *key_eth_addrs; key_eth_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS, target_container); memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs)); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS)) { struct flow_dissector_key_num_of_vlans *key_num_of_vlans; key_num_of_vlans = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS, target_container); key_num_of_vlans->num_of_vlans = 0; } proto_again: fdret = FLOW_DISSECT_RET_CONTINUE; switch (proto) { case htons(ETH_P_IP): { const struct iphdr *iph; struct iphdr _iph; iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); if (!iph || iph->ihl < 5) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += iph->ihl * 4; ip_proto = iph->protocol; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); memcpy(&key_addrs->v4addrs.src, &iph->saddr, sizeof(key_addrs->v4addrs.src)); memcpy(&key_addrs->v4addrs.dst, &iph->daddr, sizeof(key_addrs->v4addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } __skb_flow_dissect_ipv4(skb, flow_dissector, target_container, data, iph); if (ip_is_fragment(iph)) { key_control->flags |= FLOW_DIS_IS_FRAGMENT; if (iph->frag_off & htons(IP_OFFSET)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } else { key_control->flags |= FLOW_DIS_FIRST_FRAG; if (!(flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } } } break; } case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); if (!iph) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } ip_proto = iph->nexthdr; nhoff += sizeof(struct ipv6hdr); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS, target_container); memcpy(&key_addrs->v6addrs.src, &iph->saddr, sizeof(key_addrs->v6addrs.src)); memcpy(&key_addrs->v6addrs.dst, &iph->daddr, sizeof(key_addrs->v6addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } if ((dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL) || (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)) && ip6_flowlabel(iph)) { __be32 flow_label = ip6_flowlabel(iph); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL, target_container); key_tags->flow_label = ntohl(flow_label); } if (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } } __skb_flow_dissect_ipv6(skb, flow_dissector, target_container, data, iph); break; } case htons(ETH_P_8021AD): case htons(ETH_P_8021Q): { const struct vlan_hdr *vlan = NULL; struct vlan_hdr _vlan; __be16 saved_vlan_tpid = proto; if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX && skb && skb_vlan_tag_present(skb)) { proto = skb->protocol; } else { vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan); if (!vlan) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } proto = vlan->h_vlan_encapsulated_proto; nhoff += sizeof(*vlan); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS) && !(key_control->flags & FLOW_DIS_ENCAPSULATION)) { struct flow_dissector_key_num_of_vlans *key_nvs; key_nvs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS, target_container); key_nvs->num_of_vlans++; } if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX) { dissector_vlan = FLOW_DISSECTOR_KEY_VLAN; } else if (dissector_vlan == FLOW_DISSECTOR_KEY_VLAN) { dissector_vlan = FLOW_DISSECTOR_KEY_CVLAN; } else { fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } if (dissector_uses_key(flow_dissector, dissector_vlan)) { key_vlan = skb_flow_dissector_target(flow_dissector, dissector_vlan, target_container); if (!vlan) { key_vlan->vlan_id = skb_vlan_tag_get_id(skb); key_vlan->vlan_priority = skb_vlan_tag_get_prio(skb); } else { key_vlan->vlan_id = ntohs(vlan->h_vlan_TCI) & VLAN_VID_MASK; key_vlan->vlan_priority = (ntohs(vlan->h_vlan_TCI) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } key_vlan->vlan_tpid = saved_vlan_tpid; key_vlan->vlan_eth_type = proto; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } case htons(ETH_P_PPP_SES): { struct { struct pppoe_hdr hdr; __be16 proto; } *hdr, _hdr; u16 ppp_proto; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (!is_pppoe_ses_hdr_valid(&hdr->hdr)) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } /* least significant bit of the most significant octet * indicates if protocol field was compressed */ ppp_proto = ntohs(hdr->proto); if (ppp_proto & 0x0100) { ppp_proto = ppp_proto >> 8; nhoff += PPPOE_SES_HLEN - 1; } else { nhoff += PPPOE_SES_HLEN; } if (ppp_proto == PPP_IP) { proto = htons(ETH_P_IP); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_IPV6) { proto = htons(ETH_P_IPV6); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_MPLS_UC) { proto = htons(ETH_P_MPLS_UC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_MPLS_MC) { proto = htons(ETH_P_MPLS_MC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto_is_valid(ppp_proto)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; } else { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PPPOE)) { struct flow_dissector_key_pppoe *key_pppoe; key_pppoe = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PPPOE, target_container); key_pppoe->session_id = hdr->hdr.sid; key_pppoe->ppp_proto = htons(ppp_proto); key_pppoe->type = htons(ETH_P_PPP_SES); } break; } case htons(ETH_P_TIPC): { struct tipc_basic_hdr *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TIPC)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_TIPC, target_container); key_addrs->tipckey.key = tipc_hdr_rps_key(hdr); key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC; } fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case htons(ETH_P_MPLS_UC): case htons(ETH_P_MPLS_MC): fdret = __skb_flow_dissect_mpls(skb, flow_dissector, target_container, data, nhoff, hlen, mpls_lse, &mpls_el); nhoff += sizeof(struct mpls_label); mpls_lse++; break; case htons(ETH_P_FCOE): if ((hlen - nhoff) < FCOE_HEADER_LEN) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += FCOE_HEADER_LEN; fdret = FLOW_DISSECT_RET_OUT_GOOD; break; case htons(ETH_P_ARP): case htons(ETH_P_RARP): fdret = __skb_flow_dissect_arp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case htons(ETH_P_BATMAN): fdret = __skb_flow_dissect_batadv(skb, key_control, data, &proto, &nhoff, hlen, flags); break; case htons(ETH_P_1588): { struct ptp_header *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += ntohs(hdr->message_length); fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case htons(ETH_P_PRP): case htons(ETH_P_HSR): { struct hsr_tag *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } proto = hdr->encap_proto; nhoff += HSR_HLEN; fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } default: fdret = FLOW_DISSECT_RET_OUT_BAD; break; } /* Process result of proto processing */ switch (fdret) { case FLOW_DISSECT_RET_OUT_GOOD: goto out_good; case FLOW_DISSECT_RET_PROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto proto_again; goto out_good; case FLOW_DISSECT_RET_CONTINUE: case FLOW_DISSECT_RET_IPPROTO_AGAIN: break; case FLOW_DISSECT_RET_OUT_BAD: default: goto out_bad; } ip_proto_again: fdret = FLOW_DISSECT_RET_CONTINUE; switch (ip_proto) { case IPPROTO_GRE: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = __skb_flow_dissect_gre(skb, key_control, flow_dissector, target_container, data, &proto, &nhoff, &hlen, flags); break; case NEXTHDR_HOP: case NEXTHDR_ROUTING: case NEXTHDR_DEST: { u8 _opthdr[2], *opthdr; if (proto != htons(ETH_P_IPV6)) break; opthdr = __skb_header_pointer(skb, nhoff, sizeof(_opthdr), data, hlen, &_opthdr); if (!opthdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } ip_proto = opthdr[0]; nhoff += (opthdr[1] + 1) << 3; fdret = FLOW_DISSECT_RET_IPPROTO_AGAIN; break; } case NEXTHDR_FRAGMENT: { struct frag_hdr _fh, *fh; if (proto != htons(ETH_P_IPV6)) break; fh = __skb_header_pointer(skb, nhoff, sizeof(_fh), data, hlen, &_fh); if (!fh) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } key_control->flags |= FLOW_DIS_IS_FRAGMENT; nhoff += sizeof(_fh); ip_proto = fh->nexthdr; if (!(fh->frag_off & htons(IP6_OFFSET))) { key_control->flags |= FLOW_DIS_FIRST_FRAG; if (flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG) { fdret = FLOW_DISSECT_RET_IPPROTO_AGAIN; break; } } fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case IPPROTO_IPIP: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } proto = htons(ETH_P_IP); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_IPV6: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } proto = htons(ETH_P_IPV6); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_MPLS: proto = htons(ETH_P_MPLS_UC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_TCP: __skb_flow_dissect_tcp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_ICMP: case IPPROTO_ICMPV6: __skb_flow_dissect_icmp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_L2TP: __skb_flow_dissect_l2tpv3(skb, flow_dissector, target_container, data, nhoff, hlen); break; default: break; } if (!(key_control->flags & FLOW_DIS_IS_FRAGMENT)) __skb_flow_dissect_ports(skb, flow_dissector, target_container, data, nhoff, ip_proto, hlen); /* Process result of IP proto processing */ switch (fdret) { case FLOW_DISSECT_RET_PROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto proto_again; break; case FLOW_DISSECT_RET_IPPROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto ip_proto_again; break; case FLOW_DISSECT_RET_OUT_GOOD: case FLOW_DISSECT_RET_CONTINUE: break; case FLOW_DISSECT_RET_OUT_BAD: default: goto out_bad; } out_good: ret = true; out: key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen); key_basic->n_proto = proto; key_basic->ip_proto = ip_proto; return ret; out_bad: ret = false; goto out; } EXPORT_SYMBOL(__skb_flow_dissect); static siphash_aligned_key_t hashrnd; static __always_inline void __flow_hash_secret_init(void) { net_get_random_once(&hashrnd, sizeof(hashrnd)); } static const void *flow_keys_hash_start(const struct flow_keys *flow) { BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % SIPHASH_ALIGNMENT); return &flow->FLOW_KEYS_HASH_START_FIELD; } static inline size_t flow_keys_hash_length(const struct flow_keys *flow) { size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs); BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32)); switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: diff -= sizeof(flow->addrs.v4addrs); break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: diff -= sizeof(flow->addrs.v6addrs); break; case FLOW_DISSECTOR_KEY_TIPC: diff -= sizeof(flow->addrs.tipckey); break; } return sizeof(*flow) - diff; } __be32 flow_get_u32_src(const struct flow_keys *flow) { switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: return flow->addrs.v4addrs.src; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: return (__force __be32)ipv6_addr_hash( &flow->addrs.v6addrs.src); case FLOW_DISSECTOR_KEY_TIPC: return flow->addrs.tipckey.key; default: return 0; } } EXPORT_SYMBOL(flow_get_u32_src); __be32 flow_get_u32_dst(const struct flow_keys *flow) { switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: return flow->addrs.v4addrs.dst; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: return (__force __be32)ipv6_addr_hash( &flow->addrs.v6addrs.dst); default: return 0; } } EXPORT_SYMBOL(flow_get_u32_dst); /* Sort the source and destination IP and the ports, * to have consistent hash within the two directions */ static inline void __flow_hash_consistentify(struct flow_keys *keys) { int addr_diff, i; switch (keys->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: if ((__force u32)keys->addrs.v4addrs.dst < (__force u32)keys->addrs.v4addrs.src) swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst); if ((__force u16)keys->ports.dst < (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: addr_diff = memcmp(&keys->addrs.v6addrs.dst, &keys->addrs.v6addrs.src, sizeof(keys->addrs.v6addrs.dst)); if (addr_diff < 0) { for (i = 0; i < 4; i++) swap(keys->addrs.v6addrs.src.s6_addr32[i], keys->addrs.v6addrs.dst.s6_addr32[i]); } if ((__force u16)keys->ports.dst < (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; } } static inline u32 __flow_hash_from_keys(struct flow_keys *keys, const siphash_key_t *keyval) { u32 hash; __flow_hash_consistentify(keys); hash = siphash(flow_keys_hash_start(keys), flow_keys_hash_length(keys), keyval); if (!hash) hash = 1; return hash; } u32 flow_hash_from_keys(struct flow_keys *keys) { __flow_hash_secret_init(); return __flow_hash_from_keys(keys, &hashrnd); } EXPORT_SYMBOL(flow_hash_from_keys); static inline u32 ___skb_get_hash(const struct sk_buff *skb, struct flow_keys *keys, const siphash_key_t *keyval) { skb_flow_dissect_flow_keys(skb, keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); return __flow_hash_from_keys(keys, keyval); } struct _flow_keys_digest_data { __be16 n_proto; u8 ip_proto; u8 padding; __be32 ports; __be32 src; __be32 dst; }; void make_flow_keys_digest(struct flow_keys_digest *digest, const struct flow_keys *flow) { struct _flow_keys_digest_data *data = (struct _flow_keys_digest_data *)digest; BUILD_BUG_ON(sizeof(*data) > sizeof(*digest)); memset(digest, 0, sizeof(*digest)); data->n_proto = flow->basic.n_proto; data->ip_proto = flow->basic.ip_proto; data->ports = flow->ports.ports; data->src = flow->addrs.v4addrs.src; data->dst = flow->addrs.v4addrs.dst; } EXPORT_SYMBOL(make_flow_keys_digest); static struct flow_dissector flow_keys_dissector_symmetric __read_mostly; u32 __skb_get_hash_symmetric(const struct sk_buff *skb) { struct flow_keys keys; __flow_hash_secret_init(); memset(&keys, 0, sizeof(keys)); __skb_flow_dissect(NULL, skb, &flow_keys_dissector_symmetric, &keys, NULL, 0, 0, 0, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); return __flow_hash_from_keys(&keys, &hashrnd); } EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); /** * __skb_get_hash: calculate a flow hash * @skb: sk_buff to calculate flow hash from * * This function calculates a flow hash based on src/dst addresses * and src/dst port numbers. Sets hash in skb to non-zero hash value * on success, zero indicates no valid hash. Also, sets l4_hash in skb * if hash is a canonical 4-tuple hash over transport ports. */ void __skb_get_hash(struct sk_buff *skb) { struct flow_keys keys; u32 hash; __flow_hash_secret_init(); hash = ___skb_get_hash(skb, &keys, &hashrnd); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } EXPORT_SYMBOL(__skb_get_hash); __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb) { struct flow_keys keys; return ___skb_get_hash(skb, &keys, perturb); } EXPORT_SYMBOL(skb_get_hash_perturb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen) { u32 poff = keys->control.thoff; /* skip L4 headers for fragments after the first */ if ((keys->control.flags & FLOW_DIS_IS_FRAGMENT) && !(keys->control.flags & FLOW_DIS_FIRST_FRAG)) return poff; switch (keys->basic.ip_proto) { case IPPROTO_TCP: { /* access doff as u8 to avoid unaligned access */ const u8 *doff; u8 _doff; doff = __skb_header_pointer(skb, poff + 12, sizeof(_doff), data, hlen, &_doff); if (!doff) return poff; poff += max_t(u32, sizeof(struct tcphdr), (*doff & 0xF0) >> 2); break; } case IPPROTO_UDP: case IPPROTO_UDPLITE: poff += sizeof(struct udphdr); break; /* For the rest, we do not really care about header * extensions at this point for now. */ case IPPROTO_ICMP: poff += sizeof(struct icmphdr); break; case IPPROTO_ICMPV6: poff += sizeof(struct icmp6hdr); break; case IPPROTO_IGMP: poff += sizeof(struct igmphdr); break; case IPPROTO_DCCP: poff += sizeof(struct dccp_hdr); break; case IPPROTO_SCTP: poff += sizeof(struct sctphdr); break; } return poff; } /** * skb_get_poff - get the offset to the payload * @skb: sk_buff to get the payload offset from * * The function will get the offset to the payload as far as it could * be dissected. The main user is currently BPF, so that we can dynamically * truncate packets without needing to push actual payload to the user * space and can analyze headers only, instead. */ u32 skb_get_poff(const struct sk_buff *skb) { struct flow_keys_basic keys; if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) return 0; return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb)); } __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys) { memset(keys, 0, sizeof(*keys)); memcpy(&keys->addrs.v6addrs.src, &fl6->saddr, sizeof(keys->addrs.v6addrs.src)); memcpy(&keys->addrs.v6addrs.dst, &fl6->daddr, sizeof(keys->addrs.v6addrs.dst)); keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; keys->ports.src = fl6->fl6_sport; keys->ports.dst = fl6->fl6_dport; keys->keyid.keyid = fl6->fl6_gre_key; keys->tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); keys->basic.ip_proto = fl6->flowi6_proto; return flow_hash_from_keys(keys); } EXPORT_SYMBOL(__get_hash_from_flowi6); static const struct flow_dissector_key flow_keys_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct flow_keys, addrs.v4addrs), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { .key_id = FLOW_DISSECTOR_KEY_TIPC, .offset = offsetof(struct flow_keys, addrs.tipckey), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct flow_keys, ports), }, { .key_id = FLOW_DISSECTOR_KEY_VLAN, .offset = offsetof(struct flow_keys, vlan), }, { .key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL, .offset = offsetof(struct flow_keys, tags), }, { .key_id = FLOW_DISSECTOR_KEY_GRE_KEYID, .offset = offsetof(struct flow_keys, keyid), }, }; static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct flow_keys, addrs.v4addrs), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct flow_keys, ports), }, }; static const struct flow_dissector_key flow_keys_basic_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, }; struct flow_dissector flow_keys_dissector __read_mostly; EXPORT_SYMBOL(flow_keys_dissector); struct flow_dissector flow_keys_basic_dissector __read_mostly; EXPORT_SYMBOL(flow_keys_basic_dissector); static int __init init_default_flow_dissectors(void) { skb_flow_dissector_init(&flow_keys_dissector, flow_keys_dissector_keys, ARRAY_SIZE(flow_keys_dissector_keys)); skb_flow_dissector_init(&flow_keys_dissector_symmetric, flow_keys_dissector_symmetric_keys, ARRAY_SIZE(flow_keys_dissector_symmetric_keys)); skb_flow_dissector_init(&flow_keys_basic_dissector, flow_keys_basic_dissector_keys, ARRAY_SIZE(flow_keys_basic_dissector_keys)); return 0; } core_initcall(init_default_flow_dissectors); |
| 1634 1634 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 | /* * This file implement the Wireless Extensions proc API. * * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. * * (As all part of the Linux kernel, this file is GPL) */ /* * The /proc/net/wireless file is a human readable user-space interface * exporting various wireless specific statistics from the wireless devices. * This is the most popular part of the Wireless Extensions ;-) * * This interface is a pure clone of /proc/net/dev (in net/core/dev.c). * The content of the file is basically the content of "struct iw_statistics". */ #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/wireless.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <net/iw_handler.h> #include <net/wext.h> static void wireless_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { /* Get stats from the driver */ struct iw_statistics *stats = get_wireless_stats(dev); static struct iw_statistics nullstats = {}; /* show device if it's wireless regardless of current stats */ if (!stats) { #ifdef CONFIG_WIRELESS_EXT if (dev->wireless_handlers) stats = &nullstats; #endif #ifdef CONFIG_CFG80211 if (dev->ieee80211_ptr) stats = &nullstats; #endif } if (stats) { seq_printf(seq, "%6s: %04x %3d%c %3d%c %3d%c %6d %6d %6d " "%6d %6d %6d\n", dev->name, stats->status, stats->qual.qual, stats->qual.updated & IW_QUAL_QUAL_UPDATED ? '.' : ' ', ((__s32) stats->qual.level) - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), stats->qual.updated & IW_QUAL_LEVEL_UPDATED ? '.' : ' ', ((__s32) stats->qual.noise) - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), stats->qual.updated & IW_QUAL_NOISE_UPDATED ? '.' : ' ', stats->discard.nwid, stats->discard.code, stats->discard.fragment, stats->discard.retries, stats->discard.misc, stats->miss.beacon); if (stats != &nullstats) stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; } } /* ---------------------------------------------------------------- */ /* * Print info for /proc/net/wireless (print all entries) */ static int wireless_dev_seq_show(struct seq_file *seq, void *v) { might_sleep(); if (v == SEQ_START_TOKEN) seq_printf(seq, "Inter-| sta-| Quality | Discarded " "packets | Missed | WE\n" " face | tus | link level noise | nwid " "crypt frag retry misc | beacon | %d\n", WIRELESS_EXT); else wireless_seq_printf_stats(seq, v); return 0; } static void *wireless_dev_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); loff_t off; struct net_device *dev; rtnl_lock(); if (!*pos) return SEQ_START_TOKEN; off = 1; for_each_netdev(net, dev) if (off++ == *pos) return dev; return NULL; } static void *wireless_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); ++*pos; return v == SEQ_START_TOKEN ? first_net_device(net) : next_net_device(v); } static void wireless_dev_seq_stop(struct seq_file *seq, void *v) { rtnl_unlock(); } static const struct seq_operations wireless_seq_ops = { .start = wireless_dev_seq_start, .next = wireless_dev_seq_next, .stop = wireless_dev_seq_stop, .show = wireless_dev_seq_show, }; int __net_init wext_proc_init(struct net *net) { /* Create /proc/net/wireless entry */ if (!proc_create_net("wireless", 0444, net->proc_net, &wireless_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } void __net_exit wext_proc_exit(struct net *net) { remove_proc_entry("wireless", net->proc_net); } |
| 40 32 40 32 41 62 62 1 62 62 26 32 31 32 32 2 32 61 24 3 7 18 24 75 40 1 40 40 14 40 12 40 62 27 1 27 27 27 24 75 26 59 59 1 26 6 61 61 61 61 61 61 61 61 28 1 1 1 14 1 14 14 75 61 61 28 28 28 28 28 75 58 58 58 58 1 58 58 6 72 15 133 133 133 8 8 8 8 8 141 141 8 8 8 8 133 133 133 133 141 141 10 1 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2016 Facebook */ #include <linux/cpumask.h> #include <linux/spinlock.h> #include <linux/percpu.h> #include "bpf_lru_list.h" #define LOCAL_FREE_TARGET (128) #define LOCAL_NR_SCANS LOCAL_FREE_TARGET #define PERCPU_FREE_TARGET (4) #define PERCPU_NR_SCANS PERCPU_FREE_TARGET /* Helpers to get the local list index */ #define LOCAL_LIST_IDX(t) ((t) - BPF_LOCAL_LIST_T_OFFSET) #define LOCAL_FREE_LIST_IDX LOCAL_LIST_IDX(BPF_LRU_LOCAL_LIST_T_FREE) #define LOCAL_PENDING_LIST_IDX LOCAL_LIST_IDX(BPF_LRU_LOCAL_LIST_T_PENDING) #define IS_LOCAL_LIST_TYPE(t) ((t) >= BPF_LOCAL_LIST_T_OFFSET) static int get_next_cpu(int cpu) { cpu = cpumask_next(cpu, cpu_possible_mask); if (cpu >= nr_cpu_ids) cpu = cpumask_first(cpu_possible_mask); return cpu; } /* Local list helpers */ static struct list_head *local_free_list(struct bpf_lru_locallist *loc_l) { return &loc_l->lists[LOCAL_FREE_LIST_IDX]; } static struct list_head *local_pending_list(struct bpf_lru_locallist *loc_l) { return &loc_l->lists[LOCAL_PENDING_LIST_IDX]; } /* bpf_lru_node helpers */ static bool bpf_lru_node_is_ref(const struct bpf_lru_node *node) { return node->ref; } static void bpf_lru_list_count_inc(struct bpf_lru_list *l, enum bpf_lru_list_type type) { if (type < NR_BPF_LRU_LIST_COUNT) l->counts[type]++; } static void bpf_lru_list_count_dec(struct bpf_lru_list *l, enum bpf_lru_list_type type) { if (type < NR_BPF_LRU_LIST_COUNT) l->counts[type]--; } static void __bpf_lru_node_move_to_free(struct bpf_lru_list *l, struct bpf_lru_node *node, struct list_head *free_list, enum bpf_lru_list_type tgt_free_type) { if (WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(node->type))) return; /* If the removing node is the next_inactive_rotation candidate, * move the next_inactive_rotation pointer also. */ if (&node->list == l->next_inactive_rotation) l->next_inactive_rotation = l->next_inactive_rotation->prev; bpf_lru_list_count_dec(l, node->type); node->type = tgt_free_type; list_move(&node->list, free_list); } /* Move nodes from local list to the LRU list */ static void __bpf_lru_node_move_in(struct bpf_lru_list *l, struct bpf_lru_node *node, enum bpf_lru_list_type tgt_type) { if (WARN_ON_ONCE(!IS_LOCAL_LIST_TYPE(node->type)) || WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(tgt_type))) return; bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; node->ref = 0; list_move(&node->list, &l->lists[tgt_type]); } /* Move nodes between or within active and inactive list (like * active to inactive, inactive to active or tail of active back to * the head of active). */ static void __bpf_lru_node_move(struct bpf_lru_list *l, struct bpf_lru_node *node, enum bpf_lru_list_type tgt_type) { if (WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(node->type)) || WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(tgt_type))) return; if (node->type != tgt_type) { bpf_lru_list_count_dec(l, node->type); bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; } node->ref = 0; /* If the moving node is the next_inactive_rotation candidate, * move the next_inactive_rotation pointer also. */ if (&node->list == l->next_inactive_rotation) l->next_inactive_rotation = l->next_inactive_rotation->prev; list_move(&node->list, &l->lists[tgt_type]); } static bool bpf_lru_list_inactive_low(const struct bpf_lru_list *l) { return l->counts[BPF_LRU_LIST_T_INACTIVE] < l->counts[BPF_LRU_LIST_T_ACTIVE]; } /* Rotate the active list: * 1. Start from tail * 2. If the node has the ref bit set, it will be rotated * back to the head of active list with the ref bit cleared. * Give this node one more chance to survive in the active list. * 3. If the ref bit is not set, move it to the head of the * inactive list. * 4. It will at most scan nr_scans nodes */ static void __bpf_lru_list_rotate_active(struct bpf_lru *lru, struct bpf_lru_list *l) { struct list_head *active = &l->lists[BPF_LRU_LIST_T_ACTIVE]; struct bpf_lru_node *node, *tmp_node, *first_node; unsigned int i = 0; first_node = list_first_entry(active, struct bpf_lru_node, list); list_for_each_entry_safe_reverse(node, tmp_node, active, list) { if (bpf_lru_node_is_ref(node)) __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_ACTIVE); else __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE); if (++i == lru->nr_scans || node == first_node) break; } } /* Rotate the inactive list. It starts from the next_inactive_rotation * 1. If the node has ref bit set, it will be moved to the head * of active list with the ref bit cleared. * 2. If the node does not have ref bit set, it will leave it * at its current location (i.e. do nothing) so that it can * be considered during the next inactive_shrink. * 3. It will at most scan nr_scans nodes */ static void __bpf_lru_list_rotate_inactive(struct bpf_lru *lru, struct bpf_lru_list *l) { struct list_head *inactive = &l->lists[BPF_LRU_LIST_T_INACTIVE]; struct list_head *cur, *last, *next = inactive; struct bpf_lru_node *node; unsigned int i = 0; if (list_empty(inactive)) return; last = l->next_inactive_rotation->next; if (last == inactive) last = last->next; cur = l->next_inactive_rotation; while (i < lru->nr_scans) { if (cur == inactive) { cur = cur->prev; continue; } node = list_entry(cur, struct bpf_lru_node, list); next = cur->prev; if (bpf_lru_node_is_ref(node)) __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_ACTIVE); if (cur == last) break; cur = next; i++; } l->next_inactive_rotation = next; } /* Shrink the inactive list. It starts from the tail of the * inactive list and only move the nodes without the ref bit * set to the designated free list. */ static unsigned int __bpf_lru_list_shrink_inactive(struct bpf_lru *lru, struct bpf_lru_list *l, unsigned int tgt_nshrink, struct list_head *free_list, enum bpf_lru_list_type tgt_free_type) { struct list_head *inactive = &l->lists[BPF_LRU_LIST_T_INACTIVE]; struct bpf_lru_node *node, *tmp_node; unsigned int nshrinked = 0; unsigned int i = 0; list_for_each_entry_safe_reverse(node, tmp_node, inactive, list) { if (bpf_lru_node_is_ref(node)) { __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_ACTIVE); } else if (lru->del_from_htab(lru->del_arg, node)) { __bpf_lru_node_move_to_free(l, node, free_list, tgt_free_type); if (++nshrinked == tgt_nshrink) break; } if (++i == lru->nr_scans) break; } return nshrinked; } /* 1. Rotate the active list (if needed) * 2. Always rotate the inactive list */ static void __bpf_lru_list_rotate(struct bpf_lru *lru, struct bpf_lru_list *l) { if (bpf_lru_list_inactive_low(l)) __bpf_lru_list_rotate_active(lru, l); __bpf_lru_list_rotate_inactive(lru, l); } /* Calls __bpf_lru_list_shrink_inactive() to shrink some * ref-bit-cleared nodes and move them to the designated * free list. * * If it cannot get a free node after calling * __bpf_lru_list_shrink_inactive(). It will just remove * one node from either inactive or active list without * honoring the ref-bit. It prefers inactive list to active * list in this situation. */ static unsigned int __bpf_lru_list_shrink(struct bpf_lru *lru, struct bpf_lru_list *l, unsigned int tgt_nshrink, struct list_head *free_list, enum bpf_lru_list_type tgt_free_type) { struct bpf_lru_node *node, *tmp_node; struct list_head *force_shrink_list; unsigned int nshrinked; nshrinked = __bpf_lru_list_shrink_inactive(lru, l, tgt_nshrink, free_list, tgt_free_type); if (nshrinked) return nshrinked; /* Do a force shrink by ignoring the reference bit */ if (!list_empty(&l->lists[BPF_LRU_LIST_T_INACTIVE])) force_shrink_list = &l->lists[BPF_LRU_LIST_T_INACTIVE]; else force_shrink_list = &l->lists[BPF_LRU_LIST_T_ACTIVE]; list_for_each_entry_safe_reverse(node, tmp_node, force_shrink_list, list) { if (lru->del_from_htab(lru->del_arg, node)) { __bpf_lru_node_move_to_free(l, node, free_list, tgt_free_type); return 1; } } return 0; } /* Flush the nodes from the local pending list to the LRU list */ static void __local_list_flush(struct bpf_lru_list *l, struct bpf_lru_locallist *loc_l) { struct bpf_lru_node *node, *tmp_node; list_for_each_entry_safe_reverse(node, tmp_node, local_pending_list(loc_l), list) { if (bpf_lru_node_is_ref(node)) __bpf_lru_node_move_in(l, node, BPF_LRU_LIST_T_ACTIVE); else __bpf_lru_node_move_in(l, node, BPF_LRU_LIST_T_INACTIVE); } } static void bpf_lru_list_push_free(struct bpf_lru_list *l, struct bpf_lru_node *node) { unsigned long flags; if (WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(node->type))) return; raw_spin_lock_irqsave(&l->lock, flags); __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_FREE); raw_spin_unlock_irqrestore(&l->lock, flags); } static void bpf_lru_list_pop_free_to_local(struct bpf_lru *lru, struct bpf_lru_locallist *loc_l) { struct bpf_lru_list *l = &lru->common_lru.lru_list; struct bpf_lru_node *node, *tmp_node; unsigned int nfree = 0; raw_spin_lock(&l->lock); __local_list_flush(l, loc_l); __bpf_lru_list_rotate(lru, l); list_for_each_entry_safe(node, tmp_node, &l->lists[BPF_LRU_LIST_T_FREE], list) { __bpf_lru_node_move_to_free(l, node, local_free_list(loc_l), BPF_LRU_LOCAL_LIST_T_FREE); if (++nfree == LOCAL_FREE_TARGET) break; } if (nfree < LOCAL_FREE_TARGET) __bpf_lru_list_shrink(lru, l, LOCAL_FREE_TARGET - nfree, local_free_list(loc_l), BPF_LRU_LOCAL_LIST_T_FREE); raw_spin_unlock(&l->lock); } static void __local_list_add_pending(struct bpf_lru *lru, struct bpf_lru_locallist *loc_l, int cpu, struct bpf_lru_node *node, u32 hash) { *(u32 *)((void *)node + lru->hash_offset) = hash; node->cpu = cpu; node->type = BPF_LRU_LOCAL_LIST_T_PENDING; node->ref = 0; list_add(&node->list, local_pending_list(loc_l)); } static struct bpf_lru_node * __local_list_pop_free(struct bpf_lru_locallist *loc_l) { struct bpf_lru_node *node; node = list_first_entry_or_null(local_free_list(loc_l), struct bpf_lru_node, list); if (node) list_del(&node->list); return node; } static struct bpf_lru_node * __local_list_pop_pending(struct bpf_lru *lru, struct bpf_lru_locallist *loc_l) { struct bpf_lru_node *node; bool force = false; ignore_ref: /* Get from the tail (i.e. older element) of the pending list. */ list_for_each_entry_reverse(node, local_pending_list(loc_l), list) { if ((!bpf_lru_node_is_ref(node) || force) && lru->del_from_htab(lru->del_arg, node)) { list_del(&node->list); return node; } } if (!force) { force = true; goto ignore_ref; } return NULL; } static struct bpf_lru_node *bpf_percpu_lru_pop_free(struct bpf_lru *lru, u32 hash) { struct list_head *free_list; struct bpf_lru_node *node = NULL; struct bpf_lru_list *l; unsigned long flags; int cpu = raw_smp_processor_id(); l = per_cpu_ptr(lru->percpu_lru, cpu); raw_spin_lock_irqsave(&l->lock, flags); __bpf_lru_list_rotate(lru, l); free_list = &l->lists[BPF_LRU_LIST_T_FREE]; if (list_empty(free_list)) __bpf_lru_list_shrink(lru, l, PERCPU_FREE_TARGET, free_list, BPF_LRU_LIST_T_FREE); if (!list_empty(free_list)) { node = list_first_entry(free_list, struct bpf_lru_node, list); *(u32 *)((void *)node + lru->hash_offset) = hash; node->ref = 0; __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE); } raw_spin_unlock_irqrestore(&l->lock, flags); return node; } static struct bpf_lru_node *bpf_common_lru_pop_free(struct bpf_lru *lru, u32 hash) { struct bpf_lru_locallist *loc_l, *steal_loc_l; struct bpf_common_lru *clru = &lru->common_lru; struct bpf_lru_node *node; int steal, first_steal; unsigned long flags; int cpu = raw_smp_processor_id(); loc_l = per_cpu_ptr(clru->local_list, cpu); raw_spin_lock_irqsave(&loc_l->lock, flags); node = __local_list_pop_free(loc_l); if (!node) { bpf_lru_list_pop_free_to_local(lru, loc_l); node = __local_list_pop_free(loc_l); } if (node) __local_list_add_pending(lru, loc_l, cpu, node, hash); raw_spin_unlock_irqrestore(&loc_l->lock, flags); if (node) return node; /* No free nodes found from the local free list and * the global LRU list. * * Steal from the local free/pending list of the * current CPU and remote CPU in RR. It starts * with the loc_l->next_steal CPU. */ first_steal = loc_l->next_steal; steal = first_steal; do { steal_loc_l = per_cpu_ptr(clru->local_list, steal); raw_spin_lock_irqsave(&steal_loc_l->lock, flags); node = __local_list_pop_free(steal_loc_l); if (!node) node = __local_list_pop_pending(lru, steal_loc_l); raw_spin_unlock_irqrestore(&steal_loc_l->lock, flags); steal = get_next_cpu(steal); } while (!node && steal != first_steal); loc_l->next_steal = steal; if (node) { raw_spin_lock_irqsave(&loc_l->lock, flags); __local_list_add_pending(lru, loc_l, cpu, node, hash); raw_spin_unlock_irqrestore(&loc_l->lock, flags); } return node; } struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash) { if (lru->percpu) return bpf_percpu_lru_pop_free(lru, hash); else return bpf_common_lru_pop_free(lru, hash); } static void bpf_common_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node) { u8 node_type = READ_ONCE(node->type); unsigned long flags; if (WARN_ON_ONCE(node_type == BPF_LRU_LIST_T_FREE) || WARN_ON_ONCE(node_type == BPF_LRU_LOCAL_LIST_T_FREE)) return; if (node_type == BPF_LRU_LOCAL_LIST_T_PENDING) { struct bpf_lru_locallist *loc_l; loc_l = per_cpu_ptr(lru->common_lru.local_list, node->cpu); raw_spin_lock_irqsave(&loc_l->lock, flags); if (unlikely(node->type != BPF_LRU_LOCAL_LIST_T_PENDING)) { raw_spin_unlock_irqrestore(&loc_l->lock, flags); goto check_lru_list; } node->type = BPF_LRU_LOCAL_LIST_T_FREE; node->ref = 0; list_move(&node->list, local_free_list(loc_l)); raw_spin_unlock_irqrestore(&loc_l->lock, flags); return; } check_lru_list: bpf_lru_list_push_free(&lru->common_lru.lru_list, node); } static void bpf_percpu_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node) { struct bpf_lru_list *l; unsigned long flags; l = per_cpu_ptr(lru->percpu_lru, node->cpu); raw_spin_lock_irqsave(&l->lock, flags); __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_FREE); raw_spin_unlock_irqrestore(&l->lock, flags); } void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node) { if (lru->percpu) bpf_percpu_lru_push_free(lru, node); else bpf_common_lru_push_free(lru, node); } static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset, u32 elem_size, u32 nr_elems) { struct bpf_lru_list *l = &lru->common_lru.lru_list; u32 i; for (i = 0; i < nr_elems; i++) { struct bpf_lru_node *node; node = (struct bpf_lru_node *)(buf + node_offset); node->type = BPF_LRU_LIST_T_FREE; node->ref = 0; list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); buf += elem_size; } } static void bpf_percpu_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset, u32 elem_size, u32 nr_elems) { u32 i, pcpu_entries; int cpu; struct bpf_lru_list *l; pcpu_entries = nr_elems / num_possible_cpus(); i = 0; for_each_possible_cpu(cpu) { struct bpf_lru_node *node; l = per_cpu_ptr(lru->percpu_lru, cpu); again: node = (struct bpf_lru_node *)(buf + node_offset); node->cpu = cpu; node->type = BPF_LRU_LIST_T_FREE; node->ref = 0; list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); i++; buf += elem_size; if (i == nr_elems) break; if (i % pcpu_entries) goto again; } } void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset, u32 elem_size, u32 nr_elems) { if (lru->percpu) bpf_percpu_lru_populate(lru, buf, node_offset, elem_size, nr_elems); else bpf_common_lru_populate(lru, buf, node_offset, elem_size, nr_elems); } static void bpf_lru_locallist_init(struct bpf_lru_locallist *loc_l, int cpu) { int i; for (i = 0; i < NR_BPF_LRU_LOCAL_LIST_T; i++) INIT_LIST_HEAD(&loc_l->lists[i]); loc_l->next_steal = cpu; raw_spin_lock_init(&loc_l->lock); } static void bpf_lru_list_init(struct bpf_lru_list *l) { int i; for (i = 0; i < NR_BPF_LRU_LIST_T; i++) INIT_LIST_HEAD(&l->lists[i]); for (i = 0; i < NR_BPF_LRU_LIST_COUNT; i++) l->counts[i] = 0; l->next_inactive_rotation = &l->lists[BPF_LRU_LIST_T_INACTIVE]; raw_spin_lock_init(&l->lock); } int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset, del_from_htab_func del_from_htab, void *del_arg) { int cpu; if (percpu) { lru->percpu_lru = alloc_percpu(struct bpf_lru_list); if (!lru->percpu_lru) return -ENOMEM; for_each_possible_cpu(cpu) { struct bpf_lru_list *l; l = per_cpu_ptr(lru->percpu_lru, cpu); bpf_lru_list_init(l); } lru->nr_scans = PERCPU_NR_SCANS; } else { struct bpf_common_lru *clru = &lru->common_lru; clru->local_list = alloc_percpu(struct bpf_lru_locallist); if (!clru->local_list) return -ENOMEM; for_each_possible_cpu(cpu) { struct bpf_lru_locallist *loc_l; loc_l = per_cpu_ptr(clru->local_list, cpu); bpf_lru_locallist_init(loc_l, cpu); } bpf_lru_list_init(&clru->lru_list); lru->nr_scans = LOCAL_NR_SCANS; } lru->percpu = percpu; lru->del_from_htab = del_from_htab; lru->del_arg = del_arg; lru->hash_offset = hash_offset; return 0; } void bpf_lru_destroy(struct bpf_lru *lru) { if (lru->percpu) free_percpu(lru->percpu_lru); else free_percpu(lru->common_lru.local_list); } |
| 25 26 25 25 25 25 25 4 4 4 25 25 25 27 27 5 27 2 24 25 25 4 4 4 4 25 25 25 25 25 25 25 27 27 26 24 25 25 26 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich */ #include "bridge_loop_avoidance.h" #include "main.h" #include <linux/atomic.h> #include <linux/byteorder/generic.h> #include <linux/compiler.h> #include <linux/container_of.h> #include <linux/crc16.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/workqueue.h> #include <net/arp.h> #include <net/genetlink.h> #include <net/netlink.h> #include <net/sock.h> #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> #include "hard-interface.h" #include "hash.h" #include "log.h" #include "netlink.h" #include "originator.h" #include "soft-interface.h" #include "translation-table.h" static const u8 batadv_announce_mac[4] = {0x43, 0x05, 0x43, 0x05}; static void batadv_bla_periodic_work(struct work_struct *work); static void batadv_bla_send_announce(struct batadv_priv *bat_priv, struct batadv_bla_backbone_gw *backbone_gw); /** * batadv_choose_claim() - choose the right bucket for a claim. * @data: data to hash * @size: size of the hash table * * Return: the hash index of the claim */ static inline u32 batadv_choose_claim(const void *data, u32 size) { const struct batadv_bla_claim *claim = data; u32 hash = 0; hash = jhash(&claim->addr, sizeof(claim->addr), hash); hash = jhash(&claim->vid, sizeof(claim->vid), hash); return hash % size; } /** * batadv_choose_backbone_gw() - choose the right bucket for a backbone gateway. * @data: data to hash * @size: size of the hash table * * Return: the hash index of the backbone gateway */ static inline u32 batadv_choose_backbone_gw(const void *data, u32 size) { const struct batadv_bla_backbone_gw *gw; u32 hash = 0; gw = data; hash = jhash(&gw->orig, sizeof(gw->orig), hash); hash = jhash(&gw->vid, sizeof(gw->vid), hash); return hash % size; } /** * batadv_compare_backbone_gw() - compare address and vid of two backbone gws * @node: list node of the first entry to compare * @data2: pointer to the second backbone gateway * * Return: true if the backbones have the same data, false otherwise */ static bool batadv_compare_backbone_gw(const struct hlist_node *node, const void *data2) { const void *data1 = container_of(node, struct batadv_bla_backbone_gw, hash_entry); const struct batadv_bla_backbone_gw *gw1 = data1; const struct batadv_bla_backbone_gw *gw2 = data2; if (!batadv_compare_eth(gw1->orig, gw2->orig)) return false; if (gw1->vid != gw2->vid) return false; return true; } /** * batadv_compare_claim() - compare address and vid of two claims * @node: list node of the first entry to compare * @data2: pointer to the second claims * * Return: true if the claim have the same data, 0 otherwise */ static bool batadv_compare_claim(const struct hlist_node *node, const void *data2) { const void *data1 = container_of(node, struct batadv_bla_claim, hash_entry); const struct batadv_bla_claim *cl1 = data1; const struct batadv_bla_claim *cl2 = data2; if (!batadv_compare_eth(cl1->addr, cl2->addr)) return false; if (cl1->vid != cl2->vid) return false; return true; } /** * batadv_backbone_gw_release() - release backbone gw from lists and queue for * free after rcu grace period * @ref: kref pointer of the backbone gw */ static void batadv_backbone_gw_release(struct kref *ref) { struct batadv_bla_backbone_gw *backbone_gw; backbone_gw = container_of(ref, struct batadv_bla_backbone_gw, refcount); kfree_rcu(backbone_gw, rcu); } /** * batadv_backbone_gw_put() - decrement the backbone gw refcounter and possibly * release it * @backbone_gw: backbone gateway to be free'd */ static void batadv_backbone_gw_put(struct batadv_bla_backbone_gw *backbone_gw) { if (!backbone_gw) return; kref_put(&backbone_gw->refcount, batadv_backbone_gw_release); } /** * batadv_claim_release() - release claim from lists and queue for free after * rcu grace period * @ref: kref pointer of the claim */ static void batadv_claim_release(struct kref *ref) { struct batadv_bla_claim *claim; struct batadv_bla_backbone_gw *old_backbone_gw; claim = container_of(ref, struct batadv_bla_claim, refcount); spin_lock_bh(&claim->backbone_lock); old_backbone_gw = claim->backbone_gw; claim->backbone_gw = NULL; spin_unlock_bh(&claim->backbone_lock); spin_lock_bh(&old_backbone_gw->crc_lock); old_backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); spin_unlock_bh(&old_backbone_gw->crc_lock); batadv_backbone_gw_put(old_backbone_gw); kfree_rcu(claim, rcu); } /** * batadv_claim_put() - decrement the claim refcounter and possibly release it * @claim: claim to be free'd */ static void batadv_claim_put(struct batadv_bla_claim *claim) { if (!claim) return; kref_put(&claim->refcount, batadv_claim_release); } /** * batadv_claim_hash_find() - looks for a claim in the claim hash * @bat_priv: the bat priv with all the soft interface information * @data: search data (may be local/static data) * * Return: claim if found or NULL otherwise. */ static struct batadv_bla_claim * batadv_claim_hash_find(struct batadv_priv *bat_priv, struct batadv_bla_claim *data) { struct batadv_hashtable *hash = bat_priv->bla.claim_hash; struct hlist_head *head; struct batadv_bla_claim *claim; struct batadv_bla_claim *claim_tmp = NULL; int index; if (!hash) return NULL; index = batadv_choose_claim(data, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { if (!batadv_compare_claim(&claim->hash_entry, data)) continue; if (!kref_get_unless_zero(&claim->refcount)) continue; claim_tmp = claim; break; } rcu_read_unlock(); return claim_tmp; } /** * batadv_backbone_hash_find() - looks for a backbone gateway in the hash * @bat_priv: the bat priv with all the soft interface information * @addr: the address of the originator * @vid: the VLAN ID * * Return: backbone gateway if found or NULL otherwise */ static struct batadv_bla_backbone_gw * batadv_backbone_hash_find(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid) { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; struct batadv_bla_backbone_gw search_entry, *backbone_gw; struct batadv_bla_backbone_gw *backbone_gw_tmp = NULL; int index; if (!hash) return NULL; ether_addr_copy(search_entry.orig, addr); search_entry.vid = vid; index = batadv_choose_backbone_gw(&search_entry, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (!batadv_compare_backbone_gw(&backbone_gw->hash_entry, &search_entry)) continue; if (!kref_get_unless_zero(&backbone_gw->refcount)) continue; backbone_gw_tmp = backbone_gw; break; } rcu_read_unlock(); return backbone_gw_tmp; } /** * batadv_bla_del_backbone_claims() - delete all claims for a backbone * @backbone_gw: backbone gateway where the claims should be removed */ static void batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) { struct batadv_hashtable *hash; struct hlist_node *node_tmp; struct hlist_head *head; struct batadv_bla_claim *claim; int i; spinlock_t *list_lock; /* protects write access to the hash lists */ hash = backbone_gw->bat_priv->bla.claim_hash; if (!hash) return; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(claim, node_tmp, head, hash_entry) { if (claim->backbone_gw != backbone_gw) continue; batadv_claim_put(claim); hlist_del_rcu(&claim->hash_entry); } spin_unlock_bh(list_lock); } /* all claims gone, initialize CRC */ spin_lock_bh(&backbone_gw->crc_lock); backbone_gw->crc = BATADV_BLA_CRC_INIT; spin_unlock_bh(&backbone_gw->crc_lock); } /** * batadv_bla_send_claim() - sends a claim frame according to the provided info * @bat_priv: the bat priv with all the soft interface information * @mac: the mac address to be announced within the claim * @vid: the VLAN ID * @claimtype: the type of the claim (CLAIM, UNCLAIM, ANNOUNCE, ...) */ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, const u8 *mac, unsigned short vid, int claimtype) { struct sk_buff *skb; struct ethhdr *ethhdr; struct batadv_hard_iface *primary_if; struct net_device *soft_iface; u8 *hw_src; struct batadv_bla_claim_dst local_claim_dest; __be32 zeroip = 0; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) return; memcpy(&local_claim_dest, &bat_priv->bla.claim_dest, sizeof(local_claim_dest)); local_claim_dest.type = claimtype; soft_iface = primary_if->soft_iface; skb = arp_create(ARPOP_REPLY, ETH_P_ARP, /* IP DST: 0.0.0.0 */ zeroip, primary_if->soft_iface, /* IP SRC: 0.0.0.0 */ zeroip, /* Ethernet DST: Broadcast */ NULL, /* Ethernet SRC/HW SRC: originator mac */ primary_if->net_dev->dev_addr, /* HW DST: FF:43:05:XX:YY:YY * with XX = claim type * and YY:YY = group id */ (u8 *)&local_claim_dest); if (!skb) goto out; ethhdr = (struct ethhdr *)skb->data; hw_src = (u8 *)ethhdr + ETH_HLEN + sizeof(struct arphdr); /* now we pretend that the client would have sent this ... */ switch (claimtype) { case BATADV_CLAIM_TYPE_CLAIM: /* normal claim frame * set Ethernet SRC to the clients mac */ ether_addr_copy(ethhdr->h_source, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): CLAIM %pM on vid %d\n", __func__, mac, batadv_print_vid(vid)); break; case BATADV_CLAIM_TYPE_UNCLAIM: /* unclaim frame * set HW SRC to the clients mac */ ether_addr_copy(hw_src, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): UNCLAIM %pM on vid %d\n", __func__, mac, batadv_print_vid(vid)); break; case BATADV_CLAIM_TYPE_ANNOUNCE: /* announcement frame * set HW SRC to the special mac containing the crc */ ether_addr_copy(hw_src, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): ANNOUNCE of %pM on vid %d\n", __func__, ethhdr->h_source, batadv_print_vid(vid)); break; case BATADV_CLAIM_TYPE_REQUEST: /* request frame * set HW SRC and header destination to the receiving backbone * gws mac */ ether_addr_copy(hw_src, mac); ether_addr_copy(ethhdr->h_dest, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): REQUEST of %pM to %pM on vid %d\n", __func__, ethhdr->h_source, ethhdr->h_dest, batadv_print_vid(vid)); break; case BATADV_CLAIM_TYPE_LOOPDETECT: ether_addr_copy(ethhdr->h_source, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): LOOPDETECT of %pM to %pM on vid %d\n", __func__, ethhdr->h_source, ethhdr->h_dest, batadv_print_vid(vid)); break; } if (vid & BATADV_VLAN_HAS_TAG) { skb = vlan_insert_tag(skb, htons(ETH_P_8021Q), vid & VLAN_VID_MASK); if (!skb) goto out; } skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, soft_iface); batadv_inc_counter(bat_priv, BATADV_CNT_RX); batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES, skb->len + ETH_HLEN); netif_rx(skb); out: batadv_hardif_put(primary_if); } /** * batadv_bla_loopdetect_report() - worker for reporting the loop * @work: work queue item * * Throws an uevent, as the loopdetect check function can't do that itself * since the kernel may sleep while throwing uevents. */ static void batadv_bla_loopdetect_report(struct work_struct *work) { struct batadv_bla_backbone_gw *backbone_gw; struct batadv_priv *bat_priv; char vid_str[6] = { '\0' }; backbone_gw = container_of(work, struct batadv_bla_backbone_gw, report_work); bat_priv = backbone_gw->bat_priv; batadv_info(bat_priv->soft_iface, "Possible loop on VLAN %d detected which can't be handled by BLA - please check your network setup!\n", batadv_print_vid(backbone_gw->vid)); snprintf(vid_str, sizeof(vid_str), "%d", batadv_print_vid(backbone_gw->vid)); vid_str[sizeof(vid_str) - 1] = 0; batadv_throw_uevent(bat_priv, BATADV_UEV_BLA, BATADV_UEV_LOOPDETECT, vid_str); batadv_backbone_gw_put(backbone_gw); } /** * batadv_bla_get_backbone_gw() - finds or creates a backbone gateway * @bat_priv: the bat priv with all the soft interface information * @orig: the mac address of the originator * @vid: the VLAN ID * @own_backbone: set if the requested backbone is local * * Return: the (possibly created) backbone gateway or NULL on error */ static struct batadv_bla_backbone_gw * batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, const u8 *orig, unsigned short vid, bool own_backbone) { struct batadv_bla_backbone_gw *entry; struct batadv_orig_node *orig_node; int hash_added; entry = batadv_backbone_hash_find(bat_priv, orig, vid); if (entry) return entry; batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): not found (%pM, %d), creating new entry\n", __func__, orig, batadv_print_vid(vid)); entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) return NULL; entry->vid = vid; entry->lasttime = jiffies; entry->crc = BATADV_BLA_CRC_INIT; entry->bat_priv = bat_priv; spin_lock_init(&entry->crc_lock); atomic_set(&entry->request_sent, 0); atomic_set(&entry->wait_periods, 0); ether_addr_copy(entry->orig, orig); INIT_WORK(&entry->report_work, batadv_bla_loopdetect_report); kref_init(&entry->refcount); kref_get(&entry->refcount); hash_added = batadv_hash_add(bat_priv->bla.backbone_hash, batadv_compare_backbone_gw, batadv_choose_backbone_gw, entry, &entry->hash_entry); if (unlikely(hash_added != 0)) { /* hash failed, free the structure */ kfree(entry); return NULL; } /* this is a gateway now, remove any TT entry on this VLAN */ orig_node = batadv_orig_hash_find(bat_priv, orig); if (orig_node) { batadv_tt_global_del_orig(bat_priv, orig_node, vid, "became a backbone gateway"); batadv_orig_node_put(orig_node); } if (own_backbone) { batadv_bla_send_announce(bat_priv, entry); /* this will be decreased in the worker thread */ atomic_inc(&entry->request_sent); atomic_set(&entry->wait_periods, BATADV_BLA_WAIT_PERIODS); atomic_inc(&bat_priv->bla.num_requests); } return entry; } /** * batadv_bla_update_own_backbone_gw() - updates the own backbone gw for a VLAN * @bat_priv: the bat priv with all the soft interface information * @primary_if: the selected primary interface * @vid: VLAN identifier * * update or add the own backbone gw to make sure we announce * where we receive other backbone gws */ static void batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; backbone_gw = batadv_bla_get_backbone_gw(bat_priv, primary_if->net_dev->dev_addr, vid, true); if (unlikely(!backbone_gw)) return; backbone_gw->lasttime = jiffies; batadv_backbone_gw_put(backbone_gw); } /** * batadv_bla_answer_request() - answer a bla request by sending own claims * @bat_priv: the bat priv with all the soft interface information * @primary_if: interface where the request came on * @vid: the vid where the request came on * * Repeat all of our own claims, and finally send an ANNOUNCE frame * to allow the requester another check if the CRC is correct now. */ static void batadv_bla_answer_request(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, unsigned short vid) { struct hlist_head *head; struct batadv_hashtable *hash; struct batadv_bla_claim *claim; struct batadv_bla_backbone_gw *backbone_gw; int i; batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): received a claim request, send all of our own claims again\n", __func__); backbone_gw = batadv_backbone_hash_find(bat_priv, primary_if->net_dev->dev_addr, vid); if (!backbone_gw) return; hash = bat_priv->bla.claim_hash; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { /* only own claims are interesting */ if (claim->backbone_gw != backbone_gw) continue; batadv_bla_send_claim(bat_priv, claim->addr, claim->vid, BATADV_CLAIM_TYPE_CLAIM); } rcu_read_unlock(); } /* finally, send an announcement frame */ batadv_bla_send_announce(bat_priv, backbone_gw); batadv_backbone_gw_put(backbone_gw); } /** * batadv_bla_send_request() - send a request to repeat claims * @backbone_gw: the backbone gateway from whom we are out of sync * * When the crc is wrong, ask the backbone gateway for a full table update. * After the request, it will repeat all of his own claims and finally * send an announcement claim with which we can check again. */ static void batadv_bla_send_request(struct batadv_bla_backbone_gw *backbone_gw) { /* first, remove all old entries */ batadv_bla_del_backbone_claims(backbone_gw); batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, "Sending REQUEST to %pM\n", backbone_gw->orig); /* send request */ batadv_bla_send_claim(backbone_gw->bat_priv, backbone_gw->orig, backbone_gw->vid, BATADV_CLAIM_TYPE_REQUEST); /* no local broadcasts should be sent or received, for now. */ if (!atomic_read(&backbone_gw->request_sent)) { atomic_inc(&backbone_gw->bat_priv->bla.num_requests); atomic_set(&backbone_gw->request_sent, 1); } } /** * batadv_bla_send_announce() - Send an announcement frame * @bat_priv: the bat priv with all the soft interface information * @backbone_gw: our backbone gateway which should be announced */ static void batadv_bla_send_announce(struct batadv_priv *bat_priv, struct batadv_bla_backbone_gw *backbone_gw) { u8 mac[ETH_ALEN]; __be16 crc; memcpy(mac, batadv_announce_mac, 4); spin_lock_bh(&backbone_gw->crc_lock); crc = htons(backbone_gw->crc); spin_unlock_bh(&backbone_gw->crc_lock); memcpy(&mac[4], &crc, 2); batadv_bla_send_claim(bat_priv, mac, backbone_gw->vid, BATADV_CLAIM_TYPE_ANNOUNCE); } /** * batadv_bla_add_claim() - Adds a claim in the claim hash * @bat_priv: the bat priv with all the soft interface information * @mac: the mac address of the claim * @vid: the VLAN ID of the frame * @backbone_gw: the backbone gateway which claims it */ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, const u8 *mac, const unsigned short vid, struct batadv_bla_backbone_gw *backbone_gw) { struct batadv_bla_backbone_gw *old_backbone_gw; struct batadv_bla_claim *claim; struct batadv_bla_claim search_claim; bool remove_crc = false; int hash_added; ether_addr_copy(search_claim.addr, mac); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); /* create a new claim entry if it does not exist yet. */ if (!claim) { claim = kzalloc(sizeof(*claim), GFP_ATOMIC); if (!claim) return; ether_addr_copy(claim->addr, mac); spin_lock_init(&claim->backbone_lock); claim->vid = vid; claim->lasttime = jiffies; kref_get(&backbone_gw->refcount); claim->backbone_gw = backbone_gw; kref_init(&claim->refcount); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): adding new entry %pM, vid %d to hash ...\n", __func__, mac, batadv_print_vid(vid)); kref_get(&claim->refcount); hash_added = batadv_hash_add(bat_priv->bla.claim_hash, batadv_compare_claim, batadv_choose_claim, claim, &claim->hash_entry); if (unlikely(hash_added != 0)) { /* only local changes happened. */ kfree(claim); return; } } else { claim->lasttime = jiffies; if (claim->backbone_gw == backbone_gw) /* no need to register a new backbone */ goto claim_free_ref; batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): changing ownership for %pM, vid %d to gw %pM\n", __func__, mac, batadv_print_vid(vid), backbone_gw->orig); remove_crc = true; } /* replace backbone_gw atomically and adjust reference counters */ spin_lock_bh(&claim->backbone_lock); old_backbone_gw = claim->backbone_gw; kref_get(&backbone_gw->refcount); claim->backbone_gw = backbone_gw; spin_unlock_bh(&claim->backbone_lock); if (remove_crc) { /* remove claim address from old backbone_gw */ spin_lock_bh(&old_backbone_gw->crc_lock); old_backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); spin_unlock_bh(&old_backbone_gw->crc_lock); } batadv_backbone_gw_put(old_backbone_gw); /* add claim address to new backbone_gw */ spin_lock_bh(&backbone_gw->crc_lock); backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); spin_unlock_bh(&backbone_gw->crc_lock); backbone_gw->lasttime = jiffies; claim_free_ref: batadv_claim_put(claim); } /** * batadv_bla_claim_get_backbone_gw() - Get valid reference for backbone_gw of * claim * @claim: claim whose backbone_gw should be returned * * Return: valid reference to claim::backbone_gw */ static struct batadv_bla_backbone_gw * batadv_bla_claim_get_backbone_gw(struct batadv_bla_claim *claim) { struct batadv_bla_backbone_gw *backbone_gw; spin_lock_bh(&claim->backbone_lock); backbone_gw = claim->backbone_gw; kref_get(&backbone_gw->refcount); spin_unlock_bh(&claim->backbone_lock); return backbone_gw; } /** * batadv_bla_del_claim() - delete a claim from the claim hash * @bat_priv: the bat priv with all the soft interface information * @mac: mac address of the claim to be removed * @vid: VLAN id for the claim to be removed */ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, const u8 *mac, const unsigned short vid) { struct batadv_bla_claim search_claim, *claim; struct batadv_bla_claim *claim_removed_entry; struct hlist_node *claim_removed_node; ether_addr_copy(search_claim.addr, mac); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); if (!claim) return; batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): %pM, vid %d\n", __func__, mac, batadv_print_vid(vid)); claim_removed_node = batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim, batadv_choose_claim, claim); if (!claim_removed_node) goto free_claim; /* reference from the hash is gone */ claim_removed_entry = hlist_entry(claim_removed_node, struct batadv_bla_claim, hash_entry); batadv_claim_put(claim_removed_entry); free_claim: /* don't need the reference from hash_find() anymore */ batadv_claim_put(claim); } /** * batadv_handle_announce() - check for ANNOUNCE frame * @bat_priv: the bat priv with all the soft interface information * @an_addr: announcement mac address (ARP Sender HW address) * @backbone_addr: originator address of the sender (Ethernet source MAC) * @vid: the VLAN ID of the frame * * Return: true if handled */ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, u8 *backbone_addr, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; u16 backbone_crc, crc; if (memcmp(an_addr, batadv_announce_mac, 4) != 0) return false; backbone_gw = batadv_bla_get_backbone_gw(bat_priv, backbone_addr, vid, false); if (unlikely(!backbone_gw)) return true; /* handle as ANNOUNCE frame */ backbone_gw->lasttime = jiffies; crc = ntohs(*((__force __be16 *)(&an_addr[4]))); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n", __func__, batadv_print_vid(vid), backbone_gw->orig, crc); spin_lock_bh(&backbone_gw->crc_lock); backbone_crc = backbone_gw->crc; spin_unlock_bh(&backbone_gw->crc_lock); if (backbone_crc != crc) { batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, "%s(): CRC FAILED for %pM/%d (my = %#.4x, sent = %#.4x)\n", __func__, backbone_gw->orig, batadv_print_vid(backbone_gw->vid), backbone_crc, crc); batadv_bla_send_request(backbone_gw); } else { /* if we have sent a request and the crc was OK, * we can allow traffic again. */ if (atomic_read(&backbone_gw->request_sent)) { atomic_dec(&backbone_gw->bat_priv->bla.num_requests); atomic_set(&backbone_gw->request_sent, 0); } } batadv_backbone_gw_put(backbone_gw); return true; } /** * batadv_handle_request() - check for REQUEST frame * @bat_priv: the bat priv with all the soft interface information * @primary_if: the primary hard interface of this batman soft interface * @backbone_addr: backbone address to be requested (ARP sender HW MAC) * @ethhdr: ethernet header of a packet * @vid: the VLAN ID of the frame * * Return: true if handled */ static bool batadv_handle_request(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, u8 *backbone_addr, struct ethhdr *ethhdr, unsigned short vid) { /* check for REQUEST frame */ if (!batadv_compare_eth(backbone_addr, ethhdr->h_dest)) return false; /* sanity check, this should not happen on a normal switch, * we ignore it in this case. */ if (!batadv_compare_eth(ethhdr->h_dest, primary_if->net_dev->dev_addr)) return true; batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): REQUEST vid %d (sent by %pM)...\n", __func__, batadv_print_vid(vid), ethhdr->h_source); batadv_bla_answer_request(bat_priv, primary_if, vid); return true; } /** * batadv_handle_unclaim() - check for UNCLAIM frame * @bat_priv: the bat priv with all the soft interface information * @primary_if: the primary hard interface of this batman soft interface * @backbone_addr: originator address of the backbone (Ethernet source) * @claim_addr: Client to be unclaimed (ARP sender HW MAC) * @vid: the VLAN ID of the frame * * Return: true if handled */ static bool batadv_handle_unclaim(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, const u8 *backbone_addr, const u8 *claim_addr, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; /* unclaim in any case if it is our own */ if (primary_if && batadv_compare_eth(backbone_addr, primary_if->net_dev->dev_addr)) batadv_bla_send_claim(bat_priv, claim_addr, vid, BATADV_CLAIM_TYPE_UNCLAIM); backbone_gw = batadv_backbone_hash_find(bat_priv, backbone_addr, vid); if (!backbone_gw) return true; /* this must be an UNCLAIM frame */ batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): UNCLAIM %pM on vid %d (sent by %pM)...\n", __func__, claim_addr, batadv_print_vid(vid), backbone_gw->orig); batadv_bla_del_claim(bat_priv, claim_addr, vid); batadv_backbone_gw_put(backbone_gw); return true; } /** * batadv_handle_claim() - check for CLAIM frame * @bat_priv: the bat priv with all the soft interface information * @primary_if: the primary hard interface of this batman soft interface * @backbone_addr: originator address of the backbone (Ethernet Source) * @claim_addr: client mac address to be claimed (ARP sender HW MAC) * @vid: the VLAN ID of the frame * * Return: true if handled */ static bool batadv_handle_claim(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, const u8 *backbone_addr, const u8 *claim_addr, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; /* register the gateway if not yet available, and add the claim. */ backbone_gw = batadv_bla_get_backbone_gw(bat_priv, backbone_addr, vid, false); if (unlikely(!backbone_gw)) return true; /* this must be a CLAIM frame */ batadv_bla_add_claim(bat_priv, claim_addr, vid, backbone_gw); if (batadv_compare_eth(backbone_addr, primary_if->net_dev->dev_addr)) batadv_bla_send_claim(bat_priv, claim_addr, vid, BATADV_CLAIM_TYPE_CLAIM); /* TODO: we could call something like tt_local_del() here. */ batadv_backbone_gw_put(backbone_gw); return true; } /** * batadv_check_claim_group() - check for claim group membership * @bat_priv: the bat priv with all the soft interface information * @primary_if: the primary interface of this batman interface * @hw_src: the Hardware source in the ARP Header * @hw_dst: the Hardware destination in the ARP Header * @ethhdr: pointer to the Ethernet header of the claim frame * * checks if it is a claim packet and if it's on the same group. * This function also applies the group ID of the sender * if it is in the same mesh. * * Return: * 2 - if it is a claim packet and on the same group * 1 - if is a claim packet from another group * 0 - if it is not a claim packet */ static int batadv_check_claim_group(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, u8 *hw_src, u8 *hw_dst, struct ethhdr *ethhdr) { u8 *backbone_addr; struct batadv_orig_node *orig_node; struct batadv_bla_claim_dst *bla_dst, *bla_dst_own; bla_dst = (struct batadv_bla_claim_dst *)hw_dst; bla_dst_own = &bat_priv->bla.claim_dest; /* if announcement packet, use the source, * otherwise assume it is in the hw_src */ switch (bla_dst->type) { case BATADV_CLAIM_TYPE_CLAIM: backbone_addr = hw_src; break; case BATADV_CLAIM_TYPE_REQUEST: case BATADV_CLAIM_TYPE_ANNOUNCE: case BATADV_CLAIM_TYPE_UNCLAIM: backbone_addr = ethhdr->h_source; break; default: return 0; } /* don't accept claim frames from ourselves */ if (batadv_compare_eth(backbone_addr, primary_if->net_dev->dev_addr)) return 0; /* if its already the same group, it is fine. */ if (bla_dst->group == bla_dst_own->group) return 2; /* lets see if this originator is in our mesh */ orig_node = batadv_orig_hash_find(bat_priv, backbone_addr); /* don't accept claims from gateways which are not in * the same mesh or group. */ if (!orig_node) return 1; /* if our mesh friends mac is bigger, use it for ourselves. */ if (ntohs(bla_dst->group) > ntohs(bla_dst_own->group)) { batadv_dbg(BATADV_DBG_BLA, bat_priv, "taking other backbones claim group: %#.4x\n", ntohs(bla_dst->group)); bla_dst_own->group = bla_dst->group; } batadv_orig_node_put(orig_node); return 2; } /** * batadv_bla_process_claim() - Check if this is a claim frame, and process it * @bat_priv: the bat priv with all the soft interface information * @primary_if: the primary hard interface of this batman soft interface * @skb: the frame to be checked * * Return: true if it was a claim frame, otherwise return false to * tell the callee that it can use the frame on its own. */ static bool batadv_bla_process_claim(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, struct sk_buff *skb) { struct batadv_bla_claim_dst *bla_dst, *bla_dst_own; u8 *hw_src, *hw_dst; struct vlan_hdr *vhdr, vhdr_buf; struct ethhdr *ethhdr; struct arphdr *arphdr; unsigned short vid; int vlan_depth = 0; __be16 proto; int headlen; int ret; vid = batadv_get_vid(skb, 0); ethhdr = eth_hdr(skb); proto = ethhdr->h_proto; headlen = ETH_HLEN; if (vid & BATADV_VLAN_HAS_TAG) { /* Traverse the VLAN/Ethertypes. * * At this point it is known that the first protocol is a VLAN * header, so start checking at the encapsulated protocol. * * The depth of the VLAN headers is recorded to drop BLA claim * frames encapsulated into multiple VLAN headers (QinQ). */ do { vhdr = skb_header_pointer(skb, headlen, VLAN_HLEN, &vhdr_buf); if (!vhdr) return false; proto = vhdr->h_vlan_encapsulated_proto; headlen += VLAN_HLEN; vlan_depth++; } while (proto == htons(ETH_P_8021Q)); } if (proto != htons(ETH_P_ARP)) return false; /* not a claim frame */ /* this must be a ARP frame. check if it is a claim. */ if (unlikely(!pskb_may_pull(skb, headlen + arp_hdr_len(skb->dev)))) return false; /* pskb_may_pull() may have modified the pointers, get ethhdr again */ ethhdr = eth_hdr(skb); arphdr = (struct arphdr *)((u8 *)ethhdr + headlen); /* Check whether the ARP frame carries a valid * IP information */ if (arphdr->ar_hrd != htons(ARPHRD_ETHER)) return false; if (arphdr->ar_pro != htons(ETH_P_IP)) return false; if (arphdr->ar_hln != ETH_ALEN) return false; if (arphdr->ar_pln != 4) return false; hw_src = (u8 *)arphdr + sizeof(struct arphdr); hw_dst = hw_src + ETH_ALEN + 4; bla_dst = (struct batadv_bla_claim_dst *)hw_dst; bla_dst_own = &bat_priv->bla.claim_dest; /* check if it is a claim frame in general */ if (memcmp(bla_dst->magic, bla_dst_own->magic, sizeof(bla_dst->magic)) != 0) return false; /* check if there is a claim frame encapsulated deeper in (QinQ) and * drop that, as this is not supported by BLA but should also not be * sent via the mesh. */ if (vlan_depth > 1) return true; /* Let the loopdetect frames on the mesh in any case. */ if (bla_dst->type == BATADV_CLAIM_TYPE_LOOPDETECT) return false; /* check if it is a claim frame. */ ret = batadv_check_claim_group(bat_priv, primary_if, hw_src, hw_dst, ethhdr); if (ret == 1) batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): received a claim frame from another group. From: %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", __func__, ethhdr->h_source, batadv_print_vid(vid), hw_src, hw_dst); if (ret < 2) return !!ret; /* become a backbone gw ourselves on this vlan if not happened yet */ batadv_bla_update_own_backbone_gw(bat_priv, primary_if, vid); /* check for the different types of claim frames ... */ switch (bla_dst->type) { case BATADV_CLAIM_TYPE_CLAIM: if (batadv_handle_claim(bat_priv, primary_if, hw_src, ethhdr->h_source, vid)) return true; break; case BATADV_CLAIM_TYPE_UNCLAIM: if (batadv_handle_unclaim(bat_priv, primary_if, ethhdr->h_source, hw_src, vid)) return true; break; case BATADV_CLAIM_TYPE_ANNOUNCE: if (batadv_handle_announce(bat_priv, hw_src, ethhdr->h_source, vid)) return true; break; case BATADV_CLAIM_TYPE_REQUEST: if (batadv_handle_request(bat_priv, primary_if, hw_src, ethhdr, vid)) return true; break; } batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): ERROR - this looks like a claim frame, but is useless. eth src %pM on vid %d ...(hw_src %pM, hw_dst %pM)\n", __func__, ethhdr->h_source, batadv_print_vid(vid), hw_src, hw_dst); return true; } /** * batadv_bla_purge_backbone_gw() - Remove backbone gateways after a timeout or * immediately * @bat_priv: the bat priv with all the soft interface information * @now: whether the whole hash shall be wiped now * * Check when we last heard from other nodes, and remove them in case of * a time out, or clean all backbone gws if now is set. */ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) { struct batadv_bla_backbone_gw *backbone_gw; struct hlist_node *node_tmp; struct hlist_head *head; struct batadv_hashtable *hash; spinlock_t *list_lock; /* protects write access to the hash lists */ int i; hash = bat_priv->bla.backbone_hash; if (!hash) return; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(backbone_gw, node_tmp, head, hash_entry) { if (now) goto purge_now; if (!batadv_has_timed_out(backbone_gw->lasttime, BATADV_BLA_BACKBONE_TIMEOUT)) continue; batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, "%s(): backbone gw %pM timed out\n", __func__, backbone_gw->orig); purge_now: /* don't wait for the pending request anymore */ if (atomic_read(&backbone_gw->request_sent)) atomic_dec(&bat_priv->bla.num_requests); batadv_bla_del_backbone_claims(backbone_gw); hlist_del_rcu(&backbone_gw->hash_entry); batadv_backbone_gw_put(backbone_gw); } spin_unlock_bh(list_lock); } } /** * batadv_bla_purge_claims() - Remove claims after a timeout or immediately * @bat_priv: the bat priv with all the soft interface information * @primary_if: the selected primary interface, may be NULL if now is set * @now: whether the whole hash shall be wiped now * * Check when we heard last time from our own claims, and remove them in case of * a time out, or clean all claims if now is set */ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, int now) { struct batadv_bla_backbone_gw *backbone_gw; struct batadv_bla_claim *claim; struct hlist_head *head; struct batadv_hashtable *hash; int i; hash = bat_priv->bla.claim_hash; if (!hash) return; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { backbone_gw = batadv_bla_claim_get_backbone_gw(claim); if (now) goto purge_now; if (!batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr)) goto skip; if (!batadv_has_timed_out(claim->lasttime, BATADV_BLA_CLAIM_TIMEOUT)) goto skip; batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): timed out.\n", __func__); purge_now: batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): %pM, vid %d\n", __func__, claim->addr, claim->vid); batadv_handle_unclaim(bat_priv, primary_if, backbone_gw->orig, claim->addr, claim->vid); skip: batadv_backbone_gw_put(backbone_gw); } rcu_read_unlock(); } } /** * batadv_bla_update_orig_address() - Update the backbone gateways when the own * originator address changes * @bat_priv: the bat priv with all the soft interface information * @primary_if: the new selected primary_if * @oldif: the old primary interface, may be NULL */ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, struct batadv_hard_iface *oldif) { struct batadv_bla_backbone_gw *backbone_gw; struct hlist_head *head; struct batadv_hashtable *hash; __be16 group; int i; /* reset bridge loop avoidance group id */ group = htons(crc16(0, primary_if->net_dev->dev_addr, ETH_ALEN)); bat_priv->bla.claim_dest.group = group; /* purge everything when bridge loop avoidance is turned off */ if (!atomic_read(&bat_priv->bridge_loop_avoidance)) oldif = NULL; if (!oldif) { batadv_bla_purge_claims(bat_priv, NULL, 1); batadv_bla_purge_backbone_gw(bat_priv, 1); return; } hash = bat_priv->bla.backbone_hash; if (!hash) return; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { /* own orig still holds the old value. */ if (!batadv_compare_eth(backbone_gw->orig, oldif->net_dev->dev_addr)) continue; ether_addr_copy(backbone_gw->orig, primary_if->net_dev->dev_addr); /* send an announce frame so others will ask for our * claims and update their tables. */ batadv_bla_send_announce(bat_priv, backbone_gw); } rcu_read_unlock(); } } /** * batadv_bla_send_loopdetect() - send a loopdetect frame * @bat_priv: the bat priv with all the soft interface information * @backbone_gw: the backbone gateway for which a loop should be detected * * To detect loops that the bridge loop avoidance can't handle, send a loop * detection packet on the backbone. Unlike other BLA frames, this frame will * be allowed on the mesh by other nodes. If it is received on the mesh, this * indicates that there is a loop. */ static void batadv_bla_send_loopdetect(struct batadv_priv *bat_priv, struct batadv_bla_backbone_gw *backbone_gw) { batadv_dbg(BATADV_DBG_BLA, bat_priv, "Send loopdetect frame for vid %d\n", backbone_gw->vid); batadv_bla_send_claim(bat_priv, bat_priv->bla.loopdetect_addr, backbone_gw->vid, BATADV_CLAIM_TYPE_LOOPDETECT); } /** * batadv_bla_status_update() - purge bla interfaces if necessary * @net_dev: the soft interface net device */ void batadv_bla_status_update(struct net_device *net_dev) { struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hard_iface *primary_if; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) return; /* this function already purges everything when bla is disabled, * so just call that one. */ batadv_bla_update_orig_address(bat_priv, primary_if, primary_if); batadv_hardif_put(primary_if); } /** * batadv_bla_periodic_work() - performs periodic bla work * @work: kernel work struct * * periodic work to do: * * purge structures when they are too old * * send announcements */ static void batadv_bla_periodic_work(struct work_struct *work) { struct delayed_work *delayed_work; struct batadv_priv *bat_priv; struct batadv_priv_bla *priv_bla; struct hlist_head *head; struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hashtable *hash; struct batadv_hard_iface *primary_if; bool send_loopdetect = false; int i; delayed_work = to_delayed_work(work); priv_bla = container_of(delayed_work, struct batadv_priv_bla, work); bat_priv = container_of(priv_bla, struct batadv_priv, bla); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; batadv_bla_purge_claims(bat_priv, primary_if, 0); batadv_bla_purge_backbone_gw(bat_priv, 0); if (!atomic_read(&bat_priv->bridge_loop_avoidance)) goto out; if (atomic_dec_and_test(&bat_priv->bla.loopdetect_next)) { /* set a new random mac address for the next bridge loop * detection frames. Set the locally administered bit to avoid * collisions with users mac addresses. */ eth_random_addr(bat_priv->bla.loopdetect_addr); bat_priv->bla.loopdetect_addr[0] = 0xba; bat_priv->bla.loopdetect_addr[1] = 0xbe; bat_priv->bla.loopdetect_lasttime = jiffies; atomic_set(&bat_priv->bla.loopdetect_next, BATADV_BLA_LOOPDETECT_PERIODS); /* mark for sending loop detect on all VLANs */ send_loopdetect = true; } hash = bat_priv->bla.backbone_hash; if (!hash) goto out; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (!batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr)) continue; backbone_gw->lasttime = jiffies; batadv_bla_send_announce(bat_priv, backbone_gw); if (send_loopdetect) batadv_bla_send_loopdetect(bat_priv, backbone_gw); /* request_sent is only set after creation to avoid * problems when we are not yet known as backbone gw * in the backbone. * * We can reset this now after we waited some periods * to give bridge forward delays and bla group forming * some grace time. */ if (atomic_read(&backbone_gw->request_sent) == 0) continue; if (!atomic_dec_and_test(&backbone_gw->wait_periods)) continue; atomic_dec(&backbone_gw->bat_priv->bla.num_requests); atomic_set(&backbone_gw->request_sent, 0); } rcu_read_unlock(); } out: batadv_hardif_put(primary_if); queue_delayed_work(batadv_event_workqueue, &bat_priv->bla.work, msecs_to_jiffies(BATADV_BLA_PERIOD_LENGTH)); } /* The hash for claim and backbone hash receive the same key because they * are getting initialized by hash_new with the same key. Reinitializing * them with to different keys to allow nested locking without generating * lockdep warnings */ static struct lock_class_key batadv_claim_hash_lock_class_key; static struct lock_class_key batadv_backbone_hash_lock_class_key; /** * batadv_bla_init() - initialize all bla structures * @bat_priv: the bat priv with all the soft interface information * * Return: 0 on success, < 0 on error. */ int batadv_bla_init(struct batadv_priv *bat_priv) { int i; u8 claim_dest[ETH_ALEN] = {0xff, 0x43, 0x05, 0x00, 0x00, 0x00}; struct batadv_hard_iface *primary_if; u16 crc; unsigned long entrytime; spin_lock_init(&bat_priv->bla.bcast_duplist_lock); batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla hash registering\n"); /* setting claim destination address */ memcpy(&bat_priv->bla.claim_dest.magic, claim_dest, 3); bat_priv->bla.claim_dest.type = 0; primary_if = batadv_primary_if_get_selected(bat_priv); if (primary_if) { crc = crc16(0, primary_if->net_dev->dev_addr, ETH_ALEN); bat_priv->bla.claim_dest.group = htons(crc); batadv_hardif_put(primary_if); } else { bat_priv->bla.claim_dest.group = 0; /* will be set later */ } /* initialize the duplicate list */ entrytime = jiffies - msecs_to_jiffies(BATADV_DUPLIST_TIMEOUT); for (i = 0; i < BATADV_DUPLIST_SIZE; i++) bat_priv->bla.bcast_duplist[i].entrytime = entrytime; bat_priv->bla.bcast_duplist_curr = 0; atomic_set(&bat_priv->bla.loopdetect_next, BATADV_BLA_LOOPDETECT_PERIODS); if (bat_priv->bla.claim_hash) return 0; bat_priv->bla.claim_hash = batadv_hash_new(128); if (!bat_priv->bla.claim_hash) return -ENOMEM; bat_priv->bla.backbone_hash = batadv_hash_new(32); if (!bat_priv->bla.backbone_hash) { batadv_hash_destroy(bat_priv->bla.claim_hash); return -ENOMEM; } batadv_hash_set_lock_class(bat_priv->bla.claim_hash, &batadv_claim_hash_lock_class_key); batadv_hash_set_lock_class(bat_priv->bla.backbone_hash, &batadv_backbone_hash_lock_class_key); batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla hashes initialized\n"); INIT_DELAYED_WORK(&bat_priv->bla.work, batadv_bla_periodic_work); queue_delayed_work(batadv_event_workqueue, &bat_priv->bla.work, msecs_to_jiffies(BATADV_BLA_PERIOD_LENGTH)); return 0; } /** * batadv_bla_check_duplist() - Check if a frame is in the broadcast dup. * @bat_priv: the bat priv with all the soft interface information * @skb: contains the multicast packet to be checked * @payload_ptr: pointer to position inside the head buffer of the skb * marking the start of the data to be CRC'ed * @orig: originator mac address, NULL if unknown * * Check if it is on our broadcast list. Another gateway might have sent the * same packet because it is connected to the same backbone, so we have to * remove this duplicate. * * This is performed by checking the CRC, which will tell us * with a good chance that it is the same packet. If it is furthermore * sent by another host, drop it. We allow equal packets from * the same host however as this might be intended. * * Return: true if a packet is in the duplicate list, false otherwise. */ static bool batadv_bla_check_duplist(struct batadv_priv *bat_priv, struct sk_buff *skb, u8 *payload_ptr, const u8 *orig) { struct batadv_bcast_duplist_entry *entry; bool ret = false; int i, curr; __be32 crc; /* calculate the crc ... */ crc = batadv_skb_crc32(skb, payload_ptr); spin_lock_bh(&bat_priv->bla.bcast_duplist_lock); for (i = 0; i < BATADV_DUPLIST_SIZE; i++) { curr = (bat_priv->bla.bcast_duplist_curr + i); curr %= BATADV_DUPLIST_SIZE; entry = &bat_priv->bla.bcast_duplist[curr]; /* we can stop searching if the entry is too old ; * later entries will be even older */ if (batadv_has_timed_out(entry->entrytime, BATADV_DUPLIST_TIMEOUT)) break; if (entry->crc != crc) continue; /* are the originators both known and not anonymous? */ if (orig && !is_zero_ether_addr(orig) && !is_zero_ether_addr(entry->orig)) { /* If known, check if the new frame came from * the same originator: * We are safe to take identical frames from the * same orig, if known, as multiplications in * the mesh are detected via the (orig, seqno) pair. * So we can be a bit more liberal here and allow * identical frames from the same orig which the source * host might have sent multiple times on purpose. */ if (batadv_compare_eth(entry->orig, orig)) continue; } /* this entry seems to match: same crc, not too old, * and from another gw. therefore return true to forbid it. */ ret = true; goto out; } /* not found, add a new entry (overwrite the oldest entry) * and allow it, its the first occurrence. */ curr = (bat_priv->bla.bcast_duplist_curr + BATADV_DUPLIST_SIZE - 1); curr %= BATADV_DUPLIST_SIZE; entry = &bat_priv->bla.bcast_duplist[curr]; entry->crc = crc; entry->entrytime = jiffies; /* known originator */ if (orig) ether_addr_copy(entry->orig, orig); /* anonymous originator */ else eth_zero_addr(entry->orig); bat_priv->bla.bcast_duplist_curr = curr; out: spin_unlock_bh(&bat_priv->bla.bcast_duplist_lock); return ret; } /** * batadv_bla_check_ucast_duplist() - Check if a frame is in the broadcast dup. * @bat_priv: the bat priv with all the soft interface information * @skb: contains the multicast packet to be checked, decapsulated from a * unicast_packet * * Check if it is on our broadcast list. Another gateway might have sent the * same packet because it is connected to the same backbone, so we have to * remove this duplicate. * * Return: true if a packet is in the duplicate list, false otherwise. */ static bool batadv_bla_check_ucast_duplist(struct batadv_priv *bat_priv, struct sk_buff *skb) { return batadv_bla_check_duplist(bat_priv, skb, (u8 *)skb->data, NULL); } /** * batadv_bla_check_bcast_duplist() - Check if a frame is in the broadcast dup. * @bat_priv: the bat priv with all the soft interface information * @skb: contains the bcast_packet to be checked * * Check if it is on our broadcast list. Another gateway might have sent the * same packet because it is connected to the same backbone, so we have to * remove this duplicate. * * Return: true if a packet is in the duplicate list, false otherwise. */ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_bcast_packet *bcast_packet; u8 *payload_ptr; bcast_packet = (struct batadv_bcast_packet *)skb->data; payload_ptr = (u8 *)(bcast_packet + 1); return batadv_bla_check_duplist(bat_priv, skb, payload_ptr, bcast_packet->orig); } /** * batadv_bla_is_backbone_gw_orig() - Check if the originator is a gateway for * the VLAN identified by vid. * @bat_priv: the bat priv with all the soft interface information * @orig: originator mac address * @vid: VLAN identifier * * Return: true if orig is a backbone for this vid, false otherwise. */ bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, u8 *orig, unsigned short vid) { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; struct batadv_bla_backbone_gw *backbone_gw; int i; if (!atomic_read(&bat_priv->bridge_loop_avoidance)) return false; if (!hash) return false; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (batadv_compare_eth(backbone_gw->orig, orig) && backbone_gw->vid == vid) { rcu_read_unlock(); return true; } } rcu_read_unlock(); } return false; } /** * batadv_bla_is_backbone_gw() - check if originator is a backbone gw for a VLAN * @skb: the frame to be checked * @orig_node: the orig_node of the frame * @hdr_size: maximum length of the frame * * Return: true if the orig_node is also a gateway on the soft interface, * otherwise it returns false. */ bool batadv_bla_is_backbone_gw(struct sk_buff *skb, struct batadv_orig_node *orig_node, int hdr_size) { struct batadv_bla_backbone_gw *backbone_gw; unsigned short vid; if (!atomic_read(&orig_node->bat_priv->bridge_loop_avoidance)) return false; /* first, find out the vid. */ if (!pskb_may_pull(skb, hdr_size + ETH_HLEN)) return false; vid = batadv_get_vid(skb, hdr_size); /* see if this originator is a backbone gw for this VLAN */ backbone_gw = batadv_backbone_hash_find(orig_node->bat_priv, orig_node->orig, vid); if (!backbone_gw) return false; batadv_backbone_gw_put(backbone_gw); return true; } /** * batadv_bla_free() - free all bla structures * @bat_priv: the bat priv with all the soft interface information * * for softinterface free or module unload */ void batadv_bla_free(struct batadv_priv *bat_priv) { struct batadv_hard_iface *primary_if; cancel_delayed_work_sync(&bat_priv->bla.work); primary_if = batadv_primary_if_get_selected(bat_priv); if (bat_priv->bla.claim_hash) { batadv_bla_purge_claims(bat_priv, primary_if, 1); batadv_hash_destroy(bat_priv->bla.claim_hash); bat_priv->bla.claim_hash = NULL; } if (bat_priv->bla.backbone_hash) { batadv_bla_purge_backbone_gw(bat_priv, 1); batadv_hash_destroy(bat_priv->bla.backbone_hash); bat_priv->bla.backbone_hash = NULL; } batadv_hardif_put(primary_if); } /** * batadv_bla_loopdetect_check() - check and handle a detected loop * @bat_priv: the bat priv with all the soft interface information * @skb: the packet to check * @primary_if: interface where the request came on * @vid: the VLAN ID of the frame * * Checks if this packet is a loop detect frame which has been sent by us, * throws an uevent and logs the event if that is the case. * * Return: true if it is a loop detect frame which is to be dropped, false * otherwise. */ static bool batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_hard_iface *primary_if, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; struct ethhdr *ethhdr; bool ret; ethhdr = eth_hdr(skb); /* Only check for the MAC address and skip more checks here for * performance reasons - this function is on the hotpath, after all. */ if (!batadv_compare_eth(ethhdr->h_source, bat_priv->bla.loopdetect_addr)) return false; /* If the packet came too late, don't forward it on the mesh * but don't consider that as loop. It might be a coincidence. */ if (batadv_has_timed_out(bat_priv->bla.loopdetect_lasttime, BATADV_BLA_LOOPDETECT_TIMEOUT)) return true; backbone_gw = batadv_bla_get_backbone_gw(bat_priv, primary_if->net_dev->dev_addr, vid, true); if (unlikely(!backbone_gw)) return true; ret = queue_work(batadv_event_workqueue, &backbone_gw->report_work); /* backbone_gw is unreferenced in the report work function * if queue_work() call was successful */ if (!ret) batadv_backbone_gw_put(backbone_gw); return true; } /** * batadv_bla_rx() - check packets coming from the mesh. * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * @vid: the VLAN ID of the frame * @packet_type: the batman packet type this frame came in * * batadv_bla_rx avoidance checks if: * * we have to race for a claim * * if the frame is allowed on the LAN * * In these cases, the skb is further handled by this function * * Return: true if handled, otherwise it returns false and the caller shall * further process the skb. */ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, int packet_type) { struct batadv_bla_backbone_gw *backbone_gw; struct ethhdr *ethhdr; struct batadv_bla_claim search_claim, *claim = NULL; struct batadv_hard_iface *primary_if; bool own_claim; bool ret; ethhdr = eth_hdr(skb); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto handled; if (!atomic_read(&bat_priv->bridge_loop_avoidance)) goto allow; if (batadv_bla_loopdetect_check(bat_priv, skb, primary_if, vid)) goto handled; if (unlikely(atomic_read(&bat_priv->bla.num_requests))) /* don't allow multicast packets while requests are in flight */ if (is_multicast_ether_addr(ethhdr->h_dest)) /* Both broadcast flooding or multicast-via-unicasts * delivery might send to multiple backbone gateways * sharing the same LAN and therefore need to coordinate * which backbone gateway forwards into the LAN, * by claiming the payload source address. * * Broadcast flooding and multicast-via-unicasts * delivery use the following two batman packet types. * Note: explicitly exclude BATADV_UNICAST_4ADDR, * as the DHCP gateway feature will send explicitly * to only one BLA gateway, so the claiming process * should be avoided there. */ if (packet_type == BATADV_BCAST || packet_type == BATADV_UNICAST) goto handled; /* potential duplicates from foreign BLA backbone gateways via * multicast-in-unicast packets */ if (is_multicast_ether_addr(ethhdr->h_dest) && packet_type == BATADV_UNICAST && batadv_bla_check_ucast_duplist(bat_priv, skb)) goto handled; ether_addr_copy(search_claim.addr, ethhdr->h_source); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); if (!claim) { /* possible optimization: race for a claim */ /* No claim exists yet, claim it for us! */ batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): Unclaimed MAC %pM found. Claim it. Local: %s\n", __func__, ethhdr->h_source, batadv_is_my_client(bat_priv, ethhdr->h_source, vid) ? "yes" : "no"); batadv_handle_claim(bat_priv, primary_if, primary_if->net_dev->dev_addr, ethhdr->h_source, vid); goto allow; } /* if it is our own claim ... */ backbone_gw = batadv_bla_claim_get_backbone_gw(claim); own_claim = batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr); batadv_backbone_gw_put(backbone_gw); if (own_claim) { /* ... allow it in any case */ claim->lasttime = jiffies; goto allow; } /* if it is a multicast ... */ if (is_multicast_ether_addr(ethhdr->h_dest) && (packet_type == BATADV_BCAST || packet_type == BATADV_UNICAST)) { /* ... drop it. the responsible gateway is in charge. * * We need to check packet type because with the gateway * feature, broadcasts (like DHCP requests) may be sent * using a unicast 4 address packet type. See comment above. */ goto handled; } else { /* seems the client considers us as its best gateway. * send a claim and update the claim table * immediately. */ batadv_handle_claim(bat_priv, primary_if, primary_if->net_dev->dev_addr, ethhdr->h_source, vid); goto allow; } allow: batadv_bla_update_own_backbone_gw(bat_priv, primary_if, vid); ret = false; goto out; handled: kfree_skb(skb); ret = true; out: batadv_hardif_put(primary_if); batadv_claim_put(claim); return ret; } /** * batadv_bla_tx() - check packets going into the mesh * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * @vid: the VLAN ID of the frame * * batadv_bla_tx checks if: * * a claim was received which has to be processed * * the frame is allowed on the mesh * * in these cases, the skb is further handled by this function. * * This call might reallocate skb data. * * Return: true if handled, otherwise it returns false and the caller shall * further process the skb. */ bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct ethhdr *ethhdr; struct batadv_bla_claim search_claim, *claim = NULL; struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hard_iface *primary_if; bool client_roamed; bool ret = false; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; if (!atomic_read(&bat_priv->bridge_loop_avoidance)) goto allow; if (batadv_bla_process_claim(bat_priv, primary_if, skb)) goto handled; ethhdr = eth_hdr(skb); if (unlikely(atomic_read(&bat_priv->bla.num_requests))) /* don't allow broadcasts while requests are in flight */ if (is_multicast_ether_addr(ethhdr->h_dest)) goto handled; ether_addr_copy(search_claim.addr, ethhdr->h_source); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); /* if no claim exists, allow it. */ if (!claim) goto allow; /* check if we are responsible. */ backbone_gw = batadv_bla_claim_get_backbone_gw(claim); client_roamed = batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr); batadv_backbone_gw_put(backbone_gw); if (client_roamed) { /* if yes, the client has roamed and we have * to unclaim it. */ if (batadv_has_timed_out(claim->lasttime, 100)) { /* only unclaim if the last claim entry is * older than 100 ms to make sure we really * have a roaming client here. */ batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): Roaming client %pM detected. Unclaim it.\n", __func__, ethhdr->h_source); batadv_handle_unclaim(bat_priv, primary_if, primary_if->net_dev->dev_addr, ethhdr->h_source, vid); goto allow; } else { batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): Race for claim %pM detected. Drop packet.\n", __func__, ethhdr->h_source); goto handled; } } /* check if it is a multicast/broadcast frame */ if (is_multicast_ether_addr(ethhdr->h_dest)) { /* drop it. the responsible gateway has forwarded it into * the backbone network. */ goto handled; } else { /* we must allow it. at least if we are * responsible for the DESTINATION. */ goto allow; } allow: batadv_bla_update_own_backbone_gw(bat_priv, primary_if, vid); ret = false; goto out; handled: ret = true; out: batadv_hardif_put(primary_if); batadv_claim_put(claim); return ret; } /** * batadv_bla_claim_dump_entry() - dump one entry of the claim table * to a netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @primary_if: primary interface * @claim: entry to dump * * Return: 0 or error code. */ static int batadv_bla_claim_dump_entry(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_hard_iface *primary_if, struct batadv_bla_claim *claim) { const u8 *primary_addr = primary_if->net_dev->dev_addr; u16 backbone_crc; bool is_own; void *hdr; int ret = -EINVAL; hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq, &batadv_netlink_family, NLM_F_MULTI, BATADV_CMD_GET_BLA_CLAIM); if (!hdr) { ret = -ENOBUFS; goto out; } genl_dump_check_consistent(cb, hdr); is_own = batadv_compare_eth(claim->backbone_gw->orig, primary_addr); spin_lock_bh(&claim->backbone_gw->crc_lock); backbone_crc = claim->backbone_gw->crc; spin_unlock_bh(&claim->backbone_gw->crc_lock); if (is_own) if (nla_put_flag(msg, BATADV_ATTR_BLA_OWN)) { genlmsg_cancel(msg, hdr); goto out; } if (nla_put(msg, BATADV_ATTR_BLA_ADDRESS, ETH_ALEN, claim->addr) || nla_put_u16(msg, BATADV_ATTR_BLA_VID, claim->vid) || nla_put(msg, BATADV_ATTR_BLA_BACKBONE, ETH_ALEN, claim->backbone_gw->orig) || nla_put_u16(msg, BATADV_ATTR_BLA_CRC, backbone_crc)) { genlmsg_cancel(msg, hdr); goto out; } genlmsg_end(msg, hdr); ret = 0; out: return ret; } /** * batadv_bla_claim_dump_bucket() - dump one bucket of the claim table * to a netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @primary_if: primary interface * @hash: hash to dump * @bucket: bucket index to dump * @idx_skip: How many entries to skip * * Return: always 0. */ static int batadv_bla_claim_dump_bucket(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_hard_iface *primary_if, struct batadv_hashtable *hash, unsigned int bucket, int *idx_skip) { struct batadv_bla_claim *claim; int idx = 0; int ret = 0; spin_lock_bh(&hash->list_locks[bucket]); cb->seq = atomic_read(&hash->generation) << 1 | 1; hlist_for_each_entry(claim, &hash->table[bucket], hash_entry) { if (idx++ < *idx_skip) continue; ret = batadv_bla_claim_dump_entry(msg, portid, cb, primary_if, claim); if (ret) { *idx_skip = idx - 1; goto unlock; } } *idx_skip = 0; unlock: spin_unlock_bh(&hash->list_locks[bucket]); return ret; } /** * batadv_bla_claim_dump() - dump claim table to a netlink socket * @msg: buffer for the message * @cb: callback structure containing arguments * * Return: message length. */ int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if = NULL; int portid = NETLINK_CB(cb->skb).portid; struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_hashtable *hash; struct batadv_priv *bat_priv; int bucket = cb->args[0]; int idx = cb->args[1]; int ifindex; int ret = 0; ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); if (!ifindex) return -EINVAL; soft_iface = dev_get_by_index(net, ifindex); if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { ret = -ENODEV; goto out; } bat_priv = netdev_priv(soft_iface); hash = bat_priv->bla.claim_hash; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; goto out; } while (bucket < hash->size) { if (batadv_bla_claim_dump_bucket(msg, portid, cb, primary_if, hash, bucket, &idx)) break; bucket++; } cb->args[0] = bucket; cb->args[1] = idx; ret = msg->len; out: batadv_hardif_put(primary_if); dev_put(soft_iface); return ret; } /** * batadv_bla_backbone_dump_entry() - dump one entry of the backbone table to a * netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @primary_if: primary interface * @backbone_gw: entry to dump * * Return: 0 or error code. */ static int batadv_bla_backbone_dump_entry(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_hard_iface *primary_if, struct batadv_bla_backbone_gw *backbone_gw) { const u8 *primary_addr = primary_if->net_dev->dev_addr; u16 backbone_crc; bool is_own; int msecs; void *hdr; int ret = -EINVAL; hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq, &batadv_netlink_family, NLM_F_MULTI, BATADV_CMD_GET_BLA_BACKBONE); if (!hdr) { ret = -ENOBUFS; goto out; } genl_dump_check_consistent(cb, hdr); is_own = batadv_compare_eth(backbone_gw->orig, primary_addr); spin_lock_bh(&backbone_gw->crc_lock); backbone_crc = backbone_gw->crc; spin_unlock_bh(&backbone_gw->crc_lock); msecs = jiffies_to_msecs(jiffies - backbone_gw->lasttime); if (is_own) if (nla_put_flag(msg, BATADV_ATTR_BLA_OWN)) { genlmsg_cancel(msg, hdr); goto out; } if (nla_put(msg, BATADV_ATTR_BLA_BACKBONE, ETH_ALEN, backbone_gw->orig) || nla_put_u16(msg, BATADV_ATTR_BLA_VID, backbone_gw->vid) || nla_put_u16(msg, BATADV_ATTR_BLA_CRC, backbone_crc) || nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, msecs)) { genlmsg_cancel(msg, hdr); goto out; } genlmsg_end(msg, hdr); ret = 0; out: return ret; } /** * batadv_bla_backbone_dump_bucket() - dump one bucket of the backbone table to * a netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @primary_if: primary interface * @hash: hash to dump * @bucket: bucket index to dump * @idx_skip: How many entries to skip * * Return: always 0. */ static int batadv_bla_backbone_dump_bucket(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_hard_iface *primary_if, struct batadv_hashtable *hash, unsigned int bucket, int *idx_skip) { struct batadv_bla_backbone_gw *backbone_gw; int idx = 0; int ret = 0; spin_lock_bh(&hash->list_locks[bucket]); cb->seq = atomic_read(&hash->generation) << 1 | 1; hlist_for_each_entry(backbone_gw, &hash->table[bucket], hash_entry) { if (idx++ < *idx_skip) continue; ret = batadv_bla_backbone_dump_entry(msg, portid, cb, primary_if, backbone_gw); if (ret) { *idx_skip = idx - 1; goto unlock; } } *idx_skip = 0; unlock: spin_unlock_bh(&hash->list_locks[bucket]); return ret; } /** * batadv_bla_backbone_dump() - dump backbone table to a netlink socket * @msg: buffer for the message * @cb: callback structure containing arguments * * Return: message length. */ int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if = NULL; int portid = NETLINK_CB(cb->skb).portid; struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_hashtable *hash; struct batadv_priv *bat_priv; int bucket = cb->args[0]; int idx = cb->args[1]; int ifindex; int ret = 0; ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); if (!ifindex) return -EINVAL; soft_iface = dev_get_by_index(net, ifindex); if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { ret = -ENODEV; goto out; } bat_priv = netdev_priv(soft_iface); hash = bat_priv->bla.backbone_hash; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; goto out; } while (bucket < hash->size) { if (batadv_bla_backbone_dump_bucket(msg, portid, cb, primary_if, hash, bucket, &idx)) break; bucket++; } cb->args[0] = bucket; cb->args[1] = idx; ret = msg->len; out: batadv_hardif_put(primary_if); dev_put(soft_iface); return ret; } #ifdef CONFIG_BATMAN_ADV_DAT /** * batadv_bla_check_claim() - check if address is claimed * * @bat_priv: the bat priv with all the soft interface information * @addr: mac address of which the claim status is checked * @vid: the VLAN ID * * addr is checked if this address is claimed by the local device itself. * * Return: true if bla is disabled or the mac is claimed by the device, * false if the device addr is already claimed by another gateway */ bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr, unsigned short vid) { struct batadv_bla_claim search_claim; struct batadv_bla_claim *claim = NULL; struct batadv_hard_iface *primary_if = NULL; bool ret = true; if (!atomic_read(&bat_priv->bridge_loop_avoidance)) return ret; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) return ret; /* First look if the mac address is claimed */ ether_addr_copy(search_claim.addr, addr); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); /* If there is a claim and we are not owner of the claim, * return false. */ if (claim) { if (!batadv_compare_eth(claim->backbone_gw->orig, primary_if->net_dev->dev_addr)) ret = false; batadv_claim_put(claim); } batadv_hardif_put(primary_if); return ret; } #endif |
| 1290 1290 1289 1290 1290 1289 7457 7456 7455 3 2242 7455 15 1989 1290 1290 1290 1290 1290 1290 1290 1289 1290 1290 1290 1289 1290 1290 1290 7458 7453 7460 7458 7460 7457 7457 7455 7457 7457 1 7453 1987 1961 6932 6931 6932 6933 669 669 653 653 654 671 10273 10066 10042 10042 10036 10038 34 10041 10136 407 2537 2081 2082 2569 1529 5 27 27 27 27 8 8 8 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 | // 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 <net/sock.h> #include "internal.h" 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)) /* * 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 void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int count) { unsigned int cpy, set; cpy = count / BITS_PER_BYTE; set = (nfdt->max_fds - count) / BITS_PER_BYTE; memcpy(nfdt->open_fds, ofdt->open_fds, cpy); memset((char *)nfdt->open_fds + cpy, 0, set); memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); memset((char *)nfdt->close_on_exec + cpy, 0, set); cpy = BITBIT_SIZE(count); set = BITBIT_SIZE(nfdt->max_fds) - cpy; memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); memset((char *)nfdt->full_fds_bits + cpy, 0, set); } /* * 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, ofdt->max_fds); } /* * 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". * * The ALIGN(nr, BITS_PER_LONG) here is for clarity: since we just multiplied * by that "1024/sizeof(ptr)" before, we already know there are sufficient * clear low bits. Clang seems to realize that, gcc ends up being confused. * * On a 128-bit machine, the ALIGN() would actually matter. In the meantime, * let's consider it documentation (and maybe a test-case for gcc to improve * its code generation ;) */ static struct fdtable * alloc_fdtable(unsigned int nr) { struct fdtable *fdt; 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. */ nr /= (1024 / sizeof(struct file *)); nr = roundup_pow_of_two(nr + 1); nr *= (1024 / sizeof(struct file *)); nr = ALIGN(nr, BITS_PER_LONG); /* * 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. Deal * with that in caller, it's cheaper that way. * * 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 = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1; 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 NULL; } /* * 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; 1 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); /* 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 (!new_fdt) return -ENOMEM; /* * extremely unlikely race - sysctl_nr_open decreased between the check in * caller and alloc_fdtable(). Cheaper to catch it here... */ if (unlikely(new_fdt->max_fds <= nr)) { __free_fdtable(new_fdt); return -EMFILE; } 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 1; } /* * 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 when nothing done; 1 when files were * expanded and execution may have blocked. * 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 expanded = 0; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return expanded; /* Can we expand? */ if (nr >= sysctl_nr_open) return -EMFILE; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); expanded = 1; 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; expanded = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return expanded; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->close_on_exec); } static inline void __clear_close_on_exec(unsigned int fd, struct fdtable *fdt) { 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) { __set_bit(fd, fdt->open_fds); 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); __clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits); } static unsigned int count_open_files(struct fdtable *fdt) { unsigned int size = fdt->max_fds; unsigned int i; /* Find the last open fd */ for (i = size / BITS_PER_LONG; i > 0; ) { if (fdt->open_fds[--i]) break; } i = (i + 1) * BITS_PER_LONG; return i; } /* * 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. * * 'max_fds' will normally already be properly aligned, but it * turns out that in the close_range() -> __close_range() -> * unshare_fd() -> dup_fd() -> sane_fdtable_size() we can end * up having a 'max_fds' value that isn't already aligned. * * Rather than make close_range() have to worry about this, * just make that BITS_PER_LONG alignment be part of a sane * fdtable size. Becuase that's really what it is. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds) { unsigned int count; count = count_open_files(fdt); if (max_fds < NR_OPEN_DEFAULT) max_fds = NR_OPEN_DEFAULT; return ALIGN(min(count, max_fds), BITS_PER_LONG); } /* * Allocate a new files structure and copy contents from the * passed in files structure. * errorp will be valid only when the returned files_struct is NULL. */ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; *errorp = -ENOMEM; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) goto out; 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, max_fds); /* * 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 - 1); if (!new_fdt) { *errorp = -ENOMEM; goto out_release; } /* beyond sysctl_nr_open; nothing to do */ if (unlikely(new_fdt->max_fds < open_files)) { __free_fdtable(new_fdt); *errorp = -EMFILE; goto out_release; } /* * 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, max_fds); } copy_fd_bitmaps(new_fdt, old_fdt, open_files); 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; out_release: kmem_cache_free(files_cachep, newf); out: return NULL; } 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 = xchg(&fdt->fd[i], NULL); 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; unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / 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 (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 (fd >= end) goto out; error = expand_files(files, fd); if (error < 0) goto out; /* * If we needed to expand the fs array we * might have blocked - try again. */ if (error) goto repeat; if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); error = fd; #if 1 /* Sanity check */ if (rcu_access_pointer(fdt->fd[fd]) != NULL) { printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd); rcu_assign_pointer(fdt->fd[fd], NULL); } #endif 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; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); BUG_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); /** * pick_file - return file associatd with fd * @files: file struct to retrieve file from * @fd: file descriptor to retrieve file for * * Context: files_lock must be held. * * Returns: The file associated with @fd (NULL if @fd is not open) */ static struct file *pick_file(struct files_struct *files, unsigned fd) { struct fdtable *fdt = files_fdtable(files); struct file *file; if (fd >= fdt->max_fds) return NULL; 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 = pick_file(files, fd); spin_unlock(&files->file_lock); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(close_fd); /* for ksys_close() */ /** * last_fd - return last valid index into fd table * @cur_fds: files struct * * 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 *cur_fds, unsigned int fd, unsigned int max_fd) { unsigned n; rcu_read_lock(); n = last_fd(files_fdtable(cur_fds)); rcu_read_unlock(); max_fd = min(max_fd, n); while (fd <= max_fd) { struct file *file; spin_lock(&cur_fds->file_lock); file = pick_file(cur_fds, fd++); spin_unlock(&cur_fds->file_lock); if (file) { /* found a valid file to close */ filp_close(file, cur_fds); cond_resched(); } } } /** * __close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. */ int __close_range(unsigned fd, unsigned 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) { int ret; unsigned int max_unshare_fds = NR_OPEN_MAX; /* * 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)) { /* * If the requested range is greater than the current * maximum, we're closing everything so only copy all * file descriptors beneath the lowest file descriptor. */ rcu_read_lock(); if (max_fd >= last_fd(files_fdtable(cur_fds))) max_unshare_fds = fd; rcu_read_unlock(); } ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds); if (ret) return ret; /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ if (fds) 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; } /* * See close_fd_get_file() below, this variant assumes current->files->file_lock * is held. */ struct file *__close_fd_get_file(unsigned int fd) { return pick_file(current->files, fd); } /* * variant of close_fd that gets a ref on the file for later fput. * The caller must ensure that filp_close() called on the file. */ struct file *close_fd_get_file(unsigned int fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = pick_file(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 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; if (unlikely(fd >= fdt->max_fds)) return NULL; fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds); file = rcu_dereference_raw(*fdentry); if (unlikely(!file)) return NULL; if (unlikely(file->f_mode & mask)) return NULL; /* * Ok, we have a file pointer. However, because we do * this all locklessly under RCU, we may be racing with * that file being closed. * * Such a race can take two forms: * * (a) the file ref already went down to zero, * and get_file_rcu() fails. Just try again: */ if (unlikely(!get_file_rcu(file))) continue; /* * (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(rcu_dereference_raw(files->fdt) != fdt) || unlikely(rcu_dereference_raw(*fdentry) != file)) { fput(file); continue; } /* * 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 *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; struct file *file = NULL; task_lock(task); files = task->files; if (files) file = files_lookup_fd_rcu(files, fd); task_unlock(task); return file; } struct file *task_lookup_next_fd_rcu(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) { for (; fd < files_fdtable(files)->max_fds; fd++) { file = files_lookup_fd_rcu(files, fd); if (file) break; } } task_unlock(task); *ret_fd = fd; return file; } EXPORT_SYMBOL(task_lookup_next_fd_rcu); /* * 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. */ static unsigned long __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 (atomic_read_acquire(&files->count) == 1) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return 0; return (unsigned long)file; } else { file = __fget(fd, mask); if (!file) return 0; return FDPUT_FPUT | (unsigned long)file; } } unsigned long __fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(__fdget); unsigned long __fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } unsigned long __fdget_pos(unsigned int fd) { unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); if (file && (file->f_mode & FMODE_ATOMIC_POS)) { if (file_count(file) > 1) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } } return v; } 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; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (flag) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { struct files_struct *files = current->files; struct fdtable *fdt; bool res; rcu_read_lock(); fdt = files_fdtable(files); res = close_on_exec(fd, fdt); 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); 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); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); 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; } 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; } int receive_fd(struct file *file, unsigned int o_flags) { return __receive_fd(file, NULL, o_flags); } EXPORT_SYMBOL_GPL(receive_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; int retval = oldfd; rcu_read_lock(); if (!files_lookup_fd_rcu(files, oldfd)) retval = -EBADF; rcu_read_unlock(); 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); |
| 4 4 4 36 36 36 36 1 35 35 35 35 35 35 4 4 24 24 24 24 24 24 24 24 24 24 24 2 2 2 1 1 2 2 2 2 2 2 2 2 1 1 1 2 2 2 4 4 4 4 4 37 38 38 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mac80211 configuration hooks for cfg80211 * * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH * Copyright (C) 2018-2022 Intel Corporation */ #include <linux/ieee80211.h> #include <linux/nl80211.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <linux/rcupdate.h> #include <linux/fips.h> #include <linux/if_ether.h> #include <net/cfg80211.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "rate.h" #include "mesh.h" #include "wme.h" static struct ieee80211_link_data * ieee80211_link_or_deflink(struct ieee80211_sub_if_data *sdata, int link_id, bool require_valid) { struct ieee80211_link_data *link; if (link_id < 0) { /* * For keys, if sdata is not an MLD, we might not use * the return value at all (if it's not a pairwise key), * so in that case (require_valid==false) don't error. */ if (require_valid && sdata->vif.valid_links) return ERR_PTR(-EINVAL); return &sdata->deflink; } link = sdata_dereference(sdata->link[link_id], sdata); if (!link) return ERR_PTR(-ENOLINK); return link; } static void ieee80211_set_mu_mimo_follow(struct ieee80211_sub_if_data *sdata, struct vif_params *params) { bool mu_mimo_groups = false; bool mu_mimo_follow = false; if (params->vht_mumimo_groups) { u64 membership; BUILD_BUG_ON(sizeof(membership) != WLAN_MEMBERSHIP_LEN); memcpy(sdata->vif.bss_conf.mu_group.membership, params->vht_mumimo_groups, WLAN_MEMBERSHIP_LEN); memcpy(sdata->vif.bss_conf.mu_group.position, params->vht_mumimo_groups + WLAN_MEMBERSHIP_LEN, WLAN_USER_POSITION_LEN); ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_MU_GROUPS); /* don't care about endianness - just check for 0 */ memcpy(&membership, params->vht_mumimo_groups, WLAN_MEMBERSHIP_LEN); mu_mimo_groups = membership != 0; } if (params->vht_mumimo_follow_addr) { mu_mimo_follow = is_valid_ether_addr(params->vht_mumimo_follow_addr); ether_addr_copy(sdata->u.mntr.mu_follow_addr, params->vht_mumimo_follow_addr); } sdata->vif.bss_conf.mu_mimo_owner = mu_mimo_groups || mu_mimo_follow; } static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, struct vif_params *params) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *monitor_sdata; /* check flags first */ if (params->flags && ieee80211_sdata_running(sdata)) { u32 mask = MONITOR_FLAG_COOK_FRAMES | MONITOR_FLAG_ACTIVE; /* * Prohibit MONITOR_FLAG_COOK_FRAMES and * MONITOR_FLAG_ACTIVE to be changed while the * interface is up. * Else we would need to add a lot of cruft * to update everything: * cooked_mntrs, monitor and all fif_* counters * reconfigure hardware */ if ((params->flags & mask) != (sdata->u.mntr.flags & mask)) return -EBUSY; } /* also validate MU-MIMO change */ monitor_sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (!monitor_sdata && (params->vht_mumimo_groups || params->vht_mumimo_follow_addr)) return -EOPNOTSUPP; /* apply all changes now - no failures allowed */ if (monitor_sdata) ieee80211_set_mu_mimo_follow(monitor_sdata, params); if (params->flags) { if (ieee80211_sdata_running(sdata)) { ieee80211_adjust_monitor_flags(sdata, -1); sdata->u.mntr.flags = params->flags; ieee80211_adjust_monitor_flags(sdata, 1); ieee80211_configure_filter(local); } else { /* * Because the interface is down, ieee80211_do_stop * and ieee80211_do_open take care of "everything" * mentioned in the comment above. */ sdata->u.mntr.flags = params->flags; } } return 0; } static int ieee80211_set_ap_mbssid_options(struct ieee80211_sub_if_data *sdata, struct cfg80211_mbssid_config params, struct ieee80211_bss_conf *link_conf) { struct ieee80211_sub_if_data *tx_sdata; sdata->vif.mbssid_tx_vif = NULL; link_conf->bssid_index = 0; link_conf->nontransmitted = false; link_conf->ema_ap = false; if (sdata->vif.type != NL80211_IFTYPE_AP || !params.tx_wdev) return -EINVAL; tx_sdata = IEEE80211_WDEV_TO_SUB_IF(params.tx_wdev); if (!tx_sdata) return -EINVAL; if (tx_sdata == sdata) { sdata->vif.mbssid_tx_vif = &sdata->vif; } else { sdata->vif.mbssid_tx_vif = &tx_sdata->vif; link_conf->nontransmitted = true; link_conf->bssid_index = params.index; } if (params.ema) link_conf->ema_ap = true; return 0; } static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy, const char *name, unsigned char name_assign_type, enum nl80211_iftype type, struct vif_params *params) { struct ieee80211_local *local = wiphy_priv(wiphy); struct wireless_dev *wdev; struct ieee80211_sub_if_data *sdata; int err; err = ieee80211_if_add(local, name, name_assign_type, &wdev, type, params); if (err) return ERR_PTR(err); sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (type == NL80211_IFTYPE_MONITOR) { err = ieee80211_set_mon_options(sdata, params); if (err) { ieee80211_if_remove(sdata); return NULL; } } return wdev; } static int ieee80211_del_iface(struct wiphy *wiphy, struct wireless_dev *wdev) { ieee80211_if_remove(IEEE80211_WDEV_TO_SUB_IF(wdev)); return 0; } static int ieee80211_change_iface(struct wiphy *wiphy, struct net_device *dev, enum nl80211_iftype type, struct vif_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta; int ret; ret = ieee80211_if_change_type(sdata, type); if (ret) return ret; if (type == NL80211_IFTYPE_AP_VLAN && params->use_4addr == 0) { RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); ieee80211_check_fast_rx_iface(sdata); } else if (type == NL80211_IFTYPE_STATION && params->use_4addr >= 0) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; if (params->use_4addr == ifmgd->use_4addr) return 0; /* FIXME: no support for 4-addr MLO yet */ if (sdata->vif.valid_links) return -EOPNOTSUPP; sdata->u.mgd.use_4addr = params->use_4addr; if (!ifmgd->associated) return 0; mutex_lock(&local->sta_mtx); sta = sta_info_get(sdata, sdata->deflink.u.mgd.bssid); if (sta) drv_sta_set_4addr(local, sdata, &sta->sta, params->use_4addr); mutex_unlock(&local->sta_mtx); if (params->use_4addr) ieee80211_send_4addr_nullfunc(local, sdata); } if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { ret = ieee80211_set_mon_options(sdata, params); if (ret) return ret; } return 0; } static int ieee80211_start_p2p_device(struct wiphy *wiphy, struct wireless_dev *wdev) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); int ret; mutex_lock(&sdata->local->chanctx_mtx); ret = ieee80211_check_combinations(sdata, NULL, 0, 0); mutex_unlock(&sdata->local->chanctx_mtx); if (ret < 0) return ret; return ieee80211_do_open(wdev, true); } static void ieee80211_stop_p2p_device(struct wiphy *wiphy, struct wireless_dev *wdev) { ieee80211_sdata_stop(IEEE80211_WDEV_TO_SUB_IF(wdev)); } static int ieee80211_start_nan(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); int ret; mutex_lock(&sdata->local->chanctx_mtx); ret = ieee80211_check_combinations(sdata, NULL, 0, 0); mutex_unlock(&sdata->local->chanctx_mtx); if (ret < 0) return ret; ret = ieee80211_do_open(wdev, true); if (ret) return ret; ret = drv_start_nan(sdata->local, sdata, conf); if (ret) ieee80211_sdata_stop(sdata); sdata->u.nan.conf = *conf; return ret; } static void ieee80211_stop_nan(struct wiphy *wiphy, struct wireless_dev *wdev) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); drv_stop_nan(sdata->local, sdata); ieee80211_sdata_stop(sdata); } static int ieee80211_nan_change_conf(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf, u32 changes) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct cfg80211_nan_conf new_conf; int ret = 0; if (sdata->vif.type != NL80211_IFTYPE_NAN) return -EOPNOTSUPP; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; new_conf = sdata->u.nan.conf; if (changes & CFG80211_NAN_CONF_CHANGED_PREF) new_conf.master_pref = conf->master_pref; if (changes & CFG80211_NAN_CONF_CHANGED_BANDS) new_conf.bands = conf->bands; ret = drv_nan_change_conf(sdata->local, sdata, &new_conf, changes); if (!ret) sdata->u.nan.conf = new_conf; return ret; } static int ieee80211_add_nan_func(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_func *nan_func) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); int ret; if (sdata->vif.type != NL80211_IFTYPE_NAN) return -EOPNOTSUPP; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; spin_lock_bh(&sdata->u.nan.func_lock); ret = idr_alloc(&sdata->u.nan.function_inst_ids, nan_func, 1, sdata->local->hw.max_nan_de_entries + 1, GFP_ATOMIC); spin_unlock_bh(&sdata->u.nan.func_lock); if (ret < 0) return ret; nan_func->instance_id = ret; WARN_ON(nan_func->instance_id == 0); ret = drv_add_nan_func(sdata->local, sdata, nan_func); if (ret) { spin_lock_bh(&sdata->u.nan.func_lock); idr_remove(&sdata->u.nan.function_inst_ids, nan_func->instance_id); spin_unlock_bh(&sdata->u.nan.func_lock); } return ret; } static struct cfg80211_nan_func * ieee80211_find_nan_func_by_cookie(struct ieee80211_sub_if_data *sdata, u64 cookie) { struct cfg80211_nan_func *func; int id; lockdep_assert_held(&sdata->u.nan.func_lock); idr_for_each_entry(&sdata->u.nan.function_inst_ids, func, id) { if (func->cookie == cookie) return func; } return NULL; } static void ieee80211_del_nan_func(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct cfg80211_nan_func *func; u8 instance_id = 0; if (sdata->vif.type != NL80211_IFTYPE_NAN || !ieee80211_sdata_running(sdata)) return; spin_lock_bh(&sdata->u.nan.func_lock); func = ieee80211_find_nan_func_by_cookie(sdata, cookie); if (func) instance_id = func->instance_id; spin_unlock_bh(&sdata->u.nan.func_lock); if (instance_id) drv_del_nan_func(sdata->local, sdata, instance_id); } static int ieee80211_set_noack_map(struct wiphy *wiphy, struct net_device *dev, u16 noack_map) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); sdata->noack_map = noack_map; ieee80211_check_fast_xmit_iface(sdata); return 0; } static int ieee80211_set_tx(struct ieee80211_sub_if_data *sdata, const u8 *mac_addr, u8 key_idx) { struct ieee80211_local *local = sdata->local; struct ieee80211_key *key; struct sta_info *sta; int ret = -EINVAL; if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_EXT_KEY_ID)) return -EINVAL; sta = sta_info_get_bss(sdata, mac_addr); if (!sta) return -EINVAL; if (sta->ptk_idx == key_idx) return 0; mutex_lock(&local->key_mtx); key = key_mtx_dereference(local, sta->ptk[key_idx]); if (key && key->conf.flags & IEEE80211_KEY_FLAG_NO_AUTO_TX) ret = ieee80211_set_tx_key(key); mutex_unlock(&local->key_mtx); return ret; } static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr, struct key_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, false); struct ieee80211_local *local = sdata->local; struct sta_info *sta = NULL; struct ieee80211_key *key; int err; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; if (IS_ERR(link)) return PTR_ERR(link); if (pairwise && params->mode == NL80211_KEY_SET_TX) return ieee80211_set_tx(sdata, mac_addr, key_idx); /* reject WEP and TKIP keys if WEP failed to initialize */ switch (params->cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_WEP104: if (link_id >= 0) return -EINVAL; if (WARN_ON_ONCE(fips_enabled)) return -EINVAL; break; default: break; } key = ieee80211_key_alloc(params->cipher, key_idx, params->key_len, params->key, params->seq_len, params->seq); if (IS_ERR(key)) return PTR_ERR(key); key->conf.link_id = link_id; if (pairwise) key->conf.flags |= IEEE80211_KEY_FLAG_PAIRWISE; if (params->mode == NL80211_KEY_NO_TX) key->conf.flags |= IEEE80211_KEY_FLAG_NO_AUTO_TX; mutex_lock(&local->sta_mtx); if (mac_addr) { sta = sta_info_get_bss(sdata, mac_addr); /* * The ASSOC test makes sure the driver is ready to * receive the key. When wpa_supplicant has roamed * using FT, it attempts to set the key before * association has completed, this rejects that attempt * so it will set the key again after association. * * TODO: accept the key if we have a station entry and * add it to the device after the station. */ if (!sta || !test_sta_flag(sta, WLAN_STA_ASSOC)) { ieee80211_key_free_unused(key); err = -ENOENT; goto out_unlock; } } switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: if (sdata->u.mgd.mfp != IEEE80211_MFP_DISABLED) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: /* Keys without a station are used for TX only */ if (sta && test_sta_flag(sta, WLAN_STA_MFP)) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; case NL80211_IFTYPE_ADHOC: /* no MFP (yet) */ break; case NL80211_IFTYPE_MESH_POINT: #ifdef CONFIG_MAC80211_MESH if (sdata->u.mesh.security != IEEE80211_MESH_SEC_NONE) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; #endif case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_NAN: case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_OCB: /* shouldn't happen */ WARN_ON_ONCE(1); break; } err = ieee80211_key_link(key, link, sta); out_unlock: mutex_unlock(&local->sta_mtx); return err; } static struct ieee80211_key * ieee80211_lookup_key(struct ieee80211_sub_if_data *sdata, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr) { struct ieee80211_local *local = sdata->local; struct ieee80211_link_data *link = &sdata->deflink; struct ieee80211_key *key; if (link_id >= 0) { link = rcu_dereference_check(sdata->link[link_id], lockdep_is_held(&sdata->wdev.mtx)); if (!link) return NULL; } if (mac_addr) { struct sta_info *sta; struct link_sta_info *link_sta; sta = sta_info_get_bss(sdata, mac_addr); if (!sta) return NULL; if (link_id >= 0) { link_sta = rcu_dereference_check(sta->link[link_id], lockdep_is_held(&local->sta_mtx)); if (!link_sta) return NULL; } else { link_sta = &sta->deflink; } if (pairwise && key_idx < NUM_DEFAULT_KEYS) return rcu_dereference_check_key_mtx(local, sta->ptk[key_idx]); if (!pairwise && key_idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + NUM_DEFAULT_BEACON_KEYS) return rcu_dereference_check_key_mtx(local, link_sta->gtk[key_idx]); return NULL; } if (pairwise && key_idx < NUM_DEFAULT_KEYS) return rcu_dereference_check_key_mtx(local, sdata->keys[key_idx]); key = rcu_dereference_check_key_mtx(local, link->gtk[key_idx]); if (key) return key; /* or maybe it was a WEP key */ if (key_idx < NUM_DEFAULT_KEYS) return rcu_dereference_check_key_mtx(local, sdata->keys[key_idx]); return NULL; } static int ieee80211_del_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct ieee80211_key *key; int ret; mutex_lock(&local->sta_mtx); mutex_lock(&local->key_mtx); key = ieee80211_lookup_key(sdata, link_id, key_idx, pairwise, mac_addr); if (!key) { ret = -ENOENT; goto out_unlock; } ieee80211_key_free(key, sdata->vif.type == NL80211_IFTYPE_STATION); ret = 0; out_unlock: mutex_unlock(&local->key_mtx); mutex_unlock(&local->sta_mtx); return ret; } static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr, void *cookie, void (*callback)(void *cookie, struct key_params *params)) { struct ieee80211_sub_if_data *sdata; u8 seq[6] = {0}; struct key_params params; struct ieee80211_key *key; u64 pn64; u32 iv32; u16 iv16; int err = -ENOENT; struct ieee80211_key_seq kseq = {}; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); key = ieee80211_lookup_key(sdata, link_id, key_idx, pairwise, mac_addr); if (!key) goto out; memset(¶ms, 0, sizeof(params)); params.cipher = key->conf.cipher; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: pn64 = atomic64_read(&key->conf.tx_pn); iv32 = TKIP_PN_TO_IV32(pn64); iv16 = TKIP_PN_TO_IV16(pn64); if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { drv_get_key_seq(sdata->local, key, &kseq); iv32 = kseq.tkip.iv32; iv16 = kseq.tkip.iv16; } seq[0] = iv16 & 0xff; seq[1] = (iv16 >> 8) & 0xff; seq[2] = iv32 & 0xff; seq[3] = (iv32 >> 8) & 0xff; seq[4] = (iv32 >> 16) & 0xff; seq[5] = (iv32 >> 24) & 0xff; params.seq = seq; params.seq_len = 6; break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), aes_cmac)); fallthrough; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), aes_gmac)); fallthrough; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), gcmp)); if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { drv_get_key_seq(sdata->local, key, &kseq); memcpy(seq, kseq.ccmp.pn, 6); } else { pn64 = atomic64_read(&key->conf.tx_pn); seq[0] = pn64; seq[1] = pn64 >> 8; seq[2] = pn64 >> 16; seq[3] = pn64 >> 24; seq[4] = pn64 >> 32; seq[5] = pn64 >> 40; } params.seq = seq; params.seq_len = 6; break; default: if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) break; if (WARN_ON(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) break; drv_get_key_seq(sdata->local, key, &kseq); params.seq = kseq.hw.seq; params.seq_len = kseq.hw.seq_len; break; } params.key = key->conf.key; params.key_len = key->conf.keylen; callback(cookie, ¶ms); err = 0; out: rcu_read_unlock(); return err; } static int ieee80211_config_default_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool uni, bool multi) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, false); if (IS_ERR(link)) return PTR_ERR(link); ieee80211_set_default_key(link, key_idx, uni, multi); return 0; } static int ieee80211_config_default_mgmt_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, true); if (IS_ERR(link)) return PTR_ERR(link); ieee80211_set_default_mgmt_key(link, key_idx); return 0; } static int ieee80211_config_default_beacon_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, true); if (IS_ERR(link)) return PTR_ERR(link); ieee80211_set_default_beacon_key(link, key_idx); return 0; } void sta_set_rate_info_tx(struct sta_info *sta, const struct ieee80211_tx_rate *rate, struct rate_info *rinfo) { rinfo->flags = 0; if (rate->flags & IEEE80211_TX_RC_MCS) { rinfo->flags |= RATE_INFO_FLAGS_MCS; rinfo->mcs = rate->idx; } else if (rate->flags & IEEE80211_TX_RC_VHT_MCS) { rinfo->flags |= RATE_INFO_FLAGS_VHT_MCS; rinfo->mcs = ieee80211_rate_get_vht_mcs(rate); rinfo->nss = ieee80211_rate_get_vht_nss(rate); } else { struct ieee80211_supported_band *sband; int shift = ieee80211_vif_get_shift(&sta->sdata->vif); u16 brate; sband = ieee80211_get_sband(sta->sdata); WARN_ON_ONCE(sband && !sband->bitrates); if (sband && sband->bitrates) { brate = sband->bitrates[rate->idx].bitrate; rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift); } } if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) rinfo->bw = RATE_INFO_BW_40; else if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) rinfo->bw = RATE_INFO_BW_80; else if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH) rinfo->bw = RATE_INFO_BW_160; else rinfo->bw = RATE_INFO_BW_20; if (rate->flags & IEEE80211_TX_RC_SHORT_GI) rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI; } static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *mac, struct station_info *sinfo) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta; int ret = -ENOENT; mutex_lock(&local->sta_mtx); sta = sta_info_get_by_idx(sdata, idx); if (sta) { ret = 0; memcpy(mac, sta->sta.addr, ETH_ALEN); sta_set_sinfo(sta, sinfo, true); } mutex_unlock(&local->sta_mtx); return ret; } static int ieee80211_dump_survey(struct wiphy *wiphy, struct net_device *dev, int idx, struct survey_info *survey) { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); return drv_get_survey(local, idx, survey); } static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev, const u8 *mac, struct station_info *sinfo) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta; int ret = -ENOENT; mutex_lock(&local->sta_mtx); sta = sta_info_get_bss(sdata, mac); if (sta) { ret = 0; sta_set_sinfo(sta, sinfo, true); } mutex_unlock(&local->sta_mtx); return ret; } static int ieee80211_set_monitor_channel(struct wiphy *wiphy, struct cfg80211_chan_def *chandef) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; int ret = 0; if (cfg80211_chandef_identical(&local->monitor_chandef, chandef)) return 0; mutex_lock(&local->mtx); if (local->use_chanctx) { sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (sdata) { ieee80211_link_release_channel(&sdata->deflink); ret = ieee80211_link_use_channel(&sdata->deflink, chandef, IEEE80211_CHANCTX_EXCLUSIVE); } } else if (local->open_count == local->monitors) { local->_oper_chandef = *chandef; ieee80211_hw_config(local, 0); } if (ret == 0) local->monitor_chandef = *chandef; mutex_unlock(&local->mtx); return ret; } static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, const u8 *resp, size_t resp_len, const struct ieee80211_csa_settings *csa, const struct ieee80211_color_change_settings *cca, struct ieee80211_link_data *link) { struct probe_resp *new, *old; if (!resp || !resp_len) return 1; old = sdata_dereference(link->u.ap.probe_resp, sdata); new = kzalloc(sizeof(struct probe_resp) + resp_len, GFP_KERNEL); if (!new) return -ENOMEM; new->len = resp_len; memcpy(new->data, resp, resp_len); if (csa) memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_presp, csa->n_counter_offsets_presp * sizeof(new->cntdwn_counter_offsets[0])); else if (cca) new->cntdwn_counter_offsets[0] = cca->counter_offset_presp; rcu_assign_pointer(link->u.ap.probe_resp, new); if (old) kfree_rcu(old, rcu_head); return 0; } static int ieee80211_set_fils_discovery(struct ieee80211_sub_if_data *sdata, struct cfg80211_fils_discovery *params, struct ieee80211_link_data *link, struct ieee80211_bss_conf *link_conf) { struct fils_discovery_data *new, *old = NULL; struct ieee80211_fils_discovery *fd; if (!params->tmpl || !params->tmpl_len) return -EINVAL; fd = &link_conf->fils_discovery; fd->min_interval = params->min_interval; fd->max_interval = params->max_interval; old = sdata_dereference(link->u.ap.fils_discovery, sdata); new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL); if (!new) return -ENOMEM; new->len = params->tmpl_len; memcpy(new->data, params->tmpl, params->tmpl_len); rcu_assign_pointer(link->u.ap.fils_discovery, new); if (old) kfree_rcu(old, rcu_head); return 0; } static int ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata, struct cfg80211_unsol_bcast_probe_resp *params, struct ieee80211_link_data *link, struct ieee80211_bss_conf *link_conf) { struct unsol_bcast_probe_resp_data *new, *old = NULL; if (!params->tmpl || !params->tmpl_len) return -EINVAL; old = sdata_dereference(link->u.ap.unsol_bcast_probe_resp, sdata); new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL); if (!new) return -ENOMEM; new->len = params->tmpl_len; memcpy(new->data, params->tmpl, params->tmpl_len); rcu_assign_pointer(link->u.ap.unsol_bcast_probe_resp, new); if (old) kfree_rcu(old, rcu_head); link_conf->unsol_bcast_probe_resp_interval = params->interval; return 0; } static int ieee80211_set_ftm_responder_params( struct ieee80211_sub_if_data *sdata, const u8 *lci, size_t lci_len, const u8 *civicloc, size_t civicloc_len, struct ieee80211_bss_conf *link_conf) { struct ieee80211_ftm_responder_params *new, *old; u8 *pos; int len; if (!lci_len && !civicloc_len) return 0; old = link_conf->ftmr_params; len = lci_len + civicloc_len; new = kzalloc(sizeof(*new) + len, GFP_KERNEL); if (!new) return -ENOMEM; pos = (u8 *)(new + 1); if (lci_len) { new->lci_len = lci_len; new->lci = pos; memcpy(pos, lci, lci_len); pos += lci_len; } if (civicloc_len) { new->civicloc_len = civicloc_len; new->civicloc = pos; memcpy(pos, civicloc, civicloc_len); pos += civicloc_len; } link_conf->ftmr_params = new; kfree(old); return 0; } static int ieee80211_copy_mbssid_beacon(u8 *pos, struct cfg80211_mbssid_elems *dst, struct cfg80211_mbssid_elems *src) { int i, offset = 0; for (i = 0; i < src->cnt; i++) { memcpy(pos + offset, src->elem[i].data, src->elem[i].len); dst->elem[i].len = src->elem[i].len; dst->elem[i].data = pos + offset; offset += dst->elem[i].len; } dst->cnt = src->cnt; return offset; } static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, struct cfg80211_beacon_data *params, const struct ieee80211_csa_settings *csa, const struct ieee80211_color_change_settings *cca) { struct cfg80211_mbssid_elems *mbssid = NULL; struct beacon_data *new, *old; int new_head_len, new_tail_len; int size, err; u32 changed = BSS_CHANGED_BEACON; struct ieee80211_bss_conf *link_conf = link->conf; old = sdata_dereference(link->u.ap.beacon, sdata); /* Need to have a beacon head if we don't have one yet */ if (!params->head && !old) return -EINVAL; /* new or old head? */ if (params->head) new_head_len = params->head_len; else new_head_len = old->head_len; /* new or old tail? */ if (params->tail || !old) /* params->tail_len will be zero for !params->tail */ new_tail_len = params->tail_len; else new_tail_len = old->tail_len; size = sizeof(*new) + new_head_len + new_tail_len; /* new or old multiple BSSID elements? */ if (params->mbssid_ies) { mbssid = params->mbssid_ies; size += struct_size(new->mbssid_ies, elem, mbssid->cnt); size += ieee80211_get_mbssid_beacon_len(mbssid); } else if (old && old->mbssid_ies) { mbssid = old->mbssid_ies; size += struct_size(new->mbssid_ies, elem, mbssid->cnt); size += ieee80211_get_mbssid_beacon_len(mbssid); } new = kzalloc(size, GFP_KERNEL); if (!new) return -ENOMEM; /* start filling the new info now */ /* * pointers go into the block we allocated, * memory is | beacon_data | head | tail | mbssid_ies */ new->head = ((u8 *) new) + sizeof(*new); new->tail = new->head + new_head_len; new->head_len = new_head_len; new->tail_len = new_tail_len; /* copy in optional mbssid_ies */ if (mbssid) { u8 *pos = new->tail + new->tail_len; new->mbssid_ies = (void *)pos; pos += struct_size(new->mbssid_ies, elem, mbssid->cnt); ieee80211_copy_mbssid_beacon(pos, new->mbssid_ies, mbssid); /* update bssid_indicator */ link_conf->bssid_indicator = ilog2(__roundup_pow_of_two(mbssid->cnt + 1)); } if (csa) { new->cntdwn_current_counter = csa->count; memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_beacon, csa->n_counter_offsets_beacon * sizeof(new->cntdwn_counter_offsets[0])); } else if (cca) { new->cntdwn_current_counter = cca->count; new->cntdwn_counter_offsets[0] = cca->counter_offset_beacon; } /* copy in head */ if (params->head) memcpy(new->head, params->head, new_head_len); else memcpy(new->head, old->head, new_head_len); /* copy in optional tail */ if (params->tail) memcpy(new->tail, params->tail, new_tail_len); else if (old) memcpy(new->tail, old->tail, new_tail_len); err = ieee80211_set_probe_resp(sdata, params->probe_resp, params->probe_resp_len, csa, cca, link); if (err < 0) { kfree(new); return err; } if (err == 0) changed |= BSS_CHANGED_AP_PROBE_RESP; if (params->ftm_responder != -1) { link_conf->ftm_responder = params->ftm_responder; err = ieee80211_set_ftm_responder_params(sdata, params->lci, params->lci_len, params->civicloc, params->civicloc_len, link_conf); if (err < 0) { kfree(new); return err; } changed |= BSS_CHANGED_FTM_RESPONDER; } rcu_assign_pointer(link->u.ap.beacon, new); sdata->u.ap.active = true; if (old) kfree_rcu(old, rcu_head); return changed; } static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ap_settings *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct beacon_data *old; struct ieee80211_sub_if_data *vlan; u32 changed = BSS_CHANGED_BEACON_INT | BSS_CHANGED_BEACON_ENABLED | BSS_CHANGED_BEACON | BSS_CHANGED_P2P_PS | BSS_CHANGED_TXPOWER | BSS_CHANGED_TWT; int i, err; int prev_beacon_int; unsigned int link_id = params->beacon.link_id; struct ieee80211_link_data *link; struct ieee80211_bss_conf *link_conf; link = sdata_dereference(sdata->link[link_id], sdata); if (!link) return -ENOLINK; link_conf = link->conf; old = sdata_dereference(link->u.ap.beacon, sdata); if (old) return -EALREADY; if (params->smps_mode != NL80211_SMPS_OFF) return -ENOTSUPP; link->smps_mode = IEEE80211_SMPS_OFF; link->needed_rx_chains = sdata->local->rx_chains; prev_beacon_int = link_conf->beacon_int; link_conf->beacon_int = params->beacon_interval; if (params->he_cap && params->he_oper) { link_conf->he_support = true; link_conf->htc_trig_based_pkt_ext = le32_get_bits(params->he_oper->he_oper_params, IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK); link_conf->frame_time_rts_th = le32_get_bits(params->he_oper->he_oper_params, IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK); changed |= BSS_CHANGED_HE_OBSS_PD; if (params->beacon.he_bss_color.enabled) changed |= BSS_CHANGED_HE_BSS_COLOR; } if (sdata->vif.type == NL80211_IFTYPE_AP && params->mbssid_config.tx_wdev) { err = ieee80211_set_ap_mbssid_options(sdata, params->mbssid_config, link_conf); if (err) return err; } mutex_lock(&local->mtx); err = ieee80211_link_use_channel(link, ¶ms->chandef, IEEE80211_CHANCTX_SHARED); if (!err) ieee80211_link_copy_chanctx_to_vlans(link, false); mutex_unlock(&local->mtx); if (err) { link_conf->beacon_int = prev_beacon_int; return err; } /* * Apply control port protocol, this allows us to * not encrypt dynamic WEP control frames. */ sdata->control_port_protocol = params->crypto.control_port_ethertype; sdata->control_port_no_encrypt = params->crypto.control_port_no_encrypt; sdata->control_port_over_nl80211 = params->crypto.control_port_over_nl80211; sdata->control_port_no_preauth = params->crypto.control_port_no_preauth; list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) { vlan->control_port_protocol = params->crypto.control_port_ethertype; vlan->control_port_no_encrypt = params->crypto.control_port_no_encrypt; vlan->control_port_over_nl80211 = params->crypto.control_port_over_nl80211; vlan->control_port_no_preauth = params->crypto.control_port_no_preauth; } link_conf->dtim_period = params->dtim_period; link_conf->enable_beacon = true; link_conf->allow_p2p_go_ps = sdata->vif.p2p; link_conf->twt_responder = params->twt_responder; link_conf->he_obss_pd = params->he_obss_pd; link_conf->he_bss_color = params->beacon.he_bss_color; sdata->vif.cfg.s1g = params->chandef.chan->band == NL80211_BAND_S1GHZ; sdata->vif.cfg.ssid_len = params->ssid_len; if (params->ssid_len) memcpy(sdata->vif.cfg.ssid, params->ssid, params->ssid_len); link_conf->hidden_ssid = (params->hidden_ssid != NL80211_HIDDEN_SSID_NOT_IN_USE); memset(&link_conf->p2p_noa_attr, 0, sizeof(link_conf->p2p_noa_attr)); link_conf->p2p_noa_attr.oppps_ctwindow = params->p2p_ctwindow & IEEE80211_P2P_OPPPS_CTWINDOW_MASK; if (params->p2p_opp_ps) link_conf->p2p_noa_attr.oppps_ctwindow |= IEEE80211_P2P_OPPPS_ENABLE_BIT; sdata->beacon_rate_set = false; if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_BEACON_RATE_LEGACY)) { for (i = 0; i < NUM_NL80211_BANDS; i++) { sdata->beacon_rateidx_mask[i] = params->beacon_rate.control[i].legacy; if (sdata->beacon_rateidx_mask[i]) sdata->beacon_rate_set = true; } } if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) link_conf->beacon_tx_rate = params->beacon_rate; err = ieee80211_assign_beacon(sdata, link, ¶ms->beacon, NULL, NULL); if (err < 0) goto error; changed |= err; if (params->fils_discovery.max_interval) { err = ieee80211_set_fils_discovery(sdata, ¶ms->fils_discovery, link, link_conf); if (err < 0) goto error; changed |= BSS_CHANGED_FILS_DISCOVERY; } if (params->unsol_bcast_probe_resp.interval) { err = ieee80211_set_unsol_bcast_probe_resp(sdata, ¶ms->unsol_bcast_probe_resp, link, link_conf); if (err < 0) goto error; changed |= BSS_CHANGED_UNSOL_BCAST_PROBE_RESP; } err = drv_start_ap(sdata->local, sdata, link_conf); if (err) { old = sdata_dereference(link->u.ap.beacon, sdata); if (old) kfree_rcu(old, rcu_head); RCU_INIT_POINTER(link->u.ap.beacon, NULL); sdata->u.ap.active = false; goto error; } ieee80211_recalc_dtim(local, sdata); ieee80211_vif_cfg_change_notify(sdata, BSS_CHANGED_SSID); ieee80211_link_info_change_notify(sdata, link, changed); netif_carrier_on(dev); list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) netif_carrier_on(vlan->dev); return 0; error: mutex_lock(&local->mtx); ieee80211_link_release_channel(link); mutex_unlock(&local->mtx); return err; } static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_beacon_data *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link; struct beacon_data *old; int err; struct ieee80211_bss_conf *link_conf; sdata_assert_lock(sdata); link = sdata_dereference(sdata->link[params->link_id], sdata); if (!link) return -ENOLINK; link_conf = link->conf; /* don't allow changing the beacon while a countdown is in place - offset * of channel switch counter may change */ if (link_conf->csa_active || link_conf->color_change_active) return -EBUSY; old = sdata_dereference(link->u.ap.beacon, sdata); if (!old) return -ENOENT; err = ieee80211_assign_beacon(sdata, link, params, NULL, NULL); if (err < 0) return err; if (params->he_bss_color_valid && params->he_bss_color.enabled != link_conf->he_bss_color.enabled) { link_conf->he_bss_color.enabled = params->he_bss_color.enabled; err |= BSS_CHANGED_HE_BSS_COLOR; } ieee80211_link_info_change_notify(sdata, link, err); return 0; } static void ieee80211_free_next_beacon(struct ieee80211_link_data *link) { if (!link->u.ap.next_beacon) return; kfree(link->u.ap.next_beacon->mbssid_ies); kfree(link->u.ap.next_beacon); link->u.ap.next_beacon = NULL; } static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_sub_if_data *vlan; struct ieee80211_local *local = sdata->local; struct beacon_data *old_beacon; struct probe_resp *old_probe_resp; struct fils_discovery_data *old_fils_discovery; struct unsol_bcast_probe_resp_data *old_unsol_bcast_probe_resp; struct cfg80211_chan_def chandef; struct ieee80211_link_data *link = sdata_dereference(sdata->link[link_id], sdata); struct ieee80211_bss_conf *link_conf = link->conf; sdata_assert_lock(sdata); old_beacon = sdata_dereference(link->u.ap.beacon, sdata); if (!old_beacon) return -ENOENT; old_probe_resp = sdata_dereference(link->u.ap.probe_resp, sdata); old_fils_discovery = sdata_dereference(link->u.ap.fils_discovery, sdata); old_unsol_bcast_probe_resp = sdata_dereference(link->u.ap.unsol_bcast_probe_resp, sdata); /* abort any running channel switch */ mutex_lock(&local->mtx); link_conf->csa_active = false; if (link->csa_block_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); link->csa_block_tx = false; } mutex_unlock(&local->mtx); ieee80211_free_next_beacon(link); /* turn off carrier for this interface and dependent VLANs */ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) netif_carrier_off(vlan->dev); netif_carrier_off(dev); /* remove beacon and probe response */ sdata->u.ap.active = false; RCU_INIT_POINTER(link->u.ap.beacon, NULL); RCU_INIT_POINTER(link->u.ap.probe_resp, NULL); RCU_INIT_POINTER(link->u.ap.fils_discovery, NULL); RCU_INIT_POINTER(link->u.ap.unsol_bcast_probe_resp, NULL); kfree_rcu(old_beacon, rcu_head); if (old_probe_resp) kfree_rcu(old_probe_resp, rcu_head); if (old_fils_discovery) kfree_rcu(old_fils_discovery, rcu_head); if (old_unsol_bcast_probe_resp) kfree_rcu(old_unsol_bcast_probe_resp, rcu_head); kfree(link_conf->ftmr_params); link_conf->ftmr_params = NULL; __sta_info_flush(sdata, true); ieee80211_free_keys(sdata, true); link_conf->enable_beacon = false; sdata->beacon_rate_set = false; sdata->vif.cfg.ssid_len = 0; clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state); ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_BEACON_ENABLED); if (sdata->wdev.cac_started) { chandef = link_conf->chandef; cancel_delayed_work_sync(&link->dfs_cac_timer_work); cfg80211_cac_event(sdata->dev, &chandef, NL80211_RADAR_CAC_ABORTED, GFP_KERNEL); } drv_stop_ap(sdata->local, sdata, link_conf); /* free all potentially still buffered bcast frames */ local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps.bc_buf); ieee80211_purge_tx_queue(&local->hw, &sdata->u.ap.ps.bc_buf); mutex_lock(&local->mtx); ieee80211_link_copy_chanctx_to_vlans(link, true); ieee80211_link_release_channel(link); mutex_unlock(&local->mtx); return 0; } static int sta_apply_auth_flags(struct ieee80211_local *local, struct sta_info *sta, u32 mask, u32 set) { int ret; if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED) && set & BIT(NL80211_STA_FLAG_AUTHENTICATED) && !test_sta_flag(sta, WLAN_STA_AUTH)) { ret = sta_info_move_state(sta, IEEE80211_STA_AUTH); if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_ASSOCIATED) && set & BIT(NL80211_STA_FLAG_ASSOCIATED) && !test_sta_flag(sta, WLAN_STA_ASSOC)) { /* * When peer becomes associated, init rate control as * well. Some drivers require rate control initialized * before drv_sta_state() is called. */ if (!test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) rate_control_rate_init(sta); ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_AUTHORIZED)) { if (set & BIT(NL80211_STA_FLAG_AUTHORIZED)) ret = sta_info_move_state(sta, IEEE80211_STA_AUTHORIZED); else if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); else ret = 0; if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_ASSOCIATED) && !(set & BIT(NL80211_STA_FLAG_ASSOCIATED)) && test_sta_flag(sta, WLAN_STA_ASSOC)) { ret = sta_info_move_state(sta, IEEE80211_STA_AUTH); if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED) && !(set & BIT(NL80211_STA_FLAG_AUTHENTICATED)) && test_sta_flag(sta, WLAN_STA_AUTH)) { ret = sta_info_move_state(sta, IEEE80211_STA_NONE); if (ret) return ret; } return 0; } static void sta_apply_mesh_params(struct ieee80211_local *local, struct sta_info *sta, struct station_parameters *params) { #ifdef CONFIG_MAC80211_MESH struct ieee80211_sub_if_data *sdata = sta->sdata; u32 changed = 0; if (params->sta_modify_mask & STATION_PARAM_APPLY_PLINK_STATE) { switch (params->plink_state) { case NL80211_PLINK_ESTAB: if (sta->mesh->plink_state != NL80211_PLINK_ESTAB) changed = mesh_plink_inc_estab_count(sdata); sta->mesh->plink_state = params->plink_state; sta->mesh->aid = params->peer_aid; ieee80211_mps_sta_status_update(sta); changed |= ieee80211_mps_set_sta_local_pm(sta, sdata->u.mesh.mshcfg.power_mode); ewma_mesh_tx_rate_avg_init(&sta->mesh->tx_rate_avg); /* init at low value */ ewma_mesh_tx_rate_avg_add(&sta->mesh->tx_rate_avg, 10); break; case NL80211_PLINK_LISTEN: case NL80211_PLINK_BLOCKED: case NL80211_PLINK_OPN_SNT: case NL80211_PLINK_OPN_RCVD: case NL80211_PLINK_CNF_RCVD: case NL80211_PLINK_HOLDING: if (sta->mesh->plink_state == NL80211_PLINK_ESTAB) changed = mesh_plink_dec_estab_count(sdata); sta->mesh->plink_state = params->plink_state; ieee80211_mps_sta_status_update(sta); changed |= ieee80211_mps_set_sta_local_pm(sta, NL80211_MESH_POWER_UNKNOWN); break; default: /* nothing */ break; } } switch (params->plink_action) { case NL80211_PLINK_ACTION_NO_ACTION: /* nothing */ break; case NL80211_PLINK_ACTION_OPEN: changed |= mesh_plink_open(sta); break; case NL80211_PLINK_ACTION_BLOCK: changed |= mesh_plink_block(sta); break; } if (params->local_pm) changed |= ieee80211_mps_set_sta_local_pm(sta, params->local_pm); ieee80211_mbss_info_change_notify(sdata, changed); #endif } static int sta_link_apply_parameters(struct ieee80211_local *local, struct sta_info *sta, bool new_link, struct link_station_parameters *params) { int ret = 0; struct ieee80211_supported_band *sband; struct ieee80211_sub_if_data *sdata = sta->sdata; u32 link_id = params->link_id < 0 ? 0 : params->link_id; struct ieee80211_link_data *link = sdata_dereference(sdata->link[link_id], sdata); struct link_sta_info *link_sta = rcu_dereference_protected(sta->link[link_id], lockdep_is_held(&local->sta_mtx)); /* * If there are no changes, then accept a link that doesn't exist, * unless it's a new link. */ if (params->link_id < 0 && !new_link && !params->link_mac && !params->txpwr_set && !params->supported_rates_len && !params->ht_capa && !params->vht_capa && !params->he_capa && !params->eht_capa && !params->opmode_notif_used) return 0; if (!link || !link_sta) return -EINVAL; sband = ieee80211_get_link_sband(link); if (!sband) return -EINVAL; if (params->link_mac) { if (new_link) { memcpy(link_sta->addr, params->link_mac, ETH_ALEN); memcpy(link_sta->pub->addr, params->link_mac, ETH_ALEN); } else if (!ether_addr_equal(link_sta->addr, params->link_mac)) { return -EINVAL; } } else if (new_link) { return -EINVAL; } if (params->txpwr_set) { link_sta->pub->txpwr.type = params->txpwr.type; if (params->txpwr.type == NL80211_TX_POWER_LIMITED) link_sta->pub->txpwr.power = params->txpwr.power; ret = drv_sta_set_txpwr(local, sdata, sta); if (ret) return ret; } if (params->supported_rates && params->supported_rates_len) { ieee80211_parse_bitrates(link->conf->chandef.width, sband, params->supported_rates, params->supported_rates_len, &link_sta->pub->supp_rates[sband->band]); } if (params->ht_capa) ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, params->ht_capa, link_sta); /* VHT can override some HT caps such as the A-MSDU max length */ if (params->vht_capa) ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, params->vht_capa, link_sta); if (params->he_capa) ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, (void *)params->he_capa, params->he_capa_len, (void *)params->he_6ghz_capa, link_sta); if (params->eht_capa) ieee80211_eht_cap_ie_to_sta_eht_cap(sdata, sband, (u8 *)params->he_capa, params->he_capa_len, params->eht_capa, params->eht_capa_len, link_sta); if (params->opmode_notif_used) { /* returned value is only needed for rc update, but the * rc isn't initialized here yet, so ignore it */ __ieee80211_vht_handle_opmode(sdata, link_sta, params->opmode_notif, sband->band); } return ret; } static int sta_apply_parameters(struct ieee80211_local *local, struct sta_info *sta, struct station_parameters *params) { struct ieee80211_sub_if_data *sdata = sta->sdata; u32 mask, set; int ret = 0; mask = params->sta_flags_mask; set = params->sta_flags_set; if (ieee80211_vif_is_mesh(&sdata->vif)) { /* * In mesh mode, ASSOCIATED isn't part of the nl80211 * API but must follow AUTHENTICATED for driver state. */ if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED)) mask |= BIT(NL80211_STA_FLAG_ASSOCIATED); if (set & BIT(NL80211_STA_FLAG_AUTHENTICATED)) set |= BIT(NL80211_STA_FLAG_ASSOCIATED); } else if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { /* * TDLS -- everything follows authorized, but * only becoming authorized is possible, not * going back */ if (set & BIT(NL80211_STA_FLAG_AUTHORIZED)) { set |= BIT(NL80211_STA_FLAG_AUTHENTICATED) | BIT(NL80211_STA_FLAG_ASSOCIATED); mask |= BIT(NL80211_STA_FLAG_AUTHENTICATED) | BIT(NL80211_STA_FLAG_ASSOCIATED); } } if (mask & BIT(NL80211_STA_FLAG_WME) && local->hw.queues >= IEEE80211_NUM_ACS) sta->sta.wme = set & BIT(NL80211_STA_FLAG_WME); /* auth flags will be set later for TDLS, * and for unassociated stations that move to associated */ if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER) && !((mask & BIT(NL80211_STA_FLAG_ASSOCIATED)) && (set & BIT(NL80211_STA_FLAG_ASSOCIATED)))) { ret = sta_apply_auth_flags(local, sta, mask, set); if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) { if (set & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) set_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE); else clear_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE); } if (mask & BIT(NL80211_STA_FLAG_MFP)) { sta->sta.mfp = !!(set & BIT(NL80211_STA_FLAG_MFP)); if (set & BIT(NL80211_STA_FLAG_MFP)) set_sta_flag(sta, WLAN_STA_MFP); else clear_sta_flag(sta, WLAN_STA_MFP); } if (mask & BIT(NL80211_STA_FLAG_TDLS_PEER)) { if (set & BIT(NL80211_STA_FLAG_TDLS_PEER)) set_sta_flag(sta, WLAN_STA_TDLS_PEER); else clear_sta_flag(sta, WLAN_STA_TDLS_PEER); } /* mark TDLS channel switch support, if the AP allows it */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && !sdata->deflink.u.mgd.tdls_chan_switch_prohibited && params->ext_capab_len >= 4 && params->ext_capab[3] & WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH) set_sta_flag(sta, WLAN_STA_TDLS_CHAN_SWITCH); if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && !sdata->u.mgd.tdls_wider_bw_prohibited && ieee80211_hw_check(&local->hw, TDLS_WIDER_BW) && params->ext_capab_len >= 8 && params->ext_capab[7] & WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED) set_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW); if (params->sta_modify_mask & STATION_PARAM_APPLY_UAPSD) { sta->sta.uapsd_queues = params->uapsd_queues; sta->sta.max_sp = params->max_sp; } ieee80211_sta_set_max_amsdu_subframes(sta, params->ext_capab, params->ext_capab_len); /* * cfg80211 validates this (1-2007) and allows setting the AID * only when creating a new station entry */ if (params->aid) sta->sta.aid = params->aid; /* * Some of the following updates would be racy if called on an * existing station, via ieee80211_change_station(). However, * all such changes are rejected by cfg80211 except for updates * changing the supported rates on an existing but not yet used * TDLS peer. */ if (params->listen_interval >= 0) sta->listen_interval = params->listen_interval; ret = sta_link_apply_parameters(local, sta, false, ¶ms->link_sta_params); if (ret) return ret; if (params->support_p2p_ps >= 0) sta->sta.support_p2p_ps = params->support_p2p_ps; if (ieee80211_vif_is_mesh(&sdata->vif)) sta_apply_mesh_params(local, sta, params); if (params->airtime_weight) sta->airtime_weight = params->airtime_weight; /* set the STA state after all sta info from usermode has been set */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) || set & BIT(NL80211_STA_FLAG_ASSOCIATED)) { ret = sta_apply_auth_flags(local, sta, mask, set); if (ret) return ret; } /* Mark the STA as MLO if MLD MAC address is available */ if (params->link_sta_params.mld_mac) sta->sta.mlo = true; return 0; } static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, const u8 *mac, struct station_parameters *params) { struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; struct ieee80211_sub_if_data *sdata; int err; if (params->vlan) { sdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN && sdata->vif.type != NL80211_IFTYPE_AP) return -EINVAL; } else sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (ether_addr_equal(mac, sdata->vif.addr)) return -EINVAL; if (!is_valid_ether_addr(mac)) return -EINVAL; if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER) && sdata->vif.type == NL80211_IFTYPE_STATION && !sdata->u.mgd.associated) return -EINVAL; /* * If we have a link ID, it can be a non-MLO station on an AP MLD, * but we need to have a link_mac in that case as well, so use the * STA's MAC address in that case. */ if (params->link_sta_params.link_id >= 0) sta = sta_info_alloc_with_link(sdata, mac, params->link_sta_params.link_id, params->link_sta_params.link_mac ?: mac, GFP_KERNEL); else sta = sta_info_alloc(sdata, mac, GFP_KERNEL); if (!sta) return -ENOMEM; if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) sta->sta.tdls = true; /* Though the mutex is not needed here (since the station is not * visible yet), sta_apply_parameters (and inner functions) require * the mutex due to other paths. */ mutex_lock(&local->sta_mtx); err = sta_apply_parameters(local, sta, params); mutex_unlock(&local->sta_mtx); if (err) { sta_info_free(local, sta); return err; } /* * for TDLS and for unassociated station, rate control should be * initialized only when rates are known and station is marked * authorized/associated */ if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER) && test_sta_flag(sta, WLAN_STA_ASSOC)) rate_control_rate_init(sta); return sta_info_insert(sta); } static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev, struct station_del_parameters *params) { struct ieee80211_sub_if_data *sdata; sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (params->mac) return sta_info_destroy_addr_bss(sdata, params->mac); sta_info_flush(sdata); return 0; } static int ieee80211_change_station(struct wiphy *wiphy, struct net_device *dev, const u8 *mac, struct station_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; struct ieee80211_sub_if_data *vlansdata; enum cfg80211_station_type statype; int err; mutex_lock(&local->sta_mtx); sta = sta_info_get_bss(sdata, mac); if (!sta) { err = -ENOENT; goto out_err; } switch (sdata->vif.type) { case NL80211_IFTYPE_MESH_POINT: if (sdata->u.mesh.user_mpm) statype = CFG80211_STA_MESH_PEER_USER; else statype = CFG80211_STA_MESH_PEER_KERNEL; break; case NL80211_IFTYPE_ADHOC: statype = CFG80211_STA_IBSS; break; case NL80211_IFTYPE_STATION: if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { statype = CFG80211_STA_AP_STA; break; } if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) statype = CFG80211_STA_TDLS_PEER_ACTIVE; else statype = CFG80211_STA_TDLS_PEER_SETUP; break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: if (test_sta_flag(sta, WLAN_STA_ASSOC)) statype = CFG80211_STA_AP_CLIENT; else statype = CFG80211_STA_AP_CLIENT_UNASSOC; break; default: err = -EOPNOTSUPP; goto out_err; } err = cfg80211_check_station_change(wiphy, params, statype); if (err) goto out_err; if (params->vlan && params->vlan != sta->sdata->dev) { vlansdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); if (params->vlan->ieee80211_ptr->use_4addr) { if (vlansdata->u.vlan.sta) { err = -EBUSY; goto out_err; } rcu_assign_pointer(vlansdata->u.vlan.sta, sta); __ieee80211_check_fast_rx_iface(vlansdata); drv_sta_set_4addr(local, sta->sdata, &sta->sta, true); } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && sta->sdata->u.vlan.sta) { ieee80211_clear_fast_rx(sta); RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL); } if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ieee80211_vif_dec_num_mcast(sta->sdata); sta->sdata = vlansdata; ieee80211_check_fast_xmit(sta); if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { ieee80211_vif_inc_num_mcast(sta->sdata); cfg80211_send_layer2_update(sta->sdata->dev, sta->sta.addr); } } /* we use sta_info_get_bss() so this might be different */ if (sdata != sta->sdata) { mutex_lock_nested(&sta->sdata->wdev.mtx, 1); err = sta_apply_parameters(local, sta, params); mutex_unlock(&sta->sdata->wdev.mtx); } else { err = sta_apply_parameters(local, sta, params); } if (err) goto out_err; mutex_unlock(&local->sta_mtx); if (sdata->vif.type == NL80211_IFTYPE_STATION && params->sta_flags_mask & BIT(NL80211_STA_FLAG_AUTHORIZED)) { ieee80211_recalc_ps(local); ieee80211_recalc_ps_vif(sdata); } return 0; out_err: mutex_unlock(&local->sta_mtx); return err; } #ifdef CONFIG_MAC80211_MESH static int ieee80211_add_mpath(struct wiphy *wiphy, struct net_device *dev, const u8 *dst, const u8 *next_hop) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; struct sta_info *sta; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); sta = sta_info_get(sdata, next_hop); if (!sta) { rcu_read_unlock(); return -ENOENT; } mpath = mesh_path_add(sdata, dst); if (IS_ERR(mpath)) { rcu_read_unlock(); return PTR_ERR(mpath); } mesh_path_fix_nexthop(mpath, sta); rcu_read_unlock(); return 0; } static int ieee80211_del_mpath(struct wiphy *wiphy, struct net_device *dev, const u8 *dst) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (dst) return mesh_path_del(sdata, dst); mesh_path_flush_by_iface(sdata); return 0; } static int ieee80211_change_mpath(struct wiphy *wiphy, struct net_device *dev, const u8 *dst, const u8 *next_hop) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; struct sta_info *sta; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); sta = sta_info_get(sdata, next_hop); if (!sta) { rcu_read_unlock(); return -ENOENT; } mpath = mesh_path_lookup(sdata, dst); if (!mpath) { rcu_read_unlock(); return -ENOENT; } mesh_path_fix_nexthop(mpath, sta); rcu_read_unlock(); return 0; } static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, struct mpath_info *pinfo) { struct sta_info *next_hop_sta = rcu_dereference(mpath->next_hop); if (next_hop_sta) memcpy(next_hop, next_hop_sta->sta.addr, ETH_ALEN); else eth_zero_addr(next_hop); memset(pinfo, 0, sizeof(*pinfo)); pinfo->generation = mpath->sdata->u.mesh.mesh_paths_generation; pinfo->filled = MPATH_INFO_FRAME_QLEN | MPATH_INFO_SN | MPATH_INFO_METRIC | MPATH_INFO_EXPTIME | MPATH_INFO_DISCOVERY_TIMEOUT | MPATH_INFO_DISCOVERY_RETRIES | MPATH_INFO_FLAGS | MPATH_INFO_HOP_COUNT | MPATH_INFO_PATH_CHANGE; pinfo->frame_qlen = mpath->frame_queue.qlen; pinfo->sn = mpath->sn; pinfo->metric = mpath->metric; if (time_before(jiffies, mpath->exp_time)) pinfo->exptime = jiffies_to_msecs(mpath->exp_time - jiffies); pinfo->discovery_timeout = jiffies_to_msecs(mpath->discovery_timeout); pinfo->discovery_retries = mpath->discovery_retries; if (mpath->flags & MESH_PATH_ACTIVE) pinfo->flags |= NL80211_MPATH_FLAG_ACTIVE; if (mpath->flags & MESH_PATH_RESOLVING) pinfo->flags |= NL80211_MPATH_FLAG_RESOLVING; if (mpath->flags & MESH_PATH_SN_VALID) pinfo->flags |= NL80211_MPATH_FLAG_SN_VALID; if (mpath->flags & MESH_PATH_FIXED) pinfo->flags |= NL80211_MPATH_FLAG_FIXED; if (mpath->flags & MESH_PATH_RESOLVED) pinfo->flags |= NL80211_MPATH_FLAG_RESOLVED; pinfo->hop_count = mpath->hop_count; pinfo->path_change_count = mpath->path_change_count; } static int ieee80211_get_mpath(struct wiphy *wiphy, struct net_device *dev, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); mpath = mesh_path_lookup(sdata, dst); if (!mpath) { rcu_read_unlock(); return -ENOENT; } memcpy(dst, mpath->dst, ETH_ALEN); mpath_set_pinfo(mpath, next_hop, pinfo); rcu_read_unlock(); return 0; } static int ieee80211_dump_mpath(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); mpath = mesh_path_lookup_by_idx(sdata, idx); if (!mpath) { rcu_read_unlock(); return -ENOENT; } memcpy(dst, mpath->dst, ETH_ALEN); mpath_set_pinfo(mpath, next_hop, pinfo); rcu_read_unlock(); return 0; } static void mpp_set_pinfo(struct mesh_path *mpath, u8 *mpp, struct mpath_info *pinfo) { memset(pinfo, 0, sizeof(*pinfo)); memcpy(mpp, mpath->mpp, ETH_ALEN); pinfo->generation = mpath->sdata->u.mesh.mpp_paths_generation; } static int ieee80211_get_mpp(struct wiphy *wiphy, struct net_device *dev, u8 *dst, u8 *mpp, struct mpath_info *pinfo) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); mpath = mpp_path_lookup(sdata, dst); if (!mpath) { rcu_read_unlock(); return -ENOENT; } memcpy(dst, mpath->dst, ETH_ALEN); mpp_set_pinfo(mpath, mpp, pinfo); rcu_read_unlock(); return 0; } static int ieee80211_dump_mpp(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *dst, u8 *mpp, struct mpath_info *pinfo) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); mpath = mpp_path_lookup_by_idx(sdata, idx); if (!mpath) { rcu_read_unlock(); return -ENOENT; } memcpy(dst, mpath->dst, ETH_ALEN); mpp_set_pinfo(mpath, mpp, pinfo); rcu_read_unlock(); return 0; } static int ieee80211_get_mesh_config(struct wiphy *wiphy, struct net_device *dev, struct mesh_config *conf) { struct ieee80211_sub_if_data *sdata; sdata = IEEE80211_DEV_TO_SUB_IF(dev); memcpy(conf, &(sdata->u.mesh.mshcfg), sizeof(struct mesh_config)); return 0; } static inline bool _chg_mesh_attr(enum nl80211_meshconf_params parm, u32 mask) { return (mask >> (parm-1)) & 0x1; } static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh, const struct mesh_setup *setup) { u8 *new_ie; struct ieee80211_sub_if_data *sdata = container_of(ifmsh, struct ieee80211_sub_if_data, u.mesh); int i; /* allocate information elements */ new_ie = NULL; if (setup->ie_len) { new_ie = kmemdup(setup->ie, setup->ie_len, GFP_KERNEL); if (!new_ie) return -ENOMEM; } ifmsh->ie_len = setup->ie_len; ifmsh->ie = new_ie; /* now copy the rest of the setup parameters */ ifmsh->mesh_id_len = setup->mesh_id_len; memcpy(ifmsh->mesh_id, setup->mesh_id, ifmsh->mesh_id_len); ifmsh->mesh_sp_id = setup->sync_method; ifmsh->mesh_pp_id = setup->path_sel_proto; ifmsh->mesh_pm_id = setup->path_metric; ifmsh->user_mpm = setup->user_mpm; ifmsh->mesh_auth_id = setup->auth_id; ifmsh->security = IEEE80211_MESH_SEC_NONE; ifmsh->userspace_handles_dfs = setup->userspace_handles_dfs; if (setup->is_authenticated) ifmsh->security |= IEEE80211_MESH_SEC_AUTHED; if (setup->is_secure) ifmsh->security |= IEEE80211_MESH_SEC_SECURED; /* mcast rate setting in Mesh Node */ memcpy(sdata->vif.bss_conf.mcast_rate, setup->mcast_rate, sizeof(setup->mcast_rate)); sdata->vif.bss_conf.basic_rates = setup->basic_rates; sdata->vif.bss_conf.beacon_int = setup->beacon_interval; sdata->vif.bss_conf.dtim_period = setup->dtim_period; sdata->beacon_rate_set = false; if (wiphy_ext_feature_isset(sdata->local->hw.wiphy, NL80211_EXT_FEATURE_BEACON_RATE_LEGACY)) { for (i = 0; i < NUM_NL80211_BANDS; i++) { sdata->beacon_rateidx_mask[i] = setup->beacon_rate.control[i].legacy; if (sdata->beacon_rateidx_mask[i]) sdata->beacon_rate_set = true; } } return 0; } static int ieee80211_update_mesh_config(struct wiphy *wiphy, struct net_device *dev, u32 mask, const struct mesh_config *nconf) { struct mesh_config *conf; struct ieee80211_sub_if_data *sdata; struct ieee80211_if_mesh *ifmsh; sdata = IEEE80211_DEV_TO_SUB_IF(dev); ifmsh = &sdata->u.mesh; /* Set the config options which we are interested in setting */ conf = &(sdata->u.mesh.mshcfg); if (_chg_mesh_attr(NL80211_MESHCONF_RETRY_TIMEOUT, mask)) conf->dot11MeshRetryTimeout = nconf->dot11MeshRetryTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_CONFIRM_TIMEOUT, mask)) conf->dot11MeshConfirmTimeout = nconf->dot11MeshConfirmTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_HOLDING_TIMEOUT, mask)) conf->dot11MeshHoldingTimeout = nconf->dot11MeshHoldingTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_MAX_PEER_LINKS, mask)) conf->dot11MeshMaxPeerLinks = nconf->dot11MeshMaxPeerLinks; if (_chg_mesh_attr(NL80211_MESHCONF_MAX_RETRIES, mask)) conf->dot11MeshMaxRetries = nconf->dot11MeshMaxRetries; if (_chg_mesh_attr(NL80211_MESHCONF_TTL, mask)) conf->dot11MeshTTL = nconf->dot11MeshTTL; if (_chg_mesh_attr(NL80211_MESHCONF_ELEMENT_TTL, mask)) conf->element_ttl = nconf->element_ttl; if (_chg_mesh_attr(NL80211_MESHCONF_AUTO_OPEN_PLINKS, mask)) { if (ifmsh->user_mpm) return -EBUSY; conf->auto_open_plinks = nconf->auto_open_plinks; } if (_chg_mesh_attr(NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, mask)) conf->dot11MeshNbrOffsetMaxNeighbor = nconf->dot11MeshNbrOffsetMaxNeighbor; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, mask)) conf->dot11MeshHWMPmaxPREQretries = nconf->dot11MeshHWMPmaxPREQretries; if (_chg_mesh_attr(NL80211_MESHCONF_PATH_REFRESH_TIME, mask)) conf->path_refresh_time = nconf->path_refresh_time; if (_chg_mesh_attr(NL80211_MESHCONF_MIN_DISCOVERY_TIMEOUT, mask)) conf->min_discovery_timeout = nconf->min_discovery_timeout; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_ACTIVE_PATH_TIMEOUT, mask)) conf->dot11MeshHWMPactivePathTimeout = nconf->dot11MeshHWMPactivePathTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL, mask)) conf->dot11MeshHWMPpreqMinInterval = nconf->dot11MeshHWMPpreqMinInterval; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_PERR_MIN_INTERVAL, mask)) conf->dot11MeshHWMPperrMinInterval = nconf->dot11MeshHWMPperrMinInterval; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME, mask)) conf->dot11MeshHWMPnetDiameterTraversalTime = nconf->dot11MeshHWMPnetDiameterTraversalTime; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_ROOTMODE, mask)) { conf->dot11MeshHWMPRootMode = nconf->dot11MeshHWMPRootMode; ieee80211_mesh_root_setup(ifmsh); } if (_chg_mesh_attr(NL80211_MESHCONF_GATE_ANNOUNCEMENTS, mask)) { /* our current gate announcement implementation rides on root * announcements, so require this ifmsh to also be a root node * */ if (nconf->dot11MeshGateAnnouncementProtocol && !(conf->dot11MeshHWMPRootMode > IEEE80211_ROOTMODE_ROOT)) { conf->dot11MeshHWMPRootMode = IEEE80211_PROACTIVE_RANN; ieee80211_mesh_root_setup(ifmsh); } conf->dot11MeshGateAnnouncementProtocol = nconf->dot11MeshGateAnnouncementProtocol; } if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_RANN_INTERVAL, mask)) conf->dot11MeshHWMPRannInterval = nconf->dot11MeshHWMPRannInterval; if (_chg_mesh_attr(NL80211_MESHCONF_FORWARDING, mask)) conf->dot11MeshForwarding = nconf->dot11MeshForwarding; if (_chg_mesh_attr(NL80211_MESHCONF_RSSI_THRESHOLD, mask)) { /* our RSSI threshold implementation is supported only for * devices that report signal in dBm. */ if (!ieee80211_hw_check(&sdata->local->hw, SIGNAL_DBM)) return -ENOTSUPP; conf->rssi_threshold = nconf->rssi_threshold; } if (_chg_mesh_attr(NL80211_MESHCONF_HT_OPMODE, mask)) { conf->ht_opmode = nconf->ht_opmode; sdata->vif.bss_conf.ht_operation_mode = nconf->ht_opmode; ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_HT); } if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, mask)) conf->dot11MeshHWMPactivePathToRootTimeout = nconf->dot11MeshHWMPactivePathToRootTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_ROOT_INTERVAL, mask)) conf->dot11MeshHWMProotInterval = nconf->dot11MeshHWMProotInterval; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL, mask)) conf->dot11MeshHWMPconfirmationInterval = nconf->dot11MeshHWMPconfirmationInterval; if (_chg_mesh_attr(NL80211_MESHCONF_POWER_MODE, mask)) { conf->power_mode = nconf->power_mode; ieee80211_mps_local_status_update(sdata); } if (_chg_mesh_attr(NL80211_MESHCONF_AWAKE_WINDOW, mask)) conf->dot11MeshAwakeWindowDuration = nconf->dot11MeshAwakeWindowDuration; if (_chg_mesh_attr(NL80211_MESHCONF_PLINK_TIMEOUT, mask)) conf->plink_timeout = nconf->plink_timeout; if (_chg_mesh_attr(NL80211_MESHCONF_CONNECTED_TO_GATE, mask)) conf->dot11MeshConnectedToMeshGate = nconf->dot11MeshConnectedToMeshGate; if (_chg_mesh_attr(NL80211_MESHCONF_NOLEARN, mask)) conf->dot11MeshNolearn = nconf->dot11MeshNolearn; if (_chg_mesh_attr(NL80211_MESHCONF_CONNECTED_TO_AS, mask)) conf->dot11MeshConnectedToAuthServer = nconf->dot11MeshConnectedToAuthServer; ieee80211_mbss_info_change_notify(sdata, BSS_CHANGED_BEACON); return 0; } static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev, const struct mesh_config *conf, const struct mesh_setup *setup) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; int err; memcpy(&ifmsh->mshcfg, conf, sizeof(struct mesh_config)); err = copy_mesh_setup(ifmsh, setup); if (err) return err; sdata->control_port_over_nl80211 = setup->control_port_over_nl80211; /* can mesh use other SMPS modes? */ sdata->deflink.smps_mode = IEEE80211_SMPS_OFF; sdata->deflink.needed_rx_chains = sdata->local->rx_chains; mutex_lock(&sdata->local->mtx); err = ieee80211_link_use_channel(&sdata->deflink, &setup->chandef, IEEE80211_CHANCTX_SHARED); mutex_unlock(&sdata->local->mtx); if (err) return err; return ieee80211_start_mesh(sdata); } static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); ieee80211_stop_mesh(sdata); mutex_lock(&sdata->local->mtx); ieee80211_link_release_channel(&sdata->deflink); kfree(sdata->u.mesh.ie); mutex_unlock(&sdata->local->mtx); return 0; } #endif static int ieee80211_change_bss(struct wiphy *wiphy, struct net_device *dev, struct bss_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_supported_band *sband; u32 changed = 0; if (!sdata_dereference(sdata->deflink.u.ap.beacon, sdata)) return -ENOENT; sband = ieee80211_get_sband(sdata); if (!sband) return -EINVAL; if (params->use_cts_prot >= 0) { sdata->vif.bss_conf.use_cts_prot = params->use_cts_prot; changed |= BSS_CHANGED_ERP_CTS_PROT; } if (params->use_short_preamble >= 0) { sdata->vif.bss_conf.use_short_preamble = params->use_short_preamble; changed |= BSS_CHANGED_ERP_PREAMBLE; } if (!sdata->vif.bss_conf.use_short_slot && (sband->band == NL80211_BAND_5GHZ || sband->band == NL80211_BAND_6GHZ)) { sdata->vif.bss_conf.use_short_slot = true; changed |= BSS_CHANGED_ERP_SLOT; } if (params->use_short_slot_time >= 0) { sdata->vif.bss_conf.use_short_slot = params->use_short_slot_time; changed |= BSS_CHANGED_ERP_SLOT; } if (params->basic_rates) { ieee80211_parse_bitrates(sdata->vif.bss_conf.chandef.width, wiphy->bands[sband->band], params->basic_rates, params->basic_rates_len, &sdata->vif.bss_conf.basic_rates); changed |= BSS_CHANGED_BASIC_RATES; ieee80211_check_rate_mask(&sdata->deflink); } if (params->ap_isolate >= 0) { if (params->ap_isolate) sdata->flags |= IEEE80211_SDATA_DONT_BRIDGE_PACKETS; else sdata->flags &= ~IEEE80211_SDATA_DONT_BRIDGE_PACKETS; ieee80211_check_fast_rx_iface(sdata); } if (params->ht_opmode >= 0) { sdata->vif.bss_conf.ht_operation_mode = (u16) params->ht_opmode; changed |= BSS_CHANGED_HT; } if (params->p2p_ctwindow >= 0) { sdata->vif.bss_conf.p2p_noa_attr.oppps_ctwindow &= ~IEEE80211_P2P_OPPPS_CTWINDOW_MASK; sdata->vif.bss_conf.p2p_noa_attr.oppps_ctwindow |= params->p2p_ctwindow & IEEE80211_P2P_OPPPS_CTWINDOW_MASK; changed |= BSS_CHANGED_P2P_PS; } if (params->p2p_opp_ps > 0) { sdata->vif.bss_conf.p2p_noa_attr.oppps_ctwindow |= IEEE80211_P2P_OPPPS_ENABLE_BIT; changed |= BSS_CHANGED_P2P_PS; } else if (params->p2p_opp_ps == 0) { sdata->vif.bss_conf.p2p_noa_attr.oppps_ctwindow &= ~IEEE80211_P2P_OPPPS_ENABLE_BIT; changed |= BSS_CHANGED_P2P_PS; } ieee80211_link_info_change_notify(sdata, &sdata->deflink, changed); return 0; } static int ieee80211_set_txq_params(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_txq_params *params) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, params->link_id, true); struct ieee80211_tx_queue_params p; if (!local->ops->conf_tx) return -EOPNOTSUPP; if (local->hw.queues < IEEE80211_NUM_ACS) return -EOPNOTSUPP; if (IS_ERR(link)) return PTR_ERR(link); memset(&p, 0, sizeof(p)); p.aifs = params->aifs; p.cw_max = params->cwmax; p.cw_min = params->cwmin; p.txop = params->txop; /* * Setting tx queue params disables u-apsd because it's only * called in master mode. */ p.uapsd = false; ieee80211_regulatory_limit_wmm_params(sdata, &p, params->ac); link->tx_conf[params->ac] = p; if (drv_conf_tx(local, link, params->ac, &p)) { wiphy_debug(local->hw.wiphy, "failed to set TX queue parameters for AC %d\n", params->ac); return -EINVAL; } ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_QOS); return 0; } #ifdef CONFIG_PM static int ieee80211_suspend(struct wiphy *wiphy, struct cfg80211_wowlan *wowlan) { return __ieee80211_suspend(wiphy_priv(wiphy), wowlan); } static int ieee80211_resume(struct wiphy *wiphy) { return __ieee80211_resume(wiphy_priv(wiphy)); } #else #define ieee80211_suspend NULL #define ieee80211_resume NULL #endif static int ieee80211_scan(struct wiphy *wiphy, struct cfg80211_scan_request *req) { struct ieee80211_sub_if_data *sdata; sdata = IEEE80211_WDEV_TO_SUB_IF(req->wdev); switch (ieee80211_vif_type_p2p(&sdata->vif)) { case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_P2P_DEVICE: break; case NL80211_IFTYPE_P2P_GO: if (sdata->local->ops->hw_scan) break; /* * FIXME: implement NoA while scanning in software, * for now fall through to allow scanning only when * beaconing hasn't been configured yet */ fallthrough; case NL80211_IFTYPE_AP: /* * If the scan has been forced (and the driver supports * forcing), don't care about being beaconing already. * This will create problems to the attached stations (e.g. all * the frames sent while scanning on other channel will be * lost) */ if (sdata->deflink.u.ap.beacon && (!(wiphy->features & NL80211_FEATURE_AP_SCAN) || !(req->flags & NL80211_SCAN_FLAG_AP))) return -EOPNOTSUPP; break; case NL80211_IFTYPE_NAN: default: return -EOPNOTSUPP; } return ieee80211_request_scan(sdata, req); } static void ieee80211_abort_scan(struct wiphy *wiphy, struct wireless_dev *wdev) { ieee80211_scan_cancel(wiphy_priv(wiphy)); } static int ieee80211_sched_scan_start(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_sched_scan_request *req) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (!sdata->local->ops->sched_scan_start) return -EOPNOTSUPP; return ieee80211_request_sched_scan_start(sdata, req); } static int ieee80211_sched_scan_stop(struct wiphy *wiphy, struct net_device *dev, u64 reqid) { struct ieee80211_local *local = wiphy_priv(wiphy); if (!local->ops->sched_scan_stop) return -EOPNOTSUPP; return ieee80211_request_sched_scan_stop(local); } static int ieee80211_auth(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_auth_request *req) { return ieee80211_mgd_auth(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_assoc(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_assoc_request *req) { return ieee80211_mgd_assoc(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_deauth(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_deauth_request *req) { return ieee80211_mgd_deauth(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_disassoc(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_disassoc_request *req) { return ieee80211_mgd_disassoc(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_join_ibss(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ibss_params *params) { return ieee80211_ibss_join(IEEE80211_DEV_TO_SUB_IF(dev), params); } static int ieee80211_leave_ibss(struct wiphy *wiphy, struct net_device *dev) { return ieee80211_ibss_leave(IEEE80211_DEV_TO_SUB_IF(dev)); } static int ieee80211_join_ocb(struct wiphy *wiphy, struct net_device *dev, struct ocb_setup *setup) { return ieee80211_ocb_join(IEEE80211_DEV_TO_SUB_IF(dev), setup); } static int ieee80211_leave_ocb(struct wiphy *wiphy, struct net_device *dev) { return ieee80211_ocb_leave(IEEE80211_DEV_TO_SUB_IF(dev)); } static int ieee80211_set_mcast_rate(struct wiphy *wiphy, struct net_device *dev, int rate[NUM_NL80211_BANDS]) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); memcpy(sdata->vif.bss_conf.mcast_rate, rate, sizeof(int) * NUM_NL80211_BANDS); ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_MCAST_RATE); return 0; } static int ieee80211_set_wiphy_params(struct wiphy *wiphy, u32 changed) { struct ieee80211_local *local = wiphy_priv(wiphy); int err; if (changed & WIPHY_PARAM_FRAG_THRESHOLD) { ieee80211_check_fast_xmit_all(local); err = drv_set_frag_threshold(local, wiphy->frag_threshold); if (err) { ieee80211_check_fast_xmit_all(local); return err; } } if ((changed & WIPHY_PARAM_COVERAGE_CLASS) || (changed & WIPHY_PARAM_DYN_ACK)) { s16 coverage_class; coverage_class = changed & WIPHY_PARAM_COVERAGE_CLASS ? wiphy->coverage_class : -1; err = drv_set_coverage_class(local, coverage_class); if (err) return err; } if (changed & WIPHY_PARAM_RTS_THRESHOLD) { err = drv_set_rts_threshold(local, wiphy->rts_threshold); if (err) return err; } if (changed & WIPHY_PARAM_RETRY_SHORT) { if (wiphy->retry_short > IEEE80211_MAX_TX_RETRY) return -EINVAL; local->hw.conf.short_frame_max_tx_count = wiphy->retry_short; } if (changed & WIPHY_PARAM_RETRY_LONG) { if (wiphy->retry_long > IEEE80211_MAX_TX_RETRY) return -EINVAL; local->hw.conf.long_frame_max_tx_count = wiphy->retry_long; } if (changed & (WIPHY_PARAM_RETRY_SHORT | WIPHY_PARAM_RETRY_LONG)) ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_RETRY_LIMITS); if (changed & (WIPHY_PARAM_TXQ_LIMIT | WIPHY_PARAM_TXQ_MEMORY_LIMIT | WIPHY_PARAM_TXQ_QUANTUM)) ieee80211_txq_set_params(local); return 0; } static int ieee80211_set_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev, enum nl80211_tx_power_setting type, int mbm) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; enum nl80211_tx_power_setting txp_type = type; bool update_txp_type = false; bool has_monitor = false; if (wdev) { sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (!sdata) return -EOPNOTSUPP; } switch (type) { case NL80211_TX_POWER_AUTOMATIC: sdata->deflink.user_power_level = IEEE80211_UNSET_POWER_LEVEL; txp_type = NL80211_TX_POWER_LIMITED; break; case NL80211_TX_POWER_LIMITED: case NL80211_TX_POWER_FIXED: if (mbm < 0 || (mbm % 100)) return -EOPNOTSUPP; sdata->deflink.user_power_level = MBM_TO_DBM(mbm); break; } if (txp_type != sdata->vif.bss_conf.txpower_type) { update_txp_type = true; sdata->vif.bss_conf.txpower_type = txp_type; } ieee80211_recalc_txpower(sdata, update_txp_type); return 0; } switch (type) { case NL80211_TX_POWER_AUTOMATIC: local->user_power_level = IEEE80211_UNSET_POWER_LEVEL; txp_type = NL80211_TX_POWER_LIMITED; break; case NL80211_TX_POWER_LIMITED: case NL80211_TX_POWER_FIXED: if (mbm < 0 || (mbm % 100)) return -EOPNOTSUPP; local->user_power_level = MBM_TO_DBM(mbm); break; } mutex_lock(&local->iflist_mtx); list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { has_monitor = true; continue; } sdata->deflink.user_power_level = local->user_power_level; if (txp_type != sdata->vif.bss_conf.txpower_type) update_txp_type = true; sdata->vif.bss_conf.txpower_type = txp_type; } list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type == NL80211_IFTYPE_MONITOR) continue; ieee80211_recalc_txpower(sdata, update_txp_type); } mutex_unlock(&local->iflist_mtx); if (has_monitor) { sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (sdata) { sdata->deflink.user_power_level = local->user_power_level; if (txp_type != sdata->vif.bss_conf.txpower_type) update_txp_type = true; sdata->vif.bss_conf.txpower_type = txp_type; ieee80211_recalc_txpower(sdata, update_txp_type); } } return 0; } static int ieee80211_get_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev, int *dbm) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (local->ops->get_txpower) return drv_get_txpower(local, sdata, dbm); if (!local->use_chanctx) *dbm = local->hw.conf.power_level; else *dbm = sdata->vif.bss_conf.txpower; return 0; } static void ieee80211_rfkill_poll(struct wiphy *wiphy) { struct ieee80211_local *local = wiphy_priv(wiphy); drv_rfkill_poll(local); } #ifdef CONFIG_NL80211_TESTMODE static int ieee80211_testmode_cmd(struct wiphy *wiphy, struct wireless_dev *wdev, void *data, int len) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_vif *vif = NULL; if (!local->ops->testmode_cmd) return -EOPNOTSUPP; if (wdev) { struct ieee80211_sub_if_data *sdata; sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (sdata->flags & IEEE80211_SDATA_IN_DRIVER) vif = &sdata->vif; } return local->ops->testmode_cmd(&local->hw, vif, data, len); } static int ieee80211_testmode_dump(struct wiphy *wiphy, struct sk_buff *skb, struct netlink_callback *cb, void *data, int len) { struct ieee80211_local *local = wiphy_priv(wiphy); if (!local->ops->testmode_dump) return -EOPNOTSUPP; return local->ops->testmode_dump(&local->hw, skb, cb, data, len); } #endif int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, enum ieee80211_smps_mode smps_mode) { const u8 *ap; enum ieee80211_smps_mode old_req; int err; struct sta_info *sta; bool tdls_peer_found = false; lockdep_assert_held(&sdata->wdev.mtx); if (WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION)) return -EINVAL; old_req = link->u.mgd.req_smps; link->u.mgd.req_smps = smps_mode; if (old_req == smps_mode && smps_mode != IEEE80211_SMPS_AUTOMATIC) return 0; /* * If not associated, or current association is not an HT * association, there's no need to do anything, just store * the new value until we associate. */ if (!sdata->u.mgd.associated || link->conf->chandef.width == NL80211_CHAN_WIDTH_20_NOHT) return 0; ap = link->u.mgd.bssid; rcu_read_lock(); list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { if (!sta->sta.tdls || sta->sdata != sdata || !sta->uploaded || !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) continue; tdls_peer_found = true; break; } rcu_read_unlock(); if (smps_mode == IEEE80211_SMPS_AUTOMATIC) { if (tdls_peer_found || !sdata->u.mgd.powersave) smps_mode = IEEE80211_SMPS_OFF; else smps_mode = IEEE80211_SMPS_DYNAMIC; } /* send SM PS frame to AP */ err = ieee80211_send_smps_action(sdata, smps_mode, ap, ap); if (err) link->u.mgd.req_smps = old_req; else if (smps_mode != IEEE80211_SMPS_OFF && tdls_peer_found) ieee80211_teardown_tdls_peers(sdata); return err; } static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, bool enabled, int timeout) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); unsigned int link_id; if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!ieee80211_hw_check(&local->hw, SUPPORTS_PS)) return -EOPNOTSUPP; if (enabled == sdata->u.mgd.powersave && timeout == local->dynamic_ps_forced_timeout) return 0; sdata->u.mgd.powersave = enabled; local->dynamic_ps_forced_timeout = timeout; /* no change, but if automatic follow powersave */ sdata_lock(sdata); for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { struct ieee80211_link_data *link; link = sdata_dereference(sdata->link[link_id], sdata); if (!link) continue; __ieee80211_request_smps_mgd(sdata, link, link->u.mgd.req_smps); } sdata_unlock(sdata); if (ieee80211_hw_check(&local->hw, SUPPORTS_DYNAMIC_PS)) ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); ieee80211_recalc_ps(local); ieee80211_recalc_ps_vif(sdata); ieee80211_check_fast_rx_iface(sdata); return 0; } static int ieee80211_set_cqm_rssi_config(struct wiphy *wiphy, struct net_device *dev, s32 rssi_thold, u32 rssi_hyst) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_vif *vif = &sdata->vif; struct ieee80211_bss_conf *bss_conf = &vif->bss_conf; if (rssi_thold == bss_conf->cqm_rssi_thold && rssi_hyst == bss_conf->cqm_rssi_hyst) return 0; if (sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER && !(sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) return -EOPNOTSUPP; bss_conf->cqm_rssi_thold = rssi_thold; bss_conf->cqm_rssi_hyst = rssi_hyst; bss_conf->cqm_rssi_low = 0; bss_conf->cqm_rssi_high = 0; sdata->deflink.u.mgd.last_cqm_event_signal = 0; /* tell the driver upon association, unless already associated */ if (sdata->u.mgd.associated && sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI) ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_CQM); return 0; } static int ieee80211_set_cqm_rssi_range_config(struct wiphy *wiphy, struct net_device *dev, s32 rssi_low, s32 rssi_high) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_vif *vif = &sdata->vif; struct ieee80211_bss_conf *bss_conf = &vif->bss_conf; if (sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER) return -EOPNOTSUPP; bss_conf->cqm_rssi_low = rssi_low; bss_conf->cqm_rssi_high = rssi_high; bss_conf->cqm_rssi_thold = 0; bss_conf->cqm_rssi_hyst = 0; sdata->deflink.u.mgd.last_cqm_event_signal = 0; /* tell the driver upon association, unless already associated */ if (sdata->u.mgd.associated && sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI) ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_CQM); return 0; } static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id, const u8 *addr, const struct cfg80211_bitrate_mask *mask) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); int i, ret; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; /* * If active validate the setting and reject it if it doesn't leave * at least one basic rate usable, since we really have to be able * to send something, and if we're an AP we have to be able to do * so at a basic rate so that all clients can receive it. */ if (rcu_access_pointer(sdata->vif.bss_conf.chanctx_conf) && sdata->vif.bss_conf.chandef.chan) { u32 basic_rates = sdata->vif.bss_conf.basic_rates; enum nl80211_band band = sdata->vif.bss_conf.chandef.chan->band; if (!(mask->control[band].legacy & basic_rates)) return -EINVAL; } if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) { ret = drv_set_bitrate_mask(local, sdata, mask); if (ret) return ret; } for (i = 0; i < NUM_NL80211_BANDS; i++) { struct ieee80211_supported_band *sband = wiphy->bands[i]; int j; sdata->rc_rateidx_mask[i] = mask->control[i].legacy; memcpy(sdata->rc_rateidx_mcs_mask[i], mask->control[i].ht_mcs, sizeof(mask->control[i].ht_mcs)); memcpy(sdata->rc_rateidx_vht_mcs_mask[i], mask->control[i].vht_mcs, sizeof(mask->control[i].vht_mcs)); sdata->rc_has_mcs_mask[i] = false; sdata->rc_has_vht_mcs_mask[i] = false; if (!sband) continue; for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) { if (sdata->rc_rateidx_mcs_mask[i][j] != 0xff) { sdata->rc_has_mcs_mask[i] = true; break; } } for (j = 0; j < NL80211_VHT_NSS_MAX; j++) { if (sdata->rc_rateidx_vht_mcs_mask[i][j] != 0xffff) { sdata->rc_has_vht_mcs_mask[i] = true; break; } } } return 0; } static int ieee80211_start_radar_detection(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_chan_def *chandef, u32 cac_time_ms) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; int err; mutex_lock(&local->mtx); if (!list_empty(&local->roc_list) || local->scanning) { err = -EBUSY; goto out_unlock; } /* whatever, but channel contexts should not complain about that one */ sdata->deflink.smps_mode = IEEE80211_SMPS_OFF; sdata->deflink.needed_rx_chains = local->rx_chains; err = ieee80211_link_use_channel(&sdata->deflink, chandef, IEEE80211_CHANCTX_SHARED); if (err) goto out_unlock; ieee80211_queue_delayed_work(&sdata->local->hw, &sdata->deflink.dfs_cac_timer_work, msecs_to_jiffies(cac_time_ms)); out_unlock: mutex_unlock(&local->mtx); return err; } static void ieee80211_end_cac(struct wiphy *wiphy, struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; mutex_lock(&local->mtx); list_for_each_entry(sdata, &local->interfaces, list) { /* it might be waiting for the local->mtx, but then * by the time it gets it, sdata->wdev.cac_started * will no longer be true */ cancel_delayed_work(&sdata->deflink.dfs_cac_timer_work); if (sdata->wdev.cac_started) { ieee80211_link_release_channel(&sdata->deflink); sdata->wdev.cac_started = false; } } mutex_unlock(&local->mtx); } static struct cfg80211_beacon_data * cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon) { struct cfg80211_beacon_data *new_beacon; u8 *pos; int len; len = beacon->head_len + beacon->tail_len + beacon->beacon_ies_len + beacon->proberesp_ies_len + beacon->assocresp_ies_len + beacon->probe_resp_len + beacon->lci_len + beacon->civicloc_len + ieee80211_get_mbssid_beacon_len(beacon->mbssid_ies); new_beacon = kzalloc(sizeof(*new_beacon) + len, GFP_KERNEL); if (!new_beacon) return NULL; if (beacon->mbssid_ies && beacon->mbssid_ies->cnt) { new_beacon->mbssid_ies = kzalloc(struct_size(new_beacon->mbssid_ies, elem, beacon->mbssid_ies->cnt), GFP_KERNEL); if (!new_beacon->mbssid_ies) { kfree(new_beacon); return NULL; } } pos = (u8 *)(new_beacon + 1); if (beacon->head_len) { new_beacon->head_len = beacon->head_len; new_beacon->head = pos; memcpy(pos, beacon->head, beacon->head_len); pos += beacon->head_len; } if (beacon->tail_len) { new_beacon->tail_len = beacon->tail_len; new_beacon->tail = pos; memcpy(pos, beacon->tail, beacon->tail_len); pos += beacon->tail_len; } if (beacon->beacon_ies_len) { new_beacon->beacon_ies_len = beacon->beacon_ies_len; new_beacon->beacon_ies = pos; memcpy(pos, beacon->beacon_ies, beacon->beacon_ies_len); pos += beacon->beacon_ies_len; } if (beacon->proberesp_ies_len) { new_beacon->proberesp_ies_len = beacon->proberesp_ies_len; new_beacon->proberesp_ies = pos; memcpy(pos, beacon->proberesp_ies, beacon->proberesp_ies_len); pos += beacon->proberesp_ies_len; } if (beacon->assocresp_ies_len) { new_beacon->assocresp_ies_len = beacon->assocresp_ies_len; |