| 79 1 78 3 137 2 2 1 78 53 141 141 130 48 48 29 29 19 19 4 1 1 1 1 2040 629 22 11 6 1 5 17 6 879 865 1636 1637 2497 2496 3 1 1 1 6 4 3 20 5 2 15 1 3 1 1 1 3 2 2 3 1 9 9 2 16 2 6 3 1 10 12 10 3 21 21 30 30 22 22 237 237 98 1 3356 3259 1606 341 341 481 237 201 201 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io */ /* Devmaps primary use is as a backend map for XDP BPF helper call * bpf_redirect_map(). Because XDP is mostly concerned with performance we * spent some effort to ensure the datapath with redirect maps does not use * any locking. This is a quick note on the details. * * We have three possible paths to get into the devmap control plane bpf * syscalls, bpf programs, and driver side xmit/flush operations. A bpf syscall * will invoke an update, delete, or lookup operation. To ensure updates and * deletes appear atomic from the datapath side xchg() is used to modify the * netdev_map array. Then because the datapath does a lookup into the netdev_map * array (read-only) from an RCU critical section we use call_rcu() to wait for * an rcu grace period before free'ing the old data structures. This ensures the * datapath always has a valid copy. However, the datapath does a "flush" * operation that pushes any pending packets in the driver outside the RCU * critical section. Each bpf_dtab_netdev tracks these pending operations using * a per-cpu flush list. The bpf_dtab_netdev object will not be destroyed until * this list is empty, indicating outstanding flush operations have completed. * * BPF syscalls may race with BPF program calls on any of the update, delete * or lookup operations. As noted above the xchg() operation also keep the * netdev_map consistent in this case. From the devmap side BPF programs * calling into these operations are the same as multiple user space threads * making system calls. * * Finally, any of the above may race with a netdev_unregister notifier. The * unregister notifier must search for net devices in the map structure that * contain a reference to the net device and remove them. This is a two step * process (a) dereference the bpf_dtab_netdev object in netdev_map and (b) * check to see if the ifindex is the same as the net_device being removed. * When removing the dev a cmpxchg() is used to ensure the correct dev is * removed, in the case of a concurrent update or delete operation it is * possible that the initially referenced dev is no longer in the map. As the * notifier hook walks the map we know that new dev references can not be * added by the user because core infrastructure ensures dev_get_by_index() * calls will fail at this point. * * The devmap_hash type is a map type which interprets keys as ifindexes and * indexes these using a hashmap. This allows maps that use ifindex as key to be * densely packed instead of having holes in the lookup array for unused * ifindexes. The setup and packet enqueue/send code is shared between the two * types of devmap; only the lookup and insertion is different. */ #include <linux/bpf.h> #include <net/xdp.h> #include <linux/filter.h> #include <trace/events/xdp.h> #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) struct xdp_dev_bulk_queue { struct xdp_frame *q[DEV_MAP_BULK_SIZE]; struct list_head flush_node; struct net_device *dev; struct net_device *dev_rx; struct bpf_prog *xdp_prog; unsigned int count; }; struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ struct hlist_node index_hlist; struct bpf_dtab *dtab; struct bpf_prog *xdp_prog; struct rcu_head rcu; unsigned int idx; struct bpf_devmap_val val; }; struct bpf_dtab { struct bpf_map map; struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */ struct list_head list; /* these are only used for DEVMAP_HASH type maps */ struct hlist_head *dev_index_head; spinlock_t index_lock; unsigned int items; u32 n_buckets; }; static DEFINE_PER_CPU(struct list_head, dev_flush_list); static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); static struct hlist_head *dev_map_create_hash(unsigned int entries, int numa_node) { int i; struct hlist_head *hash; hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node); if (hash != NULL) for (i = 0; i < entries; i++) INIT_HLIST_HEAD(&hash[i]); return hash; } static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, int idx) { return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; } static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { u32 valsize = attr->value_size; /* check sanity of attributes. 2 value sizes supported: * 4 bytes: ifindex * 8 bytes: ifindex + prog fd */ if (attr->max_entries == 0 || attr->key_size != 4 || (valsize != offsetofend(struct bpf_devmap_val, ifindex) && valsize != offsetofend(struct bpf_devmap_val, bpf_prog.fd)) || attr->map_flags & ~DEV_CREATE_FLAG_MASK) return -EINVAL; /* Lookup returns a pointer straight to dev->ifindex, so make sure the * verifier prevents writes from the BPF side */ attr->map_flags |= BPF_F_RDONLY_PROG; bpf_map_init_from_attr(&dtab->map, attr); if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { /* hash table size must be power of 2; roundup_pow_of_two() can * overflow into UB on 32-bit arches, so check that first */ if (dtab->map.max_entries > 1UL << 31) return -EINVAL; dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) return -ENOMEM; spin_lock_init(&dtab->index_lock); } else { dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) return -ENOMEM; } return 0; } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; int err; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); dtab = kzalloc(sizeof(*dtab), GFP_USER | __GFP_ACCOUNT); if (!dtab) return ERR_PTR(-ENOMEM); err = dev_map_init_map(dtab, attr); if (err) { kfree(dtab); return ERR_PTR(err); } spin_lock(&dev_map_lock); list_add_tail_rcu(&dtab->list, &dev_map_list); spin_unlock(&dev_map_lock); return &dtab->map; } static void dev_map_free(struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 i; /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, * so the programs (can be more than one that used this map) were * disconnected from events. The following synchronize_rcu() guarantees * both rcu read critical sections complete and waits for * preempt-disable regions (NAPI being the relevant context here) so we * are certain there will be no further reads against the netdev_map and * all flush operations are complete. Flush operations can only be done * from NAPI context for this reason. */ spin_lock(&dev_map_lock); list_del_rcu(&dtab->list); spin_unlock(&dev_map_lock); bpf_clear_redirect_map(map); synchronize_rcu(); /* Make sure prior __dev_map_entry_free() have completed. */ rcu_barrier(); if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { hlist_del_rcu(&dev->index_hlist); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } } bpf_map_area_free(dtab->dev_index_head); } else { for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev; dev = rcu_dereference_raw(dtab->netdev_map[i]); if (!dev) continue; if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } bpf_map_area_free(dtab->netdev_map); } kfree(dtab); } static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 index = key ? *(u32 *)key : U32_MAX; u32 *next = next_key; if (index >= dtab->map.max_entries) { *next = 0; return 0; } if (index == dtab->map.max_entries - 1) return -ENOENT; *next = index + 1; return 0; } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct hlist_head *head = dev_map_index_hash(dtab, key); struct bpf_dtab_netdev *dev; hlist_for_each_entry_rcu(dev, head, index_hlist, lockdep_is_held(&dtab->index_lock)) if (dev->idx == key) return dev; return NULL; } static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 idx, *next = next_key; struct bpf_dtab_netdev *dev, *next_dev; struct hlist_head *head; int i = 0; if (!key) goto find_first; idx = *(u32 *)key; dev = __dev_map_hash_lookup_elem(map, idx); if (!dev) goto find_first; next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } i = idx & (dtab->n_buckets - 1); i++; find_first: for (; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } } return -ENOENT; } static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, struct xdp_frame **frames, int n, struct net_device *tx_dev, struct net_device *rx_dev) { struct xdp_txq_info txq = { .dev = tx_dev }; struct xdp_rxq_info rxq = { .dev = rx_dev }; struct xdp_buff xdp; int i, nframes = 0; for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; u32 act; int err; xdp_convert_frame_to_buff(xdpf, &xdp); xdp.txq = &txq; xdp.rxq = &rxq; act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { case XDP_PASS: err = xdp_update_frame_from_buff(&xdp, xdpf); if (unlikely(err < 0)) xdp_return_frame_rx_napi(xdpf); else frames[nframes++] = xdpf; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: trace_xdp_exception(tx_dev, xdp_prog, act); fallthrough; case XDP_DROP: xdp_return_frame_rx_napi(xdpf); break; } } return nframes; /* sent frames count */ } static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { struct net_device *dev = bq->dev; unsigned int cnt = bq->count; int sent = 0, err = 0; int to_send = cnt; int i; if (unlikely(!cnt)) return; for (i = 0; i < cnt; i++) { struct xdp_frame *xdpf = bq->q[i]; prefetch(xdpf); } if (bq->xdp_prog) { to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx); if (!to_send) goto out; } sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags); if (sent < 0) { /* If ndo_xdp_xmit fails with an errno, no frames have * been xmit'ed. */ err = sent; sent = 0; } /* If not all frames have been transmitted, it is our * responsibility to free them */ for (i = sent; unlikely(i < to_send); i++) xdp_return_frame_rx_napi(bq->q[i]); out: bq->count = 0; trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err); } /* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the * driver before returning from its napi->poll() routine. See the comment above * xdp_do_flush() in filter.c. */ void __dev_flush(void) { struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); struct xdp_dev_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { bq_xmit_all(bq, XDP_XMIT_FLUSH); bq->dev_rx = NULL; bq->xdp_prog = NULL; __list_del_clearprev(&bq->flush_node); } } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *obj; if (key >= map->max_entries) return NULL; obj = rcu_dereference_check(dtab->netdev_map[key], rcu_read_lock_bh_held()); return obj; } /* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu * variable access, and map elements stick around. See comment above * xdp_do_flush() in filter.c. */ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) bq_xmit_all(bq, 0); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed * from net_device drivers NAPI func end. * * Do the same with xdp_prog and flush_list since these fields * are only ever modified together. */ if (!bq->dev_rx) { bq->dev_rx = dev_rx; bq->xdp_prog = xdp_prog; list_add(&bq->flush_node, flush_list); } bq->q[bq->count++] = xdpf; } static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { int err; if (!dev->netdev_ops->ndo_xdp_xmit) return -EOPNOTSUPP; err = xdp_ok_fwd_dev(dev, xdpf->len); if (unlikely(err)) return err; bq_enqueue(dev, xdpf, dev_rx, xdp_prog); return 0; } static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst) { struct xdp_txq_info txq = { .dev = dst->dev }; struct xdp_buff xdp; u32 act; if (!dst->xdp_prog) return XDP_PASS; __skb_pull(skb, skb->mac_len); xdp.txq = &txq; act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog); switch (act) { case XDP_PASS: __skb_push(skb, skb->mac_len); break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dst->dev, dst->xdp_prog, act); fallthrough; case XDP_DROP: kfree_skb(skb); break; } return act; } int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return __xdp_enqueue(dev, xdpf, dev_rx, NULL); } int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { struct net_device *dev = dst->dev; return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog); } static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) { if (!obj || !obj->dev->netdev_ops->ndo_xdp_xmit) return false; if (xdp_ok_fwd_dev(obj->dev, xdpf->len)) return false; return true; } static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj, struct net_device *dev_rx, struct xdp_frame *xdpf) { struct xdp_frame *nxdpf; nxdpf = xdpf_clone(xdpf); if (!nxdpf) return -ENOMEM; bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog); return 0; } static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifindex) { while (num_excluded--) { if (ifindex == excluded[num_excluded]) return true; } return false; } /* Get ifindex of each upper device. 'indexes' must be able to hold at * least MAX_NEST_DEV elements. * Returns the number of ifindexes added. */ static int get_upper_ifindexes(struct net_device *dev, int *indexes) { struct net_device *upper; struct list_head *iter; int n = 0; netdev_for_each_upper_dev_rcu(dev, upper, iter) { indexes[n++] = upper->ifindex; } return n; } int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev_rx, excluded_devices); excluded_devices[num_excluded++] = dev_rx->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_rcu(dst, head, index_hlist, lockdep_is_held(&dtab->index_lock)) { if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } } /* consume the last copy of the frame */ if (last_dst) bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog); else xdp_return_frame_rx_napi(xdpf); /* dtab is empty */ return 0; } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { int err; err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; /* Redirect has already succeeded semantically at this point, so we just * return 0 even if packet is dropped. Helper below takes care of * freeing skb. */ if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS) return 0; skb->dev = dst->dev; generic_xdp_tx(skb, xdp_prog); return 0; } static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { struct sk_buff *nskb; int err; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; err = dev_map_generic_redirect(dst, nskb, xdp_prog); if (unlikely(err)) { consume_skb(nskb); return err; } return 0; } int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; struct hlist_node *next; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev, excluded_devices); excluded_devices[num_excluded++] = dev->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!dst) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dst, next, head, index_hlist) { if (!dst) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } } /* consume the first skb and return */ if (last_dst) return dev_map_generic_redirect(last_dst, skb, xdp_prog); /* dtab is empty */ consume_skb(skb); return 0; } static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void __dev_map_entry_free(struct rcu_head *rcu) { struct bpf_dtab_netdev *dev; dev = container_of(rcu, struct bpf_dtab_netdev, rcu); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } static int dev_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; u32 k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL)); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; } static int dev_map_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; u32 k = *(u32 *)key; unsigned long flags; int ret = -ENOENT; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, k); if (old_dev) { dtab->items--; hlist_del_init_rcu(&old_dev->index_hlist); call_rcu(&old_dev->rcu, __dev_map_entry_free); ret = 0; } spin_unlock_irqrestore(&dtab->index_lock, flags); return ret; } static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_dtab *dtab, struct bpf_devmap_val *val, unsigned int idx) { struct bpf_prog *prog = NULL; struct bpf_dtab_netdev *dev; dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, dtab->map.numa_node); if (!dev) return ERR_PTR(-ENOMEM); dev->dev = dev_get_by_index(net, val->ifindex); if (!dev->dev) goto err_out; if (val->bpf_prog.fd > 0) { prog = bpf_prog_get_type_dev(val->bpf_prog.fd, BPF_PROG_TYPE_XDP, false); if (IS_ERR(prog)) goto err_put_dev; if (prog->expected_attach_type != BPF_XDP_DEVMAP) goto err_put_prog; } dev->idx = idx; dev->dtab = dtab; if (prog) { dev->xdp_prog = prog; dev->val.bpf_prog.id = prog->aux->id; } else { dev->xdp_prog = NULL; dev->val.bpf_prog.id = 0; } dev->val.ifindex = val->ifindex; return dev; err_put_prog: bpf_prog_put(prog); err_put_dev: dev_put(dev->dev); err_out: kfree(dev); return ERR_PTR(-EINVAL); } static int __dev_map_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 i = *(u32 *)key; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; if (unlikely(i >= dtab->map.max_entries)) return -E2BIG; if (unlikely(map_flags == BPF_NOEXIST)) return -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (!val.ifindex) { dev = NULL; /* can not specify fd if ifindex is 0 */ if (val.bpf_prog.fd > 0) return -EINVAL; } else { dev = __dev_map_alloc_node(net, dtab, &val, i); if (IS_ERR(dev)) return PTR_ERR(dev); } /* Use call_rcu() here to ensure rcu critical sections have completed * Remembering the driver side flush operation will happen before the * net device is removed. */ old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev))); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; } static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 idx = *(u32 *)key; unsigned long flags; int err = -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (unlikely(map_flags > BPF_EXIST || !val.ifindex)) return -EINVAL; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, idx); if (old_dev && (map_flags & BPF_NOEXIST)) goto out_err; dev = __dev_map_alloc_node(net, dtab, &val, idx); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out_err; } if (old_dev) { hlist_del_rcu(&old_dev->index_hlist); } else { if (dtab->items >= dtab->map.max_entries) { spin_unlock_irqrestore(&dtab->index_lock, flags); call_rcu(&dev->rcu, __dev_map_entry_free); return -E2BIG; } dtab->items++; } hlist_add_head_rcu(&dev->index_hlist, dev_map_index_hash(dtab, idx)); spin_unlock_irqrestore(&dtab->index_lock, flags); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; out_err: spin_unlock_irqrestore(&dtab->index_lock, flags); return err; } static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_hash_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static int dev_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_lookup_elem); } static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_hash_lookup_elem); } static int dev_map_btf_id; const struct bpf_map_ops dev_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_get_next_key, .map_lookup_elem = dev_map_lookup_elem, .map_update_elem = dev_map_update_elem, .map_delete_elem = dev_map_delete_elem, .map_check_btf = map_check_no_btf, .map_btf_name = "bpf_dtab", .map_btf_id = &dev_map_btf_id, .map_redirect = dev_map_redirect, }; static int dev_map_hash_map_btf_id; const struct bpf_map_ops dev_map_hash_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_hash_get_next_key, .map_lookup_elem = dev_map_hash_lookup_elem, .map_update_elem = dev_map_hash_update_elem, .map_delete_elem = dev_map_hash_delete_elem, .map_check_btf = map_check_no_btf, .map_btf_name = "bpf_dtab", .map_btf_id = &dev_map_hash_map_btf_id, .map_redirect = dev_hash_map_redirect, }; static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab, struct net_device *netdev) { unsigned long flags; u32 i; spin_lock_irqsave(&dtab->index_lock, flags); for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { if (netdev != dev->dev) continue; dtab->items--; hlist_del_rcu(&dev->index_hlist); call_rcu(&dev->rcu, __dev_map_entry_free); } } spin_unlock_irqrestore(&dtab->index_lock, flags); } static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct bpf_dtab *dtab; int i, cpu; switch (event) { case NETDEV_REGISTER: if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq) break; /* will be freed in free_netdev() */ netdev->xdp_bulkq = alloc_percpu(struct xdp_dev_bulk_queue); if (!netdev->xdp_bulkq) return NOTIFY_BAD; for_each_possible_cpu(cpu) per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev; break; case NETDEV_UNREGISTER: /* This rcu_read_lock/unlock pair is needed because * dev_map_list is an RCU list AND to ensure a delete * operation does not free a netdev_map entry while we * are comparing it against the netdev being unregistered. */ rcu_read_lock(); list_for_each_entry_rcu(dtab, &dev_map_list, list) { if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dev_map_hash_remove_netdev(dtab, netdev); continue; } for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev, *odev; dev = rcu_dereference(dtab->netdev_map[i]); if (!dev || netdev != dev->dev) continue; odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); if (dev == odev) call_rcu(&dev->rcu, __dev_map_entry_free); } } rcu_read_unlock(); break; default: break; } return NOTIFY_OK; } static struct notifier_block dev_map_notifier = { .notifier_call = dev_map_notification, }; static int __init dev_map_init(void) { int cpu; /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); for_each_possible_cpu(cpu) INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu)); return 0; } subsys_initcall(dev_map_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2020 ARM Ltd. */ #ifndef __ASM_VDSO_PROCESSOR_H #define __ASM_VDSO_PROCESSOR_H #ifndef __ASSEMBLY__ /* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ static __always_inline void rep_nop(void) { asm volatile("rep; nop" ::: "memory"); } static __always_inline void cpu_relax(void) { rep_nop(); } #endif /* __ASSEMBLY__ */ #endif /* __ASM_VDSO_PROCESSOR_H */ |
| 210 10041 5579 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ATOMIC_H #define _ASM_X86_ATOMIC_H #include <linux/compiler.h> #include <linux/types.h> #include <asm/alternative.h> #include <asm/cmpxchg.h> #include <asm/rmwcc.h> #include <asm/barrier.h> /* * Atomic operations that C can't guarantee us. Useful for * resource counting etc.. */ /** * arch_atomic_read - read atomic variable * @v: pointer of type atomic_t * * Atomically reads the value of @v. */ static __always_inline int arch_atomic_read(const atomic_t *v) { /* * Note for KASAN: we deliberately don't use READ_ONCE_NOCHECK() here, * it's non-inlined function that increases binary size and stack usage. */ return __READ_ONCE((v)->counter); } /** * arch_atomic_set - set atomic variable * @v: pointer of type atomic_t * @i: required value * * Atomically sets the value of @v to @i. */ static __always_inline void arch_atomic_set(atomic_t *v, int i) { __WRITE_ONCE(v->counter, i); } /** * arch_atomic_add - add integer to atomic variable * @i: integer value to add * @v: pointer of type atomic_t * * Atomically adds @i to @v. */ static __always_inline void arch_atomic_add(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "addl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } /** * arch_atomic_sub - subtract integer from atomic variable * @i: integer value to subtract * @v: pointer of type atomic_t * * Atomically subtracts @i from @v. */ static __always_inline void arch_atomic_sub(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "subl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } /** * arch_atomic_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @v: pointer of type atomic_t * * Atomically subtracts @i from @v and returns * true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, e, "er", i); } #define arch_atomic_sub_and_test arch_atomic_sub_and_test /** * arch_atomic_inc - increment atomic variable * @v: pointer of type atomic_t * * Atomically increments @v by 1. */ static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" : "+m" (v->counter) :: "memory"); } #define arch_atomic_inc arch_atomic_inc /** * arch_atomic_dec - decrement atomic variable * @v: pointer of type atomic_t * * Atomically decrements @v by 1. */ static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" : "+m" (v->counter) :: "memory"); } #define arch_atomic_dec arch_atomic_dec /** * arch_atomic_dec_and_test - decrement and test * @v: pointer of type atomic_t * * Atomically decrements @v by 1 and * returns true if the result is 0, or false for all other * cases. */ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, e); } #define arch_atomic_dec_and_test arch_atomic_dec_and_test /** * arch_atomic_inc_and_test - increment and test * @v: pointer of type atomic_t * * Atomically increments @v by 1 * and returns true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, e); } #define arch_atomic_inc_and_test arch_atomic_inc_and_test /** * arch_atomic_add_negative - add and test if negative * @i: integer value to add * @v: pointer of type atomic_t * * Atomically adds @i to @v and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, s, "er", i); } #define arch_atomic_add_negative arch_atomic_add_negative /** * arch_atomic_add_return - add integer and return * @i: integer value to add * @v: pointer of type atomic_t * * Atomically adds @i to @v and returns @i + @v */ static __always_inline int arch_atomic_add_return(int i, atomic_t *v) { return i + xadd(&v->counter, i); } #define arch_atomic_add_return arch_atomic_add_return /** * arch_atomic_sub_return - subtract integer and return * @v: pointer of type atomic_t * @i: integer value to subtract * * Atomically subtracts @i from @v and returns @v - @i */ static __always_inline int arch_atomic_sub_return(int i, atomic_t *v) { return arch_atomic_add_return(-i, v); } #define arch_atomic_sub_return arch_atomic_sub_return static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { return xadd(&v->counter, i); } #define arch_atomic_fetch_add arch_atomic_fetch_add static __always_inline int arch_atomic_fetch_sub(int i, atomic_t *v) { return xadd(&v->counter, -i); } #define arch_atomic_fetch_sub arch_atomic_fetch_sub static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new) { return arch_cmpxchg(&v->counter, old, new); } #define arch_atomic_cmpxchg arch_atomic_cmpxchg static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { return arch_try_cmpxchg(&v->counter, old, new); } #define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg static __always_inline int arch_atomic_xchg(atomic_t *v, int new) { return arch_xchg(&v->counter, new); } #define arch_atomic_xchg arch_atomic_xchg static __always_inline void arch_atomic_and(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "andl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline int arch_atomic_fetch_and(int i, atomic_t *v) { int val = arch_atomic_read(v); do { } while (!arch_atomic_try_cmpxchg(v, &val, val & i)); return val; } #define arch_atomic_fetch_and arch_atomic_fetch_and static __always_inline void arch_atomic_or(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "orl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline int arch_atomic_fetch_or(int i, atomic_t *v) { int val = arch_atomic_read(v); do { } while (!arch_atomic_try_cmpxchg(v, &val, val | i)); return val; } #define arch_atomic_fetch_or arch_atomic_fetch_or static __always_inline void arch_atomic_xor(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "xorl %1,%0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline int arch_atomic_fetch_xor(int i, atomic_t *v) { int val = arch_atomic_read(v); do { } while (!arch_atomic_try_cmpxchg(v, &val, val ^ i)); return val; } #define arch_atomic_fetch_xor arch_atomic_fetch_xor #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else # include <asm/atomic64_64.h> #endif #endif /* _ASM_X86_ATOMIC_H */ |
| 1423 1423 511 511 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/swap_state.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie * * Rewritten to use page cache, (C) 1998 Stephen Tweedie */ #include <linux/mm.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/init.h> #include <linux/pagemap.h> #include <linux/backing-dev.h> #include <linux/blkdev.h> #include <linux/pagevec.h> #include <linux/migrate.h> #include <linux/vmalloc.h> #include <linux/swap_slots.h> #include <linux/huge_mm.h> #include <linux/shmem_fs.h> #include "internal.h" /* * swapper_space is a fiction, retained to simplify the path through * vmscan's shrink_page_list. */ static const struct address_space_operations swap_aops = { .writepage = swap_writepage, .set_page_dirty = swap_set_page_dirty, #ifdef CONFIG_MIGRATION .migratepage = migrate_page, #endif }; struct address_space *swapper_spaces[MAX_SWAPFILES] __read_mostly; static unsigned int nr_swapper_spaces[MAX_SWAPFILES] __read_mostly; static bool enable_vma_readahead __read_mostly = true; #define SWAP_RA_WIN_SHIFT (PAGE_SHIFT / 2) #define SWAP_RA_HITS_MASK ((1UL << SWAP_RA_WIN_SHIFT) - 1) #define SWAP_RA_HITS_MAX SWAP_RA_HITS_MASK #define SWAP_RA_WIN_MASK (~PAGE_MASK & ~SWAP_RA_HITS_MASK) #define SWAP_RA_HITS(v) ((v) & SWAP_RA_HITS_MASK) #define SWAP_RA_WIN(v) (((v) & SWAP_RA_WIN_MASK) >> SWAP_RA_WIN_SHIFT) #define SWAP_RA_ADDR(v) ((v) & PAGE_MASK) #define SWAP_RA_VAL(addr, win, hits) \ (((addr) & PAGE_MASK) | \ (((win) << SWAP_RA_WIN_SHIFT) & SWAP_RA_WIN_MASK) | \ ((hits) & SWAP_RA_HITS_MASK)) /* Initial readahead hits is 4 to start up with a small window */ #define GET_SWAP_RA_VAL(vma) \ (atomic_long_read(&(vma)->swap_readahead_info) ? : 4) #define INC_CACHE_INFO(x) data_race(swap_cache_info.x++) #define ADD_CACHE_INFO(x, nr) data_race(swap_cache_info.x += (nr)) static struct { unsigned long add_total; unsigned long del_total; unsigned long find_success; unsigned long find_total; } swap_cache_info; static atomic_t swapin_readahead_hits = ATOMIC_INIT(4); void show_swap_cache_info(void) { printk("%lu pages in swap cache\n", total_swapcache_pages()); printk("Swap cache stats: add %lu, delete %lu, find %lu/%lu\n", swap_cache_info.add_total, swap_cache_info.del_total, swap_cache_info.find_success, swap_cache_info.find_total); printk("Free swap = %ldkB\n", get_nr_swap_pages() << (PAGE_SHIFT - 10)); printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10)); } void *get_shadow_from_swap_cache(swp_entry_t entry) { struct address_space *address_space = swap_address_space(entry); pgoff_t idx = swp_offset(entry); struct page *page; page = xa_load(&address_space->i_pages, idx); if (xa_is_value(page)) return page; return NULL; } /* * add_to_swap_cache resembles add_to_page_cache_locked on swapper_space, * but sets SwapCache flag and private instead of mapping and index. */ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp, void **shadowp) { struct address_space *address_space = swap_address_space(entry); pgoff_t idx = swp_offset(entry); XA_STATE_ORDER(xas, &address_space->i_pages, idx, compound_order(page)); unsigned long i, nr = thp_nr_pages(page); void *old; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageSwapCache(page), page); VM_BUG_ON_PAGE(!PageSwapBacked(page), page); page_ref_add(page, nr); SetPageSwapCache(page); do { xas_lock_irq(&xas); xas_create_range(&xas); if (xas_error(&xas)) goto unlock; for (i = 0; i < nr; i++) { VM_BUG_ON_PAGE(xas.xa_index != idx + i, page); old = xas_load(&xas); if (xa_is_value(old)) { if (shadowp) *shadowp = old; } set_page_private(page + i, entry.val + i); xas_store(&xas, page); xas_next(&xas); } address_space->nrpages += nr; __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr); __mod_lruvec_page_state(page, NR_SWAPCACHE, nr); ADD_CACHE_INFO(add_total, nr); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); if (!xas_error(&xas)) return 0; ClearPageSwapCache(page); page_ref_sub(page, nr); return xas_error(&xas); } /* * This must be called only on pages that have * been verified to be in the swap cache. */ void __delete_from_swap_cache(struct page *page, swp_entry_t entry, void *shadow) { struct address_space *address_space = swap_address_space(entry); int i, nr = thp_nr_pages(page); pgoff_t idx = swp_offset(entry); XA_STATE(xas, &address_space->i_pages, idx); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageSwapCache(page), page); VM_BUG_ON_PAGE(PageWriteback(page), page); for (i = 0; i < nr; i++) { void *entry = xas_store(&xas, shadow); VM_BUG_ON_PAGE(entry != page, entry); set_page_private(page + i, 0); xas_next(&xas); } ClearPageSwapCache(page); address_space->nrpages -= nr; __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr); __mod_lruvec_page_state(page, NR_SWAPCACHE, -nr); ADD_CACHE_INFO(del_total, nr); } /** * add_to_swap - allocate swap space for a page * @page: page we want to move to swap * * Allocate swap space for the page and add the page to the * swap cache. Caller needs to hold the page lock. */ int add_to_swap(struct page *page) { swp_entry_t entry; int err; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageUptodate(page), page); entry = get_swap_page(page); if (!entry.val) return 0; /* * XArray node allocations from PF_MEMALLOC contexts could * completely exhaust the page allocator. __GFP_NOMEMALLOC * stops emergency reserves from being allocated. * * TODO: this could cause a theoretical memory reclaim * deadlock in the swap out path. */ /* * Add it to the swap cache. */ err = add_to_swap_cache(page, entry, __GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN, NULL); if (err) /* * add_to_swap_cache() doesn't return -EEXIST, so we can safely * clear SWAP_HAS_CACHE flag. */ goto fail; /* * Normally the page will be dirtied in unmap because its pte should be * dirty. A special case is MADV_FREE page. The page's pte could have * dirty bit cleared but the page's SwapBacked bit is still set because * clearing the dirty bit and SwapBacked bit has no lock protected. For * such page, unmap will not set dirty bit for it, so page reclaim will * not write the page out. This can cause data corruption when the page * is swap in later. Always setting the dirty bit for the page solves * the problem. */ set_page_dirty(page); return 1; fail: put_swap_page(page, entry); return 0; } /* * This must be called only on pages that have * been verified to be in the swap cache and locked. * It will never put the page into the free list, * the caller has a reference on the page. */ void delete_from_swap_cache(struct page *page) { swp_entry_t entry = { .val = page_private(page) }; struct address_space *address_space = swap_address_space(entry); xa_lock_irq(&address_space->i_pages); __delete_from_swap_cache(page, entry, NULL); xa_unlock_irq(&address_space->i_pages); put_swap_page(page, entry); page_ref_sub(page, thp_nr_pages(page)); } void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end) { unsigned long curr = begin; void *old; for (;;) { swp_entry_t entry = swp_entry(type, curr); struct address_space *address_space = swap_address_space(entry); XA_STATE(xas, &address_space->i_pages, curr); xa_lock_irq(&address_space->i_pages); xas_for_each(&xas, old, end) { if (!xa_is_value(old)) continue; xas_store(&xas, NULL); } xa_unlock_irq(&address_space->i_pages); /* search the next swapcache until we meet end */ curr >>= SWAP_ADDRESS_SPACE_SHIFT; curr++; curr <<= SWAP_ADDRESS_SPACE_SHIFT; if (curr > end) break; } } /* * If we are the only user, then try to free up the swap cache. * * Its ok to check for PageSwapCache without the page lock * here because we are going to recheck again inside * try_to_free_swap() _with_ the lock. * - Marcelo */ void free_swap_cache(struct page *page) { if (PageSwapCache(page) && !page_mapped(page) && trylock_page(page)) { try_to_free_swap(page); unlock_page(page); } } /* * Perform a free_page(), also freeing any swap cache associated with * this page if it is the last user of the page. */ void free_page_and_swap_cache(struct page *page) { free_swap_cache(page); if (!is_huge_zero_page(page)) put_page(page); } /* * Passed an array of pages, drop them all from swapcache and then release * them. They are removed from the LRU and freed if this is their last use. */ void free_pages_and_swap_cache(struct page **pages, int nr) { struct page **pagep = pages; int i; lru_add_drain(); for (i = 0; i < nr; i++) free_swap_cache(pagep[i]); release_pages(pagep, nr); } static inline bool swap_use_vma_readahead(void) { return READ_ONCE(enable_vma_readahead) && !atomic_read(&nr_rotate_swap); } /* * Lookup a swap entry in the swap cache. A found page will be returned * unlocked and with its refcount incremented - we rely on the kernel * lock getting page table operations atomic even if we drop the page * lock before returning. */ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr) { struct page *page; struct swap_info_struct *si; si = get_swap_device(entry); if (!si) return NULL; page = find_get_page(swap_address_space(entry), swp_offset(entry)); put_swap_device(si); INC_CACHE_INFO(find_total); if (page) { bool vma_ra = swap_use_vma_readahead(); bool readahead; INC_CACHE_INFO(find_success); /* * At the moment, we don't support PG_readahead for anon THP * so let's bail out rather than confusing the readahead stat. */ if (unlikely(PageTransCompound(page))) return page; readahead = TestClearPageReadahead(page); if (vma && vma_ra) { unsigned long ra_val; int win, hits; ra_val = GET_SWAP_RA_VAL(vma); win = SWAP_RA_WIN(ra_val); hits = SWAP_RA_HITS(ra_val); if (readahead) hits = min_t(int, hits + 1, SWAP_RA_HITS_MAX); atomic_long_set(&vma->swap_readahead_info, SWAP_RA_VAL(addr, win, hits)); } if (readahead) { count_vm_event(SWAP_RA_HIT); if (!vma || !vma_ra) atomic_inc(&swapin_readahead_hits); } } return page; } /** * find_get_incore_page - Find and get a page from the page or swap caches. * @mapping: The address_space to search. * @index: The page cache index. * * This differs from find_get_page() in that it will also look for the * page in the swap cache. * * Return: The found page or %NULL. */ struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index) { swp_entry_t swp; struct swap_info_struct *si; struct page *page = pagecache_get_page(mapping, index, FGP_ENTRY | FGP_HEAD, 0); if (!page) return page; if (!xa_is_value(page)) return find_subpage(page, index); if (!shmem_mapping(mapping)) return NULL; swp = radix_to_swp_entry(page); /* Prevent swapoff from happening to us */ si = get_swap_device(swp); if (!si) return NULL; page = find_get_page(swap_address_space(swp), swp_offset(swp)); put_swap_device(si); return page; } struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr, bool *new_page_allocated) { struct swap_info_struct *si; struct page *page; void *shadow = NULL; *new_page_allocated = false; for (;;) { int err; /* * First check the swap cache. Since this is normally * called after lookup_swap_cache() failed, re-calling * that would confuse statistics. */ si = get_swap_device(entry); if (!si) return NULL; page = find_get_page(swap_address_space(entry), swp_offset(entry)); put_swap_device(si); if (page) return page; /* * Just skip read ahead for unused swap slot. * During swap_off when swap_slot_cache is disabled, * we have to handle the race between putting * swap entry in swap cache and marking swap slot * as SWAP_HAS_CACHE. That's done in later part of code or * else swap_off will be aborted if we return NULL. */ if (!__swp_swapcount(entry) && swap_slot_cache_enabled) return NULL; /* * Get a new page to read into from swap. Allocate it now, * before marking swap_map SWAP_HAS_CACHE, when -EEXIST will * cause any racers to loop around until we add it to cache. */ page = alloc_page_vma(gfp_mask, vma, addr); if (!page) return NULL; /* * Swap entry may have been freed since our caller observed it. */ err = swapcache_prepare(entry); if (!err) break; put_page(page); if (err != -EEXIST) return NULL; /* * We might race against __delete_from_swap_cache(), and * stumble across a swap_map entry whose SWAP_HAS_CACHE * has not yet been cleared. Or race against another * __read_swap_cache_async(), which has set SWAP_HAS_CACHE * in swap_map, but not yet added its page to swap cache. */ schedule_timeout_uninterruptible(1); } /* * The swap entry is ours to swap in. Prepare the new page. */ __SetPageLocked(page); __SetPageSwapBacked(page); if (mem_cgroup_swapin_charge_page(page, NULL, gfp_mask, entry)) goto fail_unlock; /* May fail (-ENOMEM) if XArray node allocation failed. */ if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow)) goto fail_unlock; mem_cgroup_swapin_uncharge_swap(entry); if (shadow) workingset_refault(page, shadow); /* Caller will initiate read into locked page */ lru_cache_add(page); *new_page_allocated = true; return page; fail_unlock: put_swap_page(page, entry); unlock_page(page); put_page(page); return NULL; } /* * Locate a page of swap in physical memory, reserving swap cache space * and reading the disk if it is not already cached. * A failure return means that either the page allocation failed or that * the swap entry is no longer in use. */ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr, bool do_poll) { bool page_was_allocated; struct page *retpage = __read_swap_cache_async(entry, gfp_mask, vma, addr, &page_was_allocated); if (page_was_allocated) swap_readpage(retpage, do_poll); return retpage; } static unsigned int __swapin_nr_pages(unsigned long prev_offset, unsigned long offset, int hits, int max_pages, int prev_win) { unsigned int pages, last_ra; /* * This heuristic has been found to work well on both sequential and * random loads, swapping to hard disk or to SSD: please don't ask * what the "+ 2" means, it just happens to work well, that's all. */ pages = hits + 2; if (pages == 2) { /* * We can have no readahead hits to judge by: but must not get * stuck here forever, so check for an adjacent offset instead * (and don't even bother to check whether swap type is same). */ if (offset != prev_offset + 1 && offset != prev_offset - 1) pages = 1; } else { unsigned int roundup = 4; while (roundup < pages) roundup <<= 1; pages = roundup; } if (pages > max_pages) pages = max_pages; /* Don't shrink readahead too fast */ last_ra = prev_win / 2; if (pages < last_ra) pages = last_ra; return pages; } static unsigned long swapin_nr_pages(unsigned long offset) { static unsigned long prev_offset; unsigned int hits, pages, max_pages; static atomic_t last_readahead_pages; max_pages = 1 << READ_ONCE(page_cluster); if (max_pages <= 1) return 1; hits = atomic_xchg(&swapin_readahead_hits, 0); pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits, max_pages, atomic_read(&last_readahead_pages)); if (!hits) WRITE_ONCE(prev_offset, offset); atomic_set(&last_readahead_pages, pages); return pages; } /** * swap_cluster_readahead - swap in pages in hope we need them soon * @entry: swap entry of this memory * @gfp_mask: memory allocation flags * @vmf: fault information * * Returns the struct page for entry and addr, after queueing swapin. * * Primitive swap readahead code. We simply read an aligned block of * (1 << page_cluster) entries in the swap area. This method is chosen * because it doesn't cost us any seek time. We also make sure to queue * the 'original' request together with the readahead ones... * * This has been extended to use the NUMA policies from the mm triggering * the readahead. * * Caller must hold read mmap_lock if vmf->vma is not NULL. */ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_fault *vmf) { struct page *page; unsigned long entry_offset = swp_offset(entry); unsigned long offset = entry_offset; unsigned long start_offset, end_offset; unsigned long mask; struct swap_info_struct *si = swp_swap_info(entry); struct blk_plug plug; bool do_poll = true, page_allocated; struct vm_area_struct *vma = vmf->vma; unsigned long addr = vmf->address; mask = swapin_nr_pages(offset) - 1; if (!mask) goto skip; do_poll = false; /* Read a page_cluster sized and aligned cluster around offset. */ start_offset = offset & ~mask; end_offset = offset | mask; if (!start_offset) /* First page is swap header. */ start_offset++; if (end_offset >= si->max) end_offset = si->max - 1; blk_start_plug(&plug); for (offset = start_offset; offset <= end_offset ; offset++) { /* Ok, do the async read-ahead now */ page = __read_swap_cache_async( swp_entry(swp_type(entry), offset), gfp_mask, vma, addr, &page_allocated); if (!page) continue; if (page_allocated) { swap_readpage(page, false); if (offset != entry_offset) { SetPageReadahead(page); count_vm_event(SWAP_RA); } } put_page(page); } blk_finish_plug(&plug); lru_add_drain(); /* Push any new pages onto the LRU now */ skip: return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll); } int init_swap_address_space(unsigned int type, unsigned long nr_pages) { struct address_space *spaces, *space; unsigned int i, nr; nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES); spaces = kvcalloc(nr, sizeof(struct address_space), GFP_KERNEL); if (!spaces) return -ENOMEM; for (i = 0; i < nr; i++) { space = spaces + i; xa_init_flags(&space->i_pages, XA_FLAGS_LOCK_IRQ); atomic_set(&space->i_mmap_writable, 0); space->a_ops = &swap_aops; /* swap cache doesn't use writeback related tags */ mapping_set_no_writeback_tags(space); } nr_swapper_spaces[type] = nr; swapper_spaces[type] = spaces; return 0; } void exit_swap_address_space(unsigned int type) { int i; struct address_space *spaces = swapper_spaces[type]; for (i = 0; i < nr_swapper_spaces[type]; i++) VM_WARN_ON_ONCE(!mapping_empty(&spaces[i])); kvfree(spaces); nr_swapper_spaces[type] = 0; swapper_spaces[type] = NULL; } static inline void swap_ra_clamp_pfn(struct vm_area_struct *vma, unsigned long faddr, unsigned long lpfn, unsigned long rpfn, unsigned long *start, unsigned long *end) { *start = max3(lpfn, PFN_DOWN(vma->vm_start), PFN_DOWN(faddr & PMD_MASK)); *end = min3(rpfn, PFN_DOWN(vma->vm_end), PFN_DOWN((faddr & PMD_MASK) + PMD_SIZE)); } static void swap_ra_info(struct vm_fault *vmf, struct vma_swap_readahead *ra_info) { struct vm_area_struct *vma = vmf->vma; unsigned long ra_val; unsigned long faddr, pfn, fpfn; unsigned long start, end; pte_t *pte, *orig_pte; unsigned int max_win, hits, prev_win, win, left; #ifndef CONFIG_64BIT pte_t *tpte; #endif max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster), SWAP_RA_ORDER_CEILING); if (max_win == 1) { ra_info->win = 1; return; } faddr = vmf->address; orig_pte = pte = pte_offset_map(vmf->pmd, faddr); fpfn = PFN_DOWN(faddr); ra_val = GET_SWAP_RA_VAL(vma); pfn = PFN_DOWN(SWAP_RA_ADDR(ra_val)); prev_win = SWAP_RA_WIN(ra_val); hits = SWAP_RA_HITS(ra_val); ra_info->win = win = __swapin_nr_pages(pfn, fpfn, hits, max_win, prev_win); atomic_long_set(&vma->swap_readahead_info, SWAP_RA_VAL(faddr, win, 0)); if (win == 1) { pte_unmap(orig_pte); return; } /* Copy the PTEs because the page table may be unmapped */ if (fpfn == pfn + 1) swap_ra_clamp_pfn(vma, faddr, fpfn, fpfn + win, &start, &end); else if (pfn == fpfn + 1) swap_ra_clamp_pfn(vma, faddr, fpfn - win + 1, fpfn + 1, &start, &end); else { left = (win - 1) / 2; swap_ra_clamp_pfn(vma, faddr, fpfn - left, fpfn + win - left, &start, &end); } ra_info->nr_pte = end - start; ra_info->offset = fpfn - start; pte -= ra_info->offset; #ifdef CONFIG_64BIT ra_info->ptes = pte; #else tpte = ra_info->ptes; for (pfn = start; pfn != end; pfn++) *tpte++ = *pte++; #endif pte_unmap(orig_pte); } /** * swap_vma_readahead - swap in pages in hope we need them soon * @fentry: swap entry of this memory * @gfp_mask: memory allocation flags * @vmf: fault information * * Returns the struct page for entry and addr, after queueing swapin. * * Primitive swap readahead code. We simply read in a few pages whose * virtual addresses are around the fault address in the same vma. * * Caller must hold read mmap_lock if vmf->vma is not NULL. * */ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, struct vm_fault *vmf) { struct blk_plug plug; struct vm_area_struct *vma = vmf->vma; struct page *page; pte_t *pte, pentry; swp_entry_t entry; unsigned int i; bool page_allocated; struct vma_swap_readahead ra_info = { .win = 1, }; swap_ra_info(vmf, &ra_info); if (ra_info.win == 1) goto skip; blk_start_plug(&plug); for (i = 0, pte = ra_info.ptes; i < ra_info.nr_pte; i++, pte++) { pentry = *pte; if (pte_none(pentry)) continue; if (pte_present(pentry)) continue; entry = pte_to_swp_entry(pentry); if (unlikely(non_swap_entry(entry))) continue; page = __read_swap_cache_async(entry, gfp_mask, vma, vmf->address, &page_allocated); if (!page) continue; if (page_allocated) { swap_readpage(page, false); if (i != ra_info.offset) { SetPageReadahead(page); count_vm_event(SWAP_RA); } } put_page(page); } blk_finish_plug(&plug); lru_add_drain(); skip: return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address, ra_info.win == 1); } /** * swapin_readahead - swap in pages in hope we need them soon * @entry: swap entry of this memory * @gfp_mask: memory allocation flags * @vmf: fault information * * Returns the struct page for entry and addr, after queueing swapin. * * It's a main entry function for swap readahead. By the configuration, * it will read ahead blocks by cluster-based(ie, physical disk based) * or vma-based(ie, virtual address based on faulty address) readahead. */ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_fault *vmf) { return swap_use_vma_readahead() ? swap_vma_readahead(entry, gfp_mask, vmf) : swap_cluster_readahead(entry, gfp_mask, vmf); } #ifdef CONFIG_SYSFS static ssize_t vma_ra_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", enable_vma_readahead ? "true" : "false"); } static ssize_t vma_ra_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) enable_vma_readahead = true; else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) enable_vma_readahead = false; else return -EINVAL; return count; } static struct kobj_attribute vma_ra_enabled_attr = __ATTR(vma_ra_enabled, 0644, vma_ra_enabled_show, vma_ra_enabled_store); static struct attribute *swap_attrs[] = { &vma_ra_enabled_attr.attr, NULL, }; static const struct attribute_group swap_attr_group = { .attrs = swap_attrs, }; static int __init swap_init_sysfs(void) { int err; struct kobject *swap_kobj; swap_kobj = kobject_create_and_add("swap", mm_kobj); if (!swap_kobj) { pr_err("failed to create swap kobject\n"); return -ENOMEM; } err = sysfs_create_group(swap_kobj, &swap_attr_group); if (err) { pr_err("failed to register swap group\n"); goto delete_obj; } return 0; delete_obj: kobject_put(swap_kobj); return err; } subsys_initcall(swap_init_sysfs); #endif |
| 11 11 10 12 1 1 5 5 11 11 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 | // SPDX-License-Identifier: GPL-2.0 /* * XFRM virtual interface * * Copyright (C) 2018 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> */ #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/sockios.h> #include <linux/icmp.h> #include <linux/if.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_link.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/route.h> #include <linux/rtnetlink.h> #include <linux/netfilter_ipv6.h> #include <linux/slab.h> #include <linux/hash.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <net/icmp.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/ip_tunnels.h> #include <net/addrconf.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/etherdevice.h> static int xfrmi_dev_init(struct net_device *dev); static void xfrmi_dev_setup(struct net_device *dev); static struct rtnl_link_ops xfrmi_link_ops __read_mostly; static unsigned int xfrmi_net_id __read_mostly; static const struct net_device_ops xfrmi_netdev_ops; #define XFRMI_HASH_BITS 8 #define XFRMI_HASH_SIZE BIT(XFRMI_HASH_BITS) struct xfrmi_net { /* lists for storing interfaces in use */ struct xfrm_if __rcu *xfrmi[XFRMI_HASH_SIZE]; }; #define for_each_xfrmi_rcu(start, xi) \ for (xi = rcu_dereference(start); xi; xi = rcu_dereference(xi->next)) static u32 xfrmi_hash(u32 if_id) { return hash_32(if_id, XFRMI_HASH_BITS); } static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x) { struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); struct xfrm_if *xi; for_each_xfrmi_rcu(xfrmn->xfrmi[xfrmi_hash(x->if_id)], xi) { if (x->if_id == xi->p.if_id && (xi->dev->flags & IFF_UP)) return xi; } return NULL; } static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb, unsigned short family) { struct net_device *dev; int ifindex = 0; if (!secpath_exists(skb) || !skb->dev) return NULL; switch (family) { case AF_INET6: ifindex = inet6_sdif(skb); break; case AF_INET: ifindex = inet_sdif(skb); break; } if (ifindex) { struct net *net = xs_net(xfrm_input_state(skb)); dev = dev_get_by_index_rcu(net, ifindex); } else { dev = skb->dev; } if (!dev || !(dev->flags & IFF_UP)) return NULL; if (dev->netdev_ops != &xfrmi_netdev_ops) return NULL; return netdev_priv(dev); } static void xfrmi_link(struct xfrmi_net *xfrmn, struct xfrm_if *xi) { struct xfrm_if __rcu **xip = &xfrmn->xfrmi[xfrmi_hash(xi->p.if_id)]; rcu_assign_pointer(xi->next , rtnl_dereference(*xip)); rcu_assign_pointer(*xip, xi); } static void xfrmi_unlink(struct xfrmi_net *xfrmn, struct xfrm_if *xi) { struct xfrm_if __rcu **xip; struct xfrm_if *iter; for (xip = &xfrmn->xfrmi[xfrmi_hash(xi->p.if_id)]; (iter = rtnl_dereference(*xip)) != NULL; xip = &iter->next) { if (xi == iter) { rcu_assign_pointer(*xip, xi->next); break; } } } static void xfrmi_dev_free(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); gro_cells_destroy(&xi->gro_cells); free_percpu(dev->tstats); } static int xfrmi_create(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct net *net = dev_net(dev); struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); int err; dev->rtnl_link_ops = &xfrmi_link_ops; err = register_netdevice(dev); if (err < 0) goto out; xfrmi_link(xfrmn, xi); return 0; out: return err; } static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p) { struct xfrm_if __rcu **xip; struct xfrm_if *xi; struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); for (xip = &xfrmn->xfrmi[xfrmi_hash(p->if_id)]; (xi = rtnl_dereference(*xip)) != NULL; xip = &xi->next) if (xi->p.if_id == p->if_id) return xi; return NULL; } static void xfrmi_dev_uninit(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct xfrmi_net *xfrmn = net_generic(xi->net, xfrmi_net_id); xfrmi_unlink(xfrmn, xi); } static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) { skb->tstamp = 0; skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); nf_reset_ct(skb); nf_reset_trace(skb); if (!xnet) return; ipvs_reset(skb); secpath_reset(skb); skb_orphan(skb); skb->mark = 0; } static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; struct net_device *dev; struct xfrm_state *x; struct xfrm_if *xi; bool xnet; if (err && !secpath_exists(skb)) return 0; x = xfrm_input_state(skb); xi = xfrmi_lookup(xs_net(x), x); if (!xi) return 1; dev = xi->dev; skb->dev = dev; if (err) { dev->stats.rx_errors++; dev->stats.rx_dropped++; return 0; } xnet = !net_eq(xi->net, dev_net(skb->dev)); if (xnet) { inner_mode = &x->inner_mode; if (x->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); if (inner_mode == NULL) { XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMINSTATEMODEERROR); return -EINVAL; } } if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, inner_mode->family)) return -EPERM; } xfrmi_scrub_packet(skb, xnet); dev_sw_netstats_rx_add(dev, skb->len); return 0; } static int xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct xfrm_if *xi = netdev_priv(dev); struct net_device_stats *stats = &xi->dev->stats; struct dst_entry *dst = skb_dst(skb); unsigned int length = skb->len; struct net_device *tdev; struct xfrm_state *x; int err = -1; int mtu; dst_hold(dst); dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, xi->p.if_id); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto tx_err_link_failure; } x = dst->xfrm; if (!x) goto tx_err_link_failure; if (x->if_id != xi->p.if_id) goto tx_err_link_failure; tdev = dst->dev; if (tdev == dev) { stats->collisions++; net_warn_ratelimited("%s: Local routing loop detected!\n", dev->name); goto tx_err_dst_release; } mtu = dst_mtu(dst); if ((!skb_is_gso(skb) && skb->len > mtu) || (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (skb->len > 1280) icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); else goto xmit; } else { if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) goto xmit; icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } dst_release(dst); return -EMSGSIZE; } xmit: xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = tdev; err = dst_output(xi->net, skb->sk, skb); if (net_xmit_eval(err) == 0) { dev_sw_netstats_tx_add(dev, 1, length); } else { stats->tx_errors++; stats->tx_aborted_errors++; } return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: dst_release(dst); return err; } static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct net_device_stats *stats = &xi->dev->stats; struct dst_entry *dst = skb_dst(skb); struct flowi fl; int ret; memset(&fl, 0, sizeof(fl)); switch (skb->protocol) { case htons(ETH_P_IPV6): memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); xfrm_decode_session(skb, &fl, AF_INET6); if (!dst) { fl.u.ip6.flowi6_oif = dev->ifindex; fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6); if (dst->error) { dst_release(dst); stats->tx_carrier_errors++; goto tx_err; } skb_dst_set(skb, dst); } break; case htons(ETH_P_IP): memset(IPCB(skb), 0, sizeof(*IPCB(skb))); xfrm_decode_session(skb, &fl, AF_INET); if (!dst) { struct rtable *rt; fl.u.ip4.flowi4_oif = dev->ifindex; fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4); if (IS_ERR(rt)) { stats->tx_carrier_errors++; goto tx_err; } skb_dst_set(skb, &rt->dst); } break; default: goto tx_err; } fl.flowi_oif = xi->p.link; ret = xfrmi_xmit2(skb, dev, &fl); if (ret < 0) goto tx_err; return NETDEV_TX_OK; tx_err: stats->tx_errors++; stats->tx_dropped++; kfree_skb(skb); return NETDEV_TX_OK; } static int xfrmi4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct net *net = dev_net(skb->dev); int protocol = iph->protocol; struct ip_comp_hdr *ipch; struct ip_esp_hdr *esph; struct ip_auth_hdr *ah ; struct xfrm_state *x; struct xfrm_if *xi; __be32 spi; switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); spi = esph->spi; break; case IPPROTO_AH: ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); spi = ah->spi; break; case IPPROTO_COMP: ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); spi = htonl(ntohs(ipch->cpi)); break; default: return 0; } switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) return 0; break; case ICMP_REDIRECT: break; default: return 0; } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET); if (!x) return 0; xi = xfrmi_lookup(net, x); if (!xi) { xfrm_state_put(x); return -1; } if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, protocol); else ipv4_redirect(skb, net, 0, protocol); xfrm_state_put(x); return 0; } static int xfrmi6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; struct net *net = dev_net(skb->dev); int protocol = iph->nexthdr; struct ip_comp_hdr *ipch; struct ip_esp_hdr *esph; struct ip_auth_hdr *ah; struct xfrm_state *x; struct xfrm_if *xi; __be32 spi; switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data + offset); spi = esph->spi; break; case IPPROTO_AH: ah = (struct ip_auth_hdr *)(skb->data + offset); spi = ah->spi; break; case IPPROTO_COMP: ipch = (struct ip_comp_hdr *)(skb->data + offset); spi = htonl(ntohs(ipch->cpi)); break; default: return 0; } if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return 0; x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET6); if (!x) return 0; xi = xfrmi_lookup(net, x); if (!xi) { xfrm_state_put(x); return -1; } if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); else ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); xfrm_state_put(x); return 0; } static int xfrmi_change(struct xfrm_if *xi, const struct xfrm_if_parms *p) { if (xi->p.link != p->link) return -EINVAL; xi->p.if_id = p->if_id; return 0; } static int xfrmi_update(struct xfrm_if *xi, struct xfrm_if_parms *p) { struct net *net = xi->net; struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); int err; xfrmi_unlink(xfrmn, xi); synchronize_net(); err = xfrmi_change(xi, p); xfrmi_link(xfrmn, xi); netdev_state_change(xi->dev); return err; } static int xfrmi_get_iflink(const struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); return xi->p.link; } static const struct net_device_ops xfrmi_netdev_ops = { .ndo_init = xfrmi_dev_init, .ndo_uninit = xfrmi_dev_uninit, .ndo_start_xmit = xfrmi_xmit, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = xfrmi_get_iflink, }; static void xfrmi_dev_setup(struct net_device *dev) { dev->netdev_ops = &xfrmi_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_NONE; dev->mtu = ETH_DATA_LEN; dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP_MAX_MTU; dev->flags = IFF_NOARP; dev->needs_free_netdev = true; dev->priv_destructor = xfrmi_dev_free; netif_keep_dst(dev); eth_broadcast_addr(dev->broadcast); } #define XFRMI_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_GSO_SOFTWARE | \ NETIF_F_HW_CSUM) static int xfrmi_dev_init(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct net_device *phydev = __dev_get_by_index(xi->net, xi->p.link); int err; dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; err = gro_cells_init(&xi->gro_cells, dev); if (err) { free_percpu(dev->tstats); return err; } dev->features |= NETIF_F_LLTX; dev->features |= XFRMI_FEATURES; dev->hw_features |= XFRMI_FEATURES; if (phydev) { dev->needed_headroom = phydev->needed_headroom; dev->needed_tailroom = phydev->needed_tailroom; if (is_zero_ether_addr(dev->dev_addr)) eth_hw_addr_inherit(dev, phydev); if (is_zero_ether_addr(dev->broadcast)) memcpy(dev->broadcast, phydev->broadcast, dev->addr_len); } else { eth_hw_addr_random(dev); eth_broadcast_addr(dev->broadcast); } return 0; } static int xfrmi_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { return 0; } static void xfrmi_netlink_parms(struct nlattr *data[], struct xfrm_if_parms *parms) { memset(parms, 0, sizeof(*parms)); if (!data) return; if (data[IFLA_XFRM_LINK]) parms->link = nla_get_u32(data[IFLA_XFRM_LINK]); if (data[IFLA_XFRM_IF_ID]) parms->if_id = nla_get_u32(data[IFLA_XFRM_IF_ID]); } static int xfrmi_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct xfrm_if_parms p = {}; struct xfrm_if *xi; int err; xfrmi_netlink_parms(data, &p); if (!p.if_id) { NL_SET_ERR_MSG(extack, "if_id must be non zero"); return -EINVAL; } xi = xfrmi_locate(net, &p); if (xi) return -EEXIST; xi = netdev_priv(dev); xi->p = p; xi->net = net; xi->dev = dev; err = xfrmi_create(dev); return err; } static void xfrmi_dellink(struct net_device *dev, struct list_head *head) { unregister_netdevice_queue(dev, head); } static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct xfrm_if *xi = netdev_priv(dev); struct net *net = xi->net; struct xfrm_if_parms p = {}; xfrmi_netlink_parms(data, &p); if (!p.if_id) { NL_SET_ERR_MSG(extack, "if_id must be non zero"); return -EINVAL; } xi = xfrmi_locate(net, &p); if (!xi) { xi = netdev_priv(dev); } else { if (xi->dev != dev) return -EEXIST; } return xfrmi_update(xi, &p); } static size_t xfrmi_get_size(const struct net_device *dev) { return /* IFLA_XFRM_LINK */ nla_total_size(4) + /* IFLA_XFRM_IF_ID */ nla_total_size(4) + 0; } static int xfrmi_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct xfrm_if_parms *parm = &xi->p; if (nla_put_u32(skb, IFLA_XFRM_LINK, parm->link) || nla_put_u32(skb, IFLA_XFRM_IF_ID, parm->if_id)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct net *xfrmi_get_link_net(const struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); return xi->net; } static const struct nla_policy xfrmi_policy[IFLA_XFRM_MAX + 1] = { [IFLA_XFRM_LINK] = { .type = NLA_U32 }, [IFLA_XFRM_IF_ID] = { .type = NLA_U32 }, }; static struct rtnl_link_ops xfrmi_link_ops __read_mostly = { .kind = "xfrm", .maxtype = IFLA_XFRM_MAX, .policy = xfrmi_policy, .priv_size = sizeof(struct xfrm_if), .setup = xfrmi_dev_setup, .validate = xfrmi_validate, .newlink = xfrmi_newlink, .dellink = xfrmi_dellink, .changelink = xfrmi_changelink, .get_size = xfrmi_get_size, .fill_info = xfrmi_fill_info, .get_link_net = xfrmi_get_link_net, }; static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list) { struct net *net; LIST_HEAD(list); rtnl_lock(); list_for_each_entry(net, net_exit_list, exit_list) { struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); struct xfrm_if __rcu **xip; struct xfrm_if *xi; int i; for (i = 0; i < XFRMI_HASH_SIZE; i++) { for (xip = &xfrmn->xfrmi[i]; (xi = rtnl_dereference(*xip)) != NULL; xip = &xi->next) unregister_netdevice_queue(xi->dev, &list); } } unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations xfrmi_net_ops = { .exit_batch = xfrmi_exit_batch_net, .id = &xfrmi_net_id, .size = sizeof(struct xfrmi_net), }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { .handler = xfrm6_rcv, .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, }; static struct xfrm6_protocol xfrmi_ah6_protocol __read_mostly = { .handler = xfrm6_rcv, .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, }; static struct xfrm6_protocol xfrmi_ipcomp6_protocol __read_mostly = { .handler = xfrm6_rcv, .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, }; #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) static int xfrmi6_rcv_tunnel(struct sk_buff *skb) { const xfrm_address_t *saddr; __be32 spi; saddr = (const xfrm_address_t *)&ipv6_hdr(skb)->saddr; spi = xfrm6_tunnel_spi_lookup(dev_net(skb->dev), saddr); return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi, NULL); } static struct xfrm6_tunnel xfrmi_ipv6_handler __read_mostly = { .handler = xfrmi6_rcv_tunnel, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 2, }; static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { .handler = xfrmi6_rcv_tunnel, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 2, }; #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { .handler = xfrm4_rcv, .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, }; static struct xfrm4_protocol xfrmi_ah4_protocol __read_mostly = { .handler = xfrm4_rcv, .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, }; static struct xfrm4_protocol xfrmi_ipcomp4_protocol __read_mostly = { .handler = xfrm4_rcv, .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, }; #if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL) static int xfrmi4_rcv_tunnel(struct sk_buff *skb) { return xfrm4_rcv_spi(skb, IPPROTO_IPIP, ip_hdr(skb)->saddr); } static struct xfrm_tunnel xfrmi_ipip_handler __read_mostly = { .handler = xfrmi4_rcv_tunnel, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 3, }; static struct xfrm_tunnel xfrmi_ipip6_handler __read_mostly = { .handler = xfrmi4_rcv_tunnel, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 2, }; #endif static int __init xfrmi4_init(void) { int err; err = xfrm4_protocol_register(&xfrmi_esp4_protocol, IPPROTO_ESP); if (err < 0) goto xfrm_proto_esp_failed; err = xfrm4_protocol_register(&xfrmi_ah4_protocol, IPPROTO_AH); if (err < 0) goto xfrm_proto_ah_failed; err = xfrm4_protocol_register(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; #if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL) err = xfrm4_tunnel_register(&xfrmi_ipip_handler, AF_INET); if (err < 0) goto xfrm_tunnel_ipip_failed; err = xfrm4_tunnel_register(&xfrmi_ipip6_handler, AF_INET6); if (err < 0) goto xfrm_tunnel_ipip6_failed; #endif return 0; #if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL) xfrm_tunnel_ipip6_failed: xfrm4_tunnel_deregister(&xfrmi_ipip_handler, AF_INET); xfrm_tunnel_ipip_failed: xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); #endif xfrm_proto_comp_failed: xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); xfrm_proto_ah_failed: xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP); xfrm_proto_esp_failed: return err; } static void xfrmi4_fini(void) { #if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL) xfrm4_tunnel_deregister(&xfrmi_ipip6_handler, AF_INET6); xfrm4_tunnel_deregister(&xfrmi_ipip_handler, AF_INET); #endif xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP); } static int __init xfrmi6_init(void) { int err; err = xfrm6_protocol_register(&xfrmi_esp6_protocol, IPPROTO_ESP); if (err < 0) goto xfrm_proto_esp_failed; err = xfrm6_protocol_register(&xfrmi_ah6_protocol, IPPROTO_AH); if (err < 0) goto xfrm_proto_ah_failed; err = xfrm6_protocol_register(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) err = xfrm6_tunnel_register(&xfrmi_ipv6_handler, AF_INET6); if (err < 0) goto xfrm_tunnel_ipv6_failed; err = xfrm6_tunnel_register(&xfrmi_ip6ip_handler, AF_INET); if (err < 0) goto xfrm_tunnel_ip6ip_failed; #endif return 0; #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) xfrm_tunnel_ip6ip_failed: xfrm6_tunnel_deregister(&xfrmi_ipv6_handler, AF_INET6); xfrm_tunnel_ipv6_failed: xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); #endif xfrm_proto_comp_failed: xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); xfrm_proto_ah_failed: xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP); xfrm_proto_esp_failed: return err; } static void xfrmi6_fini(void) { #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) xfrm6_tunnel_deregister(&xfrmi_ip6ip_handler, AF_INET); xfrm6_tunnel_deregister(&xfrmi_ipv6_handler, AF_INET6); #endif xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP); } static const struct xfrm_if_cb xfrm_if_cb = { .decode_session = xfrmi_decode_session, }; static int __init xfrmi_init(void) { const char *msg; int err; pr_info("IPsec XFRM device driver\n"); msg = "tunnel device"; err = register_pernet_device(&xfrmi_net_ops); if (err < 0) goto pernet_dev_failed; msg = "xfrm4 protocols"; err = xfrmi4_init(); if (err < 0) goto xfrmi4_failed; msg = "xfrm6 protocols"; err = xfrmi6_init(); if (err < 0) goto xfrmi6_failed; msg = "netlink interface"; err = rtnl_link_register(&xfrmi_link_ops); if (err < 0) goto rtnl_link_failed; xfrm_if_register_cb(&xfrm_if_cb); return err; rtnl_link_failed: xfrmi6_fini(); xfrmi6_failed: xfrmi4_fini(); xfrmi4_failed: unregister_pernet_device(&xfrmi_net_ops); pernet_dev_failed: pr_err("xfrmi init: failed to register %s\n", msg); return err; } static void __exit xfrmi_fini(void) { xfrm_if_unregister_cb(); rtnl_link_unregister(&xfrmi_link_ops); xfrmi4_fini(); xfrmi6_fini(); unregister_pernet_device(&xfrmi_net_ops); } module_init(xfrmi_init); module_exit(xfrmi_fini); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("xfrm"); MODULE_ALIAS_NETDEV("xfrm0"); MODULE_AUTHOR("Steffen Klassert"); MODULE_DESCRIPTION("XFRM virtual interface"); |
| 5 5 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Spanning tree protocol; BPDU handling * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/kernel.h> #include <linux/netfilter_bridge.h> #include <linux/etherdevice.h> #include <linux/llc.h> #include <linux/slab.h> #include <linux/pkt_sched.h> #include <net/net_namespace.h> #include <net/llc.h> #include <net/llc_pdu.h> #include <net/stp.h> #include <asm/unaligned.h> #include "br_private.h" #include "br_private_stp.h" #define STP_HZ 256 #define LLC_RESERVE sizeof(struct llc_pdu_un) static int br_send_bpdu_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { return dev_queue_xmit(skb); } static void br_send_bpdu(struct net_bridge_port *p, const unsigned char *data, int length) { struct sk_buff *skb; skb = dev_alloc_skb(length+LLC_RESERVE); if (!skb) return; skb->dev = p->dev; skb->protocol = htons(ETH_P_802_2); skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, LLC_RESERVE); __skb_put_data(skb, data, length); llc_pdu_header_init(skb, LLC_PDU_TYPE_U, LLC_SAP_BSPAN, LLC_SAP_BSPAN, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(skb); llc_mac_hdr_init(skb, p->dev->dev_addr, p->br->group_addr); skb_reset_mac_header(skb); NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, dev_net(p->dev), NULL, skb, NULL, skb->dev, br_send_bpdu_finish); } static inline void br_set_ticks(unsigned char *dest, int j) { unsigned long ticks = (STP_HZ * j)/ HZ; put_unaligned_be16(ticks, dest); } static inline int br_get_ticks(const unsigned char *src) { unsigned long ticks = get_unaligned_be16(src); return DIV_ROUND_UP(ticks * HZ, STP_HZ); } /* called under bridge lock */ void br_send_config_bpdu(struct net_bridge_port *p, struct br_config_bpdu *bpdu) { unsigned char buf[35]; if (p->br->stp_enabled != BR_KERNEL_STP) return; buf[0] = 0; buf[1] = 0; buf[2] = 0; buf[3] = BPDU_TYPE_CONFIG; buf[4] = (bpdu->topology_change ? 0x01 : 0) | (bpdu->topology_change_ack ? 0x80 : 0); buf[5] = bpdu->root.prio[0]; buf[6] = bpdu->root.prio[1]; buf[7] = bpdu->root.addr[0]; buf[8] = bpdu->root.addr[1]; buf[9] = bpdu->root.addr[2]; buf[10] = bpdu->root.addr[3]; buf[11] = bpdu->root.addr[4]; buf[12] = bpdu->root.addr[5]; buf[13] = (bpdu->root_path_cost >> 24) & 0xFF; buf[14] = (bpdu->root_path_cost >> 16) & 0xFF; buf[15] = (bpdu->root_path_cost >> 8) & 0xFF; buf[16] = bpdu->root_path_cost & 0xFF; buf[17] = bpdu->bridge_id.prio[0]; buf[18] = bpdu->bridge_id.prio[1]; buf[19] = bpdu->bridge_id.addr[0]; buf[20] = bpdu->bridge_id.addr[1]; buf[21] = bpdu->bridge_id.addr[2]; buf[22] = bpdu->bridge_id.addr[3]; buf[23] = bpdu->bridge_id.addr[4]; buf[24] = bpdu->bridge_id.addr[5]; buf[25] = (bpdu->port_id >> 8) & 0xFF; buf[26] = bpdu->port_id & 0xFF; br_set_ticks(buf+27, bpdu->message_age); br_set_ticks(buf+29, bpdu->max_age); br_set_ticks(buf+31, bpdu->hello_time); br_set_ticks(buf+33, bpdu->forward_delay); br_send_bpdu(p, buf, 35); p->stp_xstats.tx_bpdu++; } /* called under bridge lock */ void br_send_tcn_bpdu(struct net_bridge_port *p) { unsigned char buf[4]; if (p->br->stp_enabled != BR_KERNEL_STP) return; buf[0] = 0; buf[1] = 0; buf[2] = 0; buf[3] = BPDU_TYPE_TCN; br_send_bpdu(p, buf, 4); p->stp_xstats.tx_tcn++; } /* * Called from llc. * * NO locks, but rcu_read_lock */ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, struct net_device *dev) { struct net_bridge_port *p; struct net_bridge *br; const unsigned char *buf; if (!pskb_may_pull(skb, 4)) goto err; /* compare of protocol id and version */ buf = skb->data; if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0) goto err; p = br_port_get_check_rcu(dev); if (!p) goto err; br = p->br; spin_lock(&br->lock); if (br->stp_enabled != BR_KERNEL_STP) goto out; if (!(br->dev->flags & IFF_UP)) goto out; if (p->state == BR_STATE_DISABLED) goto out; if (!ether_addr_equal(eth_hdr(skb)->h_dest, br->group_addr)) goto out; if (p->flags & BR_BPDU_GUARD) { br_notice(br, "BPDU received on blocked port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); br_stp_disable_port(p); goto out; } buf = skb_pull(skb, 3); if (buf[0] == BPDU_TYPE_CONFIG) { struct br_config_bpdu bpdu; if (!pskb_may_pull(skb, 32)) goto out; buf = skb->data; bpdu.topology_change = (buf[1] & 0x01) ? 1 : 0; bpdu.topology_change_ack = (buf[1] & 0x80) ? 1 : 0; bpdu.root.prio[0] = buf[2]; bpdu.root.prio[1] = buf[3]; bpdu.root.addr[0] = buf[4]; bpdu.root.addr[1] = buf[5]; bpdu.root.addr[2] = buf[6]; bpdu.root.addr[3] = buf[7]; bpdu.root.addr[4] = buf[8]; bpdu.root.addr[5] = buf[9]; bpdu.root_path_cost = (buf[10] << 24) | (buf[11] << 16) | (buf[12] << 8) | buf[13]; bpdu.bridge_id.prio[0] = buf[14]; bpdu.bridge_id.prio[1] = buf[15]; bpdu.bridge_id.addr[0] = buf[16]; bpdu.bridge_id.addr[1] = buf[17]; bpdu.bridge_id.addr[2] = buf[18]; bpdu.bridge_id.addr[3] = buf[19]; bpdu.bridge_id.addr[4] = buf[20]; bpdu.bridge_id.addr[5] = buf[21]; bpdu.port_id = (buf[22] << 8) | buf[23]; bpdu.message_age = br_get_ticks(buf+24); bpdu.max_age = br_get_ticks(buf+26); bpdu.hello_time = br_get_ticks(buf+28); bpdu.forward_delay = br_get_ticks(buf+30); if (bpdu.message_age > bpdu.max_age) { if (net_ratelimit()) br_notice(p->br, "port %u config from %pM" " (message_age %ul > max_age %ul)\n", p->port_no, eth_hdr(skb)->h_source, bpdu.message_age, bpdu.max_age); goto out; } br_received_config_bpdu(p, &bpdu); } else if (buf[0] == BPDU_TYPE_TCN) { br_received_tcn_bpdu(p); } out: spin_unlock(&br->lock); err: kfree_skb(skb); } |
| 737 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* L2TP core. * * Copyright (c) 2008,2009,2010 Katalix Systems Ltd * * This file contains some code of the original L2TPv2 pppol2tp * driver, which has the following copyright: * * Authors: Martijn van Oosterhout <kleptog@svana.org> * James Chapman (jchapman@katalix.com) * Contributors: * Michal Ostrowski <mostrows@speakeasy.net> * Arnaldo Carvalho de Melo <acme@xconectiva.com.br> * David S. Miller (davem@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/string.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/spinlock.h> #include <linux/kthread.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/jiffies.h> #include <linux/netdevice.h> #include <linux/net.h> #include <linux/inetdevice.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/udp.h> #include <linux/l2tp.h> #include <linux/hash.h> #include <linux/sort.h> #include <linux/file.h> #include <linux/nsproxy.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/dst.h> #include <net/ip.h> #include <net/udp.h> #include <net/udp_tunnel.h> #include <net/inet_common.h> #include <net/xfrm.h> #include <net/protocol.h> #include <net/inet6_connection_sock.h> #include <net/inet_ecn.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <asm/byteorder.h> #include <linux/atomic.h> #include "l2tp_core.h" #include "trace.h" #define CREATE_TRACE_POINTS #include "trace.h" #define L2TP_DRV_VERSION "V2.0" /* L2TP header constants */ #define L2TP_HDRFLAG_T 0x8000 #define L2TP_HDRFLAG_L 0x4000 #define L2TP_HDRFLAG_S 0x0800 #define L2TP_HDRFLAG_O 0x0200 #define L2TP_HDRFLAG_P 0x0100 #define L2TP_HDR_VER_MASK 0x000F #define L2TP_HDR_VER_2 0x0002 #define L2TP_HDR_VER_3 0x0003 /* L2TPv3 default L2-specific sublayer */ #define L2TP_SLFLAG_S 0x40000000 #define L2TP_SL_SEQ_MASK 0x00ffffff #define L2TP_HDR_SIZE_MAX 14 /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 #define L2TP_DEPTH_NESTING 2 #if L2TP_DEPTH_NESTING == SINGLE_DEPTH_NESTING #error "L2TP requires its own lockdep subclass" #endif /* Private data stored for received packets in the skb. */ struct l2tp_skb_cb { u32 ns; u16 has_seq; u16 length; unsigned long expires; }; #define L2TP_SKB_CB(skb) ((struct l2tp_skb_cb *)&(skb)->cb[sizeof(struct inet_skb_parm)]) static struct workqueue_struct *l2tp_wq; /* per-net private data for this module */ static unsigned int l2tp_net_id; struct l2tp_net { /* Lock for write access to l2tp_tunnel_idr */ spinlock_t l2tp_tunnel_idr_lock; struct idr l2tp_tunnel_idr; struct hlist_head l2tp_session_hlist[L2TP_HASH_SIZE_2]; /* Lock for write access to l2tp_session_hlist */ spinlock_t l2tp_session_hlist_lock; }; #if IS_ENABLED(CONFIG_IPV6) static bool l2tp_sk_is_v6(struct sock *sk) { return sk->sk_family == PF_INET6 && !ipv6_addr_v4mapped(&sk->sk_v6_daddr); } #endif static inline struct l2tp_net *l2tp_pernet(const struct net *net) { return net_generic(net, l2tp_net_id); } /* Session hash global list for L2TPv3. * The session_id SHOULD be random according to RFC3931, but several * L2TP implementations use incrementing session_ids. So we do a real * hash on the session_id, rather than a simple bitmask. */ static inline struct hlist_head * l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id) { return &pn->l2tp_session_hlist[hash_32(session_id, L2TP_HASH_BITS_2)]; } /* Session hash list. * The session_id SHOULD be random according to RFC2661, but several * L2TP implementations (Cisco and Microsoft) use incrementing * session_ids. So we do a real hash on the session_id, rather than a * simple bitmask. */ static inline struct hlist_head * l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id) { return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)]; } static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { trace_free_tunnel(tunnel); sock_put(tunnel->sock); /* the tunnel is freed in the socket destructor */ } static void l2tp_session_free(struct l2tp_session *session) { trace_free_session(session); if (session->tunnel) l2tp_tunnel_dec_refcount(session->tunnel); kfree(session); } struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk) { struct l2tp_tunnel *tunnel = sk->sk_user_data; if (tunnel) if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) return NULL; return tunnel; } EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel); void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) { refcount_inc(&tunnel->ref_count); } EXPORT_SYMBOL_GPL(l2tp_tunnel_inc_refcount); void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) { if (refcount_dec_and_test(&tunnel->ref_count)) l2tp_tunnel_free(tunnel); } EXPORT_SYMBOL_GPL(l2tp_tunnel_dec_refcount); void l2tp_session_inc_refcount(struct l2tp_session *session) { refcount_inc(&session->ref_count); } EXPORT_SYMBOL_GPL(l2tp_session_inc_refcount); void l2tp_session_dec_refcount(struct l2tp_session *session) { if (refcount_dec_and_test(&session->ref_count)) l2tp_session_free(session); } EXPORT_SYMBOL_GPL(l2tp_session_dec_refcount); /* Lookup a tunnel. A new reference is held on the returned tunnel. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) { const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel; rcu_read_lock_bh(); tunnel = idr_find(&pn->l2tp_tunnel_idr, tunnel_id); if (tunnel && refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_tunnel_get); struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) { struct l2tp_net *pn = l2tp_pernet(net); unsigned long tunnel_id, tmp; struct l2tp_tunnel *tunnel; int count = 0; rcu_read_lock_bh(); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { if (tunnel && ++count > nth && refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth); struct l2tp_session *l2tp_tunnel_get_session(struct l2tp_tunnel *tunnel, u32 session_id) { struct hlist_head *session_list; struct l2tp_session *session; session_list = l2tp_session_id_hash(tunnel, session_id); read_lock_bh(&tunnel->hlist_lock); hlist_for_each_entry(session, session_list, hlist) if (session->session_id == session_id) { l2tp_session_inc_refcount(session); read_unlock_bh(&tunnel->hlist_lock); return session; } read_unlock_bh(&tunnel->hlist_lock); return NULL; } EXPORT_SYMBOL_GPL(l2tp_tunnel_get_session); struct l2tp_session *l2tp_session_get(const struct net *net, u32 session_id) { struct hlist_head *session_list; struct l2tp_session *session; session_list = l2tp_session_id_hash_2(l2tp_pernet(net), session_id); rcu_read_lock_bh(); hlist_for_each_entry_rcu(session, session_list, global_hlist) if (session->session_id == session_id) { l2tp_session_inc_refcount(session); rcu_read_unlock_bh(); return session; } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_session_get); struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth) { int hash; struct l2tp_session *session; int count = 0; read_lock_bh(&tunnel->hlist_lock); for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) { if (++count > nth) { l2tp_session_inc_refcount(session); read_unlock_bh(&tunnel->hlist_lock); return session; } } } read_unlock_bh(&tunnel->hlist_lock); return NULL; } EXPORT_SYMBOL_GPL(l2tp_session_get_nth); /* Lookup a session by interface name. * This is very inefficient but is only used by management interfaces. */ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname) { struct l2tp_net *pn = l2tp_pernet(net); int hash; struct l2tp_session *session; rcu_read_lock_bh(); for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) { hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) { if (!strcmp(session->ifname, ifname)) { l2tp_session_inc_refcount(session); rcu_read_unlock_bh(); return session; } } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname); int l2tp_session_register(struct l2tp_session *session, struct l2tp_tunnel *tunnel) { struct l2tp_session *session_walk; struct hlist_head *g_head; struct hlist_head *head; struct l2tp_net *pn; int err; head = l2tp_session_id_hash(tunnel, session->session_id); write_lock_bh(&tunnel->hlist_lock); if (!tunnel->acpt_newsess) { err = -ENODEV; goto err_tlock; } hlist_for_each_entry(session_walk, head, hlist) if (session_walk->session_id == session->session_id) { err = -EEXIST; goto err_tlock; } if (tunnel->version == L2TP_HDR_VER_3) { pn = l2tp_pernet(tunnel->l2tp_net); g_head = l2tp_session_id_hash_2(pn, session->session_id); spin_lock_bh(&pn->l2tp_session_hlist_lock); /* IP encap expects session IDs to be globally unique, while * UDP encap doesn't. */ hlist_for_each_entry(session_walk, g_head, global_hlist) if (session_walk->session_id == session->session_id && (session_walk->tunnel->encap == L2TP_ENCAPTYPE_IP || tunnel->encap == L2TP_ENCAPTYPE_IP)) { err = -EEXIST; goto err_tlock_pnlock; } l2tp_tunnel_inc_refcount(tunnel); hlist_add_head_rcu(&session->global_hlist, g_head); spin_unlock_bh(&pn->l2tp_session_hlist_lock); } else { l2tp_tunnel_inc_refcount(tunnel); } hlist_add_head(&session->hlist, head); write_unlock_bh(&tunnel->hlist_lock); trace_register_session(session); return 0; err_tlock_pnlock: spin_unlock_bh(&pn->l2tp_session_hlist_lock); err_tlock: write_unlock_bh(&tunnel->hlist_lock); return err; } EXPORT_SYMBOL_GPL(l2tp_session_register); /***************************************************************************** * Receive data handling *****************************************************************************/ /* Queue a skb in order. We come here only if the skb has an L2TP sequence * number. */ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *skb) { struct sk_buff *skbp; struct sk_buff *tmp; u32 ns = L2TP_SKB_CB(skb)->ns; spin_lock_bh(&session->reorder_q.lock); skb_queue_walk_safe(&session->reorder_q, skbp, tmp) { if (L2TP_SKB_CB(skbp)->ns > ns) { __skb_queue_before(&session->reorder_q, skbp, skb); atomic_long_inc(&session->stats.rx_oos_packets); goto out; } } __skb_queue_tail(&session->reorder_q, skb); out: spin_unlock_bh(&session->reorder_q.lock); } /* Dequeue a single skb. */ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff *skb) { struct l2tp_tunnel *tunnel = session->tunnel; int length = L2TP_SKB_CB(skb)->length; /* We're about to requeue the skb, so return resources * to its current owner (a socket receive buffer). */ skb_orphan(skb); atomic_long_inc(&tunnel->stats.rx_packets); atomic_long_add(length, &tunnel->stats.rx_bytes); atomic_long_inc(&session->stats.rx_packets); atomic_long_add(length, &session->stats.rx_bytes); if (L2TP_SKB_CB(skb)->has_seq) { /* Bump our Nr */ session->nr++; session->nr &= session->nr_max; trace_session_seqnum_update(session); } /* call private receive handler */ if (session->recv_skb) (*session->recv_skb)(session, skb, L2TP_SKB_CB(skb)->length); else kfree_skb(skb); } /* Dequeue skbs from the session's reorder_q, subject to packet order. * Skbs that have been in the queue for too long are simply discarded. */ static void l2tp_recv_dequeue(struct l2tp_session *session) { struct sk_buff *skb; struct sk_buff *tmp; /* If the pkt at the head of the queue has the nr that we * expect to send up next, dequeue it and any other * in-sequence packets behind it. */ start: spin_lock_bh(&session->reorder_q.lock); skb_queue_walk_safe(&session->reorder_q, skb, tmp) { struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); /* If the packet has been pending on the queue for too long, discard it */ if (time_after(jiffies, cb->expires)) { atomic_long_inc(&session->stats.rx_seq_discards); atomic_long_inc(&session->stats.rx_errors); trace_session_pkt_expired(session, cb->ns); session->reorder_skip = 1; __skb_unlink(skb, &session->reorder_q); kfree_skb(skb); continue; } if (cb->has_seq) { if (session->reorder_skip) { session->reorder_skip = 0; session->nr = cb->ns; trace_session_seqnum_reset(session); } if (cb->ns != session->nr) goto out; } __skb_unlink(skb, &session->reorder_q); /* Process the skb. We release the queue lock while we * do so to let other contexts process the queue. */ spin_unlock_bh(&session->reorder_q.lock); l2tp_recv_dequeue_skb(session, skb); goto start; } out: spin_unlock_bh(&session->reorder_q.lock); } static int l2tp_seq_check_rx_window(struct l2tp_session *session, u32 nr) { u32 nws; if (nr >= session->nr) nws = nr - session->nr; else nws = (session->nr_max + 1) - (session->nr - nr); return nws < session->nr_window_size; } /* If packet has sequence numbers, queue it if acceptable. Returns 0 if * acceptable, else non-zero. */ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) { struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); if (!l2tp_seq_check_rx_window(session, cb->ns)) { /* Packet sequence number is outside allowed window. * Discard it. */ trace_session_pkt_outside_rx_window(session, cb->ns); goto discard; } if (session->reorder_timeout != 0) { /* Packet reordering enabled. Add skb to session's * reorder queue, in order of ns. */ l2tp_recv_queue_skb(session, skb); goto out; } /* Packet reordering disabled. Discard out-of-sequence packets, while * tracking the number if in-sequence packets after the first OOS packet * is seen. After nr_oos_count_max in-sequence packets, reset the * sequence number to re-enable packet reception. */ if (cb->ns == session->nr) { skb_queue_tail(&session->reorder_q, skb); } else { u32 nr_oos = cb->ns; u32 nr_next = (session->nr_oos + 1) & session->nr_max; if (nr_oos == nr_next) session->nr_oos_count++; else session->nr_oos_count = 0; session->nr_oos = nr_oos; if (session->nr_oos_count > session->nr_oos_count_max) { session->reorder_skip = 1; } if (!session->reorder_skip) { atomic_long_inc(&session->stats.rx_seq_discards); trace_session_pkt_oos(session, cb->ns); goto discard; } skb_queue_tail(&session->reorder_q, skb); } out: return 0; discard: return 1; } /* Do receive processing of L2TP data frames. We handle both L2TPv2 * and L2TPv3 data frames here. * * L2TPv2 Data Message Header * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |T|L|x|x|S|x|O|P|x|x|x|x| Ver | Length (opt) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Tunnel ID | Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ns (opt) | Nr (opt) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Offset Size (opt) | Offset pad... (opt) * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Data frames are marked by T=0. All other fields are the same as * those in L2TP control frames. * * L2TPv3 Data Message Header * * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | L2TP Session Header | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | L2-Specific Sublayer | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Tunnel Payload ... * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * L2TPv3 Session Header Over IP * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Cookie (optional, maximum 64 bits)... * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * L2TPv3 L2-Specific Sublayer Format * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |x|S|x|x|x|x|x|x| Sequence Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Cookie value and sublayer format are negotiated with the peer when * the session is set up. Unlike L2TPv2, we do not need to parse the * packet header to determine if optional fields are present. * * Caller must already have parsed the frame and determined that it is * a data (not control) frame before coming here. Fields up to the * session-id have already been parsed and ptr points to the data * after the session-id. */ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, int length) { struct l2tp_tunnel *tunnel = session->tunnel; int offset; /* Parse and check optional cookie */ if (session->peer_cookie_len > 0) { if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) { pr_debug_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n", tunnel->name, tunnel->tunnel_id, session->session_id); atomic_long_inc(&session->stats.rx_cookie_discards); goto discard; } ptr += session->peer_cookie_len; } /* Handle the optional sequence numbers. Sequence numbers are * in different places for L2TPv2 and L2TPv3. * * If we are the LAC, enable/disable sequence numbers under * the control of the LNS. If no sequence numbers present but * we were expecting them, discard frame. */ L2TP_SKB_CB(skb)->has_seq = 0; if (tunnel->version == L2TP_HDR_VER_2) { if (hdrflags & L2TP_HDRFLAG_S) { /* Store L2TP info in the skb */ L2TP_SKB_CB(skb)->ns = ntohs(*(__be16 *)ptr); L2TP_SKB_CB(skb)->has_seq = 1; ptr += 2; /* Skip past nr in the header */ ptr += 2; } } else if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) { u32 l2h = ntohl(*(__be32 *)ptr); if (l2h & 0x40000000) { /* Store L2TP info in the skb */ L2TP_SKB_CB(skb)->ns = l2h & 0x00ffffff; L2TP_SKB_CB(skb)->has_seq = 1; } ptr += 4; } if (L2TP_SKB_CB(skb)->has_seq) { /* Received a packet with sequence numbers. If we're the LAC, * check if we sre sending sequence numbers and if not, * configure it so. */ if (!session->lns_mode && !session->send_seq) { trace_session_seqnum_lns_enable(session); session->send_seq = 1; l2tp_session_set_header_len(session, tunnel->version); } } else { /* No sequence numbers. * If user has configured mandatory sequence numbers, discard. */ if (session->recv_seq) { pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } /* If we're the LAC and we're sending sequence numbers, the * LNS has requested that we no longer send sequence numbers. * If we're the LNS and we're sending sequence numbers, the * LAC is broken. Discard the frame. */ if (!session->lns_mode && session->send_seq) { trace_session_seqnum_lns_disable(session); session->send_seq = 0; l2tp_session_set_header_len(session, tunnel->version); } else if (session->send_seq) { pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } } /* Session data offset is defined only for L2TPv2 and is * indicated by an optional 16-bit value in the header. */ if (tunnel->version == L2TP_HDR_VER_2) { /* If offset bit set, skip it. */ if (hdrflags & L2TP_HDRFLAG_O) { offset = ntohs(*(__be16 *)ptr); ptr += 2 + offset; } } offset = ptr - optr; if (!pskb_may_pull(skb, offset)) goto discard; __skb_pull(skb, offset); /* Prepare skb for adding to the session's reorder_q. Hold * packets for max reorder_timeout or 1 second if not * reordering. */ L2TP_SKB_CB(skb)->length = length; L2TP_SKB_CB(skb)->expires = jiffies + (session->reorder_timeout ? session->reorder_timeout : HZ); /* Add packet to the session's receive queue. Reordering is done here, if * enabled. Saved L2TP protocol info is stored in skb->sb[]. */ if (L2TP_SKB_CB(skb)->has_seq) { if (l2tp_recv_data_seq(session, skb)) goto discard; } else { /* No sequence numbers. Add the skb to the tail of the * reorder queue. This ensures that it will be * delivered after all previous sequenced skbs. */ skb_queue_tail(&session->reorder_q, skb); } /* Try to dequeue as many skbs from reorder_q as we can. */ l2tp_recv_dequeue(session); return; discard: atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); } EXPORT_SYMBOL_GPL(l2tp_recv_common); /* Drop skbs from the session's reorder_q */ static void l2tp_session_queue_purge(struct l2tp_session *session) { struct sk_buff *skb = NULL; while ((skb = skb_dequeue(&session->reorder_q))) { atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); } } /* Internal UDP receive frame. Do the real work of receiving an L2TP data frame * here. The skb is not on a list when we get here. * Returns 0 if the packet was a data packet and was successfully passed on. * Returns 1 if the packet was not a good data packet and could not be * forwarded. All such packets are passed up to userspace to deal with. */ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) { struct l2tp_session *session = NULL; unsigned char *ptr, *optr; u16 hdrflags; u32 tunnel_id, session_id; u16 version; int length; /* UDP has verified checksum */ /* UDP always verifies the packet length. */ __skb_pull(skb, sizeof(struct udphdr)); /* Short packet? */ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { pr_debug_ratelimited("%s: recv short packet (len=%d)\n", tunnel->name, skb->len); goto invalid; } /* Point to L2TP header */ optr = skb->data; ptr = skb->data; /* Get L2TP header flags */ hdrflags = ntohs(*(__be16 *)ptr); /* Check protocol version */ version = hdrflags & L2TP_HDR_VER_MASK; if (version != tunnel->version) { pr_debug_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", tunnel->name, version, tunnel->version); goto invalid; } /* Get length of L2TP packet */ length = skb->len; /* If type is control packet, it is handled by userspace. */ if (hdrflags & L2TP_HDRFLAG_T) goto pass; /* Skip flags */ ptr += 2; if (tunnel->version == L2TP_HDR_VER_2) { /* If length is present, skip it */ if (hdrflags & L2TP_HDRFLAG_L) ptr += 2; /* Extract tunnel and session ID */ tunnel_id = ntohs(*(__be16 *)ptr); ptr += 2; session_id = ntohs(*(__be16 *)ptr); ptr += 2; } else { ptr += 2; /* skip reserved bits */ tunnel_id = tunnel->tunnel_id; session_id = ntohl(*(__be32 *)ptr); ptr += 4; } /* Find the session context */ session = l2tp_tunnel_get_session(tunnel, session_id); if (!session || !session->recv_skb) { if (session) l2tp_session_dec_refcount(session); /* Not found? Pass to userspace to deal with */ pr_debug_ratelimited("%s: no session found (%u/%u). Passing up.\n", tunnel->name, tunnel_id, session_id); goto pass; } if (tunnel->version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { l2tp_session_dec_refcount(session); goto invalid; } l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); return 0; invalid: atomic_long_inc(&tunnel->stats.rx_invalid); pass: /* Put UDP header back */ __skb_push(skb, sizeof(struct udphdr)); return 1; } /* UDP encapsulation receive handler. See net/ipv4/udp.c. * Return codes: * 0 : success. * <0: error * >0: skb should be passed up to userspace as UDP. */ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_tunnel *tunnel; /* Note that this is called from the encap_rcv hook inside an * RCU-protected region, but without the socket being locked. * Hence we use rcu_dereference_sk_user_data to access the * tunnel data structure rather the usual l2tp_sk_to_tunnel * accessor function. */ tunnel = rcu_dereference_sk_user_data(sk); if (!tunnel) goto pass_up; if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) goto pass_up; if (l2tp_udp_recv_core(tunnel, skb)) goto pass_up; return 0; pass_up: return 1; } EXPORT_SYMBOL_GPL(l2tp_udp_encap_recv); /************************************************************************ * Transmit handling ***********************************************************************/ /* Build an L2TP header for the session into the buffer provided. */ static int l2tp_build_l2tpv2_header(struct l2tp_session *session, void *buf) { struct l2tp_tunnel *tunnel = session->tunnel; __be16 *bufp = buf; __be16 *optr = buf; u16 flags = L2TP_HDR_VER_2; u32 tunnel_id = tunnel->peer_tunnel_id; u32 session_id = session->peer_session_id; if (session->send_seq) flags |= L2TP_HDRFLAG_S; /* Setup L2TP header. */ *bufp++ = htons(flags); *bufp++ = htons(tunnel_id); *bufp++ = htons(session_id); if (session->send_seq) { *bufp++ = htons(session->ns); *bufp++ = 0; session->ns++; session->ns &= 0xffff; trace_session_seqnum_update(session); } return bufp - optr; } static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf) { struct l2tp_tunnel *tunnel = session->tunnel; char *bufp = buf; char *optr = bufp; /* Setup L2TP header. The header differs slightly for UDP and * IP encapsulations. For UDP, there is 4 bytes of flags. */ if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { u16 flags = L2TP_HDR_VER_3; *((__be16 *)bufp) = htons(flags); bufp += 2; *((__be16 *)bufp) = 0; bufp += 2; } *((__be32 *)bufp) = htonl(session->peer_session_id); bufp += 4; if (session->cookie_len) { memcpy(bufp, &session->cookie[0], session->cookie_len); bufp += session->cookie_len; } if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) { u32 l2h = 0; if (session->send_seq) { l2h = 0x40000000 | session->ns; session->ns++; session->ns &= 0xffffff; trace_session_seqnum_update(session); } *((__be32 *)bufp) = htonl(l2h); bufp += 4; } return bufp - optr; } /* Queue the packet to IP for output: tunnel socket lock must be held */ static int l2tp_xmit_queue(struct l2tp_tunnel *tunnel, struct sk_buff *skb, struct flowi *fl) { int err; skb->ignore_df = 1; skb_dst_drop(skb); #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(tunnel->sock)) err = inet6_csk_xmit(tunnel->sock, skb, NULL); else #endif err = ip_queue_xmit(tunnel->sock, skb, fl); return err >= 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; } static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, unsigned int *len) { struct l2tp_tunnel *tunnel = session->tunnel; unsigned int data_len = skb->len; struct sock *sk = tunnel->sock; int headroom, uhlen, udp_len; int ret = NET_XMIT_SUCCESS; struct inet_sock *inet; struct udphdr *uh; /* Check that there's enough headroom in the skb to insert IP, * UDP and L2TP headers. If not enough, expand it to * make room. Adjust truesize. */ uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(*uh) : 0; headroom = NET_SKB_PAD + sizeof(struct iphdr) + uhlen + session->hdr_len; if (skb_cow_head(skb, headroom)) { kfree_skb(skb); return NET_XMIT_DROP; } /* Setup L2TP header */ if (tunnel->version == L2TP_HDR_VER_2) l2tp_build_l2tpv2_header(session, __skb_push(skb, session->hdr_len)); else l2tp_build_l2tpv3_header(session, __skb_push(skb, session->hdr_len)); /* Reset skb netfilter state */ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); nf_reset_ct(skb); /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by * nested socket calls on the same lockdep socket class. This can * happen when data from a user socket is routed over l2tp, which uses * another userspace socket. */ spin_lock_nested(&sk->sk_lock.slock, L2TP_DEPTH_NESTING); if (sock_owned_by_user(sk)) { kfree_skb(skb); ret = NET_XMIT_DROP; goto out_unlock; } /* The user-space may change the connection status for the user-space * provided socket at run time: we must check it under the socket lock */ if (tunnel->fd >= 0 && sk->sk_state != TCP_ESTABLISHED) { kfree_skb(skb); ret = NET_XMIT_DROP; goto out_unlock; } /* Report transmitted length before we add encap header, which keeps * statistics consistent for both UDP and IP encap tx/rx paths. */ *len = skb->len; inet = inet_sk(sk); switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* Setup UDP header */ __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->source = inet->inet_sport; uh->dest = inet->inet_dport; udp_len = uhlen + session->hdr_len + data_len; uh->len = htons(udp_len); /* Calculate UDP checksum if configured to do so */ #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(sk)) udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr, &sk->sk_v6_daddr, udp_len); else #endif udp_set_csum(sk->sk_no_check_tx, skb, inet->inet_saddr, inet->inet_daddr, udp_len); break; case L2TP_ENCAPTYPE_IP: break; } ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl); out_unlock: spin_unlock(&sk->sk_lock.slock); return ret; } /* If caller requires the skb to have a ppp header, the header must be * inserted in the skb data before calling this function. */ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb) { unsigned int len = 0; int ret; ret = l2tp_xmit_core(session, skb, &len); if (ret == NET_XMIT_SUCCESS) { atomic_long_inc(&session->tunnel->stats.tx_packets); atomic_long_add(len, &session->tunnel->stats.tx_bytes); atomic_long_inc(&session->stats.tx_packets); atomic_long_add(len, &session->stats.tx_bytes); } else { atomic_long_inc(&session->tunnel->stats.tx_errors); atomic_long_inc(&session->stats.tx_errors); } return ret; } EXPORT_SYMBOL_GPL(l2tp_xmit_skb); /***************************************************************************** * Tinnel and session create/destroy. *****************************************************************************/ /* Tunnel socket destruct hook. * The tunnel context is deleted only when all session sockets have been * closed. */ static void l2tp_tunnel_destruct(struct sock *sk) { struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); if (!tunnel) goto end; /* Disable udp encapsulation */ switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* No longer an encapsulation socket. See net/ipv4/udp.c */ (udp_sk(sk))->encap_type = 0; (udp_sk(sk))->encap_rcv = NULL; (udp_sk(sk))->encap_destroy = NULL; break; case L2TP_ENCAPTYPE_IP: break; } /* Remove hooks into tunnel socket */ write_lock_bh(&sk->sk_callback_lock); sk->sk_destruct = tunnel->old_sk_destruct; sk->sk_user_data = NULL; write_unlock_bh(&sk->sk_callback_lock); /* Call the original destructor */ if (sk->sk_destruct) (*sk->sk_destruct)(sk); kfree_rcu(tunnel, rcu); end: return; } /* Remove an l2tp session from l2tp_core's hash lists. */ static void l2tp_session_unhash(struct l2tp_session *session) { struct l2tp_tunnel *tunnel = session->tunnel; /* Remove the session from core hashes */ if (tunnel) { /* Remove from the per-tunnel hash */ write_lock_bh(&tunnel->hlist_lock); hlist_del_init(&session->hlist); write_unlock_bh(&tunnel->hlist_lock); /* For L2TPv3 we have a per-net hash: remove from there, too */ if (tunnel->version != L2TP_HDR_VER_2) { struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); spin_lock_bh(&pn->l2tp_session_hlist_lock); hlist_del_init_rcu(&session->global_hlist); spin_unlock_bh(&pn->l2tp_session_hlist_lock); synchronize_rcu(); } } } /* When the tunnel is closed, all the attached sessions need to go too. */ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) { int hash; struct hlist_node *walk; struct hlist_node *tmp; struct l2tp_session *session; write_lock_bh(&tunnel->hlist_lock); tunnel->acpt_newsess = false; for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { again: hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) { session = hlist_entry(walk, struct l2tp_session, hlist); hlist_del_init(&session->hlist); write_unlock_bh(&tunnel->hlist_lock); l2tp_session_delete(session); write_lock_bh(&tunnel->hlist_lock); /* Now restart from the beginning of this hash * chain. We always remove a session from the * list so we are guaranteed to make forward * progress. */ goto again; } } write_unlock_bh(&tunnel->hlist_lock); } /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) l2tp_tunnel_delete(tunnel); } static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel) { struct l2tp_net *pn = l2tp_pernet(net); spin_lock_bh(&pn->l2tp_tunnel_idr_lock); idr_remove(&pn->l2tp_tunnel_idr, tunnel->tunnel_id); spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); } /* Workqueue tunnel deletion function */ static void l2tp_tunnel_del_work(struct work_struct *work) { struct l2tp_tunnel *tunnel = container_of(work, struct l2tp_tunnel, del_work); struct sock *sk = tunnel->sock; struct socket *sock = sk->sk_socket; l2tp_tunnel_closeall(tunnel); /* If the tunnel socket was created within the kernel, use * the sk API to release it here. */ if (tunnel->fd < 0) { if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } } l2tp_tunnel_remove(tunnel->l2tp_net, tunnel); /* drop initial ref */ l2tp_tunnel_dec_refcount(tunnel); /* drop workqueue ref */ l2tp_tunnel_dec_refcount(tunnel); } /* Create a socket for the tunnel, if one isn't set up by * userspace. This is used for static tunnels where there is no * managing L2TP daemon. * * Since we don't want these sockets to keep a namespace alive by * themselves, we drop the socket's namespace refcount after creation. * These sockets are freed when the namespace exits using the pernet * exit hook. */ static int l2tp_tunnel_sock_create(struct net *net, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct socket **sockp) { int err = -EINVAL; struct socket *sock = NULL; struct udp_port_cfg udp_conf; switch (cfg->encap) { case L2TP_ENCAPTYPE_UDP: memset(&udp_conf, 0, sizeof(udp_conf)); #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { udp_conf.family = AF_INET6; memcpy(&udp_conf.local_ip6, cfg->local_ip6, sizeof(udp_conf.local_ip6)); memcpy(&udp_conf.peer_ip6, cfg->peer_ip6, sizeof(udp_conf.peer_ip6)); udp_conf.use_udp6_tx_checksums = !cfg->udp6_zero_tx_checksums; udp_conf.use_udp6_rx_checksums = !cfg->udp6_zero_rx_checksums; } else #endif { udp_conf.family = AF_INET; udp_conf.local_ip = cfg->local_ip; udp_conf.peer_ip = cfg->peer_ip; udp_conf.use_udp_checksums = cfg->use_udp_checksums; } udp_conf.local_udp_port = htons(cfg->local_udp_port); udp_conf.peer_udp_port = htons(cfg->peer_udp_port); err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) goto out; break; case L2TP_ENCAPTYPE_IP: #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { struct sockaddr_l2tpip6 ip6_addr = {0}; err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, IPPROTO_L2TP, &sock); if (err < 0) goto out; ip6_addr.l2tp_family = AF_INET6; memcpy(&ip6_addr.l2tp_addr, cfg->local_ip6, sizeof(ip6_addr.l2tp_addr)); ip6_addr.l2tp_conn_id = tunnel_id; err = kernel_bind(sock, (struct sockaddr *)&ip6_addr, sizeof(ip6_addr)); if (err < 0) goto out; ip6_addr.l2tp_family = AF_INET6; memcpy(&ip6_addr.l2tp_addr, cfg->peer_ip6, sizeof(ip6_addr.l2tp_addr)); ip6_addr.l2tp_conn_id = peer_tunnel_id; err = kernel_connect(sock, (struct sockaddr *)&ip6_addr, sizeof(ip6_addr), 0); if (err < 0) goto out; } else #endif { struct sockaddr_l2tpip ip_addr = {0}; err = sock_create_kern(net, AF_INET, SOCK_DGRAM, IPPROTO_L2TP, &sock); if (err < 0) goto out; ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->local_ip; ip_addr.l2tp_conn_id = tunnel_id; err = kernel_bind(sock, (struct sockaddr *)&ip_addr, sizeof(ip_addr)); if (err < 0) goto out; ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->peer_ip; ip_addr.l2tp_conn_id = peer_tunnel_id; err = kernel_connect(sock, (struct sockaddr *)&ip_addr, sizeof(ip_addr), 0); if (err < 0) goto out; } break; default: goto out; } out: *sockp = sock; if (err < 0 && sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); *sockp = NULL; } return err; } int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp) { struct l2tp_tunnel *tunnel = NULL; int err; enum l2tp_encap_type encap = L2TP_ENCAPTYPE_UDP; if (cfg) encap = cfg->encap; tunnel = kzalloc(sizeof(*tunnel), GFP_KERNEL); if (!tunnel) { err = -ENOMEM; goto err; } tunnel->version = version; tunnel->tunnel_id = tunnel_id; tunnel->peer_tunnel_id = peer_tunnel_id; tunnel->magic = L2TP_TUNNEL_MAGIC; sprintf(&tunnel->name[0], "tunl %u", tunnel_id); rwlock_init(&tunnel->hlist_lock); tunnel->acpt_newsess = true; tunnel->encap = encap; refcount_set(&tunnel->ref_count, 1); tunnel->fd = fd; /* Init delete workqueue struct */ INIT_WORK(&tunnel->del_work, l2tp_tunnel_del_work); INIT_LIST_HEAD(&tunnel->list); err = 0; err: if (tunnelp) *tunnelp = tunnel; return err; } EXPORT_SYMBOL_GPL(l2tp_tunnel_create); static int l2tp_validate_socket(const struct sock *sk, const struct net *net, enum l2tp_encap_type encap) { if (!net_eq(sock_net(sk), net)) return -EINVAL; if (sk->sk_type != SOCK_DGRAM) return -EPROTONOSUPPORT; if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6) return -EPROTONOSUPPORT; if ((encap == L2TP_ENCAPTYPE_UDP && sk->sk_protocol != IPPROTO_UDP) || (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP)) return -EPROTONOSUPPORT; if (sk->sk_user_data) return -EBUSY; return 0; } int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, struct l2tp_tunnel_cfg *cfg) { struct l2tp_net *pn = l2tp_pernet(net); u32 tunnel_id = tunnel->tunnel_id; struct socket *sock; struct sock *sk; int ret; spin_lock_bh(&pn->l2tp_tunnel_idr_lock); ret = idr_alloc_u32(&pn->l2tp_tunnel_idr, NULL, &tunnel_id, tunnel_id, GFP_ATOMIC); spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); if (ret) return ret == -ENOSPC ? -EEXIST : ret; if (tunnel->fd < 0) { ret = l2tp_tunnel_sock_create(net, tunnel->tunnel_id, tunnel->peer_tunnel_id, cfg, &sock); if (ret < 0) goto err; } else { sock = sockfd_lookup(tunnel->fd, &ret); if (!sock) goto err; } sk = sock->sk; lock_sock(sk); write_lock_bh(&sk->sk_callback_lock); ret = l2tp_validate_socket(sk, net, tunnel->encap); if (ret < 0) goto err_inval_sock; rcu_assign_sk_user_data(sk, tunnel); write_unlock_bh(&sk->sk_callback_lock); if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { struct udp_tunnel_sock_cfg udp_cfg = { .sk_user_data = tunnel, .encap_type = UDP_ENCAP_L2TPINUDP, .encap_rcv = l2tp_udp_encap_recv, .encap_destroy = l2tp_udp_encap_destroy, }; setup_udp_tunnel_sock(net, sock, &udp_cfg); } tunnel->old_sk_destruct = sk->sk_destruct; sk->sk_destruct = &l2tp_tunnel_destruct; sk->sk_allocation = GFP_ATOMIC; release_sock(sk); sock_hold(sk); tunnel->sock = sk; tunnel->l2tp_net = net; spin_lock_bh(&pn->l2tp_tunnel_idr_lock); idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id); spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); trace_register_tunnel(tunnel); if (tunnel->fd >= 0) sockfd_put(sock); return 0; err_inval_sock: write_unlock_bh(&sk->sk_callback_lock); release_sock(sk); if (tunnel->fd < 0) sock_release(sock); else sockfd_put(sock); err: l2tp_tunnel_remove(net, tunnel); return ret; } EXPORT_SYMBOL_GPL(l2tp_tunnel_register); /* This function is used by the netlink TUNNEL_DELETE command. */ void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { if (!test_and_set_bit(0, &tunnel->dead)) { trace_delete_tunnel(tunnel); l2tp_tunnel_inc_refcount(tunnel); queue_work(l2tp_wq, &tunnel->del_work); } } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); void l2tp_session_delete(struct l2tp_session *session) { if (test_and_set_bit(0, &session->dead)) return; trace_delete_session(session); l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close) (*session->session_close)(session); l2tp_session_dec_refcount(session); } EXPORT_SYMBOL_GPL(l2tp_session_delete); /* We come here whenever a session's send_seq, cookie_len or * l2specific_type parameters are set. */ void l2tp_session_set_header_len(struct l2tp_session *session, int version) { if (version == L2TP_HDR_VER_2) { session->hdr_len = 6; if (session->send_seq) session->hdr_len += 4; } else { session->hdr_len = 4 + session->cookie_len; session->hdr_len += l2tp_get_l2specific_len(session); if (session->tunnel->encap == L2TP_ENCAPTYPE_UDP) session->hdr_len += 4; } } EXPORT_SYMBOL_GPL(l2tp_session_set_header_len); struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg) { struct l2tp_session *session; session = kzalloc(sizeof(*session) + priv_size, GFP_KERNEL); if (session) { session->magic = L2TP_SESSION_MAGIC; session->tunnel = tunnel; session->session_id = session_id; session->peer_session_id = peer_session_id; session->nr = 0; if (tunnel->version == L2TP_HDR_VER_2) session->nr_max = 0xffff; else session->nr_max = 0xffffff; session->nr_window_size = session->nr_max / 2; session->nr_oos_count_max = 4; /* Use NR of first received packet */ session->reorder_skip = 1; sprintf(&session->name[0], "sess %u/%u", tunnel->tunnel_id, session->session_id); skb_queue_head_init(&session->reorder_q); INIT_HLIST_NODE(&session->hlist); INIT_HLIST_NODE(&session->global_hlist); if (cfg) { session->pwtype = cfg->pw_type; session->send_seq = cfg->send_seq; session->recv_seq = cfg->recv_seq; session->lns_mode = cfg->lns_mode; session->reorder_timeout = cfg->reorder_timeout; session->l2specific_type = cfg->l2specific_type; session->cookie_len = cfg->cookie_len; memcpy(&session->cookie[0], &cfg->cookie[0], cfg->cookie_len); session->peer_cookie_len = cfg->peer_cookie_len; memcpy(&session->peer_cookie[0], &cfg->peer_cookie[0], cfg->peer_cookie_len); } l2tp_session_set_header_len(session, tunnel->version); refcount_set(&session->ref_count, 1); return session; } return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(l2tp_session_create); /***************************************************************************** * Init and cleanup *****************************************************************************/ static __net_init int l2tp_init_net(struct net *net) { struct l2tp_net *pn = net_generic(net, l2tp_net_id); int hash; idr_init(&pn->l2tp_tunnel_idr); spin_lock_init(&pn->l2tp_tunnel_idr_lock); for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) INIT_HLIST_HEAD(&pn->l2tp_session_hlist[hash]); spin_lock_init(&pn->l2tp_session_hlist_lock); return 0; } static __net_exit void l2tp_exit_net(struct net *net) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; unsigned long tunnel_id, tmp; int hash; rcu_read_lock_bh(); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { if (tunnel) l2tp_tunnel_delete(tunnel); } rcu_read_unlock_bh(); if (l2tp_wq) flush_workqueue(l2tp_wq); rcu_barrier(); for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) WARN_ON_ONCE(!hlist_empty(&pn->l2tp_session_hlist[hash])); idr_destroy(&pn->l2tp_tunnel_idr); } static struct pernet_operations l2tp_net_ops = { .init = l2tp_init_net, .exit = l2tp_exit_net, .id = &l2tp_net_id, .size = sizeof(struct l2tp_net), }; static int __init l2tp_init(void) { int rc = 0; rc = register_pernet_device(&l2tp_net_ops); if (rc) goto out; l2tp_wq = alloc_workqueue("l2tp", WQ_UNBOUND, 0); if (!l2tp_wq) { pr_err("alloc_workqueue failed\n"); unregister_pernet_device(&l2tp_net_ops); rc = -ENOMEM; goto out; } pr_info("L2TP core driver, %s\n", L2TP_DRV_VERSION); out: return rc; } static void __exit l2tp_exit(void) { unregister_pernet_device(&l2tp_net_ops); if (l2tp_wq) { destroy_workqueue(l2tp_wq); l2tp_wq = NULL; } } module_init(l2tp_init); module_exit(l2tp_exit); MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP core"); MODULE_LICENSE("GPL"); MODULE_VERSION(L2TP_DRV_VERSION); |
| 2168 1933 1932 480 480 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Software nodes for the firmware node framework. * * Copyright (C) 2018, Intel Corporation * Author: Heikki Krogerus <heikki.krogerus@linux.intel.com> */ #include <linux/device.h> #include <linux/kernel.h> #include <linux/property.h> #include <linux/slab.h> #include "base.h" struct swnode { struct kobject kobj; struct fwnode_handle fwnode; const struct software_node *node; int id; /* hierarchy */ struct ida child_ids; struct list_head entry; struct list_head children; struct swnode *parent; unsigned int allocated:1; unsigned int managed:1; }; static DEFINE_IDA(swnode_root_ids); static struct kset *swnode_kset; #define kobj_to_swnode(_kobj_) container_of(_kobj_, struct swnode, kobj) static const struct fwnode_operations software_node_ops; bool is_software_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &software_node_ops; } EXPORT_SYMBOL_GPL(is_software_node); #define to_swnode(__fwnode) \ ({ \ typeof(__fwnode) __to_swnode_fwnode = __fwnode; \ \ is_software_node(__to_swnode_fwnode) ? \ container_of(__to_swnode_fwnode, \ struct swnode, fwnode) : NULL; \ }) static inline struct swnode *dev_to_swnode(struct device *dev) { struct fwnode_handle *fwnode = dev_fwnode(dev); if (!fwnode) return NULL; if (!is_software_node(fwnode)) fwnode = fwnode->secondary; return to_swnode(fwnode); } static struct swnode * software_node_to_swnode(const struct software_node *node) { struct swnode *swnode = NULL; struct kobject *k; if (!node) return NULL; spin_lock(&swnode_kset->list_lock); list_for_each_entry(k, &swnode_kset->list, entry) { swnode = kobj_to_swnode(k); if (swnode->node == node) break; swnode = NULL; } spin_unlock(&swnode_kset->list_lock); return swnode; } const struct software_node *to_software_node(const struct fwnode_handle *fwnode) { const struct swnode *swnode = to_swnode(fwnode); return swnode ? swnode->node : NULL; } EXPORT_SYMBOL_GPL(to_software_node); struct fwnode_handle *software_node_fwnode(const struct software_node *node) { struct swnode *swnode = software_node_to_swnode(node); return swnode ? &swnode->fwnode : NULL; } EXPORT_SYMBOL_GPL(software_node_fwnode); /* -------------------------------------------------------------------------- */ /* property_entry processing */ static const struct property_entry * property_entry_get(const struct property_entry *prop, const char *name) { if (!prop) return NULL; for (; prop->name; prop++) if (!strcmp(name, prop->name)) return prop; return NULL; } static const void *property_get_pointer(const struct property_entry *prop) { if (!prop->length) return NULL; return prop->is_inline ? &prop->value : prop->pointer; } static const void *property_entry_find(const struct property_entry *props, const char *propname, size_t length) { const struct property_entry *prop; const void *pointer; prop = property_entry_get(props, propname); if (!prop) return ERR_PTR(-EINVAL); pointer = property_get_pointer(prop); if (!pointer) return ERR_PTR(-ENODATA); if (length > prop->length) return ERR_PTR(-EOVERFLOW); return pointer; } static int property_entry_count_elems_of_size(const struct property_entry *props, const char *propname, size_t length) { const struct property_entry *prop; prop = property_entry_get(props, propname); if (!prop) return -EINVAL; return prop->length / length; } static int property_entry_read_int_array(const struct property_entry *props, const char *name, unsigned int elem_size, void *val, size_t nval) { const void *pointer; size_t length; if (!val) return property_entry_count_elems_of_size(props, name, elem_size); if (!is_power_of_2(elem_size) || elem_size > sizeof(u64)) return -ENXIO; length = nval * elem_size; pointer = property_entry_find(props, name, length); if (IS_ERR(pointer)) return PTR_ERR(pointer); memcpy(val, pointer, length); return 0; } static int property_entry_read_string_array(const struct property_entry *props, const char *propname, const char **strings, size_t nval) { const void *pointer; size_t length; int array_len; /* Find out the array length. */ array_len = property_entry_count_elems_of_size(props, propname, sizeof(const char *)); if (array_len < 0) return array_len; /* Return how many there are if strings is NULL. */ if (!strings) return array_len; array_len = min_t(size_t, nval, array_len); length = array_len * sizeof(*strings); pointer = property_entry_find(props, propname, length); if (IS_ERR(pointer)) return PTR_ERR(pointer); memcpy(strings, pointer, length); return array_len; } static void property_entry_free_data(const struct property_entry *p) { const char * const *src_str; size_t i, nval; if (p->type == DEV_PROP_STRING) { src_str = property_get_pointer(p); nval = p->length / sizeof(*src_str); for (i = 0; i < nval; i++) kfree(src_str[i]); } if (!p->is_inline) kfree(p->pointer); kfree(p->name); } static bool property_copy_string_array(const char **dst_ptr, const char * const *src_ptr, size_t nval) { int i; for (i = 0; i < nval; i++) { dst_ptr[i] = kstrdup(src_ptr[i], GFP_KERNEL); if (!dst_ptr[i] && src_ptr[i]) { while (--i >= 0) kfree(dst_ptr[i]); return false; } } return true; } static int property_entry_copy_data(struct property_entry *dst, const struct property_entry *src) { const void *pointer = property_get_pointer(src); void *dst_ptr; size_t nval; /* * Properties with no data should not be marked as stored * out of line. */ if (!src->is_inline && !src->length) return -ENODATA; /* * Reference properties are never stored inline as * they are too big. */ if (src->type == DEV_PROP_REF && src->is_inline) return -EINVAL; if (src->length <= sizeof(dst->value)) { dst_ptr = &dst->value; dst->is_inline = true; } else { dst_ptr = kmalloc(src->length, GFP_KERNEL); if (!dst_ptr) return -ENOMEM; dst->pointer = dst_ptr; } if (src->type == DEV_PROP_STRING) { nval = src->length / sizeof(const char *); if (!property_copy_string_array(dst_ptr, pointer, nval)) { if (!dst->is_inline) kfree(dst->pointer); return -ENOMEM; } } else { memcpy(dst_ptr, pointer, src->length); } dst->length = src->length; dst->type = src->type; dst->name = kstrdup(src->name, GFP_KERNEL); if (!dst->name) { property_entry_free_data(dst); return -ENOMEM; } return 0; } /** * property_entries_dup - duplicate array of properties * @properties: array of properties to copy * * This function creates a deep copy of the given NULL-terminated array * of property entries. */ struct property_entry * property_entries_dup(const struct property_entry *properties) { struct property_entry *p; int i, n = 0; int ret; if (!properties) return NULL; while (properties[n].name) n++; p = kcalloc(n + 1, sizeof(*p), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); for (i = 0; i < n; i++) { ret = property_entry_copy_data(&p[i], &properties[i]); if (ret) { while (--i >= 0) property_entry_free_data(&p[i]); kfree(p); return ERR_PTR(ret); } } return p; } EXPORT_SYMBOL_GPL(property_entries_dup); /** * property_entries_free - free previously allocated array of properties * @properties: array of properties to destroy * * This function frees given NULL-terminated array of property entries, * along with their data. */ void property_entries_free(const struct property_entry *properties) { const struct property_entry *p; if (!properties) return; for (p = properties; p->name; p++) property_entry_free_data(p); kfree(properties); } EXPORT_SYMBOL_GPL(property_entries_free); /* -------------------------------------------------------------------------- */ /* fwnode operations */ static struct fwnode_handle *software_node_get(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); kobject_get(&swnode->kobj); return &swnode->fwnode; } static void software_node_put(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); kobject_put(&swnode->kobj); } static bool software_node_property_present(const struct fwnode_handle *fwnode, const char *propname) { struct swnode *swnode = to_swnode(fwnode); return !!property_entry_get(swnode->node->properties, propname); } static int software_node_read_int_array(const struct fwnode_handle *fwnode, const char *propname, unsigned int elem_size, void *val, size_t nval) { struct swnode *swnode = to_swnode(fwnode); return property_entry_read_int_array(swnode->node->properties, propname, elem_size, val, nval); } static int software_node_read_string_array(const struct fwnode_handle *fwnode, const char *propname, const char **val, size_t nval) { struct swnode *swnode = to_swnode(fwnode); return property_entry_read_string_array(swnode->node->properties, propname, val, nval); } static const char * software_node_get_name(const struct fwnode_handle *fwnode) { const struct swnode *swnode = to_swnode(fwnode); if (!swnode) return "(null)"; return kobject_name(&swnode->kobj); } static const char * software_node_get_name_prefix(const struct fwnode_handle *fwnode) { struct fwnode_handle *parent; const char *prefix; parent = fwnode_get_parent(fwnode); if (!parent) return ""; /* Figure out the prefix from the parents. */ while (is_software_node(parent)) parent = fwnode_get_next_parent(parent); prefix = fwnode_get_name_prefix(parent); fwnode_handle_put(parent); /* Guess something if prefix was NULL. */ return prefix ?: "/"; } static struct fwnode_handle * software_node_get_parent(const struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); if (!swnode || !swnode->parent) return NULL; return fwnode_handle_get(&swnode->parent->fwnode); } static struct fwnode_handle * software_node_get_next_child(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { struct swnode *p = to_swnode(fwnode); struct swnode *c = to_swnode(child); if (!p || list_empty(&p->children) || (c && list_is_last(&c->entry, &p->children))) { fwnode_handle_put(child); return NULL; } if (c) c = list_next_entry(c, entry); else c = list_first_entry(&p->children, struct swnode, entry); fwnode_handle_put(child); return fwnode_handle_get(&c->fwnode); } static struct fwnode_handle * software_node_get_named_child_node(const struct fwnode_handle *fwnode, const char *childname) { struct swnode *swnode = to_swnode(fwnode); struct swnode *child; if (!swnode || list_empty(&swnode->children)) return NULL; list_for_each_entry(child, &swnode->children, entry) { if (!strcmp(childname, kobject_name(&child->kobj))) { kobject_get(&child->kobj); return &child->fwnode; } } return NULL; } static int software_node_get_reference_args(const struct fwnode_handle *fwnode, const char *propname, const char *nargs_prop, unsigned int nargs, unsigned int index, struct fwnode_reference_args *args) { struct swnode *swnode = to_swnode(fwnode); const struct software_node_ref_args *ref_array; const struct software_node_ref_args *ref; const struct property_entry *prop; struct fwnode_handle *refnode; u32 nargs_prop_val; int error; int i; if (!swnode) return -ENOENT; prop = property_entry_get(swnode->node->properties, propname); if (!prop) return -ENOENT; if (prop->type != DEV_PROP_REF) return -EINVAL; /* * We expect that references are never stored inline, even * single ones, as they are too big. */ if (prop->is_inline) return -EINVAL; if (index * sizeof(*ref) >= prop->length) return -ENOENT; ref_array = prop->pointer; ref = &ref_array[index]; refnode = software_node_fwnode(ref->node); if (!refnode) return -ENOENT; if (nargs_prop) { error = property_entry_read_int_array(ref->node->properties, nargs_prop, sizeof(u32), &nargs_prop_val, 1); if (error) return error; nargs = nargs_prop_val; } if (nargs > NR_FWNODE_REFERENCE_ARGS) return -EINVAL; if (!args) return 0; args->fwnode = software_node_get(refnode); args->nargs = nargs; for (i = 0; i < nargs; i++) args->args[i] = ref->args[i]; return 0; } static struct fwnode_handle * swnode_graph_find_next_port(const struct fwnode_handle *parent, struct fwnode_handle *port) { struct fwnode_handle *old = port; while ((port = software_node_get_next_child(parent, old))) { /* * fwnode ports have naming style "port@", so we search for any * children that follow that convention. */ if (!strncmp(to_swnode(port)->node->name, "port@", strlen("port@"))) return port; old = port; } return NULL; } static struct fwnode_handle * software_node_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *endpoint) { struct swnode *swnode = to_swnode(fwnode); struct fwnode_handle *parent; struct fwnode_handle *port; if (!swnode) return NULL; if (endpoint) { port = software_node_get_parent(endpoint); parent = software_node_get_parent(port); } else { parent = software_node_get_named_child_node(fwnode, "ports"); if (!parent) parent = software_node_get(&swnode->fwnode); port = swnode_graph_find_next_port(parent, NULL); } for (; port; port = swnode_graph_find_next_port(parent, port)) { endpoint = software_node_get_next_child(port, endpoint); if (endpoint) { fwnode_handle_put(port); break; } } fwnode_handle_put(parent); return endpoint; } static struct fwnode_handle * software_node_graph_get_remote_endpoint(const struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); const struct software_node_ref_args *ref; const struct property_entry *prop; if (!swnode) return NULL; prop = property_entry_get(swnode->node->properties, "remote-endpoint"); if (!prop || prop->type != DEV_PROP_REF || prop->is_inline) return NULL; ref = prop->pointer; return software_node_get(software_node_fwnode(ref[0].node)); } static struct fwnode_handle * software_node_graph_get_port_parent(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); swnode = swnode->parent; if (swnode && !strcmp(swnode->node->name, "ports")) swnode = swnode->parent; return swnode ? software_node_get(&swnode->fwnode) : NULL; } static int software_node_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint) { struct swnode *swnode = to_swnode(fwnode); const char *parent_name = swnode->parent->node->name; int ret; if (strlen("port@") >= strlen(parent_name) || strncmp(parent_name, "port@", strlen("port@"))) return -EINVAL; /* Ports have naming style "port@n", we need to select the n */ ret = kstrtou32(parent_name + strlen("port@"), 10, &endpoint->port); if (ret) return ret; endpoint->id = swnode->id; endpoint->local_fwnode = fwnode; return 0; } static const struct fwnode_operations software_node_ops = { .get = software_node_get, .put = software_node_put, .property_present = software_node_property_present, .property_read_int_array = software_node_read_int_array, .property_read_string_array = software_node_read_string_array, .get_name = software_node_get_name, .get_name_prefix = software_node_get_name_prefix, .get_parent = software_node_get_parent, .get_next_child_node = software_node_get_next_child, .get_named_child_node = software_node_get_named_child_node, .get_reference_args = software_node_get_reference_args, .graph_get_next_endpoint = software_node_graph_get_next_endpoint, .graph_get_remote_endpoint = software_node_graph_get_remote_endpoint, .graph_get_port_parent = software_node_graph_get_port_parent, .graph_parse_endpoint = software_node_graph_parse_endpoint, }; /* -------------------------------------------------------------------------- */ /** * software_node_find_by_name - Find software node by name * @parent: Parent of the software node * @name: Name of the software node * * The function will find a node that is child of @parent and that is named * @name. If no node is found, the function returns NULL. * * NOTE: you will need to drop the reference with fwnode_handle_put() after use. */ const struct software_node * software_node_find_by_name(const struct software_node *parent, const char *name) { struct swnode *swnode = NULL; struct kobject *k; if (!name) return NULL; spin_lock(&swnode_kset->list_lock); list_for_each_entry(k, &swnode_kset->list, entry) { swnode = kobj_to_swnode(k); if (parent == swnode->node->parent && swnode->node->name && !strcmp(name, swnode->node->name)) { kobject_get(&swnode->kobj); break; } swnode = NULL; } spin_unlock(&swnode_kset->list_lock); return swnode ? swnode->node : NULL; } EXPORT_SYMBOL_GPL(software_node_find_by_name); static struct software_node *software_node_alloc(const struct property_entry *properties) { struct property_entry *props; struct software_node *node; props = property_entries_dup(properties); if (IS_ERR(props)) return ERR_CAST(props); node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) { property_entries_free(props); return ERR_PTR(-ENOMEM); } node->properties = props; return node; } static void software_node_free(const struct software_node *node) { property_entries_free(node->properties); kfree(node); } static void software_node_release(struct kobject *kobj) { struct swnode *swnode = kobj_to_swnode(kobj); if (swnode->parent) { ida_simple_remove(&swnode->parent->child_ids, swnode->id); list_del(&swnode->entry); } else { ida_simple_remove(&swnode_root_ids, swnode->id); } if (swnode->allocated) software_node_free(swnode->node); ida_destroy(&swnode->child_ids); kfree(swnode); } static struct kobj_type software_node_type = { .release = software_node_release, .sysfs_ops = &kobj_sysfs_ops, }; static struct fwnode_handle * swnode_register(const struct software_node *node, struct swnode *parent, unsigned int allocated) { struct swnode *swnode; int ret; swnode = kzalloc(sizeof(*swnode), GFP_KERNEL); if (!swnode) return ERR_PTR(-ENOMEM); ret = ida_simple_get(parent ? &parent->child_ids : &swnode_root_ids, 0, 0, GFP_KERNEL); if (ret < 0) { kfree(swnode); return ERR_PTR(ret); } swnode->id = ret; swnode->node = node; swnode->parent = parent; swnode->kobj.kset = swnode_kset; fwnode_init(&swnode->fwnode, &software_node_ops); ida_init(&swnode->child_ids); INIT_LIST_HEAD(&swnode->entry); INIT_LIST_HEAD(&swnode->children); if (node->name) ret = kobject_init_and_add(&swnode->kobj, &software_node_type, parent ? &parent->kobj : NULL, "%s", node->name); else ret = kobject_init_and_add(&swnode->kobj, &software_node_type, parent ? &parent->kobj : NULL, "node%d", swnode->id); if (ret) { kobject_put(&swnode->kobj); return ERR_PTR(ret); } /* * Assign the flag only in the successful case, so * the above kobject_put() won't mess up with properties. */ swnode->allocated = allocated; if (parent) list_add_tail(&swnode->entry, &parent->children); kobject_uevent(&swnode->kobj, KOBJ_ADD); return &swnode->fwnode; } /** * software_node_register_nodes - Register an array of software nodes * @nodes: Zero terminated array of software nodes to be registered * * Register multiple software nodes at once. If any node in the array * has its .parent pointer set (which can only be to another software_node), * then its parent **must** have been registered before it is; either outside * of this function or by ordering the array such that parent comes before * child. */ int software_node_register_nodes(const struct software_node *nodes) { int ret; int i; for (i = 0; nodes[i].name; i++) { const struct software_node *parent = nodes[i].parent; if (parent && !software_node_to_swnode(parent)) { ret = -EINVAL; goto err_unregister_nodes; } ret = software_node_register(&nodes[i]); if (ret) goto err_unregister_nodes; } return 0; err_unregister_nodes: software_node_unregister_nodes(nodes); return ret; } EXPORT_SYMBOL_GPL(software_node_register_nodes); /** * software_node_unregister_nodes - Unregister an array of software nodes * @nodes: Zero terminated array of software nodes to be unregistered * * Unregister multiple software nodes at once. If parent pointers are set up * in any of the software nodes then the array **must** be ordered such that * parents come before their children. * * NOTE: If you are uncertain whether the array is ordered such that * parents will be unregistered before their children, it is wiser to * remove the nodes individually, in the correct order (child before * parent). */ void software_node_unregister_nodes(const struct software_node *nodes) { unsigned int i = 0; while (nodes[i].name) i++; while (i--) software_node_unregister(&nodes[i]); } EXPORT_SYMBOL_GPL(software_node_unregister_nodes); /** * software_node_register_node_group - Register a group of software nodes * @node_group: NULL terminated array of software node pointers to be registered * * Register multiple software nodes at once. If any node in the array * has its .parent pointer set (which can only be to another software_node), * then its parent **must** have been registered before it is; either outside * of this function or by ordering the array such that parent comes before * child. */ int software_node_register_node_group(const struct software_node **node_group) { unsigned int i; int ret; if (!node_group) return 0; for (i = 0; node_group[i]; i++) { ret = software_node_register(node_group[i]); if (ret) { software_node_unregister_node_group(node_group); return ret; } } return 0; } EXPORT_SYMBOL_GPL(software_node_register_node_group); /** * software_node_unregister_node_group - Unregister a group of software nodes * @node_group: NULL terminated array of software node pointers to be unregistered * * Unregister multiple software nodes at once. If parent pointers are set up * in any of the software nodes then the array **must** be ordered such that * parents come before their children. * * NOTE: If you are uncertain whether the array is ordered such that * parents will be unregistered before their children, it is wiser to * remove the nodes individually, in the correct order (child before * parent). */ void software_node_unregister_node_group( const struct software_node **node_group) { unsigned int i = 0; if (!node_group) return; while (node_group[i]) i++; while (i--) software_node_unregister(node_group[i]); } EXPORT_SYMBOL_GPL(software_node_unregister_node_group); /** * software_node_register - Register static software node * @node: The software node to be registered */ int software_node_register(const struct software_node *node) { struct swnode *parent = software_node_to_swnode(node->parent); if (software_node_to_swnode(node)) return -EEXIST; if (node->parent && !parent) return -EINVAL; return PTR_ERR_OR_ZERO(swnode_register(node, parent, 0)); } EXPORT_SYMBOL_GPL(software_node_register); /** * software_node_unregister - Unregister static software node * @node: The software node to be unregistered */ void software_node_unregister(const struct software_node *node) { struct swnode *swnode; swnode = software_node_to_swnode(node); if (swnode) fwnode_remove_software_node(&swnode->fwnode); } EXPORT_SYMBOL_GPL(software_node_unregister); struct fwnode_handle * fwnode_create_software_node(const struct property_entry *properties, const struct fwnode_handle *parent) { struct fwnode_handle *fwnode; struct software_node *node; struct swnode *p; if (IS_ERR(parent)) return ERR_CAST(parent); p = to_swnode(parent); if (parent && !p) return ERR_PTR(-EINVAL); node = software_node_alloc(properties); if (IS_ERR(node)) return ERR_CAST(node); node->parent = p ? p->node : NULL; fwnode = swnode_register(node, p, 1); if (IS_ERR(fwnode)) software_node_free(node); return fwnode; } EXPORT_SYMBOL_GPL(fwnode_create_software_node); void fwnode_remove_software_node(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); if (!swnode) return; kobject_put(&swnode->kobj); } EXPORT_SYMBOL_GPL(fwnode_remove_software_node); /** * device_add_software_node - Assign software node to a device * @dev: The device the software node is meant for. * @node: The software node. * * This function will make @node the secondary firmware node pointer of @dev. If * @dev has no primary node, then @node will become the primary node. The * function will register @node automatically if it wasn't already registered. */ int device_add_software_node(struct device *dev, const struct software_node *node) { struct swnode *swnode; int ret; /* Only one software node per device. */ if (dev_to_swnode(dev)) return -EBUSY; swnode = software_node_to_swnode(node); if (swnode) { kobject_get(&swnode->kobj); } else { ret = software_node_register(node); if (ret) return ret; swnode = software_node_to_swnode(node); } set_secondary_fwnode(dev, &swnode->fwnode); /* * If the device has been fully registered by the time this function is * called, software_node_notify() must be called separately so that the * symlinks get created and the reference count of the node is kept in * balance. */ if (device_is_registered(dev)) software_node_notify(dev); return 0; } EXPORT_SYMBOL_GPL(device_add_software_node); /** * device_remove_software_node - Remove device's software node * @dev: The device with the software node. * * This function will unregister the software node of @dev. */ void device_remove_software_node(struct device *dev) { struct swnode *swnode; swnode = dev_to_swnode(dev); if (!swnode) return; if (device_is_registered(dev)) software_node_notify_remove(dev); set_secondary_fwnode(dev, NULL); kobject_put(&swnode->kobj); } EXPORT_SYMBOL_GPL(device_remove_software_node); /** * device_create_managed_software_node - Create a software node for a device * @dev: The device the software node is assigned to. * @properties: Device properties for the software node. * @parent: Parent of the software node. * * Creates a software node as a managed resource for @dev, which means the * lifetime of the newly created software node is tied to the lifetime of @dev. * Software nodes created with this function should not be reused or shared * because of that. The function takes a deep copy of @properties for the * software node. * * Since the new software node is assigned directly to @dev, and since it should * not be shared, it is not returned to the caller. The function returns 0 on * success, and errno in case of an error. */ int device_create_managed_software_node(struct device *dev, const struct property_entry *properties, const struct software_node *parent) { struct fwnode_handle *p = software_node_fwnode(parent); struct fwnode_handle *fwnode; if (parent && !p) return -EINVAL; fwnode = fwnode_create_software_node(properties, p); if (IS_ERR(fwnode)) return PTR_ERR(fwnode); to_swnode(fwnode)->managed = true; set_secondary_fwnode(dev, fwnode); if (device_is_registered(dev)) software_node_notify(dev); return 0; } EXPORT_SYMBOL_GPL(device_create_managed_software_node); void software_node_notify(struct device *dev) { struct swnode *swnode; int ret; swnode = dev_to_swnode(dev); if (!swnode) return; ret = sysfs_create_link(&dev->kobj, &swnode->kobj, "software_node"); if (ret) return; ret = sysfs_create_link(&swnode->kobj, &dev->kobj, dev_name(dev)); if (ret) { sysfs_remove_link(&dev->kobj, "software_node"); return; } kobject_get(&swnode->kobj); } void software_node_notify_remove(struct device *dev) { struct swnode *swnode; swnode = dev_to_swnode(dev); if (!swnode) return; sysfs_remove_link(&swnode->kobj, dev_name(dev)); sysfs_remove_link(&dev->kobj, "software_node"); kobject_put(&swnode->kobj); if (swnode->managed) { set_secondary_fwnode(dev, NULL); kobject_put(&swnode->kobj); } } static int __init software_node_init(void) { swnode_kset = kset_create_and_add("software_nodes", NULL, kernel_kobj); if (!swnode_kset) return -ENOMEM; return 0; } postcore_initcall(software_node_init); static void __exit software_node_exit(void) { ida_destroy(&swnode_root_ids); kset_unregister(swnode_kset); } __exitcall(software_node_exit); |
| 24 48 14 61 61 65 62 14 62 11 62 49 4 3 1 48 51 50 16 49 47 47 46 46 16 13 43 24 16 24 24 7 1 24 24 24 24 24 24 24 24 24 24 24 24 24 65 10 18 20 10 10 20 20 20 20 20 20 19 1 20 20 20 20 3 17 20 3 17 5 45 1 9 7 20 20 20 176 4 4 4 4 4 4 4 4 7 27 4 5 4 4 1 14 2 6 11 21 10 11 2 19 19 1 13 11 64 64 4 61 61 61 61 61 61 61 61 61 45 61 61 21 21 2 1 1 2 1 2 12 17 17 17 86 86 85 50 37 87 45 45 45 45 1 45 1 45 45 45 837 836 837 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 | /* * kernel/cpuset.c * * Processor and Memory placement constraints for sets of tasks. * * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2007 Silicon Graphics, Inc. * Copyright (C) 2006 Google, 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. * 2006 Rework by Paul Menage to use generic cgroups * 2008 Rework of the scheduler domains and CPU hotplug handling * by Max Krasnyansky * * 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. */ #include "cgroup-internal.h" #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/cpuset.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/kthread.h> #include <linux/list.h> #include <linux/mempolicy.h> #include <linux/mm.h> #include <linux/memory.h> #include <linux/export.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/deadline.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/seq_file.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/time.h> #include <linux/time64.h> #include <linux/backing-dev.h> #include <linux/sort.h> #include <linux/oom.h> #include <linux/sched/isolation.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <linux/mutex.h> #include <linux/cgroup.h> #include <linux/wait.h> #include <trace/hooks/sched.h> #include <trace/hooks/cgroup.h> DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); /* See "Frequency meter" comments, below. */ struct fmeter { int cnt; /* unprocessed events count */ int val; /* most recent output value */ time64_t time; /* clock (secs) when val computed */ spinlock_t lock; /* guards read or write of above */ }; struct cpuset { struct cgroup_subsys_state css; unsigned long flags; /* "unsigned long" so bitops work */ /* * On default hierarchy: * * The user-configured masks can only be changed by writing to * cpuset.cpus and cpuset.mems, and won't be limited by the * parent masks. * * The effective masks is the real masks that apply to the tasks * in the cpuset. They may be changed if the configured masks are * changed or hotplug happens. * * effective_mask == configured_mask & parent's effective_mask, * and if it ends up empty, it will inherit the parent's mask. * * * On legacy hierarchy: * * The user-configured masks are always the same with effective masks. */ /* user-configured CPUs and Memory Nodes allow to tasks */ cpumask_var_t cpus_allowed; cpumask_var_t cpus_requested; nodemask_t mems_allowed; /* effective CPUs and Memory Nodes allow to tasks */ cpumask_var_t effective_cpus; nodemask_t effective_mems; /* * CPUs allocated to child sub-partitions (default hierarchy only) * - CPUs granted by the parent = effective_cpus U subparts_cpus * - effective_cpus and subparts_cpus are mutually exclusive. * * effective_cpus contains only onlined CPUs, but subparts_cpus * may have offlined ones. */ cpumask_var_t subparts_cpus; /* * This is old Memory Nodes tasks took on. * * - top_cpuset.old_mems_allowed is initialized to mems_allowed. * - A new cpuset's old_mems_allowed is initialized when some * task is moved into it. * - old_mems_allowed is used in cpuset_migrate_mm() when we change * cpuset.mems_allowed and have tasks' nodemask updated, and * then old_mems_allowed is updated to mems_allowed. */ nodemask_t old_mems_allowed; struct fmeter fmeter; /* memory_pressure filter */ /* * Tasks are being attached to this cpuset. Used to prevent * zeroing cpus/mems_allowed between ->can_attach() and ->attach(). */ int attach_in_progress; /* partition number for rebuild_sched_domains() */ int pn; /* for custom sched domain */ int relax_domain_level; /* number of CPUs in subparts_cpus */ int nr_subparts_cpus; /* partition root state */ int partition_root_state; /* * Default hierarchy only: * use_parent_ecpus - set if using parent's effective_cpus * child_ecpus_count - # of children with use_parent_ecpus set */ int use_parent_ecpus; int child_ecpus_count; /* * number of SCHED_DEADLINE tasks attached to this cpuset, so that we * know when to rebuild associated root domain bandwidth information. */ int nr_deadline_tasks; int nr_migrate_dl_tasks; u64 sum_migrate_dl_bw; /* Handle for cpuset.cpus.partition */ struct cgroup_file partition_file; }; /* * Partition root states: * * 0 - not a partition root * * 1 - partition root * * -1 - invalid partition root * None of the cpus in cpus_allowed can be put into the parent's * subparts_cpus. In this case, the cpuset is not a real partition * root anymore. However, the CPU_EXCLUSIVE bit will still be set * and the cpuset can be restored back to a partition root if the * parent cpuset can give more CPUs back to this child cpuset. */ #define PRS_DISABLED 0 #define PRS_ENABLED 1 #define PRS_ERROR -1 /* * Temporary cpumasks for working with partitions that are passed among * functions to avoid memory allocation in inner functions. */ struct tmpmasks { cpumask_var_t addmask, delmask; /* For partition root */ cpumask_var_t new_cpus; /* For update_cpumasks_hier() */ }; static inline struct cpuset *css_cs(struct cgroup_subsys_state *css) { return css ? container_of(css, struct cpuset, css) : NULL; } /* Retrieve the cpuset for a task */ static inline struct cpuset *task_cs(struct task_struct *task) { return css_cs(task_css(task, cpuset_cgrp_id)); } static inline struct cpuset *parent_cs(struct cpuset *cs) { return css_cs(cs->css.parent); } void inc_dl_tasks_cs(struct task_struct *p) { struct cpuset *cs = task_cs(p); cs->nr_deadline_tasks++; } void dec_dl_tasks_cs(struct task_struct *p) { struct cpuset *cs = task_cs(p); cs->nr_deadline_tasks--; } /* bits in struct cpuset flags field */ typedef enum { CS_ONLINE, CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE, CS_MEM_HARDWALL, CS_MEMORY_MIGRATE, CS_SCHED_LOAD_BALANCE, CS_SPREAD_PAGE, CS_SPREAD_SLAB, } cpuset_flagbits_t; /* convenient tests for these bits */ static inline bool is_cpuset_online(struct cpuset *cs) { return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css); } static inline int is_cpu_exclusive(const struct cpuset *cs) { return test_bit(CS_CPU_EXCLUSIVE, &cs->flags); } static inline int is_mem_exclusive(const struct cpuset *cs) { return test_bit(CS_MEM_EXCLUSIVE, &cs->flags); } static inline int is_mem_hardwall(const struct cpuset *cs) { return test_bit(CS_MEM_HARDWALL, &cs->flags); } static inline int is_sched_load_balance(const struct cpuset *cs) { return test_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); } static inline int is_memory_migrate(const struct cpuset *cs) { return test_bit(CS_MEMORY_MIGRATE, &cs->flags); } static inline int is_spread_page(const struct cpuset *cs) { return test_bit(CS_SPREAD_PAGE, &cs->flags); } static inline int is_spread_slab(const struct cpuset *cs) { return test_bit(CS_SPREAD_SLAB, &cs->flags); } static inline int is_partition_root(const struct cpuset *cs) { return cs->partition_root_state > 0; } /* * Send notification event of whenever partition_root_state changes. */ static inline void notify_partition_change(struct cpuset *cs, int old_prs, int new_prs) { if (old_prs != new_prs) cgroup_file_notify(&cs->partition_file); } static struct cpuset top_cpuset = { .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), .partition_root_state = PRS_ENABLED, }; /** * cpuset_for_each_child - traverse online children of a cpuset * @child_cs: loop cursor pointing to the current child * @pos_css: used for iteration * @parent_cs: target cpuset to walk children of * * Walk @child_cs through the online children of @parent_cs. Must be used * with RCU read locked. */ #define cpuset_for_each_child(child_cs, pos_css, parent_cs) \ css_for_each_child((pos_css), &(parent_cs)->css) \ if (is_cpuset_online(((child_cs) = css_cs((pos_css))))) /** * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants * @des_cs: loop cursor pointing to the current descendant * @pos_css: used for iteration * @root_cs: target cpuset to walk ancestor of * * Walk @des_cs through the online descendants of @root_cs. Must be used * with RCU read locked. The caller may modify @pos_css by calling * css_rightmost_descendant() to skip subtree. @root_cs is included in the * iteration and the first node to be visited. */ #define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs) \ css_for_each_descendant_pre((pos_css), &(root_cs)->css) \ if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) /* * There are two global locks guarding cpuset structures - cpuset_mutex and * callback_lock. We also require taking task_lock() when dereferencing a * task's cpuset pointer. See "The task_lock() exception", at the end of this * comment. The cpuset code uses only cpuset_mutex. Other kernel subsystems * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset * structures. Note that cpuset_mutex needs to be a mutex as it is used in * paths that rely on priority inheritance (e.g. scheduler - on RT) for * correctness. * * A task must hold both locks to modify cpusets. If a task holds * cpuset_mutex, it blocks others, ensuring that it is the only task able to * also acquire callback_lock and be able to modify cpusets. It can perform * various checks on the cpuset structure first, knowing nothing will change. * It can also allocate memory while just holding cpuset_mutex. While it is * performing these checks, various callback routines can briefly acquire * callback_lock to query cpusets. Once it is ready to make the changes, it * takes callback_lock, blocking everyone else. * * Calls to the kernel memory allocator can not be made while holding * callback_lock, as that would risk double tripping on callback_lock * from one of the callbacks into the cpuset code from within * __alloc_pages(). * * If a task is only holding callback_lock, then it has read-only * access to cpusets. * * Now, the task_struct fields mems_allowed and mempolicy may be changed * by other task, we use alloc_lock in the task_struct fields to protect * them. * * The cpuset_common_file_read() handlers only hold callback_lock across * small pieces of code, such as when reading out possibly multi-word * cpumasks and nodemasks. * * Accessing a task's cpuset should be done in accordance with the * guidelines for accessing subsystem state in kernel/cgroup.c */ static DEFINE_MUTEX(cpuset_mutex); void cpuset_lock(void) { mutex_lock(&cpuset_mutex); } void cpuset_unlock(void) { mutex_unlock(&cpuset_mutex); } static DEFINE_SPINLOCK(callback_lock); static struct workqueue_struct *cpuset_migrate_mm_wq; /* * CPU / memory hotplug is handled asynchronously. */ static void cpuset_hotplug_workfn(struct work_struct *work); static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); /* * Cgroup v2 behavior is used on the "cpus" and "mems" control files when * on default hierarchy or when the cpuset_v2_mode flag is set by mounting * the v1 cpuset cgroup filesystem with the "cpuset_v2_mode" mount option. * With v2 behavior, "cpus" and "mems" are always what the users have * requested and won't be changed by hotplug events. Only the effective * cpus or mems will be affected. */ static inline bool is_in_v2_mode(void) { return cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE); } /* * Return in pmask the portion of a task's cpusets's cpus_allowed that * are online and are capable of running the task. If none are found, * walk up the cpuset hierarchy until we find one that does have some * appropriate cpus. * * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_cpus(struct task_struct *tsk, struct cpumask *pmask) { const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); struct cpuset *cs; if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_online_mask))) cpumask_copy(pmask, cpu_online_mask); rcu_read_lock(); cs = task_cs(tsk); while (!cpumask_intersects(cs->effective_cpus, pmask)) { cs = parent_cs(cs); if (unlikely(!cs)) { /* * The top cpuset doesn't have any online cpu as a * consequence of a race between cpuset_hotplug_work * and cpu hotplug notifier. But we know the top * cpuset's effective_cpus is on its way to be * identical to cpu_online_mask. */ goto out_unlock; } } cpumask_and(pmask, pmask, cs->effective_cpus); out_unlock: rcu_read_unlock(); } /* * Return in *pmask the portion of a cpusets's mems_allowed that * are online, with memory. If none are online with memory, walk * up the cpuset hierarchy until we find one that does have some * online mems. The top cpuset always has some mems online. * * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { while (!nodes_intersects(cs->effective_mems, node_states[N_MEMORY])) cs = parent_cs(cs); nodes_and(*pmask, cs->effective_mems, node_states[N_MEMORY]); } /* * update task's spread flag if cpuset's page/slab spread flag is set * * Call with callback_lock or cpuset_mutex held. The check can be skipped * if on default hierarchy. */ static void cpuset_update_task_spread_flag(struct cpuset *cs, struct task_struct *tsk) { if (is_spread_page(cs)) task_set_spread_page(tsk); else task_clear_spread_page(tsk); if (is_spread_slab(cs)) task_set_spread_slab(tsk); else task_clear_spread_slab(tsk); } /* * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q? * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags * are only set if the other's are set. Call holding cpuset_mutex. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) { return cpumask_subset(p->cpus_requested, q->cpus_requested) && nodes_subset(p->mems_allowed, q->mems_allowed) && is_cpu_exclusive(p) <= is_cpu_exclusive(q) && is_mem_exclusive(p) <= is_mem_exclusive(q); } /** * alloc_cpumasks - allocate three cpumasks for cpuset * @cs: the cpuset that have cpumasks to be allocated. * @tmp: the tmpmasks structure pointer * Return: 0 if successful, -ENOMEM otherwise. * * Only one of the two input arguments should be non-NULL. */ static inline int alloc_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) { cpumask_var_t *pmask1, *pmask2, *pmask3; if (cs) { pmask1 = &cs->cpus_allowed; pmask2 = &cs->effective_cpus; pmask3 = &cs->subparts_cpus; } else { pmask1 = &tmp->new_cpus; pmask2 = &tmp->addmask; pmask3 = &tmp->delmask; } if (!zalloc_cpumask_var(pmask1, GFP_KERNEL)) return -ENOMEM; if (!zalloc_cpumask_var(pmask2, GFP_KERNEL)) goto free_one; if (!zalloc_cpumask_var(pmask3, GFP_KERNEL)) goto free_two; if (cs && !zalloc_cpumask_var(&cs->cpus_requested, GFP_KERNEL)) goto free_three; return 0; free_three: free_cpumask_var(*pmask3); free_two: free_cpumask_var(*pmask2); free_one: free_cpumask_var(*pmask1); return -ENOMEM; } /** * free_cpumasks - free cpumasks in a tmpmasks structure * @cs: the cpuset that have cpumasks to be free. * @tmp: the tmpmasks structure pointer */ static inline void free_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) { if (cs) { free_cpumask_var(cs->cpus_allowed); free_cpumask_var(cs->cpus_requested); free_cpumask_var(cs->effective_cpus); free_cpumask_var(cs->subparts_cpus); } if (tmp) { free_cpumask_var(tmp->new_cpus); free_cpumask_var(tmp->addmask); free_cpumask_var(tmp->delmask); } } /** * alloc_trial_cpuset - allocate a trial cpuset * @cs: the cpuset that the trial cpuset duplicates */ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs) { struct cpuset *trial; trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL); if (!trial) return NULL; if (alloc_cpumasks(trial, NULL)) { kfree(trial); return NULL; } cpumask_copy(trial->cpus_allowed, cs->cpus_allowed); cpumask_copy(trial->cpus_requested, cs->cpus_requested); cpumask_copy(trial->effective_cpus, cs->effective_cpus); return trial; } /** * free_cpuset - free the cpuset * @cs: the cpuset to be freed */ static inline void free_cpuset(struct cpuset *cs) { free_cpumasks(cs, NULL); kfree(cs); } /* * validate_change() - Used to validate that any proposed cpuset change * follows the structural rules for cpusets. * * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes * cpuset_mutex held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the * cpuset in the list must use cur below, not trial. * * 'trial' is the address of bulk structure copy of cur, with * perhaps one or more of the fields cpus_allowed, mems_allowed, * or flags changed to new, trial values. * * Return 0 if valid, -errno if not. */ static int validate_change(struct cpuset *cur, struct cpuset *trial) { struct cgroup_subsys_state *css; struct cpuset *c, *par; int ret; rcu_read_lock(); /* Each of our child cpusets must be a subset of us */ ret = -EBUSY; cpuset_for_each_child(c, css, cur) if (!is_cpuset_subset(c, trial)) goto out; /* Remaining checks don't apply to root cpuset */ ret = 0; if (cur == &top_cpuset) goto out; par = parent_cs(cur); /* On legacy hierarchy, we must be a subset of our parent cpuset. */ ret = -EACCES; if (!is_in_v2_mode() && !is_cpuset_subset(trial, par)) goto out; /* * If either I or some sibling (!= me) is exclusive, we can't * overlap */ ret = -EINVAL; cpuset_for_each_child(c, css, par) { if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && c != cur && cpumask_intersects(trial->cpus_requested, c->cpus_requested)) goto out; if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && c != cur && nodes_intersects(trial->mems_allowed, c->mems_allowed)) goto out; } /* * Cpusets with tasks - existing or newly being attached - can't * be changed to have empty cpus_allowed or mems_allowed. */ ret = -ENOSPC; if ((cgroup_is_populated(cur->css.cgroup) || cur->attach_in_progress)) { if (!cpumask_empty(cur->cpus_allowed) && cpumask_empty(trial->cpus_allowed)) goto out; if (!nodes_empty(cur->mems_allowed) && nodes_empty(trial->mems_allowed)) goto out; } /* * We can't shrink if we won't have enough room for SCHED_DEADLINE * tasks. */ ret = -EBUSY; if (is_cpu_exclusive(cur) && !cpuset_cpumask_can_shrink(cur->cpus_allowed, trial->cpus_allowed)) goto out; ret = 0; out: rcu_read_unlock(); return ret; } #ifdef CONFIG_SMP /* * Helper routine for generate_sched_domains(). * Do cpusets a, b have overlapping effective cpus_allowed masks? */ static int cpusets_overlap(struct cpuset *a, struct cpuset *b) { return cpumask_intersects(a->effective_cpus, b->effective_cpus); } static void update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c) { if (dattr->relax_domain_level < c->relax_domain_level) dattr->relax_domain_level = c->relax_domain_level; return; } static void update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *root_cs) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { /* skip the whole subtree if @cp doesn't have any CPU */ if (cpumask_empty(cp->cpus_allowed)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (is_sched_load_balance(cp)) update_domain_attr(dattr, cp); } rcu_read_unlock(); } /* Must be called with cpuset_mutex held. */ static inline int nr_cpusets(void) { /* jump label reference count + the top-level cpuset */ return static_key_count(&cpusets_enabled_key.key) + 1; } /* * generate_sched_domains() * * This function builds a partial partition of the systems CPUs * A 'partial partition' is a set of non-overlapping subsets whose * union is a subset of that set. * The output of this function needs to be passed to kernel/sched/core.c * partition_sched_domains() routine, which will rebuild the scheduler's * load balancing domains (sched domains) as specified by that partial * partition. * * See "What is sched_load_balance" in Documentation/admin-guide/cgroup-v1/cpusets.rst * for a background explanation of this. * * Does not return errors, on the theory that the callers of this * routine would rather not worry about failures to rebuild sched * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * * Must be called with cpuset_mutex held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a * top-down scan of all cpusets. For our purposes, rebuilding * the schedulers sched domains, we can ignore !is_sched_load_ * balance cpusets. * csa - (for CpuSet Array) Array of pointers to all the cpusets * that need to be load balanced, for convenient iterative * access by the subsequent code that finds the best partition, * i.e the set of domains (subsets) of CPUs such that the * cpus_allowed of every cpuset marked is_sched_load_balance * is a subset of one of these domains, while there are as * many such domains as possible, each as small as possible. * doms - Conversion of 'csa' to an array of cpumasks, for passing to * the kernel/sched/core.c routine partition_sched_domains() in a * convenient format, that can be easily compared to the prior * value to determine what partition elements (sched domains) * were changed (added or removed.) * * Finding the best partition (set of domains): * The triple nested loops below over i, j, k scan over the * load balanced cpusets (using the array of cpuset pointers in * csa[]) looking for pairs of cpusets that have overlapping * cpus_allowed, but which don't have the same 'pn' partition * number and gives them in the same partition number. It keeps * looping on the 'restart' label until it can no longer find * any such pairs. * * The union of the cpus_allowed masks from the set of * all cpusets having the same 'pn' value then form the one * element of the partition (one sched domain) to be passed to * partition_sched_domains(). */ static int generate_sched_domains(cpumask_var_t **domains, struct sched_domain_attr **attributes) { struct cpuset *cp; /* top-down scan of cpusets */ struct cpuset **csa; /* array of all cpuset ptrs */ int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] struct cpumask slot */ struct cgroup_subsys_state *pos_css; bool root_load_balance = is_sched_load_balance(&top_cpuset); doms = NULL; dattr = NULL; csa = NULL; /* Special case for the 99% of systems with one, full, sched domain */ if (root_load_balance && !top_cpuset.nr_subparts_cpus) { ndoms = 1; doms = alloc_sched_domains(ndoms); if (!doms) goto done; dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL); if (dattr) { *dattr = SD_ATTR_INIT; update_domain_attr_tree(dattr, &top_cpuset); } cpumask_and(doms[0], top_cpuset.effective_cpus, housekeeping_cpumask(HK_FLAG_DOMAIN)); goto done; } csa = kmalloc_array(nr_cpusets(), sizeof(cp), GFP_KERNEL); if (!csa) goto done; csn = 0; rcu_read_lock(); if (root_load_balance) csa[csn++] = &top_cpuset; cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) { if (cp == &top_cpuset) continue; /* * Continue traversing beyond @cp iff @cp has some CPUs and * isn't load balancing. The former is obvious. The * latter: All child cpusets contain a subset of the * parent's cpus, so just skip them, and then we call * update_domain_attr_tree() to calc relax_domain_level of * the corresponding sched domain. * * If root is load-balancing, we can skip @cp if it * is a subset of the root's effective_cpus. */ if (!cpumask_empty(cp->cpus_allowed) && !(is_sched_load_balance(cp) && cpumask_intersects(cp->cpus_allowed, housekeeping_cpumask(HK_FLAG_DOMAIN)))) continue; if (root_load_balance && cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus)) continue; if (is_sched_load_balance(cp) && !cpumask_empty(cp->effective_cpus)) csa[csn++] = cp; /* skip @cp's subtree if not a partition root */ if (!is_partition_root(cp)) pos_css = css_rightmost_descendant(pos_css); } rcu_read_unlock(); for (i = 0; i < csn; i++) csa[i]->pn = i; ndoms = csn; restart: /* Find the best partition (set of sched domains) */ for (i = 0; i < csn; i++) { struct cpuset *a = csa[i]; int apn = a->pn; for (j = 0; j < csn; j++) { struct cpuset *b = csa[j]; int bpn = b->pn; if (apn != bpn && cpusets_overlap(a, b)) { for (k = 0; k < csn; k++) { struct cpuset *c = csa[k]; if (c->pn == bpn) c->pn = apn; } ndoms--; /* one less element */ goto restart; } } } /* * Now we know how many domains to create. * Convert <csn, csa> to <ndoms, doms> and populate cpu masks. */ doms = alloc_sched_domains(ndoms); if (!doms) goto done; /* * The rest of the code, including the scheduler, can deal with * dattr==NULL case. No need to abort if alloc fails. */ dattr = kmalloc_array(ndoms, sizeof(struct sched_domain_attr), GFP_KERNEL); for (nslot = 0, i = 0; i < csn; i++) { struct cpuset *a = csa[i]; struct cpumask *dp; int apn = a->pn; if (apn < 0) { /* Skip completed partitions */ continue; } dp = doms[nslot]; if (nslot == ndoms) { static int warnings = 10; if (warnings) { pr_warn("rebuild_sched_domains confused: nslot %d, ndoms %d, csn %d, i %d, apn %d\n", nslot, ndoms, csn, i, apn); warnings--; } continue; } cpumask_clear(dp); if (dattr) *(dattr + nslot) = SD_ATTR_INIT; for (j = i; j < csn; j++) { struct cpuset *b = csa[j]; if (apn == b->pn) { cpumask_or(dp, dp, b->effective_cpus); cpumask_and(dp, dp, housekeeping_cpumask(HK_FLAG_DOMAIN)); if (dattr) update_domain_attr_tree(dattr + nslot, b); /* Done with this partition */ b->pn = -1; } } nslot++; } BUG_ON(nslot != ndoms); done: kfree(csa); /* * Fallback to the default domain if kmalloc() failed. * See comments in partition_sched_domains(). */ if (doms == NULL) ndoms = 1; *domains = doms; *attributes = dattr; return ndoms; } static void dl_update_tasks_root_domain(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; if (cs->nr_deadline_tasks == 0) return; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) dl_add_task_root_domain(task); css_task_iter_end(&it); } static void dl_rebuild_rd_accounting(void) { struct cpuset *cs = NULL; struct cgroup_subsys_state *pos_css; lockdep_assert_held(&cpuset_mutex); lockdep_assert_cpus_held(); lockdep_assert_held(&sched_domains_mutex); rcu_read_lock(); /* * Clear default root domain DL accounting, it will be computed again * if a task belongs to it. */ dl_clear_root_domain(&def_root_domain); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cpumask_empty(cs->effective_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; } css_get(&cs->css); rcu_read_unlock(); dl_update_tasks_root_domain(cs); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } static void partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { mutex_lock(&sched_domains_mutex); partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); dl_rebuild_rd_accounting(); mutex_unlock(&sched_domains_mutex); } /* * Rebuild scheduler domains. * * If the flag 'sched_load_balance' of any cpuset with non-empty * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset * which has that flag enabled, or if any cpuset with a non-empty * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * * Call with cpuset_mutex held. Takes cpus_read_lock(). */ static void rebuild_sched_domains_locked(void) { struct cgroup_subsys_state *pos_css; struct sched_domain_attr *attr; cpumask_var_t *doms; struct cpuset *cs; int ndoms; lockdep_assert_cpus_held(); lockdep_assert_held(&cpuset_mutex); /* * If we have raced with CPU hotplug, return early to avoid * passing doms with offlined cpu to partition_sched_domains(). * Anyways, cpuset_hotplug_workfn() will rebuild sched domains. * * With no CPUs in any subpartitions, top_cpuset's effective CPUs * should be the same as the active CPUs, so checking only top_cpuset * is enough to detect racing CPU offlines. */ if (!top_cpuset.nr_subparts_cpus && !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) return; /* * With subpartition CPUs, however, the effective CPUs of a partition * root should be only a subset of the active CPUs. Since a CPU in any * partition root could be offlined, all must be checked. */ if (top_cpuset.nr_subparts_cpus) { rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (!is_partition_root(cs)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (!cpumask_subset(cs->effective_cpus, cpu_active_mask)) { rcu_read_unlock(); return; } } rcu_read_unlock(); } /* Generate domain masks and attrs */ ndoms = generate_sched_domains(&doms, &attr); /* Have scheduler rebuild the domains */ partition_and_rebuild_sched_domains(ndoms, doms, attr); } #else /* !CONFIG_SMP */ static void rebuild_sched_domains_locked(void) { } #endif /* CONFIG_SMP */ void rebuild_sched_domains(void) { cpus_read_lock(); mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); mutex_unlock(&cpuset_mutex); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(rebuild_sched_domains); static int update_cpus_allowed(struct cpuset *cs, struct task_struct *p, const struct cpumask *new_mask) { int ret = -EINVAL; trace_android_rvh_update_cpus_allowed(p, cs->cpus_requested, new_mask, &ret); if (!ret) return ret; return set_cpus_allowed_ptr(p, new_mask); } /** * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed * * Iterate through each task of @cs updating its cpus_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_cpumask(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; bool top_cs = cs == &top_cpuset; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { /* * Percpu kthreads in top_cpuset are ignored */ if (top_cs && (task->flags & PF_KTHREAD) && kthread_is_per_cpu(task)) continue; update_cpus_allowed(cs, task, cs->effective_cpus); } css_task_iter_end(&it); } /** * compute_effective_cpumask - Compute the effective cpumask of the cpuset * @new_cpus: the temp variable for the new effective_cpus mask * @cs: the cpuset the need to recompute the new effective_cpus mask * @parent: the parent cpuset * * If the parent has subpartition CPUs, include them in the list of * allowable CPUs in computing the new effective_cpus mask. Since offlined * CPUs are not removed from subparts_cpus, we have to use cpu_active_mask * to mask those out. */ static void compute_effective_cpumask(struct cpumask *new_cpus, struct cpuset *cs, struct cpuset *parent) { if (parent->nr_subparts_cpus) { cpumask_or(new_cpus, parent->effective_cpus, parent->subparts_cpus); cpumask_and(new_cpus, new_cpus, cs->cpus_requested); cpumask_and(new_cpus, new_cpus, cpu_active_mask); } else { cpumask_and(new_cpus, cs->cpus_requested, parent_cs(cs)->effective_cpus); } } /* * Commands for update_parent_subparts_cpumask */ enum subparts_cmd { partcmd_enable, /* Enable partition root */ partcmd_disable, /* Disable partition root */ partcmd_update, /* Update parent's subparts_cpus */ }; /** * update_parent_subparts_cpumask - update subparts_cpus mask of parent cpuset * @cpuset: The cpuset that requests change in partition root state * @cmd: Partition root state change command * @newmask: Optional new cpumask for partcmd_update * @tmp: Temporary addmask and delmask * Return: 0, 1 or an error code * * For partcmd_enable, the cpuset is being transformed from a non-partition * root to a partition root. The cpus_allowed mask of the given cpuset will * be put into parent's subparts_cpus and taken away from parent's * effective_cpus. The function will return 0 if all the CPUs listed in * cpus_allowed can be granted or an error code will be returned. * * For partcmd_disable, the cpuset is being transofrmed from a partition * root back to a non-partition root. Any CPUs in cpus_allowed that are in * parent's subparts_cpus will be taken away from that cpumask and put back * into parent's effective_cpus. 0 should always be returned. * * For partcmd_update, if the optional newmask is specified, the cpu * list is to be changed from cpus_allowed to newmask. Otherwise, * cpus_allowed is assumed to remain the same. The cpuset should either * be a partition root or an invalid partition root. The partition root * state may change if newmask is NULL and none of the requested CPUs can * be granted by the parent. The function will return 1 if changes to * parent's subparts_cpus and effective_cpus happen or 0 otherwise. * Error code should only be returned when newmask is non-NULL. * * The partcmd_enable and partcmd_disable commands are used by * update_prstate(). The partcmd_update command is used by * update_cpumasks_hier() with newmask NULL and update_cpumask() with * newmask set. * * The checking is more strict when enabling partition root than the * other two commands. * * Because of the implicit cpu exclusive nature of a partition root, * cpumask changes that violates the cpu exclusivity rule will not be * permitted when checked by validate_change(). The validate_change() * function will also prevent any changes to the cpu list if it is not * a superset of children's cpu lists. */ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, struct cpumask *newmask, struct tmpmasks *tmp) { struct cpuset *parent = parent_cs(cpuset); int adding; /* Moving cpus from effective_cpus to subparts_cpus */ int deleting; /* Moving cpus from subparts_cpus to effective_cpus */ int old_prs, new_prs; bool part_error = false; /* Partition error? */ lockdep_assert_held(&cpuset_mutex); /* * The parent must be a partition root. * The new cpumask, if present, or the current cpus_allowed must * not be empty. */ if (!is_partition_root(parent) || (newmask && cpumask_empty(newmask)) || (!newmask && cpumask_empty(cpuset->cpus_allowed))) return -EINVAL; /* * Enabling/disabling partition root is not allowed if there are * online children. */ if ((cmd != partcmd_update) && css_has_online_children(&cpuset->css)) return -EBUSY; /* * Enabling partition root is not allowed if not all the CPUs * can be granted from parent's effective_cpus or at least one * CPU will be left after that. */ if ((cmd == partcmd_enable) && (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) || cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus))) return -EINVAL; /* * A cpumask update cannot make parent's effective_cpus become empty. */ adding = deleting = false; old_prs = new_prs = cpuset->partition_root_state; if (cmd == partcmd_enable) { cpumask_copy(tmp->addmask, cpuset->cpus_allowed); adding = true; } else if (cmd == partcmd_disable) { deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed, parent->subparts_cpus); } else if (newmask) { /* * partcmd_update with newmask: * * delmask = cpus_allowed & ~newmask & parent->subparts_cpus * addmask = newmask & parent->effective_cpus * & ~parent->subparts_cpus */ cpumask_andnot(tmp->delmask, cpuset->cpus_allowed, newmask); deleting = cpumask_and(tmp->delmask, tmp->delmask, parent->subparts_cpus); cpumask_and(tmp->addmask, newmask, parent->effective_cpus); adding = cpumask_andnot(tmp->addmask, tmp->addmask, parent->subparts_cpus); /* * Return error if the new effective_cpus could become empty. */ if (adding && cpumask_equal(parent->effective_cpus, tmp->addmask)) { if (!deleting) return -EINVAL; /* * As some of the CPUs in subparts_cpus might have * been offlined, we need to compute the real delmask * to confirm that. */ if (!cpumask_and(tmp->addmask, tmp->delmask, cpu_active_mask)) return -EINVAL; cpumask_copy(tmp->addmask, parent->effective_cpus); } } else { /* * partcmd_update w/o newmask: * * addmask = cpus_allowed & parent->effective_cpus * * Note that parent's subparts_cpus may have been * pre-shrunk in case there is a change in the cpu list. * So no deletion is needed. */ adding = cpumask_and(tmp->addmask, cpuset->cpus_allowed, parent->effective_cpus); part_error = cpumask_equal(tmp->addmask, parent->effective_cpus); } if (cmd == partcmd_update) { int prev_prs = cpuset->partition_root_state; /* * Check for possible transition between PRS_ENABLED * and PRS_ERROR. */ switch (cpuset->partition_root_state) { case PRS_ENABLED: if (part_error) new_prs = PRS_ERROR; break; case PRS_ERROR: if (!part_error) new_prs = PRS_ENABLED; break; } /* * Set part_error if previously in invalid state. */ part_error = (prev_prs == PRS_ERROR); } if (!part_error && (new_prs == PRS_ERROR)) return 0; /* Nothing need to be done */ if (new_prs == PRS_ERROR) { /* * Remove all its cpus from parent's subparts_cpus. */ adding = false; deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed, parent->subparts_cpus); } if (!adding && !deleting && (new_prs == old_prs)) return 0; /* * Change the parent's subparts_cpus. * Newly added CPUs will be removed from effective_cpus and * newly deleted ones will be added back to effective_cpus. */ spin_lock_irq(&callback_lock); if (adding) { cpumask_or(parent->subparts_cpus, parent->subparts_cpus, tmp->addmask); cpumask_andnot(parent->effective_cpus, parent->effective_cpus, tmp->addmask); } if (deleting) { cpumask_andnot(parent->subparts_cpus, parent->subparts_cpus, tmp->delmask); /* * Some of the CPUs in subparts_cpus might have been offlined. */ cpumask_and(tmp->delmask, tmp->delmask, cpu_active_mask); cpumask_or(parent->effective_cpus, parent->effective_cpus, tmp->delmask); } parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus); if (old_prs != new_prs) cpuset->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); notify_partition_change(cpuset, old_prs, new_prs); return cmd == partcmd_update; } /* * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree * @cs: the cpuset to consider * @tmp: temp variables for calculating effective_cpus & partition setup * * When configured cpumask is changed, the effective cpumasks of this cpuset * and all its descendants need to be updated. * * On legacy hierarchy, effective_cpus will be the same with cpu_allowed. * * Called with cpuset_mutex held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; bool need_rebuild_sched_domains = false; int old_prs, new_prs; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); compute_effective_cpumask(tmp->new_cpus, cp, parent); /* * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some CPUs. */ if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) { cpumask_copy(tmp->new_cpus, parent->effective_cpus); if (!cp->use_parent_ecpus) { cp->use_parent_ecpus = true; parent->child_ecpus_count++; } } else if (cp->use_parent_ecpus) { cp->use_parent_ecpus = false; WARN_ON_ONCE(!parent->child_ecpus_count); parent->child_ecpus_count--; } /* * Skip the whole subtree if the cpumask remains the same * and has no partition root state. */ if (!cp->partition_root_state && cpumask_equal(tmp->new_cpus, cp->effective_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; } /* * update_parent_subparts_cpumask() should have been called * for cs already in update_cpumask(). We should also call * update_tasks_cpumask() again for tasks in the parent * cpuset if the parent's subparts_cpus changes. */ old_prs = new_prs = cp->partition_root_state; if ((cp != cs) && old_prs) { switch (parent->partition_root_state) { case PRS_DISABLED: /* * If parent is not a partition root or an * invalid partition root, clear its state * and its CS_CPU_EXCLUSIVE flag. */ WARN_ON_ONCE(cp->partition_root_state != PRS_ERROR); new_prs = PRS_DISABLED; /* * clear_bit() is an atomic operation and * readers aren't interested in the state * of CS_CPU_EXCLUSIVE anyway. So we can * just update the flag without holding * the callback_lock. */ clear_bit(CS_CPU_EXCLUSIVE, &cp->flags); break; case PRS_ENABLED: if (update_parent_subparts_cpumask(cp, partcmd_update, NULL, tmp)) update_tasks_cpumask(parent); break; case PRS_ERROR: /* * When parent is invalid, it has to be too. */ new_prs = PRS_ERROR; break; } } if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); spin_lock_irq(&callback_lock); cpumask_copy(cp->effective_cpus, tmp->new_cpus); if (cp->nr_subparts_cpus && (new_prs != PRS_ENABLED)) { cp->nr_subparts_cpus = 0; cpumask_clear(cp->subparts_cpus); } else if (cp->nr_subparts_cpus) { /* * Make sure that effective_cpus & subparts_cpus * are mutually exclusive. * * In the unlikely event that effective_cpus * becomes empty. we clear cp->nr_subparts_cpus and * let its child partition roots to compete for * CPUs again. */ cpumask_andnot(cp->effective_cpus, cp->effective_cpus, cp->subparts_cpus); if (cpumask_empty(cp->effective_cpus)) { cpumask_copy(cp->effective_cpus, tmp->new_cpus); cpumask_clear(cp->subparts_cpus); cp->nr_subparts_cpus = 0; } else if (!cpumask_subset(cp->subparts_cpus, tmp->new_cpus)) { cpumask_andnot(cp->subparts_cpus, cp->subparts_cpus, tmp->new_cpus); cp->nr_subparts_cpus = cpumask_weight(cp->subparts_cpus); } } if (new_prs != old_prs) cp->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); notify_partition_change(cp, old_prs, new_prs); WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); update_tasks_cpumask(cp); /* * On legacy hierarchy, if the effective cpumask of any non- * empty cpuset is changed, we need to rebuild sched domains. * On default hierarchy, the cpuset needs to be a partition * root as well. */ if (!cpumask_empty(cp->cpus_allowed) && is_sched_load_balance(cp) && (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || is_partition_root(cp))) need_rebuild_sched_domains = true; rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); if (need_rebuild_sched_domains) rebuild_sched_domains_locked(); } /** * update_sibling_cpumasks - Update siblings cpumasks * @parent: Parent cpuset * @cs: Current cpuset * @tmp: Temp variables */ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct tmpmasks *tmp) { struct cpuset *sibling; struct cgroup_subsys_state *pos_css; lockdep_assert_held(&cpuset_mutex); /* * Check all its siblings and call update_cpumasks_hier() * if their use_parent_ecpus flag is set in order for them * to use the right effective_cpus value. * * The update_cpumasks_hier() function may sleep. So we have to * release the RCU read lock before calling it. */ rcu_read_lock(); cpuset_for_each_child(sibling, pos_css, parent) { if (sibling == cs) continue; if (!sibling->use_parent_ecpus) continue; if (!css_tryget_online(&sibling->css)) continue; rcu_read_unlock(); update_cpumasks_hier(sibling, tmp); rcu_read_lock(); css_put(&sibling->css); } rcu_read_unlock(); } /** * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it * @cs: the cpuset to consider * @trialcs: trial cpuset * @buf: buffer of cpu numbers written to this cpuset */ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; struct tmpmasks tmp; /* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */ if (cs == &top_cpuset) return -EACCES; /* * An empty cpus_requested is ok only if the cpuset has no tasks. * Since cpulist_parse() fails on an empty mask, we special case * that parsing. The validate_change() call ensures that cpusets * with tasks have cpus. */ if (!*buf) { cpumask_clear(trialcs->cpus_requested); } else { retval = cpulist_parse(buf, trialcs->cpus_requested); if (retval < 0) return retval; } if (!cpumask_subset(trialcs->cpus_requested, cpu_present_mask)) return -EINVAL; cpumask_and(trialcs->cpus_allowed, trialcs->cpus_requested, cpu_active_mask); /* Nothing to do if the cpus didn't change */ if (cpumask_equal(cs->cpus_requested, trialcs->cpus_requested)) return 0; retval = validate_change(cs, trialcs); if (retval < 0) return retval; #ifdef CONFIG_CPUMASK_OFFSTACK /* * Use the cpumasks in trialcs for tmpmasks when they are pointers * to allocated cpumasks. */ tmp.addmask = trialcs->subparts_cpus; tmp.delmask = trialcs->effective_cpus; tmp.new_cpus = trialcs->cpus_allowed; #endif if (cs->partition_root_state) { /* Cpumask of a partition root cannot be empty */ if (cpumask_empty(trialcs->cpus_allowed)) return -EINVAL; if (update_parent_subparts_cpumask(cs, partcmd_update, trialcs->cpus_allowed, &tmp) < 0) return -EINVAL; } spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); cpumask_copy(cs->cpus_requested, trialcs->cpus_requested); /* * Make sure that subparts_cpus is a subset of cpus_allowed. */ if (cs->nr_subparts_cpus) { cpumask_and(cs->subparts_cpus, cs->subparts_cpus, cs->cpus_allowed); cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus); } spin_unlock_irq(&callback_lock); update_cpumasks_hier(cs, &tmp); if (cs->partition_root_state) { struct cpuset *parent = parent_cs(cs); /* * For partition root, update the cpumasks of sibling * cpusets if they use parent's effective_cpus. */ if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmp); } return 0; } /* * Migrate memory region from one set of nodes to another. This is * performed asynchronously as it can be called from process migration path * holding locks involved in process management. All mm migrations are * performed in the queued order and can be waited for by flushing * cpuset_migrate_mm_wq. */ struct cpuset_migrate_mm_work { struct work_struct work; struct mm_struct *mm; nodemask_t from; nodemask_t to; }; static void cpuset_migrate_mm_workfn(struct work_struct *work) { struct cpuset_migrate_mm_work *mwork = container_of(work, struct cpuset_migrate_mm_work, work); /* on a wq worker, no need to worry about %current's mems_allowed */ do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL); mmput(mwork->mm); kfree(mwork); } static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to) { struct cpuset_migrate_mm_work *mwork; if (nodes_equal(*from, *to)) { mmput(mm); return; } mwork = kzalloc(sizeof(*mwork), GFP_KERNEL); if (mwork) { mwork->mm = mm; mwork->from = *from; mwork->to = *to; INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn); queue_work(cpuset_migrate_mm_wq, &mwork->work); } else { mmput(mm); } } static void cpuset_post_attach(void) { flush_workqueue(cpuset_migrate_mm_wq); } /* * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy * @tsk: the task to change * @newmems: new nodes that the task will be set * * We use the mems_allowed_seq seqlock to safely update both tsk->mems_allowed * and rebind an eventual tasks' mempolicy. If the task is allocating in * parallel, it might temporarily see an empty intersection, which results in * a seqlock check and retry before OOM or allocation failure. */ static void cpuset_change_task_nodemask(struct task_struct *tsk, nodemask_t *newmems) { task_lock(tsk); local_irq_disable(); write_seqcount_begin(&tsk->mems_allowed_seq); nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); mpol_rebind_task(tsk, newmems); tsk->mems_allowed = *newmems; write_seqcount_end(&tsk->mems_allowed_seq); local_irq_enable(); task_unlock(tsk); } static void *cpuset_being_rebound; /** * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset. * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_nodemask(struct cpuset *cs) { static nodemask_t newmems; /* protected by cpuset_mutex */ struct css_task_iter it; struct task_struct *task; cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ guarantee_online_mems(cs, &newmems); /* * The mpol_rebind_mm() call takes mmap_lock, which we couldn't * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold * the global cpuset_mutex, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. */ css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { struct mm_struct *mm; bool migrate; cpuset_change_task_nodemask(task, &newmems); mm = get_task_mm(task); if (!mm) continue; migrate = is_memory_migrate(cs); mpol_rebind_mm(mm, &cs->mems_allowed); if (migrate) cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); else mmput(mm); } css_task_iter_end(&it); /* * All the tasks' nodemasks have been updated, update * cs->old_mems_allowed. */ cs->old_mems_allowed = newmems; /* We're done rebinding vmas to this cpuset's new mems_allowed. */ cpuset_being_rebound = NULL; } /* * update_nodemasks_hier - Update effective nodemasks and tasks in the subtree * @cs: the cpuset to consider * @new_mems: a temp variable for calculating new effective_mems * * When configured nodemask is changed, the effective nodemasks of this cpuset * and all its descendants need to be updated. * * On legacy hierarchy, effective_mems will be the same with mems_allowed. * * Called with cpuset_mutex held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); nodes_and(*new_mems, cp->mems_allowed, parent->effective_mems); /* * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some MEMs. */ if (is_in_v2_mode() && nodes_empty(*new_mems)) *new_mems = parent->effective_mems; /* Skip the whole subtree if the nodemask remains the same. */ if (nodes_equal(*new_mems, cp->effective_mems)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); spin_lock_irq(&callback_lock); cp->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !nodes_equal(cp->mems_allowed, cp->effective_mems)); update_tasks_nodemask(cp); rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); } /* * Handle user request to change the 'mems' memory placement * of a cpuset. Needs to validate the request, update the * cpusets mems_allowed, and for each task in the cpuset, * update mems_allowed and rebind task's mempolicy and any vma * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * * Call with cpuset_mutex held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. */ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; /* * top_cpuset.mems_allowed tracks node_stats[N_MEMORY]; * it's read-only */ if (cs == &top_cpuset) { retval = -EACCES; goto done; } /* * An empty mems_allowed is ok iff there are no tasks in the cpuset. * Since nodelist_parse() fails on an empty mask, we special case * that parsing. The validate_change() call ensures that cpusets * with tasks have memory. */ if (!*buf) { nodes_clear(trialcs->mems_allowed); } else { retval = nodelist_parse(buf, trialcs->mems_allowed); if (retval < 0) goto done; if (!nodes_subset(trialcs->mems_allowed, top_cpuset.mems_allowed)) { retval = -EINVAL; goto done; } } if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed)) { retval = 0; /* Too easy - nothing to do */ goto done; } retval = validate_change(cs, trialcs); if (retval < 0) goto done; spin_lock_irq(&callback_lock); cs->mems_allowed = trialcs->mems_allowed; spin_unlock_irq(&callback_lock); /* use trialcs->mems_allowed as a temp variable */ update_nodemasks_hier(cs, &trialcs->mems_allowed); done: return retval; } bool current_cpuset_is_being_rebound(void) { bool ret; rcu_read_lock(); ret = task_cs(current) == cpuset_being_rebound; rcu_read_unlock(); return ret; } static int update_relax_domain_level(struct cpuset *cs, s64 val) { #ifdef CONFIG_SMP if (val < -1 || val > sched_domain_level_max + 1) return -EINVAL; #endif if (val != cs->relax_domain_level) { cs->relax_domain_level = val; if (!cpumask_empty(cs->cpus_allowed) && is_sched_load_balance(cs)) rebuild_sched_domains_locked(); } return 0; } /** * update_tasks_flags - update the spread flags of tasks in the cpuset. * @cs: the cpuset in which each task's spread flags needs to be changed * * Iterate through each task of @cs updating its spread flags. As this * function is called with cpuset_mutex held, cpuset membership stays * stable. */ static void update_tasks_flags(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) cpuset_update_task_spread_flag(cs, task); css_task_iter_end(&it); } /* * update_flag - read a 0 or a 1 in a file and update associated flag * bit: the bit to update (see cpuset_flagbits_t) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * * Call with cpuset_mutex held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on) { struct cpuset *trialcs; int balance_flag_changed; int spread_flag_changed; int err; trialcs = alloc_trial_cpuset(cs); if (!trialcs) return -ENOMEM; if (turning_on) set_bit(bit, &trialcs->flags); else clear_bit(bit, &trialcs->flags); err = validate_change(cs, trialcs); if (err < 0) goto out; balance_flag_changed = (is_sched_load_balance(cs) != is_sched_load_balance(trialcs)); spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) || (is_spread_page(cs) != is_spread_page(trialcs))); spin_lock_irq(&callback_lock); cs->flags = trialcs->flags; spin_unlock_irq(&callback_lock); if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) rebuild_sched_domains_locked(); if (spread_flag_changed) update_tasks_flags(cs); out: free_cpuset(trialcs); return err; } /* * update_prstate - update partititon_root_state * cs: the cpuset to update * new_prs: new partition root state * * Call with cpuset_mutex held. */ static int update_prstate(struct cpuset *cs, int new_prs) { int err, old_prs = cs->partition_root_state; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask; if (old_prs == new_prs) return 0; /* * Cannot force a partial or invalid partition root to a full * partition root. */ if (new_prs && (old_prs == PRS_ERROR)) return -EINVAL; if (alloc_cpumasks(NULL, &tmpmask)) return -ENOMEM; err = -EINVAL; if (!old_prs) { /* * Turning on partition root requires setting the * CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed * cannot be NULL. */ if (cpumask_empty(cs->cpus_allowed)) goto out; err = update_flag(CS_CPU_EXCLUSIVE, cs, 1); if (err) goto out; err = update_parent_subparts_cpumask(cs, partcmd_enable, NULL, &tmpmask); if (err) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); goto out; } } else { /* * Turning off partition root will clear the * CS_CPU_EXCLUSIVE bit. */ if (old_prs == PRS_ERROR) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); err = 0; goto out; } err = update_parent_subparts_cpumask(cs, partcmd_disable, NULL, &tmpmask); if (err) goto out; /* Turning off CS_CPU_EXCLUSIVE will not return error */ update_flag(CS_CPU_EXCLUSIVE, cs, 0); } update_tasks_cpumask(parent); if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmpmask); rebuild_sched_domains_locked(); out: if (!err) { spin_lock_irq(&callback_lock); cs->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); notify_partition_change(cs, old_prs, new_prs); } free_cpumasks(NULL, &tmpmask); return err; } /* * Frequency meter - How fast is some event occurring? * * These routines manage a digitally filtered, constant time based, * event frequency meter. There are four routines: * fmeter_init() - initialize a frequency meter. * fmeter_markevent() - called each time the event happens. * fmeter_getrate() - returns the recent rate of such events. * fmeter_update() - internal routine used to update fmeter. * * A common data structure is passed to each of these routines, * which is used to keep track of the state required to manage the * frequency meter and its digital filter. * * The filter works on the number of events marked per unit time. * The filter is single-pole low-pass recursive (IIR). The time unit * is 1 second. Arithmetic is done using 32-bit integers scaled to * simulate 3 decimal digits of precision (multiplied by 1000). * * With an FM_COEF of 933, and a time base of 1 second, the filter * has a half-life of 10 seconds, meaning that if the events quit * happening, then the rate returned from the fmeter_getrate() * will be cut in half each 10 seconds, until it converges to zero. * * It is not worth doing a real infinitely recursive filter. If more * than FM_MAXTICKS ticks have elapsed since the last filter event, * just compute FM_MAXTICKS ticks worth, by which point the level * will be stable. * * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid * arithmetic overflow in the fmeter_update() routine. * * Given the simple 32 bit integer arithmetic used, this meter works * best for reporting rates between one per millisecond (msec) and * one per 32 (approx) seconds. At constant rates faster than one * per msec it maxes out at values just under 1,000,000. At constant * rates between one per msec, and one per second it will stabilize * to a value N*1000, where N is the rate of events per second. * At constant rates between one per second and one per 32 seconds, * it will be choppy, moving up on the seconds that have an event, * and then decaying until the next event. At rates slower than * about one in 32 seconds, it decays all the way back to zero between * each event. */ #define FM_COEF 933 /* coefficient for half-life of 10 secs */ #define FM_MAXTICKS ((u32)99) /* useless computing more ticks than this */ #define FM_MAXCNT 1000000 /* limit cnt to avoid overflow */ #define FM_SCALE 1000 /* faux fixed point scale */ /* Initialize a frequency meter */ static void fmeter_init(struct fmeter *fmp) { fmp->cnt = 0; fmp->val = 0; fmp->time = 0; spin_lock_init(&fmp->lock); } /* Internal meter update - process cnt events and update value */ static void fmeter_update(struct fmeter *fmp) { time64_t now; u32 ticks; now = ktime_get_seconds(); ticks = now - fmp->time; if (ticks == 0) return; ticks = min(FM_MAXTICKS, ticks); while (ticks-- > 0) fmp->val = (FM_COEF * fmp->val) / FM_SCALE; fmp->time = now; fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE; fmp->cnt = 0; } /* Process any previous ticks, then bump cnt by one (times scale). */ static void fmeter_markevent(struct fmeter *fmp) { spin_lock(&fmp->lock); fmeter_update(fmp); fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE); spin_unlock(&fmp->lock); } /* Process any previous ticks, then return current value. */ static int fmeter_getrate(struct fmeter *fmp) { int val; spin_lock(&fmp->lock); fmeter_update(fmp); val = fmp->val; spin_unlock(&fmp->lock); return val; } static struct cpuset *cpuset_attach_old_cs; static void reset_migrate_dl_data(struct cpuset *cs) { cs->nr_migrate_dl_tasks = 0; cs->sum_migrate_dl_bw = 0; } /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct cpuset *cs, *oldcs; struct task_struct *task; int ret; /* used later by cpuset_attach() */ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); oldcs = cpuset_attach_old_cs; cs = css_cs(css); mutex_lock(&cpuset_mutex); /* allow moving tasks into an empty cpuset if on default hierarchy */ ret = -ENOSPC; if (!is_in_v2_mode() && (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task); if (ret) goto out_unlock; ret = security_task_setscheduler(task); if (ret) goto out_unlock; if (dl_task(task)) { cs->nr_migrate_dl_tasks++; cs->sum_migrate_dl_bw += task->dl.dl_bw; } } if (!cs->nr_migrate_dl_tasks) goto out_success; if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) { int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); if (unlikely(cpu >= nr_cpu_ids)) { reset_migrate_dl_data(cs); ret = -EINVAL; goto out_unlock; } ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); if (ret) { reset_migrate_dl_data(cs); goto out_unlock; } } out_success: /* * Mark attach is in progress. This makes validate_change() fail * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; ret = 0; out_unlock: mutex_unlock(&cpuset_mutex); return ret; } static void cpuset_cancel_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct cpuset *cs; cgroup_taskset_first(tset, &css); cs = css_cs(css); mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); if (cs->nr_migrate_dl_tasks) { int cpu = cpumask_any(cs->effective_cpus); dl_bw_free(cpu, cs->sum_migrate_dl_bw); reset_migrate_dl_data(cs); } mutex_unlock(&cpuset_mutex); } /* * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ static cpumask_var_t cpus_attach; static void cpuset_attach(struct cgroup_taskset *tset) { /* static buf protected by cpuset_mutex */ static nodemask_t cpuset_attach_nodemask_to; struct task_struct *task; struct task_struct *leader; struct cgroup_subsys_state *css; struct cpuset *cs; struct cpuset *oldcs = cpuset_attach_old_cs; cgroup_taskset_first(tset, &css); cs = css_cs(css); lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ mutex_lock(&cpuset_mutex); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cgroup_taskset_for_each(task, css, tset) { if (cs != &top_cpuset) guarantee_online_cpus(task, cpus_attach); else cpumask_copy(cpus_attach, task_cpu_possible_mask(task)); /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here */ WARN_ON_ONCE(update_cpus_allowed(cs, task, cpus_attach)); cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to); cpuset_update_task_spread_flag(cs, task); } /* * Change mm for all threadgroup leaders. This is expensive and may * sleep and should be moved outside migration path proper. */ cpuset_attach_nodemask_to = cs->effective_mems; cgroup_taskset_for_each_leader(leader, css, tset) { struct mm_struct *mm = get_task_mm(leader); if (mm) { mpol_rebind_mm(mm, &cpuset_attach_nodemask_to); /* * old_mems_allowed is the same with mems_allowed * here, except if this task is being moved * automatically due to hotplug. In that case * @mems_allowed has been updated and is empty, so * @old_mems_allowed is the right nodesets that we * migrate mm from. */ if (is_memory_migrate(cs)) cpuset_migrate_mm(mm, &oldcs->old_mems_allowed, &cpuset_attach_nodemask_to); else mmput(mm); } } cs->old_mems_allowed = cpuset_attach_nodemask_to; if (cs->nr_migrate_dl_tasks) { cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks; oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks; reset_migrate_dl_data(cs); } cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); mutex_unlock(&cpuset_mutex); } /* The various types of files and directories in a cpuset file system */ typedef enum { FILE_MEMORY_MIGRATE, FILE_CPULIST, FILE_MEMLIST, FILE_EFFECTIVE_CPULIST, FILE_EFFECTIVE_MEMLIST, FILE_SUBPARTS_CPULIST, FILE_CPU_EXCLUSIVE, FILE_MEM_EXCLUSIVE, FILE_MEM_HARDWALL, FILE_SCHED_LOAD_BALANCE, FILE_PARTITION_ROOT, FILE_SCHED_RELAX_DOMAIN_LEVEL, FILE_MEMORY_PRESSURE_ENABLED, FILE_MEMORY_PRESSURE, FILE_SPREAD_PAGE, FILE_SPREAD_SLAB, } cpuset_filetype_t; static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = 0; cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) { retval = -ENODEV; goto out_unlock; } switch (type) { case FILE_CPU_EXCLUSIVE: retval = update_flag(CS_CPU_EXCLUSIVE, cs, val); break; case FILE_MEM_EXCLUSIVE: retval = update_flag(CS_MEM_EXCLUSIVE, cs, val); break; case FILE_MEM_HARDWALL: retval = update_flag(CS_MEM_HARDWALL, cs, val); break; case FILE_SCHED_LOAD_BALANCE: retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val); break; case FILE_MEMORY_MIGRATE: retval = update_flag(CS_MEMORY_MIGRATE, cs, val); break; case FILE_MEMORY_PRESSURE_ENABLED: cpuset_memory_pressure_enabled = !!val; break; case FILE_SPREAD_PAGE: retval = update_flag(CS_SPREAD_PAGE, cs, val); break; case FILE_SPREAD_SLAB: retval = update_flag(CS_SPREAD_SLAB, cs, val); break; default: retval = -EINVAL; break; } out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, s64 val) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = -ENODEV; cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: retval = update_relax_domain_level(cs, val); break; default: retval = -EINVAL; break; } out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } /* * Common handling for a write to a "cpus" or "mems" file. */ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); struct cpuset *trialcs; int retval = -ENODEV; buf = strstrip(buf); /* * CPU or memory hotunplug may leave @cs w/o any execution * resources, in which case the hotplug code asynchronously updates * configuration and transfers all tasks to the nearest ancestor * which can execute. * * As writes to "cpus" or "mems" may restore @cs's execution * resources, wait for the previously scheduled operations before * proceeding, so that we don't end up keep removing tasks added * after execution capability is restored. * * cpuset_hotplug_work calls back into cgroup core via * cgroup_transfer_tasks() and waiting for it from a cgroupfs * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after * grabbing cpuset_mutex anyway. This only happens on the legacy * hierarchies. */ css_get(&cs->css); kernfs_break_active_protection(of->kn); flush_work(&cpuset_hotplug_work); cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; trialcs = alloc_trial_cpuset(cs); if (!trialcs) { retval = -ENOMEM; goto out_unlock; } switch (of_cft(of)->private) { case FILE_CPULIST: retval = update_cpumask(cs, trialcs, buf); break; case FILE_MEMLIST: retval = update_nodemask(cs, trialcs, buf); break; default: retval = -EINVAL; break; } free_cpuset(trialcs); out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); return retval ?: nbytes; } /* * These ascii lists should be read in a single call, by using a user * buffer large enough to hold the entire map. If read in smaller * chunks, there is no guarantee of atomicity. Since the display format * used, list of ranges of sequential numbers, is variable length, * and since these maps can change value dynamically, one could read * gibberish by doing partial reads while a list was changing. */ static int cpuset_common_seq_show(struct seq_file *sf, void *v) { struct cpuset *cs = css_cs(seq_css(sf)); cpuset_filetype_t type = seq_cft(sf)->private; int ret = 0; spin_lock_irq(&callback_lock); switch (type) { case FILE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_requested)); break; case FILE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed)); break; case FILE_EFFECTIVE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_cpus)); break; case FILE_EFFECTIVE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems)); break; case FILE_SUBPARTS_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->subparts_cpus)); break; default: ret = -EINVAL; } spin_unlock_irq(&callback_lock); return ret; } static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_CPU_EXCLUSIVE: return is_cpu_exclusive(cs); case FILE_MEM_EXCLUSIVE: return is_mem_exclusive(cs); case FILE_MEM_HARDWALL: return is_mem_hardwall(cs); case FILE_SCHED_LOAD_BALANCE: return is_sched_load_balance(cs); case FILE_MEMORY_MIGRATE: return is_memory_migrate(cs); case FILE_MEMORY_PRESSURE_ENABLED: return cpuset_memory_pressure_enabled; case FILE_MEMORY_PRESSURE: return fmeter_getrate(&cs->fmeter); case FILE_SPREAD_PAGE: return is_spread_page(cs); case FILE_SPREAD_SLAB: return is_spread_slab(cs); default: BUG(); } /* Unreachable but makes gcc happy */ return 0; } static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: return cs->relax_domain_level; default: BUG(); } /* Unreachable but makes gcc happy */ return 0; } static int sched_partition_show(struct seq_file *seq, void *v) { struct cpuset *cs = css_cs(seq_css(seq)); switch (cs->partition_root_state) { case PRS_ENABLED: seq_puts(seq, "root\n"); break; case PRS_DISABLED: seq_puts(seq, "member\n"); break; case PRS_ERROR: seq_puts(seq, "root invalid\n"); break; } return 0; } static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); int val; int retval = -ENODEV; buf = strstrip(buf); /* * Convert "root" to ENABLED, and convert "member" to DISABLED. */ if (!strcmp(buf, "root")) val = PRS_ENABLED; else if (!strcmp(buf, "member")) val = PRS_DISABLED; else return -EINVAL; css_get(&cs->css); cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; retval = update_prstate(cs, val); out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); css_put(&cs->css); return retval ?: nbytes; } /* * for the common functions, 'private' gives the type of file */ static struct cftype legacy_files[] = { { .name = "cpus", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_CPULIST, }, { .name = "mems", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * MAX_NUMNODES), .private = FILE_MEMLIST, }, { .name = "effective_cpus", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_CPULIST, }, { .name = "effective_mems", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_MEMLIST, }, { .name = "cpu_exclusive", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_CPU_EXCLUSIVE, }, { .name = "mem_exclusive", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEM_EXCLUSIVE, }, { .name = "mem_hardwall", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEM_HARDWALL, }, { .name = "sched_load_balance", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SCHED_LOAD_BALANCE, }, { .name = "sched_relax_domain_level", .read_s64 = cpuset_read_s64, .write_s64 = cpuset_write_s64, .private = FILE_SCHED_RELAX_DOMAIN_LEVEL, }, { .name = "memory_migrate", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_MIGRATE, }, { .name = "memory_pressure", .read_u64 = cpuset_read_u64, .private = FILE_MEMORY_PRESSURE, }, { .name = "memory_spread_page", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SPREAD_PAGE, }, { .name = "memory_spread_slab", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SPREAD_SLAB, }, { .name = "memory_pressure_enabled", .flags = CFTYPE_ONLY_ON_ROOT, .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_PRESSURE_ENABLED, }, { } /* terminate */ }; /* * This is currently a minimal set for the default hierarchy. It can be * expanded later on by migrating more features and control files from v1. */ static struct cftype dfl_files[] = { { .name = "cpus", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_CPULIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "mems", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * MAX_NUMNODES), .private = FILE_MEMLIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_CPULIST, }, { .name = "mems.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_MEMLIST, }, { .name = "cpus.partition", .seq_show = sched_partition_show, .write = sched_partition_write, .private = FILE_PARTITION_ROOT, .flags = CFTYPE_NOT_ON_ROOT, .file_offset = offsetof(struct cpuset, partition_file), }, { .name = "cpus.subpartitions", .seq_show = cpuset_common_seq_show, .private = FILE_SUBPARTS_CPULIST, .flags = CFTYPE_DEBUG, }, { } /* terminate */ }; /* * cpuset_css_alloc - allocate a cpuset css * cgrp: control group that the new cpuset will be part of */ static struct cgroup_subsys_state * cpuset_css_alloc(struct cgroup_subsys_state *parent_css) { struct cpuset *cs; if (!parent_css) return &top_cpuset.css; cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); if (alloc_cpumasks(cs, NULL)) { kfree(cs); return ERR_PTR(-ENOMEM); } __set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); nodes_clear(cs->mems_allowed); nodes_clear(cs->effective_mems); fmeter_init(&cs->fmeter); cs->relax_domain_level = -1; /* Set CS_MEMORY_MIGRATE for default hierarchy */ if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) __set_bit(CS_MEMORY_MIGRATE, &cs->flags); return &cs->css; } static int cpuset_css_online(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); struct cpuset *parent = parent_cs(cs); struct cpuset *tmp_cs; struct cgroup_subsys_state *pos_css; if (!parent) return 0; cpus_read_lock(); mutex_lock(&cpuset_mutex); set_bit(CS_ONLINE, &cs->flags); if (is_spread_page(parent)) set_bit(CS_SPREAD_PAGE, &cs->flags); if (is_spread_slab(parent)) set_bit(CS_SPREAD_SLAB, &cs->flags); cpuset_inc(); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(cs->effective_cpus, parent->effective_cpus); cs->effective_mems = parent->effective_mems; cs->use_parent_ecpus = true; parent->child_ecpus_count++; } spin_unlock_irq(&callback_lock); if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) goto out_unlock; /* * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is * set. This flag handling is implemented in cgroup core for * histrical reasons - the flag may be specified during mount. * * Currently, if any sibling cpusets have exclusive cpus or mem, we * refuse to clone the configuration - thereby refusing the task to * be entered, and as a result refusing the sys_unshare() or * clone() which initiated it. If this becomes a problem for some * users who wish to allow that scenario, then this could be * changed to grant parent->cpus_allowed-sibling_cpus_exclusive * (and likewise for mems) to the new cgroup. */ rcu_read_lock(); cpuset_for_each_child(tmp_cs, pos_css, parent) { if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) { rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); spin_lock_irq(&callback_lock); cs->mems_allowed = parent->mems_allowed; cs->effective_mems = parent->mems_allowed; cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); cpumask_copy(cs->cpus_requested, parent->cpus_requested); cpumask_copy(cs->effective_cpus, parent->cpus_allowed); spin_unlock_irq(&callback_lock); out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return 0; } /* * If the cpuset being removed has its flag 'sched_load_balance' * enabled, then simulate turning sched_load_balance off, which * will call rebuild_sched_domains_locked(). That is not needed * in the default hierarchy where only changes in partition * will cause repartitioning. * * If the cpuset has the 'sched.partition' flag enabled, simulate * turning 'sched.partition" off. */ static void cpuset_css_offline(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); cpus_read_lock(); mutex_lock(&cpuset_mutex); if (is_partition_root(cs)) update_prstate(cs, 0); if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && is_sched_load_balance(cs)) update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); if (cs->use_parent_ecpus) { struct cpuset *parent = parent_cs(cs); cs->use_parent_ecpus = false; parent->child_ecpus_count--; } cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags); mutex_unlock(&cpuset_mutex); cpus_read_unlock(); } static void cpuset_css_free(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); free_cpuset(cs); } static void cpuset_bind(struct cgroup_subsys_state *root_css) { mutex_lock(&cpuset_mutex); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); top_cpuset.mems_allowed = node_possible_map; } else { cpumask_copy(top_cpuset.cpus_allowed, top_cpuset.effective_cpus); top_cpuset.mems_allowed = top_cpuset.effective_mems; } spin_unlock_irq(&callback_lock); mutex_unlock(&cpuset_mutex); } /* * Make sure the new task conform to the current state of its parent, * which could have been changed by cpuset just after it inherits the * state from the parent and before it sits on the cgroup's task list. */ static void cpuset_fork(struct task_struct *task) { int inherit_cpus = 0; if (task_css_is_root(task, cpuset_cgrp_id)) return; trace_android_rvh_cpuset_fork(task, &inherit_cpus); if (!inherit_cpus) set_cpus_allowed_ptr(task, current->cpus_ptr); task->mems_allowed = current->mems_allowed; } struct cgroup_subsys cpuset_cgrp_subsys = { .css_alloc = cpuset_css_alloc, .css_online = cpuset_css_online, .css_offline = cpuset_css_offline, .css_free = cpuset_css_free, .can_attach = cpuset_can_attach, .cancel_attach = cpuset_cancel_attach, .attach = cpuset_attach, .post_attach = cpuset_post_attach, .bind = cpuset_bind, .fork = cpuset_fork, .legacy_cftypes = legacy_files, .dfl_cftypes = dfl_files, .early_init = true, .threaded = true, }; /** * cpuset_init - initialize cpusets at system boot * * Description: Initialize top_cpuset **/ int __init cpuset_init(void) { BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_requested, GFP_KERNEL)); cpumask_setall(top_cpuset.cpus_allowed); cpumask_setall(top_cpuset.cpus_requested); nodes_setall(top_cpuset.mems_allowed); cpumask_setall(top_cpuset.effective_cpus); nodes_setall(top_cpuset.effective_mems); fmeter_init(&top_cpuset.fmeter); set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags); top_cpuset.relax_domain_level = -1; BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)); return 0; } /* * If CPU and/or memory hotplug handlers, below, unplug any CPUs * or memory nodes, we need to walk over the cpuset hierarchy, * removing that CPU or node from all cpusets. If this removes the * last CPU or node from a cpuset, then move the tasks in the empty * cpuset to its next-highest non-empty parent. */ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) { struct cpuset *parent; /* * Find its next-highest non-empty parent, (top cpuset * has online cpus, so can't be empty). */ parent = parent_cs(cs); while (cpumask_empty(parent->cpus_allowed) || nodes_empty(parent->mems_allowed)) parent = parent_cs(parent); if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) { pr_err("cpuset: failed to transfer tasks out of empty cpuset "); pr_cont_cgroup_name(cs->css.cgroup); pr_cont("\n"); } } static void hotplug_update_tasks_legacy(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { bool is_empty; spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, new_cpus); cpumask_copy(cs->effective_cpus, new_cpus); cs->mems_allowed = *new_mems; cs->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); /* * Don't call update_tasks_cpumask() if the cpuset becomes empty, * as the tasks will be migratecd to an ancestor. */ if (cpus_updated && !cpumask_empty(cs->cpus_allowed)) update_tasks_cpumask(cs); if (mems_updated && !nodes_empty(cs->mems_allowed)) update_tasks_nodemask(cs); is_empty = cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed); mutex_unlock(&cpuset_mutex); /* * Move tasks to the nearest ancestor with execution resources, * This is full cgroup operation which will also call back into * cpuset. Should be done outside any lock. */ if (is_empty) remove_tasks_in_empty_cpuset(cs); mutex_lock(&cpuset_mutex); } static void hotplug_update_tasks(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { if (cpumask_empty(new_cpus)) cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; spin_lock_irq(&callback_lock); cpumask_copy(cs->effective_cpus, new_cpus); cs->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); if (cpus_updated) update_tasks_cpumask(cs); if (mems_updated) update_tasks_nodemask(cs); } static bool force_rebuild; void cpuset_force_rebuild(void) { force_rebuild = true; } /** * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug * @cs: cpuset in interest * @tmp: the tmpmasks structure pointer * * Compare @cs's cpu and mem masks against top_cpuset and if some have gone * offline, update @cs accordingly. If @cs ends up with no CPU or memory, * all its tasks are moved to the nearest ancestor with both resources. */ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) { static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated; bool mems_updated; struct cpuset *parent; retry: wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); mutex_lock(&cpuset_mutex); /* * We have raced with task attaching. We wait until attaching * is finished, so we won't attach a task to an empty cpuset. */ if (cs->attach_in_progress) { mutex_unlock(&cpuset_mutex); goto retry; } parent = parent_cs(cs); compute_effective_cpumask(&new_cpus, cs, parent); nodes_and(new_mems, cs->mems_allowed, parent->effective_mems); if (cs->nr_subparts_cpus) /* * Make sure that CPUs allocated to child partitions * do not show up in effective_cpus. */ cpumask_andnot(&new_cpus, &new_cpus, cs->subparts_cpus); if (!tmp || !cs->partition_root_state) goto update_tasks; /* * In the unlikely event that a partition root has empty * effective_cpus or its parent becomes erroneous, we have to * transition it to the erroneous state. */ if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || (parent->partition_root_state == PRS_ERROR))) { if (cs->nr_subparts_cpus) { spin_lock_irq(&callback_lock); cs->nr_subparts_cpus = 0; cpumask_clear(cs->subparts_cpus); spin_unlock_irq(&callback_lock); compute_effective_cpumask(&new_cpus, cs, parent); } /* * If the effective_cpus is empty because the child * partitions take away all the CPUs, we can keep * the current partition and let the child partitions * fight for available CPUs. */ if ((parent->partition_root_state == PRS_ERROR) || cpumask_empty(&new_cpus)) { int old_prs; update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp); old_prs = cs->partition_root_state; if (old_prs != PRS_ERROR) { spin_lock_irq(&callback_lock); cs->partition_root_state = PRS_ERROR; spin_unlock_irq(&callback_lock); notify_partition_change(cs, old_prs, PRS_ERROR); } } cpuset_force_rebuild(); } /* * On the other hand, an erroneous partition root may be transitioned * back to a regular one or a partition root with no CPU allocated * from the parent may change to erroneous. */ if (is_partition_root(parent) && ((cs->partition_root_state == PRS_ERROR) || !cpumask_intersects(&new_cpus, parent->subparts_cpus)) && update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp)) cpuset_force_rebuild(); update_tasks: cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); mems_updated = !nodes_equal(new_mems, cs->effective_mems); if (is_in_v2_mode()) hotplug_update_tasks(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); else hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); mutex_unlock(&cpuset_mutex); } /** * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset * * This function is called after either CPU or memory configuration has * changed and updates cpuset accordingly. The top_cpuset is always * synchronized to cpu_active_mask and N_MEMORY, which is necessary in * order to make cpusets transparent (of no affect) on systems that are * actively using CPU hotplug but making no active use of cpusets. * * Non-root cpusets are only affected by offlining. If any CPUs or memory * nodes have been taken down, cpuset_hotplug_update_tasks() is invoked on * all descendants. * * Note that CPU offlining during suspend is ignored. We don't modify * cpusets across suspend/resume cycles at all. */ static void cpuset_hotplug_workfn(struct work_struct *work) { static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; bool on_dfl = is_in_v2_mode(); struct tmpmasks tmp, *ptmp = NULL; if (on_dfl && !alloc_cpumasks(NULL, &tmp)) ptmp = &tmp; mutex_lock(&cpuset_mutex); /* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); new_mems = node_states[N_MEMORY]; /* * If subparts_cpus is populated, it is likely that the check below * will produce a false positive on cpus_updated when the cpu list * isn't changed. It is extra work, but it is better to be safe. */ cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus); mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); /* * In the rare case that hotplug removes all the cpus in subparts_cpus, * we assumed that cpus are updated. */ if (!cpus_updated && top_cpuset.nr_subparts_cpus) cpus_updated = true; /* synchronize cpus_allowed to cpu_active_mask */ if (cpus_updated) { spin_lock_irq(&callback_lock); if (!on_dfl) cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); /* * Make sure that CPUs allocated to child partitions * do not show up in effective_cpus. If no CPU is left, * we clear the subparts_cpus & let the child partitions * fight for the CPUs again. */ if (top_cpuset.nr_subparts_cpus) { if (cpumask_subset(&new_cpus, top_cpuset.subparts_cpus)) { top_cpuset.nr_subparts_cpus = 0; cpumask_clear(top_cpuset.subparts_cpus); } else { cpumask_andnot(&new_cpus, &new_cpus, top_cpuset.subparts_cpus); } } cpumask_copy(top_cpuset.effective_cpus, &new_cpus); spin_unlock_irq(&callback_lock); /* we don't mess with cpumasks of tasks in top_cpuset */ } /* synchronize mems_allowed to N_MEMORY */ if (mems_updated) { spin_lock_irq(&callback_lock); if (!on_dfl) top_cpuset.mems_allowed = new_mems; top_cpuset.effective_mems = new_mems; spin_unlock_irq(&callback_lock); update_tasks_nodemask(&top_cpuset); } mutex_unlock(&cpuset_mutex); /* if cpus or mems changed, we need to propagate to descendants */ if (cpus_updated || mems_updated) { struct cpuset *cs; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cs == &top_cpuset || !css_tryget_online(&cs->css)) continue; rcu_read_unlock(); cpuset_hotplug_update_tasks(cs, ptmp); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } /* rebuild sched domains if cpus_allowed has changed */ if (cpus_updated || force_rebuild) { force_rebuild = false; rebuild_sched_domains(); } free_cpumasks(NULL, ptmp); } void cpuset_update_active_cpus(void) { /* * We're inside cpu hotplug critical region which usually nests * inside cgroup synchronization. Bounce actual hotplug processing * to a work item to avoid reverse locking order. */ schedule_work(&cpuset_hotplug_work); } void cpuset_wait_for_hotplug(void) { flush_work(&cpuset_hotplug_work); } /* * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY]. * Call this routine anytime after node_states[N_MEMORY] changes. * See cpuset_update_active_cpus() for CPU hotplug handling. */ static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) { schedule_work(&cpuset_hotplug_work); return NOTIFY_OK; } static struct notifier_block cpuset_track_online_nodes_nb = { .notifier_call = cpuset_track_online_nodes, .priority = 10, /* ??! */ }; /** * cpuset_init_smp - initialize cpus_allowed * * Description: Finish top cpuset after cpu, node maps are initialized */ void __init cpuset_init_smp(void) { /* * cpus_allowd/mems_allowed set to v2 values in the initial * cpuset_bind() call will be reset to v1 values in another * cpuset_bind() call when v1 cpuset is mounted. */ top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); top_cpuset.effective_mems = node_states[N_MEMORY]; register_hotmemory_notifier(&cpuset_track_online_nodes_nb); cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0); BUG_ON(!cpuset_migrate_mm_wq); } /** * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. * @pmask: pointer to struct cpumask variable to receive cpus_allowed set. * * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of cpu_online_mask, even if this means going outside the * tasks cpuset, except when the task is in the top cpuset. **/ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { unsigned long flags; struct cpuset *cs; spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); cs = task_cs(tsk); if (cs != &top_cpuset) guarantee_online_cpus(tsk, pmask); /* * Tasks in the top cpuset won't get update to their cpumasks * when a hotplug online/offline event happens. So we include all * offline cpus in the allowed cpu list. */ if ((cs == &top_cpuset) || cpumask_empty(pmask)) { const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); /* * We first exclude cpus allocated to partitions. If there is no * allowable online cpu left, we fall back to all possible cpus. */ cpumask_andnot(pmask, possible_mask, top_cpuset.subparts_cpus); if (!cpumask_intersects(pmask, cpu_online_mask)) cpumask_copy(pmask, possible_mask); } rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); } EXPORT_SYMBOL_GPL(cpuset_cpus_allowed); /** * cpuset_cpus_allowed_fallback - final fallback before complete catastrophe. * @tsk: pointer to task_struct with which the scheduler is struggling * * Description: In the case that the scheduler cannot find an allowed cpu in * tsk->cpus_allowed, we fall back to task_cs(tsk)->cpus_allowed. In legacy * mode however, this value is the same as task_cs(tsk)->effective_cpus, * which will not contain a sane cpumask during cases such as cpu hotplugging. * This is the absolute last resort for the scheduler and it is only used if * _every_ other avenue has been traveled. * * Returns true if the affinity of @tsk was changed, false otherwise. **/ bool cpuset_cpus_allowed_fallback(struct task_struct *tsk) { const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); const struct cpumask *cs_mask; bool changed = false; rcu_read_lock(); cs_mask = task_cs(tsk)->cpus_allowed; if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) { do_set_cpus_allowed(tsk, cs_mask); changed = true; } rcu_read_unlock(); /* * We own tsk->cpus_allowed, nobody can change it under us. * * But we used cs && cs->cpus_allowed lockless and thus can * race with cgroup_attach_task() or update_cpumask() and get * the wrong tsk->cpus_allowed. However, both cases imply the * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr() * which takes task_rq_lock(). * * If we are called after it dropped the lock we must see all * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary * set any mask even if it is not right from task_cs() pov, * the pending set_cpus_allowed_ptr() will fix things. * * select_fallback_rq() will fix things ups and set cpu_possible_mask * if required. */ return changed; } void __init cpuset_init_current_mems_allowed(void) { nodes_setall(current->mems_allowed); } /** * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed. * * Description: Returns the nodemask_t mems_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of node_states[N_MEMORY], even if this means going outside the * tasks cpuset. **/ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) { nodemask_t mask; unsigned long flags; spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); guarantee_online_mems(task_cs(tsk), &mask); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); return mask; } /** * cpuset_nodemask_valid_mems_allowed - check nodemask vs. current mems_allowed * @nodemask: the nodemask to be checked * * Are any of the nodes in the nodemask allowed in current->mems_allowed? */ int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return nodes_intersects(*nodemask, current->mems_allowed); } /* * nearest_hardwall_ancestor() - Returns the nearest mem_exclusive or * mem_hardwall ancestor to the specified cpuset. Call holding * callback_lock. If no ancestor is mem_exclusive or mem_hardwall * (an unusual configuration), then returns the root cpuset. */ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) { while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && parent_cs(cs)) cs = parent_cs(cs); return cs; } /** * cpuset_node_allowed - Can we allocate on a memory node? * @node: is this an allowed node? * @gfp_mask: memory allocation flags * * If we're in interrupt, yes, we can always allocate. If @node is set in * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, * yes. If current has access to memory reserves as an oom victim, yes. * Otherwise, no. * * GFP_USER allocations are marked with the __GFP_HARDWALL bit, * and do not allow allocations outside the current tasks cpuset * unless the task has been OOM killed. * GFP_KERNEL allocations are not so marked, so can escape to the * nearest enclosing hardwalled ancestor cpuset. * * Scanning up parent cpusets requires callback_lock. The * __alloc_pages() routine only calls here with __GFP_HARDWALL bit * _not_ set if it's a GFP_KERNEL allocation, and all nodes in the * current tasks mems_allowed came up empty on the first pass over * the zonelist. So only GFP_KERNEL allocations, if all nodes in the * cpuset are short of memory, might require taking the callback_lock. * * The first call here from mm/page_alloc:get_page_from_freelist() * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, * so no allocation on a node outside the cpuset is allowed (unless * in interrupt, of course). * * The second pass through get_page_from_freelist() doesn't even call * here for GFP_ATOMIC calls. For those calls, the __alloc_pages() * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set * in alloc_flags. That logic and the checks below have the combined * affect that: * in_interrupt - any node ok (current task context irrelevant) * GFP_ATOMIC - any node ok * tsk_is_oom_victim - any node ok * GFP_KERNEL - any node in enclosing hardwalled cpuset ok * GFP_USER - only nodes in current tasks mems allowed ok. */ bool __cpuset_node_allowed(int node, gfp_t gfp_mask) { struct cpuset *cs; /* current cpuset ancestors */ int allowed; /* is allocation in zone z allowed? */ unsigned long flags; if (in_interrupt()) return true; if (node_isset(node, current->mems_allowed)) return true; /* * Allow tasks that have access to memory reserves because they have * been OOM killed to get memory anywhere. */ if (unlikely(tsk_is_oom_victim(current))) return true; if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ return false; if (current->flags & PF_EXITING) /* Let dying task have memory */ return true; /* Not hardwall and node outside mems_allowed: scan up cpusets */ spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); cs = nearest_hardwall_ancestor(task_cs(current)); allowed = node_isset(node, cs->mems_allowed); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); return allowed; } /** * cpuset_mem_spread_node() - On which node to begin search for a file page * cpuset_slab_spread_node() - On which node to begin search for a slab page * * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for * tasks in a cpuset with is_spread_page or is_spread_slab set), * and if the memory allocation used cpuset_mem_spread_node() * to determine on which node to start looking, as it will for * certain page cache or slab cache pages such as used for file * system buffers and inode caches, then instead of starting on the * local node to look for a free page, rather spread the starting * node around the tasks mems_allowed nodes. * * We don't have to worry about the returned node being offline * because "it can't happen", and even if it did, it would be ok. * * The routines calling guarantee_online_mems() are careful to * only set nodes in task->mems_allowed that are online. So it * should not be possible for the following code to return an * offline node. But if it did, that would be ok, as this routine * is not returning the node where the allocation must be, only * the node where the search should start. The zonelist passed to * __alloc_pages() will include all nodes. If the slab allocator * is passed an offline node, it will fall back to the local node. * See kmem_cache_alloc_node(). */ static int cpuset_spread_node(int *rotor) { return *rotor = next_node_in(*rotor, current->mems_allowed); } int cpuset_mem_spread_node(void) { if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) current->cpuset_mem_spread_rotor = node_random(¤t->mems_allowed); return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); } int cpuset_slab_spread_node(void) { if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) current->cpuset_slab_spread_rotor = node_random(¤t->mems_allowed); return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); } EXPORT_SYMBOL_GPL(cpuset_mem_spread_node); /** * cpuset_mems_allowed_intersects - Does @tsk1's mems_allowed intersect @tsk2's? * @tsk1: pointer to task_struct of some task. * @tsk2: pointer to task_struct of some other task. * * Description: Return true if @tsk1's mems_allowed intersects the * mems_allowed of @tsk2. Used by the OOM killer to determine if * one of the task's memory usage might impact the memory available * to the other. **/ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed); } /** * cpuset_print_current_mems_allowed - prints current's cpuset and mems_allowed * * Description: Prints current's name, cpuset name, and cached copy of its * mems_allowed to the kernel log. */ void cpuset_print_current_mems_allowed(void) { struct cgroup *cgrp; rcu_read_lock(); cgrp = task_cs(current)->css.cgroup; pr_cont(",cpuset="); pr_cont_cgroup_name(cgrp); pr_cont(",mems_allowed=%*pbl", nodemask_pr_args(¤t->mems_allowed)); rcu_read_unlock(); } /* * Collection of memory_pressure is suppressed unless * this flag is enabled by writing "1" to the special * cpuset file 'memory_pressure_enabled' in the root cpuset. */ int cpuset_memory_pressure_enabled __read_mostly; /** * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. * * Keep a running average of the rate of synchronous (direct) * page reclaim efforts initiated by tasks in each cpuset. * * This represents the rate at which some task in the cpuset * ran low on memory on all nodes it was allowed to use, and * had to enter the kernels page reclaim code in an effort to * create more free memory by tossing clean pages or swapping * or writing dirty pages. * * Display to user space in the per-cpuset read-only file * "memory_pressure". Value displayed is an integer * representing the recent rate of entry into the synchronous * (direct) page reclaim by any task attached to the cpuset. **/ void __cpuset_memory_pressure_bump(void) { rcu_read_lock(); fmeter_markevent(&task_cs(current)->fmeter); rcu_read_unlock(); } #ifdef CONFIG_PROC_PID_CPUSET /* * proc_cpuset_show() * - Print tasks cpuset path into seq_file. * - Used for /proc/<pid>/cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, * and we take cpuset_mutex, keeping cpuset_attach() from changing it * anyway. */ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { char *buf; struct cgroup_subsys_state *css; int retval; retval = -ENOMEM; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; rcu_read_lock(); spin_lock_irq(&css_set_lock); css = task_css(tsk, cpuset_cgrp_id); retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX, current->nsproxy->cgroup_ns); spin_unlock_irq(&css_set_lock); rcu_read_unlock(); if (retval >= PATH_MAX) retval = -ENAMETOOLONG; if (retval < 0) goto out_free; seq_puts(m, buf); seq_putc(m, '\n'); retval = 0; out_free: kfree(buf); out: return retval; } #endif /* CONFIG_PROC_PID_CPUSET */ /* Display task mems_allowed in /proc/<pid>/status file. */ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Mems_allowed:\t%*pb\n", nodemask_pr_args(&task->mems_allowed)); seq_printf(m, "Mems_allowed_list:\t%*pbl\n", nodemask_pr_args(&task->mems_allowed)); } |
| 1355 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 | // SPDX-License-Identifier: GPL-2.0 /* * Creating audit events from TTY input. * * Copyright (C) 2007 Red Hat, Inc. All rights reserved. * * Authors: Miloslav Trmac <mitr@redhat.com> */ #include <linux/audit.h> #include <linux/slab.h> #include <linux/tty.h> #include "tty.h" struct tty_audit_buf { struct mutex mutex; /* Protects all data below */ dev_t dev; /* The TTY which the data is from */ unsigned icanon:1; size_t valid; unsigned char *data; /* Allocated size N_TTY_BUF_SIZE */ }; static struct tty_audit_buf *tty_audit_buf_ref(void) { struct tty_audit_buf *buf; buf = current->signal->tty_audit_buf; WARN_ON(buf == ERR_PTR(-ESRCH)); return buf; } static struct tty_audit_buf *tty_audit_buf_alloc(void) { struct tty_audit_buf *buf; buf = kmalloc(sizeof(*buf), GFP_KERNEL); if (!buf) goto err; buf->data = kmalloc(N_TTY_BUF_SIZE, GFP_KERNEL); if (!buf->data) goto err_buf; mutex_init(&buf->mutex); buf->dev = MKDEV(0, 0); buf->icanon = 0; buf->valid = 0; return buf; err_buf: kfree(buf); err: return NULL; } static void tty_audit_buf_free(struct tty_audit_buf *buf) { WARN_ON(buf->valid != 0); kfree(buf->data); kfree(buf); } static void tty_audit_log(const char *description, dev_t dev, unsigned char *data, size_t size) { struct audit_buffer *ab; pid_t pid = task_pid_nr(current); uid_t uid = from_kuid(&init_user_ns, task_uid(current)); uid_t loginuid = from_kuid(&init_user_ns, audit_get_loginuid(current)); unsigned int sessionid = audit_get_sessionid(current); ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_TTY); if (ab) { char name[sizeof(current->comm)]; audit_log_format(ab, "%s pid=%u uid=%u auid=%u ses=%u major=%d" " minor=%d comm=", description, pid, uid, loginuid, sessionid, MAJOR(dev), MINOR(dev)); get_task_comm(name, current); audit_log_untrustedstring(ab, name); audit_log_format(ab, " data="); audit_log_n_hex(ab, data, size); audit_log_end(ab); } } /* * tty_audit_buf_push - Push buffered data out * * Generate an audit message from the contents of @buf, which is owned by * the current task. @buf->mutex must be locked. */ static void tty_audit_buf_push(struct tty_audit_buf *buf) { if (buf->valid == 0) return; if (audit_enabled == AUDIT_OFF) { buf->valid = 0; return; } tty_audit_log("tty", buf->dev, buf->data, buf->valid); buf->valid = 0; } /** * tty_audit_exit - Handle a task exit * * Make sure all buffered data is written out and deallocate the buffer. * Only needs to be called if current->signal->tty_audit_buf != %NULL. * * The process is single-threaded at this point; no other threads share * current->signal. */ void tty_audit_exit(void) { struct tty_audit_buf *buf; buf = xchg(¤t->signal->tty_audit_buf, ERR_PTR(-ESRCH)); if (!buf) return; tty_audit_buf_push(buf); tty_audit_buf_free(buf); } /* * tty_audit_fork - Copy TTY audit state for a new task * * Set up TTY audit state in @sig from current. @sig needs no locking. */ void tty_audit_fork(struct signal_struct *sig) { sig->audit_tty = current->signal->audit_tty; } /* * tty_audit_tiocsti - Log TIOCSTI */ void tty_audit_tiocsti(struct tty_struct *tty, char ch) { dev_t dev; dev = MKDEV(tty->driver->major, tty->driver->minor_start) + tty->index; if (tty_audit_push()) return; if (audit_enabled) tty_audit_log("ioctl=TIOCSTI", dev, &ch, 1); } /* * tty_audit_push - Flush current's pending audit data * * Returns 0 if success, -EPERM if tty audit is disabled */ int tty_audit_push(void) { struct tty_audit_buf *buf; if (~current->signal->audit_tty & AUDIT_TTY_ENABLE) return -EPERM; buf = tty_audit_buf_ref(); if (!IS_ERR_OR_NULL(buf)) { mutex_lock(&buf->mutex); tty_audit_buf_push(buf); mutex_unlock(&buf->mutex); } return 0; } /* * tty_audit_buf_get - Get an audit buffer. * * Get an audit buffer, allocate it if necessary. Return %NULL * if out of memory or ERR_PTR(-ESRCH) if tty_audit_exit() has already * occurred. Otherwise, return a new reference to the buffer. */ static struct tty_audit_buf *tty_audit_buf_get(void) { struct tty_audit_buf *buf; buf = tty_audit_buf_ref(); if (buf) return buf; buf = tty_audit_buf_alloc(); if (buf == NULL) { audit_log_lost("out of memory in TTY auditing"); return NULL; } /* Race to use this buffer, free it if another wins */ if (cmpxchg(¤t->signal->tty_audit_buf, NULL, buf) != NULL) tty_audit_buf_free(buf); return tty_audit_buf_ref(); } /* * tty_audit_add_data - Add data for TTY auditing. * * Audit @data of @size from @tty, if necessary. */ void tty_audit_add_data(struct tty_struct *tty, const void *data, size_t size) { struct tty_audit_buf *buf; unsigned int icanon = !!L_ICANON(tty); unsigned int audit_tty; dev_t dev; audit_tty = READ_ONCE(current->signal->audit_tty); if (~audit_tty & AUDIT_TTY_ENABLE) return; if (unlikely(size == 0)) return; if (tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER) return; if ((~audit_tty & AUDIT_TTY_LOG_PASSWD) && icanon && !L_ECHO(tty)) return; buf = tty_audit_buf_get(); if (IS_ERR_OR_NULL(buf)) return; mutex_lock(&buf->mutex); dev = MKDEV(tty->driver->major, tty->driver->minor_start) + tty->index; if (buf->dev != dev || buf->icanon != icanon) { tty_audit_buf_push(buf); buf->dev = dev; buf->icanon = icanon; } do { size_t run; run = N_TTY_BUF_SIZE - buf->valid; if (run > size) run = size; memcpy(buf->data + buf->valid, data, run); buf->valid += run; data += run; size -= run; if (buf->valid == N_TTY_BUF_SIZE) tty_audit_buf_push(buf); } while (size != 0); mutex_unlock(&buf->mutex); } |
| 749 749 749 749 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 | // SPDX-License-Identifier: GPL-2.0-or-later /* 6LoWPAN fragment reassembly * * Authors: * Alexander Aring <aar@pengutronix.de> * * Based on: net/ipv6/reassembly.c */ #define pr_fmt(fmt) "6LoWPAN: " fmt #include <linux/net.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/jhash.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/export.h> #include <net/ieee802154_netdev.h> #include <net/6lowpan.h> #include <net/ipv6_frag.h> #include <net/inet_frag.h> #include <net/ip.h> #include "6lowpan_i.h" static const char lowpan_frags_cache_name[] = "lowpan-frags"; static struct inet_frags lowpan_frags; static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev, struct net_device *ldev); static void lowpan_frag_init(struct inet_frag_queue *q, const void *a) { const struct frag_lowpan_compare_key *key = a; BUILD_BUG_ON(sizeof(*key) > sizeof(q->key)); memcpy(&q->key, key, sizeof(*key)); } static void lowpan_frag_expire(struct timer_list *t) { struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; fq = container_of(frag, struct frag_queue, q); spin_lock(&fq->q.lock); if (fq->q.flags & INET_FRAG_COMPLETE) goto out; inet_frag_kill(&fq->q); out: spin_unlock(&fq->q.lock); inet_frag_put(&fq->q); } static inline struct lowpan_frag_queue * fq_find(struct net *net, const struct lowpan_802154_cb *cb, const struct ieee802154_addr *src, const struct ieee802154_addr *dst) { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); struct frag_lowpan_compare_key key = {}; struct inet_frag_queue *q; key.tag = cb->d_tag; key.d_size = cb->d_size; key.src = *src; key.dst = *dst; q = inet_frag_find(ieee802154_lowpan->fqdir, &key); if (!q) return NULL; return container_of(q, struct lowpan_frag_queue, q); } static int lowpan_frag_queue(struct lowpan_frag_queue *fq, struct sk_buff *skb, u8 frag_type) { struct sk_buff *prev_tail; struct net_device *ldev; int end, offset, err; /* inet_frag_queue_* functions use skb->cb; see struct ipfrag_skb_cb * in inet_fragment.c */ BUILD_BUG_ON(sizeof(struct lowpan_802154_cb) > sizeof(struct inet_skb_parm)); BUILD_BUG_ON(sizeof(struct lowpan_802154_cb) > sizeof(struct inet6_skb_parm)); if (fq->q.flags & INET_FRAG_COMPLETE) goto err; offset = lowpan_802154_cb(skb)->d_offset << 3; end = lowpan_802154_cb(skb)->d_size; /* Is this the final fragment? */ if (offset + skb->len == end) { /* If we already have some bits beyond end * or have different end, the segment is corrupted. */ if (end < fq->q.len || ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) goto err; fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ if (fq->q.flags & INET_FRAG_LAST_IN) goto err; fq->q.len = end; } } ldev = skb->dev; if (ldev) skb->dev = NULL; barrier(); prev_tail = fq->q.fragments_tail; err = inet_frag_queue_insert(&fq->q, skb, offset, end); if (err) goto err; fq->q.stamp = skb->tstamp; if (frag_type == LOWPAN_DISPATCH_FRAG1) fq->q.flags |= INET_FRAG_FIRST_IN; fq->q.meat += skb->len; add_frag_mem_limit(fq->q.fqdir, skb->truesize); if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { int res; unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; res = lowpan_frag_reasm(fq, skb, prev_tail, ldev); skb->_skb_refdst = orefdst; return res; } skb_dst_drop(skb); return -1; err: kfree_skb(skb); return -1; } /* Check if this packet is complete. * * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. */ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *ldev) { void *reasm_data; inet_frag_kill(&fq->q); reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); if (!reasm_data) goto out_oom; inet_frag_reasm_finish(&fq->q, skb, reasm_data, false); skb->dev = ldev; skb->tstamp = fq->q.stamp; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; fq->q.last_run_head = NULL; return 1; out_oom: net_dbg_ratelimited("lowpan_frag_reasm: no memory for reassembly\n"); return -1; } static int lowpan_frag_rx_handlers_result(struct sk_buff *skb, lowpan_rx_result res) { switch (res) { case RX_QUEUED: return NET_RX_SUCCESS; case RX_CONTINUE: /* nobody cared about this packet */ net_warn_ratelimited("%s: received unknown dispatch\n", __func__); fallthrough; default: /* all others failure */ return NET_RX_DROP; } } static lowpan_rx_result lowpan_frag_rx_h_iphc(struct sk_buff *skb) { int ret; if (!lowpan_is_iphc(*skb_network_header(skb))) return RX_CONTINUE; ret = lowpan_iphc_decompress(skb); if (ret < 0) return RX_DROP; return RX_QUEUED; } static int lowpan_invoke_frag_rx_handlers(struct sk_buff *skb) { lowpan_rx_result res; #define CALL_RXH(rxh) \ do { \ res = rxh(skb); \ if (res != RX_CONTINUE) \ goto rxh_next; \ } while (0) /* likely at first */ CALL_RXH(lowpan_frag_rx_h_iphc); CALL_RXH(lowpan_rx_h_ipv6); rxh_next: return lowpan_frag_rx_handlers_result(skb, res); #undef CALL_RXH } #define LOWPAN_FRAG_DGRAM_SIZE_HIGH_MASK 0x07 #define LOWPAN_FRAG_DGRAM_SIZE_HIGH_SHIFT 8 static int lowpan_get_cb(struct sk_buff *skb, u8 frag_type, struct lowpan_802154_cb *cb) { bool fail; u8 high = 0, low = 0; __be16 d_tag = 0; fail = lowpan_fetch_skb(skb, &high, 1); fail |= lowpan_fetch_skb(skb, &low, 1); /* remove the dispatch value and use first three bits as high value * for the datagram size */ cb->d_size = (high & LOWPAN_FRAG_DGRAM_SIZE_HIGH_MASK) << LOWPAN_FRAG_DGRAM_SIZE_HIGH_SHIFT | low; fail |= lowpan_fetch_skb(skb, &d_tag, 2); cb->d_tag = ntohs(d_tag); if (frag_type == LOWPAN_DISPATCH_FRAGN) { fail |= lowpan_fetch_skb(skb, &cb->d_offset, 1); } else { skb_reset_network_header(skb); cb->d_offset = 0; /* check if datagram_size has ipv6hdr on FRAG1 */ fail |= cb->d_size < sizeof(struct ipv6hdr); /* check if we can dereference the dispatch value */ fail |= !skb->len; } if (unlikely(fail)) return -EIO; return 0; } int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type) { struct lowpan_frag_queue *fq; struct net *net = dev_net(skb->dev); struct lowpan_802154_cb *cb = lowpan_802154_cb(skb); struct ieee802154_hdr hdr = {}; int err; if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) goto err; err = lowpan_get_cb(skb, frag_type, cb); if (err < 0) goto err; if (frag_type == LOWPAN_DISPATCH_FRAG1) { err = lowpan_invoke_frag_rx_handlers(skb); if (err == NET_RX_DROP) goto err; } if (cb->d_size > IPV6_MIN_MTU) { net_warn_ratelimited("lowpan_frag_rcv: datagram size exceeds MTU\n"); goto err; } fq = fq_find(net, cb, &hdr.source, &hdr.dest); if (fq != NULL) { int ret; spin_lock(&fq->q.lock); ret = lowpan_frag_queue(fq, skb, frag_type); spin_unlock(&fq->q.lock); inet_frag_put(&fq->q); return ret; } err: kfree_skb(skb); return -1; } #ifdef CONFIG_SYSCTL static struct ctl_table lowpan_frags_ns_ctl_table[] = { { .procname = "6lowpanfrag_high_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "6lowpanfrag_low_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "6lowpanfrag_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { } }; /* secret interval has been deprecated */ static int lowpan_frags_secret_interval_unused; static struct ctl_table lowpan_frags_ctl_table[] = { { .procname = "6lowpanfrag_secret_interval", .data = &lowpan_frags_secret_interval_unused, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { } }; static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); table = lowpan_frags_ns_ctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(lowpan_frags_ns_ctl_table), GFP_KERNEL); if (table == NULL) goto err_alloc; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) table[0].procname = NULL; } table[0].data = &ieee802154_lowpan->fqdir->high_thresh; table[0].extra1 = &ieee802154_lowpan->fqdir->low_thresh; table[1].data = &ieee802154_lowpan->fqdir->low_thresh; table[1].extra2 = &ieee802154_lowpan->fqdir->high_thresh; table[2].data = &ieee802154_lowpan->fqdir->timeout; hdr = register_net_sysctl(net, "net/ieee802154/6lowpan", table); if (hdr == NULL) goto err_reg; ieee802154_lowpan->sysctl.frags_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static void __net_exit lowpan_frags_ns_sysctl_unregister(struct net *net) { struct ctl_table *table; struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); table = ieee802154_lowpan->sysctl.frags_hdr->ctl_table_arg; unregister_net_sysctl_table(ieee802154_lowpan->sysctl.frags_hdr); if (!net_eq(net, &init_net)) kfree(table); } static struct ctl_table_header *lowpan_ctl_header; static int __init lowpan_frags_sysctl_register(void) { lowpan_ctl_header = register_net_sysctl(&init_net, "net/ieee802154/6lowpan", lowpan_frags_ctl_table); return lowpan_ctl_header == NULL ? -ENOMEM : 0; } static void lowpan_frags_sysctl_unregister(void) { unregister_net_sysctl_table(lowpan_ctl_header); } #else static inline int lowpan_frags_ns_sysctl_register(struct net *net) { return 0; } static inline void lowpan_frags_ns_sysctl_unregister(struct net *net) { } static inline int __init lowpan_frags_sysctl_register(void) { return 0; } static inline void lowpan_frags_sysctl_unregister(void) { } #endif static int __net_init lowpan_frags_init_net(struct net *net) { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); int res; res = fqdir_init(&ieee802154_lowpan->fqdir, &lowpan_frags, net); if (res < 0) return res; ieee802154_lowpan->fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; ieee802154_lowpan->fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; ieee802154_lowpan->fqdir->timeout = IPV6_FRAG_TIMEOUT; res = lowpan_frags_ns_sysctl_register(net); if (res < 0) fqdir_exit(ieee802154_lowpan->fqdir); return res; } static void __net_exit lowpan_frags_pre_exit_net(struct net *net) { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); fqdir_pre_exit(ieee802154_lowpan->fqdir); } static void __net_exit lowpan_frags_exit_net(struct net *net) { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); lowpan_frags_ns_sysctl_unregister(net); fqdir_exit(ieee802154_lowpan->fqdir); } static struct pernet_operations lowpan_frags_ops = { .init = lowpan_frags_init_net, .pre_exit = lowpan_frags_pre_exit_net, .exit = lowpan_frags_exit_net, }; static u32 lowpan_key_hashfn(const void *data, u32 len, u32 seed) { return jhash2(data, sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed); } static u32 lowpan_obj_hashfn(const void *data, u32 len, u32 seed) { const struct inet_frag_queue *fq = data; return jhash2((const u32 *)&fq->key, sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed); } static int lowpan_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) { const struct frag_lowpan_compare_key *key = arg->key; const struct inet_frag_queue *fq = ptr; return !!memcmp(&fq->key, key, sizeof(*key)); } static const struct rhashtable_params lowpan_rhash_params = { .head_offset = offsetof(struct inet_frag_queue, node), .hashfn = lowpan_key_hashfn, .obj_hashfn = lowpan_obj_hashfn, .obj_cmpfn = lowpan_obj_cmpfn, .automatic_shrinking = true, }; int __init lowpan_net_frag_init(void) { int ret; lowpan_frags.constructor = lowpan_frag_init; lowpan_frags.destructor = NULL; lowpan_frags.qsize = sizeof(struct frag_queue); lowpan_frags.frag_expire = lowpan_frag_expire; lowpan_frags.frags_cache_name = lowpan_frags_cache_name; lowpan_frags.rhash_params = lowpan_rhash_params; ret = inet_frags_init(&lowpan_frags); if (ret) goto out; ret = lowpan_frags_sysctl_register(); if (ret) goto err_sysctl; ret = register_pernet_subsys(&lowpan_frags_ops); if (ret) goto err_pernet; out: return ret; err_pernet: lowpan_frags_sysctl_unregister(); err_sysctl: inet_frags_fini(&lowpan_frags); return ret; } void lowpan_net_frag_exit(void) { lowpan_frags_sysctl_unregister(); unregister_pernet_subsys(&lowpan_frags_ops); inet_frags_fini(&lowpan_frags); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef IOCONTEXT_H #define IOCONTEXT_H #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> enum { ICQ_EXITED = 1 << 2, ICQ_DESTROYED = 1 << 3, }; /* * An io_cq (icq) is association between an io_context (ioc) and a * request_queue (q). This is used by elevators which need to track * information per ioc - q pair. * * Elevator can request use of icq by setting elevator_type->icq_size and * ->icq_align. Both size and align must be larger than that of struct * io_cq and elevator can use the tail area for private information. The * recommended way to do this is defining a struct which contains io_cq as * the first member followed by private members and using its size and * align. For example, * * struct snail_io_cq { * struct io_cq icq; * int poke_snail; * int feed_snail; * }; * * struct elevator_type snail_elv_type { * .ops = { ... }, * .icq_size = sizeof(struct snail_io_cq), * .icq_align = __alignof__(struct snail_io_cq), * ... * }; * * If icq_size is set, block core will manage icq's. All requests will * have its ->elv.icq field set before elevator_ops->elevator_set_req_fn() * is called and be holding a reference to the associated io_context. * * Whenever a new icq is created, elevator_ops->elevator_init_icq_fn() is * called and, on destruction, ->elevator_exit_icq_fn(). Both functions * are called with both the associated io_context and queue locks held. * * Elevator is allowed to lookup icq using ioc_lookup_icq() while holding * queue lock but the returned icq is valid only until the queue lock is * released. Elevators can not and should not try to create or destroy * icq's. * * As icq's are linked from both ioc and q, the locking rules are a bit * complex. * * - ioc lock nests inside q lock. * * - ioc->icq_list and icq->ioc_node are protected by ioc lock. * q->icq_list and icq->q_node by q lock. * * - ioc->icq_tree and ioc->icq_hint are protected by ioc lock, while icq * itself is protected by q lock. However, both the indexes and icq * itself are also RCU managed and lookup can be performed holding only * the q lock. * * - icq's are not reference counted. They are destroyed when either the * ioc or q goes away. Each request with icq set holds an extra * reference to ioc to ensure it stays until the request is completed. * * - Linking and unlinking icq's are performed while holding both ioc and q * locks. Due to the lock ordering, q exit is simple but ioc exit * requires reverse-order double lock dance. */ struct io_cq { struct request_queue *q; struct io_context *ioc; /* * q_node and ioc_node link io_cq through icq_list of q and ioc * respectively. Both fields are unused once ioc_exit_icq() is * called and shared with __rcu_icq_cache and __rcu_head which are * used for RCU free of io_cq. */ union { struct list_head q_node; struct kmem_cache *__rcu_icq_cache; }; union { struct hlist_node ioc_node; struct rcu_head __rcu_head; }; unsigned int flags; }; /* * I/O subsystem state of the associated processes. It is refcounted * and kmalloc'ed. These could be shared between processes. */ struct io_context { atomic_long_t refcount; atomic_t active_ref; atomic_t nr_tasks; /* all the fields below are protected by this lock */ spinlock_t lock; unsigned short ioprio; struct radix_tree_root icq_tree; struct io_cq __rcu *icq_hint; struct hlist_head icq_list; struct work_struct release_work; }; /** * get_io_context_active - get active reference on ioc * @ioc: ioc of interest * * Only iocs with active reference can issue new IOs. This function * acquires an active reference on @ioc. The caller must already have an * active reference on @ioc. */ static inline void get_io_context_active(struct io_context *ioc) { WARN_ON_ONCE(atomic_long_read(&ioc->refcount) <= 0); WARN_ON_ONCE(atomic_read(&ioc->active_ref) <= 0); atomic_long_inc(&ioc->refcount); atomic_inc(&ioc->active_ref); } static inline void ioc_task_link(struct io_context *ioc) { get_io_context_active(ioc); WARN_ON_ONCE(atomic_read(&ioc->nr_tasks) <= 0); atomic_inc(&ioc->nr_tasks); } struct task_struct; #ifdef CONFIG_BLOCK void put_io_context(struct io_context *ioc); void put_io_context_active(struct io_context *ioc); void exit_io_context(struct task_struct *task); struct io_context *get_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node); #else struct io_context; static inline void put_io_context(struct io_context *ioc) { } static inline void exit_io_context(struct task_struct *task) { } #endif #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MLD_H #define LINUX_MLD_H #include <linux/in6.h> #include <linux/icmpv6.h> /* MLDv1 Query/Report/Done */ struct mld_msg { struct icmp6hdr mld_hdr; struct in6_addr mld_mca; }; #define mld_type mld_hdr.icmp6_type #define mld_code mld_hdr.icmp6_code #define mld_cksum mld_hdr.icmp6_cksum #define mld_maxdelay mld_hdr.icmp6_maxdelay #define mld_reserved mld_hdr.icmp6_dataun.un_data16[1] /* Multicast Listener Discovery version 2 headers */ /* MLDv2 Report */ struct mld2_grec { __u8 grec_type; __u8 grec_auxwords; __be16 grec_nsrcs; struct in6_addr grec_mca; struct in6_addr grec_src[]; }; struct mld2_report { struct icmp6hdr mld2r_hdr; struct mld2_grec mld2r_grec[]; }; #define mld2r_type mld2r_hdr.icmp6_type #define mld2r_resv1 mld2r_hdr.icmp6_code #define mld2r_cksum mld2r_hdr.icmp6_cksum #define mld2r_resv2 mld2r_hdr.icmp6_dataun.un_data16[0] #define mld2r_ngrec mld2r_hdr.icmp6_dataun.un_data16[1] /* MLDv2 Query */ struct mld2_query { struct icmp6hdr mld2q_hdr; struct in6_addr mld2q_mca; #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 mld2q_qrv:3, mld2q_suppress:1, mld2q_resv2:4; #elif defined(__BIG_ENDIAN_BITFIELD) __u8 mld2q_resv2:4, mld2q_suppress:1, mld2q_qrv:3; #else #error "Please fix <asm/byteorder.h>" #endif __u8 mld2q_qqic; __be16 mld2q_nsrcs; struct in6_addr mld2q_srcs[]; }; #define mld2q_type mld2q_hdr.icmp6_type #define mld2q_code mld2q_hdr.icmp6_code #define mld2q_cksum mld2q_hdr.icmp6_cksum #define mld2q_mrc mld2q_hdr.icmp6_maxdelay #define mld2q_resv1 mld2q_hdr.icmp6_dataun.un_data16[1] /* RFC3810, 5.1.3. Maximum Response Code: * * If Maximum Response Code >= 32768, Maximum Response Code represents a * floating-point value as follows: * * 0 1 2 3 4 5 6 7 8 9 A B C D E F * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |1| exp | mant | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ #define MLDV2_MRC_EXP(value) (((value) >> 12) & 0x0007) #define MLDV2_MRC_MAN(value) ((value) & 0x0fff) /* RFC3810, 5.1.9. QQIC (Querier's Query Interval Code): * * If QQIC >= 128, QQIC represents a floating-point value as follows: * * 0 1 2 3 4 5 6 7 * +-+-+-+-+-+-+-+-+ * |1| exp | mant | * +-+-+-+-+-+-+-+-+ */ #define MLDV2_QQIC_EXP(value) (((value) >> 4) & 0x07) #define MLDV2_QQIC_MAN(value) ((value) & 0x0f) #define MLD_EXP_MIN_LIMIT 32768UL #define MLDV1_MRD_MAX_COMPAT (MLD_EXP_MIN_LIMIT - 1) #define MLD_MAX_QUEUE 8 #define MLD_MAX_SKBS 32 static inline unsigned long mldv2_mrc(const struct mld2_query *mlh2) { /* RFC3810, 5.1.3. Maximum Response Code */ unsigned long ret, mc_mrc = ntohs(mlh2->mld2q_mrc); if (mc_mrc < MLD_EXP_MIN_LIMIT) { ret = mc_mrc; } else { unsigned long mc_man, mc_exp; mc_exp = MLDV2_MRC_EXP(mc_mrc); mc_man = MLDV2_MRC_MAN(mc_mrc); ret = (mc_man | 0x1000) << (mc_exp + 3); } return ret; } #endif |
| 108 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/pagevec.h * * In many places it is efficient to batch an operation up against multiple * pages. A pagevec is a multipage container which is used for that. */ #ifndef _LINUX_PAGEVEC_H #define _LINUX_PAGEVEC_H #include <linux/xarray.h> /* 15 pointers + header align the pagevec structure to a power of two */ #define PAGEVEC_SIZE 15 struct page; struct address_space; struct pagevec { unsigned char nr; bool percpu_pvec_drained; struct page *pages[PAGEVEC_SIZE]; }; void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start, pgoff_t end); static inline unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start) { return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1); } unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag); static inline unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, xa_mark_t tag) { return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag); } static inline void pagevec_init(struct pagevec *pvec) { pvec->nr = 0; pvec->percpu_pvec_drained = false; } static inline void pagevec_reinit(struct pagevec *pvec) { pvec->nr = 0; } static inline unsigned pagevec_count(struct pagevec *pvec) { return pvec->nr; } static inline unsigned pagevec_space(struct pagevec *pvec) { return PAGEVEC_SIZE - pvec->nr; } /* * Add a page to a pagevec. Returns the number of slots still available. */ static inline unsigned pagevec_add(struct pagevec *pvec, struct page *page) { pvec->pages[pvec->nr++] = page; return pagevec_space(pvec); } static inline void pagevec_release(struct pagevec *pvec) { if (pagevec_count(pvec)) __pagevec_release(pvec); } #endif /* _LINUX_PAGEVEC_H */ |
| 2 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 | // SPDX-License-Identifier: GPL-2.0 /* * To speed up listener socket lookup, create an array to store all sockets * listening on the same port. This allows a decision to be made after finding * the first socket. An optional BPF program can also be configured for * selecting the socket index from the array of available sockets. */ #include <net/ip.h> #include <net/sock_reuseport.h> #include <linux/bpf.h> #include <linux/idr.h> #include <linux/filter.h> #include <linux/rcupdate.h> #define INIT_SOCKS 128 DEFINE_SPINLOCK(reuseport_lock); static DEFINE_IDA(reuseport_ida); static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, struct sock_reuseport *reuse, bool bind_inany); void reuseport_has_conns_set(struct sock *sk) { struct sock_reuseport *reuse; if (!rcu_access_pointer(sk->sk_reuseport_cb)) return; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (likely(reuse)) reuse->has_conns = 1; spin_unlock_bh(&reuseport_lock); } EXPORT_SYMBOL(reuseport_has_conns_set); static int reuseport_sock_index(struct sock *sk, const struct sock_reuseport *reuse, bool closed) { int left, right; if (!closed) { left = 0; right = reuse->num_socks; } else { left = reuse->max_socks - reuse->num_closed_socks; right = reuse->max_socks; } for (; left < right; left++) if (reuse->socks[left] == sk) return left; return -1; } static void __reuseport_add_sock(struct sock *sk, struct sock_reuseport *reuse) { reuse->socks[reuse->num_socks] = sk; /* paired with smp_rmb() in reuseport_(select|migrate)_sock() */ smp_wmb(); reuse->num_socks++; } static bool __reuseport_detach_sock(struct sock *sk, struct sock_reuseport *reuse) { int i = reuseport_sock_index(sk, reuse, false); if (i == -1) return false; reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; reuse->num_socks--; return true; } static void __reuseport_add_closed_sock(struct sock *sk, struct sock_reuseport *reuse) { reuse->socks[reuse->max_socks - reuse->num_closed_socks - 1] = sk; /* paired with READ_ONCE() in inet_csk_bind_conflict() */ WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks + 1); } static bool __reuseport_detach_closed_sock(struct sock *sk, struct sock_reuseport *reuse) { int i = reuseport_sock_index(sk, reuse, true); if (i == -1) return false; reuse->socks[i] = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; /* paired with READ_ONCE() in inet_csk_bind_conflict() */ WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks - 1); return true; } static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { unsigned int size = sizeof(struct sock_reuseport) + sizeof(struct sock *) * max_socks; struct sock_reuseport *reuse = kzalloc(size, GFP_ATOMIC); if (!reuse) return NULL; reuse->max_socks = max_socks; RCU_INIT_POINTER(reuse->prog, NULL); return reuse; } int reuseport_alloc(struct sock *sk, bool bind_inany) { struct sock_reuseport *reuse; int id, ret = 0; /* bh lock used since this function call may precede hlist lock in * soft irq of receive path or setsockopt from process context */ spin_lock_bh(&reuseport_lock); /* Allocation attempts can occur concurrently via the setsockopt path * and the bind/hash path. Nothing to do when we lose the race. */ reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (reuse) { if (reuse->num_closed_socks) { /* sk was shutdown()ed before */ ret = reuseport_resurrect(sk, reuse, NULL, bind_inany); goto out; } /* Only set reuse->bind_inany if the bind_inany is true. * Otherwise, it will overwrite the reuse->bind_inany * which was set by the bind/hash path. */ if (bind_inany) reuse->bind_inany = bind_inany; goto out; } reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) { ret = -ENOMEM; goto out; } id = ida_alloc(&reuseport_ida, GFP_ATOMIC); if (id < 0) { kfree(reuse); ret = id; goto out; } reuse->reuseport_id = id; reuse->bind_inany = bind_inany; reuse->socks[0] = sk; reuse->num_socks = 1; rcu_assign_pointer(sk->sk_reuseport_cb, reuse); out: spin_unlock_bh(&reuseport_lock); return ret; } EXPORT_SYMBOL(reuseport_alloc); static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) { struct sock_reuseport *more_reuse; u32 more_socks_size, i; more_socks_size = reuse->max_socks * 2U; if (more_socks_size > U16_MAX) { if (reuse->num_closed_socks) { /* Make room by removing a closed sk. * The child has already been migrated. * Only reqsk left at this point. */ struct sock *sk; sk = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; RCU_INIT_POINTER(sk->sk_reuseport_cb, NULL); __reuseport_detach_closed_sock(sk, reuse); return reuse; } return NULL; } more_reuse = __reuseport_alloc(more_socks_size); if (!more_reuse) return NULL; more_reuse->num_socks = reuse->num_socks; more_reuse->num_closed_socks = reuse->num_closed_socks; more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; more_reuse->has_conns = reuse->has_conns; memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); memcpy(more_reuse->socks + (more_reuse->max_socks - more_reuse->num_closed_socks), reuse->socks + (reuse->max_socks - reuse->num_closed_socks), reuse->num_closed_socks * sizeof(struct sock *)); more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts); for (i = 0; i < reuse->max_socks; ++i) rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, more_reuse); /* Note: we use kfree_rcu here instead of reuseport_free_rcu so * that reuse and more_reuse can temporarily share a reference * to prog. */ kfree_rcu(reuse, rcu); return more_reuse; } static void reuseport_free_rcu(struct rcu_head *head) { struct sock_reuseport *reuse; reuse = container_of(head, struct sock_reuseport, rcu); sk_reuseport_prog_free(rcu_dereference_protected(reuse->prog, 1)); ida_free(&reuseport_ida, reuse->reuseport_id); kfree(reuse); } /** * reuseport_add_sock - Add a socket to the reuseport group of another. * @sk: New socket to add to the group. * @sk2: Socket belonging to the existing reuseport group. * @bind_inany: Whether or not the group is bound to a local INANY address. * * May return ENOMEM and not add socket to group under memory pressure. */ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) { struct sock_reuseport *old_reuse, *reuse; if (!rcu_access_pointer(sk2->sk_reuseport_cb)) { int err = reuseport_alloc(sk2, bind_inany); if (err) return err; } spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (old_reuse && old_reuse->num_closed_socks) { /* sk was shutdown()ed before */ int err = reuseport_resurrect(sk, old_reuse, reuse, reuse->bind_inany); spin_unlock_bh(&reuseport_lock); return err; } if (old_reuse && old_reuse->num_socks != 1) { spin_unlock_bh(&reuseport_lock); return -EBUSY; } if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); if (!reuse) { spin_unlock_bh(&reuseport_lock); return -ENOMEM; } } __reuseport_add_sock(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); spin_unlock_bh(&reuseport_lock); if (old_reuse) call_rcu(&old_reuse->rcu, reuseport_free_rcu); return 0; } EXPORT_SYMBOL(reuseport_add_sock); static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, struct sock_reuseport *reuse, bool bind_inany) { if (old_reuse == reuse) { /* If sk was in the same reuseport group, just pop sk out of * the closed section and push sk into the listening section. */ __reuseport_detach_closed_sock(sk, old_reuse); __reuseport_add_sock(sk, old_reuse); return 0; } if (!reuse) { /* In bind()/listen() path, we cannot carry over the eBPF prog * for the shutdown()ed socket. In setsockopt() path, we should * not change the eBPF prog of listening sockets by attaching a * prog to the shutdown()ed socket. Thus, we will allocate a new * reuseport group and detach sk from the old group. */ int id; reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) return -ENOMEM; id = ida_alloc(&reuseport_ida, GFP_ATOMIC); if (id < 0) { kfree(reuse); return id; } reuse->reuseport_id = id; reuse->bind_inany = bind_inany; } else { /* Move sk from the old group to the new one if * - all the other listeners in the old group were close()d or * shutdown()ed, and then sk2 has listen()ed on the same port * OR * - sk listen()ed without bind() (or with autobind), was * shutdown()ed, and then listen()s on another port which * sk2 listen()s on. */ if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); if (!reuse) return -ENOMEM; } } __reuseport_detach_closed_sock(sk, old_reuse); __reuseport_add_sock(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); if (old_reuse->num_socks + old_reuse->num_closed_socks == 0) call_rcu(&old_reuse->rcu, reuseport_free_rcu); return 0; } void reuseport_detach_sock(struct sock *sk) { struct sock_reuseport *reuse; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); /* reuseport_grow() has detached a closed sk */ if (!reuse) goto out; /* Notify the bpf side. The sk may be added to a sockarray * map. If so, sockarray logic will remove it from the map. * * Other bpf map types that work with reuseport, like sockmap, * don't need an explicit callback from here. They override sk * unhash/close ops to remove the sk from the map before we * get to this point. */ bpf_sk_reuseport_detach(sk); rcu_assign_pointer(sk->sk_reuseport_cb, NULL); if (!__reuseport_detach_closed_sock(sk, reuse)) __reuseport_detach_sock(sk, reuse); if (reuse->num_socks + reuse->num_closed_socks == 0) call_rcu(&reuse->rcu, reuseport_free_rcu); out: spin_unlock_bh(&reuseport_lock); } EXPORT_SYMBOL(reuseport_detach_sock); void reuseport_stop_listen_sock(struct sock *sk) { if (sk->sk_protocol == IPPROTO_TCP) { struct sock_reuseport *reuse; struct bpf_prog *prog; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); prog = rcu_dereference_protected(reuse->prog, lockdep_is_held(&reuseport_lock)); if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req) || (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) { /* Migration capable, move sk from the listening section * to the closed section. */ bpf_sk_reuseport_detach(sk); __reuseport_detach_sock(sk, reuse); __reuseport_add_closed_sock(sk, reuse); spin_unlock_bh(&reuseport_lock); return; } spin_unlock_bh(&reuseport_lock); } /* Not capable to do migration, detach immediately */ reuseport_detach_sock(sk); } EXPORT_SYMBOL(reuseport_stop_listen_sock); static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, struct bpf_prog *prog, struct sk_buff *skb, int hdr_len) { struct sk_buff *nskb = NULL; u32 index; if (skb_shared(skb)) { nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return NULL; skb = nskb; } /* temporarily advance data past protocol header */ if (!pskb_pull(skb, hdr_len)) { kfree_skb(nskb); return NULL; } index = bpf_prog_run_save_cb(prog, skb); __skb_push(skb, hdr_len); consume_skb(nskb); if (index >= socks) return NULL; return reuse->socks[index]; } static struct sock *reuseport_select_sock_by_hash(struct sock_reuseport *reuse, u32 hash, u16 num_socks) { int i, j; i = j = reciprocal_scale(hash, num_socks); while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) { i++; if (i >= num_socks) i = 0; if (i == j) return NULL; } return reuse->socks[i]; } /** * reuseport_select_sock - Select a socket from an SO_REUSEPORT group. * @sk: First socket in the group. * @hash: When no BPF filter is available, use this hash to select. * @skb: skb to run through BPF filter. * @hdr_len: BPF filter expects skb data pointer at payload data. If * the skb does not yet point at the payload, this parameter represents * how far the pointer needs to advance to reach the payload. * Returns a socket that should receive the packet (or NULL on error). */ struct sock *reuseport_select_sock(struct sock *sk, u32 hash, struct sk_buff *skb, int hdr_len) { struct sock_reuseport *reuse; struct bpf_prog *prog; struct sock *sk2 = NULL; u16 socks; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); /* if memory allocation failed or add call is not yet complete */ if (!reuse) goto out; prog = rcu_dereference(reuse->prog); socks = READ_ONCE(reuse->num_socks); if (likely(socks)) { /* paired with smp_wmb() in __reuseport_add_sock() */ smp_rmb(); if (!prog || !skb) goto select_by_hash; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, NULL, hash); else sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len); select_by_hash: /* no bpf or invalid bpf result: fall back to hash usage */ if (!sk2) sk2 = reuseport_select_sock_by_hash(reuse, hash, socks); } out: rcu_read_unlock(); return sk2; } EXPORT_SYMBOL(reuseport_select_sock); /** * reuseport_migrate_sock - Select a socket from an SO_REUSEPORT group. * @sk: close()ed or shutdown()ed socket in the group. * @migrating_sk: ESTABLISHED/SYN_RECV full socket in the accept queue or * NEW_SYN_RECV request socket during 3WHS. * @skb: skb to run through BPF filter. * Returns a socket (with sk_refcnt +1) that should accept the child socket * (or NULL on error). */ struct sock *reuseport_migrate_sock(struct sock *sk, struct sock *migrating_sk, struct sk_buff *skb) { struct sock_reuseport *reuse; struct sock *nsk = NULL; bool allocated = false; struct bpf_prog *prog; u16 socks; u32 hash; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); if (!reuse) goto out; socks = READ_ONCE(reuse->num_socks); if (unlikely(!socks)) goto failure; /* paired with smp_wmb() in __reuseport_add_sock() */ smp_rmb(); hash = migrating_sk->sk_hash; prog = rcu_dereference(reuse->prog); if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) { if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req)) goto select_by_hash; goto failure; } if (!skb) { skb = alloc_skb(0, GFP_ATOMIC); if (!skb) goto failure; allocated = true; } nsk = bpf_run_sk_reuseport(reuse, sk, prog, skb, migrating_sk, hash); if (allocated) kfree_skb(skb); select_by_hash: if (!nsk) nsk = reuseport_select_sock_by_hash(reuse, hash, socks); if (IS_ERR_OR_NULL(nsk) || unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt))) { nsk = NULL; goto failure; } out: rcu_read_unlock(); return nsk; failure: __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); goto out; } EXPORT_SYMBOL(reuseport_migrate_sock); int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; if (sk_unhashed(sk)) { int err; if (!sk->sk_reuseport) return -EINVAL; err = reuseport_alloc(sk, false); if (err) return err; } else if (!rcu_access_pointer(sk->sk_reuseport_cb)) { /* The socket wasn't bound with SO_REUSEPORT */ return -EINVAL; } spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); old_prog = rcu_dereference_protected(reuse->prog, lockdep_is_held(&reuseport_lock)); rcu_assign_pointer(reuse->prog, prog); spin_unlock_bh(&reuseport_lock); sk_reuseport_prog_free(old_prog); return 0; } EXPORT_SYMBOL(reuseport_attach_prog); int reuseport_detach_prog(struct sock *sk) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; old_prog = NULL; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); /* reuse must be checked after acquiring the reuseport_lock * because reuseport_grow() can detach a closed sk. */ if (!reuse) { spin_unlock_bh(&reuseport_lock); return sk->sk_reuseport ? -ENOENT : -EINVAL; } if (sk_unhashed(sk) && reuse->num_closed_socks) { spin_unlock_bh(&reuseport_lock); return -ENOENT; } old_prog = rcu_replace_pointer(reuse->prog, old_prog, lockdep_is_held(&reuseport_lock)); spin_unlock_bh(&reuseport_lock); if (!old_prog) return -ENOENT; sk_reuseport_prog_free(old_prog); return 0; } EXPORT_SYMBOL(reuseport_detach_prog); |
| 2208 29 1582 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_PGALLOC_H #define __ASM_GENERIC_PGALLOC_H #ifdef CONFIG_MMU #define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO) #define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT) /** * __pte_alloc_one_kernel - allocate a page for PTE-level kernel page table * @mm: the mm_struct of the current context * * This function is intended for architectures that need * anything beyond simple page allocation. * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm) { return (pte_t *)__get_free_page(GFP_PGTABLE_KERNEL); } #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL /** * pte_alloc_one_kernel - allocate a page for PTE-level kernel page table * @mm: the mm_struct of the current context * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) { return __pte_alloc_one_kernel(mm); } #endif /** * pte_free_kernel - free PTE-level kernel page table page * @mm: the mm_struct of the current context * @pte: pointer to the memory containing the page table */ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { free_page((unsigned long)pte); } /** * __pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * @gfp: GFP flags to use for the allocation * * Allocates a page and runs the pgtable_pte_page_ctor(). * * This function is intended for architectures that need * anything beyond simple page allocation or must have custom GFP flags. * * Return: `struct page` initialized as page table or %NULL on error */ static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp) { struct page *pte; pte = alloc_page(gfp); if (!pte) return NULL; if (!pgtable_pte_page_ctor(pte)) { __free_page(pte); return NULL; } return pte; } #ifndef __HAVE_ARCH_PTE_ALLOC_ONE /** * pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * * Allocates a page and runs the pgtable_pte_page_ctor(). * * Return: `struct page` initialized as page table or %NULL on error */ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { return __pte_alloc_one(mm, GFP_PGTABLE_USER); } #endif /* * Should really implement gc for free page table pages. This could be * done with a reference count in struct page. */ /** * pte_free - free PTE-level user page table page * @mm: the mm_struct of the current context * @pte_page: the `struct page` representing the page table */ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) { pgtable_pte_page_dtor(pte_page); __free_page(pte_page); } #if CONFIG_PGTABLE_LEVELS > 2 #ifndef __HAVE_ARCH_PMD_ALLOC_ONE /** * pmd_alloc_one - allocate a page for PMD-level page table * @mm: the mm_struct of the current context * * Allocates a page and runs the pgtable_pmd_page_ctor(). * Allocations use %GFP_PGTABLE_USER in user context and * %GFP_PGTABLE_KERNEL in kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { struct page *page; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; page = alloc_pages(gfp, 0); if (!page) return NULL; if (!pgtable_pmd_page_ctor(page)) { __free_pages(page, 0); return NULL; } return (pmd_t *)page_address(page); } #endif #ifndef __HAVE_ARCH_PMD_FREE static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); pgtable_pmd_page_dtor(virt_to_page(pmd)); free_page((unsigned long)pmd); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 #ifndef __HAVE_ARCH_PUD_ALLOC_ONE /** * pud_alloc_one - allocate a page for PUD-level page table * @mm: the mm_struct of the current context * * Allocates a page using %GFP_PGTABLE_USER for user context and * %GFP_PGTABLE_KERNEL for kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; return (pud_t *)get_zeroed_page(gfp); } #endif static inline void pud_free(struct mm_struct *mm, pud_t *pud) { BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); free_page((unsigned long)pud); } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #ifndef __HAVE_ARCH_PGD_FREE static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { free_page((unsigned long)pgd); } #endif #endif /* CONFIG_MMU */ #endif /* __ASM_GENERIC_PGALLOC_H */ |
| 296 13 4 750 750 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Internal procfs definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/proc_fs.h> #include <linux/proc_ns.h> #include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/binfmts.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> struct ctl_table_header; struct mempolicy; /* * This is not completely implemented yet. The idea is to * create an in-memory tree (like the actual /proc filesystem * tree) of these proc_dir_entries, so that we can dynamically * add new files to /proc. * * parent/subdir are used for the directory structure (every /proc file has a * parent, but "subdir" is empty for all non-directory entries). * subdir_node is used to build the rb tree "subdir" of the parent. */ struct proc_dir_entry { /* * number of callers into module in progress; * negative -> it's going away RSN */ atomic_t in_use; refcount_t refcnt; struct list_head pde_openers; /* who did ->open, but not ->release */ /* protects ->pde_openers and all struct pde_opener instances */ spinlock_t pde_unload_lock; struct completion *pde_unload_completion; const struct inode_operations *proc_iops; union { const struct proc_ops *proc_ops; const struct file_operations *proc_dir_ops; }; const struct dentry_operations *proc_dops; union { const struct seq_operations *seq_ops; int (*single_show)(struct seq_file *, void *); }; proc_write_t write; void *data; unsigned int state_size; unsigned int low_ino; nlink_t nlink; kuid_t uid; kgid_t gid; loff_t size; struct proc_dir_entry *parent; struct rb_root subdir; struct rb_node subdir_node; char *name; umode_t mode; u8 flags; u8 namelen; char inline_name[]; } __randomize_layout; #define SIZEOF_PDE ( \ sizeof(struct proc_dir_entry) < 128 ? 128 : \ sizeof(struct proc_dir_entry) < 192 ? 192 : \ sizeof(struct proc_dir_entry) < 256 ? 256 : \ sizeof(struct proc_dir_entry) < 512 ? 512 : \ 0) #define SIZEOF_PDE_INLINE_NAME (SIZEOF_PDE - sizeof(struct proc_dir_entry)) static inline bool pde_is_permanent(const struct proc_dir_entry *pde) { return pde->flags & PROC_ENTRY_PERMANENT; } static inline bool pde_has_proc_read_iter(const struct proc_dir_entry *pde) { return pde->flags & PROC_ENTRY_proc_read_iter; } static inline bool pde_has_proc_compat_ioctl(const struct proc_dir_entry *pde) { #ifdef CONFIG_COMPAT return pde->flags & PROC_ENTRY_proc_compat_ioctl; #else return false; #endif } extern struct kmem_cache *proc_dir_entry_cache; void pde_free(struct proc_dir_entry *pde); union proc_op { int (*proc_get_link)(struct dentry *, struct path *); int (*proc_show)(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task); const char *lsm; }; struct proc_inode { struct pid *pid; unsigned int fd; union proc_op op; struct proc_dir_entry *pde; struct ctl_table_header *sysctl; struct ctl_table *sysctl_entry; struct hlist_node sibling_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; } __randomize_layout; /* * General functions */ static inline struct proc_inode *PROC_I(const struct inode *inode) { return container_of(inode, struct proc_inode, vfs_inode); } static inline struct proc_dir_entry *PDE(const struct inode *inode) { return PROC_I(inode)->pde; } static inline void *__PDE_DATA(const struct inode *inode) { return PDE(inode)->data; } static inline struct pid *proc_pid(const struct inode *inode) { return PROC_I(inode)->pid; } static inline struct task_struct *get_proc_task(const struct inode *inode) { return get_pid_task(proc_pid(inode), PIDTYPE_PID); } void task_dump_owner(struct task_struct *task, umode_t mode, kuid_t *ruid, kgid_t *rgid); unsigned name_to_int(const struct qstr *qstr); /* * Offset of the first process in the /proc root directory.. */ #define FIRST_PROCESS_ENTRY 256 /* Worst case buffer size needed for holding an integer. */ #define PROC_NUMBUF 13 /* * array.c */ extern const struct file_operations proc_tid_children_operations; extern void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape); extern int proc_tid_stat(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); extern int proc_tgid_stat(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); extern int proc_pid_status(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); extern int proc_pid_statm(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); /* * base.c */ extern const struct dentry_operations pid_dentry_operations; extern int pid_getattr(struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int); extern int proc_setattr(struct user_namespace *, struct dentry *, struct iattr *); extern void proc_pid_evict_inode(struct proc_inode *); extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t); extern void pid_update_inode(struct task_struct *, struct inode *); extern int pid_delete_dentry(const struct dentry *); extern int proc_pid_readdir(struct file *, struct dir_context *); struct dentry *proc_pid_lookup(struct dentry *, unsigned int); extern loff_t mem_lseek(struct file *, loff_t, int); /* Lookups */ typedef struct dentry *instantiate_t(struct dentry *, struct task_struct *, const void *); bool proc_fill_cache(struct file *, struct dir_context *, const char *, unsigned int, instantiate_t, struct task_struct *, const void *); /* * generic.c */ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode, struct proc_dir_entry **parent, void *data); struct proc_dir_entry *proc_register(struct proc_dir_entry *dir, struct proc_dir_entry *dp); extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int); struct dentry *proc_lookup_de(struct inode *, struct dentry *, struct proc_dir_entry *); extern int proc_readdir(struct file *, struct dir_context *); int proc_readdir_de(struct file *, struct dir_context *, struct proc_dir_entry *); static inline void pde_get(struct proc_dir_entry *pde) { refcount_inc(&pde->refcnt); } extern void pde_put(struct proc_dir_entry *); static inline bool is_empty_pde(const struct proc_dir_entry *pde) { return S_ISDIR(pde->mode) && !pde->proc_iops; } extern ssize_t proc_simple_write(struct file *, const char __user *, size_t, loff_t *); /* * inode.c */ struct pde_opener { struct list_head lh; struct file *file; bool closing; struct completion *c; } __randomize_layout; extern const struct inode_operations proc_link_inode_operations; extern const struct inode_operations proc_pid_link_inode_operations; extern const struct super_operations proc_sops; void proc_init_kmemcache(void); void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock); void set_proc_pid_nlink(void); extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *); extern void proc_entry_rundown(struct proc_dir_entry *); /* * proc_namespaces.c */ extern const struct inode_operations proc_ns_dir_inode_operations; extern const struct file_operations proc_ns_dir_operations; /* * proc_net.c */ extern const struct file_operations proc_net_operations; extern const struct inode_operations proc_net_inode_operations; #ifdef CONFIG_NET extern int proc_net_init(void); #else static inline int proc_net_init(void) { return 0; } #endif /* * proc_self.c */ extern int proc_setup_self(struct super_block *); /* * proc_thread_self.c */ extern int proc_setup_thread_self(struct super_block *); extern void proc_thread_self_init(void); /* * proc_sysctl.c */ #ifdef CONFIG_PROC_SYSCTL extern int proc_sys_init(void); extern void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head); #else static inline void proc_sys_init(void) { } static inline void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head) { } #endif /* * proc_tty.c */ #ifdef CONFIG_TTY extern void proc_tty_init(void); #else static inline void proc_tty_init(void) {} #endif /* * root.c */ extern struct proc_dir_entry proc_root; extern void proc_self_init(void); /* * task_[no]mmu.c */ struct mem_size_stats; struct proc_maps_private { struct inode *inode; struct task_struct *task; struct mm_struct *mm; #ifdef CONFIG_MMU struct vm_area_struct *tail_vma; #endif #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; #endif } __randomize_layout; struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode); extern const struct file_operations proc_pid_maps_operations; extern const struct file_operations proc_pid_numa_maps_operations; extern const struct file_operations proc_pid_smaps_operations; extern const struct file_operations proc_pid_smaps_rollup_operations; extern const struct file_operations proc_clear_refs_operations; extern const struct file_operations proc_pagemap_operations; extern unsigned long task_vsize(struct mm_struct *); extern unsigned long task_statm(struct mm_struct *, unsigned long *, unsigned long *, unsigned long *, unsigned long *); extern void task_mem(struct seq_file *, struct mm_struct *); extern const struct dentry_operations proc_net_dentry_ops; static inline void pde_force_lookup(struct proc_dir_entry *pde) { /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */ pde->proc_dops = &proc_net_dentry_ops; } |
| 5579 5208 1145 4571 5204 5203 5197 947 947 947 881 68 947 279 281 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra * * Provides a framework for enqueueing and running callbacks from hardirq * context. The enqueueing is NMI-safe. */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/irq_work.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/tick.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/smp.h> #include <asm/processor.h> #include <linux/kasan.h> static DEFINE_PER_CPU(struct llist_head, raised_list); static DEFINE_PER_CPU(struct llist_head, lazy_list); /* * Claim the entry so that no one else will poke at it. */ static bool irq_work_claim(struct irq_work *work) { int oflags; oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->node.a_flags); /* * If the work is already pending, no need to raise the IPI. * The pairing smp_mb() in irq_work_single() makes sure * everything we did before is visible. */ if (oflags & IRQ_WORK_PENDING) return false; return true; } void __weak arch_irq_work_raise(void) { /* * Lame architectures will get the timer tick callback */ } /* Enqueue on current CPU, work must already be claimed and preempt disabled */ static void __irq_work_queue_local(struct irq_work *work) { /* If the work is "lazy", handle it from next tick if any */ if (atomic_read(&work->node.a_flags) & IRQ_WORK_LAZY) { if (llist_add(&work->node.llist, this_cpu_ptr(&lazy_list)) && tick_nohz_tick_stopped()) arch_irq_work_raise(); } else { if (llist_add(&work->node.llist, this_cpu_ptr(&raised_list))) arch_irq_work_raise(); } } /* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) { /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; /* Queue the entry and raise the IPI if needed. */ preempt_disable(); __irq_work_queue_local(work); preempt_enable(); return true; } EXPORT_SYMBOL_GPL(irq_work_queue); /* * Enqueue the irq_work @work on @cpu unless it's already pending * somewhere. * * Can be re-enqueued while the callback is still in progress. */ bool irq_work_queue_on(struct irq_work *work, int cpu) { #ifndef CONFIG_SMP return irq_work_queue(work); #else /* CONFIG_SMP: */ /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(cpu)); /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; kasan_record_aux_stack_noalloc(work); preempt_disable(); if (cpu != smp_processor_id()) { /* Arch remote IPI send/receive backend aren't NMI safe */ WARN_ON_ONCE(in_nmi()); __smp_call_single_queue(cpu, &work->node.llist); } else { __irq_work_queue_local(work); } preempt_enable(); return true; #endif /* CONFIG_SMP */ } EXPORT_SYMBOL_GPL(irq_work_queue_on); bool irq_work_needs_cpu(void) { struct llist_head *raised, *lazy; raised = this_cpu_ptr(&raised_list); lazy = this_cpu_ptr(&lazy_list); if (llist_empty(raised) || arch_irq_work_has_interrupt()) if (llist_empty(lazy)) return false; /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); return true; } void irq_work_single(void *arg) { struct irq_work *work = arg; int flags; /* * Clear the PENDING bit, after this point the @work can be re-used. * The PENDING bit acts as a lock, and we own it, so we can clear it * without atomic ops. */ flags = atomic_read(&work->node.a_flags); flags &= ~IRQ_WORK_PENDING; atomic_set(&work->node.a_flags, flags); /* * See irq_work_claim(). */ smp_mb(); lockdep_irq_work_enter(flags); work->func(work); lockdep_irq_work_exit(flags); /* * Clear the BUSY bit, if set, and return to the free state if no-one * else claimed it meanwhile. */ (void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY); } static void irq_work_run_list(struct llist_head *list) { struct irq_work *work, *tmp; struct llist_node *llnode; BUG_ON(!irqs_disabled()); if (llist_empty(list)) return; llnode = llist_del_all(list); llist_for_each_entry_safe(work, tmp, llnode, node.llist) irq_work_single(work); } /* * hotplug calls this through: * hotplug_cfd() -> flush_smp_call_function_queue() */ void irq_work_run(void) { irq_work_run_list(this_cpu_ptr(&raised_list)); irq_work_run_list(this_cpu_ptr(&lazy_list)); } EXPORT_SYMBOL_GPL(irq_work_run); void irq_work_tick(void) { struct llist_head *raised = this_cpu_ptr(&raised_list); if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) irq_work_run_list(raised); irq_work_run_list(this_cpu_ptr(&lazy_list)); } /* * Synchronize against the irq_work @entry, ensures the entry is not * currently in use. */ void irq_work_sync(struct irq_work *work) { lockdep_assert_irqs_enabled(); while (irq_work_is_busy(work)) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); |
| 795 247 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_FLOW_DISSECTOR_H #define _NET_FLOW_DISSECTOR_H #include <linux/types.h> #include <linux/in6.h> #include <linux/siphash.h> #include <linux/string.h> #include <uapi/linux/if_ether.h> struct bpf_prog; struct net; struct sk_buff; /** * struct flow_dissector_key_control: * @thoff: Transport header offset */ struct flow_dissector_key_control { u16 thoff; u16 addr_type; u32 flags; }; #define FLOW_DIS_IS_FRAGMENT BIT(0) #define FLOW_DIS_FIRST_FRAG BIT(1) #define FLOW_DIS_ENCAPSULATION BIT(2) enum flow_dissect_ret { FLOW_DISSECT_RET_OUT_GOOD, FLOW_DISSECT_RET_OUT_BAD, FLOW_DISSECT_RET_PROTO_AGAIN, FLOW_DISSECT_RET_IPPROTO_AGAIN, FLOW_DISSECT_RET_CONTINUE, }; /** * struct flow_dissector_key_basic: * @n_proto: Network header protocol (eg. IPv4/IPv6) * @ip_proto: Transport header protocol (eg. TCP/UDP) */ struct flow_dissector_key_basic { __be16 n_proto; u8 ip_proto; u8 padding; }; struct flow_dissector_key_tags { u32 flow_label; }; struct flow_dissector_key_vlan { union { struct { u16 vlan_id:12, vlan_dei:1, vlan_priority:3; }; __be16 vlan_tci; }; __be16 vlan_tpid; __be16 vlan_eth_type; u16 padding; }; struct flow_dissector_mpls_lse { u32 mpls_ttl:8, mpls_bos:1, mpls_tc:3, mpls_label:20; }; #define FLOW_DIS_MPLS_MAX 7 struct flow_dissector_key_mpls { struct flow_dissector_mpls_lse ls[FLOW_DIS_MPLS_MAX]; /* Label Stack */ u8 used_lses; /* One bit set for each Label Stack Entry in use */ }; static inline void dissector_set_mpls_lse(struct flow_dissector_key_mpls *mpls, int lse_index) { mpls->used_lses |= 1 << lse_index; } #define FLOW_DIS_TUN_OPTS_MAX 255 /** * struct flow_dissector_key_enc_opts: * @data: tunnel option data * @len: length of tunnel option data * @dst_opt_type: tunnel option type */ struct flow_dissector_key_enc_opts { u8 data[FLOW_DIS_TUN_OPTS_MAX]; /* Using IP_TUNNEL_OPTS_MAX is desired * here but seems difficult to #include */ u8 len; __be16 dst_opt_type; }; struct flow_dissector_key_keyid { __be32 keyid; }; /** * struct flow_dissector_key_ipv4_addrs: * @src: source ip address * @dst: destination ip address */ struct flow_dissector_key_ipv4_addrs { /* (src,dst) must be grouped, in the same way than in IP header */ __be32 src; __be32 dst; }; /** * struct flow_dissector_key_ipv6_addrs: * @src: source ip address * @dst: destination ip address */ struct flow_dissector_key_ipv6_addrs { /* (src,dst) must be grouped, in the same way than in IP header */ struct in6_addr src; struct in6_addr dst; }; /** * struct flow_dissector_key_tipc: * @key: source node address combined with selector */ struct flow_dissector_key_tipc { __be32 key; }; /** * struct flow_dissector_key_addrs: * @v4addrs: IPv4 addresses * @v6addrs: IPv6 addresses */ struct flow_dissector_key_addrs { union { struct flow_dissector_key_ipv4_addrs v4addrs; struct flow_dissector_key_ipv6_addrs v6addrs; struct flow_dissector_key_tipc tipckey; }; }; /** * flow_dissector_key_arp: * @ports: Operation, source and target addresses for an ARP header * for Ethernet hardware addresses and IPv4 protocol addresses * sip: Sender IP address * tip: Target IP address * op: Operation * sha: Sender hardware address * tpa: Target hardware address */ struct flow_dissector_key_arp { __u32 sip; __u32 tip; __u8 op; unsigned char sha[ETH_ALEN]; unsigned char tha[ETH_ALEN]; }; /** * flow_dissector_key_tp_ports: * @ports: port numbers of Transport header * src: source port number * dst: destination port number */ struct flow_dissector_key_ports { union { __be32 ports; struct { __be16 src; __be16 dst; }; }; }; /** * struct flow_dissector_key_ports_range * @tp: port number from packet * @tp_min: min port number in range * @tp_max: max port number in range */ struct flow_dissector_key_ports_range { union { struct flow_dissector_key_ports tp; struct { struct flow_dissector_key_ports tp_min; struct flow_dissector_key_ports tp_max; }; }; }; /** * flow_dissector_key_icmp: * type: ICMP type * code: ICMP code * id: session identifier */ struct flow_dissector_key_icmp { struct { u8 type; u8 code; }; u16 id; }; /** * struct flow_dissector_key_eth_addrs: * @src: source Ethernet address * @dst: destination Ethernet address */ struct flow_dissector_key_eth_addrs { /* (dst,src) must be grouped, in the same way than in ETH header */ unsigned char dst[ETH_ALEN]; unsigned char src[ETH_ALEN]; }; /** * struct flow_dissector_key_tcp: * @flags: flags */ struct flow_dissector_key_tcp { __be16 flags; }; /** * struct flow_dissector_key_ip: * @tos: tos * @ttl: ttl */ struct flow_dissector_key_ip { __u8 tos; __u8 ttl; }; /** * struct flow_dissector_key_meta: * @ingress_ifindex: ingress ifindex * @ingress_iftype: ingress interface type */ struct flow_dissector_key_meta { int ingress_ifindex; u16 ingress_iftype; }; /** * struct flow_dissector_key_ct: * @ct_state: conntrack state after converting with map * @ct_mark: conttrack mark * @ct_zone: conntrack zone * @ct_labels: conntrack labels */ struct flow_dissector_key_ct { u16 ct_state; u16 ct_zone; u32 ct_mark; u32 ct_labels[4]; }; /** * struct flow_dissector_key_hash: * @hash: hash value */ struct flow_dissector_key_hash { u32 hash; }; enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */ FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */ FLOW_DISSECTOR_KEY_PORTS, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_PORTS_RANGE, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_ICMP, /* struct flow_dissector_key_icmp */ FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */ FLOW_DISSECTOR_KEY_TIPC, /* struct flow_dissector_key_tipc */ FLOW_DISSECTOR_KEY_ARP, /* struct flow_dissector_key_arp */ FLOW_DISSECTOR_KEY_VLAN, /* struct flow_dissector_key_vlan */ FLOW_DISSECTOR_KEY_FLOW_LABEL, /* struct flow_dissector_key_tags */ FLOW_DISSECTOR_KEY_GRE_KEYID, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_MPLS_ENTROPY, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_ENC_KEYID, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */ FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */ FLOW_DISSECTOR_KEY_ENC_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_ENC_PORTS, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */ FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */ FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_vlan */ FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */ FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */ FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */ FLOW_DISSECTOR_KEY_HASH, /* struct flow_dissector_key_hash */ FLOW_DISSECTOR_KEY_MAX, }; #define FLOW_DISSECTOR_F_PARSE_1ST_FRAG BIT(0) #define FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL BIT(1) #define FLOW_DISSECTOR_F_STOP_AT_ENCAP BIT(2) struct flow_dissector_key { enum flow_dissector_key_id key_id; size_t offset; /* offset of struct flow_dissector_key_* in target the struct */ }; struct flow_dissector { unsigned int used_keys; /* each bit repesents presence of one key id */ unsigned short int offset[FLOW_DISSECTOR_KEY_MAX]; }; struct flow_keys_basic { struct flow_dissector_key_control control; struct flow_dissector_key_basic basic; }; struct flow_keys { struct flow_dissector_key_control control; #define FLOW_KEYS_HASH_START_FIELD basic struct flow_dissector_key_basic basic __aligned(SIPHASH_ALIGNMENT); struct flow_dissector_key_tags tags; struct flow_dissector_key_vlan vlan; struct flow_dissector_key_vlan cvlan; struct flow_dissector_key_keyid keyid; struct flow_dissector_key_ports ports; struct flow_dissector_key_icmp icmp; /* 'addrs' must be the last member */ struct flow_dissector_key_addrs addrs; }; #define FLOW_KEYS_HASH_OFFSET \ offsetof(struct flow_keys, FLOW_KEYS_HASH_START_FIELD) __be32 flow_get_u32_src(const struct flow_keys *flow); __be32 flow_get_u32_dst(const struct flow_keys *flow); extern struct flow_dissector flow_keys_dissector; extern struct flow_dissector flow_keys_basic_dissector; /* struct flow_keys_digest: * * This structure is used to hold a digest of the full flow keys. This is a * larger "hash" of a flow to allow definitively matching specific flows where * the 32 bit skb->hash is not large enough. The size is limited to 16 bytes so * that it can be used in CB of skb (see sch_choke for an example). */ #define FLOW_KEYS_DIGEST_LEN 16 struct flow_keys_digest { u8 data[FLOW_KEYS_DIGEST_LEN]; }; void make_flow_keys_digest(struct flow_keys_digest *digest, const struct flow_keys *flow); static inline bool flow_keys_have_l4(const struct flow_keys *keys) { return (keys->ports.ports || keys->tags.flow_label); } u32 flow_hash_from_keys(struct flow_keys *keys); 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); static inline bool dissector_uses_key(const struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { return flow_dissector->used_keys & (1 << key_id); } static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id, void *target_container) { return ((char *)target_container) + flow_dissector->offset[key_id]; } struct bpf_flow_dissector { struct bpf_flow_keys *flow_keys; const struct sk_buff *skb; const void *data; const void *data_end; }; static inline void flow_dissector_init_keys(struct flow_dissector_key_control *key_control, struct flow_dissector_key_basic *key_basic) { memset(key_control, 0, sizeof(*key_control)); memset(key_basic, 0, sizeof(*key_basic)); } #ifdef CONFIG_BPF_SYSCALL int flow_dissector_bpf_prog_attach_check(struct net *net, struct bpf_prog *prog); #endif /* CONFIG_BPF_SYSCALL */ #endif |
| 902 12642 9275 13 933 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_BITOPS_FIND_H_ #define _ASM_GENERIC_BITOPS_FIND_H_ extern unsigned long _find_next_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start, unsigned long invert, unsigned long le); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); #ifndef find_next_bit /** * find_next_bit - find the next set bit in a memory region * @addr: The address to base the search on * @offset: The bitnumber to start searching at * @size: The bitmap size in bits * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static inline unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_bit(addr, NULL, size, offset, 0UL, 0); } #endif #ifndef find_next_and_bit /** * find_next_and_bit - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @offset: The bitnumber to start searching at * @size: The bitmap size in bits * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static inline unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr1 & *addr2 & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); } #endif #ifndef find_next_zero_bit /** * find_next_zero_bit - find the next cleared bit in a memory region * @addr: The address to base the search on * @offset: The bitnumber to start searching at * @size: The bitmap size in bits * * Returns the bit number of the next zero bit * If no bits are zero, returns @size. */ static inline unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr | ~GENMASK(size - 1, offset); return val == ~0UL ? size : ffz(val); } return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); } #endif #ifdef CONFIG_GENERIC_FIND_FIRST_BIT #ifndef find_first_bit /** * find_first_bit - find the first set bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * * Returns the bit number of the first set bit. * If no bits are set, returns @size. */ static inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_bit(addr, size); } #endif #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * * Returns the bit number of the first cleared bit. * If no bits are zero, returns @size. */ static inline unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr | ~GENMASK(size - 1, 0); return val == ~0UL ? size : ffz(val); } return _find_first_zero_bit(addr, size); } #endif #else /* CONFIG_GENERIC_FIND_FIRST_BIT */ #ifndef find_first_bit #define find_first_bit(addr, size) find_next_bit((addr), (size), 0) #endif #ifndef find_first_zero_bit #define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0) #endif #endif /* CONFIG_GENERIC_FIND_FIRST_BIT */ #ifndef find_last_bit /** * find_last_bit - find the last set bit in a memory region * @addr: The address to start the search at * @size: The number of bits to search * * Returns the bit number of the last set bit, or size. */ static inline unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? __fls(val) : size; } return _find_last_bit(addr, size); } #endif /** * find_next_clump8 - find next 8-bit clump with set bits in a memory region * @clump: location to store copy of found clump * @addr: address to base the search on * @size: bitmap size in number of bits * @offset: bit offset at which to start searching * * Returns the bit offset for the next set clump; the found clump value is * copied to the location pointed by @clump. If no bits are set, returns @size. */ extern unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, unsigned long size, unsigned long offset); #define find_first_clump8(clump, bits, size) \ find_next_clump8((clump), (bits), (size), 0) #endif /*_ASM_GENERIC_BITOPS_FIND_H_ */ |
| 40 40 1 2 1 1 32 32 32 36 36 36 1 35 3 1 1 1 1 5 1 1 1 2 1 3 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2018 Facebook */ #include <linux/bpf.h> #include <linux/err.h> #include <linux/sock_diag.h> #include <net/sock_reuseport.h> struct reuseport_array { struct bpf_map map; struct sock __rcu *ptrs[]; }; static struct reuseport_array *reuseport_array(struct bpf_map *map) { return (struct reuseport_array *)map; } /* The caller must hold the reuseport_lock */ void bpf_sk_reuseport_detach(struct sock *sk) { uintptr_t sk_user_data; write_lock_bh(&sk->sk_callback_lock); sk_user_data = (uintptr_t)sk->sk_user_data; if (sk_user_data & SK_USER_DATA_BPF) { struct sock __rcu **socks; socks = (void *)(sk_user_data & SK_USER_DATA_PTRMASK); WRITE_ONCE(sk->sk_user_data, NULL); /* * Do not move this NULL assignment outside of * sk->sk_callback_lock because there is * a race with reuseport_array_free() * which does not hold the reuseport_lock. */ RCU_INIT_POINTER(*socks, NULL); } write_unlock_bh(&sk->sk_callback_lock); } static int reuseport_array_alloc_check(union bpf_attr *attr) { if (attr->value_size != sizeof(u32) && attr->value_size != sizeof(u64)) return -EINVAL; return array_map_alloc_check(attr); } static void *reuseport_array_lookup_elem(struct bpf_map *map, void *key) { struct reuseport_array *array = reuseport_array(map); u32 index = *(u32 *)key; if (unlikely(index >= array->map.max_entries)) return NULL; return rcu_dereference(array->ptrs[index]); } /* Called from syscall only */ static int reuseport_array_delete_elem(struct bpf_map *map, void *key) { struct reuseport_array *array = reuseport_array(map); u32 index = *(u32 *)key; struct sock *sk; int err; if (index >= map->max_entries) return -E2BIG; if (!rcu_access_pointer(array->ptrs[index])) return -ENOENT; spin_lock_bh(&reuseport_lock); sk = rcu_dereference_protected(array->ptrs[index], lockdep_is_held(&reuseport_lock)); if (sk) { write_lock_bh(&sk->sk_callback_lock); WRITE_ONCE(sk->sk_user_data, NULL); RCU_INIT_POINTER(array->ptrs[index], NULL); write_unlock_bh(&sk->sk_callback_lock); err = 0; } else { err = -ENOENT; } spin_unlock_bh(&reuseport_lock); return err; } static void reuseport_array_free(struct bpf_map *map) { struct reuseport_array *array = reuseport_array(map); struct sock *sk; u32 i; /* * ops->map_*_elem() will not be able to access this * array now. Hence, this function only races with * bpf_sk_reuseport_detach() which was triggered by * close() or disconnect(). * * This function and bpf_sk_reuseport_detach() are * both removing sk from "array". Who removes it * first does not matter. * * The only concern here is bpf_sk_reuseport_detach() * may access "array" which is being freed here. * bpf_sk_reuseport_detach() access this "array" * through sk->sk_user_data _and_ with sk->sk_callback_lock * held which is enough because this "array" is not freed * until all sk->sk_user_data has stopped referencing this "array". * * Hence, due to the above, taking "reuseport_lock" is not * needed here. */ /* * Since reuseport_lock is not taken, sk is accessed under * rcu_read_lock() */ rcu_read_lock(); for (i = 0; i < map->max_entries; i++) { sk = rcu_dereference(array->ptrs[i]); if (sk) { write_lock_bh(&sk->sk_callback_lock); /* * No need for WRITE_ONCE(). At this point, * no one is reading it without taking the * sk->sk_callback_lock. */ sk->sk_user_data = NULL; write_unlock_bh(&sk->sk_callback_lock); RCU_INIT_POINTER(array->ptrs[i], NULL); } } rcu_read_unlock(); /* * Once reaching here, all sk->sk_user_data is not * referenceing this "array". "array" can be freed now. */ bpf_map_area_free(array); } static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); struct reuseport_array *array; u64 array_size; if (!bpf_capable()) return ERR_PTR(-EPERM); array_size = sizeof(*array); array_size += (u64)attr->max_entries * sizeof(struct sock *); /* allocate all map elements and zero-initialize them */ array = bpf_map_area_alloc(array_size, numa_node); if (!array) return ERR_PTR(-ENOMEM); /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); return &array->map; } int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value) { struct sock *sk; int err; if (map->value_size != sizeof(u64)) return -ENOSPC; rcu_read_lock(); sk = reuseport_array_lookup_elem(map, key); if (sk) { *(u64 *)value = __sock_gen_cookie(sk); err = 0; } else { err = -ENOENT; } rcu_read_unlock(); return err; } static int reuseport_array_update_check(const struct reuseport_array *array, const struct sock *nsk, const struct sock *osk, const struct sock_reuseport *nsk_reuse, u32 map_flags) { if (osk && map_flags == BPF_NOEXIST) return -EEXIST; if (!osk && map_flags == BPF_EXIST) return -ENOENT; if (nsk->sk_protocol != IPPROTO_UDP && nsk->sk_protocol != IPPROTO_TCP) return -ENOTSUPP; if (nsk->sk_family != AF_INET && nsk->sk_family != AF_INET6) return -ENOTSUPP; if (nsk->sk_type != SOCK_STREAM && nsk->sk_type != SOCK_DGRAM) return -ENOTSUPP; /* * sk must be hashed (i.e. listening in the TCP case or binded * in the UDP case) and * it must also be a SO_REUSEPORT sk (i.e. reuse cannot be NULL). * * Also, sk will be used in bpf helper that is protected by * rcu_read_lock(). */ if (!sock_flag(nsk, SOCK_RCU_FREE) || !sk_hashed(nsk) || !nsk_reuse) return -EINVAL; /* READ_ONCE because the sk->sk_callback_lock may not be held here */ if (READ_ONCE(nsk->sk_user_data)) return -EBUSY; return 0; } /* * Called from syscall only. * The "nsk" in the fd refcnt. * The "osk" and "reuse" are protected by reuseport_lock. */ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct reuseport_array *array = reuseport_array(map); struct sock *free_osk = NULL, *osk, *nsk; struct sock_reuseport *reuse; u32 index = *(u32 *)key; uintptr_t sk_user_data; struct socket *socket; int err, fd; if (map_flags > BPF_EXIST) return -EINVAL; if (index >= map->max_entries) return -E2BIG; if (map->value_size == sizeof(u64)) { u64 fd64 = *(u64 *)value; if (fd64 > S32_MAX) return -EINVAL; fd = fd64; } else { fd = *(int *)value; } socket = sockfd_lookup(fd, &err); if (!socket) return err; nsk = socket->sk; if (!nsk) { err = -EINVAL; goto put_file; } /* Quick checks before taking reuseport_lock */ err = reuseport_array_update_check(array, nsk, rcu_access_pointer(array->ptrs[index]), rcu_access_pointer(nsk->sk_reuseport_cb), map_flags); if (err) goto put_file; spin_lock_bh(&reuseport_lock); /* * Some of the checks only need reuseport_lock * but it is done under sk_callback_lock also * for simplicity reason. */ write_lock_bh(&nsk->sk_callback_lock); osk = rcu_dereference_protected(array->ptrs[index], lockdep_is_held(&reuseport_lock)); reuse = rcu_dereference_protected(nsk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); err = reuseport_array_update_check(array, nsk, osk, reuse, map_flags); if (err) goto put_file_unlock; sk_user_data = (uintptr_t)&array->ptrs[index] | SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF; WRITE_ONCE(nsk->sk_user_data, (void *)sk_user_data); rcu_assign_pointer(array->ptrs[index], nsk); free_osk = osk; err = 0; put_file_unlock: write_unlock_bh(&nsk->sk_callback_lock); if (free_osk) { write_lock_bh(&free_osk->sk_callback_lock); WRITE_ONCE(free_osk->sk_user_data, NULL); write_unlock_bh(&free_osk->sk_callback_lock); } spin_unlock_bh(&reuseport_lock); put_file: fput(socket->file); return err; } /* Called from syscall */ static int reuseport_array_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct reuseport_array *array = reuseport_array(map); u32 index = key ? *(u32 *)key : U32_MAX; u32 *next = (u32 *)next_key; if (index >= array->map.max_entries) { *next = 0; return 0; } if (index == array->map.max_entries - 1) return -ENOENT; *next = index + 1; return 0; } static int reuseport_array_map_btf_id; const struct bpf_map_ops reuseport_array_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = reuseport_array_alloc_check, .map_alloc = reuseport_array_alloc, .map_free = reuseport_array_free, .map_lookup_elem = reuseport_array_lookup_elem, .map_get_next_key = reuseport_array_get_next_key, .map_delete_elem = reuseport_array_delete_elem, .map_btf_name = "reuseport_array", .map_btf_id = &reuseport_array_map_btf_id, }; |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_64_H #define _ASM_X86_PGTABLE_64_H #include <linux/const.h> #include <asm/pgtable_64_types.h> #ifndef __ASSEMBLY__ /* * This file contains the functions and defines necessary to modify and use * the x86-64 page table tree. */ #include <asm/processor.h> #include <linux/bitops.h> #include <linux/threads.h> #include <asm/fixmap.h> extern p4d_t level4_kernel_pgt[512]; extern p4d_t level4_ident_pgt[512]; extern pud_t level3_kernel_pgt[512]; extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM]; extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt extern void paging_init(void); static inline void sync_initial_page_table(void) { } #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pte_val(e)) #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pmd_val(e)) #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pud_val(e)) #if CONFIG_PGTABLE_LEVELS >= 5 #define p4d_ERROR(e) \ pr_err("%s:%d: bad p4d %p(%016lx)\n", \ __FILE__, __LINE__, &(e), p4d_val(e)) #endif #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pgd_val(e)) struct mm_struct; #define mm_p4d_folded mm_p4d_folded static inline bool mm_p4d_folded(struct mm_struct *mm) { return !pgtable_l5_enabled(); } void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); static inline void native_set_pte(pte_t *ptep, pte_t pte) { WRITE_ONCE(*ptep, pte); } static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { native_set_pte(ptep, native_make_pte(0)); } static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) { native_set_pte(ptep, pte); } static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { WRITE_ONCE(*pmdp, pmd); } static inline void native_pmd_clear(pmd_t *pmd) { native_set_pmd(pmd, native_make_pmd(0)); } static inline pte_t native_ptep_get_and_clear(pte_t *xp) { #ifdef CONFIG_SMP return native_make_pte(xchg(&xp->pte, 0)); #else /* native_local_ptep_get_and_clear, but duplicated because of cyclic dependency */ pte_t ret = *xp; native_pte_clear(NULL, 0, xp); return ret; #endif } static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) { #ifdef CONFIG_SMP return native_make_pmd(xchg(&xp->pmd, 0)); #else /* native_local_pmdp_get_and_clear, but duplicated because of cyclic dependency */ pmd_t ret = *xp; native_pmd_clear(xp); return ret; #endif } static inline void native_set_pud(pud_t *pudp, pud_t pud) { WRITE_ONCE(*pudp, pud); } static inline void native_pud_clear(pud_t *pud) { native_set_pud(pud, native_make_pud(0)); } static inline pud_t native_pudp_get_and_clear(pud_t *xp) { #ifdef CONFIG_SMP return native_make_pud(xchg(&xp->pud, 0)); #else /* native_local_pudp_get_and_clear, * but duplicated because of cyclic dependency */ pud_t ret = *xp; native_pud_clear(xp); return ret; #endif } static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { pgd_t pgd; if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) { WRITE_ONCE(*p4dp, p4d); return; } pgd = native_make_pgd(native_p4d_val(p4d)); pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd))); } static inline void native_p4d_clear(p4d_t *p4d) { native_set_p4d(p4d, native_make_p4d(0)); } static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd)); } static inline void native_pgd_clear(pgd_t *pgd) { native_set_pgd(pgd, native_make_pgd(0)); } /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. */ /* PGD - Level 4 access */ /* PUD - Level 3 access */ /* PMD - Level 2 access */ /* PTE - Level 1 access */ /* * Encode and de-code a swap entry * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2| 1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| X|F|SD|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above * there. We also need to avoid using A and D because of an * erratum where they can be incorrectly set by hardware on * non-present PTEs. * * SD Bits 1-4 are not used in non-present format and available for * special use described below: * * SD (1) in swp entry is used to store soft dirty bit, which helps us * remember soft dirty over page migration * * F (2) in swp entry is used to record when a pagetable is * writeprotected by userfaultfd WP support. * * Bit 7 in swp entry should be 0 because pmd_present checks not only P, * but also L and G. * * The offset is inverted by a binary not operation to make the high * physical bits set. */ #define SWP_TYPE_BITS 5 #define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) /* We always extract/encode the offset by shifting it all the way up, and then down again */ #define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) /* Extract the high bits for type */ #define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS)) /* Shift up (to get rid of type), then down to get value */ #define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT) /* * Shift the offset up "too far" by TYPE bits, then down again * The offset is inverted by a binary not operation to make the high * physical bits set. */ #define __swp_entry(type, offset) ((swp_entry_t) { \ (~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \ | ((unsigned long)(type) << (64-SWP_TYPE_BITS)) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val((pmd)) }) #define __swp_entry_to_pte(x) (__pte((x).val)) #define __swp_entry_to_pmd(x) (__pmd((x).val)) extern int kern_addr_valid(unsigned long addr); extern void cleanup_highmap(void); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 /* fs/proc/kcore.c */ #define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK) #define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK) #define __HAVE_ARCH_PTE_SAME #define vmemmap ((struct page *)VMEMMAP_START) extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); #define gup_fast_permitted gup_fast_permitted static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { if (end >> __VIRTUAL_MASK_SHIFT) return false; return true; } #include <asm/pgtable-invert.h> #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_64_H */ |
| 120 57 176 58 119 177 62 62 63 63 58 58 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 | // SPDX-License-Identifier: GPL-2.0-or-later /* xfrm6_protocol.c - Generic xfrm protocol multiplexer for ipv6. * * Copyright (C) 2013 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> * * Based on: * net/ipv4/xfrm4_protocol.c */ #include <linux/init.h> #include <linux/mutex.h> #include <linux/skbuff.h> #include <linux/icmpv6.h> #include <net/ip6_route.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/xfrm.h> static struct xfrm6_protocol __rcu *esp6_handlers __read_mostly; static struct xfrm6_protocol __rcu *ah6_handlers __read_mostly; static struct xfrm6_protocol __rcu *ipcomp6_handlers __read_mostly; static DEFINE_MUTEX(xfrm6_protocol_mutex); static inline struct xfrm6_protocol __rcu **proto_handlers(u8 protocol) { switch (protocol) { case IPPROTO_ESP: return &esp6_handlers; case IPPROTO_AH: return &ah6_handlers; case IPPROTO_COMP: return &ipcomp6_handlers; } return NULL; } #define for_each_protocol_rcu(head, handler) \ for (handler = rcu_dereference(head); \ handler != NULL; \ handler = rcu_dereference(handler->next)) \ static int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err) { int ret; struct xfrm6_protocol *handler; struct xfrm6_protocol __rcu **head = proto_handlers(protocol); if (!head) return 0; for_each_protocol_rcu(*proto_handlers(protocol), handler) if ((ret = handler->cb_handler(skb, err)) <= 0) return ret; return 0; } int xfrm6_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { int ret; struct xfrm6_protocol *handler; struct xfrm6_protocol __rcu **head = proto_handlers(nexthdr); XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; XFRM_SPI_SKB_CB(skb)->family = AF_INET6; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); if (!head) goto out; if (!skb_dst(skb)) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); int flags = RT6_LOOKUP_F_HAS_SADDR; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .daddr = ip6h->daddr, .saddr = ip6h->saddr, .flowlabel = ip6_flowinfo(ip6h), .flowi6_mark = skb->mark, .flowi6_proto = ip6h->nexthdr, }; dst = ip6_route_input_lookup(dev_net(skb->dev), skb->dev, &fl6, skb, flags); if (dst->error) goto drop; skb_dst_set(skb, dst); } for_each_protocol_rcu(*head, handler) if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL) return ret; out: icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } EXPORT_SYMBOL(xfrm6_rcv_encap); static int xfrm6_esp_rcv(struct sk_buff *skb) { int ret; struct xfrm6_protocol *handler; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; for_each_protocol_rcu(esp6_handlers, handler) if ((ret = handler->handler(skb)) != -EINVAL) return ret; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb(skb); return 0; } static int xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_protocol *handler; for_each_protocol_rcu(esp6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static int xfrm6_ah_rcv(struct sk_buff *skb) { int ret; struct xfrm6_protocol *handler; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; for_each_protocol_rcu(ah6_handlers, handler) if ((ret = handler->handler(skb)) != -EINVAL) return ret; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb(skb); return 0; } static int xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_protocol *handler; for_each_protocol_rcu(ah6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static int xfrm6_ipcomp_rcv(struct sk_buff *skb) { int ret; struct xfrm6_protocol *handler; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; for_each_protocol_rcu(ipcomp6_handlers, handler) if ((ret = handler->handler(skb)) != -EINVAL) return ret; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb(skb); return 0; } static int xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_protocol *handler; for_each_protocol_rcu(ipcomp6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static const struct inet6_protocol esp6_protocol = { .handler = xfrm6_esp_rcv, .err_handler = xfrm6_esp_err, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol ah6_protocol = { .handler = xfrm6_ah_rcv, .err_handler = xfrm6_ah_err, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol ipcomp6_protocol = { .handler = xfrm6_ipcomp_rcv, .err_handler = xfrm6_ipcomp_err, .flags = INET6_PROTO_NOPOLICY, }; static const struct xfrm_input_afinfo xfrm6_input_afinfo = { .family = AF_INET6, .callback = xfrm6_rcv_cb, }; static inline const struct inet6_protocol *netproto(unsigned char protocol) { switch (protocol) { case IPPROTO_ESP: return &esp6_protocol; case IPPROTO_AH: return &ah6_protocol; case IPPROTO_COMP: return &ipcomp6_protocol; } return NULL; } int xfrm6_protocol_register(struct xfrm6_protocol *handler, unsigned char protocol) { struct xfrm6_protocol __rcu **pprev; struct xfrm6_protocol *t; bool add_netproto = false; int ret = -EEXIST; int priority = handler->priority; if (!proto_handlers(protocol) || !netproto(protocol)) return -EINVAL; mutex_lock(&xfrm6_protocol_mutex); if (!rcu_dereference_protected(*proto_handlers(protocol), lockdep_is_held(&xfrm6_protocol_mutex))) add_netproto = true; for (pprev = proto_handlers(protocol); (t = rcu_dereference_protected(*pprev, lockdep_is_held(&xfrm6_protocol_mutex))) != NULL; pprev = &t->next) { if (t->priority < priority) break; if (t->priority == priority) goto err; } handler->next = *pprev; rcu_assign_pointer(*pprev, handler); ret = 0; err: mutex_unlock(&xfrm6_protocol_mutex); if (add_netproto) { if (inet6_add_protocol(netproto(protocol), protocol)) { pr_err("%s: can't add protocol\n", __func__); ret = -EAGAIN; } } return ret; } EXPORT_SYMBOL(xfrm6_protocol_register); int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, unsigned char protocol) { struct xfrm6_protocol __rcu **pprev; struct xfrm6_protocol *t; int ret = -ENOENT; if (!proto_handlers(protocol) || !netproto(protocol)) return -EINVAL; mutex_lock(&xfrm6_protocol_mutex); for (pprev = proto_handlers(protocol); (t = rcu_dereference_protected(*pprev, lockdep_is_held(&xfrm6_protocol_mutex))) != NULL; pprev = &t->next) { if (t == handler) { *pprev = handler->next; ret = 0; break; } } if (!rcu_dereference_protected(*proto_handlers(protocol), lockdep_is_held(&xfrm6_protocol_mutex))) { if (inet6_del_protocol(netproto(protocol), protocol) < 0) { pr_err("%s: can't remove protocol\n", __func__); ret = -EAGAIN; } } mutex_unlock(&xfrm6_protocol_mutex); synchronize_net(); return ret; } EXPORT_SYMBOL(xfrm6_protocol_deregister); int __init xfrm6_protocol_init(void) { return xfrm_input_register_afinfo(&xfrm6_input_afinfo); } void xfrm6_protocol_fini(void) { xfrm_input_unregister_afinfo(&xfrm6_input_afinfo); } |
| 229 229 229 229 235 2 2 2 229 28 28 28 8 1 2 1 1273 5173 1164 1258 3866 3864 144 2260 2942 4679 1330 866 2407 843 843 1069 1069 2934 1149 1347 1605 4071 1246 1273 953 985 729 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 | #include <linux/bpf.h> #include <linux/btf.h> #include <linux/err.h> #include <linux/irq_work.h> #include <linux/slab.h> #include <linux/filter.h> #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/wait.h> #include <linux/poll.h> #include <linux/kmemleak.h> #include <uapi/linux/btf.h> #define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE) /* non-mmap()'able part of bpf_ringbuf (everything up to consumer page) */ #define RINGBUF_PGOFF \ (offsetof(struct bpf_ringbuf, consumer_pos) >> PAGE_SHIFT) /* consumer page and producer page */ #define RINGBUF_POS_PAGES 2 #define RINGBUF_MAX_RECORD_SZ (UINT_MAX/4) /* Maximum size of ring buffer area is limited by 32-bit page offset within * record header, counted in pages. Reserve 8 bits for extensibility, and take * into account few extra pages for consumer/producer pages and * non-mmap()'able parts. This gives 64GB limit, which seems plenty for single * ring buffer. */ #define RINGBUF_MAX_DATA_SZ \ (((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE) struct bpf_ringbuf { wait_queue_head_t waitq; struct irq_work work; u64 mask; struct page **pages; int nr_pages; spinlock_t spinlock ____cacheline_aligned_in_smp; /* Consumer and producer counters are put into separate pages to allow * mapping consumer page as r/w, but restrict producer page to r/o. * This protects producer position from being modified by user-space * application and ruining in-kernel position tracking. * Note that the pending counter is placed in the same * page as the producer, so that it shares the same cache line. */ unsigned long consumer_pos __aligned(PAGE_SIZE); unsigned long producer_pos __aligned(PAGE_SIZE); unsigned long pending_pos; char data[] __aligned(PAGE_SIZE); }; struct bpf_ringbuf_map { struct bpf_map map; struct bpf_ringbuf *rb; }; /* 8-byte ring buffer record header structure */ struct bpf_ringbuf_hdr { u32 len; u32 pg_off; }; static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) { const gfp_t flags = GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL | __GFP_NOWARN | __GFP_ZERO; int nr_meta_pages = RINGBUF_PGOFF + RINGBUF_POS_PAGES; int nr_data_pages = data_sz >> PAGE_SHIFT; int nr_pages = nr_meta_pages + nr_data_pages; struct page **pages, *page; struct bpf_ringbuf *rb; size_t array_size; int i; /* Each data page is mapped twice to allow "virtual" * continuous read of samples wrapping around the end of ring * buffer area: * ------------------------------------------------------ * | meta pages | real data pages | same data pages | * ------------------------------------------------------ * | | 1 2 3 4 5 6 7 8 9 | 1 2 3 4 5 6 7 8 9 | * ------------------------------------------------------ * | | TA DA | TA DA | * ------------------------------------------------------ * ^^^^^^^ * | * Here, no need to worry about special handling of wrapped-around * data due to double-mapped data pages. This works both in kernel and * when mmap()'ed in user-space, simplifying both kernel and * user-space implementations significantly. */ array_size = (nr_meta_pages + 2 * nr_data_pages) * sizeof(*pages); pages = bpf_map_area_alloc(array_size, numa_node); if (!pages) return NULL; for (i = 0; i < nr_pages; i++) { page = alloc_pages_node(numa_node, flags, 0); if (!page) { nr_pages = i; goto err_free_pages; } pages[i] = page; if (i >= nr_meta_pages) pages[nr_data_pages + i] = page; } rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages, VM_MAP | VM_USERMAP, PAGE_KERNEL); if (rb) { kmemleak_not_leak(pages); rb->pages = pages; rb->nr_pages = nr_pages; return rb; } err_free_pages: for (i = 0; i < nr_pages; i++) __free_page(pages[i]); kvfree(pages); return NULL; } static void bpf_ringbuf_notify(struct irq_work *work) { struct bpf_ringbuf *rb = container_of(work, struct bpf_ringbuf, work); wake_up_all(&rb->waitq); } static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) { struct bpf_ringbuf *rb; rb = bpf_ringbuf_area_alloc(data_sz, numa_node); if (!rb) return NULL; spin_lock_init(&rb->spinlock); init_waitqueue_head(&rb->waitq); init_irq_work(&rb->work, bpf_ringbuf_notify); rb->mask = data_sz - 1; rb->consumer_pos = 0; rb->producer_pos = 0; rb->pending_pos = 0; return rb; } static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) { struct bpf_ringbuf_map *rb_map; if (attr->map_flags & ~RINGBUF_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); if (attr->key_size || attr->value_size || !is_power_of_2(attr->max_entries) || !PAGE_ALIGNED(attr->max_entries)) return ERR_PTR(-EINVAL); #ifdef CONFIG_64BIT /* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */ if (attr->max_entries > RINGBUF_MAX_DATA_SZ) return ERR_PTR(-E2BIG); #endif rb_map = kzalloc(sizeof(*rb_map), GFP_USER | __GFP_ACCOUNT); if (!rb_map) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&rb_map->map, attr); rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node); if (!rb_map->rb) { kfree(rb_map); return ERR_PTR(-ENOMEM); } return &rb_map->map; } static void bpf_ringbuf_free(struct bpf_ringbuf *rb) { /* copy pages pointer and nr_pages to local variable, as we are going * to unmap rb itself with vunmap() below */ struct page **pages = rb->pages; int i, nr_pages = rb->nr_pages; vunmap(rb); for (i = 0; i < nr_pages; i++) __free_page(pages[i]); kvfree(pages); } static void ringbuf_map_free(struct bpf_map *map) { struct bpf_ringbuf_map *rb_map; rb_map = container_of(map, struct bpf_ringbuf_map, map); bpf_ringbuf_free(rb_map->rb); kfree(rb_map); } static void *ringbuf_map_lookup_elem(struct bpf_map *map, void *key) { return ERR_PTR(-ENOTSUPP); } static int ringbuf_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { return -ENOTSUPP; } static int ringbuf_map_delete_elem(struct bpf_map *map, void *key) { return -ENOTSUPP; } static int ringbuf_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -ENOTSUPP; } static int ringbuf_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) { struct bpf_ringbuf_map *rb_map; rb_map = container_of(map, struct bpf_ringbuf_map, map); if (vma->vm_flags & VM_WRITE) { /* allow writable mapping for the consumer_pos only */ if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) return -EPERM; } else { vma->vm_flags &= ~VM_MAYWRITE; } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); } static unsigned long ringbuf_avail_data_sz(struct bpf_ringbuf *rb) { unsigned long cons_pos, prod_pos; cons_pos = smp_load_acquire(&rb->consumer_pos); prod_pos = smp_load_acquire(&rb->producer_pos); return prod_pos - cons_pos; } static __poll_t ringbuf_map_poll(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts) { struct bpf_ringbuf_map *rb_map; rb_map = container_of(map, struct bpf_ringbuf_map, map); poll_wait(filp, &rb_map->rb->waitq, pts); if (ringbuf_avail_data_sz(rb_map->rb)) return EPOLLIN | EPOLLRDNORM; return 0; } static int ringbuf_map_btf_id; const struct bpf_map_ops ringbuf_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = ringbuf_map_alloc, .map_free = ringbuf_map_free, .map_mmap = ringbuf_map_mmap, .map_poll = ringbuf_map_poll, .map_lookup_elem = ringbuf_map_lookup_elem, .map_update_elem = ringbuf_map_update_elem, .map_delete_elem = ringbuf_map_delete_elem, .map_get_next_key = ringbuf_map_get_next_key, .map_btf_name = "bpf_ringbuf_map", .map_btf_id = &ringbuf_map_btf_id, }; /* Given pointer to ring buffer record metadata and struct bpf_ringbuf itself, * calculate offset from record metadata to ring buffer in pages, rounded * down. This page offset is stored as part of record metadata and allows to * restore struct bpf_ringbuf * from record pointer. This page offset is * stored at offset 4 of record metadata header. */ static size_t bpf_ringbuf_rec_pg_off(struct bpf_ringbuf *rb, struct bpf_ringbuf_hdr *hdr) { return ((void *)hdr - (void *)rb) >> PAGE_SHIFT; } /* Given pointer to ring buffer record header, restore pointer to struct * bpf_ringbuf itself by using page offset stored at offset 4 */ static struct bpf_ringbuf * bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr) { unsigned long addr = (unsigned long)(void *)hdr; unsigned long off = (unsigned long)hdr->pg_off << PAGE_SHIFT; return (void*)((addr & PAGE_MASK) - off); } static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) { unsigned long cons_pos, prod_pos, new_prod_pos, pend_pos, flags; struct bpf_ringbuf_hdr *hdr; u32 len, pg_off, tmp_size, hdr_len; if (unlikely(size > RINGBUF_MAX_RECORD_SZ)) return NULL; len = round_up(size + BPF_RINGBUF_HDR_SZ, 8); if (len > rb->mask + 1) return NULL; cons_pos = smp_load_acquire(&rb->consumer_pos); if (in_nmi()) { if (!spin_trylock_irqsave(&rb->spinlock, flags)) return NULL; } else { spin_lock_irqsave(&rb->spinlock, flags); } pend_pos = rb->pending_pos; prod_pos = rb->producer_pos; new_prod_pos = prod_pos + len; while (pend_pos < prod_pos) { hdr = (void *)rb->data + (pend_pos & rb->mask); hdr_len = READ_ONCE(hdr->len); if (hdr_len & BPF_RINGBUF_BUSY_BIT) break; tmp_size = hdr_len & ~BPF_RINGBUF_DISCARD_BIT; tmp_size = round_up(tmp_size + BPF_RINGBUF_HDR_SZ, 8); pend_pos += tmp_size; } rb->pending_pos = pend_pos; /* check for out of ringbuf space: * - by ensuring producer position doesn't advance more than * (ringbuf_size - 1) ahead * - by ensuring oldest not yet committed record until newest * record does not span more than (ringbuf_size - 1) */ if (new_prod_pos - cons_pos > rb->mask || new_prod_pos - pend_pos > rb->mask) { spin_unlock_irqrestore(&rb->spinlock, flags); return NULL; } hdr = (void *)rb->data + (prod_pos & rb->mask); pg_off = bpf_ringbuf_rec_pg_off(rb, hdr); hdr->len = size | BPF_RINGBUF_BUSY_BIT; hdr->pg_off = pg_off; /* pairs with consumer's smp_load_acquire() */ smp_store_release(&rb->producer_pos, new_prod_pos); spin_unlock_irqrestore(&rb->spinlock, flags); return (void *)hdr + BPF_RINGBUF_HDR_SZ; } BPF_CALL_3(bpf_ringbuf_reserve, struct bpf_map *, map, u64, size, u64, flags) { struct bpf_ringbuf_map *rb_map; if (unlikely(flags)) return 0; rb_map = container_of(map, struct bpf_ringbuf_map, map); return (unsigned long)__bpf_ringbuf_reserve(rb_map->rb, size); } const struct bpf_func_proto bpf_ringbuf_reserve_proto = { .func = bpf_ringbuf_reserve, .ret_type = RET_PTR_TO_ALLOC_MEM_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_CONST_ALLOC_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; static void bpf_ringbuf_commit(void *sample, u64 flags, bool discard) { unsigned long rec_pos, cons_pos; struct bpf_ringbuf_hdr *hdr; struct bpf_ringbuf *rb; u32 new_len; hdr = sample - BPF_RINGBUF_HDR_SZ; rb = bpf_ringbuf_restore_from_rec(hdr); new_len = hdr->len ^ BPF_RINGBUF_BUSY_BIT; if (discard) new_len |= BPF_RINGBUF_DISCARD_BIT; /* update record header with correct final size prefix */ xchg(&hdr->len, new_len); /* if consumer caught up and is waiting for our record, notify about * new data availability */ rec_pos = (void *)hdr - (void *)rb->data; cons_pos = smp_load_acquire(&rb->consumer_pos) & rb->mask; if (flags & BPF_RB_FORCE_WAKEUP) irq_work_queue(&rb->work); else if (cons_pos == rec_pos && !(flags & BPF_RB_NO_WAKEUP)) irq_work_queue(&rb->work); } BPF_CALL_2(bpf_ringbuf_submit, void *, sample, u64, flags) { bpf_ringbuf_commit(sample, flags, false /* discard */); return 0; } const struct bpf_func_proto bpf_ringbuf_submit_proto = { .func = bpf_ringbuf_submit, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_ALLOC_MEM, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_ringbuf_discard, void *, sample, u64, flags) { bpf_ringbuf_commit(sample, flags, true /* discard */); return 0; } const struct bpf_func_proto bpf_ringbuf_discard_proto = { .func = bpf_ringbuf_discard, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_ALLOC_MEM, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_ringbuf_output, struct bpf_map *, map, void *, data, u64, size, u64, flags) { struct bpf_ringbuf_map *rb_map; void *rec; if (unlikely(flags & ~(BPF_RB_NO_WAKEUP | BPF_RB_FORCE_WAKEUP))) return -EINVAL; rb_map = container_of(map, struct bpf_ringbuf_map, map); rec = __bpf_ringbuf_reserve(rb_map->rb, size); if (!rec) return -EAGAIN; memcpy(rec, data, size); bpf_ringbuf_commit(rec, flags, false /* discard */); return 0; } const struct bpf_func_proto bpf_ringbuf_output_proto = { .func = bpf_ringbuf_output, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_ringbuf_query, struct bpf_map *, map, u64, flags) { struct bpf_ringbuf *rb; rb = container_of(map, struct bpf_ringbuf_map, map)->rb; switch (flags) { case BPF_RB_AVAIL_DATA: return ringbuf_avail_data_sz(rb); case BPF_RB_RING_SIZE: return rb->mask + 1; case BPF_RB_CONS_POS: return smp_load_acquire(&rb->consumer_pos); case BPF_RB_PROD_POS: return smp_load_acquire(&rb->producer_pos); default: return 0; } } const struct bpf_func_proto bpf_ringbuf_query_proto = { .func = bpf_ringbuf_query, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; |
| 228 202 2 1 23 2 14 12 12 2 10 10 9 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 | // SPDX-License-Identifier: GPL-2.0 #include <linux/perf_event.h> #include <linux/sysfs.h> #include <linux/nospec.h> #include <asm/intel-family.h> #include "probe.h" enum perf_msr_id { PERF_MSR_TSC = 0, PERF_MSR_APERF = 1, PERF_MSR_MPERF = 2, PERF_MSR_PPERF = 3, PERF_MSR_SMI = 4, PERF_MSR_PTSC = 5, PERF_MSR_IRPERF = 6, PERF_MSR_THERM = 7, PERF_MSR_EVENT_MAX, }; static bool test_aperfmperf(int idx, void *data) { return boot_cpu_has(X86_FEATURE_APERFMPERF); } static bool test_ptsc(int idx, void *data) { return boot_cpu_has(X86_FEATURE_PTSC); } static bool test_irperf(int idx, void *data) { return boot_cpu_has(X86_FEATURE_IRPERF); } static bool test_therm_status(int idx, void *data) { return boot_cpu_has(X86_FEATURE_DTHERM); } static bool test_intel(int idx, void *data) { if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || boot_cpu_data.x86 != 6) return false; switch (boot_cpu_data.x86_model) { case INTEL_FAM6_NEHALEM: case INTEL_FAM6_NEHALEM_G: case INTEL_FAM6_NEHALEM_EP: case INTEL_FAM6_NEHALEM_EX: case INTEL_FAM6_WESTMERE: case INTEL_FAM6_WESTMERE_EP: case INTEL_FAM6_WESTMERE_EX: case INTEL_FAM6_SANDYBRIDGE: case INTEL_FAM6_SANDYBRIDGE_X: case INTEL_FAM6_IVYBRIDGE: case INTEL_FAM6_IVYBRIDGE_X: case INTEL_FAM6_HASWELL: case INTEL_FAM6_HASWELL_X: case INTEL_FAM6_HASWELL_L: case INTEL_FAM6_HASWELL_G: case INTEL_FAM6_BROADWELL: case INTEL_FAM6_BROADWELL_D: case INTEL_FAM6_BROADWELL_G: case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SAPPHIRERAPIDS_X: case INTEL_FAM6_EMERALDRAPIDS_X: case INTEL_FAM6_ATOM_SILVERMONT: case INTEL_FAM6_ATOM_SILVERMONT_D: case INTEL_FAM6_ATOM_AIRMONT: case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_ATOM_GOLDMONT_D: case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_TREMONT_D: case INTEL_FAM6_ATOM_TREMONT: case INTEL_FAM6_ATOM_TREMONT_L: case INTEL_FAM6_XEON_PHI_KNL: case INTEL_FAM6_XEON_PHI_KNM: if (idx == PERF_MSR_SMI) return true; break; case INTEL_FAM6_SKYLAKE_L: case INTEL_FAM6_SKYLAKE: case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_KABYLAKE_L: case INTEL_FAM6_KABYLAKE: case INTEL_FAM6_COMETLAKE_L: case INTEL_FAM6_COMETLAKE: case INTEL_FAM6_ICELAKE_L: case INTEL_FAM6_ICELAKE: case INTEL_FAM6_ICELAKE_X: case INTEL_FAM6_ICELAKE_D: case INTEL_FAM6_TIGERLAKE_L: case INTEL_FAM6_TIGERLAKE: case INTEL_FAM6_ROCKETLAKE: case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; } return false; } PMU_EVENT_ATTR_STRING(tsc, attr_tsc, "event=0x00" ); PMU_EVENT_ATTR_STRING(aperf, attr_aperf, "event=0x01" ); PMU_EVENT_ATTR_STRING(mperf, attr_mperf, "event=0x02" ); PMU_EVENT_ATTR_STRING(pperf, attr_pperf, "event=0x03" ); PMU_EVENT_ATTR_STRING(smi, attr_smi, "event=0x04" ); PMU_EVENT_ATTR_STRING(ptsc, attr_ptsc, "event=0x05" ); PMU_EVENT_ATTR_STRING(irperf, attr_irperf, "event=0x06" ); PMU_EVENT_ATTR_STRING(cpu_thermal_margin, attr_therm, "event=0x07" ); PMU_EVENT_ATTR_STRING(cpu_thermal_margin.snapshot, attr_therm_snap, "1" ); PMU_EVENT_ATTR_STRING(cpu_thermal_margin.unit, attr_therm_unit, "C" ); static unsigned long msr_mask; PMU_EVENT_GROUP(events, aperf); PMU_EVENT_GROUP(events, mperf); PMU_EVENT_GROUP(events, pperf); PMU_EVENT_GROUP(events, smi); PMU_EVENT_GROUP(events, ptsc); PMU_EVENT_GROUP(events, irperf); static struct attribute *attrs_therm[] = { &attr_therm.attr.attr, &attr_therm_snap.attr.attr, &attr_therm_unit.attr.attr, NULL, }; static struct attribute_group group_therm = { .name = "events", .attrs = attrs_therm, }; static struct perf_msr msr[] = { [PERF_MSR_TSC] = { .no_check = true, }, [PERF_MSR_APERF] = { MSR_IA32_APERF, &group_aperf, test_aperfmperf, }, [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &group_mperf, test_aperfmperf, }, [PERF_MSR_PPERF] = { MSR_PPERF, &group_pperf, test_intel, }, [PERF_MSR_SMI] = { MSR_SMI_COUNT, &group_smi, test_intel, }, [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &group_ptsc, test_ptsc, }, [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &group_irperf, test_irperf, }, [PERF_MSR_THERM] = { MSR_IA32_THERM_STATUS, &group_therm, test_therm_status, }, }; static struct attribute *events_attrs[] = { &attr_tsc.attr.attr, NULL, }; static struct attribute_group events_attr_group = { .name = "events", .attrs = events_attrs, }; PMU_FORMAT_ATTR(event, "config:0-63"); static struct attribute *format_attrs[] = { &format_attr_event.attr, NULL, }; static struct attribute_group format_attr_group = { .name = "format", .attrs = format_attrs, }; static const struct attribute_group *attr_groups[] = { &events_attr_group, &format_attr_group, NULL, }; static const struct attribute_group *attr_update[] = { &group_aperf, &group_mperf, &group_pperf, &group_smi, &group_ptsc, &group_irperf, &group_therm, NULL, }; static int msr_event_init(struct perf_event *event) { u64 cfg = event->attr.config; if (event->attr.type != event->pmu->type) return -ENOENT; /* unsupported modes and filters */ if (event->attr.sample_period) /* no sampling */ return -EINVAL; if (cfg >= PERF_MSR_EVENT_MAX) return -EINVAL; cfg = array_index_nospec((unsigned long)cfg, PERF_MSR_EVENT_MAX); if (!(msr_mask & (1 << cfg))) return -EINVAL; event->hw.idx = -1; event->hw.event_base = msr[cfg].msr; event->hw.config = cfg; return 0; } static inline u64 msr_read_counter(struct perf_event *event) { u64 now; if (event->hw.event_base) rdmsrl(event->hw.event_base, now); else now = rdtsc_ordered(); return now; } static void msr_event_update(struct perf_event *event) { u64 prev, now; s64 delta; /* Careful, an NMI might modify the previous event value: */ again: prev = local64_read(&event->hw.prev_count); now = msr_read_counter(event); if (local64_cmpxchg(&event->hw.prev_count, prev, now) != prev) goto again; delta = now - prev; if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) { delta = sign_extend64(delta, 31); local64_add(delta, &event->count); } else if (unlikely(event->hw.event_base == MSR_IA32_THERM_STATUS)) { /* If valid, extract digital readout, otherwise set to -1: */ now = now & (1ULL << 31) ? (now >> 16) & 0x3f : -1; local64_set(&event->count, now); } else { local64_add(delta, &event->count); } } static void msr_event_start(struct perf_event *event, int flags) { u64 now = msr_read_counter(event); local64_set(&event->hw.prev_count, now); } static void msr_event_stop(struct perf_event *event, int flags) { msr_event_update(event); } static void msr_event_del(struct perf_event *event, int flags) { msr_event_stop(event, PERF_EF_UPDATE); } static int msr_event_add(struct perf_event *event, int flags) { if (flags & PERF_EF_START) msr_event_start(event, flags); return 0; } static struct pmu pmu_msr = { .task_ctx_nr = perf_sw_context, .attr_groups = attr_groups, .event_init = msr_event_init, .add = msr_event_add, .del = msr_event_del, .start = msr_event_start, .stop = msr_event_stop, .read = msr_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE, .attr_update = attr_update, }; static int __init msr_init(void) { if (!boot_cpu_has(X86_FEATURE_TSC)) { pr_cont("no MSR PMU driver.\n"); return 0; } msr_mask = perf_msr_probe(msr, PERF_MSR_EVENT_MAX, true, NULL); perf_pmu_register(&pmu_msr, "msr", -1); return 0; } device_initcall(msr_init); |
| 3354 3350 13 13 13 13 737 737 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * 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) { if (strscpy(name_parts->media_name, media_name, TIPC_MAX_MEDIA_NAME) < 0) return 0; if (strscpy(name_parts->if_name, if_name, TIPC_MAX_IF_NAME) < 0) return 0; } 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, (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, (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_ni(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; dev_hold(dev); 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); dev_put(net->loopback_dev); } /* 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]) { if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) { rtnl_unlock(); NL_SET_ERR_MSG(info->extack, "UDP option is unsupported"); return -EINVAL; } 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_MEDIA_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_MEDIA_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; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_GENERIC_NETLINK_H #define __NET_GENERIC_NETLINK_H #include <linux/genetlink.h> #include <linux/android_kabi.h> #include <net/netlink.h> #include <net/net_namespace.h> #define GENLMSG_DEFAULT_SIZE (NLMSG_DEFAULT_SIZE - GENL_HDRLEN) /** * struct genl_multicast_group - generic netlink multicast group * @name: name of the multicast group, names are per-family * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM) */ struct genl_multicast_group { char name[GENL_NAMSIZ]; u8 flags; }; struct genl_ops; struct genl_info; /** * struct genl_family - generic netlink family * @id: protocol family identifier (private) * @hdrsize: length of user specific header in bytes * @name: name of family * @version: protocol version * @maxattr: maximum number of attributes supported * @policy: netlink policy * @netnsok: set to true if the family can handle network * namespaces and should be presented in all of them * @parallel_ops: operations can be called in parallel and aren't * synchronized by the core genetlink code * @pre_doit: called before an operation's doit callback, it may * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may * undo operations done by pre_doit, for example release locks * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups * @mcgrp_offset: starting number of multicast group IDs in this family * (private) * @ops: the operations supported by this family * @n_ops: number of operations supported by this family * @small_ops: the small-struct operations supported by this family * @n_small_ops: number of small-struct operations supported by this family */ struct genl_family { int id; /* private */ unsigned int hdrsize; char name[GENL_NAMSIZ]; unsigned int version; unsigned int maxattr; unsigned int mcgrp_offset; /* private */ u8 netnsok:1; u8 parallel_ops:1; u8 n_ops; u8 n_small_ops; u8 n_mcgrps; const struct nla_policy *policy; int (*pre_doit)(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); void (*post_doit)(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); const struct genl_ops * ops; const struct genl_small_ops *small_ops; const struct genl_multicast_group *mcgrps; struct module *module; ANDROID_KABI_RESERVE(1); }; /** * struct genl_info - receiving information * @snd_seq: sending sequence number * @snd_portid: netlink portid of sender * @nlhdr: netlink message header * @genlhdr: generic netlink message header * @userhdr: user specific header * @attrs: netlink attributes * @_net: network namespace * @user_ptr: user pointers * @extack: extended ACK report struct */ struct genl_info { u32 snd_seq; u32 snd_portid; struct nlmsghdr * nlhdr; struct genlmsghdr * genlhdr; void * userhdr; struct nlattr ** attrs; possible_net_t _net; void * user_ptr[2]; struct netlink_ext_ack *extack; }; static inline struct net *genl_info_net(struct genl_info *info) { return read_pnet(&info->_net); } static inline void genl_info_net_set(struct genl_info *info, struct net *net) { write_pnet(&info->_net, net); } #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg) enum genl_validate_flags { GENL_DONT_VALIDATE_STRICT = BIT(0), GENL_DONT_VALIDATE_DUMP = BIT(1), GENL_DONT_VALIDATE_DUMP_STRICT = BIT(2), }; /** * struct genl_small_ops - generic netlink operations (small version) * @cmd: command identifier * @internal_flags: flags used by the family * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM) * @validate: validation flags from enum genl_validate_flags * @doit: standard command callback * @dumpit: callback for dumpers * * This is a cut-down version of struct genl_ops for users who don't need * most of the ancillary infra and want to save space. */ struct genl_small_ops { int (*doit)(struct sk_buff *skb, struct genl_info *info); int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); u8 cmd; u8 internal_flags; u8 flags; u8 validate; }; /** * struct genl_ops - generic netlink operations * @cmd: command identifier * @internal_flags: flags used by the family * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM) * @maxattr: maximum number of attributes supported * @policy: netlink policy (takes precedence over family policy) * @validate: validation flags from enum genl_validate_flags * @doit: standard command callback * @start: start callback for dumps * @dumpit: callback for dumpers * @done: completion callback for dumps */ struct genl_ops { int (*doit)(struct sk_buff *skb, struct genl_info *info); int (*start)(struct netlink_callback *cb); int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); const struct nla_policy *policy; unsigned int maxattr; u8 cmd; u8 internal_flags; u8 flags; u8 validate; ANDROID_KABI_RESERVE(1); }; /** * struct genl_info - info that is available during dumpit op call * @family: generic netlink family - for internal genl code usage * @ops: generic netlink ops - for internal genl code usage * @attrs: netlink attributes */ struct genl_dumpit_info { const struct genl_family *family; struct genl_ops op; struct nlattr **attrs; }; static inline const struct genl_dumpit_info * genl_dumpit_info(struct netlink_callback *cb) { return cb->data; } int genl_register_family(struct genl_family *family); int genl_unregister_family(const struct genl_family *family); void genl_notify(const struct genl_family *family, struct sk_buff *skb, struct genl_info *info, u32 group, gfp_t flags); void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, const struct genl_family *family, int flags, u8 cmd); /** * genlmsg_nlhdr - Obtain netlink header from user specified header * @user_hdr: user header as returned from genlmsg_put() * * Returns pointer to netlink header. */ static inline struct nlmsghdr *genlmsg_nlhdr(void *user_hdr) { return (struct nlmsghdr *)((char *)user_hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_parse_deprecated - parse attributes of a genetlink message * @nlh: netlink message header * @family: genetlink message family * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct */ static inline int genlmsg_parse_deprecated(const struct nlmsghdr *nlh, const struct genl_family *family, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * genlmsg_parse - parse attributes of a genetlink message * @nlh: netlink message header * @family: genetlink message family * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct */ static inline int genlmsg_parse(const struct nlmsghdr *nlh, const struct genl_family *family, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype, policy, NL_VALIDATE_STRICT, extack); } /** * genl_dump_check_consistent - check if sequence is consistent and advertise if not * @cb: netlink callback structure that stores the sequence number * @user_hdr: user header as returned from genlmsg_put() * * Cf. nl_dump_check_consistent(), this just provides a wrapper to make it * simpler to use with generic netlink. */ static inline void genl_dump_check_consistent(struct netlink_callback *cb, void *user_hdr) { nl_dump_check_consistent(cb, genlmsg_nlhdr(user_hdr)); } /** * genlmsg_put_reply - Add generic netlink header to a reply message * @skb: socket buffer holding the message * @info: receiver info * @family: generic netlink family * @flags: netlink message flags * @cmd: generic netlink command * * Returns pointer to user specific header */ static inline void *genlmsg_put_reply(struct sk_buff *skb, struct genl_info *info, const struct genl_family *family, int flags, u8 cmd) { return genlmsg_put(skb, info->snd_portid, info->snd_seq, family, flags, cmd); } /** * genlmsg_end - Finalize a generic netlink message * @skb: socket buffer the message is stored in * @hdr: user specific header */ static inline void genlmsg_end(struct sk_buff *skb, void *hdr) { nlmsg_end(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_cancel - Cancel construction of a generic netlink message * @skb: socket buffer the message is stored in * @hdr: generic netlink message header */ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr) { if (hdr) nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_multicast_netns - multicast a netlink message to a specific netns * @family: the generic netlink family * @net: the net namespace * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array * @flags: allocation flags */ static inline int genlmsg_multicast_netns(const struct genl_family *family, struct net *net, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return nlmsg_multicast(net->genl_sock, skb, portid, group, flags); } /** * genlmsg_multicast - multicast a netlink message to the default netns * @family: the generic netlink family * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array * @flags: allocation flags */ static inline int genlmsg_multicast(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { return genlmsg_multicast_netns(family, &init_net, skb, portid, group, flags); } /** * genlmsg_multicast_allns - multicast a netlink message to all net namespaces * @family: the generic netlink family * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array * @flags: allocation flags * * This function must hold the RTNL or rcu_read_lock(). */ int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags); /** * genlmsg_unicast - unicast a netlink message * @skb: netlink message as socket buffer * @portid: netlink portid of the destination socket */ static inline int genlmsg_unicast(struct net *net, struct sk_buff *skb, u32 portid) { return nlmsg_unicast(net->genl_sock, skb, portid); } /** * genlmsg_reply - reply to a request * @skb: netlink message to be sent back * @info: receiver information */ static inline int genlmsg_reply(struct sk_buff *skb, struct genl_info *info) { return genlmsg_unicast(genl_info_net(info), skb, info->snd_portid); } /** * gennlmsg_data - head of message payload * @gnlh: genetlink message header */ static inline void *genlmsg_data(const struct genlmsghdr *gnlh) { return ((unsigned char *) gnlh + GENL_HDRLEN); } /** * genlmsg_len - length of message payload * @gnlh: genetlink message header */ static inline int genlmsg_len(const struct genlmsghdr *gnlh) { struct nlmsghdr *nlh = (struct nlmsghdr *)((unsigned char *)gnlh - NLMSG_HDRLEN); return (nlh->nlmsg_len - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_msg_size - length of genetlink message not including padding * @payload: length of message payload */ static inline int genlmsg_msg_size(int payload) { return GENL_HDRLEN + payload; } /** * genlmsg_total_size - length of genetlink message including padding * @payload: length of message payload */ static inline int genlmsg_total_size(int payload) { return NLMSG_ALIGN(genlmsg_msg_size(payload)); } /** * genlmsg_new - Allocate a new generic netlink message * @payload: size of the message payload * @flags: the type of memory to allocate. */ static inline struct sk_buff *genlmsg_new(size_t payload, gfp_t flags) { return nlmsg_new(genlmsg_total_size(payload), flags); } /** * genl_set_err - report error to genetlink broadcast listeners * @family: the generic netlink family * @net: the network namespace to report the error to * @portid: the PORTID of a process that we want to skip (if any) * @group: the broadcast group that will notice the error * (this is the offset of the multicast group in the groups array) * @code: error code, must be negative (as usual in kernelspace) * * This function returns the number of broadcast listeners that have set the * NETLINK_RECV_NO_ENOBUFS socket option. */ static inline int genl_set_err(const struct genl_family *family, struct net *net, u32 portid, u32 group, int code) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return netlink_set_err(net->genl_sock, portid, group, code); } static inline int genl_has_listeners(const struct genl_family *family, struct net *net, unsigned int group) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return netlink_has_listeners(net->genl_sock, group); } #endif /* __NET_GENERIC_NETLINK_H */ |
| 2 2 25 18 8 23 4 25 25 48 48 29 31 29 31 57 47 41 18 38 23 59 3 2 1 1 1 4 1 3 61 61 62 61 61 61 61 61 3357 3354 6 3 3 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * drivers/net/macsec.c - MACsec device * * Copyright (c) 2015 Sabrina Dubroca <sd@queasysnail.net> */ #include <linux/types.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/module.h> #include <crypto/aead.h> #include <linux/etherdevice.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/refcount.h> #include <net/genetlink.h> #include <net/sock.h> #include <net/gro_cells.h> #include <net/macsec.h> #include <linux/phy.h> #include <linux/byteorder/generic.h> #include <linux/if_arp.h> #include <uapi/linux/if_macsec.h> #define MACSEC_SCI_LEN 8 /* SecTAG length = macsec_eth_header without the optional SCI */ #define MACSEC_TAG_LEN 6 struct macsec_eth_header { struct ethhdr eth; /* SecTAG */ u8 tci_an; #if defined(__LITTLE_ENDIAN_BITFIELD) u8 short_length:6, unused:2; #elif defined(__BIG_ENDIAN_BITFIELD) u8 unused:2, short_length:6; #else #error "Please fix <asm/byteorder.h>" #endif __be32 packet_number; u8 secure_channel_id[8]; /* optional */ } __packed; #define MACSEC_TCI_VERSION 0x80 #define MACSEC_TCI_ES 0x40 /* end station */ #define MACSEC_TCI_SC 0x20 /* SCI present */ #define MACSEC_TCI_SCB 0x10 /* epon */ #define MACSEC_TCI_E 0x08 /* encryption */ #define MACSEC_TCI_C 0x04 /* changed text */ #define MACSEC_AN_MASK 0x03 /* association number */ #define MACSEC_TCI_CONFID (MACSEC_TCI_E | MACSEC_TCI_C) /* minimum secure data length deemed "not short", see IEEE 802.1AE-2006 9.7 */ #define MIN_NON_SHORT_LEN 48 #define GCM_AES_IV_LEN 12 #define DEFAULT_ICV_LEN 16 #define for_each_rxsc(secy, sc) \ for (sc = rcu_dereference_bh(secy->rx_sc); \ sc; \ sc = rcu_dereference_bh(sc->next)) #define for_each_rxsc_rtnl(secy, sc) \ for (sc = rtnl_dereference(secy->rx_sc); \ sc; \ sc = rtnl_dereference(sc->next)) #define pn_same_half(pn1, pn2) (!(((pn1) >> 31) ^ ((pn2) >> 31))) struct gcm_iv_xpn { union { u8 short_secure_channel_id[4]; ssci_t ssci; }; __be64 pn; } __packed; struct gcm_iv { union { u8 secure_channel_id[8]; sci_t sci; }; __be32 pn; }; #define MACSEC_VALIDATE_DEFAULT MACSEC_VALIDATE_STRICT struct pcpu_secy_stats { struct macsec_dev_stats stats; struct u64_stats_sync syncp; }; /** * struct macsec_dev - private data * @secy: SecY config * @real_dev: pointer to underlying netdevice * @stats: MACsec device stats * @secys: linked list of SecY's on the underlying device * @gro_cells: pointer to the Generic Receive Offload cell * @offload: status of offloading on the MACsec device */ struct macsec_dev { struct macsec_secy secy; struct net_device *real_dev; struct pcpu_secy_stats __percpu *stats; struct list_head secys; struct gro_cells gro_cells; enum macsec_offload offload; }; /** * struct macsec_rxh_data - rx_handler private argument * @secys: linked list of SecY's on this underlying device */ struct macsec_rxh_data { struct list_head secys; }; static struct macsec_dev *macsec_priv(const struct net_device *dev) { return (struct macsec_dev *)netdev_priv(dev); } static struct macsec_rxh_data *macsec_data_rcu(const struct net_device *dev) { return rcu_dereference_bh(dev->rx_handler_data); } static struct macsec_rxh_data *macsec_data_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->rx_handler_data); } struct macsec_cb { struct aead_request *req; union { struct macsec_tx_sa *tx_sa; struct macsec_rx_sa *rx_sa; }; u8 assoc_num; bool valid; bool has_sci; }; static struct macsec_rx_sa *macsec_rxsa_get(struct macsec_rx_sa __rcu *ptr) { struct macsec_rx_sa *sa = rcu_dereference_bh(ptr); if (!sa || !sa->active) return NULL; if (!refcount_inc_not_zero(&sa->refcnt)) return NULL; return sa; } static void free_rx_sc_rcu(struct rcu_head *head) { struct macsec_rx_sc *rx_sc = container_of(head, struct macsec_rx_sc, rcu_head); free_percpu(rx_sc->stats); kfree(rx_sc); } static struct macsec_rx_sc *macsec_rxsc_get(struct macsec_rx_sc *sc) { return refcount_inc_not_zero(&sc->refcnt) ? sc : NULL; } static void macsec_rxsc_put(struct macsec_rx_sc *sc) { if (refcount_dec_and_test(&sc->refcnt)) call_rcu(&sc->rcu_head, free_rx_sc_rcu); } static void free_rxsa(struct rcu_head *head) { struct macsec_rx_sa *sa = container_of(head, struct macsec_rx_sa, rcu); crypto_free_aead(sa->key.tfm); free_percpu(sa->stats); kfree(sa); } static void macsec_rxsa_put(struct macsec_rx_sa *sa) { if (refcount_dec_and_test(&sa->refcnt)) call_rcu(&sa->rcu, free_rxsa); } static struct macsec_tx_sa *macsec_txsa_get(struct macsec_tx_sa __rcu *ptr) { struct macsec_tx_sa *sa = rcu_dereference_bh(ptr); if (!sa || !sa->active) return NULL; if (!refcount_inc_not_zero(&sa->refcnt)) return NULL; return sa; } static void free_txsa(struct rcu_head *head) { struct macsec_tx_sa *sa = container_of(head, struct macsec_tx_sa, rcu); crypto_free_aead(sa->key.tfm); free_percpu(sa->stats); kfree(sa); } static void macsec_txsa_put(struct macsec_tx_sa *sa) { if (refcount_dec_and_test(&sa->refcnt)) call_rcu(&sa->rcu, free_txsa); } static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb) { BUILD_BUG_ON(sizeof(struct macsec_cb) > sizeof(skb->cb)); return (struct macsec_cb *)skb->cb; } #define MACSEC_PORT_ES (htons(0x0001)) #define MACSEC_PORT_SCB (0x0000) #define MACSEC_UNDEF_SCI ((__force sci_t)0xffffffffffffffffULL) #define MACSEC_UNDEF_SSCI ((__force ssci_t)0xffffffff) #define MACSEC_GCM_AES_128_SAK_LEN 16 #define MACSEC_GCM_AES_256_SAK_LEN 32 #define DEFAULT_SAK_LEN MACSEC_GCM_AES_128_SAK_LEN #define DEFAULT_XPN false #define DEFAULT_SEND_SCI true #define DEFAULT_ENCRYPT false #define DEFAULT_ENCODING_SA 0 #define MACSEC_XPN_MAX_REPLAY_WINDOW (((1 << 30) - 1)) static bool send_sci(const struct macsec_secy *secy) { const struct macsec_tx_sc *tx_sc = &secy->tx_sc; return tx_sc->send_sci || (secy->n_rx_sc > 1 && !tx_sc->end_station && !tx_sc->scb); } static sci_t make_sci(u8 *addr, __be16 port) { sci_t sci; memcpy(&sci, addr, ETH_ALEN); memcpy(((char *)&sci) + ETH_ALEN, &port, sizeof(port)); return sci; } static sci_t macsec_frame_sci(struct macsec_eth_header *hdr, bool sci_present) { sci_t sci; if (sci_present) memcpy(&sci, hdr->secure_channel_id, sizeof(hdr->secure_channel_id)); else sci = make_sci(hdr->eth.h_source, MACSEC_PORT_ES); return sci; } static unsigned int macsec_sectag_len(bool sci_present) { return MACSEC_TAG_LEN + (sci_present ? MACSEC_SCI_LEN : 0); } static unsigned int macsec_hdr_len(bool sci_present) { return macsec_sectag_len(sci_present) + ETH_HLEN; } static unsigned int macsec_extra_len(bool sci_present) { return macsec_sectag_len(sci_present) + sizeof(__be16); } /* Fill SecTAG according to IEEE 802.1AE-2006 10.5.3 */ static void macsec_fill_sectag(struct macsec_eth_header *h, const struct macsec_secy *secy, u32 pn, bool sci_present) { const struct macsec_tx_sc *tx_sc = &secy->tx_sc; memset(&h->tci_an, 0, macsec_sectag_len(sci_present)); h->eth.h_proto = htons(ETH_P_MACSEC); if (sci_present) { h->tci_an |= MACSEC_TCI_SC; memcpy(&h->secure_channel_id, &secy->sci, sizeof(h->secure_channel_id)); } else { if (tx_sc->end_station) h->tci_an |= MACSEC_TCI_ES; if (tx_sc->scb) h->tci_an |= MACSEC_TCI_SCB; } h->packet_number = htonl(pn); /* with GCM, C/E clear for !encrypt, both set for encrypt */ if (tx_sc->encrypt) h->tci_an |= MACSEC_TCI_CONFID; else if (secy->icv_len != DEFAULT_ICV_LEN) h->tci_an |= MACSEC_TCI_C; h->tci_an |= tx_sc->encoding_sa; } static void macsec_set_shortlen(struct macsec_eth_header *h, size_t data_len) { if (data_len < MIN_NON_SHORT_LEN) h->short_length = data_len; } /* Checks if a MACsec interface is being offloaded to an hardware engine */ static bool macsec_is_offloaded(struct macsec_dev *macsec) { if (macsec->offload == MACSEC_OFFLOAD_MAC || macsec->offload == MACSEC_OFFLOAD_PHY) return true; return false; } /* Checks if underlying layers implement MACsec offloading functions. */ static bool macsec_check_offload(enum macsec_offload offload, struct macsec_dev *macsec) { if (!macsec || !macsec->real_dev) return false; if (offload == MACSEC_OFFLOAD_PHY) return macsec->real_dev->phydev && macsec->real_dev->phydev->macsec_ops; else if (offload == MACSEC_OFFLOAD_MAC) return macsec->real_dev->features & NETIF_F_HW_MACSEC && macsec->real_dev->macsec_ops; return false; } static const struct macsec_ops *__macsec_get_ops(enum macsec_offload offload, struct macsec_dev *macsec, struct macsec_context *ctx) { if (ctx) { memset(ctx, 0, sizeof(*ctx)); ctx->offload = offload; if (offload == MACSEC_OFFLOAD_PHY) ctx->phydev = macsec->real_dev->phydev; else if (offload == MACSEC_OFFLOAD_MAC) ctx->netdev = macsec->real_dev; } if (offload == MACSEC_OFFLOAD_PHY) return macsec->real_dev->phydev->macsec_ops; else return macsec->real_dev->macsec_ops; } /* Returns a pointer to the MACsec ops struct if any and updates the MACsec * context device reference if provided. */ static const struct macsec_ops *macsec_get_ops(struct macsec_dev *macsec, struct macsec_context *ctx) { if (!macsec_check_offload(macsec->offload, macsec)) return NULL; return __macsec_get_ops(macsec->offload, macsec, ctx); } /* validate MACsec packet according to IEEE 802.1AE-2018 9.12 */ static bool macsec_validate_skb(struct sk_buff *skb, u16 icv_len, bool xpn) { struct macsec_eth_header *h = (struct macsec_eth_header *)skb->data; int len = skb->len - 2 * ETH_ALEN; int extra_len = macsec_extra_len(!!(h->tci_an & MACSEC_TCI_SC)) + icv_len; /* a) It comprises at least 17 octets */ if (skb->len <= 16) return false; /* b) MACsec EtherType: already checked */ /* c) V bit is clear */ if (h->tci_an & MACSEC_TCI_VERSION) return false; /* d) ES or SCB => !SC */ if ((h->tci_an & MACSEC_TCI_ES || h->tci_an & MACSEC_TCI_SCB) && (h->tci_an & MACSEC_TCI_SC)) return false; /* e) Bits 7 and 8 of octet 4 of the SecTAG are clear */ if (h->unused) return false; /* rx.pn != 0 if not XPN (figure 10-5 with 802.11AEbw-2013 amendment) */ if (!h->packet_number && !xpn) return false; /* length check, f) g) h) i) */ if (h->short_length) return len == extra_len + h->short_length; return len >= extra_len + MIN_NON_SHORT_LEN; } #define MACSEC_NEEDED_HEADROOM (macsec_extra_len(true)) #define MACSEC_NEEDED_TAILROOM MACSEC_STD_ICV_LEN static void macsec_fill_iv_xpn(unsigned char *iv, ssci_t ssci, u64 pn, salt_t salt) { struct gcm_iv_xpn *gcm_iv = (struct gcm_iv_xpn *)iv; gcm_iv->ssci = ssci ^ salt.ssci; gcm_iv->pn = cpu_to_be64(pn) ^ salt.pn; } static void macsec_fill_iv(unsigned char *iv, sci_t sci, u32 pn) { struct gcm_iv *gcm_iv = (struct gcm_iv *)iv; gcm_iv->sci = sci; gcm_iv->pn = htonl(pn); } static struct macsec_eth_header *macsec_ethhdr(struct sk_buff *skb) { return (struct macsec_eth_header *)skb_mac_header(skb); } static void __macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa) { pr_debug("PN wrapped, transitioning to !oper\n"); tx_sa->active = false; if (secy->protect_frames) secy->operational = false; } void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa) { spin_lock_bh(&tx_sa->lock); __macsec_pn_wrapped(secy, tx_sa); spin_unlock_bh(&tx_sa->lock); } EXPORT_SYMBOL_GPL(macsec_pn_wrapped); static pn_t tx_sa_update_pn(struct macsec_tx_sa *tx_sa, struct macsec_secy *secy) { pn_t pn; spin_lock_bh(&tx_sa->lock); pn = tx_sa->next_pn_halves; if (secy->xpn) tx_sa->next_pn++; else tx_sa->next_pn_halves.lower++; if (tx_sa->next_pn == 0) __macsec_pn_wrapped(secy, tx_sa); spin_unlock_bh(&tx_sa->lock); return pn; } static void macsec_encrypt_finish(struct sk_buff *skb, struct net_device *dev) { struct macsec_dev *macsec = netdev_priv(dev); skb->dev = macsec->real_dev; skb_reset_mac_header(skb); skb->protocol = eth_hdr(skb)->h_proto; } static void macsec_count_tx(struct sk_buff *skb, struct macsec_tx_sc *tx_sc, struct macsec_tx_sa *tx_sa) { struct pcpu_tx_sc_stats *txsc_stats = this_cpu_ptr(tx_sc->stats); u64_stats_update_begin(&txsc_stats->syncp); if (tx_sc->encrypt) { txsc_stats->stats.OutOctetsEncrypted += skb->len; txsc_stats->stats.OutPktsEncrypted++; this_cpu_inc(tx_sa->stats->OutPktsEncrypted); } else { txsc_stats->stats.OutOctetsProtected += skb->len; txsc_stats->stats.OutPktsProtected++; this_cpu_inc(tx_sa->stats->OutPktsProtected); } u64_stats_update_end(&txsc_stats->syncp); } static void count_tx(struct net_device *dev, int ret, int len) { if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct pcpu_sw_netstats *stats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&stats->syncp); stats->tx_packets++; stats->tx_bytes += len; u64_stats_update_end(&stats->syncp); } } static void macsec_encrypt_done(struct crypto_async_request *base, int err) { struct sk_buff *skb = base->data; struct net_device *dev = skb->dev; struct macsec_dev *macsec = macsec_priv(dev); struct macsec_tx_sa *sa = macsec_skb_cb(skb)->tx_sa; int len, ret; aead_request_free(macsec_skb_cb(skb)->req); rcu_read_lock_bh(); macsec_encrypt_finish(skb, dev); macsec_count_tx(skb, &macsec->secy.tx_sc, macsec_skb_cb(skb)->tx_sa); len = skb->len; ret = dev_queue_xmit(skb); count_tx(dev, ret, len); rcu_read_unlock_bh(); macsec_txsa_put(sa); dev_put(dev); } static struct aead_request *macsec_alloc_req(struct crypto_aead *tfm, unsigned char **iv, struct scatterlist **sg, int num_frags) { size_t size, iv_offset, sg_offset; struct aead_request *req; void *tmp; size = sizeof(struct aead_request) + crypto_aead_reqsize(tfm); iv_offset = size; size += GCM_AES_IV_LEN; size = ALIGN(size, __alignof__(struct scatterlist)); sg_offset = size; size += sizeof(struct scatterlist) * num_frags; tmp = kmalloc(size, GFP_ATOMIC); if (!tmp) return NULL; *iv = (unsigned char *)(tmp + iv_offset); *sg = (struct scatterlist *)(tmp + sg_offset); req = tmp; aead_request_set_tfm(req, tfm); return req; } static struct sk_buff *macsec_encrypt(struct sk_buff *skb, struct net_device *dev) { int ret; struct scatterlist *sg; struct sk_buff *trailer; unsigned char *iv; struct ethhdr *eth; struct macsec_eth_header *hh; size_t unprotected_len; struct aead_request *req; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; struct macsec_dev *macsec = macsec_priv(dev); bool sci_present; pn_t pn; secy = &macsec->secy; tx_sc = &secy->tx_sc; /* 10.5.1 TX SA assignment */ tx_sa = macsec_txsa_get(tx_sc->sa[tx_sc->encoding_sa]); if (!tx_sa) { secy->operational = false; kfree_skb(skb); return ERR_PTR(-EINVAL); } if (unlikely(skb_headroom(skb) < MACSEC_NEEDED_HEADROOM || skb_tailroom(skb) < MACSEC_NEEDED_TAILROOM)) { struct sk_buff *nskb = skb_copy_expand(skb, MACSEC_NEEDED_HEADROOM, MACSEC_NEEDED_TAILROOM, GFP_ATOMIC); if (likely(nskb)) { consume_skb(skb); skb = nskb; } else { macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(-ENOMEM); } } else { skb = skb_unshare(skb, GFP_ATOMIC); if (!skb) { macsec_txsa_put(tx_sa); return ERR_PTR(-ENOMEM); } } unprotected_len = skb->len; eth = eth_hdr(skb); sci_present = send_sci(secy); hh = skb_push(skb, macsec_extra_len(sci_present)); memmove(hh, eth, 2 * ETH_ALEN); pn = tx_sa_update_pn(tx_sa, secy); if (pn.full64 == 0) { macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(-ENOLINK); } macsec_fill_sectag(hh, secy, pn.lower, sci_present); macsec_set_shortlen(hh, unprotected_len - 2 * ETH_ALEN); skb_put(skb, secy->icv_len); if (skb->len - ETH_HLEN > macsec_priv(dev)->real_dev->mtu) { struct pcpu_secy_stats *secy_stats = this_cpu_ptr(macsec->stats); u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.OutPktsTooLong++; u64_stats_update_end(&secy_stats->syncp); macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(-EINVAL); } ret = skb_cow_data(skb, 0, &trailer); if (unlikely(ret < 0)) { macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(ret); } req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg, ret); if (!req) { macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(-ENOMEM); } if (secy->xpn) macsec_fill_iv_xpn(iv, tx_sa->ssci, pn.full64, tx_sa->key.salt); else macsec_fill_iv(iv, secy->sci, pn.lower); sg_init_table(sg, ret); ret = skb_to_sgvec(skb, sg, 0, skb->len); if (unlikely(ret < 0)) { aead_request_free(req); macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(ret); } if (tx_sc->encrypt) { int len = skb->len - macsec_hdr_len(sci_present) - secy->icv_len; aead_request_set_crypt(req, sg, sg, len, iv); aead_request_set_ad(req, macsec_hdr_len(sci_present)); } else { aead_request_set_crypt(req, sg, sg, 0, iv); aead_request_set_ad(req, skb->len - secy->icv_len); } macsec_skb_cb(skb)->req = req; macsec_skb_cb(skb)->tx_sa = tx_sa; aead_request_set_callback(req, 0, macsec_encrypt_done, skb); dev_hold(skb->dev); ret = crypto_aead_encrypt(req); if (ret == -EINPROGRESS) { return ERR_PTR(ret); } else if (ret != 0) { dev_put(skb->dev); kfree_skb(skb); aead_request_free(req); macsec_txsa_put(tx_sa); return ERR_PTR(-EINVAL); } dev_put(skb->dev); aead_request_free(req); macsec_txsa_put(tx_sa); return skb; } static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u32 pn) { struct macsec_rx_sa *rx_sa = macsec_skb_cb(skb)->rx_sa; struct pcpu_rx_sc_stats *rxsc_stats = this_cpu_ptr(rx_sa->sc->stats); struct macsec_eth_header *hdr = macsec_ethhdr(skb); u32 lowest_pn = 0; spin_lock(&rx_sa->lock); if (rx_sa->next_pn_halves.lower >= secy->replay_window) lowest_pn = rx_sa->next_pn_halves.lower - secy->replay_window; /* Now perform replay protection check again * (see IEEE 802.1AE-2006 figure 10-5) */ if (secy->replay_protect && pn < lowest_pn && (!secy->xpn || pn_same_half(pn, lowest_pn))) { spin_unlock(&rx_sa->lock); u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); return false; } if (secy->validate_frames != MACSEC_VALIDATE_DISABLED) { u64_stats_update_begin(&rxsc_stats->syncp); if (hdr->tci_an & MACSEC_TCI_E) rxsc_stats->stats.InOctetsDecrypted += skb->len; else rxsc_stats->stats.InOctetsValidated += skb->len; u64_stats_update_end(&rxsc_stats->syncp); } if (!macsec_skb_cb(skb)->valid) { spin_unlock(&rx_sa->lock); /* 10.6.5 */ if (hdr->tci_an & MACSEC_TCI_C || secy->validate_frames == MACSEC_VALIDATE_STRICT) { u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsNotValid++; u64_stats_update_end(&rxsc_stats->syncp); return false; } u64_stats_update_begin(&rxsc_stats->syncp); if (secy->validate_frames == MACSEC_VALIDATE_CHECK) { rxsc_stats->stats.InPktsInvalid++; this_cpu_inc(rx_sa->stats->InPktsInvalid); } else if (pn < lowest_pn) { rxsc_stats->stats.InPktsDelayed++; } else { rxsc_stats->stats.InPktsUnchecked++; } u64_stats_update_end(&rxsc_stats->syncp); } else { u64_stats_update_begin(&rxsc_stats->syncp); if (pn < lowest_pn) { rxsc_stats->stats.InPktsDelayed++; } else { rxsc_stats->stats.InPktsOK++; this_cpu_inc(rx_sa->stats->InPktsOK); } u64_stats_update_end(&rxsc_stats->syncp); // Instead of "pn >=" - to support pn overflow in xpn if (pn + 1 > rx_sa->next_pn_halves.lower) { rx_sa->next_pn_halves.lower = pn + 1; } else if (secy->xpn && !pn_same_half(pn, rx_sa->next_pn_halves.lower)) { rx_sa->next_pn_halves.upper++; rx_sa->next_pn_halves.lower = pn + 1; } spin_unlock(&rx_sa->lock); } return true; } static void macsec_reset_skb(struct sk_buff *skb, struct net_device *dev) { skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, dev); skb_reset_network_header(skb); if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); skb_reset_mac_len(skb); } static void macsec_finalize_skb(struct sk_buff *skb, u8 icv_len, u8 hdr_len) { skb->ip_summed = CHECKSUM_NONE; memmove(skb->data + hdr_len, skb->data, 2 * ETH_ALEN); skb_pull(skb, hdr_len); pskb_trim_unique(skb, skb->len - icv_len); } static void count_rx(struct net_device *dev, int len) { struct pcpu_sw_netstats *stats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&stats->syncp); stats->rx_packets++; stats->rx_bytes += len; u64_stats_update_end(&stats->syncp); } static void macsec_decrypt_done(struct crypto_async_request *base, int err) { struct sk_buff *skb = base->data; struct net_device *dev = skb->dev; struct macsec_dev *macsec = macsec_priv(dev); struct macsec_rx_sa *rx_sa = macsec_skb_cb(skb)->rx_sa; struct macsec_rx_sc *rx_sc = rx_sa->sc; int len; u32 pn; aead_request_free(macsec_skb_cb(skb)->req); if (!err) macsec_skb_cb(skb)->valid = true; rcu_read_lock_bh(); pn = ntohl(macsec_ethhdr(skb)->packet_number); if (!macsec_post_decrypt(skb, &macsec->secy, pn)) { rcu_read_unlock_bh(); kfree_skb(skb); goto out; } macsec_finalize_skb(skb, macsec->secy.icv_len, macsec_extra_len(macsec_skb_cb(skb)->has_sci)); macsec_reset_skb(skb, macsec->secy.netdev); len = skb->len; if (gro_cells_receive(&macsec->gro_cells, skb) == NET_RX_SUCCESS) count_rx(dev, len); rcu_read_unlock_bh(); out: macsec_rxsa_put(rx_sa); macsec_rxsc_put(rx_sc); dev_put(dev); } static struct sk_buff *macsec_decrypt(struct sk_buff *skb, struct net_device *dev, struct macsec_rx_sa *rx_sa, sci_t sci, struct macsec_secy *secy) { int ret; struct scatterlist *sg; struct sk_buff *trailer; unsigned char *iv; struct aead_request *req; struct macsec_eth_header *hdr; u32 hdr_pn; u16 icv_len = secy->icv_len; macsec_skb_cb(skb)->valid = false; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) return ERR_PTR(-ENOMEM); ret = skb_cow_data(skb, 0, &trailer); if (unlikely(ret < 0)) { kfree_skb(skb); return ERR_PTR(ret); } req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg, ret); if (!req) { kfree_skb(skb); return ERR_PTR(-ENOMEM); } hdr = (struct macsec_eth_header *)skb->data; hdr_pn = ntohl(hdr->packet_number); if (secy->xpn) { pn_t recovered_pn = rx_sa->next_pn_halves; recovered_pn.lower = hdr_pn; if (hdr_pn < rx_sa->next_pn_halves.lower && !pn_same_half(hdr_pn, rx_sa->next_pn_halves.lower)) recovered_pn.upper++; macsec_fill_iv_xpn(iv, rx_sa->ssci, recovered_pn.full64, rx_sa->key.salt); } else { macsec_fill_iv(iv, sci, hdr_pn); } sg_init_table(sg, ret); ret = skb_to_sgvec(skb, sg, 0, skb->len); if (unlikely(ret < 0)) { aead_request_free(req); kfree_skb(skb); return ERR_PTR(ret); } if (hdr->tci_an & MACSEC_TCI_E) { /* confidentiality: ethernet + macsec header * authenticated, encrypted payload */ int len = skb->len - macsec_hdr_len(macsec_skb_cb(skb)->has_sci); aead_request_set_crypt(req, sg, sg, len, iv); aead_request_set_ad(req, macsec_hdr_len(macsec_skb_cb(skb)->has_sci)); skb = skb_unshare(skb, GFP_ATOMIC); if (!skb) { aead_request_free(req); return ERR_PTR(-ENOMEM); } } else { /* integrity only: all headers + data authenticated */ aead_request_set_crypt(req, sg, sg, icv_len, iv); aead_request_set_ad(req, skb->len - icv_len); } macsec_skb_cb(skb)->req = req; skb->dev = dev; aead_request_set_callback(req, 0, macsec_decrypt_done, skb); dev_hold(dev); ret = crypto_aead_decrypt(req); if (ret == -EINPROGRESS) { return ERR_PTR(ret); } else if (ret != 0) { /* decryption/authentication failed * 10.6 if validateFrames is disabled, deliver anyway */ if (ret != -EBADMSG) { kfree_skb(skb); skb = ERR_PTR(ret); } } else { macsec_skb_cb(skb)->valid = true; } dev_put(dev); aead_request_free(req); return skb; } static struct macsec_rx_sc *find_rx_sc(struct macsec_secy *secy, sci_t sci) { struct macsec_rx_sc *rx_sc; for_each_rxsc(secy, rx_sc) { if (rx_sc->sci == sci) return rx_sc; } return NULL; } static struct macsec_rx_sc *find_rx_sc_rtnl(struct macsec_secy *secy, sci_t sci) { struct macsec_rx_sc *rx_sc; for_each_rxsc_rtnl(secy, rx_sc) { if (rx_sc->sci == sci) return rx_sc; } return NULL; } static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) { /* Deliver to the uncontrolled port by default */ enum rx_handler_result ret = RX_HANDLER_PASS; struct ethhdr *hdr = eth_hdr(skb); struct macsec_rxh_data *rxd; struct macsec_dev *macsec; rcu_read_lock(); rxd = macsec_data_rcu(skb->dev); list_for_each_entry_rcu(macsec, &rxd->secys, secys) { struct sk_buff *nskb; struct pcpu_secy_stats *secy_stats = this_cpu_ptr(macsec->stats); struct net_device *ndev = macsec->secy.netdev; /* If h/w offloading is enabled, HW decodes frames and strips * the SecTAG, so we have to deduce which port to deliver to. */ if (macsec_is_offloaded(macsec) && netif_running(ndev)) { if (ether_addr_equal_64bits(hdr->h_dest, ndev->dev_addr)) { /* exact match, divert skb to this port */ skb->dev = ndev; skb->pkt_type = PACKET_HOST; ret = RX_HANDLER_ANOTHER; goto out; } else if (is_multicast_ether_addr_64bits( hdr->h_dest)) { /* multicast frame, deliver on this port too */ nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) break; nskb->dev = ndev; if (ether_addr_equal_64bits(hdr->h_dest, ndev->broadcast)) nskb->pkt_type = PACKET_BROADCAST; else nskb->pkt_type = PACKET_MULTICAST; netif_rx(nskb); } continue; } /* 10.6 If the management control validateFrames is not * Strict, frames without a SecTAG are received, counted, and * delivered to the Controlled Port */ if (macsec->secy.validate_frames == MACSEC_VALIDATE_STRICT) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoTag++; u64_stats_update_end(&secy_stats->syncp); continue; } /* deliver on this port */ nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) break; nskb->dev = ndev; if (netif_rx(nskb) == NET_RX_SUCCESS) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsUntagged++; u64_stats_update_end(&secy_stats->syncp); } } out: rcu_read_unlock(); return ret; } static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct net_device *dev = skb->dev; struct macsec_eth_header *hdr; struct macsec_secy *secy = NULL; struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; struct macsec_rxh_data *rxd; struct macsec_dev *macsec; unsigned int len; sci_t sci; u32 hdr_pn; bool cbit; struct pcpu_rx_sc_stats *rxsc_stats; struct pcpu_secy_stats *secy_stats; bool pulled_sci; int ret; if (skb_headroom(skb) < ETH_HLEN) goto drop_direct; hdr = macsec_ethhdr(skb); if (hdr->eth.h_proto != htons(ETH_P_MACSEC)) return handle_not_macsec(skb); skb = skb_unshare(skb, GFP_ATOMIC); *pskb = skb; if (!skb) return RX_HANDLER_CONSUMED; pulled_sci = pskb_may_pull(skb, macsec_extra_len(true)); if (!pulled_sci) { if (!pskb_may_pull(skb, macsec_extra_len(false))) goto drop_direct; } hdr = macsec_ethhdr(skb); /* Frames with a SecTAG that has the TCI E bit set but the C * bit clear are discarded, as this reserved encoding is used * to identify frames with a SecTAG that are not to be * delivered to the Controlled Port. */ if ((hdr->tci_an & (MACSEC_TCI_C | MACSEC_TCI_E)) == MACSEC_TCI_E) return RX_HANDLER_PASS; /* now, pull the extra length */ if (hdr->tci_an & MACSEC_TCI_SC) { if (!pulled_sci) goto drop_direct; } /* ethernet header is part of crypto processing */ skb_push(skb, ETH_HLEN); macsec_skb_cb(skb)->has_sci = !!(hdr->tci_an & MACSEC_TCI_SC); macsec_skb_cb(skb)->assoc_num = hdr->tci_an & MACSEC_AN_MASK; sci = macsec_frame_sci(hdr, macsec_skb_cb(skb)->has_sci); rcu_read_lock(); rxd = macsec_data_rcu(skb->dev); list_for_each_entry_rcu(macsec, &rxd->secys, secys) { struct macsec_rx_sc *sc = find_rx_sc(&macsec->secy, sci); sc = sc ? macsec_rxsc_get(sc) : NULL; if (sc) { secy = &macsec->secy; rx_sc = sc; break; } } if (!secy) goto nosci; dev = secy->netdev; macsec = macsec_priv(dev); secy_stats = this_cpu_ptr(macsec->stats); rxsc_stats = this_cpu_ptr(rx_sc->stats); if (!macsec_validate_skb(skb, secy->icv_len, secy->xpn)) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsBadTag++; u64_stats_update_end(&secy_stats->syncp); goto drop_nosa; } rx_sa = macsec_rxsa_get(rx_sc->sa[macsec_skb_cb(skb)->assoc_num]); if (!rx_sa) { /* 10.6.1 if the SA is not in use */ /* If validateFrames is Strict or the C bit in the * SecTAG is set, discard */ if (hdr->tci_an & MACSEC_TCI_C || secy->validate_frames == MACSEC_VALIDATE_STRICT) { u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsNotUsingSA++; u64_stats_update_end(&rxsc_stats->syncp); goto drop_nosa; } /* not Strict, the frame (with the SecTAG and ICV * removed) is delivered to the Controlled Port. */ u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsUnusedSA++; u64_stats_update_end(&rxsc_stats->syncp); goto deliver; } /* First, PN check to avoid decrypting obviously wrong packets */ hdr_pn = ntohl(hdr->packet_number); if (secy->replay_protect) { bool late; spin_lock(&rx_sa->lock); late = rx_sa->next_pn_halves.lower >= secy->replay_window && hdr_pn < (rx_sa->next_pn_halves.lower - secy->replay_window); if (secy->xpn) late = late && pn_same_half(rx_sa->next_pn_halves.lower, hdr_pn); spin_unlock(&rx_sa->lock); if (late) { u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); goto drop; } } macsec_skb_cb(skb)->rx_sa = rx_sa; /* Disabled && !changed text => skip validation */ if (hdr->tci_an & MACSEC_TCI_C || secy->validate_frames != MACSEC_VALIDATE_DISABLED) skb = macsec_decrypt(skb, dev, rx_sa, sci, secy); if (IS_ERR(skb)) { /* the decrypt callback needs the reference */ if (PTR_ERR(skb) != -EINPROGRESS) { macsec_rxsa_put(rx_sa); macsec_rxsc_put(rx_sc); } rcu_read_unlock(); *pskb = NULL; return RX_HANDLER_CONSUMED; } if (!macsec_post_decrypt(skb, secy, hdr_pn)) goto drop; deliver: macsec_finalize_skb(skb, secy->icv_len, macsec_extra_len(macsec_skb_cb(skb)->has_sci)); macsec_reset_skb(skb, secy->netdev); if (rx_sa) macsec_rxsa_put(rx_sa); macsec_rxsc_put(rx_sc); skb_orphan(skb); len = skb->len; ret = gro_cells_receive(&macsec->gro_cells, skb); if (ret == NET_RX_SUCCESS) count_rx(dev, len); else macsec->secy.netdev->stats.rx_dropped++; rcu_read_unlock(); *pskb = NULL; return RX_HANDLER_CONSUMED; drop: macsec_rxsa_put(rx_sa); drop_nosa: macsec_rxsc_put(rx_sc); rcu_read_unlock(); drop_direct: kfree_skb(skb); *pskb = NULL; return RX_HANDLER_CONSUMED; nosci: /* 10.6.1 if the SC is not found */ cbit = !!(hdr->tci_an & MACSEC_TCI_C); if (!cbit) macsec_finalize_skb(skb, DEFAULT_ICV_LEN, macsec_extra_len(macsec_skb_cb(skb)->has_sci)); list_for_each_entry_rcu(macsec, &rxd->secys, secys) { struct sk_buff *nskb; secy_stats = this_cpu_ptr(macsec->stats); /* If validateFrames is Strict or the C bit in the * SecTAG is set, discard */ if (cbit || macsec->secy.validate_frames == MACSEC_VALIDATE_STRICT) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoSCI++; u64_stats_update_end(&secy_stats->syncp); continue; } /* not strict, the frame (with the SecTAG and ICV * removed) is delivered to the Controlled Port. */ nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) break; macsec_reset_skb(nskb, macsec->secy.netdev); ret = netif_rx(nskb); if (ret == NET_RX_SUCCESS) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsUnknownSCI++; u64_stats_update_end(&secy_stats->syncp); } else { macsec->secy.netdev->stats.rx_dropped++; } } rcu_read_unlock(); *pskb = skb; return RX_HANDLER_PASS; } static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len) { struct crypto_aead *tfm; int ret; tfm = crypto_alloc_aead("gcm(aes)", 0, 0); if (IS_ERR(tfm)) return tfm; ret = crypto_aead_setkey(tfm, key, key_len); if (ret < 0) goto fail; ret = crypto_aead_setauthsize(tfm, icv_len); if (ret < 0) goto fail; return tfm; fail: crypto_free_aead(tfm); return ERR_PTR(ret); } static int init_rx_sa(struct macsec_rx_sa *rx_sa, char *sak, int key_len, int icv_len) { rx_sa->stats = alloc_percpu(struct macsec_rx_sa_stats); if (!rx_sa->stats) return -ENOMEM; rx_sa->key.tfm = macsec_alloc_tfm(sak, key_len, icv_len); if (IS_ERR(rx_sa->key.tfm)) { free_percpu(rx_sa->stats); return PTR_ERR(rx_sa->key.tfm); } rx_sa->ssci = MACSEC_UNDEF_SSCI; rx_sa->active = false; rx_sa->next_pn = 1; refcount_set(&rx_sa->refcnt, 1); spin_lock_init(&rx_sa->lock); return 0; } static void clear_rx_sa(struct macsec_rx_sa *rx_sa) { rx_sa->active = false; macsec_rxsa_put(rx_sa); } static void free_rx_sc(struct macsec_rx_sc *rx_sc) { int i; for (i = 0; i < MACSEC_NUM_AN; i++) { struct macsec_rx_sa *sa = rtnl_dereference(rx_sc->sa[i]); RCU_INIT_POINTER(rx_sc->sa[i], NULL); if (sa) clear_rx_sa(sa); } macsec_rxsc_put(rx_sc); } static struct macsec_rx_sc *del_rx_sc(struct macsec_secy *secy, sci_t sci) { struct macsec_rx_sc *rx_sc, __rcu **rx_scp; for (rx_scp = &secy->rx_sc, rx_sc = rtnl_dereference(*rx_scp); rx_sc; rx_scp = &rx_sc->next, rx_sc = rtnl_dereference(*rx_scp)) { if (rx_sc->sci == sci) { if (rx_sc->active) secy->n_rx_sc--; rcu_assign_pointer(*rx_scp, rx_sc->next); return rx_sc; } } return NULL; } static struct macsec_rx_sc *create_rx_sc(struct net_device *dev, sci_t sci, bool active) { struct macsec_rx_sc *rx_sc; struct macsec_dev *macsec; struct net_device *real_dev = macsec_priv(dev)->real_dev; struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); struct macsec_secy *secy; list_for_each_entry(macsec, &rxd->secys, secys) { if (find_rx_sc_rtnl(&macsec->secy, sci)) return ERR_PTR(-EEXIST); } rx_sc = kzalloc(sizeof(*rx_sc), GFP_KERNEL); if (!rx_sc) return ERR_PTR(-ENOMEM); rx_sc->stats = netdev_alloc_pcpu_stats(struct pcpu_rx_sc_stats); if (!rx_sc->stats) { kfree(rx_sc); return ERR_PTR(-ENOMEM); } rx_sc->sci = sci; rx_sc->active = active; refcount_set(&rx_sc->refcnt, 1); secy = &macsec_priv(dev)->secy; rcu_assign_pointer(rx_sc->next, secy->rx_sc); rcu_assign_pointer(secy->rx_sc, rx_sc); if (rx_sc->active) secy->n_rx_sc++; return rx_sc; } static int init_tx_sa(struct macsec_tx_sa *tx_sa, char *sak, int key_len, int icv_len) { tx_sa->stats = alloc_percpu(struct macsec_tx_sa_stats); if (!tx_sa->stats) return -ENOMEM; tx_sa->key.tfm = macsec_alloc_tfm(sak, key_len, icv_len); if (IS_ERR(tx_sa->key.tfm)) { free_percpu(tx_sa->stats); return PTR_ERR(tx_sa->key.tfm); } tx_sa->ssci = MACSEC_UNDEF_SSCI; tx_sa->active = false; refcount_set(&tx_sa->refcnt, 1); spin_lock_init(&tx_sa->lock); return 0; } static void clear_tx_sa(struct macsec_tx_sa *tx_sa) { tx_sa->active = false; macsec_txsa_put(tx_sa); } static struct genl_family macsec_fam; static struct net_device *get_dev_from_nl(struct net *net, struct nlattr **attrs) { int ifindex = nla_get_u32(attrs[MACSEC_ATTR_IFINDEX]); struct net_device *dev; dev = __dev_get_by_index(net, ifindex); if (!dev) return ERR_PTR(-ENODEV); if (!netif_is_macsec(dev)) return ERR_PTR(-ENODEV); return dev; } static enum macsec_offload nla_get_offload(const struct nlattr *nla) { return (__force enum macsec_offload)nla_get_u8(nla); } static sci_t nla_get_sci(const struct nlattr *nla) { return (__force sci_t)nla_get_u64(nla); } static int nla_put_sci(struct sk_buff *skb, int attrtype, sci_t value, int padattr) { return nla_put_u64_64bit(skb, attrtype, (__force u64)value, padattr); } static ssci_t nla_get_ssci(const struct nlattr *nla) { return (__force ssci_t)nla_get_u32(nla); } static int nla_put_ssci(struct sk_buff *skb, int attrtype, ssci_t value) { return nla_put_u32(skb, attrtype, (__force u64)value); } static struct macsec_tx_sa *get_txsa_from_nl(struct net *net, struct nlattr **attrs, struct nlattr **tb_sa, struct net_device **devp, struct macsec_secy **secyp, struct macsec_tx_sc **scp, u8 *assoc_num) { struct net_device *dev; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; if (!tb_sa[MACSEC_SA_ATTR_AN]) return ERR_PTR(-EINVAL); *assoc_num = nla_get_u8(tb_sa[MACSEC_SA_ATTR_AN]); dev = get_dev_from_nl(net, attrs); if (IS_ERR(dev)) return ERR_CAST(dev); if (*assoc_num >= MACSEC_NUM_AN) return ERR_PTR(-EINVAL); secy = &macsec_priv(dev)->secy; tx_sc = &secy->tx_sc; tx_sa = rtnl_dereference(tx_sc->sa[*assoc_num]); if (!tx_sa) return ERR_PTR(-ENODEV); *devp = dev; *scp = tx_sc; *secyp = secy; return tx_sa; } static struct macsec_rx_sc *get_rxsc_from_nl(struct net *net, struct nlattr **attrs, struct nlattr **tb_rxsc, struct net_device **devp, struct macsec_secy **secyp) { struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; sci_t sci; dev = get_dev_from_nl(net, attrs); if (IS_ERR(dev)) return ERR_CAST(dev); secy = &macsec_priv(dev)->secy; if (!tb_rxsc[MACSEC_RXSC_ATTR_SCI]) return ERR_PTR(-EINVAL); sci = nla_get_sci(tb_rxsc[MACSEC_RXSC_ATTR_SCI]); rx_sc = find_rx_sc_rtnl(secy, sci); if (!rx_sc) return ERR_PTR(-ENODEV); *secyp = secy; *devp = dev; return rx_sc; } static struct macsec_rx_sa *get_rxsa_from_nl(struct net *net, struct nlattr **attrs, struct nlattr **tb_rxsc, struct nlattr **tb_sa, struct net_device **devp, struct macsec_secy **secyp, struct macsec_rx_sc **scp, u8 *assoc_num) { struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; if (!tb_sa[MACSEC_SA_ATTR_AN]) return ERR_PTR(-EINVAL); *assoc_num = nla_get_u8(tb_sa[MACSEC_SA_ATTR_AN]); if (*assoc_num >= MACSEC_NUM_AN) return ERR_PTR(-EINVAL); rx_sc = get_rxsc_from_nl(net, attrs, tb_rxsc, devp, secyp); if (IS_ERR(rx_sc)) return ERR_CAST(rx_sc); rx_sa = rtnl_dereference(rx_sc->sa[*assoc_num]); if (!rx_sa) return ERR_PTR(-ENODEV); *scp = rx_sc; return rx_sa; } static const struct nla_policy macsec_genl_policy[NUM_MACSEC_ATTR] = { [MACSEC_ATTR_IFINDEX] = { .type = NLA_U32 }, [MACSEC_ATTR_RXSC_CONFIG] = { .type = NLA_NESTED }, [MACSEC_ATTR_SA_CONFIG] = { .type = NLA_NESTED }, [MACSEC_ATTR_OFFLOAD] = { .type = NLA_NESTED }, }; static const struct nla_policy macsec_genl_rxsc_policy[NUM_MACSEC_RXSC_ATTR] = { [MACSEC_RXSC_ATTR_SCI] = { .type = NLA_U64 }, [MACSEC_RXSC_ATTR_ACTIVE] = { .type = NLA_U8 }, }; static const struct nla_policy macsec_genl_sa_policy[NUM_MACSEC_SA_ATTR] = { [MACSEC_SA_ATTR_AN] = { .type = NLA_U8 }, [MACSEC_SA_ATTR_ACTIVE] = { .type = NLA_U8 }, [MACSEC_SA_ATTR_PN] = NLA_POLICY_MIN_LEN(4), [MACSEC_SA_ATTR_KEYID] = { .type = NLA_BINARY, .len = MACSEC_KEYID_LEN, }, [MACSEC_SA_ATTR_KEY] = { .type = NLA_BINARY, .len = MACSEC_MAX_KEY_LEN, }, [MACSEC_SA_ATTR_SSCI] = { .type = NLA_U32 }, [MACSEC_SA_ATTR_SALT] = { .type = NLA_BINARY, .len = MACSEC_SALT_LEN, }, }; static const struct nla_policy macsec_genl_offload_policy[NUM_MACSEC_OFFLOAD_ATTR] = { [MACSEC_OFFLOAD_ATTR_TYPE] = { .type = NLA_U8 }, }; /* Offloads an operation to a device driver */ static int macsec_offload(int (* const func)(struct macsec_context *), struct macsec_context *ctx) { int ret; if (unlikely(!func)) return 0; if (ctx->offload == MACSEC_OFFLOAD_PHY) mutex_lock(&ctx->phydev->lock); /* Phase I: prepare. The drive should fail here if there are going to be * issues in the commit phase. */ ctx->prepare = true; ret = (*func)(ctx); if (ret) goto phy_unlock; /* Phase II: commit. This step cannot fail. */ ctx->prepare = false; ret = (*func)(ctx); /* This should never happen: commit is not allowed to fail */ if (unlikely(ret)) WARN(1, "MACsec offloading commit failed (%d)\n", ret); phy_unlock: if (ctx->offload == MACSEC_OFFLOAD_PHY) mutex_unlock(&ctx->phydev->lock); return ret; } static int parse_sa_config(struct nlattr **attrs, struct nlattr **tb_sa) { if (!attrs[MACSEC_ATTR_SA_CONFIG]) return -EINVAL; if (nla_parse_nested_deprecated(tb_sa, MACSEC_SA_ATTR_MAX, attrs[MACSEC_ATTR_SA_CONFIG], macsec_genl_sa_policy, NULL)) return -EINVAL; return 0; } static int parse_rxsc_config(struct nlattr **attrs, struct nlattr **tb_rxsc) { if (!attrs[MACSEC_ATTR_RXSC_CONFIG]) return -EINVAL; if (nla_parse_nested_deprecated(tb_rxsc, MACSEC_RXSC_ATTR_MAX, attrs[MACSEC_ATTR_RXSC_CONFIG], macsec_genl_rxsc_policy, NULL)) return -EINVAL; return 0; } static bool validate_add_rxsa(struct nlattr **attrs) { if (!attrs[MACSEC_SA_ATTR_AN] || !attrs[MACSEC_SA_ATTR_KEY] || !attrs[MACSEC_SA_ATTR_KEYID]) return false; if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN) return false; if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0) return false; if (attrs[MACSEC_SA_ATTR_ACTIVE]) { if (nla_get_u8(attrs[MACSEC_SA_ATTR_ACTIVE]) > 1) return false; } if (nla_len(attrs[MACSEC_SA_ATTR_KEYID]) != MACSEC_KEYID_LEN) return false; return true; } static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; struct nlattr **attrs = info->attrs; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; unsigned char assoc_num; int pn_len; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; int err; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (!validate_add_rxsa(tb_sa)) return -EINVAL; rtnl_lock(); rx_sc = get_rxsc_from_nl(genl_info_net(info), attrs, tb_rxsc, &dev, &secy); if (IS_ERR(rx_sc)) { rtnl_unlock(); return PTR_ERR(rx_sc); } assoc_num = nla_get_u8(tb_sa[MACSEC_SA_ATTR_AN]); if (nla_len(tb_sa[MACSEC_SA_ATTR_KEY]) != secy->key_len) { pr_notice("macsec: nl: add_rxsa: bad key length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len); rtnl_unlock(); return -EINVAL; } pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN; if (tb_sa[MACSEC_SA_ATTR_PN] && nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { pr_notice("macsec: nl: add_rxsa: bad pn length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len); rtnl_unlock(); return -EINVAL; } if (secy->xpn) { if (!tb_sa[MACSEC_SA_ATTR_SSCI] || !tb_sa[MACSEC_SA_ATTR_SALT]) { rtnl_unlock(); return -EINVAL; } if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) { pr_notice("macsec: nl: add_rxsa: bad salt length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_SALT]), MACSEC_SALT_LEN); rtnl_unlock(); return -EINVAL; } } rx_sa = rtnl_dereference(rx_sc->sa[assoc_num]); if (rx_sa) { rtnl_unlock(); return -EBUSY; } rx_sa = kmalloc(sizeof(*rx_sa), GFP_KERNEL); if (!rx_sa) { rtnl_unlock(); return -ENOMEM; } err = init_rx_sa(rx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, secy->icv_len); if (err < 0) { kfree(rx_sa); rtnl_unlock(); return err; } if (tb_sa[MACSEC_SA_ATTR_PN]) { spin_lock_bh(&rx_sa->lock); rx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&rx_sa->lock); } if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) rx_sa->active = !!nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]); rx_sa->sc = rx_sc; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { err = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.rx_sa = rx_sa; ctx.secy = secy; memcpy(ctx.sa.key, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len); err = macsec_offload(ops->mdo_add_rxsa, &ctx); memzero_explicit(ctx.sa.key, secy->key_len); if (err) goto cleanup; } if (secy->xpn) { rx_sa->ssci = nla_get_ssci(tb_sa[MACSEC_SA_ATTR_SSCI]); nla_memcpy(rx_sa->key.salt.bytes, tb_sa[MACSEC_SA_ATTR_SALT], MACSEC_SALT_LEN); } nla_memcpy(rx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEYID], MACSEC_KEYID_LEN); rcu_assign_pointer(rx_sc->sa[assoc_num], rx_sa); rtnl_unlock(); return 0; cleanup: macsec_rxsa_put(rx_sa); rtnl_unlock(); return err; } static bool validate_add_rxsc(struct nlattr **attrs) { if (!attrs[MACSEC_RXSC_ATTR_SCI]) return false; if (attrs[MACSEC_RXSC_ATTR_ACTIVE]) { if (nla_get_u8(attrs[MACSEC_RXSC_ATTR_ACTIVE]) > 1) return false; } return true; } static int macsec_add_rxsc(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; sci_t sci = MACSEC_UNDEF_SCI; struct nlattr **attrs = info->attrs; struct macsec_rx_sc *rx_sc; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct macsec_secy *secy; bool active = true; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (!validate_add_rxsc(tb_rxsc)) return -EINVAL; rtnl_lock(); dev = get_dev_from_nl(genl_info_net(info), attrs); if (IS_ERR(dev)) { rtnl_unlock(); return PTR_ERR(dev); } secy = &macsec_priv(dev)->secy; sci = nla_get_sci(tb_rxsc[MACSEC_RXSC_ATTR_SCI]); if (tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]) active = nla_get_u8(tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]); rx_sc = create_rx_sc(dev, sci, active); if (IS_ERR(rx_sc)) { rtnl_unlock(); return PTR_ERR(rx_sc); } if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.rx_sc = rx_sc; ctx.secy = secy; ret = macsec_offload(ops->mdo_add_rxsc, &ctx); if (ret) goto cleanup; } rtnl_unlock(); return 0; cleanup: del_rx_sc(secy, sci); free_rx_sc(rx_sc); rtnl_unlock(); return ret; } static bool validate_add_txsa(struct nlattr **attrs) { if (!attrs[MACSEC_SA_ATTR_AN] || !attrs[MACSEC_SA_ATTR_PN] || !attrs[MACSEC_SA_ATTR_KEY] || !attrs[MACSEC_SA_ATTR_KEYID]) return false; if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN) return false; if (nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0) return false; if (attrs[MACSEC_SA_ATTR_ACTIVE]) { if (nla_get_u8(attrs[MACSEC_SA_ATTR_ACTIVE]) > 1) return false; } if (nla_len(attrs[MACSEC_SA_ATTR_KEYID]) != MACSEC_KEYID_LEN) return false; return true; } static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; struct nlattr **attrs = info->attrs; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; unsigned char assoc_num; int pn_len; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; bool was_operational; int err; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (!validate_add_txsa(tb_sa)) return -EINVAL; rtnl_lock(); dev = get_dev_from_nl(genl_info_net(info), attrs); if (IS_ERR(dev)) { rtnl_unlock(); return PTR_ERR(dev); } secy = &macsec_priv(dev)->secy; tx_sc = &secy->tx_sc; assoc_num = nla_get_u8(tb_sa[MACSEC_SA_ATTR_AN]); if (nla_len(tb_sa[MACSEC_SA_ATTR_KEY]) != secy->key_len) { pr_notice("macsec: nl: add_txsa: bad key length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len); rtnl_unlock(); return -EINVAL; } pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN; if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { pr_notice("macsec: nl: add_txsa: bad pn length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len); rtnl_unlock(); return -EINVAL; } if (secy->xpn) { if (!tb_sa[MACSEC_SA_ATTR_SSCI] || !tb_sa[MACSEC_SA_ATTR_SALT]) { rtnl_unlock(); return -EINVAL; } if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) { pr_notice("macsec: nl: add_txsa: bad salt length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_SALT]), MACSEC_SALT_LEN); rtnl_unlock(); return -EINVAL; } } tx_sa = rtnl_dereference(tx_sc->sa[assoc_num]); if (tx_sa) { rtnl_unlock(); return -EBUSY; } tx_sa = kmalloc(sizeof(*tx_sa), GFP_KERNEL); if (!tx_sa) { rtnl_unlock(); return -ENOMEM; } err = init_tx_sa(tx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, secy->icv_len); if (err < 0) { kfree(tx_sa); rtnl_unlock(); return err; } spin_lock_bh(&tx_sa->lock); tx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&tx_sa->lock); if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) tx_sa->active = !!nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]); was_operational = secy->operational; if (assoc_num == tx_sc->encoding_sa && tx_sa->active) secy->operational = true; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { err = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.tx_sa = tx_sa; ctx.secy = secy; memcpy(ctx.sa.key, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len); err = macsec_offload(ops->mdo_add_txsa, &ctx); memzero_explicit(ctx.sa.key, secy->key_len); if (err) goto cleanup; } if (secy->xpn) { tx_sa->ssci = nla_get_ssci(tb_sa[MACSEC_SA_ATTR_SSCI]); nla_memcpy(tx_sa->key.salt.bytes, tb_sa[MACSEC_SA_ATTR_SALT], MACSEC_SALT_LEN); } nla_memcpy(tx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEYID], MACSEC_KEYID_LEN); rcu_assign_pointer(tx_sc->sa[assoc_num], tx_sa); rtnl_unlock(); return 0; cleanup: secy->operational = was_operational; macsec_txsa_put(tx_sa); rtnl_unlock(); return err; } static int macsec_del_rxsa(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; u8 assoc_num; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; rtnl_lock(); rx_sa = get_rxsa_from_nl(genl_info_net(info), attrs, tb_rxsc, tb_sa, &dev, &secy, &rx_sc, &assoc_num); if (IS_ERR(rx_sa)) { rtnl_unlock(); return PTR_ERR(rx_sa); } if (rx_sa->active) { rtnl_unlock(); return -EBUSY; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.rx_sa = rx_sa; ctx.secy = secy; ret = macsec_offload(ops->mdo_del_rxsa, &ctx); if (ret) goto cleanup; } RCU_INIT_POINTER(rx_sc->sa[assoc_num], NULL); clear_rx_sa(rx_sa); rtnl_unlock(); return 0; cleanup: rtnl_unlock(); return ret; } static int macsec_del_rxsc(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; sci_t sci; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (!tb_rxsc[MACSEC_RXSC_ATTR_SCI]) return -EINVAL; rtnl_lock(); dev = get_dev_from_nl(genl_info_net(info), info->attrs); if (IS_ERR(dev)) { rtnl_unlock(); return PTR_ERR(dev); } secy = &macsec_priv(dev)->secy; sci = nla_get_sci(tb_rxsc[MACSEC_RXSC_ATTR_SCI]); rx_sc = del_rx_sc(secy, sci); if (!rx_sc) { rtnl_unlock(); return -ENODEV; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.rx_sc = rx_sc; ctx.secy = secy; ret = macsec_offload(ops->mdo_del_rxsc, &ctx); if (ret) goto cleanup; } free_rx_sc(rx_sc); rtnl_unlock(); return 0; cleanup: rtnl_unlock(); return ret; } static int macsec_del_txsa(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; u8 assoc_num; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; rtnl_lock(); tx_sa = get_txsa_from_nl(genl_info_net(info), attrs, tb_sa, &dev, &secy, &tx_sc, &assoc_num); if (IS_ERR(tx_sa)) { rtnl_unlock(); return PTR_ERR(tx_sa); } if (tx_sa->active) { rtnl_unlock(); return -EBUSY; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.tx_sa = tx_sa; ctx.secy = secy; ret = macsec_offload(ops->mdo_del_txsa, &ctx); if (ret) goto cleanup; } RCU_INIT_POINTER(tx_sc->sa[assoc_num], NULL); clear_tx_sa(tx_sa); rtnl_unlock(); return 0; cleanup: rtnl_unlock(); return ret; } static bool validate_upd_sa(struct nlattr **attrs) { if (!attrs[MACSEC_SA_ATTR_AN] || attrs[MACSEC_SA_ATTR_KEY] || attrs[MACSEC_SA_ATTR_KEYID] || attrs[MACSEC_SA_ATTR_SSCI] || attrs[MACSEC_SA_ATTR_SALT]) return false; if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN) return false; if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0) return false; if (attrs[MACSEC_SA_ATTR_ACTIVE]) { if (nla_get_u8(attrs[MACSEC_SA_ATTR_ACTIVE]) > 1) return false; } return true; } static int macsec_upd_txsa(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; u8 assoc_num; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; bool was_operational, was_active; pn_t prev_pn; int ret = 0; prev_pn.full64 = 0; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (!validate_upd_sa(tb_sa)) return -EINVAL; rtnl_lock(); tx_sa = get_txsa_from_nl(genl_info_net(info), attrs, tb_sa, &dev, &secy, &tx_sc, &assoc_num); if (IS_ERR(tx_sa)) { rtnl_unlock(); return PTR_ERR(tx_sa); } if (tb_sa[MACSEC_SA_ATTR_PN]) { int pn_len; pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN; if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { pr_notice("macsec: nl: upd_txsa: bad pn length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len); rtnl_unlock(); return -EINVAL; } spin_lock_bh(&tx_sa->lock); prev_pn = tx_sa->next_pn_halves; tx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&tx_sa->lock); } was_active = tx_sa->active; if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) tx_sa->active = nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]); was_operational = secy->operational; if (assoc_num == tx_sc->encoding_sa) secy->operational = tx_sa->active; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.tx_sa = tx_sa; ctx.secy = secy; ret = macsec_offload(ops->mdo_upd_txsa, &ctx); if (ret) goto cleanup; } rtnl_unlock(); return 0; cleanup: if (tb_sa[MACSEC_SA_ATTR_PN]) { spin_lock_bh(&tx_sa->lock); tx_sa->next_pn_halves = prev_pn; spin_unlock_bh(&tx_sa->lock); } tx_sa->active = was_active; secy->operational = was_operational; rtnl_unlock(); return ret; } static int macsec_upd_rxsa(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; u8 assoc_num; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; bool was_active; pn_t prev_pn; int ret = 0; prev_pn.full64 = 0; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (!validate_upd_sa(tb_sa)) return -EINVAL; rtnl_lock(); rx_sa = get_rxsa_from_nl(genl_info_net(info), attrs, tb_rxsc, tb_sa, &dev, &secy, &rx_sc, &assoc_num); if (IS_ERR(rx_sa)) { rtnl_unlock(); return PTR_ERR(rx_sa); } if (tb_sa[MACSEC_SA_ATTR_PN]) { int pn_len; pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN; if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { pr_notice("macsec: nl: upd_rxsa: bad pn length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len); rtnl_unlock(); return -EINVAL; } spin_lock_bh(&rx_sa->lock); prev_pn = rx_sa->next_pn_halves; rx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&rx_sa->lock); } was_active = rx_sa->active; if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) rx_sa->active = nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]); /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.rx_sa = rx_sa; ctx.secy = secy; ret = macsec_offload(ops->mdo_upd_rxsa, &ctx); if (ret) goto cleanup; } rtnl_unlock(); return 0; cleanup: if (tb_sa[MACSEC_SA_ATTR_PN]) { spin_lock_bh(&rx_sa->lock); rx_sa->next_pn_halves = prev_pn; spin_unlock_bh(&rx_sa->lock); } rx_sa->active = was_active; rtnl_unlock(); return ret; } static int macsec_upd_rxsc(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; unsigned int prev_n_rx_sc; bool was_active; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (!validate_add_rxsc(tb_rxsc)) return -EINVAL; rtnl_lock(); rx_sc = get_rxsc_from_nl(genl_info_net(info), attrs, tb_rxsc, &dev, &secy); if (IS_ERR(rx_sc)) { rtnl_unlock(); return PTR_ERR(rx_sc); } was_active = rx_sc->active; prev_n_rx_sc = secy->n_rx_sc; if (tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]) { bool new = !!nla_get_u8(tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]); if (rx_sc->active != new) secy->n_rx_sc += new ? 1 : -1; rx_sc->active = new; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.rx_sc = rx_sc; ctx.secy = secy; ret = macsec_offload(ops->mdo_upd_rxsc, &ctx); if (ret) goto cleanup; } rtnl_unlock(); return 0; cleanup: secy->n_rx_sc = prev_n_rx_sc; rx_sc->active = was_active; rtnl_unlock(); return ret; } static bool macsec_is_configured(struct macsec_dev *macsec) { struct macsec_secy *secy = &macsec->secy; struct macsec_tx_sc *tx_sc = &secy->tx_sc; int i; if (secy->rx_sc) return true; for (i = 0; i < MACSEC_NUM_AN; i++) if (tx_sc->sa[i]) return true; return false; } static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb_offload[MACSEC_OFFLOAD_ATTR_MAX + 1]; enum macsec_offload offload, prev_offload; int (*func)(struct macsec_context *ctx); struct nlattr **attrs = info->attrs; struct net_device *dev; const struct macsec_ops *ops; struct macsec_context ctx; struct macsec_dev *macsec; int ret = 0; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (!attrs[MACSEC_ATTR_OFFLOAD]) return -EINVAL; if (nla_parse_nested_deprecated(tb_offload, MACSEC_OFFLOAD_ATTR_MAX, attrs[MACSEC_ATTR_OFFLOAD], macsec_genl_offload_policy, NULL)) return -EINVAL; rtnl_lock(); dev = get_dev_from_nl(genl_info_net(info), attrs); if (IS_ERR(dev)) { ret = PTR_ERR(dev); goto out; } macsec = macsec_priv(dev); if (!tb_offload[MACSEC_OFFLOAD_ATTR_TYPE]) { ret = -EINVAL; goto out; } offload = nla_get_u8(tb_offload[MACSEC_OFFLOAD_ATTR_TYPE]); if (macsec->offload == offload) goto out; /* Check if the offloading mode is supported by the underlying layers */ if (offload != MACSEC_OFFLOAD_OFF && !macsec_check_offload(offload, macsec)) { ret = -EOPNOTSUPP; goto out; } /* Check if the net device is busy. */ if (netif_running(dev)) { ret = -EBUSY; goto out; } prev_offload = macsec->offload; macsec->offload = offload; /* Check if the device already has rules configured: we do not support * rules migration. */ if (macsec_is_configured(macsec)) { ret = -EBUSY; goto rollback; } ops = __macsec_get_ops(offload == MACSEC_OFFLOAD_OFF ? prev_offload : offload, macsec, &ctx); if (!ops) { ret = -EOPNOTSUPP; goto rollback; } if (prev_offload == MACSEC_OFFLOAD_OFF) func = ops->mdo_add_secy; else func = ops->mdo_del_secy; ctx.secy = &macsec->secy; ret = macsec_offload(func, &ctx); if (ret) goto rollback; rtnl_unlock(); return 0; rollback: macsec->offload = prev_offload; out: rtnl_unlock(); return ret; } static void get_tx_sa_stats(struct net_device *dev, int an, struct macsec_tx_sa *tx_sa, struct macsec_tx_sa_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.sa.assoc_num = an; ctx.sa.tx_sa = tx_sa; ctx.stats.tx_sa_stats = sum; ctx.secy = &macsec_priv(dev)->secy; macsec_offload(ops->mdo_get_tx_sa_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct macsec_tx_sa_stats *stats = per_cpu_ptr(tx_sa->stats, cpu); sum->OutPktsProtected += stats->OutPktsProtected; sum->OutPktsEncrypted += stats->OutPktsEncrypted; } } static int copy_tx_sa_stats(struct sk_buff *skb, struct macsec_tx_sa_stats *sum) { if (nla_put_u32(skb, MACSEC_SA_STATS_ATTR_OUT_PKTS_PROTECTED, sum->OutPktsProtected) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_OUT_PKTS_ENCRYPTED, sum->OutPktsEncrypted)) return -EMSGSIZE; return 0; } static void get_rx_sa_stats(struct net_device *dev, struct macsec_rx_sc *rx_sc, int an, struct macsec_rx_sa *rx_sa, struct macsec_rx_sa_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.sa.assoc_num = an; ctx.sa.rx_sa = rx_sa; ctx.stats.rx_sa_stats = sum; ctx.secy = &macsec_priv(dev)->secy; ctx.rx_sc = rx_sc; macsec_offload(ops->mdo_get_rx_sa_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct macsec_rx_sa_stats *stats = per_cpu_ptr(rx_sa->stats, cpu); sum->InPktsOK += stats->InPktsOK; sum->InPktsInvalid += stats->InPktsInvalid; sum->InPktsNotValid += stats->InPktsNotValid; sum->InPktsNotUsingSA += stats->InPktsNotUsingSA; sum->InPktsUnusedSA += stats->InPktsUnusedSA; } } static int copy_rx_sa_stats(struct sk_buff *skb, struct macsec_rx_sa_stats *sum) { if (nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_OK, sum->InPktsOK) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_INVALID, sum->InPktsInvalid) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_NOT_VALID, sum->InPktsNotValid) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_NOT_USING_SA, sum->InPktsNotUsingSA) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_UNUSED_SA, sum->InPktsUnusedSA)) return -EMSGSIZE; return 0; } static void get_rx_sc_stats(struct net_device *dev, struct macsec_rx_sc *rx_sc, struct macsec_rx_sc_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.stats.rx_sc_stats = sum; ctx.secy = &macsec_priv(dev)->secy; ctx.rx_sc = rx_sc; macsec_offload(ops->mdo_get_rx_sc_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct pcpu_rx_sc_stats *stats; struct macsec_rx_sc_stats tmp; unsigned int start; stats = per_cpu_ptr(rx_sc->stats, cpu); do { start = u64_stats_fetch_begin_irq(&stats->syncp); memcpy(&tmp, &stats->stats, sizeof(tmp)); } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); sum->InOctetsValidated += tmp.InOctetsValidated; sum->InOctetsDecrypted += tmp.InOctetsDecrypted; sum->InPktsUnchecked += tmp.InPktsUnchecked; sum->InPktsDelayed += tmp.InPktsDelayed; sum->InPktsOK += tmp.InPktsOK; sum->InPktsInvalid += tmp.InPktsInvalid; sum->InPktsLate += tmp.InPktsLate; sum->InPktsNotValid += tmp.InPktsNotValid; sum->InPktsNotUsingSA += tmp.InPktsNotUsingSA; sum->InPktsUnusedSA += tmp.InPktsUnusedSA; } } static int copy_rx_sc_stats(struct sk_buff *skb, struct macsec_rx_sc_stats *sum) { if (nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_OCTETS_VALIDATED, sum->InOctetsValidated, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_OCTETS_DECRYPTED, sum->InOctetsDecrypted, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_UNCHECKED, sum->InPktsUnchecked, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_DELAYED, sum->InPktsDelayed, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_OK, sum->InPktsOK, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_INVALID, sum->InPktsInvalid, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_LATE, sum->InPktsLate, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_NOT_VALID, sum->InPktsNotValid, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_NOT_USING_SA, sum->InPktsNotUsingSA, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_UNUSED_SA, sum->InPktsUnusedSA, MACSEC_RXSC_STATS_ATTR_PAD)) return -EMSGSIZE; return 0; } static void get_tx_sc_stats(struct net_device *dev, struct macsec_tx_sc_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.stats.tx_sc_stats = sum; ctx.secy = &macsec_priv(dev)->secy; macsec_offload(ops->mdo_get_tx_sc_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct pcpu_tx_sc_stats *stats; struct macsec_tx_sc_stats tmp; unsigned int start; stats = per_cpu_ptr(macsec_priv(dev)->secy.tx_sc.stats, cpu); do { start = u64_stats_fetch_begin_irq(&stats->syncp); memcpy(&tmp, &stats->stats, sizeof(tmp)); } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); sum->OutPktsProtected += tmp.OutPktsProtected; sum->OutPktsEncrypted += tmp.OutPktsEncrypted; sum->OutOctetsProtected += tmp.OutOctetsProtected; sum->OutOctetsEncrypted += tmp.OutOctetsEncrypted; } } static int copy_tx_sc_stats(struct sk_buff *skb, struct macsec_tx_sc_stats *sum) { if (nla_put_u64_64bit(skb, MACSEC_TXSC_STATS_ATTR_OUT_PKTS_PROTECTED, sum->OutPktsProtected, MACSEC_TXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_TXSC_STATS_ATTR_OUT_PKTS_ENCRYPTED, sum->OutPktsEncrypted, MACSEC_TXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_TXSC_STATS_ATTR_OUT_OCTETS_PROTECTED, sum->OutOctetsProtected, MACSEC_TXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_TXSC_STATS_ATTR_OUT_OCTETS_ENCRYPTED, sum->OutOctetsEncrypted, MACSEC_TXSC_STATS_ATTR_PAD)) return -EMSGSIZE; return 0; } static void get_secy_stats(struct net_device *dev, struct macsec_dev_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.stats.dev_stats = sum; ctx.secy = &macsec_priv(dev)->secy; macsec_offload(ops->mdo_get_dev_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct pcpu_secy_stats *stats; struct macsec_dev_stats tmp; unsigned int start; stats = per_cpu_ptr(macsec_priv(dev)->stats, cpu); do { start = u64_stats_fetch_begin_irq(&stats->syncp); memcpy(&tmp, &stats->stats, sizeof(tmp)); } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); sum->OutPktsUntagged += tmp.OutPktsUntagged; sum->InPktsUntagged += tmp.InPktsUntagged; sum->OutPktsTooLong += tmp.OutPktsTooLong; sum->InPktsNoTag += tmp.InPktsNoTag; sum->InPktsBadTag += tmp.InPktsBadTag; sum->InPktsUnknownSCI += tmp.InPktsUnknownSCI; sum->InPktsNoSCI += tmp.InPktsNoSCI; sum->InPktsOverrun += tmp.InPktsOverrun; } } static int copy_secy_stats(struct sk_buff *skb, struct macsec_dev_stats *sum) { if (nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_OUT_PKTS_UNTAGGED, sum->OutPktsUntagged, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_UNTAGGED, sum->InPktsUntagged, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_OUT_PKTS_TOO_LONG, sum->OutPktsTooLong, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_NO_TAG, sum->InPktsNoTag, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_BAD_TAG, sum->InPktsBadTag, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_UNKNOWN_SCI, sum->InPktsUnknownSCI, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_NO_SCI, sum->InPktsNoSCI, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_OVERRUN, sum->InPktsOverrun, MACSEC_SECY_STATS_ATTR_PAD)) return -EMSGSIZE; return 0; } static int nla_put_secy(struct macsec_secy *secy, struct sk_buff *skb) { struct macsec_tx_sc *tx_sc = &secy->tx_sc; struct nlattr *secy_nest = nla_nest_start_noflag(skb, MACSEC_ATTR_SECY); u64 csid; if (!secy_nest) return 1; switch (secy->key_len) { case MACSEC_GCM_AES_128_SAK_LEN: csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_128 : MACSEC_DEFAULT_CIPHER_ID; break; case MACSEC_GCM_AES_256_SAK_LEN: csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_256 : MACSEC_CIPHER_ID_GCM_AES_256; break; default: goto cancel; } if (nla_put_sci(skb, MACSEC_SECY_ATTR_SCI, secy->sci, MACSEC_SECY_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_ATTR_CIPHER_SUITE, csid, MACSEC_SECY_ATTR_PAD) || nla_put_u8(skb, MACSEC_SECY_ATTR_ICV_LEN, secy->icv_len) || nla_put_u8(skb, MACSEC_SECY_ATTR_OPER, secy->operational) || nla_put_u8(skb, MACSEC_SECY_ATTR_PROTECT, secy->protect_frames) || nla_put_u8(skb, MACSEC_SECY_ATTR_REPLAY, secy->replay_protect) || nla_put_u8(skb, MACSEC_SECY_ATTR_VALIDATE, secy->validate_frames) || nla_put_u8(skb, MACSEC_SECY_ATTR_ENCRYPT, tx_sc->encrypt) || nla_put_u8(skb, MACSEC_SECY_ATTR_INC_SCI, tx_sc->send_sci) || nla_put_u8(skb, MACSEC_SECY_ATTR_ES, tx_sc->end_station) || nla_put_u8(skb, MACSEC_SECY_ATTR_SCB, tx_sc->scb) || nla_put_u8(skb, MACSEC_SECY_ATTR_ENCODING_SA, tx_sc->encoding_sa)) goto cancel; if (secy->replay_protect) { if (nla_put_u32(skb, MACSEC_SECY_ATTR_WINDOW, secy->replay_window)) goto cancel; } nla_nest_end(skb, secy_nest); return 0; cancel: nla_nest_cancel(skb, secy_nest); return 1; } static noinline_for_stack int dump_secy(struct macsec_secy *secy, struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb) { struct macsec_tx_sc_stats tx_sc_stats = {0, }; struct macsec_tx_sa_stats tx_sa_stats = {0, }; struct macsec_rx_sc_stats rx_sc_stats = {0, }; struct macsec_rx_sa_stats rx_sa_stats = {0, }; struct macsec_dev *macsec = netdev_priv(dev); struct macsec_dev_stats dev_stats = {0, }; struct macsec_tx_sc *tx_sc = &secy->tx_sc; struct nlattr *txsa_list, *rxsc_list; struct macsec_rx_sc *rx_sc; struct nlattr *attr; void *hdr; int i, j; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &macsec_fam, NLM_F_MULTI, MACSEC_CMD_GET_TXSC); if (!hdr) return -EMSGSIZE; genl_dump_check_consistent(cb, hdr); if (nla_put_u32(skb, MACSEC_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; attr = nla_nest_start_noflag(skb, MACSEC_ATTR_OFFLOAD); if (!attr) goto nla_put_failure; if (nla_put_u8(skb, MACSEC_OFFLOAD_ATTR_TYPE, macsec->offload)) goto nla_put_failure; nla_nest_end(skb, attr); if (nla_put_secy(secy, skb)) goto nla_put_failure; attr = nla_nest_start_noflag(skb, MACSEC_ATTR_TXSC_STATS); if (!attr) goto nla_put_failure; get_tx_sc_stats(dev, &tx_sc_stats); if (copy_tx_sc_stats(skb, &tx_sc_stats)) { nla_nest_cancel(skb, attr); goto nla_put_failure; } nla_nest_end(skb, attr); attr = nla_nest_start_noflag(skb, MACSEC_ATTR_SECY_STATS); if (!attr) goto nla_put_failure; get_secy_stats(dev, &dev_stats); if (copy_secy_stats(skb, &dev_stats)) { nla_nest_cancel(skb, attr); goto nla_put_failure; } nla_nest_end(skb, attr); txsa_list = nla_nest_start_noflag(skb, MACSEC_ATTR_TXSA_LIST); if (!txsa_list) goto nla_put_failure; for (i = 0, j = 1; i < MACSEC_NUM_AN; i++) { struct macsec_tx_sa *tx_sa = rtnl_dereference(tx_sc->sa[i]); struct nlattr *txsa_nest; u64 pn; int pn_len; if (!tx_sa) continue; txsa_nest = nla_nest_start_noflag(skb, j++); if (!txsa_nest) { nla_nest_cancel(skb, txsa_list); goto nla_put_failure; } attr = nla_nest_start_noflag(skb, MACSEC_SA_ATTR_STATS); if (!attr) { nla_nest_cancel(skb, txsa_nest); nla_nest_cancel(skb, txsa_list); goto nla_put_failure; } memset(&tx_sa_stats, 0, sizeof(tx_sa_stats)); get_tx_sa_stats(dev, i, tx_sa, &tx_sa_stats); if (copy_tx_sa_stats(skb, &tx_sa_stats)) { nla_nest_cancel(skb, attr); nla_nest_cancel(skb, txsa_nest); nla_nest_cancel(skb, txsa_list); goto nla_put_failure; } nla_nest_end(skb, attr); if (secy->xpn) { pn = tx_sa->next_pn; pn_len = MACSEC_XPN_PN_LEN; } else { pn = tx_sa->next_pn_halves.lower; pn_len = MACSEC_DEFAULT_PN_LEN; } if (nla_put_u8(skb, MACSEC_SA_ATTR_AN, i) || nla_put(skb, MACSEC_SA_ATTR_PN, pn_len, &pn) || nla_put(skb, MACSEC_SA_ATTR_KEYID, MACSEC_KEYID_LEN, tx_sa->key.id) || (secy->xpn && nla_put_ssci(skb, MACSEC_SA_ATTR_SSCI, tx_sa->ssci)) || nla_put_u8(skb, MACSEC_SA_ATTR_ACTIVE, tx_sa->active)) { nla_nest_cancel(skb, txsa_nest); nla_nest_cancel(skb, txsa_list); goto nla_put_failure; } nla_nest_end(skb, txsa_nest); } nla_nest_end(skb, txsa_list); rxsc_list = nla_nest_start_noflag(skb, MACSEC_ATTR_RXSC_LIST); if (!rxsc_list) goto nla_put_failure; j = 1; for_each_rxsc_rtnl(secy, rx_sc) { int k; struct nlattr *rxsa_list; struct nlattr *rxsc_nest = nla_nest_start_noflag(skb, j++); if (!rxsc_nest) { nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } if (nla_put_u8(skb, MACSEC_RXSC_ATTR_ACTIVE, rx_sc->active) || nla_put_sci(skb, MACSEC_RXSC_ATTR_SCI, rx_sc->sci, MACSEC_RXSC_ATTR_PAD)) { nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } attr = nla_nest_start_noflag(skb, MACSEC_RXSC_ATTR_STATS); if (!attr) { nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } memset(&rx_sc_stats, 0, sizeof(rx_sc_stats)); get_rx_sc_stats(dev, rx_sc, &rx_sc_stats); if (copy_rx_sc_stats(skb, &rx_sc_stats)) { nla_nest_cancel(skb, attr); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } nla_nest_end(skb, attr); rxsa_list = nla_nest_start_noflag(skb, MACSEC_RXSC_ATTR_SA_LIST); if (!rxsa_list) { nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } for (i = 0, k = 1; i < MACSEC_NUM_AN; i++) { struct macsec_rx_sa *rx_sa = rtnl_dereference(rx_sc->sa[i]); struct nlattr *rxsa_nest; u64 pn; int pn_len; if (!rx_sa) continue; rxsa_nest = nla_nest_start_noflag(skb, k++); if (!rxsa_nest) { nla_nest_cancel(skb, rxsa_list); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } attr = nla_nest_start_noflag(skb, MACSEC_SA_ATTR_STATS); if (!attr) { nla_nest_cancel(skb, rxsa_list); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } memset(&rx_sa_stats, 0, sizeof(rx_sa_stats)); get_rx_sa_stats(dev, rx_sc, i, rx_sa, &rx_sa_stats); if (copy_rx_sa_stats(skb, &rx_sa_stats)) { nla_nest_cancel(skb, attr); nla_nest_cancel(skb, rxsa_list); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } nla_nest_end(skb, attr); if (secy->xpn) { pn = rx_sa->next_pn; pn_len = MACSEC_XPN_PN_LEN; } else { pn = rx_sa->next_pn_halves.lower; pn_len = MACSEC_DEFAULT_PN_LEN; } if (nla_put_u8(skb, MACSEC_SA_ATTR_AN, i) || nla_put(skb, MACSEC_SA_ATTR_PN, pn_len, &pn) || nla_put(skb, MACSEC_SA_ATTR_KEYID, MACSEC_KEYID_LEN, rx_sa->key.id) || (secy->xpn && nla_put_ssci(skb, MACSEC_SA_ATTR_SSCI, rx_sa->ssci)) || nla_put_u8(skb, MACSEC_SA_ATTR_ACTIVE, rx_sa->active)) { nla_nest_cancel(skb, rxsa_nest); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } nla_nest_end(skb, rxsa_nest); } nla_nest_end(skb, rxsa_list); nla_nest_end(skb, rxsc_nest); } nla_nest_end(skb, rxsc_list); genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int macsec_generation = 1; /* protected by RTNL */ static int macsec_dump_txsc(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct net_device *dev; int dev_idx, d; dev_idx = cb->args[0]; d = 0; rtnl_lock(); cb->seq = macsec_generation; for_each_netdev(net, dev) { struct macsec_secy *secy; if (d < dev_idx) goto next; if (!netif_is_macsec(dev)) goto next; secy = &macsec_priv(dev)->secy; if (dump_secy(secy, dev, skb, cb) < 0) goto done; next: d++; } done: rtnl_unlock(); cb->args[0] = d; return skb->len; } static const struct genl_small_ops macsec_genl_ops[] = { { .cmd = MACSEC_CMD_GET_TXSC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .dumpit = macsec_dump_txsc, }, { .cmd = MACSEC_CMD_ADD_RXSC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_add_rxsc, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_DEL_RXSC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_del_rxsc, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_RXSC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_upd_rxsc, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_ADD_TXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_add_txsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_DEL_TXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_del_txsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_TXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_upd_txsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_ADD_RXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_add_rxsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_DEL_RXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_del_rxsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_RXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_upd_rxsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_OFFLOAD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_upd_offload, .flags = GENL_ADMIN_PERM, }, }; static struct genl_family macsec_fam __ro_after_init = { .name = MACSEC_GENL_NAME, .hdrsize = 0, .version = MACSEC_GENL_VERSION, .maxattr = MACSEC_ATTR_MAX, .policy = macsec_genl_policy, .netnsok = true, .module = THIS_MODULE, .small_ops = macsec_genl_ops, .n_small_ops = ARRAY_SIZE(macsec_genl_ops), }; static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct macsec_dev *macsec = netdev_priv(dev); struct macsec_secy *secy = &macsec->secy; struct pcpu_secy_stats *secy_stats; int ret, len; if (macsec_is_offloaded(netdev_priv(dev))) { skb->dev = macsec->real_dev; return dev_queue_xmit(skb); } /* 10.5 */ if (!secy->protect_frames) { secy_stats = this_cpu_ptr(macsec->stats); u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.OutPktsUntagged++; u64_stats_update_end(&secy_stats->syncp); skb->dev = macsec->real_dev; len = skb->len; ret = dev_queue_xmit(skb); count_tx(dev, ret, len); return ret; } if (!secy->operational) { kfree_skb(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } skb = macsec_encrypt(skb, dev); if (IS_ERR(skb)) { if (PTR_ERR(skb) != -EINPROGRESS) dev->stats.tx_dropped++; return NETDEV_TX_OK; } macsec_count_tx(skb, &macsec->secy.tx_sc, macsec_skb_cb(skb)->tx_sa); macsec_encrypt_finish(skb, dev); len = skb->len; ret = dev_queue_xmit(skb); count_tx(dev, ret, len); return ret; } #define MACSEC_FEATURES \ (NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST) static int macsec_dev_init(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; int err; dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; err = gro_cells_init(&macsec->gro_cells, dev); if (err) { free_percpu(dev->tstats); return err; } dev->features = real_dev->features & MACSEC_FEATURES; dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE; dev->needed_headroom = real_dev->needed_headroom + MACSEC_NEEDED_HEADROOM; dev->needed_tailroom = real_dev->needed_tailroom + MACSEC_NEEDED_TAILROOM; if (is_zero_ether_addr(dev->dev_addr)) eth_hw_addr_inherit(dev, real_dev); if (is_zero_ether_addr(dev->broadcast)) memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len); return 0; } static void macsec_dev_uninit(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); gro_cells_destroy(&macsec->gro_cells); free_percpu(dev->tstats); } static netdev_features_t macsec_fix_features(struct net_device *dev, netdev_features_t features) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; features &= (real_dev->features & MACSEC_FEATURES) | NETIF_F_GSO_SOFTWARE | NETIF_F_SOFT_FEATURES; features |= NETIF_F_LLTX; return features; } static int macsec_dev_open(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; int err; err = dev_uc_add(real_dev, dev->dev_addr); if (err < 0) return err; if (dev->flags & IFF_ALLMULTI) { err = dev_set_allmulti(real_dev, 1); if (err < 0) goto del_unicast; } if (dev->flags & IFF_PROMISC) { err = dev_set_promiscuity(real_dev, 1); if (err < 0) goto clear_allmulti; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { err = -EOPNOTSUPP; goto clear_allmulti; } ctx.secy = &macsec->secy; err = macsec_offload(ops->mdo_dev_open, &ctx); if (err) goto clear_allmulti; } if (netif_carrier_ok(real_dev)) netif_carrier_on(dev); return 0; clear_allmulti: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(real_dev, -1); del_unicast: dev_uc_del(real_dev, dev->dev_addr); netif_carrier_off(dev); return err; } static int macsec_dev_stop(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; netif_carrier_off(dev); /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.secy = &macsec->secy; macsec_offload(ops->mdo_dev_stop, &ctx); } } dev_mc_unsync(real_dev, dev); dev_uc_unsync(real_dev, dev); if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(real_dev, -1); if (dev->flags & IFF_PROMISC) dev_set_promiscuity(real_dev, -1); dev_uc_del(real_dev, dev->dev_addr); return 0; } static void macsec_dev_change_rx_flags(struct net_device *dev, int change) { struct net_device *real_dev = macsec_priv(dev)->real_dev; if (!(dev->flags & IFF_UP)) return; if (change & IFF_ALLMULTI) dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1); if (change & IFF_PROMISC) dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1); } static void macsec_dev_set_rx_mode(struct net_device *dev) { struct net_device *real_dev = macsec_priv(dev)->real_dev; dev_mc_sync(real_dev, dev); dev_uc_sync(real_dev, dev); } static int macsec_set_mac_address(struct net_device *dev, void *p) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; struct sockaddr *addr = p; int err; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; if (!(dev->flags & IFF_UP)) goto out; err = dev_uc_add(real_dev, addr->sa_data); if (err < 0) return err; dev_uc_del(real_dev, dev->dev_addr); out: eth_hw_addr_set(dev, addr->sa_data); /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.secy = &macsec->secy; macsec_offload(ops->mdo_upd_secy, &ctx); } } return 0; } static int macsec_change_mtu(struct net_device *dev, int new_mtu) { struct macsec_dev *macsec = macsec_priv(dev); unsigned int extra = macsec->secy.icv_len + macsec_extra_len(true); if (macsec->real_dev->mtu - extra < new_mtu) return -ERANGE; dev->mtu = new_mtu; return 0; } static void macsec_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { if (!dev->tstats) return; dev_fetch_sw_netstats(s, dev->tstats); s->rx_dropped = dev->stats.rx_dropped; s->tx_dropped = dev->stats.tx_dropped; } static int macsec_get_iflink(const struct net_device *dev) { return macsec_priv(dev)->real_dev->ifindex; } static const struct net_device_ops macsec_netdev_ops = { .ndo_init = macsec_dev_init, .ndo_uninit = macsec_dev_uninit, .ndo_open = macsec_dev_open, .ndo_stop = macsec_dev_stop, .ndo_fix_features = macsec_fix_features, .ndo_change_mtu = macsec_change_mtu, .ndo_set_rx_mode = macsec_dev_set_rx_mode, .ndo_change_rx_flags = macsec_dev_change_rx_flags, .ndo_set_mac_address = macsec_set_mac_address, .ndo_start_xmit = macsec_start_xmit, .ndo_get_stats64 = macsec_get_stats64, .ndo_get_iflink = macsec_get_iflink, }; static const struct device_type macsec_type = { .name = "macsec", }; static const struct nla_policy macsec_rtnl_policy[IFLA_MACSEC_MAX + 1] = { [IFLA_MACSEC_SCI] = { .type = NLA_U64 }, [IFLA_MACSEC_PORT] = { .type = NLA_U16 }, [IFLA_MACSEC_ICV_LEN] = { .type = NLA_U8 }, [IFLA_MACSEC_CIPHER_SUITE] = { .type = NLA_U64 }, [IFLA_MACSEC_WINDOW] = { .type = NLA_U32 }, [IFLA_MACSEC_ENCODING_SA] = { .type = NLA_U8 }, [IFLA_MACSEC_ENCRYPT] = { .type = NLA_U8 }, [IFLA_MACSEC_PROTECT] = { .type = NLA_U8 }, [IFLA_MACSEC_INC_SCI] = { .type = NLA_U8 }, [IFLA_MACSEC_ES] = { .type = NLA_U8 }, [IFLA_MACSEC_SCB] = { .type = NLA_U8 }, [IFLA_MACSEC_REPLAY_PROTECT] = { .type = NLA_U8 }, [IFLA_MACSEC_VALIDATION] = { .type = NLA_U8 }, [IFLA_MACSEC_OFFLOAD] = { .type = NLA_U8 }, }; static void macsec_free_netdev(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); free_percpu(macsec->stats); free_percpu(macsec->secy.tx_sc.stats); } static void macsec_setup(struct net_device *dev) { ether_setup(dev); dev->min_mtu = 0; dev->max_mtu = ETH_MAX_MTU; dev->priv_flags |= IFF_NO_QUEUE; dev->netdev_ops = &macsec_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = macsec_free_netdev; SET_NETDEV_DEVTYPE(dev, &macsec_type); eth_zero_addr(dev->broadcast); } static int macsec_changelink_common(struct net_device *dev, struct nlattr *data[]) { struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; secy = &macsec_priv(dev)->secy; tx_sc = &secy->tx_sc; if (data[IFLA_MACSEC_ENCODING_SA]) { struct macsec_tx_sa *tx_sa; tx_sc->encoding_sa = nla_get_u8(data[IFLA_MACSEC_ENCODING_SA]); tx_sa = rtnl_dereference(tx_sc->sa[tx_sc->encoding_sa]); secy->operational = tx_sa && tx_sa->active; } if (data[IFLA_MACSEC_ENCRYPT]) tx_sc->encrypt = !!nla_get_u8(data[IFLA_MACSEC_ENCRYPT]); if (data[IFLA_MACSEC_PROTECT]) secy->protect_frames = !!nla_get_u8(data[IFLA_MACSEC_PROTECT]); if (data[IFLA_MACSEC_INC_SCI]) tx_sc->send_sci = !!nla_get_u8(data[IFLA_MACSEC_INC_SCI]); if (data[IFLA_MACSEC_ES]) tx_sc->end_station = !!nla_get_u8(data[IFLA_MACSEC_ES]); if (data[IFLA_MACSEC_SCB]) tx_sc->scb = !!nla_get_u8(data[IFLA_MACSEC_SCB]); if (data[IFLA_MACSEC_REPLAY_PROTECT]) secy->replay_protect = !!nla_get_u8(data[IFLA_MACSEC_REPLAY_PROTECT]); if (data[IFLA_MACSEC_VALIDATION]) secy->validate_frames = nla_get_u8(data[IFLA_MACSEC_VALIDATION]); if (data[IFLA_MACSEC_CIPHER_SUITE]) { switch (nla_get_u64(data[IFLA_MACSEC_CIPHER_SUITE])) { case MACSEC_CIPHER_ID_GCM_AES_128: case MACSEC_DEFAULT_CIPHER_ID: secy->key_len = MACSEC_GCM_AES_128_SAK_LEN; secy->xpn = false; break; case MACSEC_CIPHER_ID_GCM_AES_256: secy->key_len = MACSEC_GCM_AES_256_SAK_LEN; secy->xpn = false; break; case MACSEC_CIPHER_ID_GCM_AES_XPN_128: secy->key_len = MACSEC_GCM_AES_128_SAK_LEN; secy->xpn = true; break; case MACSEC_CIPHER_ID_GCM_AES_XPN_256: secy->key_len = MACSEC_GCM_AES_256_SAK_LEN; secy->xpn = true; break; default: return -EINVAL; } } if (data[IFLA_MACSEC_WINDOW]) { secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]); /* IEEE 802.1AEbw-2013 10.7.8 - maximum replay window * for XPN cipher suites */ if (secy->xpn && secy->replay_window > MACSEC_XPN_MAX_REPLAY_WINDOW) return -EINVAL; } return 0; } static int macsec_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macsec_dev *macsec = macsec_priv(dev); struct macsec_tx_sc tx_sc; struct macsec_secy secy; int ret; if (!data) return 0; if (data[IFLA_MACSEC_CIPHER_SUITE] || data[IFLA_MACSEC_ICV_LEN] || data[IFLA_MACSEC_SCI] || data[IFLA_MACSEC_PORT]) return -EINVAL; /* Keep a copy of unmodified secy and tx_sc, in case the offload * propagation fails, to revert macsec_changelink_common. */ memcpy(&secy, &macsec->secy, sizeof(secy)); memcpy(&tx_sc, &macsec->secy.tx_sc, sizeof(tx_sc)); ret = macsec_changelink_common(dev, data); if (ret) goto cleanup; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.secy = &macsec->secy; ret = macsec_offload(ops->mdo_upd_secy, &ctx); if (ret) goto cleanup; } return 0; cleanup: memcpy(&macsec->secy.tx_sc, &tx_sc, sizeof(tx_sc)); memcpy(&macsec->secy, &secy, sizeof(secy)); return ret; } static void macsec_del_dev(struct macsec_dev *macsec) { int i; while (macsec->secy.rx_sc) { struct macsec_rx_sc *rx_sc = rtnl_dereference(macsec->secy.rx_sc); rcu_assign_pointer(macsec->secy.rx_sc, rx_sc->next); free_rx_sc(rx_sc); } for (i = 0; i < MACSEC_NUM_AN; i++) { struct macsec_tx_sa *sa = rtnl_dereference(macsec->secy.tx_sc.sa[i]); if (sa) { RCU_INIT_POINTER(macsec->secy.tx_sc.sa[i], NULL); clear_tx_sa(sa); } } } static void macsec_common_dellink(struct net_device *dev, struct list_head *head) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (ops) { ctx.secy = &macsec->secy; macsec_offload(ops->mdo_del_secy, &ctx); } } unregister_netdevice_queue(dev, head); list_del_rcu(&macsec->secys); macsec_del_dev(macsec); netdev_upper_dev_unlink(real_dev, dev); macsec_generation++; } static void macsec_dellink(struct net_device *dev, struct list_head *head) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); macsec_common_dellink(dev, head); if (list_empty(&rxd->secys)) { netdev_rx_handler_unregister(real_dev); kfree(rxd); } } static int register_macsec_dev(struct net_device *real_dev, struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); if (!rxd) { int err; rxd = kmalloc(sizeof(*rxd), GFP_KERNEL); if (!rxd) return -ENOMEM; INIT_LIST_HEAD(&rxd->secys); err = netdev_rx_handler_register(real_dev, macsec_handle_frame, rxd); if (err < 0) { kfree(rxd); return err; } } list_add_tail_rcu(&macsec->secys, &rxd->secys); return 0; } static bool sci_exists(struct net_device *dev, sci_t sci) { struct macsec_rxh_data *rxd = macsec_data_rtnl(dev); struct macsec_dev *macsec; list_for_each_entry(macsec, &rxd->secys, secys) { if (macsec->secy.sci == sci) return true; } return false; } static sci_t dev_to_sci(struct net_device *dev, __be16 port) { return make_sci(dev->dev_addr, port); } static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len) { struct macsec_dev *macsec = macsec_priv(dev); struct macsec_secy *secy = &macsec->secy; macsec->stats = netdev_alloc_pcpu_stats(struct pcpu_secy_stats); if (!macsec->stats) return -ENOMEM; secy->tx_sc.stats = netdev_alloc_pcpu_stats(struct pcpu_tx_sc_stats); if (!secy->tx_sc.stats) { free_percpu(macsec->stats); return -ENOMEM; } if (sci == MACSEC_UNDEF_SCI) sci = dev_to_sci(dev, MACSEC_PORT_ES); secy->netdev = dev; secy->operational = true; secy->key_len = DEFAULT_SAK_LEN; secy->icv_len = icv_len; secy->validate_frames = MACSEC_VALIDATE_DEFAULT; secy->protect_frames = true; secy->replay_protect = false; secy->xpn = DEFAULT_XPN; secy->sci = sci; secy->tx_sc.active = true; secy->tx_sc.encoding_sa = DEFAULT_ENCODING_SA; secy->tx_sc.encrypt = DEFAULT_ENCRYPT; secy->tx_sc.send_sci = DEFAULT_SEND_SCI; secy->tx_sc.end_station = false; secy->tx_sc.scb = false; return 0; } static struct lock_class_key macsec_netdev_addr_lock_key; static int macsec_newlink(struct net *net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macsec_dev *macsec = macsec_priv(dev); rx_handler_func_t *rx_handler; u8 icv_len = DEFAULT_ICV_LEN; struct net_device *real_dev; int err, mtu; sci_t sci; if (!tb[IFLA_LINK]) return -EINVAL; real_dev = __dev_get_by_index(net, nla_get_u32(tb[IFLA_LINK])); if (!real_dev) return -ENODEV; if (real_dev->type != ARPHRD_ETHER) return -EINVAL; dev->priv_flags |= IFF_MACSEC; macsec->real_dev = real_dev; if (data && data[IFLA_MACSEC_OFFLOAD]) macsec->offload = nla_get_offload(data[IFLA_MACSEC_OFFLOAD]); else /* MACsec offloading is off by default */ macsec->offload = MACSEC_OFFLOAD_OFF; /* Check if the offloading mode is supported by the underlying layers */ if (macsec->offload != MACSEC_OFFLOAD_OFF && !macsec_check_offload(macsec->offload, macsec)) return -EOPNOTSUPP; /* send_sci must be set to true when transmit sci explicitly is set */ if ((data && data[IFLA_MACSEC_SCI]) && (data && data[IFLA_MACSEC_INC_SCI])) { u8 send_sci = !!nla_get_u8(data[IFLA_MACSEC_INC_SCI]); if (!send_sci) return -EINVAL; } if (data && data[IFLA_MACSEC_ICV_LEN]) icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]); mtu = real_dev->mtu - icv_len - macsec_extra_len(true); if (mtu < 0) dev->mtu = 0; else dev->mtu = mtu; rx_handler = rtnl_dereference(real_dev->rx_handler); if (rx_handler && rx_handler != macsec_handle_frame) return -EBUSY; err = register_netdevice(dev); if (err < 0) return err; netdev_lockdep_set_classes(dev); lockdep_set_class(&dev->addr_list_lock, &macsec_netdev_addr_lock_key); err = netdev_upper_dev_link(real_dev, dev, extack); if (err < 0) goto unregister; /* need to be already registered so that ->init has run and * the MAC addr is set */ if (data && data[IFLA_MACSEC_SCI]) sci = nla_get_sci(data[IFLA_MACSEC_SCI]); else if (data && data[IFLA_MACSEC_PORT]) sci = dev_to_sci(dev, nla_get_be16(data[IFLA_MACSEC_PORT])); else sci = dev_to_sci(dev, MACSEC_PORT_ES); if (rx_handler && sci_exists(real_dev, sci)) { err = -EBUSY; goto unlink; } err = macsec_add_dev(dev, sci, icv_len); if (err) goto unlink; if (data) { err = macsec_changelink_common(dev, data); if (err) goto del_dev; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.secy = &macsec->secy; err = macsec_offload(ops->mdo_add_secy, &ctx); if (err) goto del_dev; } } err = register_macsec_dev(real_dev, dev); if (err < 0) goto del_dev; netif_stacked_transfer_operstate(real_dev, dev); linkwatch_fire_event(dev); macsec_generation++; return 0; del_dev: macsec_del_dev(macsec); unlink: netdev_upper_dev_unlink(real_dev, dev); unregister: unregister_netdevice(dev); return err; } static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { u64 csid = MACSEC_DEFAULT_CIPHER_ID; u8 icv_len = DEFAULT_ICV_LEN; int flag; bool es, scb, sci; if (!data) return 0; if (data[IFLA_MACSEC_CIPHER_SUITE]) csid = nla_get_u64(data[IFLA_MACSEC_CIPHER_SUITE]); if (data[IFLA_MACSEC_ICV_LEN]) { icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]); if (icv_len != DEFAULT_ICV_LEN) { char dummy_key[DEFAULT_SAK_LEN] = { 0 }; struct crypto_aead *dummy_tfm; dummy_tfm = macsec_alloc_tfm(dummy_key, DEFAULT_SAK_LEN, icv_len); if (IS_ERR(dummy_tfm)) return PTR_ERR(dummy_tfm); crypto_free_aead(dummy_tfm); } } switch (csid) { case MACSEC_CIPHER_ID_GCM_AES_128: case MACSEC_CIPHER_ID_GCM_AES_256: case MACSEC_CIPHER_ID_GCM_AES_XPN_128: case MACSEC_CIPHER_ID_GCM_AES_XPN_256: case MACSEC_DEFAULT_CIPHER_ID: if (icv_len < MACSEC_MIN_ICV_LEN || icv_len > MACSEC_STD_ICV_LEN) return -EINVAL; break; default: return -EINVAL; } if (data[IFLA_MACSEC_ENCODING_SA]) { if (nla_get_u8(data[IFLA_MACSEC_ENCODING_SA]) >= MACSEC_NUM_AN) return -EINVAL; } for (flag = IFLA_MACSEC_ENCODING_SA + 1; flag < IFLA_MACSEC_VALIDATION; flag++) { if (data[flag]) { if (nla_get_u8(data[flag]) > 1) return -EINVAL; } } es = data[IFLA_MACSEC_ES] ? nla_get_u8(data[IFLA_MACSEC_ES]) : false; sci = data[IFLA_MACSEC_INC_SCI] ? nla_get_u8(data[IFLA_MACSEC_INC_SCI]) : false; scb = data[IFLA_MACSEC_SCB] ? nla_get_u8(data[IFLA_MACSEC_SCB]) : false; if ((sci && (scb || es)) || (scb && es)) return -EINVAL; if (data[IFLA_MACSEC_VALIDATION] && nla_get_u8(data[IFLA_MACSEC_VALIDATION]) > MACSEC_VALIDATE_MAX) return -EINVAL; if ((data[IFLA_MACSEC_REPLAY_PROTECT] && nla_get_u8(data[IFLA_MACSEC_REPLAY_PROTECT])) && !data[IFLA_MACSEC_WINDOW]) return -EINVAL; return 0; } static struct net *macsec_get_link_net(const struct net_device *dev) { return dev_net(macsec_priv(dev)->real_dev); } static size_t macsec_get_size(const struct net_device *dev) { return nla_total_size_64bit(8) + /* IFLA_MACSEC_SCI */ nla_total_size(1) + /* IFLA_MACSEC_ICV_LEN */ nla_total_size_64bit(8) + /* IFLA_MACSEC_CIPHER_SUITE */ nla_total_size(4) + /* IFLA_MACSEC_WINDOW */ nla_total_size(1) + /* IFLA_MACSEC_ENCODING_SA */ nla_total_size(1) + /* IFLA_MACSEC_ENCRYPT */ nla_total_size(1) + /* IFLA_MACSEC_PROTECT */ nla_total_size(1) + /* IFLA_MACSEC_INC_SCI */ nla_total_size(1) + /* IFLA_MACSEC_ES */ nla_total_size(1) + /* IFLA_MACSEC_SCB */ nla_total_size(1) + /* IFLA_MACSEC_REPLAY_PROTECT */ nla_total_size(1) + /* IFLA_MACSEC_VALIDATION */ 0; } static int macsec_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct macsec_secy *secy = &macsec_priv(dev)->secy; struct macsec_tx_sc *tx_sc = &secy->tx_sc; u64 csid; switch (secy->key_len) { case MACSEC_GCM_AES_128_SAK_LEN: csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_128 : MACSEC_DEFAULT_CIPHER_ID; break; case MACSEC_GCM_AES_256_SAK_LEN: csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_256 : MACSEC_CIPHER_ID_GCM_AES_256; break; default: goto nla_put_failure; } if (nla_put_sci(skb, IFLA_MACSEC_SCI, secy->sci, IFLA_MACSEC_PAD) || nla_put_u8(skb, IFLA_MACSEC_ICV_LEN, secy->icv_len) || nla_put_u64_64bit(skb, IFLA_MACSEC_CIPHER_SUITE, csid, IFLA_MACSEC_PAD) || nla_put_u8(skb, IFLA_MACSEC_ENCODING_SA, tx_sc->encoding_sa) || nla_put_u8(skb, IFLA_MACSEC_ENCRYPT, tx_sc->encrypt) || nla_put_u8(skb, IFLA_MACSEC_PROTECT, secy->protect_frames) || nla_put_u8(skb, IFLA_MACSEC_INC_SCI, tx_sc->send_sci) || nla_put_u8(skb, IFLA_MACSEC_ES, tx_sc->end_station) || nla_put_u8(skb, IFLA_MACSEC_SCB, tx_sc->scb) || nla_put_u8(skb, IFLA_MACSEC_REPLAY_PROTECT, secy->replay_protect) || nla_put_u8(skb, IFLA_MACSEC_VALIDATION, secy->validate_frames) || 0) goto nla_put_failure; if (secy->replay_protect) { if (nla_put_u32(skb, IFLA_MACSEC_WINDOW, secy->replay_window)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops macsec_link_ops __read_mostly = { .kind = "macsec", .priv_size = sizeof(struct macsec_dev), .maxtype = IFLA_MACSEC_MAX, .policy = macsec_rtnl_policy, .setup = macsec_setup, .validate = macsec_validate_attr, .newlink = macsec_newlink, .changelink = macsec_changelink, .dellink = macsec_dellink, .get_size = macsec_get_size, .fill_info = macsec_fill_info, .get_link_net = macsec_get_link_net, }; static bool is_macsec_master(struct net_device *dev) { return rcu_access_pointer(dev->rx_handler) == macsec_handle_frame; } static int macsec_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *real_dev = netdev_notifier_info_to_dev(ptr); LIST_HEAD(head); if (!is_macsec_master(real_dev)) return NOTIFY_DONE; switch (event) { case NETDEV_DOWN: case NETDEV_UP: case NETDEV_CHANGE: { struct macsec_dev *m, *n; struct macsec_rxh_data *rxd; rxd = macsec_data_rtnl(real_dev); list_for_each_entry_safe(m, n, &rxd->secys, secys) { struct net_device *dev = m->secy.netdev; netif_stacked_transfer_operstate(real_dev, dev); } break; } case NETDEV_UNREGISTER: { struct macsec_dev *m, *n; struct macsec_rxh_data *rxd; rxd = macsec_data_rtnl(real_dev); list_for_each_entry_safe(m, n, &rxd->secys, secys) { macsec_common_dellink(m->secy.netdev, &head); } netdev_rx_handler_unregister(real_dev); kfree(rxd); unregister_netdevice_many(&head); break; } case NETDEV_CHANGEMTU: { struct macsec_dev *m; struct macsec_rxh_data *rxd; rxd = macsec_data_rtnl(real_dev); list_for_each_entry(m, &rxd->secys, secys) { struct net_device *dev = m->secy.netdev; unsigned int mtu = real_dev->mtu - (m->secy.icv_len + macsec_extra_len(true)); if (dev->mtu > mtu) dev_set_mtu(dev, mtu); } } } return NOTIFY_OK; } static struct notifier_block macsec_notifier = { .notifier_call = macsec_notify, }; static int __init macsec_init(void) { int err; pr_info("MACsec IEEE 802.1AE\n"); err = register_netdevice_notifier(&macsec_notifier); if (err) return err; err = rtnl_link_register(&macsec_link_ops); if (err) goto notifier; err = genl_register_family(&macsec_fam); if (err) goto rtnl; return 0; rtnl: rtnl_link_unregister(&macsec_link_ops); notifier: unregister_netdevice_notifier(&macsec_notifier); return err; } static void __exit macsec_exit(void) { genl_unregister_family(&macsec_fam); rtnl_link_unregister(&macsec_link_ops); unregister_netdevice_notifier(&macsec_notifier); rcu_barrier(); } module_init(macsec_init); module_exit(macsec_exit); MODULE_ALIAS_RTNL_LINK("macsec"); MODULE_ALIAS_GENL_FAMILY("macsec"); MODULE_DESCRIPTION("MACsec IEEE 802.1AE"); MODULE_LICENSE("GPL v2"); |
| 2604 2603 2603 2601 2561 2211 2215 2212 462 2213 2563 2564 2561 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 | // 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> #include <trace/hooks/cgroup.h> static void propagate_protected_usage(struct page_counter *c, unsigned long usage) { unsigned long protected, old_protected; unsigned long low, min; long delta; if (!c->parent) return; min = READ_ONCE(c->min); if (min || atomic_long_read(&c->min_usage)) { protected = min(usage, min); old_protected = atomic_long_xchg(&c->min_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_min_usage); } low = READ_ONCE(c->low); if (low || atomic_long_read(&c->low_usage)) { protected = min(usage, low); 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); trace_android_rvh_update_watermark(new, c); } } /** * 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); propagate_protected_usage(c, new); /* * 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); trace_android_rvh_update_watermark(new, c); } 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) 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; } |
| 7 2 1 1 2 1 147 89 5 9 85 46 51 165 37 1 44 6 112 384 240 6 23 8 7 3 4 1 11 4 14 2 3 2 7 1 135 3 7 1 2 4 12 3 214 2 5 23 2 8 748 42 1 172 213 213 214 214 214 214 250 250 250 250 213 212 85 85 85 214 112 78 78 78 78 51 112 112 112 111 7 71 72 6 78 78 78 78 78 11 2 1 2 7 1 3 3 6 6 3 1 1 51 51 51 1 7 1 7 213 1 51 47 4 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic PPP layer for Linux. * * Copyright 1999-2002 Paul Mackerras. * * The generic PPP layer handles the PPP network interfaces, the * /dev/ppp device, packet and VJ compression, and multilink. * It talks to PPP `channels' via the interface defined in * include/linux/ppp_channel.h. Channels provide the basic means for * sending and receiving PPP frames on some kind of communications * channel. * * Part of the code in this driver was inspired by the old async-only * PPP driver, written by Michael Callahan and Al Longyear, and * subsequently hacked by Paul Mackerras. * * ==FILEVERSION 20041108== */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/kmod.h> #include <linux/init.h> #include <linux/list.h> #include <linux/idr.h> #include <linux/netdevice.h> #include <linux/poll.h> #include <linux/ppp_defs.h> #include <linux/filter.h> #include <linux/ppp-ioctl.h> #include <linux/ppp_channel.h> #include <linux/ppp-comp.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/spinlock.h> #include <linux/rwsem.h> #include <linux/stddef.h> #include <linux/device.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/file.h> #include <asm/unaligned.h> #include <net/slhc_vj.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/nsproxy.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #define PPP_VERSION "2.4.2" /* * Network protocols we support. */ #define NP_IP 0 /* Internet Protocol V4 */ #define NP_IPV6 1 /* Internet Protocol V6 */ #define NP_IPX 2 /* IPX protocol */ #define NP_AT 3 /* Appletalk protocol */ #define NP_MPLS_UC 4 /* MPLS unicast */ #define NP_MPLS_MC 5 /* MPLS multicast */ #define NUM_NP 6 /* Number of NPs. */ #define MPHDRLEN 6 /* multilink protocol header length */ #define MPHDRLEN_SSN 4 /* ditto with short sequence numbers */ #define PPP_PROTO_LEN 2 #define PPP_LCP_HDRLEN 4 /* The filter instructions generated by libpcap are constructed * assuming a four-byte PPP header on each packet, where the last * 2 bytes are the protocol field defined in the RFC and the first * byte of the first 2 bytes indicates the direction. * The second byte is currently unused, but we still need to initialize * it to prevent crafted BPF programs from reading them which would * cause reading of uninitialized data. */ #define PPP_FILTER_OUTBOUND_TAG 0x0100 #define PPP_FILTER_INBOUND_TAG 0x0000 /* * An instance of /dev/ppp can be associated with either a ppp * interface unit or a ppp channel. In both cases, file->private_data * points to one of these. */ struct ppp_file { enum { INTERFACE=1, CHANNEL } kind; struct sk_buff_head xq; /* pppd transmit queue */ struct sk_buff_head rq; /* receive queue for pppd */ wait_queue_head_t rwait; /* for poll on reading /dev/ppp */ refcount_t refcnt; /* # refs (incl /dev/ppp attached) */ int hdrlen; /* space to leave for headers */ int index; /* interface unit / channel number */ int dead; /* unit/channel has been shut down */ }; #define PF_TO_X(pf, X) container_of(pf, X, file) #define PF_TO_PPP(pf) PF_TO_X(pf, struct ppp) #define PF_TO_CHANNEL(pf) PF_TO_X(pf, struct channel) /* * Data structure to hold primary network stats for which * we want to use 64 bit storage. Other network stats * are stored in dev->stats of the ppp strucute. */ struct ppp_link_stats { u64 rx_packets; u64 tx_packets; u64 rx_bytes; u64 tx_bytes; }; /* * Data structure describing one ppp unit. * A ppp unit corresponds to a ppp network interface device * and represents a multilink bundle. * It can have 0 or more ppp channels connected to it. */ struct ppp { struct ppp_file file; /* stuff for read/write/poll 0 */ struct file *owner; /* file that owns this unit 48 */ struct list_head channels; /* list of attached channels 4c */ int n_channels; /* how many channels are attached 54 */ spinlock_t rlock; /* lock for receive side 58 */ spinlock_t wlock; /* lock for transmit side 5c */ int __percpu *xmit_recursion; /* xmit recursion detect */ int mru; /* max receive unit 60 */ unsigned int flags; /* control bits 64 */ unsigned int xstate; /* transmit state bits 68 */ unsigned int rstate; /* receive state bits 6c */ int debug; /* debug flags 70 */ struct slcompress *vj; /* state for VJ header compression */ enum NPmode npmode[NUM_NP]; /* what to do with each net proto 78 */ struct sk_buff *xmit_pending; /* a packet ready to go out 88 */ struct compressor *xcomp; /* transmit packet compressor 8c */ void *xc_state; /* its internal state 90 */ struct compressor *rcomp; /* receive decompressor 94 */ void *rc_state; /* its internal state 98 */ unsigned long last_xmit; /* jiffies when last pkt sent 9c */ unsigned long last_recv; /* jiffies when last pkt rcvd a0 */ struct net_device *dev; /* network interface device a4 */ int closing; /* is device closing down? a8 */ #ifdef CONFIG_PPP_MULTILINK int nxchan; /* next channel to send something on */ u32 nxseq; /* next sequence number to send */ int mrru; /* MP: max reconst. receive unit */ u32 nextseq; /* MP: seq no of next packet */ u32 minseq; /* MP: min of most recent seqnos */ struct sk_buff_head mrq; /* MP: receive reconstruction queue */ #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER struct bpf_prog *pass_filter; /* filter for packets to pass */ struct bpf_prog *active_filter; /* filter for pkts to reset idle */ #endif /* CONFIG_PPP_FILTER */ struct net *ppp_net; /* the net we belong to */ struct ppp_link_stats stats64; /* 64 bit network stats */ }; /* * Bits in flags: SC_NO_TCP_CCID, SC_CCP_OPEN, SC_CCP_UP, SC_LOOP_TRAFFIC, * SC_MULTILINK, SC_MP_SHORTSEQ, SC_MP_XSHORTSEQ, SC_COMP_TCP, SC_REJ_COMP_TCP, * SC_MUST_COMP * Bits in rstate: SC_DECOMP_RUN, SC_DC_ERROR, SC_DC_FERROR. * Bits in xstate: SC_COMP_RUN */ #define SC_FLAG_BITS (SC_NO_TCP_CCID|SC_CCP_OPEN|SC_CCP_UP|SC_LOOP_TRAFFIC \ |SC_MULTILINK|SC_MP_SHORTSEQ|SC_MP_XSHORTSEQ \ |SC_COMP_TCP|SC_REJ_COMP_TCP|SC_MUST_COMP) /* * Private data structure for each channel. * This includes the data structure used for multilink. */ struct channel { struct ppp_file file; /* stuff for read/write/poll */ struct list_head list; /* link in all/new_channels list */ struct ppp_channel *chan; /* public channel data structure */ struct rw_semaphore chan_sem; /* protects `chan' during chan ioctl */ spinlock_t downl; /* protects `chan', file.xq dequeue */ struct ppp *ppp; /* ppp unit we're connected to */ struct net *chan_net; /* the net channel belongs to */ struct list_head clist; /* link in list of channels per unit */ rwlock_t upl; /* protects `ppp' and 'bridge' */ struct channel __rcu *bridge; /* "bridged" ppp channel */ #ifdef CONFIG_PPP_MULTILINK u8 avail; /* flag used in multilink stuff */ u8 had_frag; /* >= 1 fragments have been sent */ u32 lastseq; /* MP: last sequence # received */ int speed; /* speed of the corresponding ppp channel*/ #endif /* CONFIG_PPP_MULTILINK */ }; struct ppp_config { struct file *file; s32 unit; bool ifname_is_set; }; /* * SMP locking issues: * Both the ppp.rlock and ppp.wlock locks protect the ppp.channels * list and the ppp.n_channels field, you need to take both locks * before you modify them. * The lock ordering is: channel.upl -> ppp.wlock -> ppp.rlock -> * channel.downl. */ static DEFINE_MUTEX(ppp_mutex); static atomic_t ppp_unit_count = ATOMIC_INIT(0); static atomic_t channel_count = ATOMIC_INIT(0); /* per-net private data for this module */ static unsigned int ppp_net_id __read_mostly; struct ppp_net { /* units to ppp mapping */ struct idr units_idr; /* * all_ppp_mutex protects the units_idr mapping. * It also ensures that finding a ppp unit in the units_idr * map and updating its file.refcnt field is atomic. */ struct mutex all_ppp_mutex; /* channels */ struct list_head all_channels; struct list_head new_channels; int last_channel_index; /* * all_channels_lock protects all_channels and * last_channel_index, and the atomicity of find * a channel and updating its file.refcnt field. */ spinlock_t all_channels_lock; }; /* Get the PPP protocol number from a skb */ #define PPP_PROTO(skb) get_unaligned_be16((skb)->data) /* We limit the length of ppp->file.rq to this (arbitrary) value */ #define PPP_MAX_RQLEN 32 /* * Maximum number of multilink fragments queued up. * This has to be large enough to cope with the maximum latency of * the slowest channel relative to the others. Strictly it should * depend on the number of channels and their characteristics. */ #define PPP_MP_MAX_QLEN 128 /* Multilink header bits. */ #define B 0x80 /* this fragment begins a packet */ #define E 0x40 /* this fragment ends a packet */ /* Compare multilink sequence numbers (assumed to be 32 bits wide) */ #define seq_before(a, b) ((s32)((a) - (b)) < 0) #define seq_after(a, b) ((s32)((a) - (b)) > 0) /* Prototypes. */ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct file *file, unsigned int cmd, unsigned long arg); static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb); static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb); static void ppp_push(struct ppp *ppp); static void ppp_channel_push(struct channel *pch); static void ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch); static void ppp_receive_error(struct ppp *ppp); static void ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb); static struct sk_buff *ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb); #ifdef CONFIG_PPP_MULTILINK static void ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch); static void ppp_mp_insert(struct ppp *ppp, struct sk_buff *skb); static struct sk_buff *ppp_mp_reconstruct(struct ppp *ppp); static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb); #endif /* CONFIG_PPP_MULTILINK */ static int ppp_set_compress(struct ppp *ppp, struct ppp_option_data *data); static void ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound); static void ppp_ccp_closed(struct ppp *ppp); static struct compressor *find_compressor(int type); static void ppp_get_stats(struct ppp *ppp, struct ppp_stats *st); static int ppp_create_interface(struct net *net, struct file *file, int *unit); static void init_ppp_file(struct ppp_file *pf, int kind); static void ppp_destroy_interface(struct ppp *ppp); static struct ppp *ppp_find_unit(struct ppp_net *pn, int unit); static struct channel *ppp_find_channel(struct ppp_net *pn, int unit); static int ppp_connect_channel(struct channel *pch, int unit); static int ppp_disconnect_channel(struct channel *pch); static void ppp_destroy_channel(struct channel *pch); static int unit_get(struct idr *p, void *ptr, int min); static int unit_set(struct idr *p, void *ptr, int n); static void unit_put(struct idr *p, int n); static void *unit_find(struct idr *p, int n); static void ppp_setup(struct net_device *dev); static const struct net_device_ops ppp_netdev_ops; static struct class *ppp_class; /* per net-namespace data */ static inline struct ppp_net *ppp_pernet(struct net *net) { return net_generic(net, ppp_net_id); } /* Translates a PPP protocol number to a NP index (NP == network protocol) */ static inline int proto_to_npindex(int proto) { switch (proto) { case PPP_IP: return NP_IP; case PPP_IPV6: return NP_IPV6; case PPP_IPX: return NP_IPX; case PPP_AT: return NP_AT; case PPP_MPLS_UC: return NP_MPLS_UC; case PPP_MPLS_MC: return NP_MPLS_MC; } return -EINVAL; } /* Translates an NP index into a PPP protocol number */ static const int npindex_to_proto[NUM_NP] = { PPP_IP, PPP_IPV6, PPP_IPX, PPP_AT, PPP_MPLS_UC, PPP_MPLS_MC, }; /* Translates an ethertype into an NP index */ static inline int ethertype_to_npindex(int ethertype) { switch (ethertype) { case ETH_P_IP: return NP_IP; case ETH_P_IPV6: return NP_IPV6; case ETH_P_IPX: return NP_IPX; case ETH_P_PPPTALK: case ETH_P_ATALK: return NP_AT; case ETH_P_MPLS_UC: return NP_MPLS_UC; case ETH_P_MPLS_MC: return NP_MPLS_MC; } return -1; } /* Translates an NP index into an ethertype */ static const int npindex_to_ethertype[NUM_NP] = { ETH_P_IP, ETH_P_IPV6, ETH_P_IPX, ETH_P_PPPTALK, ETH_P_MPLS_UC, ETH_P_MPLS_MC, }; /* * Locking shorthand. */ #define ppp_xmit_lock(ppp) spin_lock_bh(&(ppp)->wlock) #define ppp_xmit_unlock(ppp) spin_unlock_bh(&(ppp)->wlock) #define ppp_recv_lock(ppp) spin_lock_bh(&(ppp)->rlock) #define ppp_recv_unlock(ppp) spin_unlock_bh(&(ppp)->rlock) #define ppp_lock(ppp) do { ppp_xmit_lock(ppp); \ ppp_recv_lock(ppp); } while (0) #define ppp_unlock(ppp) do { ppp_recv_unlock(ppp); \ ppp_xmit_unlock(ppp); } while (0) /* * /dev/ppp device routines. * The /dev/ppp device is used by pppd to control the ppp unit. * It supports the read, write, ioctl and poll functions. * Open instances of /dev/ppp can be in one of three states: * unattached, attached to a ppp unit, or attached to a ppp channel. */ static int ppp_open(struct inode *inode, struct file *file) { /* * This could (should?) be enforced by the permissions on /dev/ppp. */ if (!ns_capable(file->f_cred->user_ns, CAP_NET_ADMIN)) return -EPERM; return 0; } static int ppp_release(struct inode *unused, struct file *file) { struct ppp_file *pf = file->private_data; struct ppp *ppp; if (pf) { file->private_data = NULL; if (pf->kind == INTERFACE) { ppp = PF_TO_PPP(pf); rtnl_lock(); if (file == ppp->owner) unregister_netdevice(ppp->dev); rtnl_unlock(); } if (refcount_dec_and_test(&pf->refcnt)) { switch (pf->kind) { case INTERFACE: ppp_destroy_interface(PF_TO_PPP(pf)); break; case CHANNEL: ppp_destroy_channel(PF_TO_CHANNEL(pf)); break; } } } return 0; } static ssize_t ppp_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct ppp_file *pf = file->private_data; DECLARE_WAITQUEUE(wait, current); ssize_t ret; struct sk_buff *skb = NULL; struct iovec iov; struct iov_iter to; ret = count; if (!pf) return -ENXIO; add_wait_queue(&pf->rwait, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); skb = skb_dequeue(&pf->rq); if (skb) break; ret = 0; if (pf->dead) break; if (pf->kind == INTERFACE) { /* * Return 0 (EOF) on an interface that has no * channels connected, unless it is looping * network traffic (demand mode). */ struct ppp *ppp = PF_TO_PPP(pf); ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) { ppp_recv_unlock(ppp); break; } ppp_recv_unlock(ppp); } ret = -EAGAIN; if (file->f_flags & O_NONBLOCK) break; ret = -ERESTARTSYS; if (signal_pending(current)) break; schedule(); } set_current_state(TASK_RUNNING); remove_wait_queue(&pf->rwait, &wait); if (!skb) goto out; ret = -EOVERFLOW; if (skb->len > count) goto outf; ret = -EFAULT; iov.iov_base = buf; iov.iov_len = count; iov_iter_init(&to, READ, &iov, 1, count); if (skb_copy_datagram_iter(skb, 0, &to, skb->len)) goto outf; ret = skb->len; outf: kfree_skb(skb); out: return ret; } static bool ppp_check_packet(struct sk_buff *skb, size_t count) { /* LCP packets must include LCP header which 4 bytes long: * 1-byte code, 1-byte identifier, and 2-byte length. */ return get_unaligned_be16(skb->data) != PPP_LCP || count >= PPP_PROTO_LEN + PPP_LCP_HDRLEN; } static ssize_t ppp_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct ppp_file *pf = file->private_data; struct sk_buff *skb; ssize_t ret; if (!pf) return -ENXIO; /* All PPP packets should start with the 2-byte protocol */ if (count < PPP_PROTO_LEN) return -EINVAL; ret = -ENOMEM; skb = alloc_skb(count + pf->hdrlen, GFP_KERNEL); if (!skb) goto out; skb_reserve(skb, pf->hdrlen); ret = -EFAULT; if (copy_from_user(skb_put(skb, count), buf, count)) { kfree_skb(skb); goto out; } ret = -EINVAL; if (unlikely(!ppp_check_packet(skb, count))) { kfree_skb(skb); goto out; } switch (pf->kind) { case INTERFACE: ppp_xmit_process(PF_TO_PPP(pf), skb); break; case CHANNEL: skb_queue_tail(&pf->xq, skb); ppp_channel_push(PF_TO_CHANNEL(pf)); break; } ret = count; out: return ret; } /* No kernel lock - fine */ static __poll_t ppp_poll(struct file *file, poll_table *wait) { struct ppp_file *pf = file->private_data; __poll_t mask; if (!pf) return 0; poll_wait(file, &pf->rwait, wait); mask = EPOLLOUT | EPOLLWRNORM; if (skb_peek(&pf->rq)) mask |= EPOLLIN | EPOLLRDNORM; if (pf->dead) mask |= EPOLLHUP; else if (pf->kind == INTERFACE) { /* see comment in ppp_read */ struct ppp *ppp = PF_TO_PPP(pf); ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) mask |= EPOLLIN | EPOLLRDNORM; ppp_recv_unlock(ppp); } return mask; } #ifdef CONFIG_PPP_FILTER static struct bpf_prog *get_filter(struct sock_fprog *uprog) { struct sock_fprog_kern fprog; struct bpf_prog *res = NULL; int err; if (!uprog->len) return NULL; /* uprog->len is unsigned short, so no overflow here */ fprog.len = uprog->len; fprog.filter = memdup_user(uprog->filter, uprog->len * sizeof(struct sock_filter)); if (IS_ERR(fprog.filter)) return ERR_CAST(fprog.filter); err = bpf_prog_create(&res, &fprog); kfree(fprog.filter); return err ? ERR_PTR(err) : res; } static struct bpf_prog *ppp_get_filter(struct sock_fprog __user *p) { struct sock_fprog uprog; if (copy_from_user(&uprog, p, sizeof(struct sock_fprog))) return ERR_PTR(-EFAULT); return get_filter(&uprog); } #ifdef CONFIG_COMPAT struct sock_fprog32 { unsigned short len; compat_caddr_t filter; }; #define PPPIOCSPASS32 _IOW('t', 71, struct sock_fprog32) #define PPPIOCSACTIVE32 _IOW('t', 70, struct sock_fprog32) static struct bpf_prog *compat_ppp_get_filter(struct sock_fprog32 __user *p) { struct sock_fprog32 uprog32; struct sock_fprog uprog; if (copy_from_user(&uprog32, p, sizeof(struct sock_fprog32))) return ERR_PTR(-EFAULT); uprog.len = uprog32.len; uprog.filter = compat_ptr(uprog32.filter); return get_filter(&uprog); } #endif #endif /* Bridge one PPP channel to another. * When two channels are bridged, ppp_input on one channel is redirected to * the other's ops->start_xmit handler. * In order to safely bridge channels we must reject channels which are already * part of a bridge instance, or which form part of an existing unit. * Once successfully bridged, each channel holds a reference on the other * to prevent it being freed while the bridge is extant. */ static int ppp_bridge_channels(struct channel *pch, struct channel *pchb) { write_lock_bh(&pch->upl); if (pch->ppp || rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl))) { write_unlock_bh(&pch->upl); return -EALREADY; } refcount_inc(&pchb->file.refcnt); rcu_assign_pointer(pch->bridge, pchb); write_unlock_bh(&pch->upl); write_lock_bh(&pchb->upl); if (pchb->ppp || rcu_dereference_protected(pchb->bridge, lockdep_is_held(&pchb->upl))) { write_unlock_bh(&pchb->upl); goto err_unset; } refcount_inc(&pch->file.refcnt); rcu_assign_pointer(pchb->bridge, pch); write_unlock_bh(&pchb->upl); return 0; err_unset: write_lock_bh(&pch->upl); /* Re-read pch->bridge with upl held in case it was modified concurrently */ pchb = rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl)); RCU_INIT_POINTER(pch->bridge, NULL); write_unlock_bh(&pch->upl); synchronize_rcu(); if (pchb) if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); return -EALREADY; } static int ppp_unbridge_channels(struct channel *pch) { struct channel *pchb, *pchbb; write_lock_bh(&pch->upl); pchb = rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl)); if (!pchb) { write_unlock_bh(&pch->upl); return -EINVAL; } RCU_INIT_POINTER(pch->bridge, NULL); write_unlock_bh(&pch->upl); /* Only modify pchb if phcb->bridge points back to pch. * If not, it implies that there has been a race unbridging (and possibly * even rebridging) pchb. We should leave pchb alone to avoid either a * refcount underflow, or breaking another established bridge instance. */ write_lock_bh(&pchb->upl); pchbb = rcu_dereference_protected(pchb->bridge, lockdep_is_held(&pchb->upl)); if (pchbb == pch) RCU_INIT_POINTER(pchb->bridge, NULL); write_unlock_bh(&pchb->upl); synchronize_rcu(); if (pchbb == pch) if (refcount_dec_and_test(&pch->file.refcnt)) ppp_destroy_channel(pch); if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); return 0; } static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ppp_file *pf; struct ppp *ppp; int err = -EFAULT, val, val2, i; struct ppp_idle32 idle32; struct ppp_idle64 idle64; struct npioctl npi; int unit, cflags; struct slcompress *vj; void __user *argp = (void __user *)arg; int __user *p = argp; mutex_lock(&ppp_mutex); pf = file->private_data; if (!pf) { err = ppp_unattached_ioctl(current->nsproxy->net_ns, pf, file, cmd, arg); goto out; } if (cmd == PPPIOCDETACH) { /* * PPPIOCDETACH is no longer supported as it was heavily broken, * and is only known to have been used by pppd older than * ppp-2.4.2 (released November 2003). */ pr_warn_once("%s (%d) used obsolete PPPIOCDETACH ioctl\n", current->comm, current->pid); err = -EINVAL; goto out; } if (pf->kind == CHANNEL) { struct channel *pch, *pchb; struct ppp_channel *chan; struct ppp_net *pn; pch = PF_TO_CHANNEL(pf); switch (cmd) { case PPPIOCCONNECT: if (get_user(unit, p)) break; err = ppp_connect_channel(pch, unit); break; case PPPIOCDISCONN: err = ppp_disconnect_channel(pch); break; case PPPIOCBRIDGECHAN: if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(current->nsproxy->net_ns); spin_lock_bh(&pn->all_channels_lock); pchb = ppp_find_channel(pn, unit); /* Hold a reference to prevent pchb being freed while * we establish the bridge. */ if (pchb) refcount_inc(&pchb->file.refcnt); spin_unlock_bh(&pn->all_channels_lock); if (!pchb) break; err = ppp_bridge_channels(pch, pchb); /* Drop earlier refcount now bridge establishment is complete */ if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); break; case PPPIOCUNBRIDGECHAN: err = ppp_unbridge_channels(pch); break; default: down_read(&pch->chan_sem); chan = pch->chan; err = -ENOTTY; if (chan && chan->ops->ioctl) err = chan->ops->ioctl(chan, cmd, arg); up_read(&pch->chan_sem); } goto out; } if (pf->kind != INTERFACE) { /* can't happen */ pr_err("PPP: not interface or channel??\n"); err = -EINVAL; goto out; } ppp = PF_TO_PPP(pf); switch (cmd) { case PPPIOCSMRU: if (get_user(val, p)) break; ppp->mru = val; err = 0; break; case PPPIOCSFLAGS: if (get_user(val, p)) break; ppp_lock(ppp); cflags = ppp->flags & ~val; #ifdef CONFIG_PPP_MULTILINK if (!(ppp->flags & SC_MULTILINK) && (val & SC_MULTILINK)) ppp->nextseq = 0; #endif ppp->flags = val & SC_FLAG_BITS; ppp_unlock(ppp); if (cflags & SC_CCP_OPEN) ppp_ccp_closed(ppp); err = 0; break; case PPPIOCGFLAGS: val = ppp->flags | ppp->xstate | ppp->rstate; if (put_user(val, p)) break; err = 0; break; case PPPIOCSCOMPRESS: { struct ppp_option_data data; if (copy_from_user(&data, argp, sizeof(data))) err = -EFAULT; else err = ppp_set_compress(ppp, &data); break; } case PPPIOCGUNIT: if (put_user(ppp->file.index, p)) break; err = 0; break; case PPPIOCSDEBUG: if (get_user(val, p)) break; ppp->debug = val; err = 0; break; case PPPIOCGDEBUG: if (put_user(ppp->debug, p)) break; err = 0; break; case PPPIOCGIDLE32: idle32.xmit_idle = (jiffies - ppp->last_xmit) / HZ; idle32.recv_idle = (jiffies - ppp->last_recv) / HZ; if (copy_to_user(argp, &idle32, sizeof(idle32))) break; err = 0; break; case PPPIOCGIDLE64: idle64.xmit_idle = (jiffies - ppp->last_xmit) / HZ; idle64.recv_idle = (jiffies - ppp->last_recv) / HZ; if (copy_to_user(argp, &idle64, sizeof(idle64))) break; err = 0; break; case PPPIOCSMAXCID: if (get_user(val, p)) break; val2 = 15; if ((val >> 16) != 0) { val2 = val >> 16; val &= 0xffff; } vj = slhc_init(val2+1, val+1); if (IS_ERR(vj)) { err = PTR_ERR(vj); break; } ppp_lock(ppp); if (ppp->vj) slhc_free(ppp->vj); ppp->vj = vj; ppp_unlock(ppp); err = 0; break; case PPPIOCGNPMODE: case PPPIOCSNPMODE: if (copy_from_user(&npi, argp, sizeof(npi))) break; err = proto_to_npindex(npi.protocol); if (err < 0) break; i = err; if (cmd == PPPIOCGNPMODE) { err = -EFAULT; npi.mode = ppp->npmode[i]; if (copy_to_user(argp, &npi, sizeof(npi))) break; } else { ppp->npmode[i] = npi.mode; /* we may be able to transmit more packets now (??) */ netif_wake_queue(ppp->dev); } err = 0; break; #ifdef CONFIG_PPP_FILTER case PPPIOCSPASS: case PPPIOCSACTIVE: { struct bpf_prog *filter = ppp_get_filter(argp); struct bpf_prog **which; if (IS_ERR(filter)) { err = PTR_ERR(filter); break; } if (cmd == PPPIOCSPASS) which = &ppp->pass_filter; else which = &ppp->active_filter; ppp_lock(ppp); if (*which) bpf_prog_destroy(*which); *which = filter; ppp_unlock(ppp); err = 0; break; } #endif /* CONFIG_PPP_FILTER */ #ifdef CONFIG_PPP_MULTILINK case PPPIOCSMRRU: if (get_user(val, p)) break; ppp_recv_lock(ppp); ppp->mrru = val; ppp_recv_unlock(ppp); err = 0; break; #endif /* CONFIG_PPP_MULTILINK */ default: err = -ENOTTY; } out: mutex_unlock(&ppp_mutex); return err; } #ifdef CONFIG_COMPAT struct ppp_option_data32 { compat_uptr_t ptr; u32 length; compat_int_t transmit; }; #define PPPIOCSCOMPRESS32 _IOW('t', 77, struct ppp_option_data32) static long ppp_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ppp_file *pf; int err = -ENOIOCTLCMD; void __user *argp = (void __user *)arg; mutex_lock(&ppp_mutex); pf = file->private_data; if (pf && pf->kind == INTERFACE) { struct ppp *ppp = PF_TO_PPP(pf); switch (cmd) { #ifdef CONFIG_PPP_FILTER case PPPIOCSPASS32: case PPPIOCSACTIVE32: { struct bpf_prog *filter = compat_ppp_get_filter(argp); struct bpf_prog **which; if (IS_ERR(filter)) { err = PTR_ERR(filter); break; } if (cmd == PPPIOCSPASS32) which = &ppp->pass_filter; else which = &ppp->active_filter; ppp_lock(ppp); if (*which) bpf_prog_destroy(*which); *which = filter; ppp_unlock(ppp); err = 0; break; } #endif /* CONFIG_PPP_FILTER */ case PPPIOCSCOMPRESS32: { struct ppp_option_data32 data32; if (copy_from_user(&data32, argp, sizeof(data32))) { err = -EFAULT; } else { struct ppp_option_data data = { .ptr = compat_ptr(data32.ptr), .length = data32.length, .transmit = data32.transmit }; err = ppp_set_compress(ppp, &data); } break; } } } mutex_unlock(&ppp_mutex); /* all other commands have compatible arguments */ if (err == -ENOIOCTLCMD) err = ppp_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); return err; } #endif static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct file *file, unsigned int cmd, unsigned long arg) { int unit, err = -EFAULT; struct ppp *ppp; struct channel *chan; struct ppp_net *pn; int __user *p = (int __user *)arg; switch (cmd) { case PPPIOCNEWUNIT: /* Create a new ppp unit */ if (get_user(unit, p)) break; err = ppp_create_interface(net, file, &unit); if (err < 0) break; err = -EFAULT; if (put_user(unit, p)) break; err = 0; break; case PPPIOCATTACH: /* Attach to an existing ppp unit */ if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(net); mutex_lock(&pn->all_ppp_mutex); ppp = ppp_find_unit(pn, unit); if (ppp) { refcount_inc(&ppp->file.refcnt); file->private_data = &ppp->file; err = 0; } mutex_unlock(&pn->all_ppp_mutex); break; case PPPIOCATTCHAN: if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(net); spin_lock_bh(&pn->all_channels_lock); chan = ppp_find_channel(pn, unit); if (chan) { refcount_inc(&chan->file.refcnt); file->private_data = &chan->file; err = 0; } spin_unlock_bh(&pn->all_channels_lock); break; default: err = -ENOTTY; } return err; } static const struct file_operations ppp_device_fops = { .owner = THIS_MODULE, .read = ppp_read, .write = ppp_write, .poll = ppp_poll, .unlocked_ioctl = ppp_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ppp_compat_ioctl, #endif .open = ppp_open, .release = ppp_release, .llseek = noop_llseek, }; static __net_init int ppp_init_net(struct net *net) { struct ppp_net *pn = net_generic(net, ppp_net_id); idr_init(&pn->units_idr); mutex_init(&pn->all_ppp_mutex); INIT_LIST_HEAD(&pn->all_channels); INIT_LIST_HEAD(&pn->new_channels); spin_lock_init(&pn->all_channels_lock); return 0; } static __net_exit void ppp_exit_net(struct net *net) { struct ppp_net *pn = net_generic(net, ppp_net_id); struct net_device *dev; struct net_device *aux; struct ppp *ppp; LIST_HEAD(list); int id; rtnl_lock(); for_each_netdev_safe(net, dev, aux) { if (dev->netdev_ops == &ppp_netdev_ops) unregister_netdevice_queue(dev, &list); } idr_for_each_entry(&pn->units_idr, ppp, id) /* Skip devices already unregistered by previous loop */ if (!net_eq(dev_net(ppp->dev), net)) unregister_netdevice_queue(ppp->dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); mutex_destroy(&pn->all_ppp_mutex); idr_destroy(&pn->units_idr); WARN_ON_ONCE(!list_empty(&pn->all_channels)); WARN_ON_ONCE(!list_empty(&pn->new_channels)); } static struct pernet_operations ppp_net_ops = { .init = ppp_init_net, .exit = ppp_exit_net, .id = &ppp_net_id, .size = sizeof(struct ppp_net), }; static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) { struct ppp_net *pn = ppp_pernet(ppp->ppp_net); int ret; mutex_lock(&pn->all_ppp_mutex); if (unit < 0) { ret = unit_get(&pn->units_idr, ppp, 0); if (ret < 0) goto err; if (!ifname_is_set) { while (1) { snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ret); if (!__dev_get_by_name(ppp->ppp_net, ppp->dev->name)) break; unit_put(&pn->units_idr, ret); ret = unit_get(&pn->units_idr, ppp, ret + 1); if (ret < 0) goto err; } } } else { /* Caller asked for a specific unit number. Fail with -EEXIST * if unavailable. For backward compatibility, return -EEXIST * too if idr allocation fails; this makes pppd retry without * requesting a specific unit number. */ if (unit_find(&pn->units_idr, unit)) { ret = -EEXIST; goto err; } ret = unit_set(&pn->units_idr, ppp, unit); if (ret < 0) { /* Rewrite error for backward compatibility */ ret = -EEXIST; goto err; } } ppp->file.index = ret; if (!ifname_is_set) snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ppp->file.index); mutex_unlock(&pn->all_ppp_mutex); ret = register_netdevice(ppp->dev); if (ret < 0) goto err_unit; atomic_inc(&ppp_unit_count); return 0; err_unit: mutex_lock(&pn->all_ppp_mutex); unit_put(&pn->units_idr, ppp->file.index); err: mutex_unlock(&pn->all_ppp_mutex); return ret; } static int ppp_dev_configure(struct net *src_net, struct net_device *dev, const struct ppp_config *conf) { struct ppp *ppp = netdev_priv(dev); int indx; int err; int cpu; ppp->dev = dev; ppp->ppp_net = src_net; ppp->mru = PPP_MRU; ppp->owner = conf->file; init_ppp_file(&ppp->file, INTERFACE); ppp->file.hdrlen = PPP_HDRLEN - 2; /* don't count proto bytes */ for (indx = 0; indx < NUM_NP; ++indx) ppp->npmode[indx] = NPMODE_PASS; INIT_LIST_HEAD(&ppp->channels); spin_lock_init(&ppp->rlock); spin_lock_init(&ppp->wlock); ppp->xmit_recursion = alloc_percpu(int); if (!ppp->xmit_recursion) { err = -ENOMEM; goto err1; } for_each_possible_cpu(cpu) (*per_cpu_ptr(ppp->xmit_recursion, cpu)) = 0; #ifdef CONFIG_PPP_MULTILINK ppp->minseq = -1; skb_queue_head_init(&ppp->mrq); #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER ppp->pass_filter = NULL; ppp->active_filter = NULL; #endif /* CONFIG_PPP_FILTER */ err = ppp_unit_register(ppp, conf->unit, conf->ifname_is_set); if (err < 0) goto err2; conf->file->private_data = &ppp->file; return 0; err2: free_percpu(ppp->xmit_recursion); err1: return err; } static const struct nla_policy ppp_nl_policy[IFLA_PPP_MAX + 1] = { [IFLA_PPP_DEV_FD] = { .type = NLA_S32 }, }; static int ppp_nl_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (!data) return -EINVAL; if (!data[IFLA_PPP_DEV_FD]) return -EINVAL; if (nla_get_s32(data[IFLA_PPP_DEV_FD]) < 0) return -EBADF; return 0; } static int ppp_nl_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ppp_config conf = { .unit = -1, .ifname_is_set = true, }; struct file *file; int err; file = fget(nla_get_s32(data[IFLA_PPP_DEV_FD])); if (!file) return -EBADF; /* rtnl_lock is already held here, but ppp_create_interface() locks * ppp_mutex before holding rtnl_lock. Using mutex_trylock() avoids * possible deadlock due to lock order inversion, at the cost of * pushing the problem back to userspace. */ if (!mutex_trylock(&ppp_mutex)) { err = -EBUSY; goto out; } if (file->f_op != &ppp_device_fops || file->private_data) { err = -EBADF; goto out_unlock; } conf.file = file; /* Don't use device name generated by the rtnetlink layer when ifname * isn't specified. Let ppp_dev_configure() set the device name using * the PPP unit identifer as suffix (i.e. ppp<unit_id>). This allows * userspace to infer the device name using to the PPPIOCGUNIT ioctl. */ if (!tb[IFLA_IFNAME] || !nla_len(tb[IFLA_IFNAME]) || !*(char *)nla_data(tb[IFLA_IFNAME])) conf.ifname_is_set = false; err = ppp_dev_configure(src_net, dev, &conf); out_unlock: mutex_unlock(&ppp_mutex); out: fput(file); return err; } static void ppp_nl_dellink(struct net_device *dev, struct list_head *head) { unregister_netdevice_queue(dev, head); } static size_t ppp_nl_get_size(const struct net_device *dev) { return 0; } static int ppp_nl_fill_info(struct sk_buff *skb, const struct net_device *dev) { return 0; } static struct net *ppp_nl_get_link_net(const struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); return ppp->ppp_net; } static struct rtnl_link_ops ppp_link_ops __read_mostly = { .kind = "ppp", .maxtype = IFLA_PPP_MAX, .policy = ppp_nl_policy, .priv_size = sizeof(struct ppp), .setup = ppp_setup, .validate = ppp_nl_validate, .newlink = ppp_nl_newlink, .dellink = ppp_nl_dellink, .get_size = ppp_nl_get_size, .fill_info = ppp_nl_fill_info, .get_link_net = ppp_nl_get_link_net, }; #define PPP_MAJOR 108 /* Called at boot time if ppp is compiled into the kernel, or at module load time (from init_module) if compiled as a module. */ static int __init ppp_init(void) { int err; pr_info("PPP generic driver version " PPP_VERSION "\n"); err = register_pernet_device(&ppp_net_ops); if (err) { pr_err("failed to register PPP pernet device (%d)\n", err); goto out; } err = register_chrdev(PPP_MAJOR, "ppp", &ppp_device_fops); if (err) { pr_err("failed to register PPP device (%d)\n", err); goto out_net; } ppp_class = class_create(THIS_MODULE, "ppp"); if (IS_ERR(ppp_class)) { err = PTR_ERR(ppp_class); goto out_chrdev; } err = rtnl_link_register(&ppp_link_ops); if (err) { pr_err("failed to register rtnetlink PPP handler\n"); goto out_class; } /* not a big deal if we fail here :-) */ device_create(ppp_class, NULL, MKDEV(PPP_MAJOR, 0), NULL, "ppp"); return 0; out_class: class_destroy(ppp_class); out_chrdev: unregister_chrdev(PPP_MAJOR, "ppp"); out_net: unregister_pernet_device(&ppp_net_ops); out: return err; } /* * Network interface unit routines. */ static netdev_tx_t ppp_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); int npi, proto; unsigned char *pp; npi = ethertype_to_npindex(ntohs(skb->protocol)); if (npi < 0) goto outf; /* Drop, accept or reject the packet */ switch (ppp->npmode[npi]) { case NPMODE_PASS: break; case NPMODE_QUEUE: /* it would be nice to have a way to tell the network system to queue this one up for later. */ goto outf; case NPMODE_DROP: case NPMODE_ERROR: goto outf; } /* Put the 2-byte PPP protocol number on the front, making sure there is room for the address and control fields. */ if (skb_cow_head(skb, PPP_HDRLEN)) goto outf; pp = skb_push(skb, 2); proto = npindex_to_proto[npi]; put_unaligned_be16(proto, pp); skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(dev))); ppp_xmit_process(ppp, skb); return NETDEV_TX_OK; outf: kfree_skb(skb); ++dev->stats.tx_dropped; return NETDEV_TX_OK; } static int ppp_net_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *addr, int cmd) { struct ppp *ppp = netdev_priv(dev); int err = -EFAULT; struct ppp_stats stats; struct ppp_comp_stats cstats; char *vers; switch (cmd) { case SIOCGPPPSTATS: ppp_get_stats(ppp, &stats); if (copy_to_user(addr, &stats, sizeof(stats))) break; err = 0; break; case SIOCGPPPCSTATS: memset(&cstats, 0, sizeof(cstats)); if (ppp->xc_state) ppp->xcomp->comp_stat(ppp->xc_state, &cstats.c); if (ppp->rc_state) ppp->rcomp->decomp_stat(ppp->rc_state, &cstats.d); if (copy_to_user(addr, &cstats, sizeof(cstats))) break; err = 0; break; case SIOCGPPPVER: vers = PPP_VERSION; if (copy_to_user(addr, vers, strlen(vers) + 1)) break; err = 0; break; default: err = -EINVAL; } return err; } static void ppp_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64) { struct ppp *ppp = netdev_priv(dev); ppp_recv_lock(ppp); stats64->rx_packets = ppp->stats64.rx_packets; stats64->rx_bytes = ppp->stats64.rx_bytes; ppp_recv_unlock(ppp); ppp_xmit_lock(ppp); stats64->tx_packets = ppp->stats64.tx_packets; stats64->tx_bytes = ppp->stats64.tx_bytes; ppp_xmit_unlock(ppp); stats64->rx_errors = dev->stats.rx_errors; stats64->tx_errors = dev->stats.tx_errors; stats64->rx_dropped = dev->stats.rx_dropped; stats64->tx_dropped = dev->stats.tx_dropped; stats64->rx_length_errors = dev->stats.rx_length_errors; } static int ppp_dev_init(struct net_device *dev) { struct ppp *ppp; netdev_lockdep_set_classes(dev); ppp = netdev_priv(dev); /* Let the netdevice take a reference on the ppp file. This ensures * that ppp_destroy_interface() won't run before the device gets * unregistered. */ refcount_inc(&ppp->file.refcnt); return 0; } static void ppp_dev_uninit(struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); struct ppp_net *pn = ppp_pernet(ppp->ppp_net); ppp_lock(ppp); ppp->closing = 1; ppp_unlock(ppp); mutex_lock(&pn->all_ppp_mutex); unit_put(&pn->units_idr, ppp->file.index); mutex_unlock(&pn->all_ppp_mutex); ppp->owner = NULL; ppp->file.dead = 1; wake_up_interruptible(&ppp->file.rwait); } static void ppp_dev_priv_destructor(struct net_device *dev) { struct ppp *ppp; ppp = netdev_priv(dev); if (refcount_dec_and_test(&ppp->file.refcnt)) ppp_destroy_interface(ppp); } static int ppp_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct ppp *ppp = netdev_priv(ctx->dev); struct ppp_channel *chan; struct channel *pch; if (ppp->flags & SC_MULTILINK) return -EOPNOTSUPP; if (list_empty(&ppp->channels)) return -ENODEV; pch = list_first_entry(&ppp->channels, struct channel, clist); chan = pch->chan; if (!chan->ops->fill_forward_path) return -EOPNOTSUPP; return chan->ops->fill_forward_path(ctx, path, chan); } static const struct net_device_ops ppp_netdev_ops = { .ndo_init = ppp_dev_init, .ndo_uninit = ppp_dev_uninit, .ndo_start_xmit = ppp_start_xmit, .ndo_siocdevprivate = ppp_net_siocdevprivate, .ndo_get_stats64 = ppp_get_stats64, .ndo_fill_forward_path = ppp_fill_forward_path, }; static struct device_type ppp_type = { .name = "ppp", }; static void ppp_setup(struct net_device *dev) { dev->netdev_ops = &ppp_netdev_ops; SET_NETDEV_DEVTYPE(dev, &ppp_type); dev->features |= NETIF_F_LLTX; dev->hard_header_len = PPP_HDRLEN; dev->mtu = PPP_MRU; dev->addr_len = 0; dev->tx_queue_len = 3; dev->type = ARPHRD_PPP; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->priv_destructor = ppp_dev_priv_destructor; netif_keep_dst(dev); } /* * Transmit-side routines. */ /* Called to do any work queued up on the transmit side that can now be done */ static void __ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { ppp_xmit_lock(ppp); if (!ppp->closing) { ppp_push(ppp); if (skb) skb_queue_tail(&ppp->file.xq, skb); while (!ppp->xmit_pending && (skb = skb_dequeue(&ppp->file.xq))) ppp_send_frame(ppp, skb); /* If there's no work left to do, tell the core net code that we can accept some more. */ if (!ppp->xmit_pending && !skb_peek(&ppp->file.xq)) netif_wake_queue(ppp->dev); else netif_stop_queue(ppp->dev); } else { kfree_skb(skb); } ppp_xmit_unlock(ppp); } static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { local_bh_disable(); if (unlikely(*this_cpu_ptr(ppp->xmit_recursion))) goto err; (*this_cpu_ptr(ppp->xmit_recursion))++; __ppp_xmit_process(ppp, skb); (*this_cpu_ptr(ppp->xmit_recursion))--; local_bh_enable(); return; err: local_bh_enable(); kfree_skb(skb); if (net_ratelimit()) netdev_err(ppp->dev, "recursion detected\n"); } static inline struct sk_buff * pad_compress_skb(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *new_skb; int len; int new_skb_size = ppp->dev->mtu + ppp->xcomp->comp_extra + ppp->dev->hard_header_len; int compressor_skb_size = ppp->dev->mtu + ppp->xcomp->comp_extra + PPP_HDRLEN; new_skb = alloc_skb(new_skb_size, GFP_ATOMIC); if (!new_skb) { if (net_ratelimit()) netdev_err(ppp->dev, "PPP: no memory (comp pkt)\n"); return NULL; } if (ppp->dev->hard_header_len > PPP_HDRLEN) skb_reserve(new_skb, ppp->dev->hard_header_len - PPP_HDRLEN); /* compressor still expects A/C bytes in hdr */ len = ppp->xcomp->compress(ppp->xc_state, skb->data - 2, new_skb->data, skb->len + 2, compressor_skb_size); if (len > 0 && (ppp->flags & SC_CCP_UP)) { consume_skb(skb); skb = new_skb; skb_put(skb, len); skb_pull(skb, 2); /* pull off A/C bytes */ } else if (len == 0) { /* didn't compress, or CCP not up yet */ consume_skb(new_skb); new_skb = skb; } else { /* * (len < 0) * MPPE requires that we do not send unencrypted * frames. The compressor will return -1 if we * should drop the frame. We cannot simply test * the compress_proto because MPPE and MPPC share * the same number. */ if (net_ratelimit()) netdev_err(ppp->dev, "ppp: compressor dropped pkt\n"); kfree_skb(skb); consume_skb(new_skb); new_skb = NULL; } return new_skb; } /* * Compress and send a frame. * The caller should have locked the xmit path, * and xmit_pending should be 0. */ static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) { int proto = PPP_PROTO(skb); struct sk_buff *new_skb; int len; unsigned char *cp; skb->dev = ppp->dev; if (proto < 0x8000) { #ifdef CONFIG_PPP_FILTER /* check if the packet passes the pass and active filters. * See comment for PPP_FILTER_OUTBOUND_TAG above. */ *(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_OUTBOUND_TAG); if (ppp->pass_filter && bpf_prog_run(ppp->pass_filter, skb) == 0) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: outbound frame " "not passed\n"); kfree_skb(skb); return; } /* if this packet passes the active filter, record the time */ if (!(ppp->active_filter && bpf_prog_run(ppp->active_filter, skb) == 0)) ppp->last_xmit = jiffies; skb_pull(skb, 2); #else /* for data packets, record the time */ ppp->last_xmit = jiffies; #endif /* CONFIG_PPP_FILTER */ } ++ppp->stats64.tx_packets; ppp->stats64.tx_bytes += skb->len - PPP_PROTO_LEN; switch (proto) { case PPP_IP: if (!ppp->vj || (ppp->flags & SC_COMP_TCP) == 0) break; /* try to do VJ TCP header compression */ new_skb = alloc_skb(skb->len + ppp->dev->hard_header_len - 2, GFP_ATOMIC); if (!new_skb) { netdev_err(ppp->dev, "PPP: no memory (VJ comp pkt)\n"); goto drop; } skb_reserve(new_skb, ppp->dev->hard_header_len - 2); cp = skb->data + 2; len = slhc_compress(ppp->vj, cp, skb->len - 2, new_skb->data + 2, &cp, !(ppp->flags & SC_NO_TCP_CCID)); if (cp == skb->data + 2) { /* didn't compress */ consume_skb(new_skb); } else { if (cp[0] & SL_TYPE_COMPRESSED_TCP) { proto = PPP_VJC_COMP; cp[0] &= ~SL_TYPE_COMPRESSED_TCP; } else { proto = PPP_VJC_UNCOMP; cp[0] = skb->data[2]; } consume_skb(skb); skb = new_skb; cp = skb_put(skb, len + 2); cp[0] = 0; cp[1] = proto; } break; case PPP_CCP: /* peek at outbound CCP frames */ ppp_ccp_peek(ppp, skb, 0); break; } /* try to do packet compression */ if ((ppp->xstate & SC_COMP_RUN) && ppp->xc_state && proto != PPP_LCP && proto != PPP_CCP) { if (!(ppp->flags & SC_CCP_UP) && (ppp->flags & SC_MUST_COMP)) { if (net_ratelimit()) netdev_err(ppp->dev, "ppp: compression required but " "down - pkt dropped.\n"); goto drop; } skb = pad_compress_skb(ppp, skb); if (!skb) goto drop; } /* * If we are waiting for traffic (demand dialling), * queue it up for pppd to receive. */ if (ppp->flags & SC_LOOP_TRAFFIC) { if (ppp->file.rq.qlen > PPP_MAX_RQLEN) goto drop; skb_queue_tail(&ppp->file.rq, skb); wake_up_interruptible(&ppp->file.rwait); return; } ppp->xmit_pending = skb; ppp_push(ppp); return; drop: kfree_skb(skb); ++ppp->dev->stats.tx_errors; } /* * Try to send the frame in xmit_pending. * The caller should have the xmit path locked. */ static void ppp_push(struct ppp *ppp) { struct list_head *list; struct channel *pch; struct sk_buff *skb = ppp->xmit_pending; if (!skb) return; list = &ppp->channels; if (list_empty(list)) { /* nowhere to send the packet, just drop it */ ppp->xmit_pending = NULL; kfree_skb(skb); return; } if ((ppp->flags & SC_MULTILINK) == 0) { /* not doing multilink: send it down the first channel */ list = list->next; pch = list_entry(list, struct channel, clist); spin_lock(&pch->downl); if (pch->chan) { if (pch->chan->ops->start_xmit(pch->chan, skb)) ppp->xmit_pending = NULL; } else { /* channel got unregistered */ kfree_skb(skb); ppp->xmit_pending = NULL; } spin_unlock(&pch->downl); return; } #ifdef CONFIG_PPP_MULTILINK /* Multilink: fragment the packet over as many links as can take the packet at the moment. */ if (!ppp_mp_explode(ppp, skb)) return; #endif /* CONFIG_PPP_MULTILINK */ ppp->xmit_pending = NULL; kfree_skb(skb); } #ifdef CONFIG_PPP_MULTILINK static bool mp_protocol_compress __read_mostly = true; module_param(mp_protocol_compress, bool, 0644); MODULE_PARM_DESC(mp_protocol_compress, "compress protocol id in multilink fragments"); /* * Divide a packet to be transmitted into fragments and * send them out the individual links. */ static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb) { int len, totlen; int i, bits, hdrlen, mtu; int flen; int navail, nfree, nzero; int nbigger; int totspeed; int totfree; unsigned char *p, *q; struct list_head *list; struct channel *pch; struct sk_buff *frag; struct ppp_channel *chan; totspeed = 0; /*total bitrate of the bundle*/ nfree = 0; /* # channels which have no packet already queued */ navail = 0; /* total # of usable channels (not deregistered) */ nzero = 0; /* number of channels with zero speed associated*/ totfree = 0; /*total # of channels available and *having no queued packets before *starting the fragmentation*/ hdrlen = (ppp->flags & SC_MP_XSHORTSEQ)? MPHDRLEN_SSN: MPHDRLEN; i = 0; list_for_each_entry(pch, &ppp->channels, clist) { if (pch->chan) { pch->avail = 1; navail++; pch->speed = pch->chan->speed; } else { pch->avail = 0; } if (pch->avail) { if (skb_queue_empty(&pch->file.xq) || !pch->had_frag) { if (pch->speed == 0) nzero++; else totspeed += pch->speed; pch->avail = 2; ++nfree; ++totfree; } if (!pch->had_frag && i < ppp->nxchan) ppp->nxchan = i; } ++i; } /* * Don't start sending this packet unless at least half of * the channels are free. This gives much better TCP * performance if we have a lot of channels. */ if (nfree == 0 || nfree < navail / 2) return 0; /* can't take now, leave it in xmit_pending */ /* Do protocol field compression */ p = skb->data; len = skb->len; if (*p == 0 && mp_protocol_compress) { ++p; --len; } totlen = len; nbigger = len % nfree; /* skip to the channel after the one we last used and start at that one */ list = &ppp->channels; for (i = 0; i < ppp->nxchan; ++i) { list = list->next; if (list == &ppp->channels) { i = 0; break; } } /* create a fragment for each channel */ bits = B; while (len > 0) { list = list->next; if (list == &ppp->channels) { i = 0; continue; } pch = list_entry(list, struct channel, clist); ++i; if (!pch->avail) continue; /* * Skip this channel if it has a fragment pending already and * we haven't given a fragment to all of the free channels. */ if (pch->avail == 1) { if (nfree > 0) continue; } else { pch->avail = 1; } /* check the channel's mtu and whether it is still attached. */ spin_lock(&pch->downl); if (pch->chan == NULL) { /* can't use this channel, it's being deregistered */ if (pch->speed == 0) nzero--; else totspeed -= pch->speed; spin_unlock(&pch->downl); pch->avail = 0; totlen = len; totfree--; nfree--; if (--navail == 0) break; continue; } /* *if the channel speed is not set divide *the packet evenly among the free channels; *otherwise divide it according to the speed *of the channel we are going to transmit on */ flen = len; if (nfree > 0) { if (pch->speed == 0) { flen = len/nfree; if (nbigger > 0) { flen++; nbigger--; } } else { flen = (((totfree - nzero)*(totlen + hdrlen*totfree)) / ((totspeed*totfree)/pch->speed)) - hdrlen; if (nbigger > 0) { flen += ((totfree - nzero)*pch->speed)/totspeed; nbigger -= ((totfree - nzero)*pch->speed)/ totspeed; } } nfree--; } /* *check if we are on the last channel or *we exceded the length of the data to *fragment */ if ((nfree <= 0) || (flen > len)) flen = len; /* *it is not worth to tx on slow channels: *in that case from the resulting flen according to the *above formula will be equal or less than zero. *Skip the channel in this case */ if (flen <= 0) { pch->avail = 2; spin_unlock(&pch->downl); continue; } /* * hdrlen includes the 2-byte PPP protocol field, but the * MTU counts only the payload excluding the protocol field. * (RFC1661 Section 2) */ mtu = pch->chan->mtu - (hdrlen - 2); if (mtu < 4) mtu = 4; if (flen > mtu) flen = mtu; if (flen == len) bits |= E; frag = alloc_skb(flen + hdrlen + (flen == 0), GFP_ATOMIC); if (!frag) goto noskb; q = skb_put(frag, flen + hdrlen); /* make the MP header */ put_unaligned_be16(PPP_MP, q); if (ppp->flags & SC_MP_XSHORTSEQ) { q[2] = bits + ((ppp->nxseq >> 8) & 0xf); q[3] = ppp->nxseq; } else { q[2] = bits; q[3] = ppp->nxseq >> 16; q[4] = ppp->nxseq >> 8; q[5] = ppp->nxseq; } memcpy(q + hdrlen, p, flen); /* try to send it down the channel */ chan = pch->chan; if (!skb_queue_empty(&pch->file.xq) || !chan->ops->start_xmit(chan, frag)) skb_queue_tail(&pch->file.xq, frag); pch->had_frag = 1; p += flen; len -= flen; ++ppp->nxseq; bits = 0; spin_unlock(&pch->downl); } ppp->nxchan = i; return 1; noskb: spin_unlock(&pch->downl); if (ppp->debug & 1) netdev_err(ppp->dev, "PPP: no memory (fragment)\n"); ++ppp->dev->stats.tx_errors; ++ppp->nxseq; return 1; /* abandon the frame */ } #endif /* CONFIG_PPP_MULTILINK */ /* Try to send data out on a channel */ static void __ppp_channel_push(struct channel *pch) { struct sk_buff *skb; struct ppp *ppp; spin_lock(&pch->downl); if (pch->chan) { while (!skb_queue_empty(&pch->file.xq)) { skb = skb_dequeue(&pch->file.xq); if (!pch->chan->ops->start_xmit(pch->chan, skb)) { /* put the packet back and try again later */ skb_queue_head(&pch->file.xq, skb); break; } } } else { /* channel got deregistered */ skb_queue_purge(&pch->file.xq); } spin_unlock(&pch->downl); /* see if there is anything from the attached unit to be sent */ if (skb_queue_empty(&pch->file.xq)) { ppp = pch->ppp; if (ppp) __ppp_xmit_process(ppp, NULL); } } static void ppp_channel_push(struct channel *pch) { read_lock_bh(&pch->upl); if (pch->ppp) { (*this_cpu_ptr(pch->ppp->xmit_recursion))++; __ppp_channel_push(pch); (*this_cpu_ptr(pch->ppp->xmit_recursion))--; } else { __ppp_channel_push(pch); } read_unlock_bh(&pch->upl); } /* * Receive-side routines. */ struct ppp_mp_skb_parm { u32 sequence; u8 BEbits; }; #define PPP_MP_CB(skb) ((struct ppp_mp_skb_parm *)((skb)->cb)) static inline void ppp_do_recv(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { ppp_recv_lock(ppp); if (!ppp->closing) ppp_receive_frame(ppp, skb, pch); else kfree_skb(skb); ppp_recv_unlock(ppp); } /** * __ppp_decompress_proto - Decompress protocol field, slim version. * @skb: Socket buffer where protocol field should be decompressed. It must have * at least 1 byte of head room and 1 byte of linear data. First byte of * data must be a protocol field byte. * * Decompress protocol field in PPP header if it's compressed, e.g. when * Protocol-Field-Compression (PFC) was negotiated. No checks w.r.t. skb data * length are done in this function. */ static void __ppp_decompress_proto(struct sk_buff *skb) { if (skb->data[0] & 0x01) *(u8 *)skb_push(skb, 1) = 0x00; } /** * ppp_decompress_proto - Check skb data room and decompress protocol field. * @skb: Socket buffer where protocol field should be decompressed. First byte * of data must be a protocol field byte. * * Decompress protocol field in PPP header if it's compressed, e.g. when * Protocol-Field-Compression (PFC) was negotiated. This function also makes * sure that skb data room is sufficient for Protocol field, before and after * decompression. * * Return: true - decompressed successfully, false - not enough room in skb. */ static bool ppp_decompress_proto(struct sk_buff *skb) { /* At least one byte should be present (if protocol is compressed) */ if (!pskb_may_pull(skb, 1)) return false; __ppp_decompress_proto(skb); /* Protocol field should occupy 2 bytes when not compressed */ return pskb_may_pull(skb, 2); } /* Attempt to handle a frame via. a bridged channel, if one exists. * If the channel is bridged, the frame is consumed by the bridge. * If not, the caller must handle the frame by normal recv mechanisms. * Returns true if the frame is consumed, false otherwise. */ static bool ppp_channel_bridge_input(struct channel *pch, struct sk_buff *skb) { struct channel *pchb; rcu_read_lock(); pchb = rcu_dereference(pch->bridge); if (!pchb) goto out_rcu; spin_lock_bh(&pchb->downl); if (!pchb->chan) { /* channel got unregistered */ kfree_skb(skb); goto outl; } skb_scrub_packet(skb, !net_eq(pch->chan_net, pchb->chan_net)); if (!pchb->chan->ops->start_xmit(pchb->chan, skb)) kfree_skb(skb); outl: spin_unlock_bh(&pchb->downl); out_rcu: rcu_read_unlock(); /* If pchb is set then we've consumed the packet */ return !!pchb; } void ppp_input(struct ppp_channel *chan, struct sk_buff *skb) { struct channel *pch = chan->ppp; int proto; if (!pch) { kfree_skb(skb); return; } /* If the channel is bridged, transmit via. bridge */ if (ppp_channel_bridge_input(pch, skb)) return; read_lock_bh(&pch->upl); if (!ppp_decompress_proto(skb)) { kfree_skb(skb); if (pch->ppp) { ++pch->ppp->dev->stats.rx_length_errors; ppp_receive_error(pch->ppp); } goto done; } proto = PPP_PROTO(skb); if (!pch->ppp || proto >= 0xc000 || proto == PPP_CCPFRAG) { /* put it on the channel queue */ skb_queue_tail(&pch->file.rq, skb); /* drop old frames if queue too long */ while (pch->file.rq.qlen > PPP_MAX_RQLEN && (skb = skb_dequeue(&pch->file.rq))) kfree_skb(skb); wake_up_interruptible(&pch->file.rwait); } else { ppp_do_recv(pch->ppp, skb, pch); } done: read_unlock_bh(&pch->upl); } /* Put a 0-length skb in the receive queue as an error indication */ void ppp_input_error(struct ppp_channel *chan, int code) { struct channel *pch = chan->ppp; struct sk_buff *skb; if (!pch) return; read_lock_bh(&pch->upl); if (pch->ppp) { skb = alloc_skb(0, GFP_ATOMIC); if (skb) { skb->len = 0; /* probably unnecessary */ skb->cb[0] = code; ppp_do_recv(pch->ppp, skb, pch); } } read_unlock_bh(&pch->upl); } /* * We come in here to process a received frame. * The receive side of the ppp unit is locked. */ static void ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { /* note: a 0-length skb is used as an error indication */ if (skb->len > 0) { skb_checksum_complete_unset(skb); #ifdef CONFIG_PPP_MULTILINK /* XXX do channel-level decompression here */ if (PPP_PROTO(skb) == PPP_MP) ppp_receive_mp_frame(ppp, skb, pch); else #endif /* CONFIG_PPP_MULTILINK */ ppp_receive_nonmp_frame(ppp, skb); } else { kfree_skb(skb); ppp_receive_error(ppp); } } static void ppp_receive_error(struct ppp *ppp) { ++ppp->dev->stats.rx_errors; if (ppp->vj) slhc_toss(ppp->vj); } static void ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *ns; int proto, len, npi; /* * Decompress the frame, if compressed. * Note that some decompressors need to see uncompressed frames * that come in as well as compressed frames. */ if (ppp->rc_state && (ppp->rstate & SC_DECOMP_RUN) && (ppp->rstate & (SC_DC_FERROR | SC_DC_ERROR)) == 0) skb = ppp_decompress_frame(ppp, skb); if (ppp->flags & SC_MUST_COMP && ppp->rstate & SC_DC_FERROR) goto err; /* At this point the "Protocol" field MUST be decompressed, either in * ppp_input(), ppp_decompress_frame() or in ppp_receive_mp_frame(). */ proto = PPP_PROTO(skb); switch (proto) { case PPP_VJC_COMP: /* decompress VJ compressed packets */ if (!ppp->vj || (ppp->flags & SC_REJ_COMP_TCP)) goto err; if (skb_tailroom(skb) < 124 || skb_cloned(skb)) { /* copy to a new sk_buff with more tailroom */ ns = dev_alloc_skb(skb->len + 128); if (!ns) { netdev_err(ppp->dev, "PPP: no memory " "(VJ decomp)\n"); goto err; } skb_reserve(ns, 2); skb_copy_bits(skb, 0, skb_put(ns, skb->len), skb->len); consume_skb(skb); skb = ns; } else skb->ip_summed = CHECKSUM_NONE; len = slhc_uncompress(ppp->vj, skb->data + 2, skb->len - 2); if (len <= 0) { netdev_printk(KERN_DEBUG, ppp->dev, "PPP: VJ decompression error\n"); goto err; } len += 2; if (len > skb->len) skb_put(skb, len - skb->len); else if (len < skb->len) skb_trim(skb, len); proto = PPP_IP; break; case PPP_VJC_UNCOMP: if (!ppp->vj || (ppp->flags & SC_REJ_COMP_TCP)) goto err; /* Until we fix the decompressor need to make sure * data portion is linear. */ if (!pskb_may_pull(skb, skb->len)) goto err; if (slhc_remember(ppp->vj, skb->data + 2, skb->len - 2) <= 0) { netdev_err(ppp->dev, "PPP: VJ uncompressed error\n"); goto err; } proto = PPP_IP; break; case PPP_CCP: ppp_ccp_peek(ppp, skb, 1); break; } ++ppp->stats64.rx_packets; ppp->stats64.rx_bytes += skb->len - 2; npi = proto_to_npindex(proto); if (npi < 0) { /* control or unknown frame - pass it to pppd */ skb_queue_tail(&ppp->file.rq, skb); /* limit queue length by dropping old frames */ while (ppp->file.rq.qlen > PPP_MAX_RQLEN && (skb = skb_dequeue(&ppp->file.rq))) kfree_skb(skb); /* wake up any process polling or blocking on read */ wake_up_interruptible(&ppp->file.rwait); } else { /* network protocol frame - give it to the kernel */ #ifdef CONFIG_PPP_FILTER if (ppp->pass_filter || ppp->active_filter) { if (skb_unclone(skb, GFP_ATOMIC)) goto err; /* Check if the packet passes the pass and active filters. * See comment for PPP_FILTER_INBOUND_TAG above. */ *(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_INBOUND_TAG); if (ppp->pass_filter && bpf_prog_run(ppp->pass_filter, skb) == 0) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: inbound frame " "not passed\n"); kfree_skb(skb); return; } if (!(ppp->active_filter && bpf_prog_run(ppp->active_filter, skb) == 0)) ppp->last_recv = jiffies; __skb_pull(skb, 2); } else #endif /* CONFIG_PPP_FILTER */ ppp->last_recv = jiffies; if ((ppp->dev->flags & IFF_UP) == 0 || ppp->npmode[npi] != NPMODE_PASS) { kfree_skb(skb); } else { /* chop off protocol */ skb_pull_rcsum(skb, 2); skb->dev = ppp->dev; skb->protocol = htons(npindex_to_ethertype[npi]); skb_reset_mac_header(skb); skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(ppp->dev))); netif_rx(skb); } } return; err: kfree_skb(skb); ppp_receive_error(ppp); } static struct sk_buff * ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb) { int proto = PPP_PROTO(skb); struct sk_buff *ns; int len; /* Until we fix all the decompressor's need to make sure * data portion is linear. */ if (!pskb_may_pull(skb, skb->len)) goto err; if (proto == PPP_COMP) { int obuff_size; switch(ppp->rcomp->compress_proto) { case CI_MPPE: obuff_size = ppp->mru + PPP_HDRLEN + 1; break; default: obuff_size = ppp->mru + PPP_HDRLEN; break; } ns = dev_alloc_skb(obuff_size); if (!ns) { netdev_err(ppp->dev, "ppp_decompress_frame: " "no memory\n"); goto err; } /* the decompressor still expects the A/C bytes in the hdr */ len = ppp->rcomp->decompress(ppp->rc_state, skb->data - 2, skb->len + 2, ns->data, obuff_size); if (len < 0) { /* Pass the compressed frame to pppd as an error indication. */ if (len == DECOMP_FATALERROR) ppp->rstate |= SC_DC_FERROR; kfree_skb(ns); goto err; } consume_skb(skb); skb = ns; skb_put(skb, len); skb_pull(skb, 2); /* pull off the A/C bytes */ /* Don't call __ppp_decompress_proto() here, but instead rely on * corresponding algo (mppe/bsd/deflate) to decompress it. */ } else { /* Uncompressed frame - pass to decompressor so it can update its dictionary if necessary. */ if (ppp->rcomp->incomp) ppp->rcomp->incomp(ppp->rc_state, skb->data - 2, skb->len + 2); } return skb; err: ppp->rstate |= SC_DC_ERROR; ppp_receive_error(ppp); return skb; } #ifdef CONFIG_PPP_MULTILINK /* * Receive a multilink frame. * We put it on the reconstruction queue and then pull off * as many completed frames as we can. */ static void ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { u32 mask, seq; struct channel *ch; int mphdrlen = (ppp->flags & SC_MP_SHORTSEQ)? MPHDRLEN_SSN: MPHDRLEN; if (!pskb_may_pull(skb, mphdrlen + 1) || ppp->mrru == 0) goto err; /* no good, throw it away */ /* Decode sequence number and begin/end bits */ if (ppp->flags & SC_MP_SHORTSEQ) { seq = ((skb->data[2] & 0x0f) << 8) | skb->data[3]; mask = 0xfff; } else { seq = (skb->data[3] << 16) | (skb->data[4] << 8)| skb->data[5]; mask = 0xffffff; } PPP_MP_CB(skb)->BEbits = skb->data[2]; skb_pull(skb, mphdrlen); /* pull off PPP and MP headers */ /* * Do protocol ID decompression on the first fragment of each packet. * We have to do that here, because ppp_receive_nonmp_frame() expects * decompressed protocol field. */ if (PPP_MP_CB(skb)->BEbits & B) __ppp_decompress_proto(skb); /* * Expand sequence number to 32 bits, making it as close * as possible to ppp->minseq. */ seq |= ppp->minseq & ~mask; if ((int)(ppp->minseq - seq) > (int)(mask >> 1)) seq += mask + 1; else if ((int)(seq - ppp->minseq) > (int)(mask >> 1)) seq -= mask + 1; /* should never happen */ PPP_MP_CB(skb)->sequence = seq; pch->lastseq = seq; /* * If this packet comes before the next one we were expecting, * drop it. */ if (seq_before(seq, ppp->nextseq)) { kfree_skb(skb); ++ppp->dev->stats.rx_dropped; ppp_receive_error(ppp); return; } /* * Reevaluate minseq, the minimum over all channels of the * last sequence number received on each channel. Because of * the increasing sequence number rule, we know that any fragment * before `minseq' which hasn't arrived is never going to arrive. * The list of channels can't change because we have the receive * side of the ppp unit locked. */ list_for_each_entry(ch, &ppp->channels, clist) { if (seq_before(ch->lastseq, seq)) seq = ch->lastseq; } if (seq_before(ppp->minseq, seq)) ppp->minseq = seq; /* Put the fragment on the reconstruction queue */ ppp_mp_insert(ppp, skb); /* If the queue is getting long, don't wait any longer for packets before the start of the queue. */ if (skb_queue_len(&ppp->mrq) >= PPP_MP_MAX_QLEN) { struct sk_buff *mskb = skb_peek(&ppp->mrq); if (seq_before(ppp->minseq, PPP_MP_CB(mskb)->sequence)) ppp->minseq = PPP_MP_CB(mskb)->sequence; } /* Pull completed packets off the queue and receive them. */ while ((skb = ppp_mp_reconstruct(ppp))) { if (pskb_may_pull(skb, 2)) ppp_receive_nonmp_frame(ppp, skb); else { ++ppp->dev->stats.rx_length_errors; kfree_skb(skb); ppp_receive_error(ppp); } } return; err: kfree_skb(skb); ppp_receive_error(ppp); } /* * Insert a fragment on the MP reconstruction queue. * The queue is ordered by increasing sequence number. */ static void ppp_mp_insert(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *p; struct sk_buff_head *list = &ppp->mrq; u32 seq = PPP_MP_CB(skb)->sequence; /* N.B. we don't need to lock the list lock because we have the ppp unit receive-side lock. */ skb_queue_walk(list, p) { if (seq_before(seq, PPP_MP_CB(p)->sequence)) break; } __skb_queue_before(list, p, skb); } /* * Reconstruct a packet from the MP fragment queue. * We go through increasing sequence numbers until we find a * complete packet, or we get to the sequence number for a fragment * which hasn't arrived but might still do so. */ static struct sk_buff * ppp_mp_reconstruct(struct ppp *ppp) { u32 seq = ppp->nextseq; u32 minseq = ppp->minseq; struct sk_buff_head *list = &ppp->mrq; struct sk_buff *p, *tmp; struct sk_buff *head, *tail; struct sk_buff *skb = NULL; int lost = 0, len = 0; if (ppp->mrru == 0) /* do nothing until mrru is set */ return NULL; head = __skb_peek(list); tail = NULL; skb_queue_walk_safe(list, p, tmp) { again: if (seq_before(PPP_MP_CB(p)->sequence, seq)) { /* this can't happen, anyway ignore the skb */ netdev_err(ppp->dev, "ppp_mp_reconstruct bad " "seq %u < %u\n", PPP_MP_CB(p)->sequence, seq); __skb_unlink(p, list); kfree_skb(p); continue; } if (PPP_MP_CB(p)->sequence != seq) { u32 oldseq; /* Fragment `seq' is missing. If it is after minseq, it might arrive later, so stop here. */ if (seq_after(seq, minseq)) break; /* Fragment `seq' is lost, keep going. */ lost = 1; oldseq = seq; seq = seq_before(minseq, PPP_MP_CB(p)->sequence)? minseq + 1: PPP_MP_CB(p)->sequence; if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "lost frag %u..%u\n", oldseq, seq-1); goto again; } /* * At this point we know that all the fragments from * ppp->nextseq to seq are either present or lost. * Also, there are no complete packets in the queue * that have no missing fragments and end before this * fragment. */ /* B bit set indicates this fragment starts a packet */ if (PPP_MP_CB(p)->BEbits & B) { head = p; lost = 0; len = 0; } len += p->len; /* Got a complete packet yet? */ if (lost == 0 && (PPP_MP_CB(p)->BEbits & E) && (PPP_MP_CB(head)->BEbits & B)) { if (len > ppp->mrru + 2) { ++ppp->dev->stats.rx_length_errors; netdev_printk(KERN_DEBUG, ppp->dev, "PPP: reconstructed packet" " is too long (%d)\n", len); } else { tail = p; break; } ppp->nextseq = seq + 1; } /* * If this is the ending fragment of a packet, * and we haven't found a complete valid packet yet, * we can discard up to and including this fragment. */ if (PPP_MP_CB(p)->BEbits & E) { struct sk_buff *tmp2; skb_queue_reverse_walk_from_safe(list, p, tmp2) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "discarding frag %u\n", PPP_MP_CB(p)->sequence); __skb_unlink(p, list); kfree_skb(p); } head = skb_peek(list); if (!head) break; } ++seq; } /* If we have a complete packet, copy it all into one skb. */ if (tail != NULL) { /* If we have discarded any fragments, signal a receive error. */ if (PPP_MP_CB(head)->sequence != ppp->nextseq) { skb_queue_walk_safe(list, p, tmp) { if (p == head) break; if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "discarding frag %u\n", PPP_MP_CB(p)->sequence); __skb_unlink(p, list); kfree_skb(p); } if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, " missed pkts %u..%u\n", ppp->nextseq, PPP_MP_CB(head)->sequence-1); ++ppp->dev->stats.rx_dropped; ppp_receive_error(ppp); } skb = head; if (head != tail) { struct sk_buff **fragpp = &skb_shinfo(skb)->frag_list; p = skb_queue_next(list, head); __skb_unlink(skb, list); skb_queue_walk_from_safe(list, p, tmp) { __skb_unlink(p, list); *fragpp = p; p->next = NULL; fragpp = &p->next; skb->len += p->len; skb->data_len += p->len; skb->truesize += p->truesize; if (p == tail) break; } } else { __skb_unlink(skb, list); } ppp->nextseq = PPP_MP_CB(tail)->sequence + 1; } return skb; } #endif /* CONFIG_PPP_MULTILINK */ /* * Channel interface. */ /* Create a new, unattached ppp channel. */ int ppp_register_channel(struct ppp_channel *chan) { return ppp_register_net_channel(current->nsproxy->net_ns, chan); } /* Create a new, unattached ppp channel for specified net. */ int ppp_register_net_channel(struct net *net, struct ppp_channel *chan) { struct channel *pch; struct ppp_net *pn; pch = kzalloc(sizeof(struct channel), GFP_KERNEL); if (!pch) return -ENOMEM; pn = ppp_pernet(net); pch->ppp = NULL; pch->chan = chan; pch->chan_net = get_net(net); chan->ppp = pch; init_ppp_file(&pch->file, CHANNEL); pch->file.hdrlen = chan->hdrlen; #ifdef CONFIG_PPP_MULTILINK pch->lastseq = -1; #endif /* CONFIG_PPP_MULTILINK */ init_rwsem(&pch->chan_sem); spin_lock_init(&pch->downl); rwlock_init(&pch->upl); spin_lock_bh(&pn->all_channels_lock); pch->file.index = ++pn->last_channel_index; list_add(&pch->list, &pn->new_channels); atomic_inc(&channel_count); spin_unlock_bh(&pn->all_channels_lock); return 0; } /* * Return the index of a channel. */ int ppp_channel_index(struct ppp_channel *chan) { struct channel *pch = chan->ppp; if (pch) return pch->file.index; return -1; } /* * Return the PPP unit number to which a channel is connected. */ int ppp_unit_number(struct ppp_channel *chan) { struct channel *pch = chan->ppp; int unit = -1; if (pch) { read_lock_bh(&pch->upl); if (pch->ppp) unit = pch->ppp->file.index; read_unlock_bh(&pch->upl); } return unit; } /* * Return the PPP device interface name of a channel. */ char *ppp_dev_name(struct ppp_channel *chan) { struct channel *pch = chan->ppp; char *name = NULL; if (pch) { read_lock_bh(&pch->upl); if (pch->ppp && pch->ppp->dev) name = pch->ppp->dev->name; read_unlock_bh(&pch->upl); } return name; } /* * Disconnect a channel from the generic layer. * This must be called in process context. */ void ppp_unregister_channel(struct ppp_channel *chan) { struct channel *pch = chan->ppp; struct ppp_net *pn; if (!pch) return; /* should never happen */ chan->ppp = NULL; /* * This ensures that we have returned from any calls into the * the channel's start_xmit or ioctl routine before we proceed. */ down_write(&pch->chan_sem); spin_lock_bh(&pch->downl); pch->chan = NULL; spin_unlock_bh(&pch->downl); up_write(&pch->chan_sem); ppp_disconnect_channel(pch); pn = ppp_pernet(pch->chan_net); spin_lock_bh(&pn->all_channels_lock); list_del(&pch->list); spin_unlock_bh(&pn->all_channels_lock); ppp_unbridge_channels(pch); pch->file.dead = 1; wake_up_interruptible(&pch->file.rwait); if (refcount_dec_and_test(&pch->file.refcnt)) ppp_destroy_channel(pch); } /* * Callback from a channel when it can accept more to transmit. * This should be called at BH/softirq level, not interrupt level. */ void ppp_output_wakeup(struct ppp_channel *chan) { struct channel *pch = chan->ppp; if (!pch) return; ppp_channel_push(pch); } /* * Compression control. */ /* Process the PPPIOCSCOMPRESS ioctl. */ static int ppp_set_compress(struct ppp *ppp, struct ppp_option_data *data) { int err = -EFAULT; struct compressor *cp, *ocomp; void *state, *ostate; unsigned char ccp_option[CCP_MAX_OPTION_LENGTH]; if (data->length > CCP_MAX_OPTION_LENGTH) goto out; if (copy_from_user(ccp_option, data->ptr, data->length)) goto out; err = -EINVAL; if (data->length < 2 || ccp_option[1] < 2 || ccp_option[1] > data->length) goto out; cp = try_then_request_module( find_compressor(ccp_option[0]), "ppp-compress-%d", ccp_option[0]); if (!cp) goto out; err = -ENOBUFS; if (data->transmit) { state = cp->comp_alloc(ccp_option, data->length); if (state) { ppp_xmit_lock(ppp); ppp->xstate &= ~SC_COMP_RUN; ocomp = ppp->xcomp; ostate = ppp->xc_state; ppp->xcomp = cp; ppp->xc_state = state; ppp_xmit_unlock(ppp); if (ostate) { ocomp->comp_free(ostate); module_put(ocomp->owner); } err = 0; } else module_put(cp->owner); } else { state = cp->decomp_alloc(ccp_option, data->length); if (state) { ppp_recv_lock(ppp); ppp->rstate &= ~SC_DECOMP_RUN; ocomp = ppp->rcomp; ostate = ppp->rc_state; ppp->rcomp = cp; ppp->rc_state = state; ppp_recv_unlock(ppp); if (ostate) { ocomp->decomp_free(ostate); module_put(ocomp->owner); } err = 0; } else module_put(cp->owner); } out: return err; } /* * Look at a CCP packet and update our state accordingly. * We assume the caller has the xmit or recv path locked. */ static void ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound) { unsigned char *dp; int len; if (!pskb_may_pull(skb, CCP_HDRLEN + 2)) return; /* no header */ dp = skb->data + 2; switch (CCP_CODE(dp)) { case CCP_CONFREQ: /* A ConfReq starts negotiation of compression * in one direction of transmission, * and hence brings it down...but which way? * * Remember: * A ConfReq indicates what the sender would like to receive */ if(inbound) /* He is proposing what I should send */ ppp->xstate &= ~SC_COMP_RUN; else /* I am proposing to what he should send */ ppp->rstate &= ~SC_DECOMP_RUN; break; case CCP_TERMREQ: case CCP_TERMACK: /* * CCP is going down, both directions of transmission */ ppp->rstate &= ~SC_DECOMP_RUN; ppp->xstate &= ~SC_COMP_RUN; break; case CCP_CONFACK: if ((ppp->flags & (SC_CCP_OPEN | SC_CCP_UP)) != SC_CCP_OPEN) break; len = CCP_LENGTH(dp); if (!pskb_may_pull(skb, len + 2)) return; /* too short */ dp += CCP_HDRLEN; len -= CCP_HDRLEN; if (len < CCP_OPT_MINLEN || len < CCP_OPT_LENGTH(dp)) break; if (inbound) { /* we will start receiving compressed packets */ if (!ppp->rc_state) break; if (ppp->rcomp->decomp_init(ppp->rc_state, dp, len, ppp->file.index, 0, ppp->mru, ppp->debug)) { ppp->rstate |= SC_DECOMP_RUN; ppp->rstate &= ~(SC_DC_ERROR | SC_DC_FERROR); } } else { /* we will soon start sending compressed packets */ if (!ppp->xc_state) break; if (ppp->xcomp->comp_init(ppp->xc_state, dp, len, ppp->file.index, 0, ppp->debug)) ppp->xstate |= SC_COMP_RUN; } break; case CCP_RESETACK: /* reset the [de]compressor */ if ((ppp->flags & SC_CCP_UP) == 0) break; if (inbound) { if (ppp->rc_state && (ppp->rstate & SC_DECOMP_RUN)) { ppp->rcomp->decomp_reset(ppp->rc_state); ppp->rstate &= ~SC_DC_ERROR; } } else { if (ppp->xc_state && (ppp->xstate & SC_COMP_RUN)) ppp->xcomp->comp_reset(ppp->xc_state); } break; } } /* Free up compression resources. */ static void ppp_ccp_closed(struct ppp *ppp) { void *xstate, *rstate; struct compressor *xcomp, *rcomp; ppp_lock(ppp); ppp->flags &= ~(SC_CCP_OPEN | SC_CCP_UP); ppp->xstate = 0; xcomp = ppp->xcomp; xstate = ppp->xc_state; ppp->xc_state = NULL; ppp->rstate = 0; rcomp = ppp->rcomp; rstate = ppp->rc_state; ppp->rc_state = NULL; ppp_unlock(ppp); if (xstate) { xcomp->comp_free(xstate); module_put(xcomp->owner); } if (rstate) { rcomp->decomp_free(rstate); module_put(rcomp->owner); } } /* List of compressors. */ static LIST_HEAD(compressor_list); static DEFINE_SPINLOCK(compressor_list_lock); struct compressor_entry { struct list_head list; struct compressor *comp; }; static struct compressor_entry * find_comp_entry(int proto) { struct compressor_entry *ce; list_for_each_entry(ce, &compressor_list, list) { if (ce->comp->compress_proto == proto) return ce; } return NULL; } /* Register a compressor */ int ppp_register_compressor(struct compressor *cp) { struct compressor_entry *ce; int ret; spin_lock(&compressor_list_lock); ret = -EEXIST; if (find_comp_entry(cp->compress_proto)) goto out; ret = -ENOMEM; ce = kmalloc(sizeof(struct compressor_entry), GFP_ATOMIC); if (!ce) goto out; ret = 0; ce->comp = cp; list_add(&ce->list, &compressor_list); out: spin_unlock(&compressor_list_lock); return ret; } /* Unregister a compressor */ void ppp_unregister_compressor(struct compressor *cp) { struct compressor_entry *ce; spin_lock(&compressor_list_lock); ce = find_comp_entry(cp->compress_proto); if (ce && ce->comp == cp) { list_del(&ce->list); kfree(ce); } spin_unlock(&compressor_list_lock); } /* Find a compressor. */ static struct compressor * find_compressor(int type) { struct compressor_entry *ce; struct compressor *cp = NULL; spin_lock(&compressor_list_lock); ce = find_comp_entry(type); if (ce) { cp = ce->comp; if (!try_module_get(cp->owner)) cp = NULL; } spin_unlock(&compressor_list_lock); return cp; } /* * Miscelleneous stuff. */ static void ppp_get_stats(struct ppp *ppp, struct ppp_stats *st) { struct slcompress *vj = ppp->vj; memset(st, 0, sizeof(*st)); st->p.ppp_ipackets = ppp->stats64.rx_packets; st->p.ppp_ierrors = ppp->dev->stats.rx_errors; st->p.ppp_ibytes = ppp->stats64.rx_bytes; st->p.ppp_opackets = ppp->stats64.tx_packets; st->p.ppp_oerrors = ppp->dev->stats.tx_errors; st->p.ppp_obytes = ppp->stats64.tx_bytes; if (!vj) return; st->vj.vjs_packets = vj->sls_o_compressed + vj->sls_o_uncompressed; st->vj.vjs_compressed = vj->sls_o_compressed; st->vj.vjs_searches = vj->sls_o_searches; st->vj.vjs_misses = vj->sls_o_misses; st->vj.vjs_errorin = vj->sls_i_error; st->vj.vjs_tossed = vj->sls_i_tossed; st->vj.vjs_uncompressedin = vj->sls_i_uncompressed; st->vj.vjs_compressedin = vj->sls_i_compressed; } /* * Stuff for handling the lists of ppp units and channels * and for initialization. */ /* * Create a new ppp interface unit. Fails if it can't allocate memory * or if there is already a unit with the requested number. * unit == -1 means allocate a new number. */ static int ppp_create_interface(struct net *net, struct file *file, int *unit) { struct ppp_config conf = { .file = file, .unit = *unit, .ifname_is_set = false, }; struct net_device *dev; struct ppp *ppp; int err; dev = alloc_netdev(sizeof(struct ppp), "", NET_NAME_ENUM, ppp_setup); if (!dev) { err = -ENOMEM; goto err; } dev_net_set(dev, net); dev->rtnl_link_ops = &ppp_link_ops; rtnl_lock(); err = ppp_dev_configure(net, dev, &conf); if (err < 0) goto err_dev; ppp = netdev_priv(dev); *unit = ppp->file.index; rtnl_unlock(); return 0; err_dev: rtnl_unlock(); free_netdev(dev); err: return err; } /* * Initialize a ppp_file structure. */ static void init_ppp_file(struct ppp_file *pf, int kind) { pf->kind = kind; skb_queue_head_init(&pf->xq); skb_queue_head_init(&pf->rq); refcount_set(&pf->refcnt, 1); init_waitqueue_head(&pf->rwait); } /* * Free the memory used by a ppp unit. This is only called once * there are no channels connected to the unit and no file structs * that reference the unit. */ static void ppp_destroy_interface(struct ppp *ppp) { atomic_dec(&ppp_unit_count); if (!ppp->file.dead || ppp->n_channels) { /* "can't happen" */ netdev_err(ppp->dev, "ppp: destroying ppp struct %p " "but dead=%d n_channels=%d !\n", ppp, ppp->file.dead, ppp->n_channels); return; } ppp_ccp_closed(ppp); if (ppp->vj) { slhc_free(ppp->vj); ppp->vj = NULL; } skb_queue_purge(&ppp->file.xq); skb_queue_purge(&ppp->file.rq); #ifdef CONFIG_PPP_MULTILINK skb_queue_purge(&ppp->mrq); #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER if (ppp->pass_filter) { bpf_prog_destroy(ppp->pass_filter); ppp->pass_filter = NULL; } if (ppp->active_filter) { bpf_prog_destroy(ppp->active_filter); ppp->active_filter = NULL; } #endif /* CONFIG_PPP_FILTER */ kfree_skb(ppp->xmit_pending); free_percpu(ppp->xmit_recursion); free_netdev(ppp->dev); } /* * Locate an existing ppp unit. * The caller should have locked the all_ppp_mutex. */ static struct ppp * ppp_find_unit(struct ppp_net *pn, int unit) { return unit_find(&pn->units_idr, unit); } /* * Locate an existing ppp channel. * The caller should have locked the all_channels_lock. * First we look in the new_channels list, then in the * all_channels list. If found in the new_channels list, * we move it to the all_channels list. This is for speed * when we have a lot of channels in use. */ static struct channel * ppp_find_channel(struct ppp_net *pn, int unit) { struct channel *pch; list_for_each_entry(pch, &pn->new_channels, list) { if (pch->file.index == unit) { list_move(&pch->list, &pn->all_channels); return pch; } } list_for_each_entry(pch, &pn->all_channels, list) { if (pch->file.index == unit) return pch; } return NULL; } /* * Connect a PPP channel to a PPP interface unit. */ static int ppp_connect_channel(struct channel *pch, int unit) { struct ppp *ppp; struct ppp_net *pn; int ret = -ENXIO; int hdrlen; pn = ppp_pernet(pch->chan_net); mutex_lock(&pn->all_ppp_mutex); ppp = ppp_find_unit(pn, unit); if (!ppp) goto out; write_lock_bh(&pch->upl); ret = -EINVAL; if (pch->ppp || rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl))) goto outl; ppp_lock(ppp); spin_lock_bh(&pch->downl); if (!pch->chan) { /* Don't connect unregistered channels */ spin_unlock_bh(&pch->downl); ppp_unlock(ppp); ret = -ENOTCONN; goto outl; } spin_unlock_bh(&pch->downl); if (pch->file.hdrlen > ppp->file.hdrlen) ppp->file.hdrlen = pch->file.hdrlen; hdrlen = pch->file.hdrlen + 2; /* for protocol bytes */ if (hdrlen > ppp->dev->hard_header_len) ppp->dev->hard_header_len = hdrlen; list_add_tail(&pch->clist, &ppp->channels); ++ppp->n_channels; pch->ppp = ppp; refcount_inc(&ppp->file.refcnt); ppp_unlock(ppp); ret = 0; outl: write_unlock_bh(&pch->upl); out: mutex_unlock(&pn->all_ppp_mutex); return ret; } /* * Disconnect a channel from its ppp unit. */ static int ppp_disconnect_channel(struct channel *pch) { struct ppp *ppp; int err = -EINVAL; write_lock_bh(&pch->upl); ppp = pch->ppp; pch->ppp = NULL; write_unlock_bh(&pch->upl); if (ppp) { /* remove it from the ppp unit's list */ ppp_lock(ppp); list_del(&pch->clist); if (--ppp->n_channels == 0) wake_up_interruptible(&ppp->file.rwait); ppp_unlock(ppp); if (refcount_dec_and_test(&ppp->file.refcnt)) ppp_destroy_interface(ppp); err = 0; } return err; } /* * Free up the resources used by a ppp channel. */ static void ppp_destroy_channel(struct channel *pch) { put_net(pch->chan_net); pch->chan_net = NULL; atomic_dec(&channel_count); if (!pch->file.dead) { /* "can't happen" */ pr_err("ppp: destroying undead channel %p !\n", pch); return; } skb_queue_purge(&pch->file.xq); skb_queue_purge(&pch->file.rq); kfree(pch); } static void __exit ppp_cleanup(void) { /* should never happen */ if (atomic_read(&ppp_unit_count) || atomic_read(&channel_count)) pr_err("PPP: removing module but units remain!\n"); rtnl_link_unregister(&ppp_link_ops); unregister_chrdev(PPP_MAJOR, "ppp"); device_destroy(ppp_class, MKDEV(PPP_MAJOR, 0)); class_destroy(ppp_class); unregister_pernet_device(&ppp_net_ops); } /* * Units handling. Caller must protect concurrent access * by holding all_ppp_mutex */ /* associate pointer with specified number */ static int unit_set(struct idr *p, void *ptr, int n) { int unit; unit = idr_alloc(p, ptr, n, n + 1, GFP_KERNEL); if (unit == -ENOSPC) unit = -EINVAL; return unit; } /* get new free unit number and associate pointer with it */ static int unit_get(struct idr *p, void *ptr, int min) { return idr_alloc(p, ptr, min, 0, GFP_KERNEL); } /* put unit number back to a pool */ static void unit_put(struct idr *p, int n) { idr_remove(p, n); } /* get pointer associated with the number */ static void *unit_find(struct idr *p, int n) { return idr_find(p, n); } /* Module/initialization stuff */ module_init(ppp_init); module_exit(ppp_cleanup); EXPORT_SYMBOL(ppp_register_net_channel); EXPORT_SYMBOL(ppp_register_channel); EXPORT_SYMBOL(ppp_unregister_channel); EXPORT_SYMBOL(ppp_channel_index); EXPORT_SYMBOL(ppp_unit_number); EXPORT_SYMBOL(ppp_dev_name); EXPORT_SYMBOL(ppp_input); EXPORT_SYMBOL(ppp_input_error); EXPORT_SYMBOL(ppp_output_wakeup); EXPORT_SYMBOL(ppp_register_compressor); EXPORT_SYMBOL(ppp_unregister_compressor); MODULE_LICENSE("GPL"); MODULE_ALIAS_CHARDEV(PPP_MAJOR, 0); MODULE_ALIAS_RTNL_LINK("ppp"); MODULE_ALIAS("devname:ppp"); |
| 3363 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_JIFFIES_H #define _LINUX_JIFFIES_H #include <linux/cache.h> #include <linux/limits.h> #include <linux/math64.h> #include <linux/minmax.h> #include <linux/types.h> #include <linux/time.h> #include <linux/timex.h> #include <vdso/jiffies.h> #include <asm/param.h> /* for HZ */ #include <generated/timeconst.h> /* * The following defines establish the engineering parameters of the PLL * model. The HZ variable establishes the timer interrupt frequency, 100 Hz * for the SunOS kernel, 256 Hz for the Ultrix kernel and 1024 Hz for the * OSF/1 kernel. The SHIFT_HZ define expresses the same value as the * nearest power of two in order to avoid hardware multiply operations. */ #if HZ >= 12 && HZ < 24 # define SHIFT_HZ 4 #elif HZ >= 24 && HZ < 48 # define SHIFT_HZ 5 #elif HZ >= 48 && HZ < 96 # define SHIFT_HZ 6 #elif HZ >= 96 && HZ < 192 # define SHIFT_HZ 7 #elif HZ >= 192 && HZ < 384 # define SHIFT_HZ 8 #elif HZ >= 384 && HZ < 768 # define SHIFT_HZ 9 #elif HZ >= 768 && HZ < 1536 # define SHIFT_HZ 10 #elif HZ >= 1536 && HZ < 3072 # define SHIFT_HZ 11 #elif HZ >= 3072 && HZ < 6144 # define SHIFT_HZ 12 #elif HZ >= 6144 && HZ < 12288 # define SHIFT_HZ 13 #else # error Invalid value of HZ. #endif /* Suppose we want to divide two numbers NOM and DEN: NOM/DEN, then we can * improve accuracy by shifting LSH bits, hence calculating: * (NOM << LSH) / DEN * This however means trouble for large NOM, because (NOM << LSH) may no * longer fit in 32 bits. The following way of calculating this gives us * some slack, under the following conditions: * - (NOM / DEN) fits in (32 - LSH) bits. * - (NOM % DEN) fits in (32 - LSH) bits. */ #define SH_DIV(NOM,DEN,LSH) ( (((NOM) / (DEN)) << (LSH)) \ + ((((NOM) % (DEN)) << (LSH)) + (DEN) / 2) / (DEN)) /* LATCH is used in the interval timer and ftape setup. */ #define LATCH ((CLOCK_TICK_RATE + HZ/2) / HZ) /* For divider */ extern int register_refined_jiffies(long clock_tick_rate); /* TICK_USEC is the time between ticks in usec assuming SHIFTED_HZ */ #define TICK_USEC ((USEC_PER_SEC + HZ/2) / HZ) /* USER_TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ #define USER_TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ) #ifndef __jiffy_arch_data #define __jiffy_arch_data #endif /* * The 64-bit value is not atomic - you MUST NOT read it * without sampling the sequence number in jiffies_lock. * get_jiffies_64() will do this for you as appropriate. */ extern u64 __cacheline_aligned_in_smp jiffies_64; extern unsigned long volatile __cacheline_aligned_in_smp __jiffy_arch_data jiffies; #if (BITS_PER_LONG < 64) u64 get_jiffies_64(void); #else static inline u64 get_jiffies_64(void) { return (u64)jiffies; } #endif /* * These inlines deal with timer wrapping correctly. You are * strongly encouraged to use them * 1. Because people otherwise forget * 2. Because if the timer wrap changes in future you won't have to * alter your driver code. * * time_after(a,b) returns true if the time a is after time b. * * Do this with "<0" and ">=0" to only test the sign of the result. A * good compiler would generate better code (and a really good compiler * wouldn't care). Gcc is currently neither. */ #define time_after(a,b) \ (typecheck(unsigned long, a) && \ typecheck(unsigned long, b) && \ ((long)((b) - (a)) < 0)) #define time_before(a,b) time_after(b,a) #define time_after_eq(a,b) \ (typecheck(unsigned long, a) && \ typecheck(unsigned long, b) && \ ((long)((a) - (b)) >= 0)) #define time_before_eq(a,b) time_after_eq(b,a) /* * Calculate whether a is in the range of [b, c]. */ #define time_in_range(a,b,c) \ (time_after_eq(a,b) && \ time_before_eq(a,c)) /* * Calculate whether a is in the range of [b, c). */ #define time_in_range_open(a,b,c) \ (time_after_eq(a,b) && \ time_before(a,c)) /* Same as above, but does so with platform independent 64bit types. * These must be used when utilizing jiffies_64 (i.e. return value of * get_jiffies_64() */ #define time_after64(a,b) \ (typecheck(__u64, a) && \ typecheck(__u64, b) && \ ((__s64)((b) - (a)) < 0)) #define time_before64(a,b) time_after64(b,a) #define time_after_eq64(a,b) \ (typecheck(__u64, a) && \ typecheck(__u64, b) && \ ((__s64)((a) - (b)) >= 0)) #define time_before_eq64(a,b) time_after_eq64(b,a) #define time_in_range64(a, b, c) \ (time_after_eq64(a, b) && \ time_before_eq64(a, c)) /* * These four macros compare jiffies and 'a' for convenience. */ /* time_is_before_jiffies(a) return true if a is before jiffies */ #define time_is_before_jiffies(a) time_after(jiffies, a) #define time_is_before_jiffies64(a) time_after64(get_jiffies_64(), a) /* time_is_after_jiffies(a) return true if a is after jiffies */ #define time_is_after_jiffies(a) time_before(jiffies, a) #define time_is_after_jiffies64(a) time_before64(get_jiffies_64(), a) /* time_is_before_eq_jiffies(a) return true if a is before or equal to jiffies*/ #define time_is_before_eq_jiffies(a) time_after_eq(jiffies, a) #define time_is_before_eq_jiffies64(a) time_after_eq64(get_jiffies_64(), a) /* time_is_after_eq_jiffies(a) return true if a is after or equal to jiffies*/ #define time_is_after_eq_jiffies(a) time_before_eq(jiffies, a) #define time_is_after_eq_jiffies64(a) time_before_eq64(get_jiffies_64(), a) /* * Have the 32 bit jiffies value wrap 5 minutes after boot * so jiffies wrap bugs show up earlier. */ #define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-300*HZ)) /* * Change timeval to jiffies, trying to avoid the * most obvious overflows.. * * And some not so obvious. * * Note that we don't want to return LONG_MAX, because * for various timeout reasons we often end up having * to wait "jiffies+1" in order to guarantee that we wait * at _least_ "jiffies" - so "jiffies+1" had better still * be positive. */ #define MAX_JIFFY_OFFSET ((LONG_MAX >> 1)-1) extern unsigned long preset_lpj; /* * We want to do realistic conversions of time so we need to use the same * values the update wall clock code uses as the jiffies size. This value * is: TICK_NSEC (which is defined in timex.h). This * is a constant and is in nanoseconds. We will use scaled math * with a set of scales defined here as SEC_JIFFIE_SC, USEC_JIFFIE_SC and * NSEC_JIFFIE_SC. Note that these defines contain nothing but * constants and so are computed at compile time. SHIFT_HZ (computed in * timex.h) adjusts the scaling for different HZ values. * Scaled math??? What is that? * * Scaled math is a way to do integer math on values that would, * otherwise, either overflow, underflow, or cause undesired div * instructions to appear in the execution path. In short, we "scale" * up the operands so they take more bits (more precision, less * underflow), do the desired operation and then "scale" the result back * by the same amount. If we do the scaling by shifting we avoid the * costly mpy and the dastardly div instructions. * Suppose, for example, we want to convert from seconds to jiffies * where jiffies is defined in nanoseconds as NSEC_PER_JIFFIE. The * simple math is: jiff = (sec * NSEC_PER_SEC) / NSEC_PER_JIFFIE; We * observe that (NSEC_PER_SEC / NSEC_PER_JIFFIE) is a constant which we * might calculate at compile time, however, the result will only have * about 3-4 bits of precision (less for smaller values of HZ). * * So, we scale as follows: * jiff = (sec) * (NSEC_PER_SEC / NSEC_PER_JIFFIE); * jiff = ((sec) * ((NSEC_PER_SEC * SCALE)/ NSEC_PER_JIFFIE)) / SCALE; * Then we make SCALE a power of two so: * jiff = ((sec) * ((NSEC_PER_SEC << SCALE)/ NSEC_PER_JIFFIE)) >> SCALE; * Now we define: * #define SEC_CONV = ((NSEC_PER_SEC << SCALE)/ NSEC_PER_JIFFIE)) * jiff = (sec * SEC_CONV) >> SCALE; * * Often the math we use will expand beyond 32-bits so we tell C how to * do this and pass the 64-bit result of the mpy through the ">> SCALE" * which should take the result back to 32-bits. We want this expansion * to capture as much precision as possible. At the same time we don't * want to overflow so we pick the SCALE to avoid this. In this file, * that means using a different scale for each range of HZ values (as * defined in timex.h). * * For those who want to know, gcc will give a 64-bit result from a "*" * operator if the result is a long long AND at least one of the * operands is cast to long long (usually just prior to the "*" so as * not to confuse it into thinking it really has a 64-bit operand, * which, buy the way, it can do, but it takes more code and at least 2 * mpys). * We also need to be aware that one second in nanoseconds is only a * couple of bits away from overflowing a 32-bit word, so we MUST use * 64-bits to get the full range time in nanoseconds. */ /* * Here are the scales we will use. One for seconds, nanoseconds and * microseconds. * * Within the limits of cpp we do a rough cut at the SEC_JIFFIE_SC and * check if the sign bit is set. If not, we bump the shift count by 1. * (Gets an extra bit of precision where we can use it.) * We know it is set for HZ = 1024 and HZ = 100 not for 1000. * Haven't tested others. * Limits of cpp (for #if expressions) only long (no long long), but * then we only need the most signicant bit. */ #define SEC_JIFFIE_SC (31 - SHIFT_HZ) #if !((((NSEC_PER_SEC << 2) / TICK_NSEC) << (SEC_JIFFIE_SC - 2)) & 0x80000000) #undef SEC_JIFFIE_SC #define SEC_JIFFIE_SC (32 - SHIFT_HZ) #endif #define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29) #define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) /* * The maximum jiffie value is (MAX_INT >> 1). Here we translate that * into seconds. The 64-bit case will overflow if we are not careful, * so use the messy SH_DIV macro to do it. Still all constants. */ #if BITS_PER_LONG < 64 # define MAX_SEC_IN_JIFFIES \ (long)((u64)((u64)MAX_JIFFY_OFFSET * TICK_NSEC) / NSEC_PER_SEC) #else /* take care of overflow on 64 bits machines */ # define MAX_SEC_IN_JIFFIES \ (SH_DIV((MAX_JIFFY_OFFSET >> SEC_JIFFIE_SC) * TICK_NSEC, NSEC_PER_SEC, 1) - 1) #endif /* * Convert various time units to each other: */ extern unsigned int jiffies_to_msecs(const unsigned long j); extern unsigned int jiffies_to_usecs(const unsigned long j); static inline u64 jiffies_to_nsecs(const unsigned long j) { return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC; } extern u64 jiffies64_to_nsecs(u64 j); extern u64 jiffies64_to_msecs(u64 j); extern unsigned long __msecs_to_jiffies(const unsigned int m); #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) /* * HZ is equal to or smaller than 1000, and 1000 is a nice round * multiple of HZ, divide with the factor between them, but round * upwards: */ static inline unsigned long _msecs_to_jiffies(const unsigned int m) { return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ); } #elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) /* * HZ is larger than 1000, and HZ is a nice round multiple of 1000 - * simply multiply with the factor between them. * * But first make sure the multiplication result cannot overflow: */ static inline unsigned long _msecs_to_jiffies(const unsigned int m) { if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return m * (HZ / MSEC_PER_SEC); } #else /* * Generic case - multiply, round and divide. But first check that if * we are doing a net multiplication, that we wouldn't overflow: */ static inline unsigned long _msecs_to_jiffies(const unsigned int m) { if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32) >> MSEC_TO_HZ_SHR32; } #endif /** * msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds * * conversion is done as follows: * * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) * * - 'too large' values [that would result in larger than * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. * * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. * for the details see _msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. * the HZ range specific helpers _msecs_to_jiffies() are called both * directly here and from __msecs_to_jiffies() in the case where * constant folding is not possible. */ static __always_inline unsigned long msecs_to_jiffies(const unsigned int m) { if (__builtin_constant_p(m)) { if ((int)m < 0) return MAX_JIFFY_OFFSET; return _msecs_to_jiffies(m); } else { return __msecs_to_jiffies(m); } } extern unsigned long __usecs_to_jiffies(const unsigned int u); #if !(USEC_PER_SEC % HZ) static inline unsigned long _usecs_to_jiffies(const unsigned int u) { return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ); } #else static inline unsigned long _usecs_to_jiffies(const unsigned int u) { return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32) >> USEC_TO_HZ_SHR32; } #endif /** * usecs_to_jiffies: - convert microseconds to jiffies * @u: time in microseconds * * conversion is done as follows: * * - 'too large' values [that would result in larger than * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. * * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows as for msecs_to_jiffies. * * usecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __usecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. * the HZ range specific helpers _usecs_to_jiffies() are called both * directly here and from __msecs_to_jiffies() in the case where * constant folding is not possible. */ static __always_inline unsigned long usecs_to_jiffies(const unsigned int u) { if (__builtin_constant_p(u)) { if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return _usecs_to_jiffies(u); } else { return __usecs_to_jiffies(u); } } extern unsigned long timespec64_to_jiffies(const struct timespec64 *value); extern void jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value); extern clock_t jiffies_to_clock_t(unsigned long x); static inline clock_t jiffies_delta_to_clock_t(long delta) { return jiffies_to_clock_t(max(0L, delta)); } static inline unsigned int jiffies_delta_to_msecs(long delta) { return jiffies_to_msecs(max(0L, delta)); } extern unsigned long clock_t_to_jiffies(unsigned long x); extern u64 jiffies_64_to_clock_t(u64 x); extern u64 nsec_to_clock_t(u64 x); extern u64 nsecs_to_jiffies64(u64 n); extern unsigned long nsecs_to_jiffies(u64 n); #define TIMESTAMP_SIZE 30 #endif |
| 750 750 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_police.c Input police filter * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * J Hadi Salim (action changes) */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/slab.h> #include <net/act_api.h> #include <net/netlink.h> #include <net/pkt_cls.h> #include <net/tc_act/tc_police.h> /* Each policer is serialized by its individual spinlock */ static unsigned int police_net_id; static struct tc_action_ops act_police_ops; static int tcf_police_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, const struct tc_action_ops *ops, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, police_net_id); return tcf_generic_walker(tn, skb, cb, type, ops, extack); } static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { [TCA_POLICE_RATE] = { .len = TC_RTAB_SIZE }, [TCA_POLICE_PEAKRATE] = { .len = TC_RTAB_SIZE }, [TCA_POLICE_AVRATE] = { .type = NLA_U32 }, [TCA_POLICE_RESULT] = { .type = NLA_U32 }, [TCA_POLICE_RATE64] = { .type = NLA_U64 }, [TCA_POLICE_PEAKRATE64] = { .type = NLA_U64 }, [TCA_POLICE_PKTRATE64] = { .type = NLA_U64, .min = 1 }, [TCA_POLICE_PKTBURST64] = { .type = NLA_U64, .min = 1 }, }; static int tcf_police_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { int ret = 0, tcfp_result = TC_ACT_OK, err, size; bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_POLICE_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_police *parm; struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; struct tc_action_net *tn = net_generic(net, police_net_id); struct tcf_police_params *new; bool exists = false; u32 index; u64 rate64, prate64; u64 pps, ppsburst; if (nla == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_POLICE_MAX, nla, police_policy, NULL); if (err < 0) return err; if (tb[TCA_POLICE_TBF] == NULL) return -EINVAL; size = nla_len(tb[TCA_POLICE_TBF]); if (size != sizeof(*parm) && size != sizeof(struct tc_police_compat)) return -EINVAL; parm = nla_data(tb[TCA_POLICE_TBF]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return 0; if (!exists) { ret = tcf_idr_create(tn, index, NULL, a, &act_police_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; spin_lock_init(&(to_police(*a)->tcfp_lock)); } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; police = to_police(*a); if (parm->rate.rate) { err = -ENOMEM; R_tab = qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE], NULL); if (R_tab == NULL) goto failure; if (parm->peakrate.rate) { P_tab = qdisc_get_rtab(&parm->peakrate, tb[TCA_POLICE_PEAKRATE], NULL); if (P_tab == NULL) goto failure; } } if (est) { err = gen_replace_estimator(&police->tcf_bstats, police->common.cpu_bstats, &police->tcf_rate_est, &police->tcf_lock, NULL, est); if (err) goto failure; } else if (tb[TCA_POLICE_AVRATE] && (ret == ACT_P_CREATED || !gen_estimator_active(&police->tcf_rate_est))) { err = -EINVAL; goto failure; } if (tb[TCA_POLICE_RESULT]) { tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); if (TC_ACT_EXT_CMP(tcfp_result, TC_ACT_GOTO_CHAIN)) { NL_SET_ERR_MSG(extack, "goto chain not allowed on fallback"); err = -EINVAL; goto failure; } } if ((tb[TCA_POLICE_PKTRATE64] && !tb[TCA_POLICE_PKTBURST64]) || (!tb[TCA_POLICE_PKTRATE64] && tb[TCA_POLICE_PKTBURST64])) { NL_SET_ERR_MSG(extack, "Both or neither packet-per-second burst and rate must be provided"); err = -EINVAL; goto failure; } if (tb[TCA_POLICE_PKTRATE64] && R_tab) { NL_SET_ERR_MSG(extack, "packet-per-second and byte-per-second rate limits not allowed in same action"); err = -EINVAL; goto failure; } new = kzalloc(sizeof(*new), GFP_KERNEL); if (unlikely(!new)) { err = -ENOMEM; goto failure; } /* No failure allowed after this point */ new->tcfp_result = tcfp_result; new->tcfp_mtu = parm->mtu; if (!new->tcfp_mtu) { new->tcfp_mtu = ~0; if (R_tab) new->tcfp_mtu = 255 << R_tab->rate.cell_log; } if (R_tab) { new->rate_present = true; rate64 = tb[TCA_POLICE_RATE64] ? nla_get_u64(tb[TCA_POLICE_RATE64]) : 0; psched_ratecfg_precompute(&new->rate, &R_tab->rate, rate64); qdisc_put_rtab(R_tab); } else { new->rate_present = false; } if (P_tab) { new->peak_present = true; prate64 = tb[TCA_POLICE_PEAKRATE64] ? nla_get_u64(tb[TCA_POLICE_PEAKRATE64]) : 0; psched_ratecfg_precompute(&new->peak, &P_tab->rate, prate64); qdisc_put_rtab(P_tab); } else { new->peak_present = false; } new->tcfp_burst = PSCHED_TICKS2NS(parm->burst); if (new->peak_present) new->tcfp_mtu_ptoks = (s64)psched_l2t_ns(&new->peak, new->tcfp_mtu); if (tb[TCA_POLICE_AVRATE]) new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); if (tb[TCA_POLICE_PKTRATE64]) { pps = nla_get_u64(tb[TCA_POLICE_PKTRATE64]); ppsburst = nla_get_u64(tb[TCA_POLICE_PKTBURST64]); new->pps_present = true; new->tcfp_pkt_burst = PSCHED_TICKS2NS(ppsburst); psched_ppscfg_precompute(&new->ppsrate, pps); } spin_lock_bh(&police->tcf_lock); spin_lock_bh(&police->tcfp_lock); police->tcfp_t_c = ktime_get_ns(); police->tcfp_toks = new->tcfp_burst; if (new->peak_present) police->tcfp_ptoks = new->tcfp_mtu_ptoks; spin_unlock_bh(&police->tcfp_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); new = rcu_replace_pointer(police->params, new, lockdep_is_held(&police->tcf_lock)); spin_unlock_bh(&police->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (new) kfree_rcu(new, rcu); return ret; failure: qdisc_put_rtab(P_tab); qdisc_put_rtab(R_tab); if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static bool tcf_police_mtu_check(struct sk_buff *skb, u32 limit) { u32 len; if (skb_is_gso(skb)) return skb_gso_validate_mac_len(skb, limit); len = qdisc_pkt_len(skb); if (skb_at_tc_ingress(skb)) len += skb->mac_len; return len <= limit; } static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_police *police = to_police(a); s64 now, toks, ppstoks = 0, ptoks = 0; struct tcf_police_params *p; int ret; tcf_lastuse_update(&police->tcf_tm); bstats_cpu_update(this_cpu_ptr(police->common.cpu_bstats), skb); ret = READ_ONCE(police->tcf_action); p = rcu_dereference_bh(police->params); if (p->tcfp_ewma_rate) { struct gnet_stats_rate_est64 sample; if (!gen_estimator_read(&police->tcf_rate_est, &sample) || sample.bps >= p->tcfp_ewma_rate) goto inc_overlimits; } if (tcf_police_mtu_check(skb, p->tcfp_mtu)) { if (!p->rate_present && !p->pps_present) { ret = p->tcfp_result; goto end; } now = ktime_get_ns(); spin_lock_bh(&police->tcfp_lock); toks = min_t(s64, now - police->tcfp_t_c, p->tcfp_burst); if (p->peak_present) { ptoks = toks + police->tcfp_ptoks; if (ptoks > p->tcfp_mtu_ptoks) ptoks = p->tcfp_mtu_ptoks; ptoks -= (s64)psched_l2t_ns(&p->peak, qdisc_pkt_len(skb)); } if (p->rate_present) { toks += police->tcfp_toks; if (toks > p->tcfp_burst) toks = p->tcfp_burst; toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb)); } else if (p->pps_present) { ppstoks = min_t(s64, now - police->tcfp_t_c, p->tcfp_pkt_burst); ppstoks += police->tcfp_pkttoks; if (ppstoks > p->tcfp_pkt_burst) ppstoks = p->tcfp_pkt_burst; ppstoks -= (s64)psched_pkt2t_ns(&p->ppsrate, 1); } if ((toks | ptoks | ppstoks) >= 0) { police->tcfp_t_c = now; police->tcfp_toks = toks; police->tcfp_ptoks = ptoks; police->tcfp_pkttoks = ppstoks; spin_unlock_bh(&police->tcfp_lock); ret = p->tcfp_result; goto inc_drops; } spin_unlock_bh(&police->tcfp_lock); } inc_overlimits: qstats_overlimit_inc(this_cpu_ptr(police->common.cpu_qstats)); inc_drops: if (ret == TC_ACT_SHOT) qstats_drop_inc(this_cpu_ptr(police->common.cpu_qstats)); end: return ret; } static void tcf_police_cleanup(struct tc_action *a) { struct tcf_police *police = to_police(a); struct tcf_police_params *p; p = rcu_dereference_protected(police->params, 1); if (p) kfree_rcu(p, rcu); } static void tcf_police_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_police *police = to_police(a); struct tcf_t *tm = &police->tcf_tm; tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_police *police = to_police(a); struct tcf_police_params *p; struct tc_police opt = { .index = police->tcf_index, .refcnt = refcount_read(&police->tcf_refcnt) - ref, .bindcnt = atomic_read(&police->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&police->tcf_lock); opt.action = police->tcf_action; p = rcu_dereference_protected(police->params, lockdep_is_held(&police->tcf_lock)); opt.mtu = p->tcfp_mtu; opt.burst = PSCHED_NS2TICKS(p->tcfp_burst); if (p->rate_present) { psched_ratecfg_getrate(&opt.rate, &p->rate); if ((p->rate.rate_bytes_ps >= (1ULL << 32)) && nla_put_u64_64bit(skb, TCA_POLICE_RATE64, p->rate.rate_bytes_ps, TCA_POLICE_PAD)) goto nla_put_failure; } if (p->peak_present) { psched_ratecfg_getrate(&opt.peakrate, &p->peak); if ((p->peak.rate_bytes_ps >= (1ULL << 32)) && nla_put_u64_64bit(skb, TCA_POLICE_PEAKRATE64, p->peak.rate_bytes_ps, TCA_POLICE_PAD)) goto nla_put_failure; } if (p->pps_present) { if (nla_put_u64_64bit(skb, TCA_POLICE_PKTRATE64, p->ppsrate.rate_pkts_ps, TCA_POLICE_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(skb, TCA_POLICE_PKTBURST64, PSCHED_NS2TICKS(p->tcfp_pkt_burst), TCA_POLICE_PAD)) goto nla_put_failure; } if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt)) goto nla_put_failure; if (p->tcfp_result && nla_put_u32(skb, TCA_POLICE_RESULT, p->tcfp_result)) goto nla_put_failure; if (p->tcfp_ewma_rate && nla_put_u32(skb, TCA_POLICE_AVRATE, p->tcfp_ewma_rate)) goto nla_put_failure; tcf_tm_dump(&t, &police->tcf_tm); if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD)) goto nla_put_failure; spin_unlock_bh(&police->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&police->tcf_lock); nlmsg_trim(skb, b); return -1; } static int tcf_police_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, police_net_id); return tcf_idr_search(tn, a, index); } MODULE_AUTHOR("Alexey Kuznetsov"); MODULE_DESCRIPTION("Policing actions"); MODULE_LICENSE("GPL"); static struct tc_action_ops act_police_ops = { .kind = "police", .id = TCA_ID_POLICE, .owner = THIS_MODULE, .stats_update = tcf_police_stats_update, .act = tcf_police_act, .dump = tcf_police_dump, .init = tcf_police_init, .walk = tcf_police_walker, .lookup = tcf_police_search, .cleanup = tcf_police_cleanup, .size = sizeof(struct tcf_police), }; static __net_init int police_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, police_net_id); return tc_action_net_init(net, tn, &act_police_ops); } static void __net_exit police_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, police_net_id); } static struct pernet_operations police_net_ops = { .init = police_init_net, .exit_batch = police_exit_net, .id = &police_net_id, .size = sizeof(struct tc_action_net), }; static int __init police_init_module(void) { return tcf_register_action(&act_police_ops, &police_net_ops); } static void __exit police_cleanup_module(void) { tcf_unregister_action(&act_police_ops, &police_net_ops); } module_init(police_init_module); module_exit(police_cleanup_module); |
| 23 23 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net> * * Based on the original implementation which is: * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE * Copyright 2003 Andi Kleen, SuSE Labs. * * Parts of the original code have been moved to arch/x86/vdso/vma.c * * This file implements vsyscall emulation. vsyscalls are a legacy ABI: * Userspace can request certain kernel services by calling fixed * addresses. This concept is problematic: * * - It interferes with ASLR. * - It's awkward to write code that lives in kernel addresses but is * callable by userspace at fixed addresses. * - The whole concept is impossible for 32-bit compat userspace. * - UML cannot easily virtualize a vsyscall. * * As of mid-2014, I believe that there is no new userspace code that * will use a vsyscall if the vDSO is present. I hope that there will * soon be no new userspace code that will ever use a vsyscall. * * The code in this file emulates vsyscalls when notified of a page * fault to a vsyscall address. */ #include <linux/kernel.h> #include <linux/timer.h> #include <linux/sched/signal.h> #include <linux/mm_types.h> #include <linux/syscalls.h> #include <linux/ratelimit.h> #include <asm/vsyscall.h> #include <asm/unistd.h> #include <asm/fixmap.h> #include <asm/traps.h> #include <asm/paravirt.h> #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" static enum { EMULATE, XONLY, NONE } vsyscall_mode __ro_after_init = #ifdef CONFIG_LEGACY_VSYSCALL_NONE NONE; #elif defined(CONFIG_LEGACY_VSYSCALL_XONLY) XONLY; #else EMULATE; #endif static int __init vsyscall_setup(char *str) { if (str) { if (!strcmp("emulate", str)) vsyscall_mode = EMULATE; else if (!strcmp("xonly", str)) vsyscall_mode = XONLY; else if (!strcmp("none", str)) vsyscall_mode = NONE; else return -EINVAL; return 0; } return -EINVAL; } early_param("vsyscall", vsyscall_setup); static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, const char *message) { if (!show_unhandled_signals) return; printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", level, current->comm, task_pid_nr(current), message, regs->ip, regs->cs, regs->sp, regs->ax, regs->si, regs->di); } static int addr_to_vsyscall_nr(unsigned long addr) { int nr; if ((addr & ~0xC00UL) != VSYSCALL_ADDR) return -EINVAL; nr = (addr & 0xC00UL) >> 10; if (nr >= 3) return -EINVAL; return nr; } static bool write_ok_or_segv(unsigned long ptr, size_t size) { if (!access_ok((void __user *)ptr, size)) { struct thread_struct *thread = ¤t->thread; thread->error_code = X86_PF_USER | X86_PF_WRITE; thread->cr2 = ptr; thread->trap_nr = X86_TRAP_PF; force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)ptr); return false; } else { return true; } } bool emulate_vsyscall(unsigned long error_code, struct pt_regs *regs, unsigned long address) { unsigned long caller; int vsyscall_nr, syscall_nr, tmp; long ret; unsigned long orig_dx; /* Write faults or kernel-privilege faults never get fixed up. */ if ((error_code & (X86_PF_WRITE | X86_PF_USER)) != X86_PF_USER) return false; if (!(error_code & X86_PF_INSTR)) { /* Failed vsyscall read */ if (vsyscall_mode == EMULATE) return false; /* * User code tried and failed to read the vsyscall page. */ warn_bad_vsyscall(KERN_INFO, regs, "vsyscall read attempt denied -- look up the vsyscall kernel parameter if you need a workaround"); return false; } /* * No point in checking CS -- the only way to get here is a user mode * trap to a high address, which means that we're in 64-bit user code. */ WARN_ON_ONCE(address != regs->ip); if (vsyscall_mode == NONE) { warn_bad_vsyscall(KERN_INFO, regs, "vsyscall attempted with vsyscall=none"); return false; } vsyscall_nr = addr_to_vsyscall_nr(address); trace_emulate_vsyscall(vsyscall_nr); if (vsyscall_nr < 0) { warn_bad_vsyscall(KERN_WARNING, regs, "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround"); goto sigsegv; } if (get_user(caller, (unsigned long __user *)regs->sp) != 0) { warn_bad_vsyscall(KERN_WARNING, regs, "vsyscall with bad stack (exploit attempt?)"); goto sigsegv; } /* * Check for access_ok violations and find the syscall nr. * * NULL is a valid user pointer (in the access_ok sense) on 32-bit and * 64-bit, so we don't need to special-case it here. For all the * vsyscalls, NULL means "don't write anything" not "write it at * address 0". */ switch (vsyscall_nr) { case 0: if (!write_ok_or_segv(regs->di, sizeof(struct __kernel_old_timeval)) || !write_ok_or_segv(regs->si, sizeof(struct timezone))) { ret = -EFAULT; goto check_fault; } syscall_nr = __NR_gettimeofday; break; case 1: if (!write_ok_or_segv(regs->di, sizeof(__kernel_old_time_t))) { ret = -EFAULT; goto check_fault; } syscall_nr = __NR_time; break; case 2: if (!write_ok_or_segv(regs->di, sizeof(unsigned)) || !write_ok_or_segv(regs->si, sizeof(unsigned))) { ret = -EFAULT; goto check_fault; } syscall_nr = __NR_getcpu; break; } /* * Handle seccomp. regs->ip must be the original value. * See seccomp_send_sigsys and Documentation/userspace-api/seccomp_filter.rst. * * We could optimize the seccomp disabled case, but performance * here doesn't matter. */ regs->orig_ax = syscall_nr; regs->ax = -ENOSYS; tmp = secure_computing(); if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); force_exit_sig(SIGSYS); return true; } regs->orig_ax = -1; if (tmp) goto do_ret; /* skip requested */ /* * With a real vsyscall, page faults cause SIGSEGV. */ ret = -EFAULT; switch (vsyscall_nr) { case 0: /* this decodes regs->di and regs->si on its own */ ret = __x64_sys_gettimeofday(regs); break; case 1: /* this decodes regs->di on its own */ ret = __x64_sys_time(regs); break; case 2: /* while we could clobber regs->dx, we didn't in the past... */ orig_dx = regs->dx; regs->dx = 0; /* this decodes regs->di, regs->si and regs->dx on its own */ ret = __x64_sys_getcpu(regs); regs->dx = orig_dx; break; } check_fault: if (ret == -EFAULT) { /* Bad news -- userspace fed a bad pointer to a vsyscall. */ warn_bad_vsyscall(KERN_INFO, regs, "vsyscall fault (exploit attempt?)"); goto sigsegv; } regs->ax = ret; do_ret: /* Emulate a ret instruction. */ regs->ip = caller; regs->sp += 8; return true; sigsegv: force_sig(SIGSEGV); return true; } /* * A pseudo VMA to allow ptrace access for the vsyscall page. This only * covers the 64bit vsyscall page now. 32bit has a real VMA now and does * not need special handling anymore: */ static const char *gate_vma_name(struct vm_area_struct *vma) { return "[vsyscall]"; } static const struct vm_operations_struct gate_vma_ops = { .name = gate_vma_name, }; static struct vm_area_struct gate_vma __ro_after_init = { .vm_start = VSYSCALL_ADDR, .vm_end = VSYSCALL_ADDR + PAGE_SIZE, .vm_page_prot = PAGE_READONLY_EXEC, .vm_flags = VM_READ | VM_EXEC, .vm_ops = &gate_vma_ops, }; struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { #ifdef CONFIG_COMPAT if (!mm || !(mm->context.flags & MM_CONTEXT_HAS_VSYSCALL)) return NULL; #endif if (vsyscall_mode == NONE) return NULL; return &gate_vma; } int in_gate_area(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma = get_gate_vma(mm); if (!vma) return 0; return (addr >= vma->vm_start) && (addr < vma->vm_end); } /* * Use this when you have no reliable mm, typically from interrupt * context. It is less reliable than using a task's mm and may give * false positives. */ int in_gate_area_no_mm(unsigned long addr) { return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR; } /* * The VSYSCALL page is the only user-accessible page in the kernel address * range. Normally, the kernel page tables can have _PAGE_USER clear, but * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls * are enabled. * * Some day we may create a "minimal" vsyscall mode in which we emulate * vsyscalls but leave the page not present. If so, we skip calling * this. */ void __init set_vsyscall_pgtable_user_bits(pgd_t *root) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset_pgd(root, VSYSCALL_ADDR); set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER)); p4d = p4d_offset(pgd, VSYSCALL_ADDR); #if CONFIG_PGTABLE_LEVELS >= 5 set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER)); #endif pud = pud_offset(p4d, VSYSCALL_ADDR); set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER)); pmd = pmd_offset(pud, VSYSCALL_ADDR); set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER)); } void __init map_vsyscall(void) { extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); /* * For full emulation, the page needs to exist for real. In * execute-only mode, there is no PTE at all backing the vsyscall * page. */ if (vsyscall_mode == EMULATE) { __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, PAGE_KERNEL_VVAR); set_vsyscall_pgtable_user_bits(swapper_pg_dir); } if (vsyscall_mode == XONLY) gate_vma.vm_flags = VM_EXEC; BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != (unsigned long)VSYSCALL_ADDR); } |
| 1852 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/buffer.c * * Copyright (C) 1991, 1992, 2002 Linus Torvalds */ /* * Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95 * * Removed a lot of unnecessary code and simplified things now that * the buffer cache isn't our primary cache - Andrew Tridgell 12/96 * * Speed up hash, lru, and free list operations. Use gfp() for allocating * hash table, use SLAB cache for buffer heads. SMP threading. -DaveM * * Added 32k buffer block sizes - these are required older ARM systems. - RMK * * async buffer flushing, 1999 Andrea Arcangeli <andrea@suse.de> */ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/iomap.h> #include <linux/mm.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/capability.h> #include <linux/blkdev.h> #include <linux/file.h> #include <linux/quotaops.h> #include <linux/highmem.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #include <linux/hash.h> #include <linux/suspend.h> #include <linux/buffer_head.h> #include <linux/task_io_accounting_ops.h> #include <linux/bio.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/mpage.h> #include <linux/bit_spinlock.h> #include <linux/pagevec.h> #include <linux/sched/mm.h> #include <trace/events/block.h> #include <linux/fscrypt.h> #include "internal.h" static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, enum rw_hint hint, struct writeback_control *wbc); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) inline void touch_buffer(struct buffer_head *bh) { trace_block_touch_buffer(bh); mark_page_accessed(bh->b_page); } EXPORT_SYMBOL(touch_buffer); void __lock_buffer(struct buffer_head *bh) { wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); void unlock_buffer(struct buffer_head *bh) { clear_bit_unlock(BH_Lock, &bh->b_state); smp_mb__after_atomic(); wake_up_bit(&bh->b_state, BH_Lock); } EXPORT_SYMBOL(unlock_buffer); /* * Returns if the page has dirty or writeback buffers. If all the buffers * are unlocked and clean then the PageDirty information is stale. If * any of the pages are locked, it is assumed they are locked for IO. */ void buffer_check_dirty_writeback(struct page *page, bool *dirty, bool *writeback) { struct buffer_head *head, *bh; *dirty = false; *writeback = false; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) return; if (PageWriteback(page)) *writeback = true; head = page_buffers(page); bh = head; do { if (buffer_locked(bh)) *writeback = true; if (buffer_dirty(bh)) *dirty = true; bh = bh->b_this_page; } while (bh != head); } EXPORT_SYMBOL(buffer_check_dirty_writeback); /* * Block until a buffer comes unlocked. This doesn't stop it * from becoming locked again - you have to lock it yourself * if you want to preserve its state. */ void __wait_on_buffer(struct buffer_head * bh) { wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__wait_on_buffer); static void buffer_io_error(struct buffer_head *bh, char *msg) { if (!test_bit(BH_Quiet, &bh->b_state)) printk_ratelimited(KERN_ERR "Buffer I/O error on dev %pg, logical block %llu%s\n", bh->b_bdev, (unsigned long long)bh->b_blocknr, msg); } /* * End-of-IO handler helper function which does not touch the bh after * unlocking it. * Note: unlock_buffer() sort-of does touch the bh after unlocking it, but * a race there is benign: unlock_buffer() only use the bh's address for * hashing after unlocking the buffer, so it doesn't actually touch the bh * itself. */ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { /* This happens, due to failed read-ahead attempts. */ clear_buffer_uptodate(bh); } unlock_buffer(bh); } /* * Default synchronous end-of-IO handler.. Just mark it up-to-date and * unlock the buffer. This is what ll_rw_block uses too. */ void end_buffer_read_sync(struct buffer_head *bh, int uptodate) { __end_buffer_read_notouch(bh, uptodate); put_bh(bh); } EXPORT_SYMBOL(end_buffer_read_sync); void end_buffer_write_sync(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost sync page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } unlock_buffer(bh); put_bh(bh); } EXPORT_SYMBOL_NS(end_buffer_write_sync, ANDROID_GKI_VFS_EXPORT_ONLY); /* * Various filesystems appear to want __find_get_block to be non-blocking. * But it's the page lock which protects the buffers. To get around this, * we get exclusion from try_to_free_buffers with the blockdev mapping's * private_lock. * * Hack idea: for the blockdev mapping, private_lock contention * may be quite high. This code could TryLock the page, and if that * succeeds, there is no need to take private_lock. */ static struct buffer_head * __find_get_block_slow(struct block_device *bdev, sector_t block) { struct inode *bd_inode = bdev->bd_inode; struct address_space *bd_mapping = bd_inode->i_mapping; struct buffer_head *ret = NULL; pgoff_t index; struct buffer_head *bh; struct buffer_head *head; struct page *page; int all_mapped = 1; static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); if (!page) goto out; spin_lock(&bd_mapping->private_lock); if (!page_has_buffers(page)) goto out_unlock; head = page_buffers(page); bh = head; do { if (!buffer_mapped(bh)) all_mapped = 0; else if (bh->b_blocknr == block) { ret = bh; get_bh(bh); goto out_unlock; } bh = bh->b_this_page; } while (bh != head); /* we might be here because some of the buffers on this page are * not mapped. This is due to various races between * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); if (all_mapped && __ratelimit(&last_warned)) { printk("__find_get_block_slow() failed. block=%llu, " "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " "device %pg blocksize: %d\n", (unsigned long long)block, (unsigned long long)bh->b_blocknr, bh->b_state, bh->b_size, bdev, 1 << bd_inode->i_blkbits); } out_unlock: spin_unlock(&bd_mapping->private_lock); put_page(page); out: return ret; } static void end_buffer_async_read(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct page *page; int page_uptodate = 1; BUG_ON(!buffer_async_read(bh)); page = bh->b_page; if (uptodate) { set_buffer_uptodate(bh); } else { clear_buffer_uptodate(bh); buffer_io_error(bh, ", async page read"); SetPageError(page); } /* * Be _very_ careful from here on. Bad things can happen if * two buffer heads end IO at almost the same time and both * decide that the page is now completely done. */ first = page_buffers(page); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; do { if (!buffer_uptodate(tmp)) page_uptodate = 0; if (buffer_async_read(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } while (tmp != bh); spin_unlock_irqrestore(&first->b_uptodate_lock, flags); /* * If none of the buffers had errors and they are all * uptodate then we can set the page uptodate. */ if (page_uptodate && !PageError(page)) SetPageUptodate(page); unlock_page(page); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); return; } struct decrypt_bh_ctx { struct work_struct work; struct buffer_head *bh; }; static void decrypt_bh(struct work_struct *work) { struct decrypt_bh_ctx *ctx = container_of(work, struct decrypt_bh_ctx, work); struct buffer_head *bh = ctx->bh; int err; err = fscrypt_decrypt_pagecache_blocks(bh->b_page, bh->b_size, bh_offset(bh)); end_buffer_async_read(bh, err == 0); kfree(ctx); } /* * I/O completion handler for block_read_full_page() - pages * which come unlocked at the end of I/O. */ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) { /* Decrypt if needed */ if (uptodate && fscrypt_inode_uses_fs_layer_crypto(bh->b_page->mapping->host)) { struct decrypt_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); if (ctx) { INIT_WORK(&ctx->work, decrypt_bh); ctx->bh = bh; fscrypt_enqueue_decrypt_work(&ctx->work); return; } uptodate = 0; } end_buffer_async_read(bh, uptodate); } /* * Completion handler for block_write_full_page() - pages which are unlocked * during I/O, and which have PageWriteback cleared upon I/O completion. */ void end_buffer_async_write(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct page *page; BUG_ON(!buffer_async_write(bh)); page = bh->b_page; if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost async page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); SetPageError(page); } first = page_buffers(page); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_write(bh); unlock_buffer(bh); tmp = bh->b_this_page; while (tmp != bh) { if (buffer_async_write(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } spin_unlock_irqrestore(&first->b_uptodate_lock, flags); end_page_writeback(page); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); return; } EXPORT_SYMBOL(end_buffer_async_write); /* * If a page's buffers are under async readin (end_buffer_async_read * completion) then there is a possibility that another thread of * control could lock one of the buffers after it has completed * but while some of the other buffers have not completed. This * locked buffer would confuse end_buffer_async_read() into not unlocking * the page. So the absence of BH_Async_Read tells end_buffer_async_read() * that this buffer is not under async I/O. * * The page comes unlocked when it has no locked buffer_async buffers * left. * * PageLocked prevents anyone starting new async I/O reads any of * the buffers. * * PageWriteback is used to prevent simultaneous writeout of the same * page. * * PageLocked prevents anyone from starting writeback of a page which is * under read I/O (PageWriteback is only ever set against a locked page). */ static void mark_buffer_async_read(struct buffer_head *bh) { bh->b_end_io = end_buffer_async_read_io; set_buffer_async_read(bh); } static void mark_buffer_async_write_endio(struct buffer_head *bh, bh_end_io_t *handler) { bh->b_end_io = handler; set_buffer_async_write(bh); } void mark_buffer_async_write(struct buffer_head *bh) { mark_buffer_async_write_endio(bh, end_buffer_async_write); } EXPORT_SYMBOL_NS(mark_buffer_async_write, ANDROID_GKI_VFS_EXPORT_ONLY); /* * fs/buffer.c contains helper functions for buffer-backed address space's * fsync functions. A common requirement for buffer-based filesystems is * that certain data from the backing blockdev needs to be written out for * a successful fsync(). For example, ext2 indirect blocks need to be * written back and waited upon before fsync() returns. * * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(), * inode_has_buffers() and invalidate_inode_buffers() are provided for the * management of a list of dependent buffers at ->i_mapping->private_list. * * Locking is a little subtle: try_to_free_buffers() will remove buffers * from their controlling inode's queue when they are being freed. But * try_to_free_buffers() will be operating against the *blockdev* mapping * at the time, not against the S_ISREG file which depends on those buffers. * So the locking for private_list is via the private_lock in the address_space * which backs the buffers. Which is different from the address_space * against which the buffers are listed. So for a particular address_space, * mapping->private_lock does *not* protect mapping->private_list! In fact, * mapping->private_list will always be protected by the backing blockdev's * ->private_lock. * * Which introduces a requirement: all buffers on an address_space's * ->private_list must be from the same address_space: the blockdev's. * * address_spaces which do not place buffers at ->private_list via these * utility functions are free to use private_lock and private_list for * whatever they want. The only requirement is that list_empty(private_list) * be true at clear_inode() time. * * FIXME: clear_inode should not call invalidate_inode_buffers(). The * filesystems should do that. invalidate_inode_buffers() should just go * BUG_ON(!list_empty). * * FIXME: mark_buffer_dirty_inode() is a data-plane operation. It should * take an address_space, not an inode. And it should be called * mark_buffer_dirty_fsync() to clearly define why those buffers are being * queued up. * * FIXME: mark_buffer_dirty_inode() doesn't need to add the buffer to the * list if it is already on a list. Because if the buffer is on a list, * it *must* already be on the right one. If not, the filesystem is being * silly. This will save a ton of locking. But first we have to ensure * that buffers are taken *off* the old inode's list when they are freed * (presumably in truncate). That requires careful auditing of all * filesystems (do it inside bforget()). It could also be done by bringing * b_inode back. */ /* * The buffer's backing address_space's private_lock must be held */ static void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); WARN_ON(!bh->b_assoc_map); bh->b_assoc_map = NULL; } int inode_has_buffers(struct inode *inode) { return !list_empty(&inode->i_data.private_list); } /* * osync is designed to support O_SYNC io. It waits synchronously for * all already-submitted IO to complete, but does not queue any new * writes to the disk. * * To do O_SYNC writes, just queue the buffer writes with ll_rw_block as * you dirty the buffers, and then use osync_inode_buffers to wait for * completion. Any other dirty buffers which are not yet queued for * write will not be flushed to disk by the osync. */ static int osync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head *p; int err = 0; spin_lock(lock); repeat: list_for_each_prev(p, list) { bh = BH_ENTRY(p); if (buffer_locked(bh)) { get_bh(bh); spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); goto repeat; } } spin_unlock(lock); return err; } void emergency_thaw_bdev(struct super_block *sb) { while (sb->s_bdev && !thaw_bdev(sb->s_bdev)) printk(KERN_WARNING "Emergency Thaw on %pg\n", sb->s_bdev); } /** * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers * @mapping: the mapping which wants those buffers written * * Starts I/O against the buffers at mapping->private_list, and waits upon * that I/O. * * Basically, this is a convenience function for fsync(). * @mapping is a file or directory which needs those buffers to be written for * a successful fsync(). */ int sync_mapping_buffers(struct address_space *mapping) { struct address_space *buffer_mapping = mapping->private_data; if (buffer_mapping == NULL || list_empty(&mapping->private_list)) return 0; return fsync_buffers_list(&buffer_mapping->private_lock, &mapping->private_list); } EXPORT_SYMBOL(sync_mapping_buffers); /* * Called when we've recently written block `bblock', and it is known that * `bblock' was for a buffer_boundary() buffer. This means that the block at * `bblock + 1' is probably a dirty indirect block. Hunt it down and, if it's * dirty, schedule it for IO. So that indirects merge nicely with their data. */ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize) { struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize); if (bh) { if (buffer_dirty(bh)) ll_rw_block(REQ_OP_WRITE, 0, 1, &bh); put_bh(bh); } } void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) { struct address_space *mapping = inode->i_mapping; struct address_space *buffer_mapping = bh->b_page->mapping; mark_buffer_dirty(bh); if (!mapping->private_data) { mapping->private_data = buffer_mapping; } else { BUG_ON(mapping->private_data != buffer_mapping); } if (!bh->b_assoc_map) { spin_lock(&buffer_mapping->private_lock); list_move_tail(&bh->b_assoc_buffers, &mapping->private_list); bh->b_assoc_map = mapping; spin_unlock(&buffer_mapping->private_lock); } } EXPORT_SYMBOL(mark_buffer_dirty_inode); /* * Add a page to the dirty page list. * * It is a sad fact of life that this function is called from several places * deeply under spinlocking. It may not sleep. * * If the page has buffers, the uptodate buffers are set dirty, to preserve * dirty-state coherency between the page and the buffers. It the page does * not have buffers then when they are later attached they will all be set * dirty. * * The buffers are dirtied before the page is dirtied. There's a small race * window in which a writepage caller may see the page cleanness but not the * buffer dirtiness. That's fine. If this code were to set the page dirty * before the buffers, a concurrent writepage caller could clear the page dirty * bit, see a bunch of clean buffers and we'd end up with dirty buffers/clean * page on the dirty page list. * * We use private_lock to lock against try_to_free_buffers while using the * page's buffer list. Also use this to protect against clean buffers being * added to the page after it was set dirty. * * FIXME: may need to call ->reservepage here as well. That's rather up to the * address_space though. */ int __set_page_dirty_buffers(struct page *page) { int newly_dirty; struct address_space *mapping = page_mapping(page); if (unlikely(!mapping)) return !TestSetPageDirty(page); spin_lock(&mapping->private_lock); if (page_has_buffers(page)) { struct buffer_head *head = page_buffers(page); struct buffer_head *bh = head; do { set_buffer_dirty(bh); bh = bh->b_this_page; } while (bh != head); } /* * Lock out page's memcg migration to keep PageDirty * synchronized with per-memcg dirty page counters. */ lock_page_memcg(page); newly_dirty = !TestSetPageDirty(page); spin_unlock(&mapping->private_lock); if (newly_dirty) __set_page_dirty(page, mapping, 1); unlock_page_memcg(page); if (newly_dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); return newly_dirty; } EXPORT_SYMBOL_NS(__set_page_dirty_buffers, ANDROID_GKI_VFS_EXPORT_ONLY); /* * Write out and wait upon a list of buffers. * * We have conflicting pressures: we want to make sure that all * initially dirty buffers get waited on, but that any subsequently * dirtied buffers don't. After all, we don't want fsync to last * forever if somebody is actively writing to the file. * * Do this in two main stages: first we copy dirty buffers to a * temporary inode list, queueing the writes as we go. Then we clean * up, waiting for those writes to complete. * * During this second stage, any subsequent updates to the file may end * up refiling the buffer on the original inode's dirty list again, so * there is a chance we will end up with a buffer queued for write but * not yet completed on that list. So, as a final cleanup we go through * the osync code to catch these locked, dirty buffers without requeuing * any newly dirty buffers for write. */ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head tmp; struct address_space *mapping; int err = 0, err2; struct blk_plug plug; INIT_LIST_HEAD(&tmp); blk_start_plug(&plug); spin_lock(lock); while (!list_empty(list)) { bh = BH_ENTRY(list->next); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh) || buffer_locked(bh)) { list_add(&bh->b_assoc_buffers, &tmp); bh->b_assoc_map = mapping; if (buffer_dirty(bh)) { get_bh(bh); spin_unlock(lock); /* * Ensure any pending I/O completes so that * write_dirty_buffer() actually writes the * current contents - it is a noop if I/O is * still in flight on potentially older * contents. */ write_dirty_buffer(bh, REQ_SYNC); /* * Kick off IO for the previous mapping. Note * that we will not run the very last mapping, * wait_on_buffer() will do that for us * through sync_buffer(). */ brelse(bh); spin_lock(lock); } } } spin_unlock(lock); blk_finish_plug(&plug); spin_lock(lock); while (!list_empty(&tmp)) { bh = BH_ENTRY(tmp.prev); get_bh(bh); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh)) { list_add(&bh->b_assoc_buffers, &mapping->private_list); bh->b_assoc_map = mapping; } spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); } spin_unlock(lock); err2 = osync_buffers_list(lock, list); if (err) return err; else return err2; } /* * Invalidate any and all dirty buffers on a given inode. We are * probably unmounting the fs, but that doesn't mean we have already * done a sync(). Just drop the buffers from the inode list. * * NOTE: we take the inode's blockdev's mapping's private_lock. Which * assumes that all the buffers are against the blockdev. Not true * for reiserfs. */ void invalidate_inode_buffers(struct inode *inode) { if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->private_list; struct address_space *buffer_mapping = mapping->private_data; spin_lock(&buffer_mapping->private_lock); while (!list_empty(list)) __remove_assoc_queue(BH_ENTRY(list->next)); spin_unlock(&buffer_mapping->private_lock); } } EXPORT_SYMBOL(invalidate_inode_buffers); /* * Remove any clean buffers from the inode's buffer list. This is called * when we're trying to free the inode itself. Those buffers can pin it. * * Returns true if all buffers were removed. */ int remove_inode_buffers(struct inode *inode) { int ret = 1; if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->private_list; struct address_space *buffer_mapping = mapping->private_data; spin_lock(&buffer_mapping->private_lock); while (!list_empty(list)) { struct buffer_head *bh = BH_ENTRY(list->next); if (buffer_dirty(bh)) { ret = 0; break; } __remove_assoc_queue(bh); } spin_unlock(&buffer_mapping->private_lock); } return ret; } /* * Create the appropriate buffers when given a page for data area and * the size of each buffer.. Use the bh->b_this_page linked list to * follow the buffers created. Return NULL if unable to create more * buffers. * * The retry flag is used to differentiate async IO (paging, swapping) * which may not fail from ordinary buffer allocations. */ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry) { struct buffer_head *bh, *head; gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; long offset; struct mem_cgroup *memcg, *old_memcg; if (retry) gfp |= __GFP_NOFAIL; /* The page lock pins the memcg */ memcg = page_memcg(page); old_memcg = set_active_memcg(memcg); head = NULL; offset = PAGE_SIZE; while ((offset -= size) >= 0) { bh = alloc_buffer_head(gfp); if (!bh) goto no_grow; bh->b_this_page = head; bh->b_blocknr = -1; head = bh; bh->b_size = size; /* Link the buffer to its page */ set_bh_page(bh, page, offset); } out: set_active_memcg(old_memcg); return head; /* * In case anything failed, we just free everything we got. */ no_grow: if (head) { do { bh = head; head = head->b_this_page; free_buffer_head(bh); } while (head); } goto out; } EXPORT_SYMBOL_GPL(alloc_page_buffers); static inline void link_dev_buffers(struct page *page, struct buffer_head *head) { struct buffer_head *bh, *tail; bh = head; do { tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; attach_page_private(page, head); } static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) { sector_t retval = ~((sector_t)0); loff_t sz = i_size_read(bdev->bd_inode); if (sz) { unsigned int sizebits = blksize_bits(size); retval = (sz >> sizebits); } return retval; } /* * Initialise the state of a blockdev page's buffers. */ static sector_t init_page_buffers(struct page *page, struct block_device *bdev, sector_t block, int size) { struct buffer_head *head = page_buffers(page); struct buffer_head *bh = head; int uptodate = PageUptodate(page); sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode), size); do { if (!buffer_mapped(bh)) { bh->b_end_io = NULL; bh->b_private = NULL; bh->b_bdev = bdev; bh->b_blocknr = block; if (uptodate) set_buffer_uptodate(bh); if (block < end_block) set_buffer_mapped(bh); } block++; bh = bh->b_this_page; } while (bh != head); /* * Caller needs to validate requested block against end of device. */ return end_block; } /* * Create the page-cache page that contains the requested block. * * This is used purely for blockdev mappings. */ static int grow_dev_page(struct block_device *bdev, sector_t block, pgoff_t index, int size, int sizebits, gfp_t gfp) { struct inode *inode = bdev->bd_inode; struct page *page; struct buffer_head *bh; sector_t end_block; int ret = 0; gfp_t gfp_mask; gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp; /* * XXX: __getblk_slow() can not really deal with failure and * will endlessly loop on improvised global reclaim. Prefer * looping in the allocator rather than here, at least that * code knows what it's doing. */ gfp_mask |= __GFP_NOFAIL; page = find_or_create_page(inode->i_mapping, index, gfp_mask); BUG_ON(!PageLocked(page)); if (page_has_buffers(page)) { bh = page_buffers(page); if (bh->b_size == size) { end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, size); goto done; } if (!try_to_free_buffers(page)) goto failed; } /* * Allocate some buffers for this page */ bh = alloc_page_buffers(page, size, true); /* * Link the page to the buffers and initialise them. Take the * lock to be atomic wrt __find_get_block(), which does not * run under the page lock. */ spin_lock(&inode->i_mapping->private_lock); link_dev_buffers(page, bh); end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, size); spin_unlock(&inode->i_mapping->private_lock); done: ret = (block < end_block) ? 1 : -ENXIO; failed: unlock_page(page); put_page(page); return ret; } /* * Create buffers for the specified block device block's page. If * that page was dirty, the buffers are set dirty also. */ static int grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp) { pgoff_t index; int sizebits; sizebits = PAGE_SHIFT - __ffs(size); index = block >> sizebits; /* * Check for a block which wants to lie outside our maximum possible * pagecache index. (this comparison is done using sector_t types). */ if (unlikely(index != block >> sizebits)) { printk(KERN_ERR "%s: requested out-of-range block %llu for " "device %pg\n", __func__, (unsigned long long)block, bdev); return -EIO; } /* Create a page with the proper size buffers.. */ return grow_dev_page(bdev, block, index, size, sizebits, gfp); } static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { /* Size must be multiple of hard sectorsize */ if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { printk(KERN_ERR "getblk(): invalid block size %d requested\n", size); printk(KERN_ERR "logical block size: %d\n", bdev_logical_block_size(bdev)); dump_stack(); return NULL; } for (;;) { struct buffer_head *bh; int ret; bh = __find_get_block(bdev, block, size); if (bh) return bh; ret = grow_buffers(bdev, block, size, gfp); if (ret < 0) return NULL; } } /* * The relationship between dirty buffers and dirty pages: * * Whenever a page has any dirty buffers, the page's dirty bit is set, and * the page is tagged dirty in the page cache. * * At all times, the dirtiness of the buffers represents the dirtiness of * subsections of the page. If the page has buffers, the page dirty bit is * merely a hint about the true dirty state. * * When a page is set dirty in its entirety, all its buffers are marked dirty * (if the page has buffers). * * When a buffer is marked dirty, its page is dirtied, but the page's other * buffers are not. * * Also. When blockdev buffers are explicitly read with bread(), they * individually become uptodate. But their backing page remains not * uptodate - even if all of its buffers are uptodate. A subsequent * block_read_full_page() against that page will discover all the uptodate * buffers, will set the page uptodate and will perform no I/O. */ /** * mark_buffer_dirty - mark a buffer_head as needing writeout * @bh: the buffer_head to mark dirty * * mark_buffer_dirty() will set the dirty bit against the buffer, then set * its backing page dirty, then tag the page as dirty in the page cache * and then attach the address_space's inode to its superblock's dirty * inode list. * * mark_buffer_dirty() is atomic. It takes bh->b_page->mapping->private_lock, * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) { WARN_ON_ONCE(!buffer_uptodate(bh)); trace_block_dirty_buffer(bh); /* * Very *carefully* optimize the it-is-already-dirty case. * * Don't let the final "is it dirty" escape to before we * perhaps modified the buffer. */ if (buffer_dirty(bh)) { smp_mb(); if (buffer_dirty(bh)) return; } if (!test_set_buffer_dirty(bh)) { struct page *page = bh->b_page; struct address_space *mapping = NULL; lock_page_memcg(page); if (!TestSetPageDirty(page)) { mapping = page_mapping(page); if (mapping) __set_page_dirty(page, mapping, 0); } unlock_page_memcg(page); if (mapping) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } } EXPORT_SYMBOL_NS(mark_buffer_dirty, ANDROID_GKI_VFS_EXPORT_ONLY); void mark_buffer_write_io_error(struct buffer_head *bh) { struct super_block *sb; set_buffer_write_io_error(bh); /* FIXME: do we need to set this in both places? */ if (bh->b_page && bh->b_page->mapping) mapping_set_error(bh->b_page->mapping, -EIO); if (bh->b_assoc_map) mapping_set_error(bh->b_assoc_map, -EIO); rcu_read_lock(); sb = READ_ONCE(bh->b_bdev->bd_super); if (sb) errseq_set(&sb->s_wb_err, -EIO); rcu_read_unlock(); } EXPORT_SYMBOL_NS(mark_buffer_write_io_error, ANDROID_GKI_VFS_EXPORT_ONLY); /* * Decrement a buffer_head's reference count. If all buffers against a page * have zero reference count, are clean and unlocked, and if the page is clean * and unlocked then try_to_free_buffers() may strip the buffers from the page * in preparation for freeing it (sometimes, rarely, buffers are removed from * a page but it ends up not being freed, and buffers may later be reattached). */ void __brelse(struct buffer_head * buf) { if (atomic_read(&buf->b_count)) { put_bh(buf); return; } WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n"); } EXPORT_SYMBOL_NS(__brelse, ANDROID_GKI_VFS_EXPORT_ONLY); /* * bforget() is like brelse(), except it discards any * potentially dirty data. */ void __bforget(struct buffer_head *bh) { clear_buffer_dirty(bh); if (bh->b_assoc_map) { struct address_space *buffer_mapping = bh->b_page->mapping; spin_lock(&buffer_mapping->private_lock); list_del_init(&bh->b_assoc_buffers); bh->b_assoc_map = NULL; spin_unlock(&buffer_mapping->private_lock); } __brelse(bh); } EXPORT_SYMBOL_NS(__bforget, ANDROID_GKI_VFS_EXPORT_ONLY); static struct buffer_head *__bread_slow(struct buffer_head *bh) { lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); return bh; } else { get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, 0, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; } brelse(bh); return NULL; } /* * Per-cpu buffer LRU implementation. To reduce the cost of __find_get_block(). * The bhs[] array is sorted - newest buffer is at bhs[0]. Buffers have their * refcount elevated by one when they're in an LRU. A buffer can only appear * once in a particular CPU's LRU. A single buffer can be present in multiple * CPU's LRUs at the same time. * * This is a transparent caching front-end to sb_bread(), sb_getblk() and * sb_find_get_block(). * * The LRUs themselves only need locking against invalidate_bh_lrus. We use * a local interrupt disable for that. */ #define BH_LRU_SIZE 16 struct bh_lru { struct buffer_head *bhs[BH_LRU_SIZE]; }; static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }}; #ifdef CONFIG_SMP #define bh_lru_lock() local_irq_disable() #define bh_lru_unlock() local_irq_enable() #else #define bh_lru_lock() preempt_disable() #define bh_lru_unlock() preempt_enable() #endif static inline void check_irqs_on(void) { #ifdef irqs_disabled BUG_ON(irqs_disabled()); #endif } /* * Install a buffer_head into this cpu's LRU. If not already in the LRU, it is * inserted at the front, and the buffer_head at the back if any is evicted. * Or, if already in the LRU it is moved to the front. */ static void bh_lru_install(struct buffer_head *bh) { struct buffer_head *evictee = bh; struct bh_lru *b; int i; check_irqs_on(); bh_lru_lock(); /* * the refcount of buffer_head in bh_lru prevents dropping the * attached page(i.e., try_to_free_buffers) so it could cause * failing page migration. * Skip putting upcoming bh into bh_lru until migration is done. */ if (lru_cache_disabled()) { bh_lru_unlock(); return; } b = this_cpu_ptr(&bh_lrus); for (i = 0; i < BH_LRU_SIZE; i++) { swap(evictee, b->bhs[i]); if (evictee == bh) { bh_lru_unlock(); return; } } get_bh(bh); bh_lru_unlock(); brelse(evictee); } /* * Look up the bh in this cpu's LRU. If it's there, move it to the head. */ static struct buffer_head * lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *ret = NULL; unsigned int i; check_irqs_on(); bh_lru_lock(); for (i = 0; i < BH_LRU_SIZE; i++) { struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]); if (bh && bh->b_blocknr == block && bh->b_bdev == bdev && bh->b_size == size) { if (i) { while (i) { __this_cpu_write(bh_lrus.bhs[i], __this_cpu_read(bh_lrus.bhs[i - 1])); i--; } __this_cpu_write(bh_lrus.bhs[0], bh); } get_bh(bh); ret = bh; break; } } bh_lru_unlock(); return ret; } /* * Perform a pagecache lookup for the matching buffer. If it's there, refresh * it in the LRU and mark it as accessed. If it is not present then return * NULL */ struct buffer_head * __find_get_block(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block); if (bh) bh_lru_install(bh); } else touch_buffer(bh); return bh; } EXPORT_SYMBOL(__find_get_block); /* * __getblk_gfp() will locate (and, if necessary, create) the buffer_head * which corresponds to the passed block_device, block and size. The * returned buffer has its reference count incremented. * * __getblk_gfp() will lock up the machine if grow_dev_page's * try_to_free_buffers() attempt is failing. FIXME, perhaps? */ struct buffer_head * __getblk_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh = __find_get_block(bdev, block, size); might_sleep(); if (bh == NULL) bh = __getblk_slow(bdev, block, size, gfp); return bh; } EXPORT_SYMBOL(__getblk_gfp); /* * Do async read-ahead on a buffer.. */ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *bh = __getblk(bdev, block, size); if (likely(bh)) { ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh); brelse(bh); } } EXPORT_SYMBOL_NS(__breadahead, ANDROID_GKI_VFS_EXPORT_ONLY); void __breadahead_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp); if (likely(bh)) { ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh); brelse(bh); } } EXPORT_SYMBOL(__breadahead_gfp); /** * __bread_gfp() - 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 * @gfp: page allocation flag * * Reads a specified block, and returns buffer head that contains it. * The page cache can be allocated from non-movable area * not to prevent page migration if you set gfp to zero. * It returns NULL if the block was unreadable. */ struct buffer_head * __bread_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp); if (likely(bh) && !buffer_uptodate(bh)) bh = __bread_slow(bh); return bh; } EXPORT_SYMBOL_NS(__bread_gfp, ANDROID_GKI_VFS_EXPORT_ONLY); static void __invalidate_bh_lrus(struct bh_lru *b) { int i; for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } } /* * invalidate_bh_lrus() is called rarely - but not only at unmount. * This doesn't race because it runs in each cpu either in irq * or with preempt disabled. */ static void invalidate_bh_lru(void *arg) { struct bh_lru *b = &get_cpu_var(bh_lrus); __invalidate_bh_lrus(b); put_cpu_var(bh_lrus); } bool has_bh_in_lru(int cpu, void *dummy) { struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu); int i; for (i = 0; i < BH_LRU_SIZE; i++) { if (b->bhs[i]) return true; } return false; } void invalidate_bh_lrus(void) { on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1); } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); /* * It's called from workqueue context so we need a bh_lru_lock to close * the race with preemption/irq. */ void invalidate_bh_lrus_cpu(void) { struct bh_lru *b; bh_lru_lock(); b = this_cpu_ptr(&bh_lrus); __invalidate_bh_lrus(b); bh_lru_unlock(); } void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset) { bh->b_page = page; BUG_ON(offset >= PAGE_SIZE); if (PageHighMem(page)) /* * This catches illegal uses and preserves the offset: */ bh->b_data = (char *)(0 + offset); else bh->b_data = page_address(page) + offset; } EXPORT_SYMBOL(set_bh_page); /* * Called when truncating a buffer on a page completely. */ /* Bits that are cleared during an invalidate */ #define BUFFER_FLAGS_DISCARD \ (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ 1 << BH_Delay | 1 << BH_Unwritten) static void discard_buffer(struct buffer_head * bh) { unsigned long b_state, b_state_old; lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; b_state = bh->b_state; for (;;) { b_state_old = cmpxchg(&bh->b_state, b_state, (b_state & ~BUFFER_FLAGS_DISCARD)); if (b_state_old == b_state) break; b_state = b_state_old; } unlock_buffer(bh); } /** * block_invalidatepage - invalidate part or all of a buffer-backed page * * @page: the page which is affected * @offset: start of the range to invalidate * @length: length of the range to invalidate * * block_invalidatepage() is called when all or part of the page has become * invalidated by a truncate operation. * * block_invalidatepage() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void block_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { struct buffer_head *head, *bh, *next; unsigned int curr_off = 0; unsigned int stop = length + offset; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) goto out; /* * Check for overflow */ BUG_ON(stop > PAGE_SIZE || stop < length); head = page_buffers(page); bh = head; do { unsigned int next_off = curr_off + bh->b_size; next = bh->b_this_page; /* * Are we still fully in range ? */ if (next_off > stop) goto out; /* * is this block fully invalidated? */ if (offset <= curr_off) discard_buffer(bh); curr_off = next_off; bh = next; } while (bh != head); /* * We release buffers only if the entire page is being invalidated. * The get_block cached value has been unconditionally invalidated, * so real IO is not possible anymore. */ if (length == PAGE_SIZE) try_to_release_page(page, 0); out: return; } EXPORT_SYMBOL_NS(block_invalidatepage, ANDROID_GKI_VFS_EXPORT_ONLY); /* * We attach and possibly dirty the buffers atomically wrt * __set_page_dirty_buffers() via private_lock. try_to_free_buffers * is already excluded via the page lock. */ void create_empty_buffers(struct page *page, unsigned long blocksize, unsigned long b_state) { struct buffer_head *bh, *head, *tail; head = alloc_page_buffers(page, blocksize, true); bh = head; do { bh->b_state |= b_state; tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; spin_lock(&page->mapping->private_lock); if (PageUptodate(page) || PageDirty(page)) { bh = head; do { if (PageDirty(page)) set_buffer_dirty(bh); if (PageUptodate(page)) set_buffer_uptodate(bh); bh = bh->b_this_page; } while (bh != head); } attach_page_private(page, head); spin_unlock(&page->mapping->private_lock); } EXPORT_SYMBOL_NS(create_empty_buffers, ANDROID_GKI_VFS_EXPORT_ONLY); /** * clean_bdev_aliases: clean a range of buffers in block device * @bdev: Block device to clean buffers in * @block: Start of a range of blocks to clean * @len: Number of blocks to clean * * We are taking a range of blocks for data and we don't want writeback of any * buffer-cache aliases starting from return from this function and until the * moment when something will explicitly mark the buffer dirty (hopefully that * will not happen until we will free that block ;-) We don't even need to mark * it not-uptodate - nobody can expect anything from a newly allocated buffer * anyway. We used to use unmap_buffer() for such invalidation, but that was * wrong. We definitely don't want to mark the alias unmapped, for example - it * would confuse anyone who might pick it with bread() afterwards... * * Also.. Note that bforget() doesn't lock the buffer. So there can be * writeout I/O going on against recently-freed buffers. We don't wait on that * I/O in bforget() - it's more efficient to wait on the I/O only if we really * need to. That happens here. */ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) { struct inode *bd_inode = bdev->bd_inode; struct address_space *bd_mapping = bd_inode->i_mapping; struct pagevec pvec; pgoff_t index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); pgoff_t end; int i, count; struct buffer_head *bh; struct buffer_head *head; end = (block + len - 1) >> (PAGE_SHIFT - bd_inode->i_blkbits); pagevec_init(&pvec); while (pagevec_lookup_range(&pvec, bd_mapping, &index, end)) { count = pagevec_count(&pvec); for (i = 0; i < count; i++) { struct page *page = pvec.pages[i]; if (!page_has_buffers(page)) continue; /* * We use page lock instead of bd_mapping->private_lock * to pin buffers here since we can afford to sleep and * it scales better than a global spinlock lock. */ lock_page(page); /* Recheck when the page is locked which pins bhs */ if (!page_has_buffers(page)) goto unlock_page; head = page_buffers(page); bh = head; do { if (!buffer_mapped(bh) || (bh->b_blocknr < block)) goto next; if (bh->b_blocknr >= block + len) break; clear_buffer_dirty(bh); wait_on_buffer(bh); clear_buffer_req(bh); next: bh = bh->b_this_page; } while (bh != head); unlock_page: unlock_page(page); } pagevec_release(&pvec); cond_resched(); /* End of range already reached? */ if (index > end || !index) break; } } EXPORT_SYMBOL_NS(clean_bdev_aliases, ANDROID_GKI_VFS_EXPORT_ONLY); /* * Size is a power-of-two in the range 512..PAGE_SIZE, * and the case we care about most is PAGE_SIZE. * * So this *could* possibly be written with those * constraints in mind (relevant mostly if some * architecture has a slow bit-scan instruction) */ static inline int block_size_bits(unsigned int blocksize) { return ilog2(blocksize); } static struct buffer_head *create_page_buffers(struct page *page, struct inode *inode, unsigned int b_state) { BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) create_empty_buffers(page, 1 << READ_ONCE(inode->i_blkbits), b_state); return page_buffers(page); } /* * NOTE! All mapped/uptodate combinations are valid: * * Mapped Uptodate Meaning * * No No "unknown" - must do get_block() * No Yes "hole" - zero-filled * Yes No "allocated" - allocated on disk, not read in * Yes Yes "valid" - allocated and up-to-date in memory. * * "Dirty" is valid only with the last case (mapped+uptodate). */ /* * While block_write_full_page is writing back the dirty buffers under * the page lock, whoever dirtied the buffers may decide to clean them * again at any time. We handle that by only looking at the buffer * state inside lock_buffer(). * * If block_write_full_page() is called for regular writeback * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a * locked buffer. This only can happen if someone has written the buffer * directly, with submit_bh(). At the address_space level PageWriteback * prevents this contention from occurring. * * If block_write_full_page() is called with wbc->sync_mode == * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this * causes the writes to be flagged as synchronous writes. */ 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 err; sector_t block; sector_t last_block; struct buffer_head *bh, *head; unsigned int blocksize, bbits; int nr_underway = 0; int write_flags = wbc_to_write_flags(wbc); head = create_page_buffers(page, inode, (1 << BH_Dirty)|(1 << BH_Uptodate)); /* * Be very careful. We have no exclusion from __set_page_dirty_buffers * here, and the (potentially unmapped) buffers may become dirty at * any time. If a buffer becomes dirty here after we've inspected it * then we just miss that fact, and the page stays dirty. * * Buffers outside i_size may be dirtied by __set_page_dirty_buffers; * handle that here by just cleaning them. */ bh = head; blocksize = bh->b_size; bbits = block_size_bits(blocksize); block = (sector_t)page->index << (PAGE_SHIFT - bbits); last_block = (i_size_read(inode) - 1) >> bbits; /* * Get all the dirty buffers mapped to disk addresses and * handle any aliases from the underlying blockdev's mapping. */ do { if (block > last_block) { /* * mapped buffers outside i_size will occur, because * this page can be outside i_size when there is a * truncate in progress. */ /* * The buffer was zeroed by block_write_full_page() */ clear_buffer_dirty(bh); set_buffer_uptodate(bh); } else if ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, block, bh, 1); if (err) goto recover; clear_buffer_delay(bh); if (buffer_new(bh)) { /* blockdev mappings never come here */ clear_buffer_new(bh); clean_bdev_bh_alias(bh); } } bh = bh->b_this_page; block++; } while (bh != head); do { if (!buffer_mapped(bh)) continue; /* * If it's a fully non-blocking write attempt and we cannot * lock the buffer then redirty the page. Note that this can * potentially cause a busy-wait loop from writeback threads * and kswapd activity, but those code paths have their own * higher-level throttling. */ if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else if (!trylock_buffer(bh)) { redirty_page_for_writepage(wbc, page); continue; } if (test_clear_buffer_dirty(bh)) { mark_buffer_async_write_endio(bh, handler); } else { unlock_buffer(bh); } } while ((bh = bh->b_this_page) != head); /* * The page and its buffers are protected by PageWriteback(), so we can * drop the bh refcounts early. */ BUG_ON(PageWriteback(page)); set_page_writeback(page); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); unlock_page(page); err = 0; done: if (nr_underway == 0) { /* * The page was marked dirty, but the buffers were * clean. Someone wrote them back by hand with * ll_rw_block/submit_bh. A rare case. */ end_page_writeback(page); /* * The page and buffer_heads can be released at any time from * here on. */ } return err; recover: /* * ENOSPC, or some other error. We may already have added some * blocks to the file, so we need to write these out to avoid * exposing stale data. * The page is currently locked and not marked for writeback */ bh = head; /* Recovery: lock and submit the mapped buffers */ do { if (buffer_mapped(bh) && buffer_dirty(bh) && !buffer_delay(bh)) { lock_buffer(bh); mark_buffer_async_write_endio(bh, handler); } else { /* * The buffer may have been set dirty during * attachment to a dirty page. */ clear_buffer_dirty(bh); } } while ((bh = bh->b_this_page) != head); SetPageError(page); BUG_ON(PageWriteback(page)); mapping_set_error(page->mapping, err); set_page_writeback(page); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); unlock_page(page); goto done; } EXPORT_SYMBOL(__block_write_full_page); /* * If a page has any new buffers, zero them out here, and mark them uptodate * and dirty so they'll be written out (in order to prevent uninitialised * block data from leaking). And clear the new bit. */ void page_zero_new_buffers(struct page *page, unsigned from, unsigned to) { unsigned int block_start, block_end; struct buffer_head *head, *bh; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) return; bh = head = page_buffers(page); block_start = 0; do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { if (!PageUptodate(page)) { unsigned start, size; start = max(from, block_start); size = min(to, block_end) - start; zero_user(page, start, size); set_buffer_uptodate(bh); } clear_buffer_new(bh); mark_buffer_dirty(bh); } } block_start = block_end; bh = bh->b_this_page; } while (bh != head); } EXPORT_SYMBOL_NS(page_zero_new_buffers, ANDROID_GKI_VFS_EXPORT_ONLY); static void iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, const struct iomap *iomap) { loff_t offset = block << inode->i_blkbits; bh->b_bdev = iomap->bdev; /* * Block points to offset in file we need to map, iomap contains * the offset at which the map starts. If the map ends before the * current block, then do not map the buffer and let the caller * handle it. */ BUG_ON(offset >= iomap->offset + iomap->length); switch (iomap->type) { case IOMAP_HOLE: /* * If the buffer is not up to date or beyond the current EOF, * we need to mark it as new to ensure sub-block zeroing is * executed if necessary. */ if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); break; case IOMAP_DELALLOC: if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); set_buffer_uptodate(bh); set_buffer_mapped(bh); set_buffer_delay(bh); break; case IOMAP_UNWRITTEN: /* * For unwritten regions, we always need to ensure that regions * in the block we are not writing to are zeroed. Mark the * buffer as new to ensure this. */ set_buffer_new(bh); set_buffer_unwritten(bh); fallthrough; case IOMAP_MAPPED: if ((iomap->flags & IOMAP_F_NEW) || offset >= i_size_read(inode)) set_buffer_new(bh); bh->b_blocknr = (iomap->addr + offset - iomap->offset) >> inode->i_blkbits; set_buffer_mapped(bh); break; } } int __block_write_begin_int(struct page *page, loff_t pos, unsigned len, get_block_t *get_block, const struct iomap *iomap) { unsigned from = pos & (PAGE_SIZE - 1); unsigned to = from + len; struct inode *inode = page->mapping->host; unsigned block_start, block_end; sector_t block; int err = 0; unsigned blocksize, bbits; struct buffer_head *bh, *head, *wait[2], **wait_bh=wait; BUG_ON(!PageLocked(page)); BUG_ON(from > PAGE_SIZE); BUG_ON(to > PAGE_SIZE); BUG_ON(from > to); head = create_page_buffers(page, inode, 0); blocksize = head->b_size; bbits = block_size_bits(blocksize); block = (sector_t)page->index << (PAGE_SHIFT - bbits); 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 (PageUptodate(page)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } continue; } if (buffer_new(bh)) clear_buffer_new(bh); if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); if (get_block) { err = get_block(inode, block, bh, 1); if (err) break; } else { iomap_to_bh(inode, block, bh, iomap); } if (buffer_new(bh)) { clean_bdev_bh_alias(bh); if (PageUptodate(page)) { clear_buffer_new(bh); set_buffer_uptodate(bh); mark_buffer_dirty(bh); continue; } if (block_end > to || block_start < from) zero_user_segments(page, to, block_end, block_start, from); continue; } } if (PageUptodate(page)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); continue; } if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh) && (block_start < from || block_end > to)) { ll_rw_block(REQ_OP_READ, 0, 1, &bh); *wait_bh++=bh; } } /* * If we issued read requests - let them complete. */ while(wait_bh > wait) { wait_on_buffer(*--wait_bh); if (!buffer_uptodate(*wait_bh)) err = -EIO; } if (unlikely(err)) page_zero_new_buffers(page, from, to); return err; } int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block) { return __block_write_begin_int(page, pos, len, get_block, NULL); } EXPORT_SYMBOL(__block_write_begin); static int __block_commit_write(struct inode *inode, struct page *page, unsigned from, unsigned to) { unsigned block_start, block_end; int partial = 0; unsigned blocksize; struct buffer_head *bh, *head; bh = head = page_buffers(page); blocksize = bh->b_size; block_start = 0; do { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (!buffer_uptodate(bh)) partial = 1; } else { set_buffer_uptodate(bh); mark_buffer_dirty(bh); } if (buffer_new(bh)) clear_buffer_new(bh); block_start = block_end; bh = bh->b_this_page; } while (bh != head); /* * If this is a partial write which happened to make all buffers * uptodate then we can optimize away a bogus readpage() for * the next read(). Here we 'discover' whether the page went * uptodate as a result of this (potentially partial) write. */ if (!partial) SetPageUptodate(page); return 0; } /* * block_write_begin takes care of the basic task of block allocation and * bringing partial write blocks uptodate first. * * The filesystem needs to handle block truncation upon failure. */ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, get_block_t *get_block) { pgoff_t index = pos >> PAGE_SHIFT; struct page *page; int status; page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; status = __block_write_begin(page, pos, len, get_block); if (unlikely(status)) { unlock_page(page); put_page(page); page = NULL; } *pagep = page; return status; } EXPORT_SYMBOL(block_write_begin); int block_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; unsigned start; start = pos & (PAGE_SIZE - 1); if (unlikely(copied < len)) { /* * The buffers that were written will now be uptodate, so we * don't have to worry about a readpage reading them and * overwriting a partial write. However if we have encountered * a short write and only partially written into a buffer, it * will not be marked uptodate, so a readpage might come in and * destroy our partial write. * * Do the simplest thing, and just treat any short write to a * non uptodate page as a zero-length write, and force the * caller to redo the whole thing. */ if (!PageUptodate(page)) copied = 0; page_zero_new_buffers(page, start+copied, start+len); } flush_dcache_page(page); /* This could be a short (even 0-length) commit */ __block_commit_write(inode, page, start, start+copied); return copied; } EXPORT_SYMBOL(block_write_end); int generic_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; loff_t old_size = inode->i_size; bool i_size_changed = false; copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); /* * No need to use i_size_read() here, the i_size cannot change under us * because we hold i_rwsem. * * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. */ if (pos + copied > inode->i_size) { i_size_write(inode, pos + copied); i_size_changed = true; } unlock_page(page); put_page(page); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock * ordering of page lock and transaction start for journaling * filesystems. */ if (i_size_changed) mark_inode_dirty(inode); return copied; } EXPORT_SYMBOL_NS(generic_write_end, ANDROID_GKI_VFS_EXPORT_ONLY); /* * block_is_partially_uptodate checks whether buffers within a page are * uptodate or not. * * Returns true if all buffers which correspond to a file portion * we want to read are uptodate. */ int block_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count) { unsigned block_start, block_end, blocksize; unsigned to; struct buffer_head *bh, *head; int ret = 1; if (!page_has_buffers(page)) return 0; head = page_buffers(page); blocksize = head->b_size; to = min_t(unsigned, PAGE_SIZE - from, count); to = from + to; if (from < blocksize && to > PAGE_SIZE - blocksize) return 0; bh = head; block_start = 0; do { block_end = block_start + blocksize; if (block_end > from && block_start < to) { if (!buffer_uptodate(bh)) { ret = 0; break; } if (block_end >= to) break; } block_start = block_end; bh = bh->b_this_page; } while (bh != head); return ret; } EXPORT_SYMBOL_NS(block_is_partially_uptodate, ANDROID_GKI_VFS_EXPORT_ONLY); /* * Generic "read page" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. * Reads the page asynchronously --- the unlock_buffer() and * set/clear_buffer_uptodate() functions propagate buffer state into the * page struct once IO has completed. */ int block_read_full_page(struct page *page, get_block_t *get_block) { struct inode *inode = page->mapping->host; sector_t iblock, lblock; struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE]; unsigned int blocksize, bbits; int nr, i; int fully_mapped = 1; head = create_page_buffers(page, inode, 0); blocksize = head->b_size; bbits = block_size_bits(blocksize); iblock = (sector_t)page->index << (PAGE_SHIFT - bbits); lblock = (i_size_read(inode)+blocksize-1) >> bbits; bh = head; nr = 0; i = 0; do { if (buffer_uptodate(bh)) continue; if (!buffer_mapped(bh)) { int err = 0; fully_mapped = 0; if (iblock < lblock) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) SetPageError(page); } if (!buffer_mapped(bh)) { zero_user(page, i * blocksize, blocksize); if (!err) set_buffer_uptodate(bh); continue; } /* * get_block() might have updated the buffer * synchronously */ if (buffer_uptodate(bh)) continue; } arr[nr++] = bh; } while (i++, iblock++, (bh = bh->b_this_page) != head); if (fully_mapped) SetPageMappedToDisk(page); if (!nr) { /* * All buffers are uptodate - we can set the page uptodate * as well. But not if get_block() returned an error. */ if (!PageError(page)) SetPageUptodate(page); unlock_page(page); return 0; } /* Stage two: lock the buffers */ for (i = 0; i < nr; i++) { bh = arr[i]; lock_buffer(bh); mark_buffer_async_read(bh); } /* * Stage 3: start the IO. Check for uptodateness * inside the buffer lock in case another process reading * the underlying blockdev brought it uptodate (the sct fix). */ for (i = 0; i < nr; i++) { bh = arr[i]; if (buffer_uptodate(bh)) end_buffer_async_read(bh, 1); else submit_bh(REQ_OP_READ, 0, bh); } return 0; } EXPORT_SYMBOL(block_read_full_page); /* utility function for filesystems that need to do work on expanding * truncates. Uses filesystem pagecache writes to allow the filesystem to * deal with the hole. */ int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; struct page *page; void *fsdata = NULL; int err; err = inode_newsize_ok(inode, size); if (err) goto out; err = pagecache_write_begin(NULL, mapping, size, 0, AOP_FLAG_CONT_EXPAND, &page, &fsdata); if (err) goto out; err = pagecache_write_end(NULL, mapping, size, 0, 0, page, fsdata); BUG_ON(err > 0); out: return err; } EXPORT_SYMBOL_NS(generic_cont_expand_simple, ANDROID_GKI_VFS_EXPORT_ONLY); static int cont_expand_zero(struct file *file, struct address_space *mapping, loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); struct page *page; void *fsdata = NULL; pgoff_t index, curidx; loff_t curpos; unsigned zerofrom, offset, len; int err = 0; index = pos >> PAGE_SHIFT; offset = pos & ~PAGE_MASK; while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) { zerofrom = curpos & ~PAGE_MASK; if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = PAGE_SIZE - zerofrom; err = pagecache_write_begin(file, mapping, curpos, len, 0, &page, &fsdata); if (err) goto out; zero_user(page, zerofrom, len); err = pagecache_write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; balance_dirty_pages_ratelimited(mapping); if (fatal_signal_pending(current)) { err = -EINTR; goto out; } } /* page covers the boundary, find the boundary offset */ if (index == curidx) { zerofrom = curpos & ~PAGE_MASK; /* if we will expand the thing last block will be filled */ if (offset <= zerofrom) { goto out; } if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = offset - zerofrom; err = pagecache_write_begin(file, mapping, curpos, len, 0, &page, &fsdata); if (err) goto out; zero_user(page, zerofrom, len); err = pagecache_write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; } out: return err; } /* * For moronic filesystems that do not allow holes in file. * We may have to extend the file. */ int cont_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); unsigned int zerofrom; int err; err = cont_expand_zero(file, mapping, pos, bytes); if (err) return err; zerofrom = *bytes & ~PAGE_MASK; if (pos+len > *bytes && zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } return block_write_begin(mapping, pos, len, flags, pagep, get_block); } EXPORT_SYMBOL(cont_write_begin); int block_commit_write(struct page *page, unsigned from, unsigned to) { struct inode *inode = page->mapping->host; __block_commit_write(inode,page,from,to); return 0; } EXPORT_SYMBOL(block_commit_write); /* * block_page_mkwrite() is not allowed to change the file size as it gets * called from a page fault handler when a page is first dirtied. Hence we must * be careful to check for EOF conditions here. We set the page up correctly * for a written page which means we get ENOSPC checking when writing into * holes and correct delalloc and unwritten extent mapping on filesystems that * support these features. * * We are not allowed to take the i_mutex here so we have to play games to * protect against truncate races as the page could now be beyond EOF. Because * truncate writes the inode size before removing pages, once we have the * page lock we can determine safely if the page is beyond EOF. If it is not * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. * * Direct callers of this function should protect against filesystem freezing * using sb_start_pagefault() - sb_end_pagefault() functions. */ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block) { struct page *page = vmf->page; struct inode *inode = file_inode(vma->vm_file); unsigned long end; loff_t size; int ret; lock_page(page); size = i_size_read(inode); if ((page->mapping != inode->i_mapping) || (page_offset(page) > size)) { /* We overload EFAULT to mean page got truncated */ ret = -EFAULT; goto out_unlock; } /* page is wholly or partially inside EOF */ if (((page->index + 1) << PAGE_SHIFT) > size) end = size & ~PAGE_MASK; else end = PAGE_SIZE; ret = __block_write_begin(page, 0, end, get_block); if (!ret) ret = block_commit_write(page, 0, end); if (unlikely(ret < 0)) goto out_unlock; set_page_dirty(page); wait_for_stable_page(page); return 0; out_unlock: unlock_page(page); return ret; } EXPORT_SYMBOL(block_page_mkwrite); /* * nobh_write_begin()'s prereads are special: the buffer_heads are freed * immediately, while under the page lock. So it needs a special end_io * handler which does not touch the bh after unlocking it. */ static void end_buffer_read_nobh(struct buffer_head *bh, int uptodate) { __end_buffer_read_notouch(bh, uptodate); } /* * Attach the singly-linked list of buffers created by nobh_write_begin, to * the page (converting it to circular linked list and taking care of page * dirty races). */ static void attach_nobh_buffers(struct page *page, struct buffer_head *head) { struct buffer_head *bh; BUG_ON(!PageLocked(page)); spin_lock(&page->mapping->private_lock); bh = head; do { if (PageDirty(page)) set_buffer_dirty(bh); if (!bh->b_this_page) bh->b_this_page = head; bh = bh->b_this_page; } while (bh != head); attach_page_private(page, head); spin_unlock(&page->mapping->private_lock); } /* * On entry, the page is fully not uptodate. * On exit the page is fully uptodate in the areas outside (from,to) * The filesystem needs to handle block truncation upon failure. */ int nobh_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, get_block_t *get_block) { struct inode *inode = mapping->host; const unsigned blkbits = inode->i_blkbits; const unsigned blocksize = 1 << blkbits; struct buffer_head *head, *bh; struct page *page; pgoff_t index; unsigned from, to; unsigned block_in_page; unsigned block_start, block_end; sector_t block_in_file; int nr_reads = 0; int ret = 0; int is_mapped_to_disk = 1; index = pos >> PAGE_SHIFT; from = pos & (PAGE_SIZE - 1); to = from + len; page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; *pagep = page; *fsdata = NULL; if (page_has_buffers(page)) { ret = __block_write_begin(page, pos, len, get_block); if (unlikely(ret)) goto out_release; return ret; } if (PageMappedToDisk(page)) return 0; /* * Allocate buffers so that we can keep track of state, and potentially * attach them to the page if an error occurs. In the common case of * no error, they will just be freed again without ever being attached * to the page (which is all OK, because we're under the page lock). * * Be careful: the buffer linked list is a NULL terminated one, rather * than the circular one we're used to. */ head = alloc_page_buffers(page, blocksize, false); if (!head) { ret = -ENOMEM; goto out_release; } block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits); /* * We loop across all blocks in the page, whether or not they are * part of the affected region. This is so we can discover if the * page is fully mapped-to-disk. */ for (block_start = 0, block_in_page = 0, bh = head; block_start < PAGE_SIZE; block_in_page++, block_start += blocksize, bh = bh->b_this_page) { int create; block_end = block_start + blocksize; bh->b_state = 0; create = 1; if (block_start >= to) create = 0; ret = get_block(inode, block_in_file + block_in_page, bh, create); if (ret) goto failed; if (!buffer_mapped(bh)) is_mapped_to_disk = 0; if (buffer_new(bh)) clean_bdev_bh_alias(bh); if (PageUptodate(page)) { set_buffer_uptodate(bh); continue; } if (buffer_new(bh) || !buffer_mapped(bh)) { zero_user_segments(page, block_start, from, to, block_end); continue; } if (buffer_uptodate(bh)) continue; /* reiserfs does this */ if (block_start < from || block_end > to) { lock_buffer(bh); bh->b_end_io = end_buffer_read_nobh; submit_bh(REQ_OP_READ, 0, bh); nr_reads++; } } if (nr_reads) { /* * The page is locked, so these buffers are protected from * any VM or truncate activity. Hence we don't need to care * for the buffer_head refcounts. */ for (bh = head; bh; bh = bh->b_this_page) { wait_on_buffer(bh); if (!buffer_uptodate(bh)) ret = -EIO; } if (ret) goto failed; } if (is_mapped_to_disk) SetPageMappedToDisk(page); *fsdata = head; /* to be released by nobh_write_end */ return 0; failed: BUG_ON(!ret); /* * Error recovery is a bit difficult. We need to zero out blocks that * were newly allocated, and dirty them to ensure they get written out. * Buffers need to be attached to the page at this point, otherwise * the handling of potential IO errors during writeout would be hard * (could try doing synchronous writeout, but what if that fails too?) */ attach_nobh_buffers(page, head); page_zero_new_buffers(page, from, to); out_release: unlock_page(page); put_page(page); *pagep = NULL; return ret; } EXPORT_SYMBOL(nobh_write_begin); int nobh_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = page->mapping->host; struct buffer_head *head = fsdata; struct buffer_head *bh; BUG_ON(fsdata != NULL && page_has_buffers(page)); if (unlikely(copied < len) && head) attach_nobh_buffers(page, head); if (page_has_buffers(page)) return generic_write_end(file, mapping, pos, len, copied, page, fsdata); SetPageUptodate(page); set_page_dirty(page); if (pos+copied > inode->i_size) { i_size_write(inode, pos+copied); mark_inode_dirty(inode); } unlock_page(page); put_page(page); while (head) { bh = head; head = head->b_this_page; free_buffer_head(bh); } return copied; } EXPORT_SYMBOL(nobh_write_end); /* * nobh_writepage() - based on block_full_write_page() except * that it tries to operate without attaching bufferheads to * the page. */ int nobh_writepage(struct page *page, get_block_t *get_block, struct writeback_control *wbc) { struct inode * const inode = page->mapping->host; loff_t i_size = i_size_read(inode); const pgoff_t end_index = i_size >> PAGE_SHIFT; unsigned offset; int ret; /* Is the page fully inside i_size? */ if (page->index < end_index) goto out; /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { unlock_page(page); return 0; /* don't care */ } /* * The page straddles i_size. It must be zeroed out on each and every * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ zero_user_segment(page, offset, PAGE_SIZE); out: ret = mpage_writepage(page, get_block, wbc); if (ret == -EAGAIN) ret = __block_write_full_page(inode, page, get_block, wbc, end_buffer_async_write); return ret; } EXPORT_SYMBOL(nobh_writepage); int nobh_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize; sector_t iblock; unsigned length, pos; struct inode *inode = mapping->host; struct page *page; struct buffer_head map_bh; int err; blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ if (!length) return 0; length = blocksize - length; iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits); page = grab_cache_page(mapping, index); err = -ENOMEM; if (!page) goto out; if (page_has_buffers(page)) { has_buffers: unlock_page(page); put_page(page); return block_truncate_page(mapping, from, get_block); } /* Find the buffer that contains "offset" */ pos = blocksize; while (offset >= pos) { iblock++; pos += blocksize; } map_bh.b_size = blocksize; map_bh.b_state = 0; err = get_block(inode, iblock, &map_bh, 0); if (err) goto unlock; /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(&map_bh)) goto unlock; /* Ok, it's mapped. Make sure it's up-to-date */ if (!PageUptodate(page)) { err = mapping->a_ops->readpage(NULL, page); if (err) { put_page(page); goto out; } lock_page(page); if (!PageUptodate(page)) { err = -EIO; goto unlock; } if (page_has_buffers(page)) goto has_buffers; } zero_user(page, offset, length); set_page_dirty(page); err = 0; unlock: unlock_page(page); put_page(page); out: return err; } EXPORT_SYMBOL(nobh_truncate_page); int block_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize; sector_t iblock; unsigned length, pos; struct inode *inode = mapping->host; struct page *page; struct buffer_head *bh; int err; blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ if (!length) return 0; length = blocksize - length; iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits); page = grab_cache_page(mapping, index); err = -ENOMEM; if (!page) goto out; if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); /* Find the buffer that contains "offset" */ bh = page_buffers(page); pos = blocksize; while (offset >= pos) { bh = bh->b_this_page; iblock++; pos += blocksize; } err = 0; if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) goto unlock; /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(bh)) goto unlock; } /* Ok, it's mapped. Make sure it's up-to-date */ if (PageUptodate(page)) set_buffer_uptodate(bh); if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) { err = -EIO; ll_rw_block(REQ_OP_READ, 0, 1, &bh); wait_on_buffer(bh); /* Uhhuh. Read error. Complain and punt. */ if (!buffer_uptodate(bh)) goto unlock; } zero_user(page, offset, length); mark_buffer_dirty(bh); err = 0; unlock: unlock_page(page); put_page(page); out: return err; } EXPORT_SYMBOL(block_truncate_page); /* * The generic ->writepage function for buffer-backed address_spaces */ int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc) { struct inode * const inode = page->mapping->host; loff_t i_size = i_size_read(inode); const pgoff_t end_index = i_size >> PAGE_SHIFT; unsigned offset; /* Is the page fully inside i_size? */ if (page->index < end_index) return __block_write_full_page(inode, page, get_block, wbc, end_buffer_async_write); /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { unlock_page(page); return 0; /* don't care */ } /* * The page straddles i_size. It must be zeroed out on each and every * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ zero_user_segment(page, offset, PAGE_SIZE); return __block_write_full_page(inode, page, get_block, wbc, end_buffer_async_write); } EXPORT_SYMBOL(block_write_full_page); sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block_t *get_block) { struct inode *inode = mapping->host; struct buffer_head tmp = { .b_size = i_blocksize(inode), }; get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } EXPORT_SYMBOL_NS(generic_block_bmap, ANDROID_GKI_VFS_EXPORT_ONLY); static void end_bio_bh_io_sync(struct bio *bio) { struct buffer_head *bh = bio->bi_private; if (unlikely(bio_flagged(bio, BIO_QUIET))) set_bit(BH_Quiet, &bh->b_state); bh->b_end_io(bh, !bio->bi_status); bio_put(bio); } static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, enum rw_hint write_hint, struct writeback_control *wbc) { struct bio *bio; BUG_ON(!buffer_locked(bh)); BUG_ON(!buffer_mapped(bh)); BUG_ON(!bh->b_end_io); BUG_ON(buffer_delay(bh)); BUG_ON(buffer_unwritten(bh)); /* * Only clear out a write error when rewriting */ if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE)) clear_buffer_write_io_error(bh); bio = bio_alloc(GFP_NOIO, 1); fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_write_hint = write_hint; bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); BUG_ON(bio->bi_iter.bi_size != bh->b_size); bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; if (buffer_meta(bh)) op_flags |= REQ_META; if (buffer_prio(bh)) op_flags |= REQ_PRIO; bio_set_op_attrs(bio, op, op_flags); /* Take care of bh's that straddle the end of the device */ guard_bio_eod(bio); if (wbc) { wbc_init_bio(wbc, bio); wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size); } submit_bio(bio); return 0; } int submit_bh(int op, int op_flags, struct buffer_head *bh) { return submit_bh_wbc(op, op_flags, bh, 0, NULL); } EXPORT_SYMBOL(submit_bh); /** * ll_rw_block: low-level access to block devices (DEPRECATED) * @op: whether to %READ or %WRITE * @op_flags: req_flag_bits * @nr: number of &struct buffer_heads in the array * @bhs: array of pointers to &struct buffer_head * * ll_rw_block() takes an array of pointers to &struct buffer_heads, and * requests an I/O operation on them, either a %REQ_OP_READ or a %REQ_OP_WRITE. * @op_flags contains flags modifying the detailed I/O behavior, most notably * %REQ_RAHEAD. * * This function drops any buffer that it cannot get a lock on (with the * BH_Lock state bit), any buffer that appears to be clean when doing a write * request, and any buffer that appears to be up-to-date when doing read * request. Further it marks as clean buffers that are processed for * writing (the buffer cache won't assume that they are actually clean * until the buffer gets unlocked). * * ll_rw_block sets b_end_io to simple completion handler that marks * the buffer up-to-date (if appropriate), unlocks the buffer and wakes * any waiters. * * All of the buffers must be for the same device, and must also be a * multiple of the current approved size for the device. */ void ll_rw_block(int op, int op_flags, int nr, struct buffer_head *bhs[]) { int i; for (i = 0; i < nr; i++) { struct buffer_head *bh = bhs[i]; if (!trylock_buffer(bh)) continue; if (op == WRITE) { if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(op, op_flags, bh); continue; } } else { if (!buffer_uptodate(bh)) { bh->b_end_io = end_buffer_read_sync; get_bh(bh); submit_bh(op, op_flags, bh); continue; } } unlock_buffer(bh); } } EXPORT_SYMBOL_NS(ll_rw_block, ANDROID_GKI_VFS_EXPORT_ONLY); void write_dirty_buffer(struct buffer_head *bh, int op_flags) { lock_buffer(bh); if (!test_clear_buffer_dirty(bh)) { unlock_buffer(bh); return; } bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(REQ_OP_WRITE, op_flags, bh); } EXPORT_SYMBOL(write_dirty_buffer); /* * For a data-integrity writeout, we need to wait upon any in-progress I/O * and then start new I/O and then wait upon it. The caller must have a ref on * the buffer_head. */ int __sync_dirty_buffer(struct buffer_head *bh, int op_flags) { int ret = 0; WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { /* * The bh should be mapped, but it might not be if the * device was hot-removed. Not much we can do but fail the I/O. */ if (!buffer_mapped(bh)) { unlock_buffer(bh); return -EIO; } get_bh(bh); bh->b_end_io = end_buffer_write_sync; ret = submit_bh(REQ_OP_WRITE, op_flags, bh); wait_on_buffer(bh); if (!ret && !buffer_uptodate(bh)) ret = -EIO; } else { unlock_buffer(bh); } return ret; } EXPORT_SYMBOL_NS(__sync_dirty_buffer, ANDROID_GKI_VFS_EXPORT_ONLY); int sync_dirty_buffer(struct buffer_head *bh) { return __sync_dirty_buffer(bh, REQ_SYNC); } EXPORT_SYMBOL_NS(sync_dirty_buffer, ANDROID_GKI_VFS_EXPORT_ONLY); /* * try_to_free_buffers() checks if all the buffers on this particular page * are unused, and releases them if so. * * Exclusion against try_to_free_buffers may be obtained by either * locking the page or by holding its mapping's private_lock. * * If the page is dirty but all the buffers are clean then we need to * be sure to mark the page clean as well. This is because the page * may be against a block device, and a later reattachment of buffers * to a dirty page will set *all* buffers dirty. Which would corrupt * filesystem data on the same device. * * The same applies to regular filesystem pages: if all the buffers are * clean then we set the page clean and proceed. To do that, we require * total exclusion from __set_page_dirty_buffers(). That is obtained with * private_lock. * * try_to_free_buffers() is non-blocking. */ static inline int buffer_busy(struct buffer_head *bh) { return atomic_read(&bh->b_count) | (bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock))); } static int drop_buffers(struct page *page, struct buffer_head **buffers_to_free) { struct buffer_head *head = page_buffers(page); struct buffer_head *bh; bh = head; do { if (buffer_busy(bh)) goto failed; bh = bh->b_this_page; } while (bh != head); do { struct buffer_head *next = bh->b_this_page; if (bh->b_assoc_map) __remove_assoc_queue(bh); bh = next; } while (bh != head); *buffers_to_free = head; detach_page_private(page); return 1; failed: return 0; } int try_to_free_buffers(struct page *page) { struct address_space * const mapping = page->mapping; struct buffer_head *buffers_to_free = NULL; int ret = 0; BUG_ON(!PageLocked(page)); if (PageWriteback(page)) return 0; if (mapping == NULL) { /* can this still happen? */ ret = drop_buffers(page, &buffers_to_free); goto out; } spin_lock(&mapping->private_lock); ret = drop_buffers(page, &buffers_to_free); /* * If the filesystem writes its buffers by hand (eg ext3) * then we can have clean buffers against a dirty page. We * clean the page here; otherwise the VM will never notice * that the filesystem did any IO at all. * * Also, during truncate, discard_buffer will have marked all * the page's buffers clean. We discover that here and clean * the page also. * * private_lock must be held over this entire operation in order * to synchronise against __set_page_dirty_buffers and prevent the * dirty bit from being lost. */ if (ret) cancel_dirty_page(page); spin_unlock(&mapping->private_lock); out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; do { struct buffer_head *next = bh->b_this_page; free_buffer_head(bh); bh = next; } while (bh != buffers_to_free); } return ret; } EXPORT_SYMBOL(try_to_free_buffers); /* * Buffer-head allocation */ static struct kmem_cache *bh_cachep __read_mostly; /* * Once the number of bh's in the machine exceeds this level, we start * stripping them in writeback. */ static unsigned long max_buffer_heads; int buffer_heads_over_limit; struct bh_accounting { int nr; /* Number of live bh's */ int ratelimit; /* Limit cacheline bouncing */ }; static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0}; static void recalc_bh_state(void) { int i; int tot = 0; if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096) return; __this_cpu_write(bh_accounting.ratelimit, 0); for_each_online_cpu(i) tot += per_cpu(bh_accounting, i).nr; buffer_heads_over_limit = (tot > max_buffer_heads); } struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); spin_lock_init(&ret->b_uptodate_lock); preempt_disable(); __this_cpu_inc(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } return ret; } EXPORT_SYMBOL(alloc_buffer_head); void free_buffer_head(struct buffer_head *bh) { BUG_ON(!list_empty(&bh->b_assoc_buffers)); kmem_cache_free(bh_cachep, bh); preempt_disable(); __this_cpu_dec(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } EXPORT_SYMBOL(free_buffer_head); static int buffer_exit_cpu_dead(unsigned int cpu) { int i; struct bh_lru *b = &per_cpu(bh_lrus, cpu); for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr); per_cpu(bh_accounting, cpu).nr = 0; return 0; } /** * bh_uptodate_or_lock - Test whether the buffer is uptodate * @bh: struct buffer_head * * Return true if the buffer is up-to-date and false, * with the buffer locked, if not. */ int bh_uptodate_or_lock(struct buffer_head *bh) { if (!buffer_uptodate(bh)) { lock_buffer(bh); if (!buffer_uptodate(bh)) return 0; unlock_buffer(bh); } return 1; } EXPORT_SYMBOL(bh_uptodate_or_lock); /** * bh_submit_read - Submit a locked buffer for reading * @bh: struct buffer_head * * Returns zero on success and -EIO on error. */ int bh_submit_read(struct buffer_head *bh) { BUG_ON(!buffer_locked(bh)); if (buffer_uptodate(bh)) { unlock_buffer(bh); return 0; } get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, 0, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return 0; return -EIO; } EXPORT_SYMBOL(bh_submit_read); void __init buffer_init(void) { unsigned long nrpages; int ret; bh_cachep = kmem_cache_create("buffer_head", sizeof(struct buffer_head), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_MEM_SPREAD), NULL); /* * Limit the bh occupancy to 10% of ZONE_NORMAL */ nrpages = (nr_free_buffer_pages() * 10) / 100; max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head)); ret = cpuhp_setup_state_nocalls(CPUHP_FS_BUFF_DEAD, "fs/buffer:dead", NULL, buffer_exit_cpu_dead); WARN_ON(ret < 0); } |
| 8861 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | // SPDX-License-Identifier: GPL-2.0 #include <linux/err.h> #include <linux/bug.h> #include <linux/atomic.h> #include <linux/errseq.h> #include <linux/log2.h> /* * An errseq_t is a way of recording errors in one place, and allowing any * number of "subscribers" to tell whether it has changed since a previous * point where it was sampled. * * It's implemented as an unsigned 32-bit value. The low order bits are * designated to hold an error code (between 0 and -MAX_ERRNO). The upper bits * are used as a counter. This is done with atomics instead of locking so that * these functions can be called from any context. * * The general idea is for consumers to sample an errseq_t value. That value * can later be used to tell whether any new errors have occurred since that * sampling was done. * * Note that there is a risk of collisions if new errors are being recorded * frequently, since we have so few bits to use as a counter. * * To mitigate this, one bit is used as a flag to tell whether the value has * been sampled since a new value was recorded. That allows us to avoid bumping * the counter if no one has sampled it since the last time an error was * recorded. * * A new errseq_t should always be zeroed out. A errseq_t value of all zeroes * is the special (but common) case where there has never been an error. An all * zero value thus serves as the "epoch" if one wishes to know whether there * has ever been an error set since it was first initialized. */ /* The low bits are designated for error code (max of MAX_ERRNO) */ #define ERRSEQ_SHIFT ilog2(MAX_ERRNO + 1) /* This bit is used as a flag to indicate whether the value has been seen */ #define ERRSEQ_SEEN (1 << ERRSEQ_SHIFT) /* The lowest bit of the counter */ #define ERRSEQ_CTR_INC (1 << (ERRSEQ_SHIFT + 1)) /** * errseq_set - set a errseq_t for later reporting * @eseq: errseq_t field that should be set * @err: error to set (must be between -1 and -MAX_ERRNO) * * This function sets the error in @eseq, and increments the sequence counter * if the last sequence was sampled at some point in the past. * * Any error set will always overwrite an existing error. * * Return: The previous value, primarily for debugging purposes. The * return value should not be used as a previously sampled value in later * calls as it will not have the SEEN flag set. */ errseq_t errseq_set(errseq_t *eseq, int err) { errseq_t cur, old; /* MAX_ERRNO must be able to serve as a mask */ BUILD_BUG_ON_NOT_POWER_OF_2(MAX_ERRNO + 1); /* * Ensure the error code actually fits where we want it to go. If it * doesn't then just throw a warning and don't record anything. We * also don't accept zero here as that would effectively clear a * previous error. */ old = READ_ONCE(*eseq); if (WARN(unlikely(err == 0 || (unsigned int)-err > MAX_ERRNO), "err = %d\n", err)) return old; for (;;) { errseq_t new; /* Clear out error bits and set new error */ new = (old & ~(MAX_ERRNO|ERRSEQ_SEEN)) | -err; /* Only increment if someone has looked at it */ if (old & ERRSEQ_SEEN) new += ERRSEQ_CTR_INC; /* If there would be no change, then call it done */ if (new == old) { cur = new; break; } /* Try to swap the new value into place */ cur = cmpxchg(eseq, old, new); /* * Call it success if we did the swap or someone else beat us * to it for the same value. */ if (likely(cur == old || cur == new)) break; /* Raced with an update, try again */ old = cur; } return cur; } EXPORT_SYMBOL(errseq_set); /** * errseq_sample() - Grab current errseq_t value. * @eseq: Pointer to errseq_t to be sampled. * * This function allows callers to initialise their errseq_t variable. * If the error has been "seen", new callers will not see an old error. * If there is an unseen error in @eseq, the caller of this function will * see it the next time it checks for an error. * * Context: Any context. * Return: The current errseq value. */ errseq_t errseq_sample(errseq_t *eseq) { errseq_t old = READ_ONCE(*eseq); /* If nobody has seen this error yet, then we can be the first. */ if (!(old & ERRSEQ_SEEN)) old = 0; return old; } EXPORT_SYMBOL(errseq_sample); /** * errseq_check() - Has an error occurred since a particular sample point? * @eseq: Pointer to errseq_t value to be checked. * @since: Previously-sampled errseq_t from which to check. * * Grab the value that eseq points to, and see if it has changed @since * the given value was sampled. The @since value is not advanced, so there * is no need to mark the value as seen. * * Return: The latest error set in the errseq_t or 0 if it hasn't changed. */ int errseq_check(errseq_t *eseq, errseq_t since) { errseq_t cur = READ_ONCE(*eseq); if (likely(cur == since)) return 0; return -(cur & MAX_ERRNO); } EXPORT_SYMBOL(errseq_check); /** * errseq_check_and_advance() - Check an errseq_t and advance to current value. * @eseq: Pointer to value being checked and reported. * @since: Pointer to previously-sampled errseq_t to check against and advance. * * Grab the eseq value, and see whether it matches the value that @since * points to. If it does, then just return 0. * * If it doesn't, then the value has changed. Set the "seen" flag, and try to * swap it into place as the new eseq value. Then, set that value as the new * "since" value, and return whatever the error portion is set to. * * Note that no locking is provided here for concurrent updates to the "since" * value. The caller must provide that if necessary. Because of this, callers * may want to do a lockless errseq_check before taking the lock and calling * this. * * Return: Negative errno if one has been stored, or 0 if no new error has * occurred. */ int errseq_check_and_advance(errseq_t *eseq, errseq_t *since) { int err = 0; errseq_t old, new; /* * Most callers will want to use the inline wrapper to check this, * so that the common case of no error is handled without needing * to take the lock that protects the "since" value. */ old = READ_ONCE(*eseq); if (old != *since) { /* * Set the flag and try to swap it into place if it has * changed. * * We don't care about the outcome of the swap here. If the * swap doesn't occur, then it has either been updated by a * writer who is altering the value in some way (updating * counter or resetting the error), or another reader who is * just setting the "seen" flag. Either outcome is OK, and we * can advance "since" and return an error based on what we * have. */ new = old | ERRSEQ_SEEN; if (new != old) cmpxchg(eseq, old, new); *since = new; err = -(new & MAX_ERRNO); } return err; } EXPORT_SYMBOL(errseq_check_and_advance); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAPOPS_H #define _LINUX_SWAPOPS_H #include <linux/radix-tree.h> #include <linux/bug.h> #include <linux/mm_types.h> #ifdef CONFIG_MMU /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in * the low-order bits. * * We arrange the `type' and `offset' fields so that `type' is at the seven * high-order bits of the swp_entry_t and `offset' is right-aligned in the * remaining bits. Although `type' itself needs only five bits, we allow for * shmem/tmpfs to shift it all up a further two bits: see swp_to_radix_entry(). * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ #define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) #define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) /* Clear all flags but only keep swp_entry_t related information */ static inline pte_t pte_swp_clear_flags(pte_t pte) { if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); if (pte_swp_uffd_wp(pte)) pte = pte_swp_clear_uffd_wp(pte); return pte; } /* * Store a type+offset into a swp_entry_t in an arch-independent format */ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) { swp_entry_t ret; ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK); return ret; } /* * Extract the `type' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline unsigned swp_type(swp_entry_t entry) { return (entry.val >> SWP_TYPE_SHIFT); } /* * Extract the `offset' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline pgoff_t swp_offset(swp_entry_t entry) { return entry.val & SWP_OFFSET_MASK; } /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { return !pte_none(pte) && !pte_present(pte); } /* * Convert the arch-dependent pte representation of a swp_entry_t into an * arch-independent swp_entry_t. */ static inline swp_entry_t pte_to_swp_entry(pte_t pte) { swp_entry_t arch_entry; pte = pte_swp_clear_flags(pte); arch_entry = __pte_to_swp_entry(pte); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } /* * Convert the arch-independent representation of a swp_entry_t into the * arch-dependent pte representation. */ static inline pte_t swp_entry_to_pte(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pte(arch_entry); } static inline swp_entry_t radix_to_swp_entry(void *arg) { swp_entry_t entry; entry.val = xa_to_value(arg); return entry; } static inline void *swp_to_radix_entry(swp_entry_t entry) { return xa_mk_value(entry.val); } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_READ, offset); } static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_WRITE, offset); } static inline bool is_device_private_entry(swp_entry_t entry) { int type = swp_type(entry); return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; } static inline bool is_writable_device_private_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_EXCLUSIVE_READ, offset); } static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_EXCLUSIVE_WRITE, offset); } static inline bool is_device_exclusive_entry(swp_entry_t entry) { return swp_type(entry) == SWP_DEVICE_EXCLUSIVE_READ || swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE; } static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE); } #else /* CONFIG_DEVICE_PRIVATE */ static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline bool is_device_private_entry(swp_entry_t entry) { return false; } static inline bool is_writable_device_private_entry(swp_entry_t entry) { return false; } static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline bool is_device_exclusive_entry(swp_entry_t entry) { return false; } static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) { return false; } #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || swp_type(entry) == SWP_MIGRATION_WRITE); } static inline int is_writable_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ, offset); } static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_WRITE, offset); } extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); extern void migration_entry_wait_huge(struct vm_area_struct *vma, struct mm_struct *mm, pte_t *pte); #else static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline int is_migration_entry(swp_entry_t swp) { return 0; } static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, struct mm_struct *mm, pte_t *pte) { } static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } #endif static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) { struct page *p = pfn_to_page(swp_offset(entry)); /* * Any use of migration entries may only occur while the * corresponding page is locked */ BUG_ON(is_migration_entry(entry) && !PageLocked(p)); return p; } /* * A pfn swap entry is a special type of swap entry that always has a pfn stored * in the swap offset. They are used to represent unaddressable device memory * and to restrict access to a page undergoing migration. */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { return is_migration_entry(entry) || is_device_private_entry(entry) || is_device_exclusive_entry(entry); } struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page); extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new); extern void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd); static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { swp_entry_t arch_entry; if (pmd_swp_soft_dirty(pmd)) pmd = pmd_swp_clear_soft_dirty(pmd); if (pmd_swp_uffd_wp(pmd)) pmd = pmd_swp_clear_uffd_wp(pmd); arch_entry = __pmd_to_swp_entry(pmd); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pmd(arch_entry); } static inline int is_pmd_migration_entry(pmd_t pmd) { return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } #else static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { BUILD_BUG(); } static inline void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) { BUILD_BUG(); } static inline void pmd_migration_entry_wait(struct mm_struct *m, pmd_t *p) { } static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { return swp_entry(0, 0); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { return __pmd(0); } static inline int is_pmd_migration_entry(pmd_t pmd) { return 0; } #endif #ifdef CONFIG_MEMORY_FAILURE extern atomic_long_t num_poisoned_pages __read_mostly; /* * Support for hardware poisoned pages */ static inline swp_entry_t make_hwpoison_entry(struct page *page) { BUG_ON(!PageLocked(page)); return swp_entry(SWP_HWPOISON, page_to_pfn(page)); } static inline int is_hwpoison_entry(swp_entry_t entry) { return swp_type(entry) == SWP_HWPOISON; } static inline unsigned long hwpoison_entry_to_pfn(swp_entry_t entry) { return swp_offset(entry); } static inline void num_poisoned_pages_inc(void) { atomic_long_inc(&num_poisoned_pages); } static inline void num_poisoned_pages_dec(void) { atomic_long_dec(&num_poisoned_pages); } #else static inline swp_entry_t make_hwpoison_entry(struct page *page) { return swp_entry(0, 0); } static inline int is_hwpoison_entry(swp_entry_t swp) { return 0; } static inline void num_poisoned_pages_inc(void) { } #endif #if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || \ defined(CONFIG_DEVICE_PRIVATE) static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; } #else static inline int non_swap_entry(swp_entry_t entry) { return 0; } #endif #endif /* CONFIG_MMU */ #endif /* _LINUX_SWAPOPS_H */ |
| 750 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* Connection tracking via netlink socket. Allows for user space * protocol helpers and general trouble making from userspace. * * (C) 2001 by Jay Schulist <jschlst@samba.org> * (C) 2002-2006 by Harald Welte <laforge@gnumonks.org> * (C) 2003 by Patrick Mchardy <kaber@trash.net> * (C) 2005-2012 by Pablo Neira Ayuso <pablo@netfilter.org> * * Initial connection tracking via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) * * Further development of this code funded by Astaro AG (http://www.astaro.com) * * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. */ #include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/rculist.h> #include <linux/rculist_nulls.h> #include <linux/types.h> #include <linux/timer.h> #include <linux/security.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/netlink.h> #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/siphash.h> #include <linux/netfilter.h> #include <net/netlink.h> #include <net/sock.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> #include <net/netfilter/nf_conntrack_labels.h> #include <net/netfilter/nf_conntrack_synproxy.h> #if IS_ENABLED(CONFIG_NF_NAT) #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_helper.h> #endif #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> #include "nf_internals.h" MODULE_LICENSE("GPL"); static int ctnetlink_dump_tuples_proto(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l4proto *l4proto) { int ret = 0; struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, CTA_TUPLE_PROTO); if (!nest_parms) goto nla_put_failure; if (nla_put_u8(skb, CTA_PROTO_NUM, tuple->dst.protonum)) goto nla_put_failure; if (likely(l4proto->tuple_to_nlattr)) ret = l4proto->tuple_to_nlattr(skb, tuple); nla_nest_end(skb, nest_parms); return ret; nla_put_failure: return -1; } static int ipv4_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { if (nla_put_in_addr(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) || nla_put_in_addr(skb, CTA_IP_V4_DST, tuple->dst.u3.ip)) return -EMSGSIZE; return 0; } static int ipv6_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { if (nla_put_in6_addr(skb, CTA_IP_V6_SRC, &tuple->src.u3.in6) || nla_put_in6_addr(skb, CTA_IP_V6_DST, &tuple->dst.u3.in6)) return -EMSGSIZE; return 0; } static int ctnetlink_dump_tuples_ip(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { int ret = 0; struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, CTA_TUPLE_IP); if (!nest_parms) goto nla_put_failure; switch (tuple->src.l3num) { case NFPROTO_IPV4: ret = ipv4_tuple_to_nlattr(skb, tuple); break; case NFPROTO_IPV6: ret = ipv6_tuple_to_nlattr(skb, tuple); break; } nla_nest_end(skb, nest_parms); return ret; nla_put_failure: return -1; } static int ctnetlink_dump_tuples(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { const struct nf_conntrack_l4proto *l4proto; int ret; rcu_read_lock(); ret = ctnetlink_dump_tuples_ip(skb, tuple); if (ret >= 0) { l4proto = nf_ct_l4proto_find(tuple->dst.protonum); ret = ctnetlink_dump_tuples_proto(skb, tuple, l4proto); } rcu_read_unlock(); return ret; } static int ctnetlink_dump_zone_id(struct sk_buff *skb, int attrtype, const struct nf_conntrack_zone *zone, int dir) { if (zone->id == NF_CT_DEFAULT_ZONE_ID || zone->dir != dir) return 0; if (nla_put_be16(skb, attrtype, htons(zone->id))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_status(struct sk_buff *skb, const struct nf_conn *ct) { if (nla_put_be32(skb, CTA_STATUS, htonl(ct->status))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_timeout(struct sk_buff *skb, const struct nf_conn *ct, bool skip_zero) { long timeout = nf_ct_expires(ct) / HZ; if (skip_zero && timeout == 0) return 0; if (nla_put_be32(skb, CTA_TIMEOUT, htonl(timeout))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct, bool destroy) { const struct nf_conntrack_l4proto *l4proto; struct nlattr *nest_proto; int ret; l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (!l4proto->to_nlattr) return 0; nest_proto = nla_nest_start(skb, CTA_PROTOINFO); if (!nest_proto) goto nla_put_failure; ret = l4proto->to_nlattr(skb, nest_proto, ct, destroy); nla_nest_end(skb, nest_proto); return ret; nla_put_failure: return -1; } static int ctnetlink_dump_helpinfo(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_helper; const struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_helper *helper; if (!help) return 0; rcu_read_lock(); helper = rcu_dereference(help->helper); if (!helper) goto out; nest_helper = nla_nest_start(skb, CTA_HELP); if (!nest_helper) goto nla_put_failure; if (nla_put_string(skb, CTA_HELP_NAME, helper->name)) goto nla_put_failure; if (helper->to_nlattr) helper->to_nlattr(skb, ct); nla_nest_end(skb, nest_helper); out: rcu_read_unlock(); return 0; nla_put_failure: rcu_read_unlock(); return -1; } static int dump_counters(struct sk_buff *skb, struct nf_conn_acct *acct, enum ip_conntrack_dir dir, int type) { enum ctattr_type attr = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG; struct nf_conn_counter *counter = acct->counter; struct nlattr *nest_count; u64 pkts, bytes; if (type == IPCTNL_MSG_CT_GET_CTRZERO) { pkts = atomic64_xchg(&counter[dir].packets, 0); bytes = atomic64_xchg(&counter[dir].bytes, 0); } else { pkts = atomic64_read(&counter[dir].packets); bytes = atomic64_read(&counter[dir].bytes); } nest_count = nla_nest_start(skb, attr); if (!nest_count) goto nla_put_failure; if (nla_put_be64(skb, CTA_COUNTERS_PACKETS, cpu_to_be64(pkts), CTA_COUNTERS_PAD) || nla_put_be64(skb, CTA_COUNTERS_BYTES, cpu_to_be64(bytes), CTA_COUNTERS_PAD)) goto nla_put_failure; nla_nest_end(skb, nest_count); return 0; nla_put_failure: return -1; } static int ctnetlink_dump_acct(struct sk_buff *skb, const struct nf_conn *ct, int type) { struct nf_conn_acct *acct = nf_conn_acct_find(ct); if (!acct) return 0; if (dump_counters(skb, acct, IP_CT_DIR_ORIGINAL, type) < 0) return -1; if (dump_counters(skb, acct, IP_CT_DIR_REPLY, type) < 0) return -1; return 0; } static int ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_count; const struct nf_conn_tstamp *tstamp; tstamp = nf_conn_tstamp_find(ct); if (!tstamp) return 0; nest_count = nla_nest_start(skb, CTA_TIMESTAMP); if (!nest_count) goto nla_put_failure; if (nla_put_be64(skb, CTA_TIMESTAMP_START, cpu_to_be64(tstamp->start), CTA_TIMESTAMP_PAD) || (tstamp->stop != 0 && nla_put_be64(skb, CTA_TIMESTAMP_STOP, cpu_to_be64(tstamp->stop), CTA_TIMESTAMP_PAD))) goto nla_put_failure; nla_nest_end(skb, nest_count); return 0; nla_put_failure: return -1; } #ifdef CONFIG_NF_CONNTRACK_MARK static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct, bool dump) { u32 mark = READ_ONCE(ct->mark); if (!mark && !dump) return 0; if (nla_put_be32(skb, CTA_MARK, htonl(mark))) goto nla_put_failure; return 0; nla_put_failure: return -1; } #else #define ctnetlink_dump_mark(a, b, c) (0) #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK static int ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_secctx; int len, ret; char *secctx; ret = security_secid_to_secctx(ct->secmark, &secctx, &len); if (ret) return 0; ret = -1; nest_secctx = nla_nest_start(skb, CTA_SECCTX); if (!nest_secctx) goto nla_put_failure; if (nla_put_string(skb, CTA_SECCTX_NAME, secctx)) goto nla_put_failure; nla_nest_end(skb, nest_secctx); ret = 0; nla_put_failure: security_release_secctx(secctx, len); return ret; } #else #define ctnetlink_dump_secctx(a, b) (0) #endif #ifdef CONFIG_NF_CONNTRACK_EVENTS static inline int ctnetlink_label_size(const struct nf_conn *ct) { struct nf_conn_labels *labels = nf_ct_labels_find(ct); if (!labels) return 0; return nla_total_size(sizeof(labels->bits)); } #endif static int ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct) { struct nf_conn_labels *labels = nf_ct_labels_find(ct); unsigned int i; if (!labels) return 0; i = 0; do { if (labels->bits[i] != 0) return nla_put(skb, CTA_LABELS, sizeof(labels->bits), labels->bits); i++; } while (i < ARRAY_SIZE(labels->bits)); return 0; } #define master_tuple(ct) &(ct->master->tuplehash[IP_CT_DIR_ORIGINAL].tuple) static int ctnetlink_dump_master(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_parms; if (!(ct->status & IPS_EXPECTED)) return 0; nest_parms = nla_nest_start(skb, CTA_TUPLE_MASTER); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, master_tuple(ct)) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int dump_ct_seq_adj(struct sk_buff *skb, const struct nf_ct_seqadj *seq, int type) { struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, type); if (!nest_parms) goto nla_put_failure; if (nla_put_be32(skb, CTA_SEQADJ_CORRECTION_POS, htonl(seq->correction_pos)) || nla_put_be32(skb, CTA_SEQADJ_OFFSET_BEFORE, htonl(seq->offset_before)) || nla_put_be32(skb, CTA_SEQADJ_OFFSET_AFTER, htonl(seq->offset_after))) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int ctnetlink_dump_ct_seq_adj(struct sk_buff *skb, struct nf_conn *ct) { struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); struct nf_ct_seqadj *seq; if (!(ct->status & IPS_SEQ_ADJUST) || !seqadj) return 0; spin_lock_bh(&ct->lock); seq = &seqadj->seq[IP_CT_DIR_ORIGINAL]; if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_ORIG) == -1) goto err; seq = &seqadj->seq[IP_CT_DIR_REPLY]; if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_REPLY) == -1) goto err; spin_unlock_bh(&ct->lock); return 0; err: spin_unlock_bh(&ct->lock); return -1; } static int ctnetlink_dump_ct_synproxy(struct sk_buff *skb, struct nf_conn *ct) { struct nf_conn_synproxy *synproxy = nfct_synproxy(ct); struct nlattr *nest_parms; if (!synproxy) return 0; nest_parms = nla_nest_start(skb, CTA_SYNPROXY); if (!nest_parms) goto nla_put_failure; if (nla_put_be32(skb, CTA_SYNPROXY_ISN, htonl(synproxy->isn)) || nla_put_be32(skb, CTA_SYNPROXY_ITS, htonl(synproxy->its)) || nla_put_be32(skb, CTA_SYNPROXY_TSOFF, htonl(synproxy->tsoff))) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct) { __be32 id = (__force __be32)nf_ct_get_id(ct); if (nla_put_be32(skb, CTA_ID, id)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_use(struct sk_buff *skb, const struct nf_conn *ct) { if (nla_put_be32(skb, CTA_USE, htonl(refcount_read(&ct->ct_general.use)))) goto nla_put_failure; return 0; nla_put_failure: return -1; } /* all these functions access ct->ext. Caller must either hold a reference * on ct or prevent its deletion by holding either the bucket spinlock or * pcpu dying list lock. */ static int ctnetlink_dump_extinfo(struct sk_buff *skb, struct nf_conn *ct, u32 type) { if (ctnetlink_dump_acct(skb, ct, type) < 0 || ctnetlink_dump_timestamp(skb, ct) < 0 || ctnetlink_dump_helpinfo(skb, ct) < 0 || ctnetlink_dump_labels(skb, ct) < 0 || ctnetlink_dump_ct_seq_adj(skb, ct) < 0 || ctnetlink_dump_ct_synproxy(skb, ct) < 0) return -1; return 0; } static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) { if (ctnetlink_dump_status(skb, ct) < 0 || ctnetlink_dump_mark(skb, ct, true) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || ctnetlink_dump_master(skb, ct) < 0) return -1; if (!test_bit(IPS_OFFLOAD_BIT, &ct->status) && (ctnetlink_dump_timeout(skb, ct, false) < 0 || ctnetlink_dump_protoinfo(skb, ct, false) < 0)) return -1; return 0; } static int ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct nf_conn *ct, bool extinfo, unsigned int flags) { const struct nf_conntrack_zone *zone; struct nlmsghdr *nlh; struct nlattr *nest_parms; unsigned int event; if (portid) flags |= NLM_F_MULTI; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_NEW); nlh = nfnl_msg_put(skb, portid, seq, event, flags, nf_ct_l3num(ct), NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_ORIG) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_REPL) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_info(skb, ct) < 0) goto nla_put_failure; if (extinfo && ctnetlink_dump_extinfo(skb, ct, type) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: nlmsg_cancel(skb, nlh); return -1; } static const struct nla_policy cta_ip_nla_policy[CTA_IP_MAX + 1] = { [CTA_IP_V4_SRC] = { .type = NLA_U32 }, [CTA_IP_V4_DST] = { .type = NLA_U32 }, [CTA_IP_V6_SRC] = { .len = sizeof(__be32) * 4 }, [CTA_IP_V6_DST] = { .len = sizeof(__be32) * 4 }, }; #if defined(CONFIG_NETFILTER_NETLINK_GLUE_CT) || defined(CONFIG_NF_CONNTRACK_EVENTS) static size_t ctnetlink_proto_size(const struct nf_conn *ct) { const struct nf_conntrack_l4proto *l4proto; size_t len, len4 = 0; len = nla_policy_len(cta_ip_nla_policy, CTA_IP_MAX + 1); len *= 3u; /* ORIG, REPLY, MASTER */ l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); len += l4proto->nlattr_size; if (l4proto->nlattr_tuple_size) { len4 = l4proto->nlattr_tuple_size(); len4 *= 3u; /* ORIG, REPLY, MASTER */ } return len + len4; } #endif static inline size_t ctnetlink_acct_size(const struct nf_conn *ct) { if (!nf_ct_ext_exist(ct, NF_CT_EXT_ACCT)) return 0; return 2 * nla_total_size(0) /* CTA_COUNTERS_ORIG|REPL */ + 2 * nla_total_size_64bit(sizeof(uint64_t)) /* CTA_COUNTERS_PACKETS */ + 2 * nla_total_size_64bit(sizeof(uint64_t)) /* CTA_COUNTERS_BYTES */ ; } static inline int ctnetlink_secctx_size(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_SECMARK int len, ret; ret = security_secid_to_secctx(ct->secmark, NULL, &len); if (ret) return 0; return nla_total_size(0) /* CTA_SECCTX */ + nla_total_size(sizeof(char) * len); /* CTA_SECCTX_NAME */ #else return 0; #endif } static inline size_t ctnetlink_timestamp_size(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP if (!nf_ct_ext_exist(ct, NF_CT_EXT_TSTAMP)) return 0; return nla_total_size(0) + 2 * nla_total_size_64bit(sizeof(uint64_t)); #else return 0; #endif } #ifdef CONFIG_NF_CONNTRACK_EVENTS static size_t ctnetlink_nlmsg_size(const struct nf_conn *ct) { return NLMSG_ALIGN(sizeof(struct nfgenmsg)) + 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */ + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */ + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */ + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */ + ctnetlink_acct_size(ct) + ctnetlink_timestamp_size(ct) + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */ + nla_total_size(0) /* CTA_PROTOINFO */ + nla_total_size(0) /* CTA_HELP */ + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + ctnetlink_secctx_size(ct) #if IS_ENABLED(CONFIG_NF_NAT) + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ #endif #ifdef CONFIG_NF_CONNTRACK_MARK + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif #ifdef CONFIG_NF_CONNTRACK_ZONES + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE|CTA_TUPLE_ZONE */ #endif + ctnetlink_proto_size(ct) + ctnetlink_label_size(ct) ; } static int ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) { const struct nf_conntrack_zone *zone; struct net *net; struct nlmsghdr *nlh; struct nlattr *nest_parms; struct nf_conn *ct = item->ct; struct sk_buff *skb; unsigned int type; unsigned int flags = 0, group; int err; if (events & (1 << IPCT_DESTROY)) { type = IPCTNL_MSG_CT_DELETE; group = NFNLGRP_CONNTRACK_DESTROY; } else if (events & ((1 << IPCT_NEW) | (1 << IPCT_RELATED))) { type = IPCTNL_MSG_CT_NEW; flags = NLM_F_CREATE|NLM_F_EXCL; group = NFNLGRP_CONNTRACK_NEW; } else if (events) { type = IPCTNL_MSG_CT_NEW; group = NFNLGRP_CONNTRACK_UPDATE; } else return 0; net = nf_ct_net(ct); if (!item->report && !nfnetlink_has_listeners(net, group)) return 0; skb = nlmsg_new(ctnetlink_nlmsg_size(ct), GFP_ATOMIC); if (skb == NULL) goto errout; type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, type); nlh = nfnl_msg_put(skb, item->portid, 0, type, flags, nf_ct_l3num(ct), NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_ORIG) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_REPL) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_id(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_status(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_DESTROY)) { if (ctnetlink_dump_timeout(skb, ct, true) < 0) goto nla_put_failure; if (ctnetlink_dump_acct(skb, ct, type) < 0 || ctnetlink_dump_timestamp(skb, ct) < 0 || ctnetlink_dump_protoinfo(skb, ct, true) < 0) goto nla_put_failure; } else { if (ctnetlink_dump_timeout(skb, ct, false) < 0) goto nla_put_failure; if (events & (1 << IPCT_PROTOINFO) && ctnetlink_dump_protoinfo(skb, ct, false) < 0) goto nla_put_failure; if ((events & (1 << IPCT_HELPER) || nfct_help(ct)) && ctnetlink_dump_helpinfo(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_SECMARK if ((events & (1 << IPCT_SECMARK) || ct->secmark) && ctnetlink_dump_secctx(skb, ct) < 0) goto nla_put_failure; #endif if (events & (1 << IPCT_LABEL) && ctnetlink_dump_labels(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_RELATED) && ctnetlink_dump_master(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_SEQADJ) && ctnetlink_dump_ct_seq_adj(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_SYNPROXY) && ctnetlink_dump_ct_synproxy(skb, ct) < 0) goto nla_put_failure; } #ifdef CONFIG_NF_CONNTRACK_MARK if (ctnetlink_dump_mark(skb, ct, events & (1 << IPCT_MARK))) goto nla_put_failure; #endif nlmsg_end(skb, nlh); err = nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); if (err == -ENOBUFS || err == -EAGAIN) return -ENOBUFS; return 0; nla_put_failure: nlmsg_cancel(skb, nlh); nlmsg_failure: kfree_skb(skb); errout: if (nfnetlink_set_err(net, 0, group, -ENOBUFS) > 0) return -ENOBUFS; return 0; } #endif /* CONFIG_NF_CONNTRACK_EVENTS */ static int ctnetlink_done(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_put((struct nf_conn *)cb->args[1]); kfree(cb->data); return 0; } struct ctnetlink_filter_u32 { u32 val; u32 mask; }; struct ctnetlink_filter { u8 family; u_int32_t orig_flags; u_int32_t reply_flags; struct nf_conntrack_tuple orig; struct nf_conntrack_tuple reply; struct nf_conntrack_zone zone; struct ctnetlink_filter_u32 mark; struct ctnetlink_filter_u32 status; }; static const struct nla_policy cta_filter_nla_policy[CTA_FILTER_MAX + 1] = { [CTA_FILTER_ORIG_FLAGS] = { .type = NLA_U32 }, [CTA_FILTER_REPLY_FLAGS] = { .type = NLA_U32 }, }; static int ctnetlink_parse_filter(const struct nlattr *attr, struct ctnetlink_filter *filter) { struct nlattr *tb[CTA_FILTER_MAX + 1]; int ret = 0; ret = nla_parse_nested(tb, CTA_FILTER_MAX, attr, cta_filter_nla_policy, NULL); if (ret) return ret; if (tb[CTA_FILTER_ORIG_FLAGS]) { filter->orig_flags = nla_get_u32(tb[CTA_FILTER_ORIG_FLAGS]); if (filter->orig_flags & ~CTA_FILTER_F_ALL) return -EOPNOTSUPP; } if (tb[CTA_FILTER_REPLY_FLAGS]) { filter->reply_flags = nla_get_u32(tb[CTA_FILTER_REPLY_FLAGS]); if (filter->reply_flags & ~CTA_FILTER_F_ALL) return -EOPNOTSUPP; } return 0; } static int ctnetlink_parse_zone(const struct nlattr *attr, struct nf_conntrack_zone *zone); static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, u32 type, u_int8_t l3num, struct nf_conntrack_zone *zone, u_int32_t flags); static int ctnetlink_filter_parse_mark(struct ctnetlink_filter_u32 *mark, const struct nlattr * const cda[]) { #ifdef CONFIG_NF_CONNTRACK_MARK if (cda[CTA_MARK]) { mark->val = ntohl(nla_get_be32(cda[CTA_MARK])); if (cda[CTA_MARK_MASK]) mark->mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK])); else mark->mask = 0xffffffff; } else if (cda[CTA_MARK_MASK]) { return -EINVAL; } #endif return 0; } static int ctnetlink_filter_parse_status(struct ctnetlink_filter_u32 *status, const struct nlattr * const cda[]) { if (cda[CTA_STATUS]) { status->val = ntohl(nla_get_be32(cda[CTA_STATUS])); if (cda[CTA_STATUS_MASK]) status->mask = ntohl(nla_get_be32(cda[CTA_STATUS_MASK])); else status->mask = status->val; /* status->val == 0? always true, else always false. */ if (status->mask == 0) return -EINVAL; } else if (cda[CTA_STATUS_MASK]) { return -EINVAL; } /* CTA_STATUS is NLA_U32, if this fires UAPI needs to be extended */ BUILD_BUG_ON(__IPS_MAX_BIT >= 32); return 0; } static struct ctnetlink_filter * ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) { struct ctnetlink_filter *filter; int err; #ifndef CONFIG_NF_CONNTRACK_MARK if (cda[CTA_MARK] || cda[CTA_MARK_MASK]) return ERR_PTR(-EOPNOTSUPP); #endif filter = kzalloc(sizeof(*filter), GFP_KERNEL); if (filter == NULL) return ERR_PTR(-ENOMEM); filter->family = family; err = ctnetlink_filter_parse_mark(&filter->mark, cda); if (err) goto err_filter; err = ctnetlink_filter_parse_status(&filter->status, cda); if (err) goto err_filter; if (!cda[CTA_FILTER]) return filter; err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone); if (err < 0) goto err_filter; err = ctnetlink_parse_filter(cda[CTA_FILTER], filter); if (err < 0) goto err_filter; if (filter->orig_flags) { if (!cda[CTA_TUPLE_ORIG]) { err = -EINVAL; goto err_filter; } err = ctnetlink_parse_tuple_filter(cda, &filter->orig, CTA_TUPLE_ORIG, filter->family, &filter->zone, filter->orig_flags); if (err < 0) goto err_filter; } if (filter->reply_flags) { if (!cda[CTA_TUPLE_REPLY]) { err = -EINVAL; goto err_filter; } err = ctnetlink_parse_tuple_filter(cda, &filter->reply, CTA_TUPLE_REPLY, filter->family, &filter->zone, filter->reply_flags); if (err < 0) goto err_filter; } return filter; err_filter: kfree(filter); return ERR_PTR(err); } static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda) { return family || cda[CTA_MARK] || cda[CTA_FILTER] || cda[CTA_STATUS]; } static int ctnetlink_start(struct netlink_callback *cb) { const struct nlattr * const *cda = cb->data; struct ctnetlink_filter *filter = NULL; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u8 family = nfmsg->nfgen_family; if (ctnetlink_needs_filter(family, cda)) { filter = ctnetlink_alloc_filter(cda, family); if (IS_ERR(filter)) return PTR_ERR(filter); } cb->data = filter; return 0; } static int ctnetlink_filter_match_tuple(struct nf_conntrack_tuple *filter_tuple, struct nf_conntrack_tuple *ct_tuple, u_int32_t flags, int family) { switch (family) { case NFPROTO_IPV4: if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) && filter_tuple->src.u3.ip != ct_tuple->src.u3.ip) return 0; if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) && filter_tuple->dst.u3.ip != ct_tuple->dst.u3.ip) return 0; break; case NFPROTO_IPV6: if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) && !ipv6_addr_cmp(&filter_tuple->src.u3.in6, &ct_tuple->src.u3.in6)) return 0; if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) && !ipv6_addr_cmp(&filter_tuple->dst.u3.in6, &ct_tuple->dst.u3.in6)) return 0; break; } if ((flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) && filter_tuple->dst.protonum != ct_tuple->dst.protonum) return 0; switch (ct_tuple->dst.protonum) { case IPPROTO_TCP: case IPPROTO_UDP: if ((flags & CTA_FILTER_FLAG(CTA_PROTO_SRC_PORT)) && filter_tuple->src.u.tcp.port != ct_tuple->src.u.tcp.port) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_DST_PORT)) && filter_tuple->dst.u.tcp.port != ct_tuple->dst.u.tcp.port) return 0; break; case IPPROTO_ICMP: if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) && filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) && filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) && filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id) return 0; break; case IPPROTO_ICMPV6: if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_TYPE)) && filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_CODE)) && filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_ID)) && filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id) return 0; break; } return 1; } static int ctnetlink_filter_match(struct nf_conn *ct, void *data) { struct ctnetlink_filter *filter = data; struct nf_conntrack_tuple *tuple; u32 status; if (filter == NULL) goto out; /* Match entries of a given L3 protocol number. * If it is not specified, ie. l3proto == 0, * then match everything. */ if (filter->family && nf_ct_l3num(ct) != filter->family) goto ignore_entry; if (filter->orig_flags) { tuple = nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL); if (!ctnetlink_filter_match_tuple(&filter->orig, tuple, filter->orig_flags, filter->family)) goto ignore_entry; } if (filter->reply_flags) { tuple = nf_ct_tuple(ct, IP_CT_DIR_REPLY); if (!ctnetlink_filter_match_tuple(&filter->reply, tuple, filter->reply_flags, filter->family)) goto ignore_entry; } #ifdef CONFIG_NF_CONNTRACK_MARK if ((READ_ONCE(ct->mark) & filter->mark.mask) != filter->mark.val) goto ignore_entry; #endif status = (u32)READ_ONCE(ct->status); if ((status & filter->status.mask) != filter->status.val) goto ignore_entry; out: return 1; ignore_entry: return 0; } static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { unsigned int flags = cb->data ? NLM_F_DUMP_FILTERED : 0; struct net *net = sock_net(skb->sk); struct nf_conn *ct, *last; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nf_conn *nf_ct_evict[8]; int res, i; spinlock_t *lockp; last = (struct nf_conn *)cb->args[1]; i = 0; local_bh_disable(); for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) { restart: while (i) { i--; if (nf_ct_should_gc(nf_ct_evict[i])) nf_ct_kill(nf_ct_evict[i]); nf_ct_put(nf_ct_evict[i]); } lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS]; nf_conntrack_lock(lockp); if (cb->args[0] >= nf_conntrack_htable_size) { spin_unlock(lockp); goto out; } hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[cb->args[0]], hnnode) { if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) continue; ct = nf_ct_tuplehash_to_ctrack(h); if (nf_ct_is_expired(ct)) { if (i < ARRAY_SIZE(nf_ct_evict) && refcount_inc_not_zero(&ct->ct_general.use)) nf_ct_evict[i++] = ct; continue; } if (!net_eq(net, nf_ct_net(ct))) continue; if (cb->args[1]) { if (ct != last) continue; cb->args[1] = 0; } if (!ctnetlink_filter_match(ct, cb->data)) continue; res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, true, flags); if (res < 0) { nf_conntrack_get(&ct->ct_general); cb->args[1] = (unsigned long)ct; spin_unlock(lockp); goto out; } } spin_unlock(lockp); if (cb->args[1]) { cb->args[1] = 0; goto restart; } } out: local_bh_enable(); if (last) { /* nf ct hash resize happened, now clear the leftover. */ if ((struct nf_conn *)cb->args[1] == last) cb->args[1] = 0; nf_ct_put(last); } while (i) { i--; if (nf_ct_should_gc(nf_ct_evict[i])) nf_ct_kill(nf_ct_evict[i]); nf_ct_put(nf_ct_evict[i]); } return skb->len; } static int ipv4_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *t, u_int32_t flags) { if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { if (!tb[CTA_IP_V4_SRC]) return -EINVAL; t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]); } if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) { if (!tb[CTA_IP_V4_DST]) return -EINVAL; t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]); } return 0; } static int ipv6_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *t, u_int32_t flags) { if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { if (!tb[CTA_IP_V6_SRC]) return -EINVAL; t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]); } if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) { if (!tb[CTA_IP_V6_DST]) return -EINVAL; t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]); } return 0; } static int ctnetlink_parse_tuple_ip(struct nlattr *attr, struct nf_conntrack_tuple *tuple, u_int32_t flags) { struct nlattr *tb[CTA_IP_MAX+1]; int ret = 0; ret = nla_parse_nested_deprecated(tb, CTA_IP_MAX, attr, NULL, NULL); if (ret < 0) return ret; ret = nla_validate_nested_deprecated(attr, CTA_IP_MAX, cta_ip_nla_policy, NULL); if (ret) return ret; switch (tuple->src.l3num) { case NFPROTO_IPV4: ret = ipv4_nlattr_to_tuple(tb, tuple, flags); break; case NFPROTO_IPV6: ret = ipv6_nlattr_to_tuple(tb, tuple, flags); break; } return ret; } static const struct nla_policy proto_nla_policy[CTA_PROTO_MAX+1] = { [CTA_PROTO_NUM] = { .type = NLA_U8 }, }; static int ctnetlink_parse_tuple_proto(struct nlattr *attr, struct nf_conntrack_tuple *tuple, u_int32_t flags) { const struct nf_conntrack_l4proto *l4proto; struct nlattr *tb[CTA_PROTO_MAX+1]; int ret = 0; ret = nla_parse_nested_deprecated(tb, CTA_PROTO_MAX, attr, proto_nla_policy, NULL); if (ret < 0) return ret; if (!(flags & CTA_FILTER_FLAG(CTA_PROTO_NUM))) return 0; if (!tb[CTA_PROTO_NUM]) return -EINVAL; tuple->dst.protonum = nla_get_u8(tb[CTA_PROTO_NUM]); rcu_read_lock(); l4proto = nf_ct_l4proto_find(tuple->dst.protonum); if (likely(l4proto->nlattr_to_tuple)) { ret = nla_validate_nested_deprecated(attr, CTA_PROTO_MAX, l4proto->nla_policy, NULL); if (ret == 0) ret = l4proto->nlattr_to_tuple(tb, tuple, flags); } rcu_read_unlock(); return ret; } static int ctnetlink_parse_zone(const struct nlattr *attr, struct nf_conntrack_zone *zone) { nf_ct_zone_init(zone, NF_CT_DEFAULT_ZONE_ID, NF_CT_DEFAULT_ZONE_DIR, 0); #ifdef CONFIG_NF_CONNTRACK_ZONES if (attr) zone->id = ntohs(nla_get_be16(attr)); #else if (attr) return -EOPNOTSUPP; #endif return 0; } static int ctnetlink_parse_tuple_zone(struct nlattr *attr, enum ctattr_type type, struct nf_conntrack_zone *zone) { int ret; if (zone->id != NF_CT_DEFAULT_ZONE_ID) return -EINVAL; ret = ctnetlink_parse_zone(attr, zone); if (ret < 0) return ret; if (type == CTA_TUPLE_REPLY) zone->dir = NF_CT_ZONE_DIR_REPL; else zone->dir = NF_CT_ZONE_DIR_ORIG; return 0; } static const struct nla_policy tuple_nla_policy[CTA_TUPLE_MAX+1] = { [CTA_TUPLE_IP] = { .type = NLA_NESTED }, [CTA_TUPLE_PROTO] = { .type = NLA_NESTED }, [CTA_TUPLE_ZONE] = { .type = NLA_U16 }, }; #define CTA_FILTER_F_ALL_CTA_PROTO \ (CTA_FILTER_F_CTA_PROTO_SRC_PORT | \ CTA_FILTER_F_CTA_PROTO_DST_PORT | \ CTA_FILTER_F_CTA_PROTO_ICMP_TYPE | \ CTA_FILTER_F_CTA_PROTO_ICMP_CODE | \ CTA_FILTER_F_CTA_PROTO_ICMP_ID | \ CTA_FILTER_F_CTA_PROTO_ICMPV6_TYPE | \ CTA_FILTER_F_CTA_PROTO_ICMPV6_CODE | \ CTA_FILTER_F_CTA_PROTO_ICMPV6_ID) static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, u32 type, u_int8_t l3num, struct nf_conntrack_zone *zone, u_int32_t flags) { struct nlattr *tb[CTA_TUPLE_MAX+1]; int err; memset(tuple, 0, sizeof(*tuple)); err = nla_parse_nested_deprecated(tb, CTA_TUPLE_MAX, cda[type], tuple_nla_policy, NULL); if (err < 0) return err; if (l3num != NFPROTO_IPV4 && l3num != NFPROTO_IPV6) return -EOPNOTSUPP; tuple->src.l3num = l3num; if (flags & CTA_FILTER_FLAG(CTA_IP_DST) || flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { if (!tb[CTA_TUPLE_IP]) return -EINVAL; err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP], tuple, flags); if (err < 0) return err; } if (flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) { if (!tb[CTA_TUPLE_PROTO]) return -EINVAL; err = ctnetlink_parse_tuple_proto(tb[CTA_TUPLE_PROTO], tuple, flags); if (err < 0) return err; } else if (flags & CTA_FILTER_FLAG(ALL_CTA_PROTO)) { /* Can't manage proto flags without a protonum */ return -EINVAL; } if ((flags & CTA_FILTER_FLAG(CTA_TUPLE_ZONE)) && tb[CTA_TUPLE_ZONE]) { if (!zone) return -EINVAL; err = ctnetlink_parse_tuple_zone(tb[CTA_TUPLE_ZONE], type, zone); if (err < 0) return err; } /* orig and expect tuples get DIR_ORIGINAL */ if (type == CTA_TUPLE_REPLY) tuple->dst.dir = IP_CT_DIR_REPLY; else tuple->dst.dir = IP_CT_DIR_ORIGINAL; return 0; } static int ctnetlink_parse_tuple(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, u32 type, u_int8_t l3num, struct nf_conntrack_zone *zone) { return ctnetlink_parse_tuple_filter(cda, tuple, type, l3num, zone, CTA_FILTER_FLAG(ALL)); } static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = { [CTA_HELP_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN - 1 }, }; static int ctnetlink_parse_help(const struct nlattr *attr, char **helper_name, struct nlattr **helpinfo) { int err; struct nlattr *tb[CTA_HELP_MAX+1]; err = nla_parse_nested_deprecated(tb, CTA_HELP_MAX, attr, help_nla_policy, NULL); if (err < 0) return err; if (!tb[CTA_HELP_NAME]) return -EINVAL; *helper_name = nla_data(tb[CTA_HELP_NAME]); if (tb[CTA_HELP_INFO]) *helpinfo = tb[CTA_HELP_INFO]; return 0; } static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_TUPLE_ORIG] = { .type = NLA_NESTED }, [CTA_TUPLE_REPLY] = { .type = NLA_NESTED }, [CTA_STATUS] = { .type = NLA_U32 }, [CTA_PROTOINFO] = { .type = NLA_NESTED }, [CTA_HELP] = { .type = NLA_NESTED }, [CTA_NAT_SRC] = { .type = NLA_NESTED }, [CTA_TIMEOUT] = { .type = NLA_U32 }, [CTA_MARK] = { .type = NLA_U32 }, [CTA_ID] = { .type = NLA_U32 }, [CTA_NAT_DST] = { .type = NLA_NESTED }, [CTA_TUPLE_MASTER] = { .type = NLA_NESTED }, [CTA_NAT_SEQ_ADJ_ORIG] = { .type = NLA_NESTED }, [CTA_NAT_SEQ_ADJ_REPLY] = { .type = NLA_NESTED }, [CTA_ZONE] = { .type = NLA_U16 }, [CTA_MARK_MASK] = { .type = NLA_U32 }, [CTA_LABELS] = { .type = NLA_BINARY, .len = NF_CT_LABELS_MAX_SIZE }, [CTA_LABELS_MASK] = { .type = NLA_BINARY, .len = NF_CT_LABELS_MAX_SIZE }, [CTA_FILTER] = { .type = NLA_NESTED }, [CTA_STATUS_MASK] = { .type = NLA_U32 }, }; static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data) { return ctnetlink_filter_match(ct, data); } static int ctnetlink_flush_conntrack(struct net *net, const struct nlattr * const cda[], u32 portid, int report, u8 family) { struct ctnetlink_filter *filter = NULL; if (ctnetlink_needs_filter(family, cda)) { if (cda[CTA_FILTER]) return -EOPNOTSUPP; filter = ctnetlink_alloc_filter(cda, family); if (IS_ERR(filter)) return PTR_ERR(filter); } nf_ct_iterate_cleanup_net(net, ctnetlink_flush_iterate, filter, portid, report); kfree(filter); return 0; } static int ctnetlink_del_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u8 family = info->nfmsg->nfgen_family; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; struct nf_conn *ct; int err; err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) return err; if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, family, &zone); else if (cda[CTA_TUPLE_REPLY]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, family, &zone); else { u_int8_t u3 = info->nfmsg->version ? family : AF_UNSPEC; return ctnetlink_flush_conntrack(info->net, cda, NETLINK_CB(skb).portid, nlmsg_report(info->nlh), u3); } if (err < 0) return err; h = nf_conntrack_find_get(info->net, &zone, &tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); if (cda[CTA_ID]) { __be32 id = nla_get_be32(cda[CTA_ID]); if (id != (__force __be32)nf_ct_get_id(ct)) { nf_ct_put(ct); return -ENOENT; } } nf_ct_delete(ct, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); nf_ct_put(ct); return 0; } static int ctnetlink_get_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; struct sk_buff *skb2; struct nf_conn *ct; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = ctnetlink_start, .dump = ctnetlink_dump_table, .done = ctnetlink_done, .data = (void *)cda, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) return err; if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3, &zone); else if (cda[CTA_TUPLE_REPLY]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3, &zone); else return -EINVAL; if (err < 0) return err; h = nf_conntrack_find_get(info->net, &zone, &tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb2) { nf_ct_put(ct); return -ENOMEM; } err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), ct, true, 0); nf_ct_put(ct); if (err <= 0) { kfree_skb(skb2); return -ENOMEM; } return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static int ctnetlink_done_list(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_put((struct nf_conn *)cb->args[1]); return 0; } static int ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying) { struct nf_conn *ct, *last; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; int res; int cpu; struct hlist_nulls_head *list; struct net *net = sock_net(skb->sk); if (cb->args[2]) return 0; last = (struct nf_conn *)cb->args[1]; for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { struct ct_pcpu *pcpu; if (!cpu_possible(cpu)) continue; pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); spin_lock_bh(&pcpu->lock); list = dying ? &pcpu->dying : &pcpu->unconfirmed; restart: hlist_nulls_for_each_entry(h, n, list, hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (l3proto && nf_ct_l3num(ct) != l3proto) continue; if (cb->args[1]) { if (ct != last) continue; cb->args[1] = 0; } /* We can't dump extension info for the unconfirmed * list because unconfirmed conntracks can have * ct->ext reallocated (and thus freed). * * In the dying list case ct->ext can't be free'd * until after we drop pcpu->lock. */ res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, dying ? true : false, 0); if (res < 0) { if (!refcount_inc_not_zero(&ct->ct_general.use)) continue; cb->args[0] = cpu; cb->args[1] = (unsigned long)ct; spin_unlock_bh(&pcpu->lock); goto out; } } if (cb->args[1]) { cb->args[1] = 0; goto restart; } spin_unlock_bh(&pcpu->lock); } cb->args[2] = 1; out: if (last) nf_ct_put(last); return skb->len; } static int ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb) { return ctnetlink_dump_list(skb, cb, true); } static int ctnetlink_get_ct_dying(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_dump_dying, .done = ctnetlink_done_list, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } return -EOPNOTSUPP; } static int ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb) { return ctnetlink_dump_list(skb, cb, false); } static int ctnetlink_get_ct_unconfirmed(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_dump_unconfirmed, .done = ctnetlink_done_list, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } return -EOPNOTSUPP; } #if IS_ENABLED(CONFIG_NF_NAT) static int ctnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) __must_hold(RCU) { const struct nf_nat_hook *nat_hook; int err; nat_hook = rcu_dereference(nf_nat_hook); if (!nat_hook) { #ifdef CONFIG_MODULES rcu_read_unlock(); nfnl_unlock(NFNL_SUBSYS_CTNETLINK); if (request_module("nf-nat") < 0) { nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); return -EOPNOTSUPP; } nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); nat_hook = rcu_dereference(nf_nat_hook); if (nat_hook) return -EAGAIN; #endif return -EOPNOTSUPP; } err = nat_hook->parse_nat_setup(ct, manip, attr); if (err == -EAGAIN) { #ifdef CONFIG_MODULES rcu_read_unlock(); nfnl_unlock(NFNL_SUBSYS_CTNETLINK); if (request_module("nf-nat-%u", nf_ct_l3num(ct)) < 0) { nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); return -EOPNOTSUPP; } nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); #else err = -EOPNOTSUPP; #endif } return err; } #endif static void __ctnetlink_change_status(struct nf_conn *ct, unsigned long on, unsigned long off) { unsigned int bit; /* Ignore these unchangable bits */ on &= ~IPS_UNCHANGEABLE_MASK; off &= ~IPS_UNCHANGEABLE_MASK; for (bit = 0; bit < __IPS_MAX_BIT; bit++) { if (on & (1 << bit)) set_bit(bit, &ct->status); else if (off & (1 << bit)) clear_bit(bit, &ct->status); } } static int ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[]) { unsigned long d; unsigned int status = ntohl(nla_get_be32(cda[CTA_STATUS])); d = ct->status ^ status; if (d & (IPS_EXPECTED|IPS_CONFIRMED|IPS_DYING)) /* unchangeable */ return -EBUSY; if (d & IPS_SEEN_REPLY && !(status & IPS_SEEN_REPLY)) /* SEEN_REPLY bit can only be set */ return -EBUSY; if (d & IPS_ASSURED && !(status & IPS_ASSURED)) /* ASSURED bit can only be set */ return -EBUSY; __ctnetlink_change_status(ct, status, 0); return 0; } static int ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[]) { #if IS_ENABLED(CONFIG_NF_NAT) int ret; if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) return 0; ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST, cda[CTA_NAT_DST]); if (ret < 0) return ret; return ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC, cda[CTA_NAT_SRC]); #else if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) return 0; return -EOPNOTSUPP; #endif } static int ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) { struct nf_conntrack_helper *helper; struct nf_conn_help *help = nfct_help(ct); char *helpname = NULL; struct nlattr *helpinfo = NULL; int err; err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo); if (err < 0) return err; /* don't change helper of sibling connections */ if (ct->master) { /* If we try to change the helper to the same thing twice, * treat the second attempt as a no-op instead of returning * an error. */ err = -EBUSY; if (help) { rcu_read_lock(); helper = rcu_dereference(help->helper); if (helper && !strcmp(helper->name, helpname)) err = 0; rcu_read_unlock(); } return err; } if (!strcmp(helpname, "")) { if (help && help->helper) { /* we had a helper before ... */ nf_ct_remove_expectations(ct); RCU_INIT_POINTER(help->helper, NULL); } return 0; } rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); return -EOPNOTSUPP; } if (help) { if (help->helper == helper) { /* update private helper data if allowed. */ if (helper->from_nlattr) helper->from_nlattr(helpinfo, ct); err = 0; } else err = -EBUSY; } else { /* we cannot set a helper for an existing conntrack */ err = -EOPNOTSUPP; } rcu_read_unlock(); return err; } static int ctnetlink_change_timeout(struct nf_conn *ct, const struct nlattr * const cda[]) { u64 timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; if (timeout > INT_MAX) timeout = INT_MAX; WRITE_ONCE(ct->timeout, nfct_time_stamp + (u32)timeout); if (test_bit(IPS_DYING_BIT, &ct->status)) return -ETIME; return 0; } #if defined(CONFIG_NF_CONNTRACK_MARK) static void ctnetlink_change_mark(struct nf_conn *ct, const struct nlattr * const cda[]) { u32 mark, newmark, mask = 0; if (cda[CTA_MARK_MASK]) mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK])); mark = ntohl(nla_get_be32(cda[CTA_MARK])); newmark = (READ_ONCE(ct->mark) & mask) ^ mark; if (newmark != READ_ONCE(ct->mark)) WRITE_ONCE(ct->mark, newmark); } #endif static const struct nla_policy protoinfo_policy[CTA_PROTOINFO_MAX+1] = { [CTA_PROTOINFO_TCP] = { .type = NLA_NESTED }, [CTA_PROTOINFO_DCCP] = { .type = NLA_NESTED }, [CTA_PROTOINFO_SCTP] = { .type = NLA_NESTED }, }; static int ctnetlink_change_protoinfo(struct nf_conn *ct, const struct nlattr * const cda[]) { const struct nlattr *attr = cda[CTA_PROTOINFO]; const struct nf_conntrack_l4proto *l4proto; struct nlattr *tb[CTA_PROTOINFO_MAX+1]; int err = 0; err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_MAX, attr, protoinfo_policy, NULL); if (err < 0) return err; l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (l4proto->from_nlattr) err = l4proto->from_nlattr(tb, ct); return err; } static const struct nla_policy seqadj_policy[CTA_SEQADJ_MAX+1] = { [CTA_SEQADJ_CORRECTION_POS] = { .type = NLA_U32 }, [CTA_SEQADJ_OFFSET_BEFORE] = { .type = NLA_U32 }, [CTA_SEQADJ_OFFSET_AFTER] = { .type = NLA_U32 }, }; static int change_seq_adj(struct nf_ct_seqadj *seq, const struct nlattr * const attr) { int err; struct nlattr *cda[CTA_SEQADJ_MAX+1]; err = nla_parse_nested_deprecated(cda, CTA_SEQADJ_MAX, attr, seqadj_policy, NULL); if (err < 0) return err; if (!cda[CTA_SEQADJ_CORRECTION_POS]) return -EINVAL; seq->correction_pos = ntohl(nla_get_be32(cda[CTA_SEQADJ_CORRECTION_POS])); if (!cda[CTA_SEQADJ_OFFSET_BEFORE]) return -EINVAL; seq->offset_before = ntohl(nla_get_be32(cda[CTA_SEQADJ_OFFSET_BEFORE])); if (!cda[CTA_SEQADJ_OFFSET_AFTER]) return -EINVAL; seq->offset_after = ntohl(nla_get_be32(cda[CTA_SEQADJ_OFFSET_AFTER])); return 0; } static int ctnetlink_change_seq_adj(struct nf_conn *ct, const struct nlattr * const cda[]) { struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); int ret = 0; if (!seqadj) return 0; spin_lock_bh(&ct->lock); if (cda[CTA_SEQ_ADJ_ORIG]) { ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_ORIGINAL], cda[CTA_SEQ_ADJ_ORIG]); if (ret < 0) goto err; set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); } if (cda[CTA_SEQ_ADJ_REPLY]) { ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_REPLY], cda[CTA_SEQ_ADJ_REPLY]); if (ret < 0) goto err; set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); } spin_unlock_bh(&ct->lock); return 0; err: spin_unlock_bh(&ct->lock); return ret; } static const struct nla_policy synproxy_policy[CTA_SYNPROXY_MAX + 1] = { [CTA_SYNPROXY_ISN] = { .type = NLA_U32 }, [CTA_SYNPROXY_ITS] = { .type = NLA_U32 }, [CTA_SYNPROXY_TSOFF] = { .type = NLA_U32 }, }; static int ctnetlink_change_synproxy(struct nf_conn *ct, const struct nlattr * const cda[]) { struct nf_conn_synproxy *synproxy = nfct_synproxy(ct); struct nlattr *tb[CTA_SYNPROXY_MAX + 1]; int err; if (!synproxy) return 0; err = nla_parse_nested_deprecated(tb, CTA_SYNPROXY_MAX, cda[CTA_SYNPROXY], synproxy_policy, NULL); if (err < 0) return err; if (!tb[CTA_SYNPROXY_ISN] || !tb[CTA_SYNPROXY_ITS] || !tb[CTA_SYNPROXY_TSOFF]) return -EINVAL; synproxy->isn = ntohl(nla_get_be32(tb[CTA_SYNPROXY_ISN])); synproxy->its = ntohl(nla_get_be32(tb[CTA_SYNPROXY_ITS])); synproxy->tsoff = ntohl(nla_get_be32(tb[CTA_SYNPROXY_TSOFF])); return 0; } static int ctnetlink_attach_labels(struct nf_conn *ct, const struct nlattr * const cda[]) { #ifdef CONFIG_NF_CONNTRACK_LABELS size_t len = nla_len(cda[CTA_LABELS]); const void *mask = cda[CTA_LABELS_MASK]; if (len & (sizeof(u32)-1)) /* must be multiple of u32 */ return -EINVAL; if (mask) { if (nla_len(cda[CTA_LABELS_MASK]) == 0 || nla_len(cda[CTA_LABELS_MASK]) != len) return -EINVAL; mask = nla_data(cda[CTA_LABELS_MASK]); } len /= sizeof(u32); return nf_connlabels_replace(ct, nla_data(cda[CTA_LABELS]), mask, len); #else return -EOPNOTSUPP; #endif } static int ctnetlink_change_conntrack(struct nf_conn *ct, const struct nlattr * const cda[]) { int err; /* only allow NAT changes and master assignation for new conntracks */ if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST] || cda[CTA_TUPLE_MASTER]) return -EOPNOTSUPP; if (cda[CTA_HELP]) { err = ctnetlink_change_helper(ct, cda); if (err < 0) return err; } if (cda[CTA_TIMEOUT]) { err = ctnetlink_change_timeout(ct, cda); if (err < 0) return err; } if (cda[CTA_STATUS]) { err = ctnetlink_change_status(ct, cda); if (err < 0) return err; } if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); if (err < 0) return err; } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) ctnetlink_change_mark(ct, cda); #endif if (cda[CTA_SEQ_ADJ_ORIG] || cda[CTA_SEQ_ADJ_REPLY]) { err = ctnetlink_change_seq_adj(ct, cda); if (err < 0) return err; } if (cda[CTA_SYNPROXY]) { err = ctnetlink_change_synproxy(ct, cda); if (err < 0) return err; } if (cda[CTA_LABELS]) { err = ctnetlink_attach_labels(ct, cda); if (err < 0) return err; } return 0; } static struct nf_conn * ctnetlink_create_conntrack(struct net *net, const struct nf_conntrack_zone *zone, const struct nlattr * const cda[], struct nf_conntrack_tuple *otuple, struct nf_conntrack_tuple *rtuple, u8 u3) { struct nf_conn *ct; int err = -EINVAL; struct nf_conntrack_helper *helper; struct nf_conn_tstamp *tstamp; u64 timeout; ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) return ERR_PTR(-ENOMEM); if (!cda[CTA_TIMEOUT]) goto err1; timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; if (timeout > INT_MAX) timeout = INT_MAX; ct->timeout = (u32)timeout + nfct_time_stamp; rcu_read_lock(); if (cda[CTA_HELP]) { char *helpname = NULL; struct nlattr *helpinfo = NULL; err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo); if (err < 0) goto err2; helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { err = -EOPNOTSUPP; goto err1; } rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper) { err = -EAGAIN; goto err2; } rcu_read_unlock(); #endif err = -EOPNOTSUPP; goto err1; } else { struct nf_conn_help *help; help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help == NULL) { err = -ENOMEM; goto err2; } /* set private helper data if allowed. */ if (helper->from_nlattr) helper->from_nlattr(helpinfo, ct); /* disable helper auto-assignment for this entry */ ct->status |= IPS_HELPER; RCU_INIT_POINTER(help->helper, helper); } } else { /* try an implicit helper assignation */ err = __nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC); if (err < 0) goto err2; } err = ctnetlink_setup_nat(ct, cda); if (err < 0) goto err2; nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC); nf_ct_labels_ext_add(ct); nfct_seqadj_ext_add(ct); nfct_synproxy_ext_add(ct); /* we must add conntrack extensions before confirmation. */ ct->status |= IPS_CONFIRMED; if (cda[CTA_STATUS]) { err = ctnetlink_change_status(ct, cda); if (err < 0) goto err2; } if (cda[CTA_SEQ_ADJ_ORIG] || cda[CTA_SEQ_ADJ_REPLY]) { err = ctnetlink_change_seq_adj(ct, cda); if (err < 0) goto err2; } memset(&ct->proto, 0, sizeof(ct->proto)); if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); if (err < 0) goto err2; } if (cda[CTA_SYNPROXY]) { err = ctnetlink_change_synproxy(ct, cda); if (err < 0) goto err2; } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) ctnetlink_change_mark(ct, cda); #endif /* setup master conntrack: this is a confirmed expectation */ if (cda[CTA_TUPLE_MASTER]) { struct nf_conntrack_tuple master; struct nf_conntrack_tuple_hash *master_h; struct nf_conn *master_ct; err = ctnetlink_parse_tuple(cda, &master, CTA_TUPLE_MASTER, u3, NULL); if (err < 0) goto err2; master_h = nf_conntrack_find_get(net, zone, &master); if (master_h == NULL) { err = -ENOENT; goto err2; } master_ct = nf_ct_tuplehash_to_ctrack(master_h); __set_bit(IPS_EXPECTED_BIT, &ct->status); ct->master = master_ct; } tstamp = nf_conn_tstamp_find(ct); if (tstamp) tstamp->start = ktime_get_real_ns(); err = nf_conntrack_hash_check_insert(ct); if (err < 0) goto err3; rcu_read_unlock(); return ct; err3: if (ct->master) nf_ct_put(ct->master); err2: rcu_read_unlock(); err1: nf_conntrack_free(ct); return ERR_PTR(err); } static int ctnetlink_new_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_zone zone; struct nf_conn *ct; int err; err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) return err; if (cda[CTA_TUPLE_ORIG]) { err = ctnetlink_parse_tuple(cda, &otuple, CTA_TUPLE_ORIG, u3, &zone); if (err < 0) return err; } if (cda[CTA_TUPLE_REPLY]) { err = ctnetlink_parse_tuple(cda, &rtuple, CTA_TUPLE_REPLY, u3, &zone); if (err < 0) return err; } if (cda[CTA_TUPLE_ORIG]) h = nf_conntrack_find_get(info->net, &zone, &otuple); else if (cda[CTA_TUPLE_REPLY]) h = nf_conntrack_find_get(info->net, &zone, &rtuple); if (h == NULL) { err = -ENOENT; if (info->nlh->nlmsg_flags & NLM_F_CREATE) { enum ip_conntrack_events events; if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY]) return -EINVAL; if (otuple.dst.protonum != rtuple.dst.protonum) return -EINVAL; ct = ctnetlink_create_conntrack(info->net, &zone, cda, &otuple, &rtuple, u3); if (IS_ERR(ct)) return PTR_ERR(ct); err = 0; if (test_bit(IPS_EXPECTED_BIT, &ct->status)) events = 1 << IPCT_RELATED; else events = 1 << IPCT_NEW; if (cda[CTA_LABELS] && ctnetlink_attach_labels(ct, cda) == 0) events |= (1 << IPCT_LABEL); nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | (1 << IPCT_PROTOINFO) | (1 << IPCT_SEQADJ) | (1 << IPCT_MARK) | (1 << IPCT_SYNPROXY) | events, ct, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); nf_ct_put(ct); } return err; } /* implicit 'else' */ err = -EEXIST; ct = nf_ct_tuplehash_to_ctrack(h); if (!(info->nlh->nlmsg_flags & NLM_F_EXCL)) { err = ctnetlink_change_conntrack(ct, cda); if (err == 0) { nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | (1 << IPCT_LABEL) | (1 << IPCT_PROTOINFO) | (1 << IPCT_SEQADJ) | (1 << IPCT_MARK) | (1 << IPCT_SYNPROXY), ct, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); } } nf_ct_put(ct); return err; } static int ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, __u16 cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS_CPU); nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, NFNETLINK_V0, htons(cpu)); if (!nlh) goto nlmsg_failure; if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) || nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) || nla_put_be32(skb, CTA_STATS_INSERT_FAILED, htonl(st->insert_failed)) || nla_put_be32(skb, CTA_STATS_DROP, htonl(st->drop)) || nla_put_be32(skb, CTA_STATS_EARLY_DROP, htonl(st->early_drop)) || nla_put_be32(skb, CTA_STATS_ERROR, htonl(st->error)) || nla_put_be32(skb, CTA_STATS_SEARCH_RESTART, htonl(st->search_restart)) || nla_put_be32(skb, CTA_STATS_CLASH_RESOLVE, htonl(st->clash_resolve)) || nla_put_be32(skb, CTA_STATS_CHAIN_TOOLONG, htonl(st->chaintoolong))) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nla_put_failure: nlmsg_failure: nlmsg_cancel(skb, nlh); return -1; } static int ctnetlink_ct_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) { int cpu; struct net *net = sock_net(skb->sk); if (cb->args[0] == nr_cpu_ids) return 0; for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { const struct ip_conntrack_stat *st; if (!cpu_possible(cpu)) continue; st = per_cpu_ptr(net->ct.stat, cpu); if (ctnetlink_ct_stat_cpu_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cpu, st) < 0) break; } cb->args[0] = cpu; return skb->len; } static int ctnetlink_stat_ct_cpu(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_ct_stat_cpu_dump, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } return 0; } static int ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct net *net) { unsigned int flags = portid ? NLM_F_MULTI : 0, event; unsigned int nr_conntracks; struct nlmsghdr *nlh; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS); nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; nr_conntracks = nf_conntrack_count(net); if (nla_put_be32(skb, CTA_STATS_GLOBAL_ENTRIES, htonl(nr_conntracks))) goto nla_put_failure; if (nla_put_be32(skb, CTA_STATS_GLOBAL_MAX_ENTRIES, htonl(nf_conntrack_max))) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nla_put_failure: nlmsg_failure: nlmsg_cancel(skb, nlh); return -1; } static int ctnetlink_stat_ct(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { struct sk_buff *skb2; int err; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) return -ENOMEM; err = ctnetlink_stat_ct_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), sock_net(skb->sk)); if (err <= 0) { kfree_skb(skb2); return -ENOMEM; } return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { [CTA_EXPECT_MASTER] = { .type = NLA_NESTED }, [CTA_EXPECT_TUPLE] = { .type = NLA_NESTED }, [CTA_EXPECT_MASK] = { .type = NLA_NESTED }, [CTA_EXPECT_TIMEOUT] = { .type = NLA_U32 }, [CTA_EXPECT_ID] = { .type = NLA_U32 }, [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN - 1 }, [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, [CTA_EXPECT_FLAGS] = { .type = NLA_U32 }, [CTA_EXPECT_CLASS] = { .type = NLA_U32 }, [CTA_EXPECT_NAT] = { .type = NLA_NESTED }, [CTA_EXPECT_FN] = { .type = NLA_NUL_STRING }, }; static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct, struct nf_conntrack_helper *helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask); #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT static size_t ctnetlink_glue_build_size(const struct nf_conn *ct) { return 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */ + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */ + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */ + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */ + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */ + nla_total_size(0) /* CTA_PROTOINFO */ + nla_total_size(0) /* CTA_HELP */ + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + ctnetlink_secctx_size(ct) + ctnetlink_acct_size(ct) + ctnetlink_timestamp_size(ct) #if IS_ENABLED(CONFIG_NF_NAT) + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ #endif #ifdef CONFIG_NF_CONNTRACK_MARK + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif #ifdef CONFIG_NF_CONNTRACK_ZONES + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE|CTA_TUPLE_ZONE */ #endif + ctnetlink_proto_size(ct) ; } static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) { const struct nf_conntrack_zone *zone; struct nlattr *nest_parms; zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_ORIG) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_REPL) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_id(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_status(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_timeout(skb, ct, false) < 0) goto nla_put_failure; if (ctnetlink_dump_protoinfo(skb, ct, false) < 0) goto nla_put_failure; if (ctnetlink_dump_acct(skb, ct, IPCTNL_MSG_CT_GET) < 0 || ctnetlink_dump_timestamp(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_helpinfo(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_SECMARK if (ct->secmark && ctnetlink_dump_secctx(skb, ct) < 0) goto nla_put_failure; #endif if (ct->master && ctnetlink_dump_master(skb, ct) < 0) goto nla_put_failure; if ((ct->status & IPS_SEQ_ADJUST) && ctnetlink_dump_ct_seq_adj(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_ct_synproxy(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_MARK if (ctnetlink_dump_mark(skb, ct, true) < 0) goto nla_put_failure; #endif if (ctnetlink_dump_labels(skb, ct) < 0) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static int ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, u_int16_t ct_attr, u_int16_t ct_info_attr) { struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, ct_attr); if (!nest_parms) goto nla_put_failure; if (__ctnetlink_glue_build(skb, ct) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (nla_put_be32(skb, ct_info_attr, htonl(ctinfo))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static int ctnetlink_update_status(struct nf_conn *ct, const struct nlattr * const cda[]) { unsigned int status = ntohl(nla_get_be32(cda[CTA_STATUS])); unsigned long d = ct->status ^ status; if (d & IPS_SEEN_REPLY && !(status & IPS_SEEN_REPLY)) /* SEEN_REPLY bit can only be set */ return -EBUSY; if (d & IPS_ASSURED && !(status & IPS_ASSURED)) /* ASSURED bit can only be set */ return -EBUSY; /* This check is less strict than ctnetlink_change_status() * because callers often flip IPS_EXPECTED bits when sending * an NFQA_CT attribute to the kernel. So ignore the * unchangeable bits but do not error out. Also user programs * are allowed to clear the bits that they are allowed to change. */ __ctnetlink_change_status(ct, status, ~status); return 0; } static int ctnetlink_glue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct) { int err; if (cda[CTA_TIMEOUT]) { err = ctnetlink_change_timeout(ct, cda); if (err < 0) return err; } if (cda[CTA_STATUS]) { err = ctnetlink_update_status(ct, cda); if (err < 0) return err; } if (cda[CTA_HELP]) { err = ctnetlink_change_helper(ct, cda); if (err < 0) return err; } if (cda[CTA_LABELS]) { err = ctnetlink_attach_labels(ct, cda); if (err < 0) return err; } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) { ctnetlink_change_mark(ct, cda); } #endif return 0; } static int ctnetlink_glue_parse(const struct nlattr *attr, struct nf_conn *ct) { struct nlattr *cda[CTA_MAX+1]; int ret; ret = nla_parse_nested_deprecated(cda, CTA_MAX, attr, ct_nla_policy, NULL); if (ret < 0) return ret; return ctnetlink_glue_parse_ct((const struct nlattr **)cda, ct); } static int ctnetlink_glue_exp_parse(const struct nlattr * const *cda, const struct nf_conn *ct, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask) { int err; err = ctnetlink_parse_tuple(cda, tuple, CTA_EXPECT_TUPLE, nf_ct_l3num(ct), NULL); if (err < 0) return err; return ctnetlink_parse_tuple(cda, mask, CTA_EXPECT_MASK, nf_ct_l3num(ct), NULL); } static int ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report) { struct nlattr *cda[CTA_EXPECT_MAX+1]; struct nf_conntrack_tuple tuple, mask; struct nf_conntrack_helper *helper = NULL; struct nf_conntrack_expect *exp; int err; err = nla_parse_nested_deprecated(cda, CTA_EXPECT_MAX, attr, exp_nla_policy, NULL); if (err < 0) return err; err = ctnetlink_glue_exp_parse((const struct nlattr * const *)cda, ct, &tuple, &mask); if (err < 0) return err; if (cda[CTA_EXPECT_HELP_NAME]) { const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper == NULL) return -EOPNOTSUPP; } exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct, helper, &tuple, &mask); if (IS_ERR(exp)) return PTR_ERR(exp); err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); return err; } static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, int diff) { if (!(ct->status & IPS_NAT_MASK)) return; nf_ct_tcp_seqadj_set(skb, ct, ctinfo, diff); } static const struct nfnl_ct_hook ctnetlink_glue_hook = { .build_size = ctnetlink_glue_build_size, .build = ctnetlink_glue_build, .parse = ctnetlink_glue_parse, .attach_expect = ctnetlink_glue_attach_expect, .seq_adjust = ctnetlink_glue_seqadj, }; #endif /* CONFIG_NETFILTER_NETLINK_GLUE_CT */ /*********************************************************************** * EXPECT ***********************************************************************/ static int ctnetlink_exp_dump_tuple(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, u32 type) { struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, type); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, tuple) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int ctnetlink_exp_dump_mask(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple_mask *mask) { const struct nf_conntrack_l4proto *l4proto; struct nf_conntrack_tuple m; struct nlattr *nest_parms; int ret; memset(&m, 0xFF, sizeof(m)); memcpy(&m.src.u3, &mask->src.u3, sizeof(m.src.u3)); m.src.u.all = mask->src.u.all; m.src.l3num = tuple->src.l3num; m.dst.protonum = tuple->dst.protonum; nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK); if (!nest_parms) goto nla_put_failure; rcu_read_lock(); ret = ctnetlink_dump_tuples_ip(skb, &m); if (ret >= 0) { l4proto = nf_ct_l4proto_find(tuple->dst.protonum); ret = ctnetlink_dump_tuples_proto(skb, &m, l4proto); } rcu_read_unlock(); if (unlikely(ret < 0)) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } #if IS_ENABLED(CONFIG_NF_NAT) static const union nf_inet_addr any_addr; #endif static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) { static __read_mostly siphash_key_t exp_id_seed; unsigned long a, b, c, d; net_get_random_once(&exp_id_seed, sizeof(exp_id_seed)); a = (unsigned long)exp; b = (unsigned long)exp->helper; c = (unsigned long)exp->master; d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed); #ifdef CONFIG_64BIT return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed); #else return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed); #endif } static int ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) { struct nf_conn *master = exp->master; long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ; struct nf_conn_help *help; #if IS_ENABLED(CONFIG_NF_NAT) struct nlattr *nest_parms; struct nf_conntrack_tuple nat_tuple = {}; #endif struct nf_ct_helper_expectfn *expfn; if (timeout < 0) timeout = 0; if (ctnetlink_exp_dump_tuple(skb, &exp->tuple, CTA_EXPECT_TUPLE) < 0) goto nla_put_failure; if (ctnetlink_exp_dump_mask(skb, &exp->tuple, &exp->mask) < 0) goto nla_put_failure; if (ctnetlink_exp_dump_tuple(skb, &master->tuplehash[IP_CT_DIR_ORIGINAL].tuple, CTA_EXPECT_MASTER) < 0) goto nla_put_failure; #if IS_ENABLED(CONFIG_NF_NAT) if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) || exp->saved_proto.all) { nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT); if (!nest_parms) goto nla_put_failure; if (nla_put_be32(skb, CTA_EXPECT_NAT_DIR, htonl(exp->dir))) goto nla_put_failure; nat_tuple.src.l3num = nf_ct_l3num(master); nat_tuple.src.u3 = exp->saved_addr; nat_tuple.dst.protonum = nf_ct_protonum(master); nat_tuple.src.u = exp->saved_proto; if (ctnetlink_exp_dump_tuple(skb, &nat_tuple, CTA_EXPECT_NAT_TUPLE) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); } #endif if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) || nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) || nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) || nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class))) goto nla_put_failure; help = nfct_help(master); if (help) { struct nf_conntrack_helper *helper; helper = rcu_dereference(help->helper); if (helper && nla_put_string(skb, CTA_EXPECT_HELP_NAME, helper->name)) goto nla_put_failure; } expfn = nf_ct_helper_expectfn_find_by_symbol(exp->expectfn); if (expfn != NULL && nla_put_string(skb, CTA_EXPECT_FN, expfn->name)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_exp_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int event, const struct nf_conntrack_expect *exp) { struct nlmsghdr *nlh; unsigned int flags = portid ? NLM_F_MULTI : 0; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, exp->tuple.src.l3num, NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; if (ctnetlink_exp_dump_expect(skb, exp) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: nlmsg_cancel(skb, nlh); return -1; } #ifdef CONFIG_NF_CONNTRACK_EVENTS static int ctnetlink_expect_event(unsigned int events, const struct nf_exp_event *item) { struct nf_conntrack_expect *exp = item->exp; struct net *net = nf_ct_exp_net(exp); struct nlmsghdr *nlh; struct sk_buff *skb; unsigned int type, group; int flags = 0; if (events & (1 << IPEXP_DESTROY)) { type = IPCTNL_MSG_EXP_DELETE; group = NFNLGRP_CONNTRACK_EXP_DESTROY; } else if (events & (1 << IPEXP_NEW)) { type = IPCTNL_MSG_EXP_NEW; flags = NLM_F_CREATE|NLM_F_EXCL; group = NFNLGRP_CONNTRACK_EXP_NEW; } else return 0; if (!item->report && !nfnetlink_has_listeners(net, group)) return 0; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (skb == NULL) goto errout; type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, type); nlh = nfnl_msg_put(skb, item->portid, 0, type, flags, exp->tuple.src.l3num, NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; if (ctnetlink_exp_dump_expect(skb, exp) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); nlmsg_failure: kfree_skb(skb); errout: nfnetlink_set_err(net, 0, 0, -ENOBUFS); return 0; } #endif static int ctnetlink_exp_done(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_expect_put((struct nf_conntrack_expect *)cb->args[1]); return 0; } static int ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; rcu_read_lock(); last = (struct nf_conntrack_expect *)cb->args[1]; for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) { restart: hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]], hnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; if (!net_eq(nf_ct_net(exp->master), net)) continue; if (cb->args[1]) { if (exp != last) continue; cb->args[1] = 0; } if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { if (!refcount_inc_not_zero(&exp->use)) continue; cb->args[1] = (unsigned long)exp; goto out; } } if (cb->args[1]) { cb->args[1] = 0; goto restart; } } out: rcu_read_unlock(); if (last) nf_ct_expect_put(last); return skb->len; } static int ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nf_conn *ct = cb->data; struct nf_conn_help *help = nfct_help(ct); u_int8_t l3proto = nfmsg->nfgen_family; if (cb->args[0]) return 0; rcu_read_lock(); last = (struct nf_conntrack_expect *)cb->args[1]; restart: hlist_for_each_entry_rcu(exp, &help->expectations, lnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; if (cb->args[1]) { if (exp != last) continue; cb->args[1] = 0; } if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { if (!refcount_inc_not_zero(&exp->use)) continue; cb->args[1] = (unsigned long)exp; goto out; } } if (cb->args[1]) { cb->args[1] = 0; goto restart; } cb->args[0] = 1; out: rcu_read_unlock(); if (last) nf_ct_expect_put(last); return skb->len; } static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { int err; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conntrack_zone zone; struct netlink_dump_control c = { .dump = ctnetlink_exp_ct_dump_table, .done = ctnetlink_exp_done, }; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3, NULL); if (err < 0) return err; err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; h = nf_conntrack_find_get(net, &zone, &tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); /* No expectation linked to this connection tracking. */ if (!nfct_help(ct)) { nf_ct_put(ct); return 0; } c.data = ct; err = netlink_dump_start(ctnl, skb, nlh, &c); nf_ct_put(ct); return err; } static int ctnetlink_get_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nf_conntrack_zone zone; struct sk_buff *skb2; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { if (cda[CTA_EXPECT_MASTER]) return ctnetlink_dump_exp_ct(info->net, info->sk, skb, info->nlh, cda, info->extack); else { struct netlink_dump_control c = { .dump = ctnetlink_exp_dump_table, .done = ctnetlink_exp_done, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } } err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; if (cda[CTA_EXPECT_TUPLE]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); else if (cda[CTA_EXPECT_MASTER]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3, NULL); else return -EINVAL; if (err < 0) return err; exp = nf_ct_expect_find_get(info->net, &zone, &tuple); if (!exp) return -ENOENT; if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } } skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb2) { nf_ct_expect_put(exp); return -ENOMEM; } rcu_read_lock(); err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp); rcu_read_unlock(); nf_ct_expect_put(exp); if (err <= 0) { kfree_skb(skb2); return -ENOMEM; } return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static bool expect_iter_name(struct nf_conntrack_expect *exp, void *data) { const struct nf_conn_help *m_help; const char *name = data; m_help = nfct_help(exp->master); return strcmp(m_help->helper->name, name) == 0; } static bool expect_iter_all(struct nf_conntrack_expect *exp, void *data) { return true; } static int ctnetlink_del_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; int err; if (cda[CTA_EXPECT_TUPLE]) { /* delete a single expect by tuple */ err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); if (err < 0) return err; /* bump usage count to 2 */ exp = nf_ct_expect_find_get(info->net, &zone, &tuple); if (!exp) return -ENOENT; if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } } /* after list removal, usage count == 1 */ spin_lock_bh(&nf_conntrack_expect_lock); if (del_timer(&exp->timeout)) { nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); nf_ct_expect_put(exp); } spin_unlock_bh(&nf_conntrack_expect_lock); /* have to put what we 'get' above. * after this line usage count == 0 */ nf_ct_expect_put(exp); } else if (cda[CTA_EXPECT_HELP_NAME]) { char *name = nla_data(cda[CTA_EXPECT_HELP_NAME]); nf_ct_expect_iterate_net(info->net, expect_iter_name, name, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); } else { /* This basically means we have to flush everything*/ nf_ct_expect_iterate_net(info->net, expect_iter_all, NULL, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); } return 0; } static int ctnetlink_change_expect(struct nf_conntrack_expect *x, const struct nlattr * const cda[]) { if (cda[CTA_EXPECT_TIMEOUT]) { if (!del_timer(&x->timeout)) return -ETIME; x->timeout.expires = jiffies + ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ; add_timer(&x->timeout); } return 0; } #if IS_ENABLED(CONFIG_NF_NAT) static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { [CTA_EXPECT_NAT_DIR] = { .type = NLA_U32 }, [CTA_EXPECT_NAT_TUPLE] = { .type = NLA_NESTED }, }; #endif static int ctnetlink_parse_expect_nat(const struct nlattr *attr, struct nf_conntrack_expect *exp, u_int8_t u3) { #if IS_ENABLED(CONFIG_NF_NAT) struct nlattr *tb[CTA_EXPECT_NAT_MAX+1]; struct nf_conntrack_tuple nat_tuple = {}; int err; err = nla_parse_nested_deprecated(tb, CTA_EXPECT_NAT_MAX, attr, exp_nat_nla_policy, NULL); if (err < 0) return err; if (!tb[CTA_EXPECT_NAT_DIR] || !tb[CTA_EXPECT_NAT_TUPLE]) return -EINVAL; err = ctnetlink_parse_tuple((const struct nlattr * const *)tb, &nat_tuple, CTA_EXPECT_NAT_TUPLE, u3, NULL); if (err < 0) return err; exp->saved_addr = nat_tuple.src.u3; exp->saved_proto = nat_tuple.src.u; exp->dir = ntohl(nla_get_be32(tb[CTA_EXPECT_NAT_DIR])); return 0; #else return -EOPNOTSUPP; #endif } static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, struct nf_conntrack_helper *helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask) { u_int32_t class = 0; struct nf_conntrack_expect *exp; struct nf_conn_help *help; int err; help = nfct_help(ct); if (!help) return ERR_PTR(-EOPNOTSUPP); if (cda[CTA_EXPECT_CLASS] && helper) { class = ntohl(nla_get_be32(cda[CTA_EXPECT_CLASS])); if (class > helper->expect_class_max) return ERR_PTR(-EINVAL); } exp = nf_ct_expect_alloc(ct); if (!exp) return ERR_PTR(-ENOMEM); if (cda[CTA_EXPECT_FLAGS]) { exp->flags = ntohl(nla_get_be32(cda[CTA_EXPECT_FLAGS])); exp->flags &= ~NF_CT_EXPECT_USERSPACE; } else { exp->flags = 0; } if (cda[CTA_EXPECT_FN]) { const char *name = nla_data(cda[CTA_EXPECT_FN]); struct nf_ct_helper_expectfn *expfn; expfn = nf_ct_helper_expectfn_find_by_name(name); if (expfn == NULL) { err = -EINVAL; goto err_out; } exp->expectfn = expfn->expectfn; } else exp->expectfn = NULL; exp->class = class; exp->master = ct; exp->helper = helper; exp->tuple = *tuple; exp->mask.src.u3 = mask->src.u3; exp->mask.src.u.all = mask->src.u.all; if (cda[CTA_EXPECT_NAT]) { err = ctnetlink_parse_expect_nat(cda[CTA_EXPECT_NAT], exp, nf_ct_l3num(ct)); if (err < 0) goto err_out; } return exp; err_out: nf_ct_expect_put(exp); return ERR_PTR(err); } static int ctnetlink_create_expect(struct net *net, const struct nf_conntrack_zone *zone, const struct nlattr * const cda[], u_int8_t u3, u32 portid, int report) { struct nf_conntrack_tuple tuple, mask, master_tuple; struct nf_conntrack_tuple_hash *h = NULL; struct nf_conntrack_helper *helper = NULL; struct nf_conntrack_expect *exp; struct nf_conn *ct; int err; /* caller guarantees that those three CTA_EXPECT_* exist */ err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK, u3, NULL); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER, u3, NULL); if (err < 0) return err; /* Look for master conntrack of this expectation */ h = nf_conntrack_find_get(net, zone, &master_tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); rcu_read_lock(); if (cda[CTA_EXPECT_HELP_NAME]) { const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); helper = __nf_conntrack_helper_find(helpname, u3, nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { err = -EOPNOTSUPP; goto err_ct; } rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, u3, nf_ct_protonum(ct)); if (helper) { err = -EAGAIN; goto err_rcu; } rcu_read_unlock(); #endif err = -EOPNOTSUPP; goto err_ct; } } exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask); if (IS_ERR(exp)) { err = PTR_ERR(exp); goto err_rcu; } err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); err_rcu: rcu_read_unlock(); err_ct: nf_ct_put(ct); return err; } static int ctnetlink_new_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nf_conntrack_zone zone; int err; if (!cda[CTA_EXPECT_TUPLE] || !cda[CTA_EXPECT_MASK] || !cda[CTA_EXPECT_MASTER]) return -EINVAL; err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); if (err < 0) return err; spin_lock_bh(&nf_conntrack_expect_lock); exp = __nf_ct_expect_find(info->net, &zone, &tuple); if (!exp) { spin_unlock_bh(&nf_conntrack_expect_lock); err = -ENOENT; if (info->nlh->nlmsg_flags & NLM_F_CREATE) { err = ctnetlink_create_expect(info->net, &zone, cda, u3, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); } return err; } err = -EEXIST; if (!(info->nlh->nlmsg_flags & NLM_F_EXCL)) err = ctnetlink_change_expect(exp, cda); spin_unlock_bh(&nf_conntrack_expect_lock); return err; } static int ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_EXP_GET_STATS_CPU); nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, NFNETLINK_V0, htons(cpu)); if (!nlh) goto nlmsg_failure; if (nla_put_be32(skb, CTA_STATS_EXP_NEW, htonl(st->expect_new)) || nla_put_be32(skb, CTA_STATS_EXP_CREATE, htonl(st->expect_create)) || nla_put_be32(skb, CTA_STATS_EXP_DELETE, htonl(st->expect_delete))) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nla_put_failure: nlmsg_failure: nlmsg_cancel(skb, nlh); return -1; } static int ctnetlink_exp_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) { int cpu; struct net *net = sock_net(skb->sk); if (cb->args[0] == nr_cpu_ids) return 0; for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { const struct ip_conntrack_stat *st; if (!cpu_possible(cpu)) continue; st = per_cpu_ptr(net->ct.stat, cpu); if (ctnetlink_exp_stat_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cpu, st) < 0) break; } cb->args[0] = cpu; return skb->len; } static int ctnetlink_stat_exp_cpu(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_exp_stat_cpu_dump, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } return 0; } #ifdef CONFIG_NF_CONNTRACK_EVENTS static struct nf_ct_event_notifier ctnl_notifier = { .ct_event = ctnetlink_conntrack_event, .exp_event = ctnetlink_expect_event, }; #endif static const struct nfnl_callback ctnl_cb[IPCTNL_MSG_MAX] = { [IPCTNL_MSG_CT_NEW] = { .call = ctnetlink_new_conntrack, .type = NFNL_CB_MUTEX, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_GET] = { .call = ctnetlink_get_conntrack, .type = NFNL_CB_MUTEX, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_DELETE] = { .call = ctnetlink_del_conntrack, .type = NFNL_CB_MUTEX, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_GET_CTRZERO] = { .call = ctnetlink_get_conntrack, .type = NFNL_CB_MUTEX, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_GET_STATS_CPU] = { .call = ctnetlink_stat_ct_cpu, .type = NFNL_CB_MUTEX, }, [IPCTNL_MSG_CT_GET_STATS] = { .call = ctnetlink_stat_ct, .type = NFNL_CB_MUTEX, }, [IPCTNL_MSG_CT_GET_DYING] = { .call = ctnetlink_get_ct_dying, .type = NFNL_CB_MUTEX, }, [IPCTNL_MSG_CT_GET_UNCONFIRMED] = { .call = ctnetlink_get_ct_unconfirmed, .type = NFNL_CB_MUTEX, }, }; static const struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = { [IPCTNL_MSG_EXP_GET] = { .call = ctnetlink_get_expect, .type = NFNL_CB_MUTEX, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, [IPCTNL_MSG_EXP_NEW] = { .call = ctnetlink_new_expect, .type = NFNL_CB_MUTEX, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, [IPCTNL_MSG_EXP_DELETE] = { .call = ctnetlink_del_expect, .type = NFNL_CB_MUTEX, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, [IPCTNL_MSG_EXP_GET_STATS_CPU] = { .call = ctnetlink_stat_exp_cpu, .type = NFNL_CB_MUTEX, }, }; static const struct nfnetlink_subsystem ctnl_subsys = { .name = "conntrack", .subsys_id = NFNL_SUBSYS_CTNETLINK, .cb_count = IPCTNL_MSG_MAX, .cb = ctnl_cb, }; static const struct nfnetlink_subsystem ctnl_exp_subsys = { .name = "conntrack_expect", .subsys_id = NFNL_SUBSYS_CTNETLINK_EXP, .cb_count = IPCTNL_MSG_EXP_MAX, .cb = ctnl_exp_cb, }; MODULE_ALIAS("ip_conntrack_netlink"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); static int __net_init ctnetlink_net_init(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_EVENTS nf_conntrack_register_notifier(net, &ctnl_notifier); #endif return 0; } static void ctnetlink_net_pre_exit(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_EVENTS nf_conntrack_unregister_notifier(net); #endif } static struct pernet_operations ctnetlink_net_ops = { .init = ctnetlink_net_init, .pre_exit = ctnetlink_net_pre_exit, }; static int __init ctnetlink_init(void) { int ret; ret = nfnetlink_subsys_register(&ctnl_subsys); if (ret < 0) { pr_err("ctnetlink_init: cannot register with nfnetlink.\n"); goto err_out; } ret = nfnetlink_subsys_register(&ctnl_exp_subsys); if (ret < 0) { pr_err("ctnetlink_init: cannot register exp with nfnetlink.\n"); goto err_unreg_subsys; } ret = register_pernet_subsys(&ctnetlink_net_ops); if (ret < 0) { pr_err("ctnetlink_init: cannot register pernet operations\n"); goto err_unreg_exp_subsys; } #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT /* setup interaction between nf_queue and nf_conntrack_netlink. */ RCU_INIT_POINTER(nfnl_ct_hook, &ctnetlink_glue_hook); #endif return 0; err_unreg_exp_subsys: nfnetlink_subsys_unregister(&ctnl_exp_subsys); err_unreg_subsys: nfnetlink_subsys_unregister(&ctnl_subsys); err_out: return ret; } static void __exit ctnetlink_exit(void) { unregister_pernet_subsys(&ctnetlink_net_ops); nfnetlink_subsys_unregister(&ctnl_exp_subsys); nfnetlink_subsys_unregister(&ctnl_subsys); #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT RCU_INIT_POINTER(nfnl_ct_hook, NULL); #endif synchronize_rcu(); } module_init(ctnetlink_init); module_exit(ctnetlink_exit); |
| 68 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * NET Generic infrastructure for INET connection oriented protocols. * * Definitions for inet_connection_sock * * Authors: Many people, see the TCP sources * * From code originally in TCP */ #ifndef _INET_CONNECTION_SOCK_H #define _INET_CONNECTION_SOCK_H #include <linux/compiler.h> #include <linux/string.h> #include <linux/timer.h> #include <linux/poll.h> #include <linux/kernel.h> #include <linux/sockptr.h> #include <linux/android_kabi.h> #include <net/inet_sock.h> #include <net/request_sock.h> /* Cancel timers, when they are not required. */ #undef INET_CSK_CLEAR_TIMERS struct inet_bind_bucket; struct tcp_congestion_ops; /* * Pointers to address related TCP functions * (i.e. things that depend on the address family) */ struct inet_connection_sock_af_ops { int (*queue_xmit)(struct sock *sk, struct sk_buff *skb, struct flowi *fl); void (*send_check)(struct sock *sk, struct sk_buff *skb); int (*rebuild_header)(struct sock *sk); void (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb); int (*conn_request)(struct sock *sk, struct sk_buff *skb); struct sock *(*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); u16 net_header_len; u16 net_frag_header_len; u16 sockaddr_len; int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); void (*addr2sockaddr)(struct sock *sk, struct sockaddr *); void (*mtu_reduced)(struct sock *sk); ANDROID_KABI_RESERVE(1); }; /** inet_connection_sock - INET connection oriented sock * * @icsk_accept_queue: FIFO of established children * @icsk_bind_hash: Bind node * @icsk_timeout: Timeout * @icsk_retransmit_timer: Resend (no ack) * @icsk_rto: Retransmit timeout * @icsk_pmtu_cookie Last pmtu seen by socket * @icsk_ca_ops Pluggable congestion control hook * @icsk_af_ops Operations which are AF_INET{4,6} specific * @icsk_ulp_ops Pluggable ULP control hook * @icsk_ulp_data ULP private data * @icsk_clean_acked Clean acked data hook * @icsk_listen_portaddr_node hash to the portaddr listener hashtable * @icsk_ca_state: Congestion control state * @icsk_retransmits: Number of unrecovered [RTO] timeouts * @icsk_pending: Scheduled timer event * @icsk_backoff: Backoff * @icsk_syn_retries: Number of allowed SYN (or equivalent) retries * @icsk_probes_out: unanswered 0 window probes * @icsk_ext_hdr_len: Network protocol overhead (IP/IPv6 options) * @icsk_ack: Delayed ACK control data * @icsk_mtup; MTU probing control data * @icsk_probes_tstamp: Probe timestamp (cleared by non-zero window ack) * @icsk_user_timeout: TCP_USER_TIMEOUT value */ struct inet_connection_sock { /* inet_sock has to be the first member! */ struct inet_sock icsk_inet; struct request_sock_queue icsk_accept_queue; struct inet_bind_bucket *icsk_bind_hash; unsigned long icsk_timeout; struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; __u32 icsk_rto; __u32 icsk_rto_min; __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; const struct tcp_ulp_ops *icsk_ulp_ops; void __rcu *icsk_ulp_data; void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq); struct hlist_node icsk_listen_portaddr_node; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); __u8 icsk_ca_state:5, icsk_ca_initialized:1, icsk_ca_setsockopt:1, icsk_ca_dst_locked:1; __u8 icsk_retransmits; __u8 icsk_pending; __u8 icsk_backoff; __u8 icsk_syn_retries; __u8 icsk_probes_out; __u16 icsk_ext_hdr_len; struct { __u8 pending; /* ACK is pending */ __u8 quick; /* Scheduled number of quick acks */ __u8 pingpong; /* The session is interactive */ __u8 retry; /* Number of attempts */ __u32 ato; /* Predicted tick of soft clock */ unsigned long timeout; /* Currently scheduled timeout */ __u32 lrcvtime; /* timestamp of last received data packet */ __u16 last_seg_size; /* Size of last incoming segment */ __u16 rcv_mss; /* MSS used for delayed ACK decisions */ } icsk_ack; struct { /* Range of MTUs to search */ int search_high; int search_low; /* Information on the current probe. */ u32 probe_size:31, /* Is the MTUP feature enabled for this connection? */ enabled:1; u32 probe_timestamp; } icsk_mtup; u32 icsk_probes_tstamp; u32 icsk_user_timeout; ANDROID_KABI_RESERVE(1); u64 icsk_ca_priv[104 / sizeof(u64)]; #define ICSK_CA_PRIV_SIZE sizeof_field(struct inet_connection_sock, icsk_ca_priv) }; #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ #define ICSK_TIME_DACK 2 /* Delayed ack timer */ #define ICSK_TIME_PROBE0 3 /* Zero window probe timer */ #define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */ #define ICSK_TIME_REO_TIMEOUT 6 /* Reordering timer */ static inline struct inet_connection_sock *inet_csk(const struct sock *sk) { return (struct inet_connection_sock *)sk; } static inline void *inet_csk_ca(const struct sock *sk) { return (void *)inet_csk(sk)->icsk_ca_priv; } struct sock *inet_csk_clone_lock(const struct sock *sk, const struct request_sock *req, const gfp_t priority); enum inet_csk_ack_state_t { ICSK_ACK_SCHED = 1, ICSK_ACK_TIMER = 2, ICSK_ACK_PUSHED = 4, ICSK_ACK_PUSHED2 = 8, ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */ }; void inet_csk_init_xmit_timers(struct sock *sk, void (*retransmit_handler)(struct timer_list *), void (*delack_handler)(struct timer_list *), void (*keepalive_handler)(struct timer_list *)); void inet_csk_clear_xmit_timers(struct sock *sk); void inet_csk_clear_xmit_timers_sync(struct sock *sk); static inline void inet_csk_schedule_ack(struct sock *sk) { inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_SCHED; } static inline int inet_csk_ack_scheduled(const struct sock *sk) { return inet_csk(sk)->icsk_ack.pending & ICSK_ACK_SCHED; } static inline void inet_csk_delack_init(struct sock *sk) { memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack)); } void inet_csk_delete_keepalive_timer(struct sock *sk); void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout); static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) { struct inet_connection_sock *icsk = inet_csk(sk); if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) { icsk->icsk_pending = 0; #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_retransmit_timer); #endif } else if (what == ICSK_TIME_DACK) { icsk->icsk_ack.pending = 0; icsk->icsk_ack.retry = 0; #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_delack_timer); #endif } else { pr_debug("inet_csk BUG: unknown timer value\n"); } } /* * Reset the retransmission timer */ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, unsigned long when, const unsigned long max_when) { struct inet_connection_sock *icsk = inet_csk(sk); if (when > max_when) { pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n", sk, what, when, (void *)_THIS_IP_); when = max_when; } if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 || what == ICSK_TIME_LOSS_PROBE || what == ICSK_TIME_REO_TIMEOUT) { icsk->icsk_pending = what; icsk->icsk_timeout = jiffies + when; sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); } else if (what == ICSK_TIME_DACK) { icsk->icsk_ack.pending |= ICSK_ACK_TIMER; icsk->icsk_ack.timeout = jiffies + when; sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout); } else { pr_debug("inet_csk BUG: unknown timer value\n"); } } static inline unsigned long inet_csk_rto_backoff(const struct inet_connection_sock *icsk, unsigned long max_when) { u64 when = (u64)icsk->icsk_rto << icsk->icsk_backoff; return (unsigned long)min_t(u64, when, max_when); } struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern); int inet_csk_get_port(struct sock *sk, unsigned short snum); struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req); struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req); struct sock *inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, struct sock *child); void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, bool own_req); static inline void inet_csk_reqsk_queue_added(struct sock *sk) { reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue); } static inline int inet_csk_reqsk_queue_len(const struct sock *sk) { return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue); } static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) { return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog); } bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) { /* The below has to be done to allow calling inet_csk_destroy_sock */ sock_set_flag(sk, SOCK_DEAD); this_cpu_inc(*sk->sk_prot->orphan_count); } void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); /* * LISTEN is a special case for poll.. */ static inline __poll_t inet_csk_listen_poll(const struct sock *sk) { return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ? (EPOLLIN | EPOLLRDNORM) : 0; } int inet_csk_listen_start(struct sock *sk, int backlog); void inet_csk_listen_stop(struct sock *sk); void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); /* update the fast reuse flag when adding a socket */ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, struct sock *sk); struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu); #define TCP_PINGPONG_THRESH 1 static inline void inet_csk_enter_pingpong_mode(struct sock *sk) { inet_csk(sk)->icsk_ack.pingpong = TCP_PINGPONG_THRESH; } static inline void inet_csk_exit_pingpong_mode(struct sock *sk) { inet_csk(sk)->icsk_ack.pingpong = 0; } static inline bool inet_csk_in_pingpong_mode(struct sock *sk) { return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; } static inline bool inet_csk_has_ulp(struct sock *sk) { return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops; } static inline void inet_init_csk_locks(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); spin_lock_init(&icsk->icsk_accept_queue.rskq_lock); spin_lock_init(&icsk->icsk_accept_queue.fastopenq.lock); } #endif /* _INET_CONNECTION_SOCK_H */ |
| 931 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Global definitions for the ARP (RFC 826) protocol. * * Version: @(#)if_arp.h 1.0.1 04/16/93 * * Authors: Original taken from Berkeley UNIX 4.3, (c) UCB 1986-1988 * Portions taken from the KA9Q/NOS (v2.00m PA0GRI) source. * Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, * Jonathan Layes <layes@loran.com> * Arnaldo Carvalho de Melo <acme@conectiva.com.br> ARPHRD_HWX25 */ #ifndef _LINUX_IF_ARP_H #define _LINUX_IF_ARP_H #include <linux/skbuff.h> #include <uapi/linux/if_arp.h> static inline struct arphdr *arp_hdr(const struct sk_buff *skb) { return (struct arphdr *)skb_network_header(skb); } static inline unsigned int arp_hdr_len(const struct net_device *dev) { switch (dev->type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) case ARPHRD_IEEE1394: /* ARP header, device address and 2 IP addresses */ return sizeof(struct arphdr) + dev->addr_len + sizeof(u32) * 2; #endif default: /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ return sizeof(struct arphdr) + (dev->addr_len + sizeof(u32)) * 2; } } static inline bool dev_is_mac_header_xmit(const struct net_device *dev) { switch (dev->type) { case ARPHRD_TUNNEL: case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: case ARPHRD_RAWIP: case ARPHRD_PIMREG: /* PPP adds its l2 header automatically in ppp_start_xmit(). * This makes it look like an l3 device to __bpf_redirect() and tcf_mirred_init(). */ case ARPHRD_PPP: return false; default: return true; } } #endif /* _LINUX_IF_ARP_H */ |
| 1355 1355 1355 1355 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/userfaultfd.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * Copyright (C) 2008-2009 Red Hat, Inc. * Copyright (C) 2015 Red Hat, Inc. * * Some part derived from fs/eventfd.c (anon inode setup) and * mm/ksm.c (mm hashing). */ #include <linux/list.h> #include <linux/hashtable.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/file.h> #include <linux/bug.h> #include <linux/anon_inodes.h> #include <linux/syscalls.h> #include <linux/userfaultfd_k.h> #include <linux/mempolicy.h> #include <linux/ioctl.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/pgsize_migration.h> int sysctl_unprivileged_userfaultfd __read_mostly; static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; /* * Start with fault_pending_wqh and fault_wqh so they're more likely * to be in the same cacheline. * * Locking order: * fd_wqh.lock * fault_pending_wqh.lock * fault_wqh.lock * event_wqh.lock * * To avoid deadlocks, IRQs must be disabled when taking any of the above locks, * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's * also taken in IRQ context. */ struct userfaultfd_ctx { /* waitqueue head for the pending (i.e. not read) userfaults */ wait_queue_head_t fault_pending_wqh; /* waitqueue head for the userfaults */ wait_queue_head_t fault_wqh; /* waitqueue head for the pseudo fd to wakeup poll/read */ wait_queue_head_t fd_wqh; /* waitqueue head for events */ wait_queue_head_t event_wqh; /* a refile sequence protected by fault_pending_wqh lock */ seqcount_spinlock_t refile_seq; /* pseudo fd refcounting */ refcount_t refcount; /* userfaultfd syscall flags */ unsigned int flags; /* features requested from the userspace */ unsigned int features; /* released */ bool released; /* memory mappings are changing because of non-cooperative event */ atomic_t mmap_changing; /* mm with one ore more vmas attached to this userfaultfd_ctx */ struct mm_struct *mm; struct rcu_head rcu_head; }; struct userfaultfd_fork_ctx { struct userfaultfd_ctx *orig; struct userfaultfd_ctx *new; struct list_head list; }; struct userfaultfd_unmap_ctx { struct userfaultfd_ctx *ctx; unsigned long start; unsigned long end; struct list_head list; }; struct userfaultfd_wait_queue { struct uffd_msg msg; wait_queue_entry_t wq; struct userfaultfd_ctx *ctx; bool waken; }; struct userfaultfd_wake_range { unsigned long start; unsigned long len; }; /* internal indication that UFFD_API ioctl was successfully executed */ #define UFFD_FEATURE_INITIALIZED (1u << 31) static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx) { return ctx->features & UFFD_FEATURE_INITIALIZED; } static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode, int wake_flags, void *key) { struct userfaultfd_wake_range *range = key; int ret; struct userfaultfd_wait_queue *uwq; unsigned long start, len; uwq = container_of(wq, struct userfaultfd_wait_queue, wq); ret = 0; /* len == 0 means wake all */ start = range->start; len = range->len; if (len && (start > uwq->msg.arg.pagefault.address || start + len <= uwq->msg.arg.pagefault.address)) goto out; WRITE_ONCE(uwq->waken, true); /* * The Program-Order guarantees provided by the scheduler * ensure uwq->waken is visible before the task is woken. */ ret = wake_up_state(wq->private, mode); if (ret) { /* * Wake only once, autoremove behavior. * * After the effect of list_del_init is visible to the other * CPUs, the waitqueue may disappear from under us, see the * !list_empty_careful() in handle_userfault(). * * try_to_wake_up() has an implicit smp_mb(), and the * wq->private is read before calling the extern function * "wake_up_state" (which in turns calls try_to_wake_up). */ list_del_init(&wq->entry); } out: return ret; } /** * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to the userfaultfd context. */ static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx) { refcount_inc(&ctx->refcount); } static void __free_userfaultfd_ctx(struct rcu_head *head) { struct userfaultfd_ctx *ctx = container_of(head, struct userfaultfd_ctx, rcu_head); kmem_cache_free(userfaultfd_ctx_cachep, ctx); } /** * userfaultfd_ctx_put - Releases a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to userfaultfd context. * * The userfaultfd context reference must have been previously acquired either * with userfaultfd_ctx_get() or userfaultfd_ctx_fdget(). */ static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx) { if (refcount_dec_and_test(&ctx->refcount)) { VM_BUG_ON(spin_is_locked(&ctx->fault_pending_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fault_wqh)); VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->event_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fd_wqh)); mmdrop(ctx->mm); call_rcu(&ctx->rcu_head, __free_userfaultfd_ctx); } } static inline void msg_init(struct uffd_msg *msg) { BUILD_BUG_ON(sizeof(struct uffd_msg) != 32); /* * Must use memset to zero out the paddings or kernel data is * leaked to userland. */ memset(msg, 0, sizeof(struct uffd_msg)); } static inline struct uffd_msg userfault_msg(unsigned long address, unsigned int flags, unsigned long reason, unsigned int features) { struct uffd_msg msg; msg_init(&msg); msg.event = UFFD_EVENT_PAGEFAULT; msg.arg.pagefault.address = address; /* * These flags indicate why the userfault occurred: * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault. * - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault. * - Neither of these flags being set indicates a MISSING fault. * * Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write * fault. Otherwise, it was a read fault. */ if (flags & FAULT_FLAG_WRITE) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE; if (reason & VM_UFFD_WP) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; if (reason & VM_UFFD_MINOR) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR; if (features & UFFD_FEATURE_THREAD_ID) msg.arg.pagefault.feat.ptid = task_pid_vnr(current); return msg; } #ifdef CONFIG_HUGETLB_PAGE /* * Same functionality as userfaultfd_must_wait below with modifications for * hugepmd ranges. */ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, struct vm_area_struct *vma, unsigned long address, unsigned long flags, unsigned long reason) { struct mm_struct *mm = ctx->mm; pte_t *ptep, pte; bool ret = true; mmap_assert_locked(mm); ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); if (!ptep) goto out; ret = false; pte = huge_ptep_get(ptep); /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. */ if (huge_pte_none(pte)) ret = true; if (!huge_pte_write(pte) && (reason & VM_UFFD_WP)) ret = true; out: return ret; } #else static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, struct vm_area_struct *vma, unsigned long address, unsigned long flags, unsigned long reason) { return false; /* should never get here */ } #endif /* CONFIG_HUGETLB_PAGE */ /* * Verify the pagetables are still not ok after having reigstered into * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any * userfault that has already been resolved, if userfaultfd_read and * UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different * threads. */ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, unsigned long address, unsigned long flags, unsigned long reason) { struct mm_struct *mm = ctx->mm; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd, _pmd; pte_t *pte; bool ret = true; mmap_assert_locked(mm); pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); /* * READ_ONCE must function as a barrier with narrower scope * and it must be equivalent to: * _pmd = *pmd; barrier(); * * This is to deal with the instability (as in * pmd_trans_unstable) of the pmd. */ _pmd = READ_ONCE(*pmd); if (pmd_none(_pmd)) goto out; ret = false; if (!pmd_present(_pmd)) goto out; if (pmd_trans_huge(_pmd)) { if (!pmd_write(_pmd) && (reason & VM_UFFD_WP)) ret = true; goto out; } /* * the pmd is stable (as in !pmd_trans_unstable) so we can re-read it * and use the standard pte_offset_map() instead of parsing _pmd. */ pte = pte_offset_map(pmd, address); /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. */ if (pte_none(*pte)) ret = true; if (!pte_write(*pte) && (reason & VM_UFFD_WP)) ret = true; pte_unmap(pte); out: return ret; } static inline unsigned int userfaultfd_get_blocking_state(unsigned int flags) { if (flags & FAULT_FLAG_INTERRUPTIBLE) return TASK_INTERRUPTIBLE; if (flags & FAULT_FLAG_KILLABLE) return TASK_KILLABLE; return TASK_UNINTERRUPTIBLE; } #ifdef CONFIG_SPECULATIVE_PAGE_FAULT bool userfaultfd_using_sigbus(struct vm_area_struct *vma, unsigned long seq) { bool ret = false; /* * Do it inside RCU section to ensure that the ctx doesn't * disappear under us. */ rcu_read_lock(); /* * Ensure that we are not looking at dangling pointer to * userfaultfd_ctx, which could happen if userfaultfd_release() is * called after vma is copied. */ if (mmap_seq_read_check(vma->vm_mm, seq, SPF_ABORT_USERFAULTFD)) { struct userfaultfd_ctx *ctx; ctx = rcu_dereference(vma->vm_userfaultfd_ctx.ctx); ret = ctx && (ctx->features & UFFD_FEATURE_SIGBUS); } rcu_read_unlock(); return ret; } #endif /* * The locking rules involved in returning VM_FAULT_RETRY depending on * FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and * FAULT_FLAG_KILLABLE are not straightforward. The "Caution" * recommendation in __lock_page_or_retry is not an understatement. * * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_lock must be released * before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is * not set. * * If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not * set, VM_FAULT_RETRY can still be returned if and only if there are * fatal_signal_pending()s, and the mmap_lock must be released before * returning it. */ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) { struct mm_struct *mm = vmf->vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue uwq; vm_fault_t ret = VM_FAULT_SIGBUS; bool must_wait; unsigned int blocking_state; /* * We don't do userfault handling for the final child pid update. * * We also don't do userfault handling during * coredumping. hugetlbfs has the special * follow_hugetlb_page() to skip missing pages in the * FOLL_DUMP case, anon memory also checks for FOLL_DUMP with * the no_page_table() helper in follow_page_mask(), but the * shmem_vm_ops->fault method is invoked even during * coredumping without mmap_lock and it ends up here. */ if (current->flags & (PF_EXITING|PF_DUMPCORE)) goto out; /* * Coredumping runs without mmap_lock so we can only check that * the mmap_lock is held, if PF_DUMPCORE was not set. */ mmap_assert_locked(mm); ctx = rcu_dereference_protected(vmf->vma->vm_userfaultfd_ctx.ctx, lockdep_is_held(&mm->mmap_lock)); if (!ctx) goto out; BUG_ON(ctx->mm != mm); /* Any unrecognized flag is a bug. */ VM_BUG_ON(reason & ~__VM_UFFD_FLAGS); /* 0 or > 1 flags set is a bug; we expect exactly 1. */ VM_BUG_ON(!reason || (reason & (reason - 1))); if (ctx->features & UFFD_FEATURE_SIGBUS) goto out; if ((vmf->flags & FAULT_FLAG_USER) == 0 && ctx->flags & UFFD_USER_MODE_ONLY) { printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd " "sysctl knob to 1 if kernel faults must be handled " "without obtaining CAP_SYS_PTRACE capability\n"); goto out; } /* * If it's already released don't get it. This avoids to loop * in __get_user_pages if userfaultfd_release waits on the * caller of handle_userfault to release the mmap_lock. */ if (unlikely(READ_ONCE(ctx->released))) { /* * Don't return VM_FAULT_SIGBUS in this case, so a non * cooperative manager can close the uffd after the * last UFFDIO_COPY, without risking to trigger an * involuntary SIGBUS if the process was starting the * userfaultfd while the userfaultfd was still armed * (but after the last UFFDIO_COPY). If the uffd * wasn't already closed when the userfault reached * this point, that would normally be solved by * userfaultfd_must_wait returning 'false'. * * If we were to return VM_FAULT_SIGBUS here, the non * cooperative manager would be instead forced to * always call UFFDIO_UNREGISTER before it can safely * close the uffd. */ ret = VM_FAULT_NOPAGE; goto out; } /* * Check that we can return VM_FAULT_RETRY. * * NOTE: it should become possible to return VM_FAULT_RETRY * even if FAULT_FLAG_TRIED is set without leading to gup() * -EBUSY failures, if the userfaultfd is to be extended for * VM_UFFD_WP tracking and we intend to arm the userfault * without first stopping userland access to the memory. For * VM_UFFD_MISSING userfaults this is enough for now. */ if (unlikely(!(vmf->flags & FAULT_FLAG_ALLOW_RETRY))) { /* * Validate the invariant that nowait must allow retry * to be sure not to return SIGBUS erroneously on * nowait invocations. */ BUG_ON(vmf->flags & FAULT_FLAG_RETRY_NOWAIT); #ifdef CONFIG_DEBUG_VM if (printk_ratelimit()) { printk(KERN_WARNING "FAULT_FLAG_ALLOW_RETRY missing %x\n", vmf->flags); dump_stack(); } #endif goto out; } /* * Handle nowait, not much to do other than tell it to retry * and wait. */ ret = VM_FAULT_RETRY; if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) goto out; /* take the reference before dropping the mmap_lock */ userfaultfd_ctx_get(ctx); init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function); uwq.wq.private = current; uwq.msg = userfault_msg(vmf->address, vmf->flags, reason, ctx->features); uwq.ctx = ctx; uwq.waken = false; blocking_state = userfaultfd_get_blocking_state(vmf->flags); spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). */ __add_wait_queue(&ctx->fault_pending_wqh, &uwq.wq); /* * The smp_mb() after __set_current_state prevents the reads * following the spin_unlock to happen before the list_add in * __add_wait_queue. */ set_current_state(blocking_state); spin_unlock_irq(&ctx->fault_pending_wqh.lock); if (!is_vm_hugetlb_page(vmf->vma)) must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags, reason); else must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma, vmf->address, vmf->flags, reason); mmap_read_unlock(mm); if (likely(must_wait && !READ_ONCE(ctx->released))) { wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); } __set_current_state(TASK_RUNNING); /* * Here we race with the list_del; list_add in * userfaultfd_ctx_read(), however because we don't ever run * list_del_init() to refile across the two lists, the prev * and next pointers will never point to self. list_add also * would never let any of the two pointers to point to * self. So list_empty_careful won't risk to see both pointers * pointing to self at any time during the list refile. The * only case where list_del_init() is called is the full * removal in the wake function and there we don't re-list_add * and it's fine not to block on the spinlock. The uwq on this * kernel stack can be released after the list_del_init. */ if (!list_empty_careful(&uwq.wq.entry)) { spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * No need of list_del_init(), the uwq on the stack * will be freed shortly anyway. */ list_del(&uwq.wq.entry); spin_unlock_irq(&ctx->fault_pending_wqh.lock); } /* * ctx may go away after this if the userfault pseudo fd is * already released. */ userfaultfd_ctx_put(ctx); out: return ret; } static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { struct userfaultfd_ctx *release_new_ctx; if (WARN_ON_ONCE(current->flags & PF_EXITING)) goto out; ewq->ctx = ctx; init_waitqueue_entry(&ewq->wq, current); release_new_ctx = NULL; spin_lock_irq(&ctx->event_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). */ __add_wait_queue(&ctx->event_wqh, &ewq->wq); for (;;) { set_current_state(TASK_KILLABLE); if (ewq->msg.event == 0) break; if (READ_ONCE(ctx->released) || fatal_signal_pending(current)) { /* * &ewq->wq may be queued in fork_event, but * __remove_wait_queue ignores the head * parameter. It would be a problem if it * didn't. */ __remove_wait_queue(&ctx->event_wqh, &ewq->wq); if (ewq->msg.event == UFFD_EVENT_FORK) { struct userfaultfd_ctx *new; new = (struct userfaultfd_ctx *) (unsigned long) ewq->msg.arg.reserved.reserved1; release_new_ctx = new; } break; } spin_unlock_irq(&ctx->event_wqh.lock); wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); spin_lock_irq(&ctx->event_wqh.lock); } __set_current_state(TASK_RUNNING); spin_unlock_irq(&ctx->event_wqh.lock); if (release_new_ctx) { struct vm_area_struct *vma; struct mm_struct *mm = release_new_ctx->mm; /* the various vma->vm_userfaultfd_ctx still points to it */ mmap_write_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) if (rcu_access_pointer(vma->vm_userfaultfd_ctx.ctx) == release_new_ctx) { rcu_assign_pointer(vma->vm_userfaultfd_ctx.ctx, NULL); vma->vm_flags &= ~__VM_UFFD_FLAGS; } mmap_write_unlock(mm); userfaultfd_ctx_put(release_new_ctx); } /* * ctx may go away after this if the userfault pseudo fd is * already released. */ out: atomic_dec(&ctx->mmap_changing); VM_BUG_ON(atomic_read(&ctx->mmap_changing) < 0); userfaultfd_ctx_put(ctx); } static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { ewq->msg.event = 0; wake_up_locked(&ctx->event_wqh); __remove_wait_queue(&ctx->event_wqh, &ewq->wq); } int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) { struct userfaultfd_ctx *ctx = NULL, *octx; struct userfaultfd_fork_ctx *fctx; octx = rcu_dereference_protected( vma->vm_userfaultfd_ctx.ctx, lockdep_is_held(&vma->vm_mm->mmap_lock)); if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) { rcu_assign_pointer(vma->vm_userfaultfd_ctx.ctx, NULL); vma->vm_flags &= ~__VM_UFFD_FLAGS; return 0; } list_for_each_entry(fctx, fcs, list) if (fctx->orig == octx) { ctx = fctx->new; break; } if (!ctx) { fctx = kmalloc(sizeof(*fctx), GFP_KERNEL); if (!fctx) return -ENOMEM; ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); if (!ctx) { kfree(fctx); return -ENOMEM; } refcount_set(&ctx->refcount, 1); ctx->flags = octx->flags; ctx->features = octx->features; ctx->released = false; atomic_set(&ctx->mmap_changing, 0); ctx->mm = vma->vm_mm; mmgrab(ctx->mm); userfaultfd_ctx_get(octx); atomic_inc(&octx->mmap_changing); fctx->orig = octx; fctx->new = ctx; list_add_tail(&fctx->list, fcs); } rcu_assign_pointer(vma->vm_userfaultfd_ctx.ctx, ctx); return 0; } static void dup_fctx(struct userfaultfd_fork_ctx *fctx) { struct userfaultfd_ctx *ctx = fctx->orig; struct userfaultfd_wait_queue ewq; msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_FORK; ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new; userfaultfd_event_wait_completion(ctx, &ewq); } void dup_userfaultfd_complete(struct list_head *fcs) { struct userfaultfd_fork_ctx *fctx, *n; list_for_each_entry_safe(fctx, n, fcs, list) { dup_fctx(fctx); list_del(&fctx->list); kfree(fctx); } } void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *vm_ctx) { struct userfaultfd_ctx *ctx; ctx = rcu_dereference_protected(vma->vm_userfaultfd_ctx.ctx, lockdep_is_held(&vma->vm_mm->mmap_lock)); if (!ctx) return; if (ctx->features & UFFD_FEATURE_EVENT_REMAP) { vm_ctx->ctx = ctx; userfaultfd_ctx_get(ctx); atomic_inc(&ctx->mmap_changing); } else { /* Drop uffd context if remap feature not enabled */ rcu_assign_pointer(vma->vm_userfaultfd_ctx.ctx, NULL); vma->vm_flags &= ~__VM_UFFD_FLAGS; } } void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx, unsigned long from, unsigned long to, unsigned long len) { struct userfaultfd_ctx *ctx = vm_ctx->ctx; struct userfaultfd_wait_queue ewq; if (!ctx) return; if (to & ~PAGE_MASK) { userfaultfd_ctx_put(ctx); return; } msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMAP; ewq.msg.arg.remap.from = from; ewq.msg.arg.remap.to = to; ewq.msg.arg.remap.len = len; userfaultfd_event_wait_completion(ctx, &ewq); } bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct mm_struct *mm = vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue ewq; ctx = rcu_dereference_protected(vma->vm_userfaultfd_ctx.ctx, lockdep_is_held(&mm->mmap_lock)); if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE)) return true; userfaultfd_ctx_get(ctx); atomic_inc(&ctx->mmap_changing); mmap_read_unlock(mm); msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMOVE; ewq.msg.arg.remove.start = start; ewq.msg.arg.remove.end = end; userfaultfd_event_wait_completion(ctx, &ewq); return false; } static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps, unsigned long start, unsigned long end) { struct userfaultfd_unmap_ctx *unmap_ctx; list_for_each_entry(unmap_ctx, unmaps, list) if (unmap_ctx->ctx == ctx && unmap_ctx->start == start && unmap_ctx->end == end) return true; return false; } int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *unmaps) { for ( ; vma && vma->vm_start < end; vma = vma->vm_next) { struct userfaultfd_unmap_ctx *unmap_ctx; struct userfaultfd_ctx *ctx = rcu_dereference_protected(vma->vm_userfaultfd_ctx.ctx, lockdep_is_held(&vma->vm_mm->mmap_lock)); if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) || has_unmap_ctx(ctx, unmaps, start, end)) continue; unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL); if (!unmap_ctx) return -ENOMEM; userfaultfd_ctx_get(ctx); atomic_inc(&ctx->mmap_changing); unmap_ctx->ctx = ctx; unmap_ctx->start = start; unmap_ctx->end = end; list_add_tail(&unmap_ctx->list, unmaps); } return 0; } void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) { struct userfaultfd_unmap_ctx *ctx, *n; struct userfaultfd_wait_queue ewq; list_for_each_entry_safe(ctx, n, uf, list) { msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_UNMAP; ewq.msg.arg.remove.start = ctx->start; ewq.msg.arg.remove.end = ctx->end; userfaultfd_event_wait_completion(ctx->ctx, &ewq); list_del(&ctx->list); kfree(ctx); } } static int userfaultfd_release(struct inode *inode, struct file *file) { struct userfaultfd_ctx *ctx = file->private_data; struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *prev; /* len == 0 means wake all */ struct userfaultfd_wake_range range = { .len = 0, }; unsigned long new_flags; WRITE_ONCE(ctx->released, true); if (!mmget_not_zero(mm)) goto wakeup; /* * Flush page faults out of all CPUs. NOTE: all page faults * must be retried without returning VM_FAULT_SIGBUS if * userfaultfd_ctx_get() succeeds but vma->vma_userfault_ctx * changes while handle_userfault released the mmap_lock. So * it's critical that released is set to true (above), before * taking the mmap_lock for writing. */ mmap_write_lock(mm); prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { struct userfaultfd_ctx *cur_uffd_ctx = rcu_dereference_protected(vma->vm_userfaultfd_ctx.ctx, lockdep_is_held(&mm->mmap_lock)); cond_resched(); BUG_ON(!!cur_uffd_ctx ^ !!(vma->vm_flags & __VM_UFFD_FLAGS)); if (cur_uffd_ctx != ctx) { prev = vma; continue; } new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), NULL_VM_UFFD_CTX, anon_vma_name(vma)); if (prev) vma = prev; else prev = vma; vma->vm_flags = new_flags; rcu_assign_pointer(vma->vm_userfaultfd_ctx.ctx, NULL); } mmap_write_unlock(mm); mmput(mm); wakeup: /* * After no new page faults can wait on this fault_*wqh, flush * the last page faults that may have been already waiting on * the fault_*wqh. */ spin_lock_irq(&ctx->fault_pending_wqh.lock); __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range); __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, &range); spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* Flush pending events that may still wait on event_wqh */ wake_up_all(&ctx->event_wqh); wake_up_poll(&ctx->fd_wqh, EPOLLHUP); userfaultfd_ctx_put(ctx); return 0; } /* fault_pending_wqh.lock must be hold by the caller */ static inline struct userfaultfd_wait_queue *find_userfault_in( wait_queue_head_t *wqh) { wait_queue_entry_t *wq; struct userfaultfd_wait_queue *uwq; lockdep_assert_held(&wqh->lock); uwq = NULL; if (!waitqueue_active(wqh)) goto out; /* walk in reverse to provide FIFO behavior to read userfaults */ wq = list_last_entry(&wqh->head, typeof(*wq), entry); uwq = container_of(wq, struct userfaultfd_wait_queue, wq); out: return uwq; } static inline struct userfaultfd_wait_queue *find_userfault( struct userfaultfd_ctx *ctx) { return find_userfault_in(&ctx->fault_pending_wqh); } static inline struct userfaultfd_wait_queue *find_userfault_evt( struct userfaultfd_ctx *ctx) { return find_userfault_in(&ctx->event_wqh); } static __poll_t userfaultfd_poll(struct file *file, poll_table *wait) { struct userfaultfd_ctx *ctx = file->private_data; __poll_t ret; poll_wait(file, &ctx->fd_wqh, wait); if (!userfaultfd_is_initialized(ctx)) return EPOLLERR; /* * poll() never guarantees that read won't block. * userfaults can be waken before they're read(). */ if (unlikely(!(file->f_flags & O_NONBLOCK))) return EPOLLERR; /* * lockless access to see if there are pending faults * __pollwait last action is the add_wait_queue but * the spin_unlock would allow the waitqueue_active to * pass above the actual list_add inside * add_wait_queue critical section. So use a full * memory barrier to serialize the list_add write of * add_wait_queue() with the waitqueue_active read * below. */ ret = 0; smp_mb(); if (waitqueue_active(&ctx->fault_pending_wqh)) ret = EPOLLIN; else if (waitqueue_active(&ctx->event_wqh)) ret = EPOLLIN; return ret; } static const struct file_operations userfaultfd_fops; static int resolve_userfault_fork(struct userfaultfd_ctx *new, struct inode *inode, struct uffd_msg *msg) { int fd; fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new, O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode); if (fd < 0) return fd; msg->arg.reserved.reserved1 = 0; msg->arg.fork.ufd = fd; return 0; } static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, struct uffd_msg *msg, struct inode *inode) { ssize_t ret; DECLARE_WAITQUEUE(wait, current); struct userfaultfd_wait_queue *uwq; /* * Handling fork event requires sleeping operations, so * we drop the event_wqh lock, then do these ops, then * lock it back and wake up the waiter. While the lock is * dropped the ewq may go away so we keep track of it * carefully. */ LIST_HEAD(fork_event); struct userfaultfd_ctx *fork_nctx = NULL; /* always take the fd_wqh lock before the fault_pending_wqh lock */ spin_lock_irq(&ctx->fd_wqh.lock); __add_wait_queue(&ctx->fd_wqh, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); spin_lock(&ctx->fault_pending_wqh.lock); uwq = find_userfault(ctx); if (uwq) { /* * Use a seqcount to repeat the lockless check * in wake_userfault() to avoid missing * wakeups because during the refile both * waitqueue could become empty if this is the * only userfault. */ write_seqcount_begin(&ctx->refile_seq); /* * The fault_pending_wqh.lock prevents the uwq * to disappear from under us. * * Refile this userfault from * fault_pending_wqh to fault_wqh, it's not * pending anymore after we read it. * * Use list_del() by hand (as * userfaultfd_wake_function also uses * list_del_init() by hand) to be sure nobody * changes __remove_wait_queue() to use * list_del_init() in turn breaking the * !list_empty_careful() check in * handle_userfault(). The uwq->wq.head list * must never be empty at any time during the * refile, or the waitqueue could disappear * from under us. The "wait_queue_head_t" * parameter of __remove_wait_queue() is unused * anyway. */ list_del(&uwq->wq.entry); add_wait_queue(&ctx->fault_wqh, &uwq->wq); write_seqcount_end(&ctx->refile_seq); /* careful to always initialize msg if ret == 0 */ *msg = uwq->msg; spin_unlock(&ctx->fault_pending_wqh.lock); ret = 0; break; } spin_unlock(&ctx->fault_pending_wqh.lock); spin_lock(&ctx->event_wqh.lock); uwq = find_userfault_evt(ctx); if (uwq) { *msg = uwq->msg; if (uwq->msg.event == UFFD_EVENT_FORK) { fork_nctx = (struct userfaultfd_ctx *) (unsigned long) uwq->msg.arg.reserved.reserved1; list_move(&uwq->wq.entry, &fork_event); /* * fork_nctx can be freed as soon as * we drop the lock, unless we take a * reference on it. */ userfaultfd_ctx_get(fork_nctx); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; } userfaultfd_event_complete(ctx, uwq); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; } spin_unlock(&ctx->event_wqh.lock); if (signal_pending(current)) { ret = -ERESTARTSYS; break; } if (no_wait) { ret = -EAGAIN; break; } spin_unlock_irq(&ctx->fd_wqh.lock); schedule(); spin_lock_irq(&ctx->fd_wqh.lock); } __remove_wait_queue(&ctx->fd_wqh, &wait); __set_current_state(TASK_RUNNING); spin_unlock_irq(&ctx->fd_wqh.lock); if (!ret && msg->event == UFFD_EVENT_FORK) { ret = resolve_userfault_fork(fork_nctx, inode, msg); spin_lock_irq(&ctx->event_wqh.lock); if (!list_empty(&fork_event)) { /* * The fork thread didn't abort, so we can * drop the temporary refcount. */ userfaultfd_ctx_put(fork_nctx); uwq = list_first_entry(&fork_event, typeof(*uwq), wq.entry); /* * If fork_event list wasn't empty and in turn * the event wasn't already released by fork * (the event is allocated on fork kernel * stack), put the event back to its place in * the event_wq. fork_event head will be freed * as soon as we return so the event cannot * stay queued there no matter the current * "ret" value. */ list_del(&uwq->wq.entry); __add_wait_queue(&ctx->event_wqh, &uwq->wq); /* * Leave the event in the waitqueue and report * error to userland if we failed to resolve * the userfault fork. */ if (likely(!ret)) userfaultfd_event_complete(ctx, uwq); } else { /* * Here the fork thread aborted and the * refcount from the fork thread on fork_nctx * has already been released. We still hold * the reference we took before releasing the * lock above. If resolve_userfault_fork * failed we've to drop it because the * fork_nctx has to be freed in such case. If * it succeeded we'll hold it because the new * uffd references it. */ if (ret) userfaultfd_ctx_put(fork_nctx); } spin_unlock_irq(&ctx->event_wqh.lock); } return ret; } static ssize_t userfaultfd_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct userfaultfd_ctx *ctx = file->private_data; ssize_t _ret, ret = 0; struct uffd_msg msg; int no_wait = file->f_flags & O_NONBLOCK; struct inode *inode = file_inode(file); if (!userfaultfd_is_initialized(ctx)) return -EINVAL; for (;;) { if (count < sizeof(msg)) return ret ? ret : -EINVAL; _ret = userfaultfd_ctx_read(ctx, no_wait, &msg, inode); if (_ret < 0) return ret ? ret : _ret; if (copy_to_user((__u64 __user *) buf, &msg, sizeof(msg))) return ret ? ret : -EFAULT; ret += sizeof(msg); buf += sizeof(msg); count -= sizeof(msg); /* * Allow to read more than one fault at time but only * block if waiting for the very first one. */ no_wait = O_NONBLOCK; } } static void __wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { spin_lock_irq(&ctx->fault_pending_wqh.lock); /* wake all in the range and autoremove */ if (waitqueue_active(&ctx->fault_pending_wqh)) __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, range); if (waitqueue_active(&ctx->fault_wqh)) __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, range); spin_unlock_irq(&ctx->fault_pending_wqh.lock); } static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { unsigned seq; bool need_wakeup; /* * To be sure waitqueue_active() is not reordered by the CPU * before the pagetable update, use an explicit SMP memory * barrier here. PT lock release or mmap_read_unlock(mm) still * have release semantics that can allow the * waitqueue_active() to be reordered before the pte update. */ smp_mb(); /* * Use waitqueue_active because it's very frequent to * change the address space atomically even if there are no * userfaults yet. So we take the spinlock only when we're * sure we've userfaults to wake. */ do { seq = read_seqcount_begin(&ctx->refile_seq); need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) || waitqueue_active(&ctx->fault_wqh); cond_resched(); } while (read_seqcount_retry(&ctx->refile_seq, seq)); if (need_wakeup) __wake_userfault(ctx, range); } static __always_inline int validate_range(struct mm_struct *mm, __u64 start, __u64 len) { __u64 task_size = mm->task_size; if (start & ~PAGE_MASK) return -EINVAL; if (len & ~PAGE_MASK) return -EINVAL; if (!len) return -EINVAL; if (start < mmap_min_addr) return -EINVAL; if (start >= task_size) return -EINVAL; if (len > task_size - start) return -EINVAL; return 0; } static inline bool vma_can_userfault(struct vm_area_struct *vma, unsigned long vm_flags) { /* FIXME: add WP support to hugetlbfs and shmem */ if (vm_flags & VM_UFFD_WP) { if (is_vm_hugetlb_page(vma) || vma_is_shmem(vma)) return false; } if (vm_flags & VM_UFFD_MINOR) { if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma))) return false; } return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || vma_is_shmem(vma); } static int userfaultfd_register(struct userfaultfd_ctx *ctx, unsigned long arg) { struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *prev, *cur; int ret; struct uffdio_register uffdio_register; struct uffdio_register __user *user_uffdio_register; unsigned long vm_flags, new_flags; bool found; bool basic_ioctls; unsigned long start, end, vma_end; user_uffdio_register = (struct uffdio_register __user *) arg; ret = -EFAULT; if (copy_from_user(&uffdio_register, user_uffdio_register, sizeof(uffdio_register)-sizeof(__u64))) goto out; ret = -EINVAL; if (!uffdio_register.mode) goto out; if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES) goto out; vm_flags = 0; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING) vm_flags |= VM_UFFD_MISSING; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) { #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP goto out; #endif vm_flags |= VM_UFFD_WP; } if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) { #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR goto out; #endif vm_flags |= VM_UFFD_MINOR; } ret = validate_range(mm, uffdio_register.range.start, uffdio_register.range.len); if (ret) goto out; start = uffdio_register.range.start; end = start + uffdio_register.range.len; ret = -ENOMEM; if (!mmget_not_zero(mm)) goto out; mmap_write_lock(mm); vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; /* check that there's at least one vma in the range */ ret = -EINVAL; if (vma->vm_start >= end) goto out_unlock; /* * If the first vma contains huge pages, make sure start address * is aligned to huge page size. */ if (is_vm_hugetlb_page(vma)) { unsigned long vma_hpagesize = vma_kernel_pagesize(vma); if (start & (vma_hpagesize - 1)) goto out_unlock; } /* * Search for not compatible vmas. */ found = false; basic_ioctls = false; for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) { struct userfaultfd_ctx *cur_uffd_ctx = rcu_dereference_protected(cur->vm_userfaultfd_ctx.ctx, lockdep_is_held(&mm->mmap_lock)); cond_resched(); BUG_ON(!!cur_uffd_ctx ^ !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* check not compatible vmas */ ret = -EINVAL; if (!vma_can_userfault(cur, vm_flags)) goto out_unlock; /* * UFFDIO_COPY will fill file holes even without * PROT_WRITE. This check enforces that if this is a * MAP_SHARED, the process has write permission to the backing * file. If VM_MAYWRITE is set it also enforces that on a * MAP_SHARED vma: there is no F_WRITE_SEAL and no further * F_WRITE_SEAL can be taken until the vma is destroyed. */ ret = -EPERM; if (unlikely(!(cur->vm_flags & VM_MAYWRITE))) goto out_unlock; /* * If this vma contains ending address, and huge pages * check alignment. */ if (is_vm_hugetlb_page(cur) && end <= cur->vm_end && end > cur->vm_start) { unsigned long vma_hpagesize = vma_kernel_pagesize(cur); ret = -EINVAL; if (end & (vma_hpagesize - 1)) goto out_unlock; } if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE)) goto out_unlock; /* * Check that this vma isn't already owned by a * different userfaultfd. We can't allow more than one * userfaultfd to own a single vma simultaneously or we * wouldn't know which one to deliver the userfaults to. */ ret = -EBUSY; if (cur_uffd_ctx && cur_uffd_ctx != ctx) goto out_unlock; /* * Note vmas containing huge pages */ if (is_vm_hugetlb_page(cur)) basic_ioctls = true; found = true; } BUG_ON(!found); if (vma->vm_start < start) prev = vma; ret = 0; do { struct userfaultfd_ctx *cur_uffd_ctx = rcu_dereference_protected(vma->vm_userfaultfd_ctx.ctx, lockdep_is_held(&mm->mmap_lock)); cond_resched(); BUG_ON(!vma_can_userfault(vma, vm_flags)); BUG_ON(cur_uffd_ctx && cur_uffd_ctx != ctx); WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); /* * Nothing to do: this vma is already registered into this * userfaultfd and with the right tracking mode too. */ if (cur_uffd_ctx == ctx && (vma->vm_flags & vm_flags) == vm_flags) goto skip; if (vma->vm_start > start) start = vma->vm_start; vma_end = min(end, vma->vm_end); new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), ((struct vm_userfaultfd_ctx){ ctx }), anon_vma_name(vma)); if (prev) { vma = prev; goto next; } if (vma->vm_start < start) { ret = split_vma(mm, vma, start, 1); if (ret) break; } if (vma->vm_end > end) { ret = split_vma(mm, vma, end, 0); if (ret) break; } next: /* * In the vma_merge() successful mprotect-like case 8: * the next vma was merged into the current one and * the current one has not been updated yet. */ vma->vm_flags = vma_pad_fixup_flags(vma, new_flags); rcu_assign_pointer(vma->vm_userfaultfd_ctx.ctx, ctx); if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma)) hugetlb_unshare_all_pmds(vma); skip: prev = vma; start = vma->vm_end; vma = vma->vm_next; } while (vma && vma->vm_start < end); out_unlock: mmap_write_unlock(mm); mmput(mm); if (!ret) { __u64 ioctls_out; ioctls_out = basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC : UFFD_API_RANGE_IOCTLS; /* * Declare the WP ioctl only if the WP mode is * specified and all checks passed with the range */ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)) ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT); /* CONTINUE ioctl is only supported for MINOR ranges. */ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR)) ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE); /* * Now that we scanned all vmas we can already tell * userland which ioctls methods are guaranteed to * succeed on this range. */ if (put_user(ioctls_out, &user_uffdio_register->ioctls)) ret = -EFAULT; } out: return ret; } static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, unsigned long arg) { struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *prev, *cur; int ret; struct uffdio_range uffdio_unregister; unsigned long new_flags; bool found; unsigned long start, end, vma_end; const void __user *buf = (void __user *)arg; ret = -EFAULT; if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) goto out; ret = validate_range(mm, uffdio_unregister.start, uffdio_unregister.len); if (ret) goto out; start = uffdio_unregister.start; end = start + uffdio_unregister.len; ret = -ENOMEM; if (!mmget_not_zero(mm)) goto out; mmap_write_lock(mm); vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; /* check that there's at least one vma in the range */ ret = -EINVAL; if (vma->vm_start >= end) goto out_unlock; /* * If the first vma contains huge pages, make sure start address * is aligned to huge page size. */ if (is_vm_hugetlb_page(vma)) { unsigned long vma_hpagesize = vma_kernel_pagesize(vma); if (start & (vma_hpagesize - 1)) goto out_unlock; } /* * Search for not compatible vmas. */ found = false; ret = -EINVAL; for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) { cond_resched(); BUG_ON(!!rcu_access_pointer(cur->vm_userfaultfd_ctx.ctx) ^ !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* * Check not compatible vmas, not strictly required * here as not compatible vmas cannot have an * userfaultfd_ctx registered on them, but this * provides for more strict behavior to notice * unregistration errors. */ if (!vma_can_userfault(cur, cur->vm_flags)) goto out_unlock; found = true; } BUG_ON(!found); if (vma->vm_start < start) prev = vma; ret = 0; do { struct userfaultfd_ctx *cur_uffd_ctx = rcu_dereference_protected(vma->vm_userfaultfd_ctx.ctx, lockdep_is_held(&mm->mmap_lock)); cond_resched(); BUG_ON(!vma_can_userfault(vma, vma->vm_flags)); /* * Nothing to do: this vma is already registered into this * userfaultfd and with the right tracking mode too. */ if (!cur_uffd_ctx) goto skip; WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); if (vma->vm_start > start) start = vma->vm_start; vma_end = min(end, vma->vm_end); if (userfaultfd_missing(vma)) { /* * Wake any concurrent pending userfault while * we unregister, so they will not hang * permanently and it avoids userland to call * UFFDIO_WAKE explicitly. */ struct userfaultfd_wake_range range; range.start = start; range.len = vma_end - start; wake_userfault(cur_uffd_ctx, &range); } new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), NULL_VM_UFFD_CTX, anon_vma_name(vma)); if (prev) { vma = prev; goto next; } if (vma->vm_start < start) { ret = split_vma(mm, vma, start, 1); if (ret) break; } if (vma->vm_end > end) { ret = split_vma(mm, vma, end, 0); if (ret) break; } next: /* * In the vma_merge() successful mprotect-like case 8: * the next vma was merged into the current one and * the current one has not been updated yet. */ vma->vm_flags = vma_pad_fixup_flags(vma, new_flags); rcu_assign_pointer(vma->vm_userfaultfd_ctx.ctx, NULL); skip: prev = vma; start = vma->vm_end; vma = vma->vm_next; } while (vma && vma->vm_start < end); out_unlock: mmap_write_unlock(mm); mmput(mm); out: return ret; } /* * userfaultfd_wake may be used in combination with the * UFFDIO_*_MODE_DONTWAKE to wakeup userfaults in batches. */ static int userfaultfd_wake(struct userfaultfd_ctx *ctx, unsigned long arg) { int ret; struct uffdio_range uffdio_wake; struct userfaultfd_wake_range range; const void __user *buf = (void __user *)arg; ret = -EFAULT; if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake))) goto out; ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len); if (ret) goto out; range.start = uffdio_wake.start; range.len = uffdio_wake.len; /* * len == 0 means wake all and we don't want to wake all here, * so check it again to be sure. */ VM_BUG_ON(!range.len); wake_userfault(ctx, &range); ret = 0; out: return ret; } static int userfaultfd_copy(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_copy uffdio_copy; struct uffdio_copy __user *user_uffdio_copy; struct userfaultfd_wake_range range; user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, /* don't copy "copy" last field */ sizeof(uffdio_copy)-sizeof(__s64))) goto out; ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len); if (ret) goto out; /* * double check for wraparound just in case. copy_from_user() * will later check uffdio_copy.src + uffdio_copy.len to fit * in the userland range. */ ret = -EINVAL; if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src) goto out; if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE| UFFDIO_COPY_MODE_WP| UFFDIO_COPY_MODE_MMAP_TRYLOCK)) goto out; if (mmget_not_zero(ctx->mm)) { ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src, uffdio_copy.len, &ctx->mmap_changing, uffdio_copy.mode); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_copy->copy))) return -EFAULT; if (ret < 0) goto out; BUG_ON(!ret); /* len == 0 would wake all */ range.len = ret; if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) { range.start = uffdio_copy.dst; wake_userfault(ctx, &range); } ret = range.len == uffdio_copy.len ? 0 : -EAGAIN; out: return ret; } static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_zeropage uffdio_zeropage; struct uffdio_zeropage __user *user_uffdio_zeropage; struct userfaultfd_wake_range range; user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, /* don't copy "zeropage" last field */ sizeof(uffdio_zeropage)-sizeof(__s64))) goto out; ret = validate_range(ctx->mm, uffdio_zeropage.range.start, uffdio_zeropage.range.len); if (ret) goto out; ret = -EINVAL; if (uffdio_zeropage.mode & ~(UFFDIO_ZEROPAGE_MODE_DONTWAKE| UFFDIO_ZEROPAGE_MODE_MMAP_TRYLOCK)) goto out; if (mmget_not_zero(ctx->mm)) { ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start, uffdio_zeropage.range.len, &ctx->mmap_changing, uffdio_zeropage.mode); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ BUG_ON(!ret); range.len = ret; if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) { range.start = uffdio_zeropage.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN; out: return ret; } static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx, unsigned long arg) { int ret; struct uffdio_writeprotect uffdio_wp; struct uffdio_writeprotect __user *user_uffdio_wp; struct userfaultfd_wake_range range; bool mode_wp, mode_dontwake; if (atomic_read(&ctx->mmap_changing)) return -EAGAIN; user_uffdio_wp = (struct uffdio_writeprotect __user *) arg; if (copy_from_user(&uffdio_wp, user_uffdio_wp, sizeof(struct uffdio_writeprotect))) return -EFAULT; ret = validate_range(ctx->mm, uffdio_wp.range.start, uffdio_wp.range.len); if (ret) return ret; if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE | UFFDIO_WRITEPROTECT_MODE_WP)) return -EINVAL; mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP; mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE; if (mode_wp && mode_dontwake) return -EINVAL; if (mmget_not_zero(ctx->mm)) { ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start, uffdio_wp.range.len, mode_wp, &ctx->mmap_changing); mmput(ctx->mm); } else { return -ESRCH; } if (ret) return ret; if (!mode_wp && !mode_dontwake) { range.start = uffdio_wp.range.start; range.len = uffdio_wp.range.len; wake_userfault(ctx, &range); } return ret; } static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_continue uffdio_continue; struct uffdio_continue __user *user_uffdio_continue; struct userfaultfd_wake_range range; user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_continue, user_uffdio_continue, /* don't copy the output fields */ sizeof(uffdio_continue) - (sizeof(__s64)))) goto out; ret = validate_range(ctx->mm, uffdio_continue.range.start, uffdio_continue.range.len); if (ret) goto out; ret = -EINVAL; /* double check for wraparound just in case. */ if (uffdio_continue.range.start + uffdio_continue.range.len <= uffdio_continue.range.start) { goto out; } if (uffdio_continue.mode & ~UFFDIO_CONTINUE_MODE_DONTWAKE) goto out; if (mmget_not_zero(ctx->mm)) { ret = mcopy_continue(ctx->mm, uffdio_continue.range.start, uffdio_continue.range.len, &ctx->mmap_changing); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ BUG_ON(!ret); range.len = ret; if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) { range.start = uffdio_continue.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN; out: return ret; } static inline unsigned int uffd_ctx_features(__u64 user_features) { /* * For the current set of features the bits just coincide. Set * UFFD_FEATURE_INITIALIZED to mark the features as enabled. */ return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED; } /* * userland asks for a certain API version and we return which bits * and ioctl commands are implemented in this kernel for such API * version or -EINVAL if unknown. */ static int userfaultfd_api(struct userfaultfd_ctx *ctx, unsigned long arg) { struct uffdio_api uffdio_api; void __user *buf = (void __user *)arg; unsigned int ctx_features; int ret; __u64 features; ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; features = uffdio_api.features; ret = -EINVAL; if (uffdio_api.api != UFFD_API) goto err_out; ret = -EPERM; if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) goto err_out; /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR uffdio_api.features &= ~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM); #endif #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP; #endif ret = -EINVAL; if (features & ~uffdio_api.features) goto err_out; uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) goto out; /* only enable the requested features for this uffd context */ ctx_features = uffd_ctx_features(features); ret = -EINVAL; if (cmpxchg(&ctx->features, 0, ctx_features) != 0) goto err_out; ret = 0; out: return ret; err_out: memset(&uffdio_api, 0, sizeof(uffdio_api)); if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) ret = -EFAULT; goto out; } static long userfaultfd_ioctl(struct file *file, unsigned cmd, unsigned long arg) { int ret = -EINVAL; struct userfaultfd_ctx *ctx = file->private_data; if (cmd != UFFDIO_API && !userfaultfd_is_initialized(ctx)) return -EINVAL; switch(cmd) { case UFFDIO_API: ret = userfaultfd_api(ctx, arg); break; case UFFDIO_REGISTER: ret = userfaultfd_register(ctx, arg); break; case UFFDIO_UNREGISTER: ret = userfaultfd_unregister(ctx, arg); break; case UFFDIO_WAKE: ret = userfaultfd_wake(ctx, arg); break; case UFFDIO_COPY: ret = userfaultfd_copy(ctx, arg); break; case UFFDIO_ZEROPAGE: ret = userfaultfd_zeropage(ctx, arg); break; case UFFDIO_WRITEPROTECT: ret = userfaultfd_writeprotect(ctx, arg); break; case UFFDIO_CONTINUE: ret = userfaultfd_continue(ctx, arg); break; } return ret; } #ifdef CONFIG_PROC_FS static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f) { struct userfaultfd_ctx *ctx = f->private_data; wait_queue_entry_t *wq; unsigned long pending = 0, total = 0; spin_lock_irq(&ctx->fault_pending_wqh.lock); list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) { pending++; total++; } list_for_each_entry(wq, &ctx->fault_wqh.head, entry) { total++; } spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* * If more protocols will be added, there will be all shown * separated by a space. Like this: * protocols: aa:... bb:... */ seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n", pending, total, UFFD_API, ctx->features, UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS); } #endif static const struct file_operations userfaultfd_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = userfaultfd_show_fdinfo, #endif .release = userfaultfd_release, .poll = userfaultfd_poll, .read = userfaultfd_read, .unlocked_ioctl = userfaultfd_ioctl, .compat_ioctl = compat_ptr_ioctl, .llseek = noop_llseek, }; static void init_once_userfaultfd_ctx(void *mem) { struct userfaultfd_ctx *ctx = (struct userfaultfd_ctx *) mem; init_waitqueue_head(&ctx->fault_pending_wqh); init_waitqueue_head(&ctx->fault_wqh); init_waitqueue_head(&ctx->event_wqh); init_waitqueue_head(&ctx->fd_wqh); seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock); } SYSCALL_DEFINE1(userfaultfd, int, flags) { struct userfaultfd_ctx *ctx; int fd; if (!sysctl_unprivileged_userfaultfd && (flags & UFFD_USER_MODE_ONLY) == 0 && !capable(CAP_SYS_PTRACE)) { printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd " "sysctl knob to 1 if kernel faults must be handled " "without obtaining CAP_SYS_PTRACE capability\n"); return -EPERM; } BUG_ON(!current->mm); /* Check the UFFD_* constants for consistency. */ BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS); BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK); if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY)) return -EINVAL; ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); if (!ctx) return -ENOMEM; refcount_set(&ctx->refcount, 1); ctx->flags = flags; ctx->features = 0; ctx->released = false; atomic_set(&ctx->mmap_changing, 0); ctx->mm = current->mm; /* prevent the mm struct to be freed */ mmgrab(ctx->mm); fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx, O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL); if (fd < 0) { mmdrop(ctx->mm); kmem_cache_free(userfaultfd_ctx_cachep, ctx); } return fd; } static int __init userfaultfd_init(void) { userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache", sizeof(struct userfaultfd_ctx), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, init_once_userfaultfd_ctx); return 0; } __initcall(userfaultfd_init); |
| 20 27 22 10 10 27 27 24 4 20 20 20 901 901 15 15 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/dst_cache.c - dst entry cache * * Copyright (c) 2016 Paolo Abeni <pabeni@redhat.com> */ #include <linux/kernel.h> #include <linux/percpu.h> #include <net/dst_cache.h> #include <net/route.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ip6_fib.h> #endif #include <uapi/linux/in.h> struct dst_cache_pcpu { unsigned long refresh_ts; struct dst_entry *dst; u32 cookie; union { struct in_addr in_saddr; struct in6_addr in6_saddr; }; }; static void dst_cache_per_cpu_dst_set(struct dst_cache_pcpu *dst_cache, struct dst_entry *dst, u32 cookie) { dst_release(dst_cache->dst); if (dst) dst_hold(dst); dst_cache->cookie = cookie; dst_cache->dst = dst; } static struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache, struct dst_cache_pcpu *idst) { struct dst_entry *dst; dst = idst->dst; if (!dst) goto fail; /* the cache already hold a dst reference; it can't go away */ dst_hold(dst); if (unlikely(!time_after(idst->refresh_ts, dst_cache->reset_ts) || (dst->obsolete && !dst->ops->check(dst, idst->cookie)))) { dst_cache_per_cpu_dst_set(idst, NULL, 0); dst_release(dst); goto fail; } return dst; fail: idst->refresh_ts = jiffies; return NULL; } struct dst_entry *dst_cache_get(struct dst_cache *dst_cache) { if (!dst_cache->cache) return NULL; return dst_cache_per_cpu_get(dst_cache, this_cpu_ptr(dst_cache->cache)); } EXPORT_SYMBOL_GPL(dst_cache_get); struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr) { struct dst_cache_pcpu *idst; struct dst_entry *dst; if (!dst_cache->cache) return NULL; idst = this_cpu_ptr(dst_cache->cache); dst = dst_cache_per_cpu_get(dst_cache, idst); if (!dst) return NULL; *saddr = idst->in_saddr.s_addr; return container_of(dst, struct rtable, dst); } EXPORT_SYMBOL_GPL(dst_cache_get_ip4); void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst, __be32 saddr) { struct dst_cache_pcpu *idst; if (!dst_cache->cache) return; idst = this_cpu_ptr(dst_cache->cache); dst_cache_per_cpu_dst_set(idst, dst, 0); idst->in_saddr.s_addr = saddr; } EXPORT_SYMBOL_GPL(dst_cache_set_ip4); #if IS_ENABLED(CONFIG_IPV6) void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst, const struct in6_addr *saddr) { struct dst_cache_pcpu *idst; if (!dst_cache->cache) return; idst = this_cpu_ptr(dst_cache->cache); dst_cache_per_cpu_dst_set(this_cpu_ptr(dst_cache->cache), dst, rt6_get_cookie((struct rt6_info *)dst)); idst->in6_saddr = *saddr; } EXPORT_SYMBOL_GPL(dst_cache_set_ip6); struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache, struct in6_addr *saddr) { struct dst_cache_pcpu *idst; struct dst_entry *dst; if (!dst_cache->cache) return NULL; idst = this_cpu_ptr(dst_cache->cache); dst = dst_cache_per_cpu_get(dst_cache, idst); if (!dst) return NULL; *saddr = idst->in6_saddr; return dst; } EXPORT_SYMBOL_GPL(dst_cache_get_ip6); #endif int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp) { dst_cache->cache = alloc_percpu_gfp(struct dst_cache_pcpu, gfp | __GFP_ZERO); if (!dst_cache->cache) return -ENOMEM; dst_cache_reset(dst_cache); return 0; } EXPORT_SYMBOL_GPL(dst_cache_init); void dst_cache_destroy(struct dst_cache *dst_cache) { int i; if (!dst_cache->cache) return; for_each_possible_cpu(i) dst_release(per_cpu_ptr(dst_cache->cache, i)->dst); free_percpu(dst_cache->cache); } EXPORT_SYMBOL_GPL(dst_cache_destroy); void dst_cache_reset_now(struct dst_cache *dst_cache) { int i; if (!dst_cache->cache) return; dst_cache->reset_ts = jiffies; for_each_possible_cpu(i) { struct dst_cache_pcpu *idst = per_cpu_ptr(dst_cache->cache, i); struct dst_entry *dst = idst->dst; idst->cookie = 0; idst->dst = NULL; dst_release(dst); } } EXPORT_SYMBOL_GPL(dst_cache_reset_now); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BLKDEV_H #define _LINUX_BLKDEV_H #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/major.h> #include <linux/genhd.h> #include <linux/list.h> #include <linux/llist.h> #include <linux/minmax.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/wait.h> #include <linux/mempool.h> #include <linux/pfn.h> #include <linux/bio.h> #include <linux/stringify.h> #include <linux/gfp.h> #include <linux/smp.h> #include <linux/rcupdate.h> #include <linux/percpu-refcount.h> #include <linux/scatterlist.h> #include <linux/blkzoned.h> #include <linux/pm.h> #include <linux/sbitmap.h> #include <linux/android_kabi.h> #include <linux/android_vendor.h> struct module; struct request_queue; struct elevator_queue; struct blk_trace; struct request; struct sg_io_hdr; struct blkcg_gq; struct blk_flush_queue; struct pr_ops; struct rq_qos; struct blk_queue_stats; struct blk_stat_callback; struct blk_keyslot_manager; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ /* Must be consistent with blk_mq_poll_stats_bkt() */ #define BLK_MQ_POLL_STATS_BKTS 16 /* Doing classic polling */ #define BLK_MQ_POLL_CLASSIC -1 /* * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ #define BLKCG_MAX_POLS 6 typedef void (rq_end_io_fn)(struct request *, blk_status_t); /* * request flags */ typedef __u32 __bitwise req_flags_t; /* drive already may have started this one */ #define RQF_STARTED ((__force req_flags_t)(1 << 1)) /* may not be passed by ioscheduler */ #define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) /* request for flush sequence */ #define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) /* merge of different types, fail separately */ #define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5)) /* track inflight for MQ */ #define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) /* don't call prep for this one */ #define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) /* vaguely specified driver internal error. Ignored by the block layer */ #define RQF_FAILED ((__force req_flags_t)(1 << 10)) /* don't warn about errors */ #define RQF_QUIET ((__force req_flags_t)(1 << 11)) /* elevator private data attached */ #define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) /* account into disk and partition IO statistics */ #define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) /* runtime pm request */ #define RQF_PM ((__force req_flags_t)(1 << 15)) /* on IO scheduler merge hash */ #define RQF_HASHED ((__force req_flags_t)(1 << 16)) /* track IO completion time */ #define RQF_STATS ((__force req_flags_t)(1 << 17)) /* Look at ->special_vec for the actual data payload instead of the bio chain. */ #define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) /* The per-zone write lock is held for this request */ #define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) /* already slept for hybrid poll */ #define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) /* * Request state for blk-mq. */ enum mq_rq_state { MQ_RQ_IDLE = 0, MQ_RQ_IN_FLIGHT = 1, MQ_RQ_COMPLETE = 2, }; /* * Try to put the fields that are referenced together in the same cacheline. * * If you modify this structure, make sure to update blk_rq_init() and * especially blk_mq_rq_ctx_init() to take care of the added fields. */ struct request { struct request_queue *q; struct blk_mq_ctx *mq_ctx; struct blk_mq_hw_ctx *mq_hctx; unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; int tag; int internal_tag; /* the following two fields are internal, NEVER access directly */ unsigned int __data_len; /* total data len */ sector_t __sector; /* sector cursor */ struct bio *bio; struct bio *biotail; struct list_head queuelist; /* * The hash is used inside the scheduler, and killed once the * request reaches the dispatch list. The ipi_list is only used * to queue the request for softirq completion, which is long * after the request has been unhashed (and even removed from * the dispatch list). */ union { struct hlist_node hash; /* merge hash */ struct llist_node ipi_list; }; /* * The rb_node is only used inside the io scheduler, requests * are pruned when moved to the dispatch queue. So let the * completion_data share space with the rb_node. */ union { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; void *completion_data; int error_count; /* for legacy drivers, don't use */ }; /* * Three pointers are available for the IO schedulers, if they need * more they have to dynamically allocate it. Flush requests are * never put on the IO scheduler. So let the flush fields share * space with the elevator data. */ union { struct { struct io_cq *icq; void *priv[2]; } elv; struct { unsigned int seq; struct list_head list; rq_end_io_fn *saved_end_io; } flush; }; struct gendisk *rq_disk; struct block_device *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ u64 alloc_time_ns; #endif /* Time that this request was allocated for this IO. */ u64 start_time_ns; /* Time that I/O was submitted to the device. */ u64 io_start_time_ns; #ifdef CONFIG_BLK_WBT unsigned short wbt_flags; #endif /* * rq sectors used for blk stats. It has the same value * with blk_rq_sectors(rq), except that it never be zeroed * by completion. */ unsigned short stats_sectors; /* * Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ unsigned short nr_phys_segments; #if defined(CONFIG_BLK_DEV_INTEGRITY) unsigned short nr_integrity_segments; #endif #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *crypt_ctx; struct blk_ksm_keyslot *crypt_keyslot; #endif unsigned short write_hint; unsigned short ioprio; enum mq_rq_state state; refcount_t ref; unsigned int timeout; unsigned long deadline; union { struct __call_single_data csd; u64 fifo_time; }; /* * completion callback. */ rq_end_io_fn *end_io; void *end_io_data; ANDROID_KABI_RESERVE(1); }; static inline int blk_validate_block_size(unsigned long bsize) { if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) return -EINVAL; return 0; } static inline bool blk_op_is_passthrough(unsigned int op) { op &= REQ_OP_MASK; return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT; } static inline bool blk_rq_is_passthrough(struct request *rq) { return blk_op_is_passthrough(req_op(rq)); } static inline unsigned short req_get_ioprio(struct request *req) { return req->ioprio; } #include <linux/elevator.h> struct bio_vec; enum blk_eh_timer_return { BLK_EH_DONE, /* drivers has completed the command */ BLK_EH_RESET_TIMER, /* reset timer and try again */ }; enum blk_queue_state { Queue_down, Queue_up, }; #define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ #define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ /* * Zoned block device models (zoned limit). * * Note: This needs to be ordered from the least to the most severe * restrictions for the inheritance in blk_stack_limits() to work. */ enum blk_zoned_model { BLK_ZONED_NONE = 0, /* Regular block device */ BLK_ZONED_HA, /* Host-aware zoned block device */ BLK_ZONED_HM, /* Host-managed zoned block device */ }; /* * BLK_BOUNCE_NONE: never bounce (default) * BLK_BOUNCE_HIGH: bounce all highmem pages */ enum blk_bounce { BLK_BOUNCE_NONE, BLK_BOUNCE_HIGH, }; struct queue_limits { enum blk_bounce bounce; unsigned long seg_boundary_mask; unsigned long virt_boundary_mask; unsigned int max_hw_sectors; unsigned int max_dev_sectors; unsigned int chunk_sectors; unsigned int max_sectors; unsigned int max_segment_size; unsigned int physical_block_size; unsigned int logical_block_size; unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; unsigned int max_write_same_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; unsigned int discard_alignment; unsigned int zone_write_granularity; unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; unsigned char misaligned; unsigned char discard_misaligned; unsigned char raid_partial_stripes_expensive; enum blk_zoned_model zoned; ANDROID_KABI_RESERVE(1); ANDROID_OEM_DATA(1); }; typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model); #ifdef CONFIG_BLK_DEV_ZONED #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); unsigned int blkdev_nr_zones(struct gendisk *disk); extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); int blk_revalidate_disk_zones(struct gendisk *disk, void (*update_driver_data)(struct gendisk *disk)); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blkdev_nr_zones(struct gendisk *disk) { return 0; } static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { return -ENOTTY; } static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { return -ENOTTY; } #endif /* CONFIG_BLK_DEV_ZONED */ struct request_queue { struct request *last_merge; struct elevator_queue *elevator; struct percpu_ref q_usage_counter; struct blk_queue_stats *stats; struct rq_qos *rq_qos; const struct blk_mq_ops *mq_ops; /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; unsigned int queue_depth; /* hw dispatch queues */ struct blk_mq_hw_ctx **queue_hw_ctx; unsigned int nr_hw_queues; /* * The queue owner gets to use this for whatever they like. * ll_rw_blk doesn't touch it. */ void *queuedata; /* * various queue flags, see QUEUE_* below */ unsigned long queue_flags; /* * Number of contexts that have called blk_set_pm_only(). If this * counter is above zero then only RQF_PM requests are processed. */ atomic_t pm_only; /* * ida allocated id for this queue. Used to index queues from * ioctx. */ int id; spinlock_t queue_lock; struct gendisk *disk; /* * queue kobject */ struct kobject kobj; /* * mq queue kobject */ struct kobject *mq_kobj; #ifdef CONFIG_BLK_DEV_INTEGRITY struct blk_integrity integrity; #endif /* CONFIG_BLK_DEV_INTEGRITY */ #ifdef CONFIG_PM struct device *dev; enum rpm_status rpm_status; #endif /* * queue settings */ unsigned long nr_requests; /* Max # of requests */ unsigned int dma_pad_mask; unsigned int dma_alignment; #ifdef CONFIG_BLK_INLINE_ENCRYPTION /* Inline crypto capabilities */ struct blk_keyslot_manager *ksm; #endif unsigned int rq_timeout; int poll_nsec; struct blk_stat_callback *poll_cb; struct blk_rq_stat poll_stat[BLK_MQ_POLL_STATS_BKTS]; struct timer_list timeout; struct work_struct timeout_work; atomic_t nr_active_requests_shared_sbitmap; struct sbitmap_queue sched_bitmap_tags; struct sbitmap_queue sched_breserved_tags; struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); struct blkcg_gq *root_blkg; struct list_head blkg_list; #endif struct queue_limits limits; unsigned int required_elevator_features; #ifdef CONFIG_BLK_DEV_ZONED /* * Zoned block device information for request dispatch control. * nr_zones is the total number of zones of the device. This is always * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones * bits which indicates if a zone is conventional (bit set) or * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones * bits which indicates if a zone is write locked, that is, if a write * request targeting the zone was dispatched. All three fields are * initialized by the low level device driver (e.g. scsi/sd.c). * Stacking drivers (device mappers) may or may not initialize * these fields. * * Reads of this information must be protected with blk_queue_enter() / * blk_queue_exit(). Modifying this information is only allowed while * no requests are being processed. See also blk_mq_freeze_queue() and * blk_mq_unfreeze_queue(). */ unsigned int nr_zones; unsigned long *conv_zones_bitmap; unsigned long *seq_zones_wlock; unsigned int max_open_zones; unsigned int max_active_zones; #endif /* CONFIG_BLK_DEV_ZONED */ int node; struct mutex debugfs_mutex; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; #endif /* * for flush operations */ struct blk_flush_queue *fq; struct list_head requeue_list; spinlock_t requeue_lock; struct delayed_work requeue_work; struct mutex sysfs_lock; struct mutex sysfs_dir_lock; /* * for reusing dead hctx instance in case of updating * nr_hw_queues */ struct list_head unused_hctx_list; spinlock_t unused_hctx_lock; int mq_freeze_depth; #ifdef CONFIG_BLK_DEV_THROTTLING /* Throttle data */ struct throtl_data *td; #endif struct rcu_head rcu_head; wait_queue_head_t mq_freeze_wq; /* * Protect concurrent access to q_usage_counter by * percpu_ref_kill() and percpu_ref_reinit(). */ struct mutex mq_freeze_lock; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; struct bio_set bio_split; struct dentry *debugfs_dir; #ifdef CONFIG_BLK_DEBUG_FS struct dentry *sched_debugfs_dir; struct dentry *rqos_debugfs_dir; #endif bool mq_sysfs_init_done; size_t cmd_size; #define BLK_MAX_WRITE_HINTS 5 u64 write_hints[BLK_MAX_WRITE_HINTS]; ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); ANDROID_OEM_DATA(1); }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ #define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ #define QUEUE_FLAG_DYING 1 /* queue being torn down */ #define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */ #define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ #define QUEUE_FLAG_DISCARD 8 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ #define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ #define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ #define QUEUE_FLAG_WC 17 /* Write back caching */ #define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ #define QUEUE_FLAG_DAX 19 /* device supports DAX */ #define QUEUE_FLAG_STATS 20 /* track IO start and completion times */ #define QUEUE_FLAG_POLL_STATS 21 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */ #define QUEUE_FLAG_SCSI_PASSTHROUGH 23 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ #define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ #define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_NOWAIT)) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) #define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) #define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) #define blk_queue_stable_writes(q) \ test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_zone_resetall(q) \ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) #define blk_queue_secure_erase(q) \ (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_scsi_passthrough(q) \ test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) #define blk_queue_pci_p2pdma(q) \ test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) #ifdef CONFIG_BLK_RQ_ALLOC_TIME #define blk_queue_rq_alloc_time(q) \ test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags) #else #define blk_queue_rq_alloc_time(q) false #endif #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) #define rq_dma_dir(rq) \ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) #define dma_map_bvec(dev, bv, dir, attrs) \ dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \ (dir), (attrs)) static inline bool queue_is_mq(struct request_queue *q) { return q->mq_ops; } #ifdef CONFIG_PM static inline enum rpm_status queue_rpm_status(struct request_queue *q) { return q->rpm_status; } #else static inline enum rpm_status queue_rpm_status(struct request_queue *q) { return RPM_ACTIVE; } #endif static inline enum blk_zoned_model blk_queue_zoned_model(struct request_queue *q) { if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) return q->limits.zoned; return BLK_ZONED_NONE; } static inline bool blk_queue_is_zoned(struct request_queue *q) { switch (blk_queue_zoned_model(q)) { case BLK_ZONED_HA: case BLK_ZONED_HM: return true; default: return false; } } static inline sector_t blk_queue_zone_sectors(struct request_queue *q) { return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } #ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int blk_queue_nr_zones(struct request_queue *q) { return blk_queue_is_zoned(q) ? q->nr_zones : 0; } static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { if (!blk_queue_is_zoned(q)) return 0; return sector >> ilog2(q->limits.chunk_sectors); } static inline bool blk_queue_zone_is_seq(struct request_queue *q, sector_t sector) { if (!blk_queue_is_zoned(q)) return false; if (!q->conv_zones_bitmap) return true; return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap); } static inline void blk_queue_max_open_zones(struct request_queue *q, unsigned int max_open_zones) { q->max_open_zones = max_open_zones; } static inline unsigned int queue_max_open_zones(const struct request_queue *q) { return q->max_open_zones; } static inline void blk_queue_max_active_zones(struct request_queue *q, unsigned int max_active_zones) { q->max_active_zones = max_active_zones; } static inline unsigned int queue_max_active_zones(const struct request_queue *q) { return q->max_active_zones; } #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blk_queue_nr_zones(struct request_queue *q) { return 0; } static inline bool blk_queue_zone_is_seq(struct request_queue *q, sector_t sector) { return false; } static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { return 0; } static inline unsigned int queue_max_open_zones(const struct request_queue *q) { return 0; } static inline unsigned int queue_max_active_zones(const struct request_queue *q) { return 0; } #endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) { return op_is_sync(rq->cmd_flags); } static inline bool rq_mergeable(struct request *rq) { if (blk_rq_is_passthrough(rq)) return false; if (req_op(rq) == REQ_OP_FLUSH) return false; if (req_op(rq) == REQ_OP_WRITE_ZEROES) return false; if (req_op(rq) == REQ_OP_ZONE_APPEND) return false; if (rq->cmd_flags & REQ_NOMERGE_FLAGS) return false; if (rq->rq_flags & RQF_NOMERGE_FLAGS) return false; return true; } static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) { if (bio_page(a) == bio_page(b) && bio_offset(a) == bio_offset(b)) return true; return false; } static inline unsigned int blk_queue_depth(struct request_queue *q) { if (q->queue_depth) return q->queue_depth; return q->nr_requests; } /* * default timeout for SG_IO if none specified */ #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) #define BLK_MIN_SG_TIMEOUT (7 * HZ) struct rq_map_data { struct page **pages; int page_order; int nr_entries; unsigned long offset; int null_mapped; int from_user; }; struct req_iterator { struct bvec_iter iter; struct bio *bio; }; /* This should not be used directly - use rq_for_each_segment */ #define for_each_bio(_bio) \ for (; _bio; _bio = _bio->bi_next) #define __rq_for_each_bio(_bio, rq) \ if ((rq->bio)) \ for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) #define rq_for_each_segment(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_segment(bvl, _iter.bio, _iter.iter) #define rq_for_each_bvec(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_bvec(bvl, _iter.bio, _iter.iter) #define rq_iter_last(bvec, _iter) \ (_iter.bio->bi_next == NULL && \ bio_iter_last(bvec, _iter.iter)) #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE # error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" #endif #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE extern void rq_flush_dcache_pages(struct request *rq); #else static inline void rq_flush_dcache_pages(struct request *rq) { } #endif extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); blk_qc_t submit_bio_noacct(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); extern struct request *blk_get_request(struct request_queue *, unsigned int op, blk_mq_req_flags_t flags); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); extern void blk_rq_unprep_clone(struct request *rq); extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); int blk_rq_append_bio(struct request *rq, struct bio *bio); extern void blk_queue_split(struct bio **); extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags); extern void blk_queue_exit(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); extern int blk_rq_unmap_user(struct bio *); extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t); extern int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); extern void blk_execute_rq_nowait(struct gendisk *, struct request *, int, rq_end_io_fn *); blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq, int at_head); /* Helper to convert REQ_OP_XXX to its string format XXX */ extern const char *blk_op_str(unsigned int op); int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { return bdev->bd_disk->queue; /* this is never NULL */ } /* * The basic unit of block I/O is a sector. It is used in a number of contexts * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9 * bytes. Variables of type sector_t represent an offset or size that is a * multiple of 512 bytes. Hence these two constants. */ #ifndef SECTOR_SHIFT #define SECTOR_SHIFT 9 #endif #ifndef SECTOR_SIZE #define SECTOR_SIZE (1 << SECTOR_SHIFT) #endif #define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) #define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) #define SECTOR_MASK (PAGE_SECTORS - 1) /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request * blk_rq_cur_bytes() : bytes left in the current segment * blk_rq_err_bytes() : bytes left till the next error boundary * blk_rq_sectors() : sectors left in the entire request * blk_rq_cur_sectors() : sectors left in the current segment * blk_rq_stats_sectors() : sectors of the entire request used for stats */ static inline sector_t blk_rq_pos(const struct request *rq) { return rq->__sector; } static inline unsigned int blk_rq_bytes(const struct request *rq) { return rq->__data_len; } static inline int blk_rq_cur_bytes(const struct request *rq) { return rq->bio ? bio_cur_bytes(rq->bio) : 0; } extern unsigned int blk_rq_err_bytes(const struct request *rq); static inline unsigned int blk_rq_sectors(const struct request *rq) { return blk_rq_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_cur_sectors(const struct request *rq) { return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_stats_sectors(const struct request *rq) { return rq->stats_sectors; } #ifdef CONFIG_BLK_DEV_ZONED /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond); static inline unsigned int bio_zone_no(struct bio *bio) { return blk_queue_zone_no(bdev_get_queue(bio->bi_bdev), bio->bi_iter.bi_sector); } static inline unsigned int bio_zone_is_seq(struct bio *bio) { return blk_queue_zone_is_seq(bdev_get_queue(bio->bi_bdev), bio->bi_iter.bi_sector); } static inline unsigned int blk_rq_zone_no(struct request *rq) { return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); } static inline unsigned int blk_rq_zone_is_seq(struct request *rq) { return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq)); } #endif /* CONFIG_BLK_DEV_ZONED */ /* * Some commands like WRITE SAME have a payload or data transfer size which * is different from the size of the request. Any driver that supports such * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to * calculate the data transfer size. */ static inline unsigned int blk_rq_payload_bytes(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec.bv_len; return blk_rq_bytes(rq); } /* * Return the first full biovec in the request. The caller needs to check that * there are any bvecs before calling this helper. */ static inline struct bio_vec req_bvec(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec; return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter); } static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, int op) { if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) return min(q->limits.max_discard_sectors, UINT_MAX >> SECTOR_SHIFT); if (unlikely(op == REQ_OP_WRITE_SAME)) return q->limits.max_write_same_sectors; if (unlikely(op == REQ_OP_WRITE_ZEROES)) return q->limits.max_write_zeroes_sectors; return q->limits.max_sectors; } /* * Return maximum size of a request at given offset. Only valid for * file system requests. */ static inline unsigned int blk_max_size_offset(struct request_queue *q, sector_t offset, unsigned int chunk_sectors) { if (!chunk_sectors) { if (q->limits.chunk_sectors) chunk_sectors = q->limits.chunk_sectors; else return q->limits.max_sectors; } if (likely(is_power_of_2(chunk_sectors))) chunk_sectors -= offset & (chunk_sectors - 1); else chunk_sectors -= sector_div(offset, chunk_sectors); return min(q->limits.max_sectors, chunk_sectors); } static inline unsigned int blk_rq_get_max_sectors(struct request *rq, sector_t offset) { struct request_queue *q = rq->q; if (blk_rq_is_passthrough(rq)) return q->limits.max_hw_sectors; if (!q->limits.chunk_sectors || req_op(rq) == REQ_OP_DISCARD || req_op(rq) == REQ_OP_SECURE_ERASE) return blk_queue_get_max_sectors(q, req_op(rq)); return min(blk_max_size_offset(q, offset, 0), blk_queue_get_max_sectors(q, req_op(rq))); } static inline unsigned int blk_rq_count_bios(struct request *rq) { unsigned int nr_bios = 0; struct bio *bio; __rq_for_each_bio(bio, rq) nr_bios++; return nr_bios; } void blk_steal_bios(struct bio_list *list, struct request *rq); /* * Request completion related functions. * * blk_update_request() completes given number of bytes and updates * the request without completing it. */ extern bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); extern void blk_abort_request(struct request *); /* * Access functions for manipulating queue properties */ extern void blk_cleanup_queue(struct request_queue *); void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce limit); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_discard_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); extern void blk_queue_max_write_same_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); extern void blk_queue_max_zone_append_sectors(struct request_queue *q, unsigned int max_zone_append_sectors); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); void blk_queue_zone_write_granularity(struct request_queue *q, unsigned int size); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); void disk_update_readahead(struct gendisk *disk); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_default_limits(struct queue_limits *lim); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, sector_t offset); extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); extern void blk_queue_required_elevator_features(struct request_queue *q, unsigned int features); extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q, struct device *dev); /* * Number of physical segments as sent to the device. * * Normally this is the number of discontiguous data segments sent by the * submitter. But for data-less command like discard we might have no * actual data segments submitted, but the driver might have to add it's * own special payload. In that case we still return 1 here so that this * special payload will be mapped. */ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return 1; return rq->nr_phys_segments; } /* * Number of discard segments (or ranges) the driver needs to fill in. * Each discard bio merged into a request is counted as one segment. */ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) { return max_t(unsigned short, rq->nr_phys_segments, 1); } int __blk_rq_map_sg(struct request_queue *q, struct request *rq, struct scatterlist *sglist, struct scatterlist **last_sg); static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, struct scatterlist *sglist) { struct scatterlist *last_sg = NULL; return __blk_rq_map_sg(q, rq, sglist, &last_sg); } extern void blk_dump_rq_flags(struct request *, char *); bool __must_check blk_get_queue(struct request_queue *); extern void blk_put_queue(struct request_queue *); void blk_mark_disk_dead(struct gendisk *disk); #ifdef CONFIG_BLOCK /* * blk_plug permits building a queue of related requests by holding the I/O * fragments for a short period. This allows merging of sequential requests * into single larger request. As the requests are moved from a per-task list to * the device's request_queue in a batch, this results in improved scalability * as the lock contention for request_queue lock is reduced. * * It is ok not to disable preemption when adding the request to the plug list * or when attempting a merge, because blk_schedule_flush_list() will only flush * the plug list when the task sleeps by itself. For details, please see * schedule() where blk_schedule_flush_plug() is called. */ struct blk_plug { struct list_head mq_list; /* blk-mq requests */ struct list_head cb_list; /* md requires an unplug callback */ unsigned short rq_count; bool multiple_queues; bool nowait; }; struct blk_plug_cb; typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool); struct blk_plug_cb { struct list_head list; blk_plug_cb_fn callback; void *data; }; extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, int size); extern void blk_start_plug(struct blk_plug *); extern void blk_finish_plug(struct blk_plug *); extern void blk_flush_plug_list(struct blk_plug *, bool); static inline void blk_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; if (plug) blk_flush_plug_list(plug, false); } static inline void blk_schedule_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; if (plug) blk_flush_plug_list(plug, true); } static inline bool blk_needs_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; return plug && (!list_empty(&plug->mq_list) || !list_empty(&plug->cb_list)); } int blkdev_issue_flush(struct block_device *bdev); long nr_blockdev_pages(void); #else /* CONFIG_BLOCK */ struct blk_plug { }; static inline void blk_start_plug(struct blk_plug *plug) { } static inline void blk_finish_plug(struct blk_plug *plug) { } static inline void blk_flush_plug(struct task_struct *task) { } static inline void blk_schedule_flush_plug(struct task_struct *task) { } static inline bool blk_needs_flush_plug(struct task_struct *tsk) { return false; } static inline int blkdev_issue_flush(struct block_device *bdev) { return 0; } static inline long nr_blockdev_pages(void) { return 0; } #endif /* CONFIG_BLOCK */ extern void blk_io_schedule(void); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); #define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, int flags, struct bio **biop); #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, unsigned flags); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned flags); static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) { return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), gfp_mask, flags); } static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask) { return blkdev_issue_zeroout(sb->s_bdev, block << (sb->s_blocksize_bits - SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), gfp_mask, 0); } static inline bool bdev_is_partition(struct block_device *bdev) { return bdev->bd_partno; } enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, BLK_MAX_SEGMENT_SIZE = 65536, BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; #define BLK_DEF_MAX_SECTORS 2560u static inline unsigned long queue_segment_boundary(const struct request_queue *q) { return q->limits.seg_boundary_mask; } static inline unsigned long queue_virt_boundary(const struct request_queue *q) { return q->limits.virt_boundary_mask; } static inline unsigned int queue_max_sectors(const struct request_queue *q) { return q->limits.max_sectors; } static inline unsigned int queue_max_bytes(struct request_queue *q) { return min_t(unsigned int, queue_max_sectors(q), INT_MAX >> 9) << 9; } static inline unsigned int queue_max_hw_sectors(const struct request_queue *q) { return q->limits.max_hw_sectors; } static inline unsigned short queue_max_segments(const struct request_queue *q) { return q->limits.max_segments; } static inline unsigned short queue_max_discard_segments(const struct request_queue *q) { return q->limits.max_discard_segments; } static inline unsigned int queue_max_segment_size(const struct request_queue *q) { return q->limits.max_segment_size; } static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q) { const struct queue_limits *l = &q->limits; return min(l->max_zone_append_sectors, l->max_sectors); } static inline unsigned int bdev_max_zone_append_sectors(struct block_device *bdev) { return queue_max_zone_append_sectors(bdev_get_queue(bdev)); } static inline unsigned int bdev_max_segments(struct block_device *bdev) { return queue_max_segments(bdev_get_queue(bdev)); } static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; if (q && q->limits.logical_block_size) retval = q->limits.logical_block_size; return retval; } static inline unsigned int bdev_logical_block_size(struct block_device *bdev) { return queue_logical_block_size(bdev_get_queue(bdev)); } static inline unsigned int queue_physical_block_size(const struct request_queue *q) { return q->limits.physical_block_size; } static inline unsigned int bdev_physical_block_size(struct block_device *bdev) { return queue_physical_block_size(bdev_get_queue(bdev)); } static inline unsigned int queue_io_min(const struct request_queue *q) { return q->limits.io_min; } static inline unsigned int bdev_io_min(struct block_device *bdev) { return queue_io_min(bdev_get_queue(bdev)); } static inline unsigned int queue_io_opt(const struct request_queue *q) { return q->limits.io_opt; } static inline int bdev_io_opt(struct block_device *bdev) { return queue_io_opt(bdev_get_queue(bdev)); } static inline unsigned int queue_zone_write_granularity(const struct request_queue *q) { return q->limits.zone_write_granularity; } static inline unsigned int bdev_zone_write_granularity(struct block_device *bdev) { return queue_zone_write_granularity(bdev_get_queue(bdev)); } static inline int queue_alignment_offset(const struct request_queue *q) { if (q->limits.misaligned) return -1; return q->limits.alignment_offset; } static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) << SECTOR_SHIFT; return (granularity + lim->alignment_offset - alignment) % granularity; } static inline int bdev_alignment_offset(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q->limits.misaligned) return -1; if (bdev_is_partition(bdev)) return queue_limit_alignment_offset(&q->limits, bdev->bd_start_sect); return q->limits.alignment_offset; } static inline int queue_discard_alignment(const struct request_queue *q) { if (q->limits.discard_misaligned) return -1; return q->limits.discard_alignment; } static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) { unsigned int alignment, granularity, offset; if (!lim->max_discard_sectors) return 0; /* Why are these in bytes, not sectors? */ alignment = lim->discard_alignment >> SECTOR_SHIFT; granularity = lim->discard_granularity >> SECTOR_SHIFT; if (!granularity) return 0; /* Offset of the partition start in 'granularity' sectors */ offset = sector_div(sector, granularity); /* And why do we do this modulus *again* in blkdev_issue_discard()? */ offset = (granularity + alignment - offset) % granularity; /* Turn it back into bytes, gaah */ return offset << SECTOR_SHIFT; } /* * Two cases of handling DISCARD merge: * If max_discard_segments > 1, the driver takes every bio * as a range and send them to controller together. The ranges * needn't to be contiguous. * Otherwise, the bios/requests will be handled as same as * others which should be contiguous. */ static inline bool blk_discard_mergable(struct request *req) { if (req_op(req) == REQ_OP_DISCARD && queue_max_discard_segments(req->q) > 1) return true; return false; } static inline int bdev_discard_alignment(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (bdev_is_partition(bdev)) return queue_limit_discard_alignment(&q->limits, bdev->bd_start_sect); return q->limits.discard_alignment; } static inline unsigned int bdev_write_same(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return q->limits.max_write_same_sectors; return 0; } static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return q->limits.max_write_zeroes_sectors; return 0; } static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return blk_queue_zoned_model(q); return BLK_ZONED_NONE; } static inline bool bdev_is_zoned(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return blk_queue_is_zoned(q); return false; } static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return blk_queue_zone_sectors(q); return 0; } static inline unsigned int bdev_max_open_zones(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return queue_max_open_zones(q); return 0; } static inline unsigned int bdev_max_active_zones(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return queue_max_active_zones(q); return 0; } static inline int queue_dma_alignment(const struct request_queue *q) { return q ? q->dma_alignment : 511; } static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr, unsigned int len) { unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask; return !(addr & alignment) && !(len & alignment); } /* assumes size > 256 */ static inline unsigned int blksize_bits(unsigned int size) { unsigned int bits = 8; do { bits++; size >>= 1; } while (size > 256); return bits; } static inline unsigned int block_size(struct block_device *bdev) { return 1 << bdev->bd_inode->i_blkbits; } int kblockd_schedule_work(struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ MODULE_ALIAS("block-major-" __stringify(major) "-*") #if defined(CONFIG_BLK_DEV_INTEGRITY) enum blk_integrity_flags { BLK_INTEGRITY_VERIFY = 1 << 0, BLK_INTEGRITY_GENERATE = 1 << 1, BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2, BLK_INTEGRITY_IP_CHECKSUM = 1 << 3, }; struct blk_integrity_iter { void *prot_buf; void *data_buf; sector_t seed; unsigned int data_size; unsigned short interval; const char *disk_name; }; typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *); typedef void (integrity_prepare_fn) (struct request *); typedef void (integrity_complete_fn) (struct request *, unsigned int); struct blk_integrity_profile { integrity_processing_fn *generate_fn; integrity_processing_fn *verify_fn; integrity_prepare_fn *prepare_fn; integrity_complete_fn *complete_fn; const char *name; }; extern void blk_integrity_register(struct gendisk *, struct blk_integrity *); extern void blk_integrity_unregister(struct gendisk *); extern int blk_integrity_compare(struct gendisk *, struct gendisk *); extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { struct blk_integrity *bi = &disk->queue->integrity; if (!bi->profile) return NULL; return bi; } static inline struct blk_integrity *bdev_get_integrity(struct block_device *bdev) { return blk_get_integrity(bdev->bd_disk); } static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) { return q->integrity.profile; } static inline bool blk_integrity_rq(struct request *rq) { return rq->cmd_flags & REQ_INTEGRITY; } static inline void blk_queue_max_integrity_segments(struct request_queue *q, unsigned int segs) { q->limits.max_integrity_segments = segs; } static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { return q->limits.max_integrity_segments; } /** * bio_integrity_intervals - Return number of integrity intervals for a bio * @bi: blk_integrity profile for device * @sectors: Size of the bio in 512-byte sectors * * Description: The block layer calculates everything in 512 byte * sectors but integrity metadata is done in terms of the data integrity * interval size of the storage device. Convert the block layer sectors * to the appropriate number of integrity intervals. */ static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { return sectors >> (bi->interval_exp - 9); } static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, unsigned int sectors) { return bio_integrity_intervals(bi, sectors) * bi->tuple_size; } /* * Return the first bvec that contains integrity data. Only drivers that are * limited to a single integrity segment should use this helper. */ static inline struct bio_vec *rq_integrity_vec(struct request *rq) { if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1)) return NULL; return rq->bio->bi_integrity->bip_vec; } #else /* CONFIG_BLK_DEV_INTEGRITY */ struct bio; struct block_device; struct gendisk; struct blk_integrity; static inline int blk_integrity_rq(struct request *rq) { return 0; } static inline int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *b) { return 0; } static inline int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *b, struct scatterlist *s) { return 0; } static inline struct blk_integrity *bdev_get_integrity(struct block_device *b) { return NULL; } static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { return NULL; } static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) { return false; } static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) { return 0; } static inline void blk_integrity_register(struct gendisk *d, struct blk_integrity *b) { } static inline void blk_integrity_unregister(struct gendisk *d) { } static inline void blk_queue_max_integrity_segments(struct request_queue *q, unsigned int segs) { } static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { return 0; } static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { return 0; } static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, unsigned int sectors) { return 0; } static inline struct bio_vec *rq_integrity_vec(struct request *rq) { return NULL; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ #ifdef CONFIG_BLK_INLINE_ENCRYPTION bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q); void blk_ksm_unregister(struct request_queue *q); #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q) { return true; } static inline void blk_ksm_unregister(struct request_queue *q) { } #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ struct block_device_operations { blk_qc_t (*submit_bio) (struct bio *bio); int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); void (*unlock_native_capacity) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); int (*set_read_only)(struct block_device *bdev, bool ro); /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); char *(*devnode)(struct gendisk *disk, umode_t *mode); struct module *owner; const struct pr_ops *pr_ops; /* * Special callback for probing GPT entry at a given sector. * Needed by Android devices, used by GPT scanner and MMC blk * driver. */ int (*alternative_gpt_sector)(struct gendisk *disk, sector_t *sector); ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_OEM_DATA(1); }; #ifdef CONFIG_COMPAT extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t, unsigned int, unsigned long); #else #define blkdev_compat_ptr_ioctl NULL #endif extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); #ifdef CONFIG_BLK_DEV_ZONED bool blk_req_needs_zone_write_lock(struct request *rq); bool blk_req_zone_write_trylock(struct request *rq); void __blk_req_zone_write_lock(struct request *rq); void __blk_req_zone_write_unlock(struct request *rq); static inline void blk_req_zone_write_lock(struct request *rq) { if (blk_req_needs_zone_write_lock(rq)) __blk_req_zone_write_lock(rq); } static inline void blk_req_zone_write_unlock(struct request *rq) { if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED) __blk_req_zone_write_unlock(rq); } static inline bool blk_req_zone_is_write_locked(struct request *rq) { return rq->q->seq_zones_wlock && test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock); } static inline bool blk_req_can_dispatch_to_zone(struct request *rq) { if (!blk_req_needs_zone_write_lock(rq)) return true; return !blk_req_zone_is_write_locked(rq); } #else static inline bool blk_req_needs_zone_write_lock(struct request *rq) { return false; } static inline void blk_req_zone_write_lock(struct request *rq) { } static inline void blk_req_zone_write_unlock(struct request *rq) { } static inline bool blk_req_zone_is_write_locked(struct request *rq) { return false; } static inline bool blk_req_can_dispatch_to_zone(struct request *rq) { return true; } #endif /* CONFIG_BLK_DEV_ZONED */ static inline void blk_wake_io_task(struct task_struct *waiter) { /* * If we're polling, the task itself is doing the completions. For * that case, we don't need to signal a wakeup, it's enough to just * mark us as RUNNING. */ if (waiter == current) __set_current_state(TASK_RUNNING); else wake_up_process(waiter); } unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op); void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time); void bio_start_io_acct_time(struct bio *bio, unsigned long start_time); unsigned long bio_start_io_acct(struct bio *bio); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev); /** * bio_end_io_acct - end I/O accounting for bio based drivers * @bio: bio to end account for * @start: start time returned by bio_start_io_acct() */ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev); } int bdev_read_only(struct block_device *bdev); int set_blocksize(struct block_device *bdev, int size); const char *bdevname(struct block_device *bdev, char *buffer); int lookup_bdev(const char *pathname, dev_t *dev); void blkdev_show(struct seq_file *seqf, off_t offset); #define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ #define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ #ifdef CONFIG_BLOCK #define BLKDEV_MAJOR_MAX 512 #else #define BLKDEV_MAJOR_MAX 0 #endif struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); int bd_prepare_to_claim(struct block_device *bdev, void *holder); void bd_abort_claiming(struct block_device *bdev, void *holder); void blkdev_put(struct block_device *bdev, fmode_t mode); /* just for blk-cgroup, don't use elsewhere */ struct block_device *blkdev_get_no_open(dev_t dev); void blkdev_put_no_open(struct block_device *bdev); struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); void bdev_add(struct block_device *bdev, dev_t dev); struct block_device *I_BDEV(struct inode *inode); int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, loff_t lend); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); int sync_blockdev(struct block_device *bdev); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); #else static inline void invalidate_bdev(struct block_device *bdev) { } static inline int sync_blockdev(struct block_device *bdev) { return 0; } static inline int sync_blockdev_nowait(struct block_device *bdev) { return 0; } static inline void sync_bdevs(bool wait) { } #endif int fsync_bdev(struct block_device *bdev); int freeze_bdev(struct block_device *bdev); int thaw_bdev(struct block_device *bdev); #endif /* _LINUX_BLKDEV_H */ |
| 4 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV4 GSO/GRO offload support * Linux INET implementation * * UDPv4 GSO support */ #include <linux/skbuff.h> #include <net/ip6_checksum.h> #include <net/udp.h> #include <net/protocol.h> #include <net/inet_common.h> static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, netdev_features_t features), __be16 new_protocol, bool is_ipv6) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); bool remcsum, need_csum, offload_csum, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); struct udphdr *uh = udp_hdr(skb); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int udp_offset, outer_hlen; __wsum partial; bool need_ipsec; if (unlikely(!pskb_may_pull(skb, tnl_hlen))) goto out; /* Adjust partial header checksum to negate old length. * We cannot rely on the value contained in uh->len as it is * possible that the actual value exceeds the boundaries of the * 16 bit length field due to the header being added outside of an * IP or IPv6 frame that was already limited to 64K - 1. */ if (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) partial = (__force __wsum)uh->len; else partial = (__force __wsum)htonl(skb->len); partial = csum_sub(csum_unfold(uh->check), partial); /* setup inner skb. */ skb->encapsulation = 0; SKB_GSO_CB(skb)->encap_level = 0; __skb_pull(skb, tnl_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, skb_inner_network_offset(skb)); skb_set_transport_header(skb, skb_inner_transport_offset(skb)); skb->mac_len = skb_inner_network_offset(skb); skb->protocol = new_protocol; need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM); skb->encap_hdr_csum = need_csum; remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM); skb->remcsum_offload = remcsum; need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && (skb->dev->features & (is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) : (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM)))); features &= skb->dev->hw_enc_features; if (need_csum) features &= ~NETIF_F_SCTP_CRC; /* The only checksum offload we care about from here on out is the * outer one so strip the existing checksum feature flags and * instead set the flag based on our outer checksum offload value. */ if (remcsum) { features &= ~NETIF_F_CSUM_MASK; if (!need_csum || offload_csum) features |= NETIF_F_HW_CSUM; } /* segment inner packet. */ segs = gso_inner_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset, mac_len); goto out; } gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); outer_hlen = skb_tnl_header_len(skb); udp_offset = outer_hlen - tnl_hlen; skb = segs; do { unsigned int len; if (remcsum) skb->ip_summed = CHECKSUM_NONE; /* Set up inner headers if we are offloading inner checksum */ if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_reset_inner_headers(skb); skb->encapsulation = 1; } skb->mac_len = mac_len; skb->protocol = protocol; __skb_push(skb, outer_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_set_transport_header(skb, udp_offset); len = skb->len - udp_offset; uh = udp_hdr(skb); /* If we are only performing partial GSO the inner header * will be using a length value equal to only one MSS sized * segment instead of the entire frame. */ if (gso_partial && skb_is_gso(skb)) { uh->len = htons(skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)uh); } else { uh->len = htons(len); } if (!need_csum) continue; uh->check = ~csum_fold(csum_add(partial, (__force __wsum)htonl(len))); if (skb->encapsulation || !offload_csum) { uh->check = gso_make_checksum(skb, ~uh->check); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); } } while ((skb = skb->next)); out: return segs; } struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) { const struct net_offload __rcu **offloads; __be16 protocol = skb->protocol; const struct net_offload *ops; struct sk_buff *segs = ERR_PTR(-EINVAL); struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, netdev_features_t features); rcu_read_lock(); switch (skb->inner_protocol_type) { case ENCAP_TYPE_ETHER: protocol = skb->inner_protocol; gso_inner_segment = skb_mac_gso_segment; break; case ENCAP_TYPE_IPPROTO: offloads = is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[skb->inner_ipproto]); if (!ops || !ops->callbacks.gso_segment) goto out_unlock; gso_inner_segment = ops->callbacks.gso_segment; break; default: goto out_unlock; } segs = __skb_udp_tunnel_segment(skb, features, gso_inner_segment, protocol, is_ipv6); out_unlock: rcu_read_unlock(); return segs; } EXPORT_SYMBOL(skb_udp_tunnel_segment); static void __udpv4_gso_segment_csum(struct sk_buff *seg, __be32 *oldip, __be32 *newip, __be16 *oldport, __be16 *newport) { struct udphdr *uh; struct iphdr *iph; if (*oldip == *newip && *oldport == *newport) return; uh = udp_hdr(seg); iph = ip_hdr(seg); if (uh->check) { inet_proto_csum_replace4(&uh->check, seg, *oldip, *newip, true); inet_proto_csum_replace2(&uh->check, seg, *oldport, *newport, false); if (!uh->check) uh->check = CSUM_MANGLED_0; } *oldport = *newport; csum_replace4(&iph->check, *oldip, *newip); *oldip = *newip; } static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs) { struct sk_buff *seg; struct udphdr *uh, *uh2; struct iphdr *iph, *iph2; seg = segs; uh = udp_hdr(seg); iph = ip_hdr(seg); if ((udp_hdr(seg)->dest == udp_hdr(seg->next)->dest) && (udp_hdr(seg)->source == udp_hdr(seg->next)->source) && (ip_hdr(seg)->daddr == ip_hdr(seg->next)->daddr) && (ip_hdr(seg)->saddr == ip_hdr(seg->next)->saddr)) return segs; while ((seg = seg->next)) { uh2 = udp_hdr(seg); iph2 = ip_hdr(seg); __udpv4_gso_segment_csum(seg, &iph2->saddr, &iph->saddr, &uh2->source, &uh->source); __udpv4_gso_segment_csum(seg, &iph2->daddr, &iph->daddr, &uh2->dest, &uh->dest); } return segs; } static void __udpv6_gso_segment_csum(struct sk_buff *seg, struct in6_addr *oldip, const struct in6_addr *newip, __be16 *oldport, __be16 newport) { struct udphdr *uh = udp_hdr(seg); if (ipv6_addr_equal(oldip, newip) && *oldport == newport) return; if (uh->check) { inet_proto_csum_replace16(&uh->check, seg, oldip->s6_addr32, newip->s6_addr32, true); inet_proto_csum_replace2(&uh->check, seg, *oldport, newport, false); if (!uh->check) uh->check = CSUM_MANGLED_0; } *oldip = *newip; *oldport = newport; } static struct sk_buff *__udpv6_gso_segment_list_csum(struct sk_buff *segs) { const struct ipv6hdr *iph; const struct udphdr *uh; struct ipv6hdr *iph2; struct sk_buff *seg; struct udphdr *uh2; seg = segs; uh = udp_hdr(seg); iph = ipv6_hdr(seg); uh2 = udp_hdr(seg->next); iph2 = ipv6_hdr(seg->next); if (!(*(const u32 *)&uh->source ^ *(const u32 *)&uh2->source) && ipv6_addr_equal(&iph->saddr, &iph2->saddr) && ipv6_addr_equal(&iph->daddr, &iph2->daddr)) return segs; while ((seg = seg->next)) { uh2 = udp_hdr(seg); iph2 = ipv6_hdr(seg); __udpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr, &uh2->source, uh->source); __udpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr, &uh2->dest, uh->dest); } return segs; } static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) { unsigned int mss = skb_shinfo(skb)->gso_size; skb = skb_segment_list(skb, features, skb_mac_header_len(skb)); if (IS_ERR(skb)) return skb; udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss); if (is_ipv6) return __udpv6_gso_segment_list_csum(skb); else return __udpv4_gso_segment_list_csum(skb); } struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features, bool is_ipv6) { struct sock *sk = gso_skb->sk; unsigned int sum_truesize = 0; struct sk_buff *segs, *seg; struct udphdr *uh; unsigned int mss; bool copy_dtor; __sum16 check; __be16 newlen; mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); if (unlikely(skb_checksum_start(gso_skb) != skb_transport_header(gso_skb) && !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST))) return ERR_PTR(-EINVAL); if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), mss); return NULL; } if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) { /* Detect modified geometry and pass those to skb_segment. */ if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) return __udp_gso_segment_list(gso_skb, features, is_ipv6); /* Setup csum, as fraglist skips this in udp4_gro_receive. */ gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head; gso_skb->csum_offset = offsetof(struct udphdr, check); gso_skb->ip_summed = CHECKSUM_PARTIAL; uh = udp_hdr(gso_skb); if (is_ipv6) uh->check = ~udp_v6_check(gso_skb->len, &ipv6_hdr(gso_skb)->saddr, &ipv6_hdr(gso_skb)->daddr, 0); else uh->check = ~udp_v4_check(gso_skb->len, ip_hdr(gso_skb)->saddr, ip_hdr(gso_skb)->daddr, 0); } skb_pull(gso_skb, sizeof(*uh)); /* clear destructor to avoid skb_segment assigning it to tail */ copy_dtor = gso_skb->destructor == sock_wfree; if (copy_dtor) { gso_skb->destructor = NULL; gso_skb->sk = NULL; } segs = skb_segment(gso_skb, features); if (IS_ERR_OR_NULL(segs)) { if (copy_dtor) { gso_skb->destructor = sock_wfree; gso_skb->sk = sk; } return segs; } /* GSO partial and frag_list segmentation only requires splitting * the frame into an MSS multiple and possibly a remainder, both * cases return a GSO skb. So update the mss now. */ if (skb_is_gso(segs)) mss *= skb_shinfo(segs)->gso_segs; seg = segs; uh = udp_hdr(seg); /* preserve TX timestamp flags and TS key for first segment */ skb_shinfo(seg)->tskey = skb_shinfo(gso_skb)->tskey; skb_shinfo(seg)->tx_flags |= (skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP); /* compute checksum adjustment based on old length versus new */ newlen = htons(sizeof(*uh) + mss); check = csum16_add(csum16_sub(uh->check, uh->len), newlen); for (;;) { if (copy_dtor) { seg->destructor = sock_wfree; seg->sk = sk; sum_truesize += seg->truesize; } if (!seg->next) break; uh->len = newlen; uh->check = check; if (seg->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(seg, ~check); else uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; seg = seg->next; uh = udp_hdr(seg); } /* last packet can be partial gso_size, account for that in checksum */ newlen = htons(skb_tail_pointer(seg) - skb_transport_header(seg) + seg->data_len); check = csum16_add(csum16_sub(uh->check, uh->len), newlen); uh->len = newlen; uh->check = check; if (seg->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(seg, ~check); else uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; /* update refcount for the packet */ if (copy_dtor) { int delta = sum_truesize - gso_skb->truesize; /* In some pathological cases, delta can be negative. * We need to either use refcount_add() or refcount_sub_and_test() */ if (likely(delta >= 0)) refcount_add(delta, &sk->sk_wmem_alloc); else WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc)); } return segs; } EXPORT_SYMBOL_GPL(__udp_gso_segment); static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; __wsum csum; struct udphdr *uh; struct iphdr *iph; if (skb->encapsulation && (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) { segs = skb_udp_tunnel_segment(skb, features, false); goto out; } if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4))) goto out; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; /* Do software UFO. Complete and fill in the UDP checksum as * HW cannot do checksum of UDP packets sent as multiple * IP fragments. */ uh = udp_hdr(skb); iph = ip_hdr(skb); uh->check = 0; csum = skb_checksum(skb, 0, skb->len, 0); uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_UNNECESSARY; /* If there is no outer header we can fake a checksum offload * due to the fact that we have already done the checksum in * software prior to segmenting the frame. */ if (!skb->encap_hdr_csum) features |= NETIF_F_HW_CSUM; /* Fragment the skb. IP headers of the fragments are updated in * inet_gso_segment() */ segs = skb_segment(skb, features); out: return segs; } #define UDP_GRO_CNT_MAX 64 static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sk_buff *pp = NULL; struct udphdr *uh2; struct sk_buff *p; unsigned int ulen; int ret = 0; int flush; /* requires non zero csum, for symmetry with GSO */ if (!uh->check) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } /* Do not deal with padded or malicious packets, sorry ! */ ulen = ntohs(uh->len); if (ulen <= sizeof(*uh) || ulen != skb_gro_len(skb)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } /* pull encapsulating udp header */ skb_gro_pull(skb, sizeof(struct udphdr)); list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; uh2 = udp_hdr(p); /* Match ports only, as csum is always non zero */ if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } if (NAPI_GRO_CB(skb)->is_flist != NAPI_GRO_CB(p)->is_flist) { NAPI_GRO_CB(skb)->flush = 1; return p; } flush = NAPI_GRO_CB(p)->flush; if (NAPI_GRO_CB(p)->flush_id != 1 || NAPI_GRO_CB(p)->count != 1 || !NAPI_GRO_CB(p)->is_atomic) flush |= NAPI_GRO_CB(p)->flush_id; else NAPI_GRO_CB(p)->is_atomic = false; /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot * leading to excessive truesize values. * On len mismatch merge the first packet shorter than gso_size, * otherwise complete the GRO packet. */ if (ulen > ntohs(uh2->len) || flush) { pp = p; } else { if (NAPI_GRO_CB(skb)->is_flist) { if (!pskb_may_pull(skb, skb_gro_offset(skb))) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } if ((skb->ip_summed != p->ip_summed) || (skb->csum_level != p->csum_level)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } ret = skb_gro_receive_list(p, skb); } else { skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); ret = skb_gro_receive(p, skb); } } if (ret || ulen != ntohs(uh2->len) || NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX) pp = p; return pp; } /* mismatch, but we never need to flush */ return NULL; } struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, struct udphdr *uh, struct sock *sk) { struct sk_buff *pp = NULL; struct sk_buff *p; struct udphdr *uh2; unsigned int off = skb_gro_offset(skb); int flush = 1; /* We can do L4 aggregation only if the packet can't land in a tunnel * otherwise we could corrupt the inner stream. Detecting such packets * cannot be foolproof and the aggregation might still happen in some * cases. Such packets should be caught in udp_unexpected_gso later. */ NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { /* If the packet was locally encapsulated in a UDP tunnel that * wasn't detected above, do not GRO. */ if (skb->encapsulation) goto out; if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled : 1; if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) || (sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) return call_gro_receive(udp_gro_receive_segment, head, skb); /* no GRO, be sure flush the current packet */ goto out; } if (NAPI_GRO_CB(skb)->encap_mark || (uh->check && skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid)) goto out; /* mark that this skb passed once through the tunnel gro layer */ NAPI_GRO_CB(skb)->encap_mark = 1; flush = 0; list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; uh2 = (struct udphdr *)(p->data + off); /* Match ports and either checksums are either both zero * or nonzero. */ if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) || (!uh->check ^ !uh2->check)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); out: skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(udp_gro_receive); static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct iphdr *iph = skb_gro_network_header(skb); return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, iph->daddr, dport, inet_iif(skb), inet_sdif(skb), &udp_table, NULL); } INDIRECT_CALLABLE_SCOPE struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sock *sk = NULL; struct sk_buff *pp; if (unlikely(!uh)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ if (NAPI_GRO_CB(skb)->flush) goto skip; if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check, inet_gro_compute_pseudo)) goto flush; else if (uh->check) skb_gro_checksum_try_convert(skb, IPPROTO_UDP, inet_gro_compute_pseudo); skip: NAPI_GRO_CB(skb)->is_ipv6 = 0; if (static_branch_unlikely(&udp_encap_needed_key)) sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest); pp = udp_gro_receive(head, skb, uh, sk); return pp; flush: NAPI_GRO_CB(skb)->flush = 1; return NULL; } static int udp_gro_complete_segment(struct sk_buff *skb) { struct udphdr *uh = udp_hdr(skb); skb->csum_start = (unsigned char *)uh - skb->head; skb->csum_offset = offsetof(struct udphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4; if (skb->encapsulation) skb->inner_transport_header = skb->transport_header; return 0; } int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup) { __be16 newlen = htons(skb->len - nhoff); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); struct sock *sk; int err; uh->len = newlen; sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb, udp4_lib_lookup_skb, skb, uh->source, uh->dest); if (sk && udp_sk(sk)->gro_complete) { skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; /* clear the encap mark, so that inner frag_list gro_complete * can take place */ NAPI_GRO_CB(skb)->encap_mark = 0; /* Set encapsulation before calling into inner gro_complete() * functions to make them set up the inner offsets. */ skb->encapsulation = 1; err = udp_sk(sk)->gro_complete(sk, skb, nhoff + sizeof(struct udphdr)); } else { err = udp_gro_complete_segment(skb); } if (skb->remcsum_offload) skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM; return err; } EXPORT_SYMBOL(udp_gro_complete); INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) { const struct iphdr *iph = ip_hdr(skb); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) { uh->len = htons(skb->len - nhoff); skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; __skb_incr_checksum_unnecessary(skb); return 0; } if (uh->check) uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr, iph->daddr, 0); return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb); } static const struct net_offload udpv4_offload = { .callbacks = { .gso_segment = udp4_ufo_fragment, .gro_receive = udp4_gro_receive, .gro_complete = udp4_gro_complete, }, }; int __init udpv4_offload_init(void) { return inet_add_offload(&udpv4_offload, IPPROTO_UDP); } |
| 773 773 7 7 41 5 6 16 22 770 1 762 755 769 768 1 767 759 6 3 9 759 13 768 2 19 19 504 502 499 403 100 505 356 36 1 112 112 112 3 110 394 77 513 508 2 12 12 368 113 14 17 510 510 510 1 466 36 111 395 395 386 1 1 7 394 395 395 5 5 5 5 5 53 33 12 19 11 10 4 16 3 17 30 5 21 7 7 14 4 119 1 119 20 1 1 20 21 21 2 941 949 749 748 749 749 749 767 768 768 2 2 2 769 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Nicira, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/rculist.h> #include <linux/err.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <net/ip_tunnels.h> #include <net/arp.h> #include <net/checksum.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/udp.h> #include <net/dst_metadata.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #endif static unsigned int ip_tunnel_hash(__be32 key, __be32 remote) { return hash_32((__force u32)key ^ (__force u32)remote, IP_TNL_HASH_BITS); } static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p, __be16 flags, __be32 key) { if (p->i_flags & TUNNEL_KEY) { if (flags & TUNNEL_KEY) return key == p->i_key; else /* key expected, none present */ return false; } else return !(flags & TUNNEL_KEY); } /* Fallback tunnel: no source, no destination, no key, no options Tunnel hash table: We require exact key match i.e. if a key is present in packet it will match only tunnel with the same key; if it is not present, it will match only keyless tunnel. All keysless packets, if not matched configured keyless tunnels will match fallback tunnel. Given src, dst and key, find appropriate for input tunnel. */ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, int link, __be16 flags, __be32 remote, __be32 local, __be32 key) { struct ip_tunnel *t, *cand = NULL; struct hlist_head *head; struct net_device *ndev; unsigned int hash; hash = ip_tunnel_hash(key, remote); head = &itn->tunnels[hash]; hlist_for_each_entry_rcu(t, head, hash_node) { if (local != t->parms.iph.saddr || remote != t->parms.iph.daddr || !(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; if (t->parms.link == link) return t; else cand = t; } hlist_for_each_entry_rcu(t, head, hash_node) { if (remote != t->parms.iph.daddr || t->parms.iph.saddr != 0 || !(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; if (t->parms.link == link) return t; else if (!cand) cand = t; } hash = ip_tunnel_hash(key, 0); head = &itn->tunnels[hash]; hlist_for_each_entry_rcu(t, head, hash_node) { if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) && (local != t->parms.iph.daddr || !ipv4_is_multicast(local))) continue; if (!(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; if (t->parms.link == link) return t; else if (!cand) cand = t; } hlist_for_each_entry_rcu(t, head, hash_node) { if ((!(flags & TUNNEL_NO_KEY) && t->parms.i_key != key) || t->parms.iph.saddr != 0 || t->parms.iph.daddr != 0 || !(t->dev->flags & IFF_UP)) continue; if (t->parms.link == link) return t; else if (!cand) cand = t; } if (cand) return cand; t = rcu_dereference(itn->collect_md_tun); if (t && t->dev->flags & IFF_UP) return t; ndev = READ_ONCE(itn->fb_tunnel_dev); if (ndev && ndev->flags & IFF_UP) return netdev_priv(ndev); return NULL; } EXPORT_SYMBOL_GPL(ip_tunnel_lookup); static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, struct ip_tunnel_parm *parms) { unsigned int h; __be32 remote; __be32 i_key = parms->i_key; if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr)) remote = parms->iph.daddr; else remote = 0; if (!(parms->i_flags & TUNNEL_KEY) && (parms->i_flags & VTI_ISVTI)) i_key = 0; h = ip_tunnel_hash(i_key, remote); return &itn->tunnels[h]; } static void ip_tunnel_add(struct ip_tunnel_net *itn, struct ip_tunnel *t) { struct hlist_head *head = ip_bucket(itn, &t->parms); if (t->collect_md) rcu_assign_pointer(itn->collect_md_tun, t); hlist_add_head_rcu(&t->hash_node, head); } static void ip_tunnel_del(struct ip_tunnel_net *itn, struct ip_tunnel *t) { if (t->collect_md) rcu_assign_pointer(itn->collect_md_tun, NULL); hlist_del_init_rcu(&t->hash_node); } static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, struct ip_tunnel_parm *parms, int type) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; __be32 key = parms->i_key; __be16 flags = parms->i_flags; int link = parms->link; struct ip_tunnel *t = NULL; struct hlist_head *head = ip_bucket(itn, parms); hlist_for_each_entry_rcu(t, head, hash_node, lockdep_rtnl_is_held()) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && link == t->parms.link && type == t->dev->type && ip_tunnel_key_match(&t->parms, flags, key)) break; } return t; } static struct net_device *__ip_tunnel_create(struct net *net, const struct rtnl_link_ops *ops, struct ip_tunnel_parm *parms) { int err; struct ip_tunnel *tunnel; struct net_device *dev; char name[IFNAMSIZ]; err = -E2BIG; if (parms->name[0]) { if (!dev_valid_name(parms->name)) goto failed; strlcpy(name, parms->name, IFNAMSIZ); } else { if (strlen(ops->kind) > (IFNAMSIZ - 3)) goto failed; strcpy(name, ops->kind); strcat(name, "%d"); } ASSERT_RTNL(); dev = alloc_netdev(ops->priv_size, name, NET_NAME_UNKNOWN, ops->setup); if (!dev) { err = -ENOMEM; goto failed; } dev_net_set(dev, net); dev->rtnl_link_ops = ops; tunnel = netdev_priv(dev); tunnel->parms = *parms; tunnel->net = net; err = register_netdevice(dev); if (err) goto failed_free; return dev; failed_free: free_netdev(dev); failed: return ERR_PTR(err); } static int ip_tunnel_bind_dev(struct net_device *dev) { struct net_device *tdev = NULL; struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *iph; int hlen = LL_MAX_HEADER; int mtu = ETH_DATA_LEN; int t_hlen = tunnel->hlen + sizeof(struct iphdr); iph = &tunnel->parms.iph; /* Guess output device to choose reasonable mtu and needed_headroom */ if (iph->daddr) { struct flowi4 fl4; struct rtable *rt; ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, RT_TOS(iph->tos), tunnel->parms.link, tunnel->fwmark, 0); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { tdev = rt->dst.dev; ip_rt_put(rt); } if (dev->type != ARPHRD_ETHER) dev->flags |= IFF_POINTOPOINT; dst_cache_reset(&tunnel->dst_cache); } if (!tdev && tunnel->parms.link) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); if (tdev) { hlen = tdev->hard_header_len + tdev->needed_headroom; mtu = min(tdev->mtu, IP_MAX_MTU); } dev->needed_headroom = t_hlen + hlen; mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0); if (mtu < IPV4_MIN_MTU) mtu = IPV4_MIN_MTU; return mtu; } static struct ip_tunnel *ip_tunnel_create(struct net *net, struct ip_tunnel_net *itn, struct ip_tunnel_parm *parms) { struct ip_tunnel *nt; struct net_device *dev; int t_hlen; int mtu; int err; dev = __ip_tunnel_create(net, itn->rtnl_link_ops, parms); if (IS_ERR(dev)) return ERR_CAST(dev); mtu = ip_tunnel_bind_dev(dev); err = dev_set_mtu(dev, mtu); if (err) goto err_dev_set_mtu; nt = netdev_priv(dev); t_hlen = nt->hlen + sizeof(struct iphdr); dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP_MAX_MTU - t_hlen; if (dev->type == ARPHRD_ETHER) dev->max_mtu -= dev->hard_header_len; ip_tunnel_add(itn, nt); return nt; err_dev_set_mtu: unregister_netdevice(dev); return ERR_PTR(err); } int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error) { const struct iphdr *iph = ip_hdr(skb); int err; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { tunnel->dev->stats.multicast++; skb->pkt_type = PACKET_BROADCAST; } #endif if ((!(tpi->flags&TUNNEL_CSUM) && (tunnel->parms.i_flags&TUNNEL_CSUM)) || ((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) { tunnel->dev->stats.rx_crc_errors++; tunnel->dev->stats.rx_errors++; goto drop; } if (tunnel->parms.i_flags&TUNNEL_SEQ) { if (!(tpi->flags&TUNNEL_SEQ) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { tunnel->dev->stats.rx_fifo_errors++; tunnel->dev->stats.rx_errors++; goto drop; } tunnel->i_seqno = ntohl(tpi->seq) + 1; } skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &iph->saddr, iph->tos); if (err > 1) { ++tunnel->dev->stats.rx_frame_errors; ++tunnel->dev->stats.rx_errors; goto drop; } } dev_sw_netstats_rx_add(tunnel->dev, skb->len); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); if (tunnel->dev->type == ARPHRD_ETHER) { skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { skb->dev = tunnel->dev; } if (tun_dst) skb_dst_set(skb, (struct dst_entry *)tun_dst); gro_cells_receive(&tunnel->gro_cells, skb); return 0; drop: if (tun_dst) dst_release((struct dst_entry *)tun_dst); kfree_skb(skb); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_rcv); int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *ops, unsigned int num) { if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; return !cmpxchg((const struct ip_tunnel_encap_ops **) &iptun_encaps[num], NULL, ops) ? 0 : -1; } EXPORT_SYMBOL(ip_tunnel_encap_add_ops); int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *ops, unsigned int num) { int ret; if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; ret = (cmpxchg((const struct ip_tunnel_encap_ops **) &iptun_encaps[num], ops, NULL) == ops) ? 0 : -1; synchronize_net(); return ret; } EXPORT_SYMBOL(ip_tunnel_encap_del_ops); int ip_tunnel_encap_setup(struct ip_tunnel *t, struct ip_tunnel_encap *ipencap) { int hlen; memset(&t->encap, 0, sizeof(t->encap)); hlen = ip_encap_hlen(ipencap); if (hlen < 0) return hlen; t->encap.type = ipencap->type; t->encap.sport = ipencap->sport; t->encap.dport = ipencap->dport; t->encap.flags = ipencap->flags; t->encap_hlen = hlen; t->hlen = t->encap_hlen + t->tun_hlen; return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_encap_setup); static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, struct rtable *rt, __be16 df, const struct iphdr *inner_iph, int tunnel_hlen, __be32 dst, bool md) { struct ip_tunnel *tunnel = netdev_priv(dev); int pkt_size; int mtu; tunnel_hlen = md ? tunnel_hlen : tunnel->hlen; pkt_size = skb->len - tunnel_hlen; pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; if (df) { mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen); mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; } else { mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; } if (skb_valid_dst(skb)) skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!skb_is_gso(skb) && (inner_iph->frag_off & htons(IP_DF)) && mtu < pkt_size) { icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); return -E2BIG; } } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { struct rt6_info *rt6; __be32 daddr; rt6 = skb_valid_dst(skb) ? (struct rt6_info *)skb_dst(skb) : NULL; daddr = md ? dst : tunnel->parms.iph.daddr; if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) { if ((daddr && !ipv4_is_multicast(daddr)) || rt6->rt6i_dst.plen == 128) { rt6->rt6i_flags |= RTF_MODIFIED; dst_metric_set(skb_dst(skb), RTAX_MTU, mtu); } } if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU && mtu < pkt_size) { icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); return -E2BIG; } } #endif return 0; } static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom) { /* we must cap headroom to some upperlimit, else pskb_expand_head * will overflow header offsets in skb_headers_offset_update(). */ static const unsigned int max_allowed = 512; if (headroom > max_allowed) headroom = max_allowed; if (headroom > READ_ONCE(dev->needed_headroom)) WRITE_ONCE(dev->needed_headroom, headroom); } void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto, int tunnel_hlen) { struct ip_tunnel *tunnel = netdev_priv(dev); u32 headroom = sizeof(struct iphdr); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; const struct iphdr *inner_iph; struct rtable *rt = NULL; struct flowi4 fl4; __be16 df = 0; u8 tos, ttl; bool use_cache; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto tx_error; key = &tun_info->key; memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); inner_iph = (const struct iphdr *)skb_inner_network_header(skb); tos = key->tos; if (tos == 1) { if (skb->protocol == htons(ETH_P_IP)) tos = inner_iph->tos; else if (skb->protocol == htons(ETH_P_IPV6)) tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), RT_TOS(tos), 0, skb->mark, skb_get_hash(skb)); if (tunnel->encap.type != TUNNEL_ENCAP_NONE) goto tx_error; use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); if (use_cache) rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl4.saddr); if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { dev->stats.tx_carrier_errors++; goto tx_error; } if (use_cache) dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, fl4.saddr); } if (rt->dst.dev == dev) { ip_rt_put(rt); dev->stats.collisions++; goto tx_error; } if (key->tun_flags & TUNNEL_DONT_FRAGMENT) df = htons(IP_DF); if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, tunnel_hlen, key->u.ipv4.dst, true)) { ip_rt_put(rt); goto tx_error; } tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = key->ttl; if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) ttl = inner_iph->ttl; else if (skb->protocol == htons(ETH_P_IPV6)) ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; else ttl = ip4_dst_hoplimit(&rt->dst); } headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; if (skb_cow_head(skb, headroom)) { ip_rt_put(rt); goto tx_dropped; } ip_tunnel_adj_headroom(dev, headroom); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; tx_error: dev->stats.tx_errors++; goto kfree; tx_dropped: dev->stats.tx_dropped++; kfree: kfree_skb(skb); } EXPORT_SYMBOL_GPL(ip_md_tunnel_xmit); void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, u8 protocol) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_info *tun_info = NULL; const struct iphdr *inner_iph; unsigned int max_headroom; /* The extra header space needed */ struct rtable *rt = NULL; /* Route to the other host */ bool use_cache = false; struct flowi4 fl4; bool md = false; bool connected; u8 tos, ttl; __be32 dst; __be16 df; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ if (!skb_dst(skb)) { dev->stats.tx_fifo_errors++; goto tx_error; } tun_info = skb_tunnel_info(skb); if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX) && ip_tunnel_info_af(tun_info) == AF_INET && tun_info->key.u.ipv4.dst) { dst = tun_info->key.u.ipv4.dst; md = true; connected = true; } else if (skb->protocol == htons(ETH_P_IP)) { rt = skb_rtable(skb); dst = rt_nexthop(rt, inner_iph->daddr); } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { const struct in6_addr *addr6; struct neighbour *neigh; bool do_tx_error_icmp; int addr_type; neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); if (!neigh) goto tx_error; addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { addr6 = &ipv6_hdr(skb)->daddr; addr_type = ipv6_addr_type(addr6); } if ((addr_type & IPV6_ADDR_COMPATv4) == 0) do_tx_error_icmp = true; else { do_tx_error_icmp = false; dst = addr6->s6_addr32[3]; } neigh_release(neigh); if (do_tx_error_icmp) goto tx_error_icmp; } #endif else goto tx_error; if (!md) connected = false; } tos = tnl_params->tos; if (tos & 0x1) { tos &= ~0x1; if (skb->protocol == htons(ETH_P_IP)) { tos = inner_iph->tos; connected = false; } else if (skb->protocol == htons(ETH_P_IPV6)) { tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); connected = false; } } ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, tunnel->fwmark, skb_get_hash(skb)); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) goto tx_error; if (connected && md) { use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); if (use_cache) rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl4.saddr); } else { rt = connected ? dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr) : NULL; } if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { dev->stats.tx_carrier_errors++; goto tx_error; } if (use_cache) dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, fl4.saddr); else if (!md && connected) dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr); } if (rt->dst.dev == dev) { ip_rt_put(rt); dev->stats.collisions++; goto tx_error; } df = tnl_params->frag_off; if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df) df |= (inner_iph->frag_off & htons(IP_DF)); if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) { ip_rt_put(rt); goto tx_error; } if (tunnel->err_count > 0) { if (time_before(jiffies, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; dst_link_failure(skb); } else tunnel->err_count = 0; } tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = tnl_params->ttl; if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) ttl = inner_iph->ttl; #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; #endif else ttl = ip4_dst_hoplimit(&rt->dst); } max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); if (skb_cow_head(skb, max_headroom)) { ip_rt_put(rt); dev->stats.tx_dropped++; kfree_skb(skb); return; } ip_tunnel_adj_headroom(dev, max_headroom); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; #if IS_ENABLED(CONFIG_IPV6) tx_error_icmp: dst_link_failure(skb); #endif tx_error: dev->stats.tx_errors++; kfree_skb(skb); } EXPORT_SYMBOL_GPL(ip_tunnel_xmit); static void ip_tunnel_update(struct ip_tunnel_net *itn, struct ip_tunnel *t, struct net_device *dev, struct ip_tunnel_parm *p, bool set_mtu, __u32 fwmark) { ip_tunnel_del(itn, t); t->parms.iph.saddr = p->iph.saddr; t->parms.iph.daddr = p->iph.daddr; t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; if (dev->type != ARPHRD_ETHER) { memcpy(dev->dev_addr, &p->iph.saddr, 4); memcpy(dev->broadcast, &p->iph.daddr, 4); } ip_tunnel_add(itn, t); t->parms.iph.ttl = p->iph.ttl; t->parms.iph.tos = p->iph.tos; t->parms.iph.frag_off = p->iph.frag_off; if (t->parms.link != p->link || t->fwmark != fwmark) { int mtu; t->parms.link = p->link; t->fwmark = fwmark; mtu = ip_tunnel_bind_dev(dev); if (set_mtu) dev->mtu = mtu; } dst_cache_reset(&t->dst_cache); netdev_state_change(dev); } int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) { int err = 0; struct ip_tunnel *t = netdev_priv(dev); struct net *net = t->net; struct ip_tunnel_net *itn = net_generic(net, t->ip_tnl_net_id); switch (cmd) { case SIOCGETTUNNEL: if (dev == itn->fb_tunnel_dev) { t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); if (!t) t = netdev_priv(dev); } memcpy(p, &t->parms, sizeof(*p)); break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (p->iph.ttl) p->iph.frag_off |= htons(IP_DF); if (!(p->i_flags & VTI_ISVTI)) { if (!(p->i_flags & TUNNEL_KEY)) p->i_key = 0; if (!(p->o_flags & TUNNEL_KEY)) p->o_key = 0; } t = ip_tunnel_find(itn, p, itn->type); if (cmd == SIOCADDTUNNEL) { if (!t) { t = ip_tunnel_create(net, itn, p); err = PTR_ERR_OR_ZERO(t); break; } err = -EEXIST; break; } if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { if (t) { if (t->dev != dev) { err = -EEXIST; break; } } else { unsigned int nflags = 0; if (ipv4_is_multicast(p->iph.daddr)) nflags = IFF_BROADCAST; else if (p->iph.daddr) nflags = IFF_POINTOPOINT; if ((dev->flags^nflags)&(IFF_POINTOPOINT|IFF_BROADCAST)) { err = -EINVAL; break; } t = netdev_priv(dev); } } if (t) { err = 0; ip_tunnel_update(itn, t, dev, p, true, 0); } else { err = -ENOENT; } break; case SIOCDELTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == itn->fb_tunnel_dev) { err = -ENOENT; t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); if (!t) goto done; err = -EPERM; if (t == netdev_priv(itn->fb_tunnel_dev)) goto done; dev = t->dev; } unregister_netdevice(dev); err = 0; break; default: err = -EINVAL; } done: return err; } EXPORT_SYMBOL_GPL(ip_tunnel_ctl); int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { struct ip_tunnel_parm p; int err; if (copy_from_user(&p, data, sizeof(p))) return -EFAULT; err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, cmd); if (!err && copy_to_user(data, &p, sizeof(p))) return -EFAULT; return err; } EXPORT_SYMBOL_GPL(ip_tunnel_siocdevprivate); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); int max_mtu = IP_MAX_MTU - t_hlen; if (dev->type == ARPHRD_ETHER) max_mtu -= dev->hard_header_len; if (new_mtu < ETH_MIN_MTU) return -EINVAL; if (new_mtu > max_mtu) { if (strict) return -EINVAL; new_mtu = max_mtu; } dev->mtu = new_mtu; return 0; } EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) { return __ip_tunnel_change_mtu(dev, new_mtu, true); } EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu); static void ip_tunnel_dev_free(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); gro_cells_destroy(&tunnel->gro_cells); dst_cache_destroy(&tunnel->dst_cache); free_percpu(dev->tstats); } void ip_tunnel_dellink(struct net_device *dev, struct list_head *head) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_net *itn; itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id); if (itn->fb_tunnel_dev != dev) { ip_tunnel_del(itn, netdev_priv(dev)); unregister_netdevice_queue(dev, head); } } EXPORT_SYMBOL_GPL(ip_tunnel_dellink); struct net *ip_tunnel_get_link_net(const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); return tunnel->net; } EXPORT_SYMBOL(ip_tunnel_get_link_net); int ip_tunnel_get_iflink(const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); return tunnel->parms.link; } EXPORT_SYMBOL(ip_tunnel_get_iflink); int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname) { struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id); struct ip_tunnel_parm parms; unsigned int i; itn->rtnl_link_ops = ops; for (i = 0; i < IP_TNL_HASH_SIZE; i++) INIT_HLIST_HEAD(&itn->tunnels[i]); if (!ops || !net_has_fallback_tunnels(net)) { struct ip_tunnel_net *it_init_net; it_init_net = net_generic(&init_net, ip_tnl_net_id); itn->type = it_init_net->type; itn->fb_tunnel_dev = NULL; return 0; } memset(&parms, 0, sizeof(parms)); if (devname) strlcpy(parms.name, devname, IFNAMSIZ); rtnl_lock(); itn->fb_tunnel_dev = __ip_tunnel_create(net, ops, &parms); /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ if (!IS_ERR(itn->fb_tunnel_dev)) { itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev); ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); itn->type = itn->fb_tunnel_dev->type; } rtnl_unlock(); return PTR_ERR_OR_ZERO(itn->fb_tunnel_dev); } EXPORT_SYMBOL_GPL(ip_tunnel_init_net); static void ip_tunnel_destroy(struct net *net, struct ip_tunnel_net *itn, struct list_head *head, struct rtnl_link_ops *ops) { struct net_device *dev, *aux; int h; for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == ops) unregister_netdevice_queue(dev, head); for (h = 0; h < IP_TNL_HASH_SIZE; h++) { struct ip_tunnel *t; struct hlist_node *n; struct hlist_head *thead = &itn->tunnels[h]; hlist_for_each_entry_safe(t, n, thead, hash_node) /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, head); } } void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id, struct rtnl_link_ops *ops) { struct ip_tunnel_net *itn; struct net *net; LIST_HEAD(list); rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { itn = net_generic(net, id); ip_tunnel_destroy(net, itn, &list, ops); } unregister_netdevice_many(&list); rtnl_unlock(); } EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets); int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p, __u32 fwmark) { struct ip_tunnel *nt; struct net *net = dev_net(dev); struct ip_tunnel_net *itn; int mtu; int err; nt = netdev_priv(dev); itn = net_generic(net, nt->ip_tnl_net_id); if (nt->collect_md) { if (rtnl_dereference(itn->collect_md_tun)) return -EEXIST; } else { if (ip_tunnel_find(itn, p, dev->type)) return -EEXIST; } nt->net = net; nt->parms = *p; nt->fwmark = fwmark; err = register_netdevice(dev); if (err) goto err_register_netdevice; if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); mtu = ip_tunnel_bind_dev(dev); if (tb[IFLA_MTU]) { unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr)); if (dev->type == ARPHRD_ETHER) max -= dev->hard_header_len; mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max); } err = dev_set_mtu(dev, mtu); if (err) goto err_dev_set_mtu; ip_tunnel_add(itn, nt); return 0; err_dev_set_mtu: unregister_netdevice(dev); err_register_netdevice: return err; } EXPORT_SYMBOL_GPL(ip_tunnel_newlink); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p, __u32 fwmark) { struct ip_tunnel *t; struct ip_tunnel *tunnel = netdev_priv(dev); struct net *net = tunnel->net; struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id); if (dev == itn->fb_tunnel_dev) return -EINVAL; t = ip_tunnel_find(itn, p, dev->type); if (t) { if (t->dev != dev) return -EEXIST; } else { t = tunnel; if (dev->type != ARPHRD_ETHER) { unsigned int nflags = 0; if (ipv4_is_multicast(p->iph.daddr)) nflags = IFF_BROADCAST; else if (p->iph.daddr) nflags = IFF_POINTOPOINT; if ((dev->flags ^ nflags) & (IFF_POINTOPOINT | IFF_BROADCAST)) return -EINVAL; } } ip_tunnel_update(itn, t, dev, p, !tb[IFLA_MTU], fwmark); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_changelink); int ip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; int err; dev->needs_free_netdev = true; dev->priv_destructor = ip_tunnel_dev_free; dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (err) { free_percpu(dev->tstats); return err; } err = gro_cells_init(&tunnel->gro_cells, dev); if (err) { dst_cache_destroy(&tunnel->dst_cache); free_percpu(dev->tstats); return err; } tunnel->dev = dev; tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); iph->version = 4; iph->ihl = 5; if (tunnel->collect_md) netif_keep_dst(dev); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); void ip_tunnel_uninit(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct net *net = tunnel->net; struct ip_tunnel_net *itn; itn = net_generic(net, tunnel->ip_tnl_net_id); ip_tunnel_del(itn, netdev_priv(dev)); if (itn->fb_tunnel_dev == dev) WRITE_ONCE(itn->fb_tunnel_dev, NULL); dst_cache_reset(&tunnel->dst_cache); } EXPORT_SYMBOL_GPL(ip_tunnel_uninit); /* Do least required initialization, rest of init is done in tunnel_init call */ void ip_tunnel_setup(struct net_device *dev, unsigned int net_id) { struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->ip_tnl_net_id = net_id; } EXPORT_SYMBOL_GPL(ip_tunnel_setup); MODULE_LICENSE("GPL"); |
| 9 8 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV6 GSO/GRO offload support * Linux INET6 implementation * * TCPv6 GSO/GRO support */ #include <linux/indirect_call_wrapper.h> #include <linux/skbuff.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/ip6_checksum.h> #include "ip6_offload.h" INDIRECT_CALLABLE_SCOPE struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb) { /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && skb_gro_checksum_validate(skb, IPPROTO_TCP, ip6_gro_compute_pseudo)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } return tcp_gro_receive(head, skb); } INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr, &iph->daddr, 0); skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; return tcp_gro_complete(skb); } static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct tcphdr *th; if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)) return ERR_PTR(-EINVAL); if (!pskb_may_pull(skb, sizeof(*th))) return ERR_PTR(-EINVAL); if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { const struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); /* Set up pseudo header, usually expect stack to have done * this. */ th->check = 0; skb->ip_summed = CHECKSUM_PARTIAL; __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr); } return tcp_gso_segment(skb, features); } static const struct net_offload tcpv6_offload = { .callbacks = { .gso_segment = tcp6_gso_segment, .gro_receive = tcp6_gro_receive, .gro_complete = tcp6_gro_complete, }, }; int __init tcpv6_offload_init(void) { return inet6_add_offload(&tcpv6_offload, IPPROTO_TCP); } |
| 2920 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 | /* 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 int kswapd (void *p); 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. */ /* * Unaddressable device memory support. See include/linux/hmm.h and * Documentation/vm/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 /* * NUMA node memory migration support */ #ifdef CONFIG_MIGRATION #define SWP_MIGRATION_NUM 2 #define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) #define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) #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) /* * 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 list 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 */ ANDROID_VENDOR_DATA(1); 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 }; /* linux/mm/workingset.c */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg); void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); #define mapping_set_update(xas, mapping) do { \ if (!dax_mapping(mapping) && !shmem_mapping(mapping)) \ xas_set_update(xas, workingset_update_node); \ } while (0) /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; extern unsigned long nr_free_buffer_pages(void); /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) /* linux/mm/swap.c */ extern void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages); extern void lru_note_cost_page(struct page *); extern void lru_cache_add(struct page *); extern void mark_page_accessed(struct page *); 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 rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); 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); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, bool may_swap); 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; extern int remove_mapping(struct address_space *mapping, struct page *page); 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); } extern void check_move_unevictable_pages(struct pagevec *pvec); extern void kswapd_run(int nid); extern void kswapd_stop(int nid); #ifdef CONFIG_SWAP #include <linux/blk_types.h> /* for bio_end_io_t */ /* linux/mm/page_io.c */ extern int swap_readpage(struct page *page, bool do_poll); extern int swap_writepage(struct page *page, struct writeback_control *wbc); extern void end_swap_bio_write(struct bio *bio); extern int __swap_writepage(struct page *page, struct writeback_control *wbc, bio_end_io_t end_write_func); extern int swap_set_page_dirty(struct page *page); 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 *); /* linux/mm/swap_state.c */ /* One swap address space for each 64M swap space */ #define SWAP_ADDRESS_SPACE_SHIFT 14 #define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) extern struct address_space *swapper_spaces[]; #define swap_address_space(entry) \ (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ >> SWAP_ADDRESS_SPACE_SHIFT]) static inline unsigned long total_swapcache_pages(void) { return global_node_page_state(NR_SWAPCACHE); } extern void show_swap_cache_info(void); extern int add_to_swap(struct page *page); extern void *get_shadow_from_swap_cache(swp_entry_t entry); extern int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp, void **shadowp); extern void __delete_from_swap_cache(struct page *page, swp_entry_t entry, void *shadow); extern void delete_from_swap_cache(struct page *); extern void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); extern void free_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); extern struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr); struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index); extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr, bool do_poll); extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr, bool *new_page_allocated); extern struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, struct vm_fault *vmf); extern struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, struct vm_fault *vmf); /* 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 *); extern swp_entry_t get_swap_page(struct page *page); extern void put_swap_page(struct page *page, 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 page_swapcount(struct page *); 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); extern bool reuse_swap_page(struct page *, int *); extern int try_to_free_swap(struct page *); 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); extern sector_t alloc_swapdev_block(int swap); static inline void put_swap_device(struct swap_info_struct *si) { percpu_ref_put(&si->users); } #else /* CONFIG_SWAP */ static inline int swap_readpage(struct page *page, bool do_poll) { return 0; } 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) { } static inline struct address_space *swap_address_space(swp_entry_t entry) { return NULL; } #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)); static inline void free_swap_cache(struct page *page) { } static inline void show_swap_cache_info(void) { } /* 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 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_page(struct page *page, swp_entry_t swp) { } static inline struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_fault *vmf) { return NULL; } static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, struct vm_fault *vmf) { return NULL; } static inline int swap_writepage(struct page *p, struct writeback_control *wbc) { return 0; } static inline struct page *lookup_swap_cache(swp_entry_t swp, struct vm_area_struct *vma, unsigned long addr) { return NULL; } static inline struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index) { return find_get_page(mapping, index); } static inline int add_to_swap(struct page *page) { return 0; } static inline void *get_shadow_from_swap_cache(swp_entry_t entry) { return NULL; } static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask, void **shadowp) { return -1; } static inline void __delete_from_swap_cache(struct page *page, swp_entry_t entry, void *shadow) { } static inline void delete_from_swap_cache(struct page *page) { } static inline void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end) { } static inline int page_swapcount(struct page *page) { return 0; } 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; } #define reuse_swap_page(page, total_map_swapcount) \ (page_trans_huge_mapcount(page, total_map_swapcount) == 1) static inline int try_to_free_swap(struct page *page) { return 0; } static inline swp_entry_t get_swap_page(struct page *page) { swp_entry_t entry; entry.val = 0; return entry; } #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 #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 #ifdef CONFIG_MEMCG_SWAP extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry); extern int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); static inline int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) { if (mem_cgroup_disabled()) return 0; return __mem_cgroup_try_charge_swap(page, 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 page *page); #else static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry) { } static inline int mem_cgroup_try_charge_swap(struct page *page, 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 page *page) { return vm_swap_full(); } #endif #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ |
| 6539 5244 38 5244 5226 5226 84 4496 38 4496 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Percpu refcounts: * (C) 2012 Google, Inc. * Author: Kent Overstreet <koverstreet@google.com> * * This implements a refcount with similar semantics to atomic_t - atomic_inc(), * atomic_dec_and_test() - but percpu. * * There's one important difference between percpu refs and normal atomic_t * refcounts; you have to keep track of your initial refcount, and then when you * start shutting down you call percpu_ref_kill() _before_ dropping the initial * refcount. * * The refcount will have a range of 0 to ((1U << 31) - 1), i.e. one bit less * than an atomic_t - this is because of the way shutdown works, see * percpu_ref_kill()/PERCPU_COUNT_BIAS. * * Before you call percpu_ref_kill(), percpu_ref_put() does not check for the * refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill() * puts the ref back in single atomic_t mode, collecting the per cpu refs and * issuing the appropriate barriers, and then marks the ref as shutting down so * that percpu_ref_put() will check for the ref hitting 0. After it returns, * it's safe to drop the initial ref. * * USAGE: * * See fs/aio.c for some example usage; it's used there for struct kioctx, which * is created when userspaces calls io_setup(), and destroyed when userspace * calls io_destroy() or the process exits. * * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it * removes the kioctx from the proccess's table of kioctxs and kills percpu_ref. * After that, there can't be any new users of the kioctx (from lookup_ioctx()) * and it's then safe to drop the initial ref with percpu_ref_put(). * * Note that the free path, free_ioctx(), needs to go through explicit call_rcu() * to synchronize with RCU protected lookup_ioctx(). percpu_ref operations don't * imply RCU grace periods of any kind and if a user wants to combine percpu_ref * with RCU protection, it must be done explicitly. * * Code that does a two stage shutdown like this often needs some kind of * explicit synchronization to ensure the initial refcount can only be dropped * once - percpu_ref_kill() does this for you, it returns true once and false if * someone else already called it. The aio code uses it this way, but it's not * necessary if the code has some other mechanism to synchronize teardown. * around. */ #ifndef _LINUX_PERCPU_REFCOUNT_H #define _LINUX_PERCPU_REFCOUNT_H #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/gfp.h> struct percpu_ref; typedef void (percpu_ref_func_t)(struct percpu_ref *); /* flags set in the lower bits of percpu_ref->percpu_count_ptr */ enum { __PERCPU_REF_ATOMIC = 1LU << 0, /* operating in atomic mode */ __PERCPU_REF_DEAD = 1LU << 1, /* (being) killed */ __PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD, __PERCPU_REF_FLAG_BITS = 2, }; /* @flags for percpu_ref_init() */ enum { /* * Start w/ ref == 1 in atomic mode. Can be switched to percpu * operation using percpu_ref_switch_to_percpu(). If initialized * with this flag, the ref will stay in atomic mode until * percpu_ref_switch_to_percpu() is invoked on it. * Implies ALLOW_REINIT. */ PERCPU_REF_INIT_ATOMIC = 1 << 0, /* * Start dead w/ ref == 0 in atomic mode. Must be revived with * percpu_ref_reinit() before used. Implies INIT_ATOMIC and * ALLOW_REINIT. */ PERCPU_REF_INIT_DEAD = 1 << 1, /* * Allow switching from atomic mode to percpu mode. */ PERCPU_REF_ALLOW_REINIT = 1 << 2, }; struct percpu_ref_data { atomic_long_t count; percpu_ref_func_t *release; percpu_ref_func_t *confirm_switch; bool force_atomic:1; bool allow_reinit:1; struct rcu_head rcu; struct percpu_ref *ref; }; struct percpu_ref { /* * The low bit of the pointer indicates whether the ref is in percpu * mode; if set, then get/put will manipulate the atomic_t. */ unsigned long percpu_count_ptr; /* * 'percpu_ref' is often embedded into user structure, and only * 'percpu_count_ptr' is required in fast path, move other fields * into 'percpu_ref_data', so we can reduce memory footprint in * fast path. */ struct percpu_ref_data *data; }; int __must_check percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, unsigned int flags, gfp_t gfp); void percpu_ref_exit(struct percpu_ref *ref); void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch); void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref); void percpu_ref_switch_to_percpu(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); void percpu_ref_resurrect(struct percpu_ref *ref); void percpu_ref_reinit(struct percpu_ref *ref); bool percpu_ref_is_zero(struct percpu_ref *ref); /** * percpu_ref_kill - drop the initial ref * @ref: percpu_ref to kill * * Must be used to drop the initial ref on a percpu refcount; must be called * precisely once before shutdown. * * Switches @ref into atomic mode before gathering up the percpu counters * and dropping the initial ref. * * There are no implied RCU grace periods between kill and release. */ static inline void percpu_ref_kill(struct percpu_ref *ref) { percpu_ref_kill_and_confirm(ref, NULL); } /* * Internal helper. Don't use outside percpu-refcount proper. The * function doesn't return the pointer and let the caller test it for NULL * because doing so forces the compiler to generate two conditional * branches as it can't assume that @ref->percpu_count is not NULL. */ static inline bool __ref_is_percpu(struct percpu_ref *ref, unsigned long __percpu **percpu_countp) { unsigned long percpu_ptr; /* * The value of @ref->percpu_count_ptr is tested for * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then * used as a pointer. If the compiler generates a separate fetch * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in * between contaminating the pointer value, meaning that * READ_ONCE() is required when fetching it. * * The dependency ordering from the READ_ONCE() pairs * with smp_store_release() in __percpu_ref_switch_to_percpu(). */ percpu_ptr = READ_ONCE(ref->percpu_count_ptr); /* * Theoretically, the following could test just ATOMIC; however, * then we'd have to mask off DEAD separately as DEAD may be * visible without ATOMIC if we race with percpu_ref_kill(). DEAD * implies ATOMIC anyway. Test them together. */ if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD)) return false; *percpu_countp = (unsigned long __percpu *)percpu_ptr; return true; } /** * percpu_ref_get_many - increment a percpu refcount * @ref: percpu_ref to get * @nr: number of references to get * * Analogous to atomic_long_add(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_add(*percpu_count, nr); else atomic_long_add(nr, &ref->data->count); rcu_read_unlock(); } /** * percpu_ref_get - increment a percpu refcount * @ref: percpu_ref to get * * Analogous to atomic_long_inc(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get(struct percpu_ref *ref) { percpu_ref_get_many(ref, 1); } /** * percpu_ref_tryget_many - try to increment a percpu refcount * @ref: percpu_ref to try-get * @nr: number of references to get * * Increment a percpu refcount by @nr unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; bool ret; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_add(*percpu_count, nr); ret = true; } else { ret = atomic_long_add_unless(&ref->data->count, nr, 0); } rcu_read_unlock(); return ret; } /** * percpu_ref_tryget - try to increment a percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget(struct percpu_ref *ref) { return percpu_ref_tryget_many(ref, 1); } /** * percpu_ref_tryget_live - try to increment a live percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless it has already been killed. Returns * %true on success; %false on failure. * * Completion of percpu_ref_kill() in itself doesn't guarantee that this * function will fail. For such guarantee, percpu_ref_kill_and_confirm() * should be used. After the confirm_kill callback is invoked, it's * guaranteed that no new reference will be given out by * percpu_ref_tryget_live(). * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; bool ret = false; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_inc(*percpu_count); ret = true; } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { ret = atomic_long_inc_not_zero(&ref->data->count); } rcu_read_unlock(); return ret; } /** * percpu_ref_put_many - decrement a percpu refcount * @ref: percpu_ref to put * @nr: number of references to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_sub(*percpu_count, nr); else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count))) ref->data->release(ref); rcu_read_unlock(); } /** * percpu_ref_put - decrement a percpu refcount * @ref: percpu_ref to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put(struct percpu_ref *ref) { percpu_ref_put_many(ref, 1); } /** * percpu_ref_is_dying - test whether a percpu refcount is dying or dead * @ref: percpu_ref to test * * Returns %true if @ref is dying or dead. * * This function is safe to call as long as @ref is between init and exit * and the caller is responsible for synchronizing against state changes. */ static inline bool percpu_ref_is_dying(struct percpu_ref *ref) { return ref->percpu_count_ptr & __PERCPU_REF_DEAD; } #endif |
| 172 255 1 737 737 737 737 737 737 737 737 737 737 737 737 737 736 737 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * net/tipc/link.c: TIPC link code * * Copyright (c) 1996-2007, 2012-2016, Ericsson AB * Copyright (c) 2004-2007, 2010-2013, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include "core.h" #include "subscr.h" #include "link.h" #include "bcast.h" #include "socket.h" #include "name_distr.h" #include "discover.h" #include "netlink.h" #include "monitor.h" #include "trace.h" #include "crypto.h" #include <linux/pkt_sched.h> struct tipc_stats { u32 sent_pkts; u32 recv_pkts; u32 sent_states; u32 recv_states; u32 sent_probes; u32 recv_probes; u32 sent_nacks; u32 recv_nacks; u32 sent_acks; u32 sent_bundled; u32 sent_bundles; u32 recv_bundled; u32 recv_bundles; u32 retransmitted; u32 sent_fragmented; u32 sent_fragments; u32 recv_fragmented; u32 recv_fragments; u32 link_congs; /* # port sends blocked by congestion */ u32 deferred_recv; u32 duplicates; u32 max_queue_sz; /* send queue size high water mark */ u32 accu_queue_sz; /* used for send queue size profiling */ u32 queue_sz_counts; /* used for send queue size profiling */ u32 msg_length_counts; /* used for message length profiling */ u32 msg_lengths_total; /* used for message length profiling */ u32 msg_length_profile[7]; /* used for msg. length profiling */ }; /** * struct tipc_link - TIPC link data structure * @addr: network address of link's peer node * @name: link name character string * @media_addr: media address to use when sending messages over link * @timer: link timer * @net: pointer to namespace struct * @refcnt: reference counter for permanent references (owner node & timer) * @peer_session: link session # being used by peer end of link * @peer_bearer_id: bearer id used by link's peer endpoint * @bearer_id: local bearer id used by link * @tolerance: minimum link continuity loss needed to reset link [in ms] * @abort_limit: # of unacknowledged continuity probes needed to reset link * @state: current state of link FSM * @peer_caps: bitmap describing capabilities of peer node * @silent_intv_cnt: # of timer intervals without any reception from peer * @proto_msg: template for control messages generated by link * @pmsg: convenience pointer to "proto_msg" field * @priority: current link priority * @net_plane: current link network plane ('A' through 'H') * @mon_state: cookie with information needed by link monitor * @backlog_limit: backlog queue congestion thresholds (indexed by importance) * @exp_msg_count: # of tunnelled messages expected during link changeover * @reset_rcv_checkpt: seq # of last acknowledged message at time of link reset * @mtu: current maximum packet size for this link * @advertised_mtu: advertised own mtu when link is being established * @transmitq: queue for sent, non-acked messages * @backlogq: queue for messages waiting to be sent * @snt_nxt: next sequence number to use for outbound messages * @ackers: # of peers that needs to ack each packet before it can be released * @acked: # last packet acked by a certain peer. Used for broadcast. * @rcv_nxt: next sequence number to expect for inbound messages * @deferred_queue: deferred queue saved OOS b'cast message received from node * @unacked_window: # of inbound messages rx'd without ack'ing back to peer * @inputq: buffer queue for messages to be delivered upwards * @namedq: buffer queue for name table messages to be delivered upwards * @next_out: ptr to first unsent outbound message in queue * @wakeupq: linked list of wakeup msgs waiting for link congestion to abate * @long_msg_seq_no: next identifier to use for outbound fragmented messages * @reasm_buf: head of partially reassembled inbound message fragments * @bc_rcvr: marks that this is a broadcast receiver link * @stats: collects statistics regarding link activity * @session: session to be used by link * @snd_nxt_state: next send seq number * @rcv_nxt_state: next rcv seq number * @in_session: have received ACTIVATE_MSG from peer * @active: link is active * @if_name: associated interface name * @rst_cnt: link reset counter * @drop_point: seq number for failover handling (FIXME) * @failover_reasm_skb: saved failover msg ptr (FIXME) * @failover_deferdq: deferred message queue for failover processing (FIXME) * @transmq: the link's transmit queue * @backlog: link's backlog by priority (importance) * @snd_nxt: next sequence number to be used * @rcv_unacked: # messages read by user, but not yet acked back to peer * @deferdq: deferred receive queue * @window: sliding window size for congestion handling * @min_win: minimal send window to be used by link * @ssthresh: slow start threshold for congestion handling * @max_win: maximal send window to be used by link * @cong_acks: congestion acks for congestion avoidance (FIXME) * @checkpoint: seq number for congestion window size handling * @reasm_tnlmsg: fragmentation/reassembly area for tunnel protocol message * @last_gap: last gap ack blocks for bcast (FIXME) * @last_ga: ptr to gap ack blocks * @bc_rcvlink: the peer specific link used for broadcast reception * @bc_sndlink: the namespace global link used for broadcast sending * @nack_state: bcast nack state * @bc_peer_is_up: peer has acked the bcast init msg */ struct tipc_link { u32 addr; char name[TIPC_MAX_LINK_NAME]; struct net *net; /* Management and link supervision data */ u16 peer_session; u16 session; u16 snd_nxt_state; u16 rcv_nxt_state; u32 peer_bearer_id; u32 bearer_id; u32 tolerance; u32 abort_limit; u32 state; u16 peer_caps; bool in_session; bool active; u32 silent_intv_cnt; char if_name[TIPC_MAX_IF_NAME]; u32 priority; char net_plane; struct tipc_mon_state mon_state; u16 rst_cnt; /* Failover/synch */ u16 drop_point; struct sk_buff *failover_reasm_skb; struct sk_buff_head failover_deferdq; /* Max packet negotiation */ u16 mtu; u16 advertised_mtu; /* Sending */ struct sk_buff_head transmq; struct sk_buff_head backlogq; struct { u16 len; u16 limit; struct sk_buff *target_bskb; } backlog[5]; u16 snd_nxt; /* Reception */ u16 rcv_nxt; u32 rcv_unacked; struct sk_buff_head deferdq; struct sk_buff_head *inputq; struct sk_buff_head *namedq; /* Congestion handling */ struct sk_buff_head wakeupq; u16 window; u16 min_win; u16 ssthresh; u16 max_win; u16 cong_acks; u16 checkpoint; /* Fragmentation/reassembly */ struct sk_buff *reasm_buf; struct sk_buff *reasm_tnlmsg; /* Broadcast */ u16 ackers; u16 acked; u16 last_gap; struct tipc_gap_ack_blks *last_ga; struct tipc_link *bc_rcvlink; struct tipc_link *bc_sndlink; u8 nack_state; bool bc_peer_is_up; /* Statistics */ struct tipc_stats stats; }; /* * Error message prefixes */ static const char *link_co_err = "Link tunneling error, "; static const char *link_rst_msg = "Resetting link "; /* Send states for broadcast NACKs */ enum { BC_NACK_SND_CONDITIONAL, BC_NACK_SND_UNCONDITIONAL, BC_NACK_SND_SUPPRESS, }; #define TIPC_BC_RETR_LIM (jiffies + msecs_to_jiffies(10)) #define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1)) /* Link FSM states: */ enum { LINK_ESTABLISHED = 0xe, LINK_ESTABLISHING = 0xe << 4, LINK_RESET = 0x1 << 8, LINK_RESETTING = 0x2 << 12, LINK_PEER_RESET = 0xd << 16, LINK_FAILINGOVER = 0xf << 20, LINK_SYNCHING = 0xc << 24 }; /* Link FSM state checking routines */ static int link_is_up(struct tipc_link *l) { return l->state & (LINK_ESTABLISHED | LINK_SYNCHING); } static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq); static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, bool probe_reply, u16 rcvgap, int tolerance, int priority, struct sk_buff_head *xmitq); static void link_print(struct tipc_link *l, const char *str); static int tipc_link_build_nack_msg(struct tipc_link *l, struct sk_buff_head *xmitq); static void tipc_link_build_bc_init_msg(struct tipc_link *l, struct sk_buff_head *xmitq); static u8 __tipc_build_gap_ack_blks(struct tipc_gap_ack_blks *ga, struct tipc_link *l, u8 start_index); static u16 tipc_build_gap_ack_blks(struct tipc_link *l, struct tipc_msg *hdr); static int tipc_link_advance_transmq(struct tipc_link *l, struct tipc_link *r, u16 acked, u16 gap, struct tipc_gap_ack_blks *ga, struct sk_buff_head *xmitq, bool *retransmitted, int *rc); static void tipc_link_update_cwin(struct tipc_link *l, int released, bool retransmitted); /* * Simple non-static link routines (i.e. referenced outside this file) */ bool tipc_link_is_up(struct tipc_link *l) { return link_is_up(l); } bool tipc_link_peer_is_down(struct tipc_link *l) { return l->state == LINK_PEER_RESET; } bool tipc_link_is_reset(struct tipc_link *l) { return l->state & (LINK_RESET | LINK_FAILINGOVER | LINK_ESTABLISHING); } bool tipc_link_is_establishing(struct tipc_link *l) { return l->state == LINK_ESTABLISHING; } bool tipc_link_is_synching(struct tipc_link *l) { return l->state == LINK_SYNCHING; } bool tipc_link_is_failingover(struct tipc_link *l) { return l->state == LINK_FAILINGOVER; } bool tipc_link_is_blocked(struct tipc_link *l) { return l->state & (LINK_RESETTING | LINK_PEER_RESET | LINK_FAILINGOVER); } static bool link_is_bc_sndlink(struct tipc_link *l) { return !l->bc_sndlink; } static bool link_is_bc_rcvlink(struct tipc_link *l) { return ((l->bc_rcvlink == l) && !link_is_bc_sndlink(l)); } void tipc_link_set_active(struct tipc_link *l, bool active) { l->active = active; } u32 tipc_link_id(struct tipc_link *l) { return l->peer_bearer_id << 16 | l->bearer_id; } int tipc_link_min_win(struct tipc_link *l) { return l->min_win; } int tipc_link_max_win(struct tipc_link *l) { return l->max_win; } int tipc_link_prio(struct tipc_link *l) { return l->priority; } unsigned long tipc_link_tolerance(struct tipc_link *l) { return l->tolerance; } struct sk_buff_head *tipc_link_inputq(struct tipc_link *l) { return l->inputq; } char tipc_link_plane(struct tipc_link *l) { return l->net_plane; } struct net *tipc_link_net(struct tipc_link *l) { return l->net; } void tipc_link_update_caps(struct tipc_link *l, u16 capabilities) { l->peer_caps = capabilities; } void tipc_link_add_bc_peer(struct tipc_link *snd_l, struct tipc_link *uc_l, struct sk_buff_head *xmitq) { struct tipc_link *rcv_l = uc_l->bc_rcvlink; snd_l->ackers++; rcv_l->acked = snd_l->snd_nxt - 1; snd_l->state = LINK_ESTABLISHED; tipc_link_build_bc_init_msg(uc_l, xmitq); } void tipc_link_remove_bc_peer(struct tipc_link *snd_l, struct tipc_link *rcv_l, struct sk_buff_head *xmitq) { u16 ack = snd_l->snd_nxt - 1; snd_l->ackers--; rcv_l->bc_peer_is_up = true; rcv_l->state = LINK_ESTABLISHED; tipc_link_bc_ack_rcv(rcv_l, ack, 0, NULL, xmitq, NULL); trace_tipc_link_reset(rcv_l, TIPC_DUMP_ALL, "bclink removed!"); tipc_link_reset(rcv_l); rcv_l->state = LINK_RESET; if (!snd_l->ackers) { trace_tipc_link_reset(snd_l, TIPC_DUMP_ALL, "zero ackers!"); tipc_link_reset(snd_l); snd_l->state = LINK_RESET; __skb_queue_purge(xmitq); } } int tipc_link_bc_peers(struct tipc_link *l) { return l->ackers; } static u16 link_bc_rcv_gap(struct tipc_link *l) { struct sk_buff *skb = skb_peek(&l->deferdq); u16 gap = 0; if (more(l->snd_nxt, l->rcv_nxt)) gap = l->snd_nxt - l->rcv_nxt; if (skb) gap = buf_seqno(skb) - l->rcv_nxt; return gap; } void tipc_link_set_mtu(struct tipc_link *l, int mtu) { l->mtu = mtu; } int tipc_link_mtu(struct tipc_link *l) { return l->mtu; } int tipc_link_mss(struct tipc_link *l) { #ifdef CONFIG_TIPC_CRYPTO return l->mtu - INT_H_SIZE - EMSG_OVERHEAD; #else return l->mtu - INT_H_SIZE; #endif } u16 tipc_link_rcv_nxt(struct tipc_link *l) { return l->rcv_nxt; } u16 tipc_link_acked(struct tipc_link *l) { return l->acked; } char *tipc_link_name(struct tipc_link *l) { return l->name; } u32 tipc_link_state(struct tipc_link *l) { return l->state; } /** * tipc_link_create - create a new link * @net: pointer to associated network namespace * @if_name: associated interface name * @bearer_id: id (index) of associated bearer * @tolerance: link tolerance to be used by link * @net_plane: network plane (A,B,c..) this link belongs to * @mtu: mtu to be advertised by link * @priority: priority to be used by link * @min_win: minimal send window to be used by link * @max_win: maximal send window to be used by link * @session: session to be used by link * @peer: node id of peer node * @peer_caps: bitmap describing peer node capabilities * @bc_sndlink: the namespace global link used for broadcast sending * @bc_rcvlink: the peer specific link used for broadcast reception * @inputq: queue to put messages ready for delivery * @namedq: queue to put binding table update messages ready for delivery * @link: return value, pointer to put the created link * @self: local unicast link id * @peer_id: 128-bit ID of peer * * Return: true if link was created, otherwise false */ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, int tolerance, char net_plane, u32 mtu, int priority, u32 min_win, u32 max_win, u32 session, u32 self, u32 peer, u8 *peer_id, u16 peer_caps, struct tipc_link *bc_sndlink, struct tipc_link *bc_rcvlink, struct sk_buff_head *inputq, struct sk_buff_head *namedq, struct tipc_link **link) { char peer_str[NODE_ID_STR_LEN] = {0,}; char self_str[NODE_ID_STR_LEN] = {0,}; struct tipc_link *l; l = kzalloc(sizeof(*l), GFP_ATOMIC); if (!l) return false; *link = l; l->session = session; /* Set link name for unicast links only */ if (peer_id) { tipc_nodeid2string(self_str, tipc_own_id(net)); if (strlen(self_str) > 16) sprintf(self_str, "%x", self); tipc_nodeid2string(peer_str, peer_id); if (strlen(peer_str) > 16) sprintf(peer_str, "%x", peer); } /* Peer i/f name will be completed by reset/activate message */ snprintf(l->name, sizeof(l->name), "%s:%s-%s:unknown", self_str, if_name, peer_str); strcpy(l->if_name, if_name); l->addr = peer; l->peer_caps = peer_caps; l->net = net; l->in_session = false; l->bearer_id = bearer_id; l->tolerance = tolerance; if (bc_rcvlink) bc_rcvlink->tolerance = tolerance; l->net_plane = net_plane; l->advertised_mtu = mtu; l->mtu = mtu; l->priority = priority; tipc_link_set_queue_limits(l, min_win, max_win); l->ackers = 1; l->bc_sndlink = bc_sndlink; l->bc_rcvlink = bc_rcvlink; l->inputq = inputq; l->namedq = namedq; l->state = LINK_RESETTING; __skb_queue_head_init(&l->transmq); __skb_queue_head_init(&l->backlogq); __skb_queue_head_init(&l->deferdq); __skb_queue_head_init(&l->failover_deferdq); skb_queue_head_init(&l->wakeupq); skb_queue_head_init(l->inputq); return true; } /** * tipc_link_bc_create - create new link to be used for broadcast * @net: pointer to associated network namespace * @mtu: mtu to be used initially if no peers * @min_win: minimal send window to be used by link * @max_win: maximal send window to be used by link * @inputq: queue to put messages ready for delivery * @namedq: queue to put binding table update messages ready for delivery * @link: return value, pointer to put the created link * @ownnode: identity of own node * @peer: node id of peer node * @peer_id: 128-bit ID of peer * @peer_caps: bitmap describing peer node capabilities * @bc_sndlink: the namespace global link used for broadcast sending * * Return: true if link was created, otherwise false */ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, u8 *peer_id, int mtu, u32 min_win, u32 max_win, u16 peer_caps, struct sk_buff_head *inputq, struct sk_buff_head *namedq, struct tipc_link *bc_sndlink, struct tipc_link **link) { struct tipc_link *l; if (!tipc_link_create(net, "", MAX_BEARERS, 0, 'Z', mtu, 0, min_win, max_win, 0, ownnode, peer, NULL, peer_caps, bc_sndlink, NULL, inputq, namedq, link)) return false; l = *link; if (peer_id) { char peer_str[NODE_ID_STR_LEN] = {0,}; tipc_nodeid2string(peer_str, peer_id); if (strlen(peer_str) > 16) sprintf(peer_str, "%x", peer); /* Broadcast receiver link name: "broadcast-link:<peer>" */ snprintf(l->name, sizeof(l->name), "%s:%s", tipc_bclink_name, peer_str); } else { strcpy(l->name, tipc_bclink_name); } trace_tipc_link_reset(l, TIPC_DUMP_ALL, "bclink created!"); tipc_link_reset(l); l->state = LINK_RESET; l->ackers = 0; l->bc_rcvlink = l; /* Broadcast send link is always up */ if (link_is_bc_sndlink(l)) l->state = LINK_ESTABLISHED; /* Disable replicast if even a single peer doesn't support it */ if (link_is_bc_rcvlink(l) && !(peer_caps & TIPC_BCAST_RCAST)) tipc_bcast_toggle_rcast(net, false); return true; } /** * tipc_link_fsm_evt - link finite state machine * @l: pointer to link * @evt: state machine event to be processed */ int tipc_link_fsm_evt(struct tipc_link *l, int evt) { int rc = 0; int old_state = l->state; switch (l->state) { case LINK_RESETTING: switch (evt) { case LINK_PEER_RESET_EVT: l->state = LINK_PEER_RESET; break; case LINK_RESET_EVT: l->state = LINK_RESET; break; case LINK_FAILURE_EVT: case LINK_FAILOVER_BEGIN_EVT: case LINK_ESTABLISH_EVT: case LINK_FAILOVER_END_EVT: case LINK_SYNCH_BEGIN_EVT: case LINK_SYNCH_END_EVT: default: goto illegal_evt; } break; case LINK_RESET: switch (evt) { case LINK_PEER_RESET_EVT: l->state = LINK_ESTABLISHING; break; case LINK_FAILOVER_BEGIN_EVT: l->state = LINK_FAILINGOVER; break; case LINK_FAILURE_EVT: case LINK_RESET_EVT: case LINK_ESTABLISH_EVT: case LINK_FAILOVER_END_EVT: break; case LINK_SYNCH_BEGIN_EVT: case LINK_SYNCH_END_EVT: default: goto illegal_evt; } break; case LINK_PEER_RESET: switch (evt) { case LINK_RESET_EVT: l->state = LINK_ESTABLISHING; break; case LINK_PEER_RESET_EVT: case LINK_ESTABLISH_EVT: case LINK_FAILURE_EVT: break; case LINK_SYNCH_BEGIN_EVT: case LINK_SYNCH_END_EVT: case LINK_FAILOVER_BEGIN_EVT: case LINK_FAILOVER_END_EVT: default: goto illegal_evt; } break; case LINK_FAILINGOVER: switch (evt) { case LINK_FAILOVER_END_EVT: l->state = LINK_RESET; break; case LINK_PEER_RESET_EVT: case LINK_RESET_EVT: case LINK_ESTABLISH_EVT: case LINK_FAILURE_EVT: break; case LINK_FAILOVER_BEGIN_EVT: case LINK_SYNCH_BEGIN_EVT: case LINK_SYNCH_END_EVT: default: goto illegal_evt; } break; case LINK_ESTABLISHING: switch (evt) { case LINK_ESTABLISH_EVT: l->state = LINK_ESTABLISHED; break; case LINK_FAILOVER_BEGIN_EVT: l->state = LINK_FAILINGOVER; break; case LINK_RESET_EVT: l->state = LINK_RESET; break; case LINK_FAILURE_EVT: case LINK_PEER_RESET_EVT: case LINK_SYNCH_BEGIN_EVT: case LINK_FAILOVER_END_EVT: break; case LINK_SYNCH_END_EVT: default: goto illegal_evt; } break; case LINK_ESTABLISHED: switch (evt) { case LINK_PEER_RESET_EVT: l->state = LINK_PEER_RESET; rc |= TIPC_LINK_DOWN_EVT; break; case LINK_FAILURE_EVT: l->state = LINK_RESETTING; rc |= TIPC_LINK_DOWN_EVT; break; case LINK_RESET_EVT: l->state = LINK_RESET; break; case LINK_ESTABLISH_EVT: case LINK_SYNCH_END_EVT: break; case LINK_SYNCH_BEGIN_EVT: l->state = LINK_SYNCHING; break; case LINK_FAILOVER_BEGIN_EVT: case LINK_FAILOVER_END_EVT: default: goto illegal_evt; } break; case LINK_SYNCHING: switch (evt) { case LINK_PEER_RESET_EVT: l->state = LINK_PEER_RESET; rc |= TIPC_LINK_DOWN_EVT; break; case LINK_FAILURE_EVT: l->state = LINK_RESETTING; rc |= TIPC_LINK_DOWN_EVT; break; case LINK_RESET_EVT: l->state = LINK_RESET; break; case LINK_ESTABLISH_EVT: case LINK_SYNCH_BEGIN_EVT: break; case LINK_SYNCH_END_EVT: l->state = LINK_ESTABLISHED; break; case LINK_FAILOVER_BEGIN_EVT: case LINK_FAILOVER_END_EVT: default: goto illegal_evt; } break; default: pr_err("Unknown FSM state %x in %s\n", l->state, l->name); } trace_tipc_link_fsm(l->name, old_state, l->state, evt); return rc; illegal_evt: pr_err("Illegal FSM event %x in state %x on link %s\n", evt, l->state, l->name); trace_tipc_link_fsm(l->name, old_state, l->state, evt); return rc; } /* link_profile_stats - update statistical profiling of traffic */ static void link_profile_stats(struct tipc_link *l) { struct sk_buff *skb; struct tipc_msg *msg; int length; /* Update counters used in statistical profiling of send traffic */ l->stats.accu_queue_sz += skb_queue_len(&l->transmq); l->stats.queue_sz_counts++; skb = skb_peek(&l->transmq); if (!skb) return; msg = buf_msg(skb); length = msg_size(msg); if (msg_user(msg) == MSG_FRAGMENTER) { if (msg_type(msg) != FIRST_FRAGMENT) return; length = msg_size(msg_inner_hdr(msg)); } l->stats.msg_lengths_total += length; l->stats.msg_length_counts++; if (length <= 64) l->stats.msg_length_profile[0]++; else if (length <= 256) l->stats.msg_length_profile[1]++; else if (length <= 1024) l->stats.msg_length_profile[2]++; else if (length <= 4096) l->stats.msg_length_profile[3]++; else if (length <= 16384) l->stats.msg_length_profile[4]++; else if (length <= 32768) l->stats.msg_length_profile[5]++; else l->stats.msg_length_profile[6]++; } /** * tipc_link_too_silent - check if link is "too silent" * @l: tipc link to be checked * * Return: true if the link 'silent_intv_cnt' is about to reach the * 'abort_limit' value, otherwise false */ bool tipc_link_too_silent(struct tipc_link *l) { return (l->silent_intv_cnt + 2 > l->abort_limit); } /* tipc_link_timeout - perform periodic task as instructed from node timeout */ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq) { int mtyp = 0; int rc = 0; bool state = false; bool probe = false; bool setup = false; u16 bc_snt = l->bc_sndlink->snd_nxt - 1; u16 bc_acked = l->bc_rcvlink->acked; struct tipc_mon_state *mstate = &l->mon_state; trace_tipc_link_timeout(l, TIPC_DUMP_NONE, " "); trace_tipc_link_too_silent(l, TIPC_DUMP_ALL, " "); switch (l->state) { case LINK_ESTABLISHED: case LINK_SYNCHING: mtyp = STATE_MSG; link_profile_stats(l); tipc_mon_get_state(l->net, l->addr, mstate, l->bearer_id); if (mstate->reset || (l->silent_intv_cnt > l->abort_limit)) return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); state = bc_acked != bc_snt; state |= l->bc_rcvlink->rcv_unacked; state |= l->rcv_unacked; state |= !skb_queue_empty(&l->transmq); probe = mstate->probing; probe |= l->silent_intv_cnt; if (probe || mstate->monitoring) l->silent_intv_cnt++; probe |= !skb_queue_empty(&l->deferdq); if (l->snd_nxt == l->checkpoint) { tipc_link_update_cwin(l, 0, 0); probe = true; } l->checkpoint = l->snd_nxt; break; case LINK_RESET: setup = l->rst_cnt++ <= 4; setup |= !(l->rst_cnt % 16); mtyp = RESET_MSG; break; case LINK_ESTABLISHING: setup = true; mtyp = ACTIVATE_MSG; break; case LINK_PEER_RESET: case LINK_RESETTING: case LINK_FAILINGOVER: break; default: break; } if (state || probe || setup) tipc_link_build_proto_msg(l, mtyp, probe, 0, 0, 0, 0, xmitq); return rc; } /** * link_schedule_user - schedule a message sender for wakeup after congestion * @l: congested link * @hdr: header of message that is being sent * Create pseudo msg to send back to user when congestion abates */ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr) { u32 dnode = tipc_own_addr(l->net); u32 dport = msg_origport(hdr); struct sk_buff *skb; /* Create and schedule wakeup pseudo message */ skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, dnode, l->addr, dport, 0, 0); if (!skb) return -ENOBUFS; msg_set_dest_droppable(buf_msg(skb), true); TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr); skb_queue_tail(&l->wakeupq, skb); l->stats.link_congs++; trace_tipc_link_conges(l, TIPC_DUMP_ALL, "wakeup scheduled!"); return -ELINKCONG; } /** * link_prepare_wakeup - prepare users for wakeup after congestion * @l: congested link * Wake up a number of waiting users, as permitted by available space * in the send queue */ static void link_prepare_wakeup(struct tipc_link *l) { struct sk_buff_head *wakeupq = &l->wakeupq; struct sk_buff_head *inputq = l->inputq; struct sk_buff *skb, *tmp; struct sk_buff_head tmpq; int avail[5] = {0,}; int imp = 0; __skb_queue_head_init(&tmpq); for (; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) avail[imp] = l->backlog[imp].limit - l->backlog[imp].len; skb_queue_walk_safe(wakeupq, skb, tmp) { imp = TIPC_SKB_CB(skb)->chain_imp; if (avail[imp] <= 0) continue; avail[imp]--; __skb_unlink(skb, wakeupq); __skb_queue_tail(&tmpq, skb); } spin_lock_bh(&inputq->lock); skb_queue_splice_tail(&tmpq, inputq); spin_unlock_bh(&inputq->lock); } /** * tipc_link_set_skb_retransmit_time - set the time at which retransmission of * the given skb should be next attempted * @skb: skb to set a future retransmission time for * @l: link the skb will be transmitted on */ static void tipc_link_set_skb_retransmit_time(struct sk_buff *skb, struct tipc_link *l) { if (link_is_bc_sndlink(l)) TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; else TIPC_SKB_CB(skb)->nxt_retr = TIPC_UC_RETR_TIME; } void tipc_link_reset(struct tipc_link *l) { struct sk_buff_head list; u32 imp; __skb_queue_head_init(&list); l->in_session = false; /* Force re-synch of peer session number before establishing */ l->peer_session--; l->session++; l->mtu = l->advertised_mtu; spin_lock_bh(&l->wakeupq.lock); skb_queue_splice_init(&l->wakeupq, &list); spin_unlock_bh(&l->wakeupq.lock); spin_lock_bh(&l->inputq->lock); skb_queue_splice_init(&list, l->inputq); spin_unlock_bh(&l->inputq->lock); __skb_queue_purge(&l->transmq); __skb_queue_purge(&l->deferdq); __skb_queue_purge(&l->backlogq); __skb_queue_purge(&l->failover_deferdq); for (imp = 0; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) { l->backlog[imp].len = 0; l->backlog[imp].target_bskb = NULL; } kfree_skb(l->reasm_buf); kfree_skb(l->reasm_tnlmsg); kfree_skb(l->failover_reasm_skb); l->reasm_buf = NULL; l->reasm_tnlmsg = NULL; l->failover_reasm_skb = NULL; l->rcv_unacked = 0; l->snd_nxt = 1; l->rcv_nxt = 1; l->snd_nxt_state = 1; l->rcv_nxt_state = 1; l->acked = 0; l->last_gap = 0; kfree(l->last_ga); l->last_ga = NULL; l->silent_intv_cnt = 0; l->rst_cnt = 0; l->bc_peer_is_up = false; memset(&l->mon_state, 0, sizeof(l->mon_state)); tipc_link_reset_stats(l); } /** * tipc_link_xmit(): enqueue buffer list according to queue situation * @l: link to use * @list: chain of buffers containing message * @xmitq: returned list of packets to be sent by caller * * Consumes the buffer chain. * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS */ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *xmitq) { struct sk_buff_head *backlogq = &l->backlogq; struct sk_buff_head *transmq = &l->transmq; struct sk_buff *skb, *_skb; u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; u16 ack = l->rcv_nxt - 1; u16 seqno = l->snd_nxt; int pkt_cnt = skb_queue_len(list); unsigned int mss = tipc_link_mss(l); unsigned int cwin = l->window; unsigned int mtu = l->mtu; struct tipc_msg *hdr; bool new_bundle; int rc = 0; int imp; if (pkt_cnt <= 0) return 0; hdr = buf_msg(skb_peek(list)); if (unlikely(msg_size(hdr) > mtu)) { pr_warn("Too large msg, purging xmit list %d %d %d %d %d!\n", skb_queue_len(list), msg_user(hdr), msg_type(hdr), msg_size(hdr), mtu); __skb_queue_purge(list); return -EMSGSIZE; } imp = msg_importance(hdr); /* Allow oversubscription of one data msg per source at congestion */ if (unlikely(l->backlog[imp].len >= l->backlog[imp].limit)) { if (imp == TIPC_SYSTEM_IMPORTANCE) { pr_warn("%s<%s>, link overflow", link_rst_msg, l->name); __skb_queue_purge(list); return -ENOBUFS; } rc = link_schedule_user(l, hdr); } if (pkt_cnt > 1) { l->stats.sent_fragmented++; l->stats.sent_fragments += pkt_cnt; } /* Prepare each packet for sending, and add to relevant queue: */ while ((skb = __skb_dequeue(list))) { if (likely(skb_queue_len(transmq) < cwin)) { hdr = buf_msg(skb); msg_set_seqno(hdr, seqno); msg_set_ack(hdr, ack); msg_set_bcast_ack(hdr, bc_ack); _skb = skb_clone(skb, GFP_ATOMIC); if (!_skb) { kfree_skb(skb); __skb_queue_purge(list); return -ENOBUFS; } __skb_queue_tail(transmq, skb); tipc_link_set_skb_retransmit_time(skb, l); __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; l->rcv_unacked = 0; l->stats.sent_pkts++; seqno++; continue; } if (tipc_msg_try_bundle(l->backlog[imp].target_bskb, &skb, mss, l->addr, &new_bundle)) { if (skb) { /* Keep a ref. to the skb for next try */ l->backlog[imp].target_bskb = skb; l->backlog[imp].len++; __skb_queue_tail(backlogq, skb); } else { if (new_bundle) { l->stats.sent_bundles++; l->stats.sent_bundled++; } l->stats.sent_bundled++; } continue; } l->backlog[imp].target_bskb = NULL; l->backlog[imp].len += (1 + skb_queue_len(list)); __skb_queue_tail(backlogq, skb); skb_queue_splice_tail_init(list, backlogq); } l->snd_nxt = seqno; return rc; } static void tipc_link_update_cwin(struct tipc_link *l, int released, bool retransmitted) { int bklog_len = skb_queue_len(&l->backlogq); struct sk_buff_head *txq = &l->transmq; int txq_len = skb_queue_len(txq); u16 cwin = l->window; /* Enter fast recovery */ if (unlikely(retransmitted)) { l->ssthresh = max_t(u16, l->window / 2, 300); l->window = min_t(u16, l->ssthresh, l->window); return; } /* Enter slow start */ if (unlikely(!released)) { l->ssthresh = max_t(u16, l->window / 2, 300); l->window = l->min_win; return; } /* Don't increase window if no pressure on the transmit queue */ if (txq_len + bklog_len < cwin) return; /* Don't increase window if there are holes the transmit queue */ if (txq_len && l->snd_nxt - buf_seqno(skb_peek(txq)) != txq_len) return; l->cong_acks += released; /* Slow start */ if (cwin <= l->ssthresh) { l->window = min_t(u16, cwin + released, l->max_win); return; } /* Congestion avoidance */ if (l->cong_acks < cwin) return; l->window = min_t(u16, ++cwin, l->max_win); l->cong_acks = 0; } static void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq) { u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; struct sk_buff_head *txq = &l->transmq; struct sk_buff *skb, *_skb; u16 ack = l->rcv_nxt - 1; u16 seqno = l->snd_nxt; struct tipc_msg *hdr; u16 cwin = l->window; u32 imp; while (skb_queue_len(txq) < cwin) { skb = skb_peek(&l->backlogq); if (!skb) break; _skb = skb_clone(skb, GFP_ATOMIC); if (!_skb) break; __skb_dequeue(&l->backlogq); hdr = buf_msg(skb); imp = msg_importance(hdr); l->backlog[imp].len--; if (unlikely(skb == l->backlog[imp].target_bskb)) l->backlog[imp].target_bskb = NULL; __skb_queue_tail(&l->transmq, skb); tipc_link_set_skb_retransmit_time(skb, l); __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; msg_set_seqno(hdr, seqno); msg_set_ack(hdr, ack); msg_set_bcast_ack(hdr, bc_ack); l->rcv_unacked = 0; l->stats.sent_pkts++; seqno++; } l->snd_nxt = seqno; } /** * link_retransmit_failure() - Detect repeated retransmit failures * @l: tipc link sender * @r: tipc link receiver (= l in case of unicast) * @rc: returned code * * Return: true if the repeated retransmit failures happens, otherwise * false */ static bool link_retransmit_failure(struct tipc_link *l, struct tipc_link *r, int *rc) { struct sk_buff *skb = skb_peek(&l->transmq); struct tipc_msg *hdr; if (!skb) return false; if (!TIPC_SKB_CB(skb)->retr_cnt) return false; if (!time_after(jiffies, TIPC_SKB_CB(skb)->retr_stamp + msecs_to_jiffies(r->tolerance * 10))) return false; hdr = buf_msg(skb); if (link_is_bc_sndlink(l) && !less(r->acked, msg_seqno(hdr))) return false; pr_warn("Retransmission failure on link <%s>\n", l->name); link_print(l, "State of link "); pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n", msg_user(hdr), msg_type(hdr), msg_size(hdr), msg_errcode(hdr)); pr_info("sqno %u, prev: %x, dest: %x\n", msg_seqno(hdr), msg_prevnode(hdr), msg_destnode(hdr)); pr_info("retr_stamp %d, retr_cnt %d\n", jiffies_to_msecs(TIPC_SKB_CB(skb)->retr_stamp), TIPC_SKB_CB(skb)->retr_cnt); trace_tipc_list_dump(&l->transmq, true, "retrans failure!"); trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!"); trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!"); if (link_is_bc_sndlink(l)) { r->state = LINK_RESET; *rc |= TIPC_LINK_DOWN_EVT; } else { *rc |= tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } return true; } /* tipc_data_input - deliver data and name distr msgs to upper layer * * Consumes buffer if message is of right type * Node lock must be held */ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *inputq) { struct sk_buff_head *mc_inputq = l->bc_rcvlink->inputq; struct tipc_msg *hdr = buf_msg(skb); switch (msg_user(hdr)) { case TIPC_LOW_IMPORTANCE: case TIPC_MEDIUM_IMPORTANCE: case TIPC_HIGH_IMPORTANCE: case TIPC_CRITICAL_IMPORTANCE: if (unlikely(msg_in_group(hdr) || msg_mcast(hdr))) { skb_queue_tail(mc_inputq, skb); return true; } fallthrough; case CONN_MANAGER: skb_queue_tail(inputq, skb); return true; case GROUP_PROTOCOL: skb_queue_tail(mc_inputq, skb); return true; case NAME_DISTRIBUTOR: l->bc_rcvlink->state = LINK_ESTABLISHED; skb_queue_tail(l->namedq, skb); return true; case MSG_BUNDLER: case TUNNEL_PROTOCOL: case MSG_FRAGMENTER: case BCAST_PROTOCOL: return false; #ifdef CONFIG_TIPC_CRYPTO case MSG_CRYPTO: if (TIPC_SKB_CB(skb)->decrypted) { tipc_crypto_msg_rcv(l->net, skb); return true; } fallthrough; #endif default: pr_warn("Dropping received illegal msg type\n"); kfree_skb(skb); return true; } } /* tipc_link_input - process packet that has passed link protocol check * * Consumes buffer */ static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *inputq, struct sk_buff **reasm_skb) { struct tipc_msg *hdr = buf_msg(skb); struct sk_buff *iskb; struct sk_buff_head tmpq; int usr = msg_user(hdr); int pos = 0; if (usr == MSG_BUNDLER) { skb_queue_head_init(&tmpq); l->stats.recv_bundles++; l->stats.recv_bundled += msg_msgcnt(hdr); while (tipc_msg_extract(skb, &iskb, &pos)) tipc_data_input(l, iskb, &tmpq); tipc_skb_queue_splice_tail(&tmpq, inputq); return 0; } else if (usr == MSG_FRAGMENTER) { l->stats.recv_fragments++; if (tipc_buf_append(reasm_skb, &skb)) { l->stats.recv_fragmented++; tipc_data_input(l, skb, inputq); } else if (!*reasm_skb && !link_is_bc_rcvlink(l)) { pr_warn_ratelimited("Unable to build fragment list\n"); return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } return 0; } else if (usr == BCAST_PROTOCOL) { tipc_bcast_lock(l->net); tipc_link_bc_init_rcv(l->bc_rcvlink, hdr); tipc_bcast_unlock(l->net); } kfree_skb(skb); return 0; } /* tipc_link_tnl_rcv() - receive TUNNEL_PROTOCOL message, drop or process the * inner message along with the ones in the old link's * deferdq * @l: tunnel link * @skb: TUNNEL_PROTOCOL message * @inputq: queue to put messages ready for delivery */ static int tipc_link_tnl_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *inputq) { struct sk_buff **reasm_skb = &l->failover_reasm_skb; struct sk_buff **reasm_tnlmsg = &l->reasm_tnlmsg; struct sk_buff_head *fdefq = &l->failover_deferdq; struct tipc_msg *hdr = buf_msg(skb); struct sk_buff *iskb; int ipos = 0; int rc = 0; u16 seqno; if (msg_type(hdr) == SYNCH_MSG) { kfree_skb(skb); return 0; } /* Not a fragment? */ if (likely(!msg_nof_fragms(hdr))) { if (unlikely(!tipc_msg_extract(skb, &iskb, &ipos))) { pr_warn_ratelimited("Unable to extract msg, defq: %d\n", skb_queue_len(fdefq)); return 0; } kfree_skb(skb); } else { /* Set fragment type for buf_append */ if (msg_fragm_no(hdr) == 1) msg_set_type(hdr, FIRST_FRAGMENT); else if (msg_fragm_no(hdr) < msg_nof_fragms(hdr)) msg_set_type(hdr, FRAGMENT); else msg_set_type(hdr, LAST_FRAGMENT); if (!tipc_buf_append(reasm_tnlmsg, &skb)) { /* Successful but non-complete reassembly? */ if (*reasm_tnlmsg || link_is_bc_rcvlink(l)) return 0; pr_warn_ratelimited("Unable to reassemble tunnel msg\n"); return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } iskb = skb; } do { seqno = buf_seqno(iskb); if (unlikely(less(seqno, l->drop_point))) { kfree_skb(iskb); continue; } if (unlikely(seqno != l->drop_point)) { __tipc_skb_queue_sorted(fdefq, seqno, iskb); continue; } l->drop_point++; if (!tipc_data_input(l, iskb, inputq)) rc |= tipc_link_input(l, iskb, inputq, reasm_skb); if (unlikely(rc)) break; } while ((iskb = __tipc_skb_dequeue(fdefq, l->drop_point))); return rc; } /** * tipc_get_gap_ack_blks - get Gap ACK blocks from PROTOCOL/STATE_MSG * @ga: returned pointer to the Gap ACK blocks if any * @l: the tipc link * @hdr: the PROTOCOL/STATE_MSG header * @uc: desired Gap ACK blocks type, i.e. unicast (= 1) or broadcast (= 0) * * Return: the total Gap ACK blocks size */ u16 tipc_get_gap_ack_blks(struct tipc_gap_ack_blks **ga, struct tipc_link *l, struct tipc_msg *hdr, bool uc) { struct tipc_gap_ack_blks *p; u16 sz = 0; /* Does peer support the Gap ACK blocks feature? */ if (l->peer_caps & TIPC_GAP_ACK_BLOCK) { p = (struct tipc_gap_ack_blks *)msg_data(hdr); sz = ntohs(p->len); /* Sanity check */ if (sz == struct_size(p, gacks, size_add(p->ugack_cnt, p->bgack_cnt))) { /* Good, check if the desired type exists */ if ((uc && p->ugack_cnt) || (!uc && p->bgack_cnt)) goto ok; /* Backward compatible: peer might not support bc, but uc? */ } else if (uc && sz == struct_size(p, gacks, p->ugack_cnt)) { if (p->ugack_cnt) { p->bgack_cnt = 0; goto ok; } } } /* Other cases: ignore! */ p = NULL; ok: *ga = p; return sz; } static u8 __tipc_build_gap_ack_blks(struct tipc_gap_ack_blks *ga, struct tipc_link *l, u8 start_index) { struct tipc_gap_ack *gacks = &ga->gacks[start_index]; struct sk_buff *skb = skb_peek(&l->deferdq); u16 expect, seqno = 0; u8 n = 0; if (!skb) return 0; expect = buf_seqno(skb); skb_queue_walk(&l->deferdq, skb) { seqno = buf_seqno(skb); if (unlikely(more(seqno, expect))) { gacks[n].ack = htons(expect - 1); gacks[n].gap = htons(seqno - expect); if (++n >= MAX_GAP_ACK_BLKS / 2) { pr_info_ratelimited("Gacks on %s: %d, ql: %d!\n", l->name, n, skb_queue_len(&l->deferdq)); return n; } } else if (unlikely(less(seqno, expect))) { pr_warn("Unexpected skb in deferdq!\n"); continue; } expect = seqno + 1; } /* last block */ gacks[n].ack = htons(seqno); gacks[n].gap = 0; n++; return n; } /* tipc_build_gap_ack_blks - build Gap ACK blocks * @l: tipc unicast link * @hdr: the tipc message buffer to store the Gap ACK blocks after built * * The function builds Gap ACK blocks for both the unicast & broadcast receiver * links of a certain peer, the buffer after built has the network data format * as found at the struct tipc_gap_ack_blks definition. * * returns the actual allocated memory size */ static u16 tipc_build_gap_ack_blks(struct tipc_link *l, struct tipc_msg *hdr) { struct tipc_link *bcl = l->bc_rcvlink; struct tipc_gap_ack_blks *ga; u16 len; ga = (struct tipc_gap_ack_blks *)msg_data(hdr); /* Start with broadcast link first */ tipc_bcast_lock(bcl->net); msg_set_bcast_ack(hdr, bcl->rcv_nxt - 1); msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl)); ga->bgack_cnt = __tipc_build_gap_ack_blks(ga, bcl, 0); tipc_bcast_unlock(bcl->net); /* Now for unicast link, but an explicit NACK only (???) */ ga->ugack_cnt = (msg_seq_gap(hdr)) ? __tipc_build_gap_ack_blks(ga, l, ga->bgack_cnt) : 0; /* Total len */ len = struct_size(ga, gacks, size_add(ga->bgack_cnt, ga->ugack_cnt)); ga->len = htons(len); return len; } /* tipc_link_advance_transmq - advance TIPC link transmq queue by releasing * acked packets, also doing retransmissions if * gaps found * @l: tipc link with transmq queue to be advanced * @r: tipc link "receiver" i.e. in case of broadcast (= "l" if unicast) * @acked: seqno of last packet acked by peer without any gaps before * @gap: # of gap packets * @ga: buffer pointer to Gap ACK blocks from peer * @xmitq: queue for accumulating the retransmitted packets if any * @retransmitted: returned boolean value if a retransmission is really issued * @rc: returned code e.g. TIPC_LINK_DOWN_EVT if a repeated retransmit failures * happens (- unlikely case) * * Return: the number of packets released from the link transmq */ static int tipc_link_advance_transmq(struct tipc_link *l, struct tipc_link *r, u16 acked, u16 gap, struct tipc_gap_ack_blks *ga, struct sk_buff_head *xmitq, bool *retransmitted, int *rc) { struct tipc_gap_ack_blks *last_ga = r->last_ga, *this_ga = NULL; struct tipc_gap_ack *gacks = NULL; struct sk_buff *skb, *_skb, *tmp; struct tipc_msg *hdr; u32 qlen = skb_queue_len(&l->transmq); u16 nacked = acked, ngap = gap, gack_cnt = 0; u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; u16 ack = l->rcv_nxt - 1; u16 seqno, n = 0; u16 end = r->acked, start = end, offset = r->last_gap; u16 si = (last_ga) ? last_ga->start_index : 0; bool is_uc = !link_is_bc_sndlink(l); bool bc_has_acked = false; trace_tipc_link_retrans(r, acked + 1, acked + gap, &l->transmq); /* Determine Gap ACK blocks if any for the particular link */ if (ga && is_uc) { /* Get the Gap ACKs, uc part */ gack_cnt = ga->ugack_cnt; gacks = &ga->gacks[ga->bgack_cnt]; } else if (ga) { /* Copy the Gap ACKs, bc part, for later renewal if needed */ this_ga = kmemdup(ga, struct_size(ga, gacks, ga->bgack_cnt), GFP_ATOMIC); if (likely(this_ga)) { this_ga->start_index = 0; /* Start with the bc Gap ACKs */ gack_cnt = this_ga->bgack_cnt; gacks = &this_ga->gacks[0]; } else { /* Hmm, we can get in trouble..., simply ignore it */ pr_warn_ratelimited("Ignoring bc Gap ACKs, no memory\n"); } } /* Advance the link transmq */ skb_queue_walk_safe(&l->transmq, skb, tmp) { seqno = buf_seqno(skb); next_gap_ack: if (less_eq(seqno, nacked)) { if (is_uc) goto release; /* Skip packets peer has already acked */ if (!more(seqno, r->acked)) continue; /* Get the next of last Gap ACK blocks */ while (more(seqno, end)) { if (!last_ga || si >= last_ga->bgack_cnt) break; start = end + offset + 1; end = ntohs(last_ga->gacks[si].ack); offset = ntohs(last_ga->gacks[si].gap); si++; WARN_ONCE(more(start, end) || (!offset && si < last_ga->bgack_cnt) || si > MAX_GAP_ACK_BLKS, "Corrupted Gap ACK: %d %d %d %d %d\n", start, end, offset, si, last_ga->bgack_cnt); } /* Check against the last Gap ACK block */ if (in_range(seqno, start, end)) continue; /* Update/release the packet peer is acking */ bc_has_acked = true; if (--TIPC_SKB_CB(skb)->ackers) continue; release: /* release skb */ __skb_unlink(skb, &l->transmq); kfree_skb(skb); } else if (less_eq(seqno, nacked + ngap)) { /* First gap: check if repeated retrans failures? */ if (unlikely(seqno == acked + 1 && link_retransmit_failure(l, r, rc))) { /* Ignore this bc Gap ACKs if any */ kfree(this_ga); this_ga = NULL; break; } /* retransmit skb if unrestricted*/ if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr)) continue; tipc_link_set_skb_retransmit_time(skb, l); _skb = pskb_copy(skb, GFP_ATOMIC); if (!_skb) continue; hdr = buf_msg(_skb); msg_set_ack(hdr, ack); msg_set_bcast_ack(hdr, bc_ack); _skb->priority = TC_PRIO_CONTROL; __skb_queue_tail(xmitq, _skb); l->stats.retransmitted++; if (!is_uc) r->stats.retransmitted++; *retransmitted = true; /* Increase actual retrans counter & mark first time */ if (!TIPC_SKB_CB(skb)->retr_cnt++) TIPC_SKB_CB(skb)->retr_stamp = jiffies; } else { /* retry with Gap ACK blocks if any */ if (n >= gack_cnt) break; nacked = ntohs(gacks[n].ack); ngap = ntohs(gacks[n].gap); n++; goto next_gap_ack; } } /* Renew last Gap ACK blocks for bc if needed */ if (bc_has_acked) { if (this_ga) { kfree(last_ga); r->last_ga = this_ga; r->last_gap = gap; } else if (last_ga) { if (less(acked, start)) { si--; offset = start - acked - 1; } else if (less(acked, end)) { acked = end; } if (si < last_ga->bgack_cnt) { last_ga->start_index = si; r->last_gap = offset; } else { kfree(last_ga); r->last_ga = NULL; r->last_gap = 0; } } else { r->last_gap = 0; } r->acked = acked; } else { kfree(this_ga); } return qlen - skb_queue_len(&l->transmq); } /* tipc_link_build_state_msg: prepare link state message for transmission * * Note that sending of broadcast ack is coordinated among nodes, to reduce * risk of ack storms towards the sender */ int tipc_link_build_state_msg(struct tipc_link *l, struct sk_buff_head *xmitq) { if (!l) return 0; /* Broadcast ACK must be sent via a unicast link => defer to caller */ if (link_is_bc_rcvlink(l)) { if (((l->rcv_nxt ^ tipc_own_addr(l->net)) & 0xf) != 0xf) return 0; l->rcv_unacked = 0; /* Use snd_nxt to store peer's snd_nxt in broadcast rcv link */ l->snd_nxt = l->rcv_nxt; return TIPC_LINK_SND_STATE; } /* Unicast ACK */ l->rcv_unacked = 0; l->stats.sent_acks++; tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, 0, xmitq); return 0; } /* tipc_link_build_reset_msg: prepare link RESET or ACTIVATE message */ void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq) { int mtyp = RESET_MSG; struct sk_buff *skb; if (l->state == LINK_ESTABLISHING) mtyp = ACTIVATE_MSG; tipc_link_build_proto_msg(l, mtyp, 0, 0, 0, 0, 0, xmitq); /* Inform peer that this endpoint is going down if applicable */ skb = skb_peek_tail(xmitq); if (skb && (l->state == LINK_RESET)) msg_set_peer_stopping(buf_msg(skb), 1); } /* tipc_link_build_nack_msg: prepare link nack message for transmission * Note that sending of broadcast NACK is coordinated among nodes, to * reduce the risk of NACK storms towards the sender */ static int tipc_link_build_nack_msg(struct tipc_link *l, struct sk_buff_head *xmitq) { u32 def_cnt = ++l->stats.deferred_recv; struct sk_buff_head *dfq = &l->deferdq; u32 defq_len = skb_queue_len(dfq); int match1, match2; if (link_is_bc_rcvlink(l)) { match1 = def_cnt & 0xf; match2 = tipc_own_addr(l->net) & 0xf; if (match1 == match2) return TIPC_LINK_SND_STATE; return 0; } if (defq_len >= 3 && !((defq_len - 3) % 16)) { u16 rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt; tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, rcvgap, 0, 0, xmitq); } return 0; } /* tipc_link_rcv - process TIPC packets/messages arriving from off-node * @l: the link that should handle the message * @skb: TIPC packet * @xmitq: queue to place packets to be sent after this call */ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq) { struct sk_buff_head *defq = &l->deferdq; struct tipc_msg *hdr = buf_msg(skb); u16 seqno, rcv_nxt, win_lim; int released = 0; int rc = 0; /* Verify and update link state */ if (unlikely(msg_user(hdr) == LINK_PROTOCOL)) return tipc_link_proto_rcv(l, skb, xmitq); /* Don't send probe at next timeout expiration */ l->silent_intv_cnt = 0; do { hdr = buf_msg(skb); seqno = msg_seqno(hdr); rcv_nxt = l->rcv_nxt; win_lim = rcv_nxt + TIPC_MAX_LINK_WIN; if (unlikely(!link_is_up(l))) { if (l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; kfree_skb(skb); break; } /* Drop if outside receive window */ if (unlikely(less(seqno, rcv_nxt) || more(seqno, win_lim))) { l->stats.duplicates++; kfree_skb(skb); break; } released += tipc_link_advance_transmq(l, l, msg_ack(hdr), 0, NULL, NULL, NULL, NULL); /* Defer delivery if sequence gap */ if (unlikely(seqno != rcv_nxt)) { if (!__tipc_skb_queue_sorted(defq, seqno, skb)) l->stats.duplicates++; rc |= tipc_link_build_nack_msg(l, xmitq); break; } /* Deliver packet */ l->rcv_nxt++; l->stats.recv_pkts++; if (unlikely(msg_user(hdr) == TUNNEL_PROTOCOL)) rc |= tipc_link_tnl_rcv(l, skb, l->inputq); else if (!tipc_data_input(l, skb, l->inputq)) rc |= tipc_link_input(l, skb, l->inputq, &l->reasm_buf); if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN)) rc |= tipc_link_build_state_msg(l, xmitq); if (unlikely(rc & ~TIPC_LINK_SND_STATE)) break; } while ((skb = __tipc_skb_dequeue(defq, l->rcv_nxt))); /* Forward queues and wake up waiting users */ if (released) { tipc_link_update_cwin(l, released, 0); tipc_link_advance_backlog(l, xmitq); if (unlikely(!skb_queue_empty(&l->wakeupq))) link_prepare_wakeup(l); } return rc; } static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, bool probe_reply, u16 rcvgap, int tolerance, int priority, struct sk_buff_head *xmitq) { struct tipc_mon_state *mstate = &l->mon_state; struct sk_buff_head *dfq = &l->deferdq; struct tipc_link *bcl = l->bc_rcvlink; struct tipc_msg *hdr; struct sk_buff *skb; bool node_up = link_is_up(bcl); u16 glen = 0, bc_rcvgap = 0; int dlen = 0; void *data; /* Don't send protocol message during reset or link failover */ if (tipc_link_is_blocked(l)) return; if (!tipc_link_is_up(l) && (mtyp == STATE_MSG)) return; if ((probe || probe_reply) && !skb_queue_empty(dfq)) rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt; skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE, tipc_max_domain_size + MAX_GAP_ACK_BLKS_SZ, l->addr, tipc_own_addr(l->net), 0, 0, 0); if (!skb) return; hdr = buf_msg(skb); data = msg_data(hdr); msg_set_session(hdr, l->session); msg_set_bearer_id(hdr, l->bearer_id); msg_set_net_plane(hdr, l->net_plane); msg_set_next_sent(hdr, l->snd_nxt); msg_set_ack(hdr, l->rcv_nxt - 1); msg_set_bcast_ack(hdr, bcl->rcv_nxt - 1); msg_set_bc_ack_invalid(hdr, !node_up); msg_set_last_bcast(hdr, l->bc_sndlink->snd_nxt - 1); msg_set_link_tolerance(hdr, tolerance); msg_set_linkprio(hdr, priority); msg_set_redundant_link(hdr, node_up); msg_set_seq_gap(hdr, 0); msg_set_seqno(hdr, l->snd_nxt + U16_MAX / 2); if (mtyp == STATE_MSG) { if (l->peer_caps & TIPC_LINK_PROTO_SEQNO) msg_set_seqno(hdr, l->snd_nxt_state++); msg_set_seq_gap(hdr, rcvgap); bc_rcvgap = link_bc_rcv_gap(bcl); msg_set_bc_gap(hdr, bc_rcvgap); msg_set_probe(hdr, probe); msg_set_is_keepalive(hdr, probe || probe_reply); if (l->peer_caps & TIPC_GAP_ACK_BLOCK) glen = tipc_build_gap_ack_blks(l, hdr); tipc_mon_prep(l->net, data + glen, &dlen, mstate, l->bearer_id); msg_set_size(hdr, INT_H_SIZE + glen + dlen); skb_trim(skb, INT_H_SIZE + glen + dlen); l->stats.sent_states++; l->rcv_unacked = 0; } else { /* RESET_MSG or ACTIVATE_MSG */ if (mtyp == ACTIVATE_MSG) { msg_set_dest_session_valid(hdr, 1); msg_set_dest_session(hdr, l->peer_session); } msg_set_max_pkt(hdr, l->advertised_mtu); strcpy(data, l->if_name); msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME); skb_trim(skb, INT_H_SIZE + TIPC_MAX_IF_NAME); } if (probe) l->stats.sent_probes++; if (rcvgap) l->stats.sent_nacks++; if (bc_rcvgap) bcl->stats.sent_nacks++; skb->priority = TC_PRIO_CONTROL; __skb_queue_tail(xmitq, skb); trace_tipc_proto_build(skb, false, l->name); } void tipc_link_create_dummy_tnl_msg(struct tipc_link *l, struct sk_buff_head *xmitq) { u32 onode = tipc_own_addr(l->net); struct tipc_msg *hdr, *ihdr; struct sk_buff_head tnlq; struct sk_buff *skb; u32 dnode = l->addr; __skb_queue_head_init(&tnlq); skb = tipc_msg_create(TUNNEL_PROTOCOL, FAILOVER_MSG, INT_H_SIZE, BASIC_H_SIZE, dnode, onode, 0, 0, 0); if (!skb) { pr_warn("%sunable to create tunnel packet\n", link_co_err); return; } hdr = buf_msg(skb); msg_set_msgcnt(hdr, 1); msg_set_bearer_id(hdr, l->peer_bearer_id); ihdr = (struct tipc_msg *)msg_data(hdr); tipc_msg_init(onode, ihdr, TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG, BASIC_H_SIZE, dnode); msg_set_errcode(ihdr, TIPC_ERR_NO_PORT); __skb_queue_tail(&tnlq, skb); tipc_link_xmit(l, &tnlq, xmitq); } /* tipc_link_tnl_prepare(): prepare and return a list of tunnel packets * with contents of the link's transmit and backlog queues. */ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, int mtyp, struct sk_buff_head *xmitq) { struct sk_buff_head *fdefq = &tnl->failover_deferdq; struct sk_buff *skb, *tnlskb; struct tipc_msg *hdr, tnlhdr; struct sk_buff_head *queue = &l->transmq; struct sk_buff_head tmpxq, tnlq, frags; u16 pktlen, pktcnt, seqno = l->snd_nxt; bool pktcnt_need_update = false; u16 syncpt; int rc; if (!tnl) return; __skb_queue_head_init(&tnlq); /* Link Synching: * From now on, send only one single ("dummy") SYNCH message * to peer. The SYNCH message does not contain any data, just * a header conveying the synch point to the peer. */ if (mtyp == SYNCH_MSG && (tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) { tnlskb = tipc_msg_create(TUNNEL_PROTOCOL, SYNCH_MSG, INT_H_SIZE, 0, l->addr, tipc_own_addr(l->net), 0, 0, 0); if (!tnlskb) { pr_warn("%sunable to create dummy SYNCH_MSG\n", link_co_err); return; } hdr = buf_msg(tnlskb); syncpt = l->snd_nxt + skb_queue_len(&l->backlogq) - 1; msg_set_syncpt(hdr, syncpt); msg_set_bearer_id(hdr, l->peer_bearer_id); __skb_queue_tail(&tnlq, tnlskb); tipc_link_xmit(tnl, &tnlq, xmitq); return; } __skb_queue_head_init(&tmpxq); __skb_queue_head_init(&frags); /* At least one packet required for safe algorithm => add dummy */ skb = tipc_msg_create(TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG, BASIC_H_SIZE, 0, l->addr, tipc_own_addr(l->net), 0, 0, TIPC_ERR_NO_PORT); if (!skb) { pr_warn("%sunable to create tunnel packet\n", link_co_err); return; } __skb_queue_tail(&tnlq, skb); tipc_link_xmit(l, &tnlq, &tmpxq); __skb_queue_purge(&tmpxq); /* Initialize reusable tunnel packet header */ tipc_msg_init(tipc_own_addr(l->net), &tnlhdr, TUNNEL_PROTOCOL, mtyp, INT_H_SIZE, l->addr); if (mtyp == SYNCH_MSG) pktcnt = l->snd_nxt - buf_seqno(skb_peek(&l->transmq)); else pktcnt = skb_queue_len(&l->transmq); pktcnt += skb_queue_len(&l->backlogq); msg_set_msgcnt(&tnlhdr, pktcnt); msg_set_bearer_id(&tnlhdr, l->peer_bearer_id); tnl: /* Wrap each packet into a tunnel packet */ skb_queue_walk(queue, skb) { hdr = buf_msg(skb); if (queue == &l->backlogq) msg_set_seqno(hdr, seqno++); pktlen = msg_size(hdr); /* Tunnel link MTU is not large enough? This could be * due to: * 1) Link MTU has just changed or set differently; * 2) Or FAILOVER on the top of a SYNCH message * * The 2nd case should not happen if peer supports * TIPC_TUNNEL_ENHANCED */ if (pktlen > tnl->mtu - INT_H_SIZE) { if (mtyp == FAILOVER_MSG && (tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) { rc = tipc_msg_fragment(skb, &tnlhdr, tnl->mtu, &frags); if (rc) { pr_warn("%sunable to frag msg: rc %d\n", link_co_err, rc); return; } pktcnt += skb_queue_len(&frags) - 1; pktcnt_need_update = true; skb_queue_splice_tail_init(&frags, &tnlq); continue; } /* Unluckily, peer doesn't have TIPC_TUNNEL_ENHANCED * => Just warn it and return! */ pr_warn_ratelimited("%stoo large msg <%d, %d>: %d!\n", link_co_err, msg_user(hdr), msg_type(hdr), msg_size(hdr)); return; } msg_set_size(&tnlhdr, pktlen + INT_H_SIZE); tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE, GFP_ATOMIC); if (!tnlskb) { pr_warn("%sunable to send packet\n", link_co_err); return; } skb_copy_to_linear_data(tnlskb, &tnlhdr, INT_H_SIZE); skb_copy_to_linear_data_offset(tnlskb, INT_H_SIZE, hdr, pktlen); __skb_queue_tail(&tnlq, tnlskb); } if (queue != &l->backlogq) { queue = &l->backlogq; goto tnl; } if (pktcnt_need_update) skb_queue_walk(&tnlq, skb) { hdr = buf_msg(skb); msg_set_msgcnt(hdr, pktcnt); } tipc_link_xmit(tnl, &tnlq, xmitq); if (mtyp == FAILOVER_MSG) { tnl->drop_point = l->rcv_nxt; tnl->failover_reasm_skb = l->reasm_buf; l->reasm_buf = NULL; /* Failover the link's deferdq */ if (unlikely(!skb_queue_empty(fdefq))) { pr_warn("Link failover deferdq not empty: %d!\n", skb_queue_len(fdefq)); __skb_queue_purge(fdefq); } skb_queue_splice_init(&l->deferdq, fdefq); } } /** * tipc_link_failover_prepare() - prepare tnl for link failover * * This is a special version of the precursor - tipc_link_tnl_prepare(), * see the tipc_node_link_failover() for details * * @l: failover link * @tnl: tunnel link * @xmitq: queue for messages to be xmited */ void tipc_link_failover_prepare(struct tipc_link *l, struct tipc_link *tnl, struct sk_buff_head *xmitq) { struct sk_buff_head *fdefq = &tnl->failover_deferdq; tipc_link_create_dummy_tnl_msg(tnl, xmitq); /* This failover link endpoint was never established before, * so it has not received anything from peer. * Otherwise, it must be a normal failover situation or the * node has entered SELF_DOWN_PEER_LEAVING and both peer nodes * would have to start over from scratch instead. */ tnl->drop_point = 1; tnl->failover_reasm_skb = NULL; /* Initiate the link's failover deferdq */ if (unlikely(!skb_queue_empty(fdefq))) { pr_warn("Link failover deferdq not empty: %d!\n", skb_queue_len(fdefq)); __skb_queue_purge(fdefq); } } /* tipc_link_validate_msg(): validate message against current link state * Returns true if message should be accepted, otherwise false */ bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr) { u16 curr_session = l->peer_session; u16 session = msg_session(hdr); int mtyp = msg_type(hdr); if (msg_user(hdr) != LINK_PROTOCOL) return true; switch (mtyp) { case RESET_MSG: if (!l->in_session) return true; /* Accept only RESET with new session number */ return more(session, curr_session); case ACTIVATE_MSG: if (!l->in_session) return true; /* Accept only ACTIVATE with new or current session number */ return !less(session, curr_session); case STATE_MSG: /* Accept only STATE with current session number */ if (!l->in_session) return false; if (session != curr_session) return false; /* Extra sanity check */ if (!link_is_up(l) && msg_ack(hdr)) return false; if (!(l->peer_caps & TIPC_LINK_PROTO_SEQNO)) return true; /* Accept only STATE with new sequence number */ return !less(msg_seqno(hdr), l->rcv_nxt_state); default: return false; } } /* tipc_link_proto_rcv(): receive link level protocol message : * Note that network plane id propagates through the network, and may * change at any time. The node with lowest numerical id determines * network plane */ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq) { struct tipc_msg *hdr = buf_msg(skb); struct tipc_gap_ack_blks *ga = NULL; bool reply = msg_probe(hdr), retransmitted = false; u32 dlen = msg_data_sz(hdr), glen = 0; u16 peers_snd_nxt = msg_next_sent(hdr); u16 peers_tol = msg_link_tolerance(hdr); u16 peers_prio = msg_linkprio(hdr); u16 gap = msg_seq_gap(hdr); u16 ack = msg_ack(hdr); u16 rcv_nxt = l->rcv_nxt; u16 rcvgap = 0; int mtyp = msg_type(hdr); int rc = 0, released; char *if_name; void *data; trace_tipc_proto_rcv(skb, false, l->name); if (dlen > U16_MAX) goto exit; if (tipc_link_is_blocked(l) || !xmitq) goto exit; if (tipc_own_addr(l->net) > msg_prevnode(hdr)) l->net_plane = msg_net_plane(hdr); if (skb_linearize(skb)) goto exit; hdr = buf_msg(skb); data = msg_data(hdr); if (!tipc_link_validate_msg(l, hdr)) { trace_tipc_skb_dump(skb, false, "PROTO invalid (1)!"); trace_tipc_link_dump(l, TIPC_DUMP_NONE, "PROTO invalid (1)!"); goto exit; } switch (mtyp) { case RESET_MSG: case ACTIVATE_MSG: /* Complete own link name with peer's interface name */ if_name = strrchr(l->name, ':') + 1; if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME) break; if (msg_data_sz(hdr) < TIPC_MAX_IF_NAME) break; strncpy(if_name, data, TIPC_MAX_IF_NAME); /* Update own tolerance if peer indicates a non-zero value */ if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) { l->tolerance = peers_tol; l->bc_rcvlink->tolerance = peers_tol; } /* Update own priority if peer's priority is higher */ if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) l->priority = peers_prio; /* If peer is going down we want full re-establish cycle */ if (msg_peer_stopping(hdr)) { rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); break; } /* If this endpoint was re-created while peer was ESTABLISHING * it doesn't know current session number. Force re-synch. */ if (mtyp == ACTIVATE_MSG && msg_dest_session_valid(hdr) && l->session != msg_dest_session(hdr)) { if (less(l->session, msg_dest_session(hdr))) l->session = msg_dest_session(hdr) + 1; break; } /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ if (mtyp == RESET_MSG || !link_is_up(l)) rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); /* ACTIVATE_MSG takes up link if it was already locally reset */ if (mtyp == ACTIVATE_MSG && l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; l->peer_session = msg_session(hdr); l->in_session = true; l->peer_bearer_id = msg_bearer_id(hdr); if (l->mtu > msg_max_pkt(hdr)) l->mtu = msg_max_pkt(hdr); break; case STATE_MSG: /* Validate Gap ACK blocks, drop if invalid */ glen = tipc_get_gap_ack_blks(&ga, l, hdr, true); if (glen > dlen) break; l->rcv_nxt_state = msg_seqno(hdr) + 1; /* Update own tolerance if peer indicates a non-zero value */ if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) { l->tolerance = peers_tol; l->bc_rcvlink->tolerance = peers_tol; } /* Update own prio if peer indicates a different value */ if ((peers_prio != l->priority) && in_range(peers_prio, 1, TIPC_MAX_LINK_PRI)) { l->priority = peers_prio; rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } l->silent_intv_cnt = 0; l->stats.recv_states++; if (msg_probe(hdr)) l->stats.recv_probes++; if (!link_is_up(l)) { if (l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; break; } tipc_mon_rcv(l->net, data + glen, dlen - glen, l->addr, &l->mon_state, l->bearer_id); /* Send NACK if peer has sent pkts we haven't received yet */ if ((reply || msg_is_keepalive(hdr)) && more(peers_snd_nxt, rcv_nxt) && !tipc_link_is_synching(l) && skb_queue_empty(&l->deferdq)) rcvgap = peers_snd_nxt - l->rcv_nxt; if (rcvgap || reply) tipc_link_build_proto_msg(l, STATE_MSG, 0, reply, rcvgap, 0, 0, xmitq); released = tipc_link_advance_transmq(l, l, ack, gap, ga, xmitq, &retransmitted, &rc); if (gap) l->stats.recv_nacks++; if (released || retransmitted) tipc_link_update_cwin(l, released, retransmitted); if (released) tipc_link_advance_backlog(l, xmitq); if (unlikely(!skb_queue_empty(&l->wakeupq))) link_prepare_wakeup(l); } exit: kfree_skb(skb); return rc; } /* tipc_link_build_bc_proto_msg() - create broadcast protocol message */ static bool tipc_link_build_bc_proto_msg(struct tipc_link *l, bool bcast, u16 peers_snd_nxt, struct sk_buff_head *xmitq) { struct sk_buff *skb; struct tipc_msg *hdr; struct sk_buff *dfrd_skb = skb_peek(&l->deferdq); u16 ack = l->rcv_nxt - 1; u16 gap_to = peers_snd_nxt - 1; skb = tipc_msg_create(BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, 0, l->addr, tipc_own_addr(l->net), 0, 0, 0); if (!skb) return false; hdr = buf_msg(skb); msg_set_last_bcast(hdr, l->bc_sndlink->snd_nxt - 1); msg_set_bcast_ack(hdr, ack); msg_set_bcgap_after(hdr, ack); if (dfrd_skb) gap_to = buf_seqno(dfrd_skb) - 1; msg_set_bcgap_to(hdr, gap_to); msg_set_non_seq(hdr, bcast); __skb_queue_tail(xmitq, skb); return true; } /* tipc_link_build_bc_init_msg() - synchronize broadcast link endpoints. * * Give a newly added peer node the sequence number where it should * start receiving and acking broadcast packets. */ static void tipc_link_build_bc_init_msg(struct tipc_link *l, struct sk_buff_head *xmitq) { struct sk_buff_head list; __skb_queue_head_init(&list); if (!tipc_link_build_bc_proto_msg(l->bc_rcvlink, false, 0, &list)) return; msg_set_bc_ack_invalid(buf_msg(skb_peek(&list)), true); tipc_link_xmit(l, &list, xmitq); } /* tipc_link_bc_init_rcv - receive initial broadcast synch data from peer */ void tipc_link_bc_init_rcv(struct tipc_link *l, struct tipc_msg *hdr) { int mtyp = msg_type(hdr); u16 peers_snd_nxt = msg_bc_snd_nxt(hdr); if (link_is_up(l)) return; if (msg_user(hdr) == BCAST_PROTOCOL) { l->rcv_nxt = peers_snd_nxt; l->state = LINK_ESTABLISHED; return; } if (l->peer_caps & TIPC_BCAST_SYNCH) return; if (msg_peer_node_is_up(hdr)) return; /* Compatibility: accept older, less safe initial synch data */ if ((mtyp == RESET_MSG) || (mtyp == ACTIVATE_MSG)) l->rcv_nxt = peers_snd_nxt; } /* tipc_link_bc_sync_rcv - update rcv link according to peer's send state */ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, struct sk_buff_head *xmitq) { u16 peers_snd_nxt = msg_bc_snd_nxt(hdr); int rc = 0; if (!link_is_up(l)) return rc; if (!msg_peer_node_is_up(hdr)) return rc; /* Open when peer acknowledges our bcast init msg (pkt #1) */ if (msg_ack(hdr)) l->bc_peer_is_up = true; if (!l->bc_peer_is_up) return rc; /* Ignore if peers_snd_nxt goes beyond receive window */ if (more(peers_snd_nxt, l->rcv_nxt + l->window)) return rc; l->snd_nxt = peers_snd_nxt; if (link_bc_rcv_gap(l)) rc |= TIPC_LINK_SND_STATE; /* Return now if sender supports nack via STATE messages */ if (l->peer_caps & TIPC_BCAST_STATE_NACK) return rc; /* Otherwise, be backwards compatible */ if (!more(peers_snd_nxt, l->rcv_nxt)) { l->nack_state = BC_NACK_SND_CONDITIONAL; return 0; } /* Don't NACK if one was recently sent or peeked */ if (l->nack_state == BC_NACK_SND_SUPPRESS) { l->nack_state = BC_NACK_SND_UNCONDITIONAL; return 0; } /* Conditionally delay NACK sending until next synch rcv */ if (l->nack_state == BC_NACK_SND_CONDITIONAL) { l->nack_state = BC_NACK_SND_UNCONDITIONAL; if ((peers_snd_nxt - l->rcv_nxt) < TIPC_MIN_LINK_WIN) return 0; } /* Send NACK now but suppress next one */ tipc_link_build_bc_proto_msg(l, true, peers_snd_nxt, xmitq); l->nack_state = BC_NACK_SND_SUPPRESS; return 0; } int tipc_link_bc_ack_rcv(struct tipc_link *r, u16 acked, u16 gap, struct tipc_gap_ack_blks *ga, struct sk_buff_head *xmitq, struct sk_buff_head *retrq) { struct tipc_link *l = r->bc_sndlink; bool unused = false; int rc = 0; if (!link_is_up(r) || !r->bc_peer_is_up) return 0; if (gap) { l->stats.recv_nacks++; r->stats.recv_nacks++; } if (less(acked, r->acked) || (acked == r->acked && !gap && !ga)) return 0; trace_tipc_link_bc_ack(r, acked, gap, &l->transmq); tipc_link_advance_transmq(l, r, acked, gap, ga, retrq, &unused, &rc); tipc_link_advance_backlog(l, xmitq); if (unlikely(!skb_queue_empty(&l->wakeupq))) link_prepare_wakeup(l); return rc; } /* tipc_link_bc_nack_rcv(): receive broadcast nack message * This function is here for backwards compatibility, since * no BCAST_PROTOCOL/STATE messages occur from TIPC v2.5. */ int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq) { struct tipc_msg *hdr = buf_msg(skb); u32 dnode = msg_destnode(hdr); int mtyp = msg_type(hdr); u16 acked = msg_bcast_ack(hdr); u16 from = acked + 1; u16 to = msg_bcgap_to(hdr); u16 peers_snd_nxt = to + 1; int rc = 0; kfree_skb(skb); if (!tipc_link_is_up(l) || !l->bc_peer_is_up) return 0; if (mtyp != STATE_MSG) return 0; if (dnode == tipc_own_addr(l->net)) { rc = tipc_link_bc_ack_rcv(l, acked, to - acked, NULL, xmitq, xmitq); l->stats.recv_nacks++; return rc; } /* Msg for other node => suppress own NACK at next sync if applicable */ if (more(peers_snd_nxt, l->rcv_nxt) && !less(l->rcv_nxt, from)) l->nack_state = BC_NACK_SND_SUPPRESS; return 0; } void tipc_link_set_queue_limits(struct tipc_link *l, u32 min_win, u32 max_win) { int max_bulk = TIPC_MAX_PUBL / (l->mtu / ITEM_SIZE); l->min_win = min_win; l->ssthresh = max_win; l->max_win = max_win; l->window = min_win; l->backlog[TIPC_LOW_IMPORTANCE].limit = min_win * 2; l->backlog[TIPC_MEDIUM_IMPORTANCE].limit = min_win * 4; l->backlog[TIPC_HIGH_IMPORTANCE].limit = min_win * 6; l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = min_win * 8; l->backlog[TIPC_SYSTEM_IMPORTANCE].limit = max_bulk; } /** * tipc_link_reset_stats - reset link statistics * @l: pointer to link */ void tipc_link_reset_stats(struct tipc_link *l) { memset(&l->stats, 0, sizeof(l->stats)); } static void link_print(struct tipc_link *l, const char *str) { struct sk_buff *hskb = skb_peek(&l->transmq); u16 head = hskb ? msg_seqno(buf_msg(hskb)) : l->snd_nxt - 1; u16 tail = l->snd_nxt - 1; pr_info("%s Link <%s> state %x\n", str, l->name, l->state); pr_info("XMTQ: %u [%u-%u], BKLGQ: %u, SNDNX: %u, RCVNX: %u\n", skb_queue_len(&l->transmq), head, tail, skb_queue_len(&l->backlogq), l->snd_nxt, l->rcv_nxt); } /* Parse and validate nested (link) properties valid for media, bearer and link */ int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]) { int err; err = nla_parse_nested_deprecated(props, TIPC_NLA_PROP_MAX, prop, tipc_nl_prop_policy, NULL); if (err) return err; if (props[TIPC_NLA_PROP_PRIO]) { u32 prio; prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (prio > TIPC_MAX_LINK_PRI) return -EINVAL; } if (props[TIPC_NLA_PROP_TOL]) { u32 tol; tol = nla_get_u32(props[TIPC_NLA_PROP_TOL]); if ((tol < TIPC_MIN_LINK_TOL) || (tol > TIPC_MAX_LINK_TOL)) return -EINVAL; } if (props[TIPC_NLA_PROP_WIN]) { u32 max_win; max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); if (max_win < TIPC_DEF_LINK_WIN || max_win > TIPC_MAX_LINK_WIN) return -EINVAL; } return 0; } static int __tipc_nl_add_stats(struct sk_buff *skb, struct tipc_stats *s) { int i; struct nlattr *stats; struct nla_map { u32 key; u32 val; }; struct nla_map map[] = { {TIPC_NLA_STATS_RX_INFO, 0}, {TIPC_NLA_STATS_RX_FRAGMENTS, s->recv_fragments}, {TIPC_NLA_STATS_RX_FRAGMENTED, s->recv_fragmented}, {TIPC_NLA_STATS_RX_BUNDLES, s->recv_bundles}, {TIPC_NLA_STATS_RX_BUNDLED, s->recv_bundled}, {TIPC_NLA_STATS_TX_INFO, 0}, {TIPC_NLA_STATS_TX_FRAGMENTS, s->sent_fragments}, {TIPC_NLA_STATS_TX_FRAGMENTED, s->sent_fragmented}, {TIPC_NLA_STATS_TX_BUNDLES, s->sent_bundles}, {TIPC_NLA_STATS_TX_BUNDLED, s->sent_bundled}, {TIPC_NLA_STATS_MSG_PROF_TOT, (s->msg_length_counts) ? s->msg_length_counts : 1}, {TIPC_NLA_STATS_MSG_LEN_CNT, s->msg_length_counts}, {TIPC_NLA_STATS_MSG_LEN_TOT, s->msg_lengths_total}, {TIPC_NLA_STATS_MSG_LEN_P0, s->msg_length_profile[0]}, {TIPC_NLA_STATS_MSG_LEN_P1, s->msg_length_profile[1]}, {TIPC_NLA_STATS_MSG_LEN_P2, s->msg_length_profile[2]}, {TIPC_NLA_STATS_MSG_LEN_P3, s->msg_length_profile[3]}, {TIPC_NLA_STATS_MSG_LEN_P4, s->msg_length_profile[4]}, {TIPC_NLA_STATS_MSG_LEN_P5, s->msg_length_profile[5]}, {TIPC_NLA_STATS_MSG_LEN_P6, s->msg_length_profile[6]}, {TIPC_NLA_STATS_RX_STATES, s->recv_states}, {TIPC_NLA_STATS_RX_PROBES, s->recv_probes}, {TIPC_NLA_STATS_RX_NACKS, s->recv_nacks}, {TIPC_NLA_STATS_RX_DEFERRED, s->deferred_recv}, {TIPC_NLA_STATS_TX_STATES, s->sent_states}, {TIPC_NLA_STATS_TX_PROBES, s->sent_probes}, {TIPC_NLA_STATS_TX_NACKS, s->sent_nacks}, {TIPC_NLA_STATS_TX_ACKS, s->sent_acks}, {TIPC_NLA_STATS_RETRANSMITTED, s->retransmitted}, {TIPC_NLA_STATS_DUPLICATES, s->duplicates}, {TIPC_NLA_STATS_LINK_CONGS, s->link_congs}, {TIPC_NLA_STATS_MAX_QUEUE, s->max_queue_sz}, {TIPC_NLA_STATS_AVG_QUEUE, s->queue_sz_counts ? (s->accu_queue_sz / s->queue_sz_counts) : 0} }; stats = nla_nest_start_noflag(skb, TIPC_NLA_LINK_STATS); if (!stats) return -EMSGSIZE; for (i = 0; i < ARRAY_SIZE(map); i++) if (nla_put_u32(skb, map[i].key, map[i].val)) goto msg_full; nla_nest_end(skb, stats); return 0; msg_full: nla_nest_cancel(skb, stats); return -EMSGSIZE; } /* Caller should hold appropriate locks to protect the link */ int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, struct tipc_link *link, int nlflags) { u32 self = tipc_own_addr(net); struct nlattr *attrs; struct nlattr *prop; void *hdr; int err; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, nlflags, TIPC_NL_LINK_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK); if (!attrs) goto msg_full; if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, link->name)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_DEST, tipc_cluster_mask(self))) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_MTU, link->mtu)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->stats.recv_pkts)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, link->stats.sent_pkts)) goto attr_msg_full; if (tipc_link_is_up(link)) if (nla_put_flag(msg->skb, TIPC_NLA_LINK_UP)) goto attr_msg_full; if (link->active) if (nla_put_flag(msg->skb, TIPC_NLA_LINK_ACTIVE)) goto attr_msg_full; prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP); if (!prop) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, link->tolerance)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, link->window)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority)) goto prop_msg_full; nla_nest_end(msg->skb, prop); err = __tipc_nl_add_stats(msg->skb, &link->stats); if (err) goto attr_msg_full; 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; } static int __tipc_nl_add_bc_link_stat(struct sk_buff *skb, struct tipc_stats *stats) { int i; struct nlattr *nest; struct nla_map { __u32 key; __u32 val; }; struct nla_map map[] = { {TIPC_NLA_STATS_RX_INFO, stats->recv_pkts}, {TIPC_NLA_STATS_RX_FRAGMENTS, stats->recv_fragments}, {TIPC_NLA_STATS_RX_FRAGMENTED, stats->recv_fragmented}, {TIPC_NLA_STATS_RX_BUNDLES, stats->recv_bundles}, {TIPC_NLA_STATS_RX_BUNDLED, stats->recv_bundled}, {TIPC_NLA_STATS_TX_INFO, stats->sent_pkts}, {TIPC_NLA_STATS_TX_FRAGMENTS, stats->sent_fragments}, {TIPC_NLA_STATS_TX_FRAGMENTED, stats->sent_fragmented}, {TIPC_NLA_STATS_TX_BUNDLES, stats->sent_bundles}, {TIPC_NLA_STATS_TX_BUNDLED, stats->sent_bundled}, {TIPC_NLA_STATS_RX_NACKS, stats->recv_nacks}, {TIPC_NLA_STATS_RX_DEFERRED, stats->deferred_recv}, {TIPC_NLA_STATS_TX_NACKS, stats->sent_nacks}, {TIPC_NLA_STATS_TX_ACKS, stats->sent_acks}, {TIPC_NLA_STATS_RETRANSMITTED, stats->retransmitted}, {TIPC_NLA_STATS_DUPLICATES, stats->duplicates}, {TIPC_NLA_STATS_LINK_CONGS, stats->link_congs}, {TIPC_NLA_STATS_MAX_QUEUE, stats->max_queue_sz}, {TIPC_NLA_STATS_AVG_QUEUE, stats->queue_sz_counts ? (stats->accu_queue_sz / stats->queue_sz_counts) : 0} }; nest = nla_nest_start_noflag(skb, TIPC_NLA_LINK_STATS); if (!nest) return -EMSGSIZE; for (i = 0; i < ARRAY_SIZE(map); i++) if (nla_put_u32(skb, map[i].key, map[i].val)) goto msg_full; nla_nest_end(skb, nest); return 0; msg_full: nla_nest_cancel(skb, nest); return -EMSGSIZE; } int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg, struct tipc_link *bcl) { int err; void *hdr; struct nlattr *attrs; struct nlattr *prop; u32 bc_mode = tipc_bcast_get_mode(net); u32 bc_ratio = tipc_bcast_get_broadcast_ratio(net); if (!bcl) return 0; tipc_bcast_lock(net); hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_LINK_GET); if (!hdr) { tipc_bcast_unlock(net); return -EMSGSIZE; } attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK); if (!attrs) goto msg_full; /* The broadcast link is always up */ if (nla_put_flag(msg->skb, TIPC_NLA_LINK_UP)) goto attr_msg_full; if (nla_put_flag(msg->skb, TIPC_NLA_LINK_BROADCAST)) goto attr_msg_full; if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, bcl->name)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, 0)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, 0)) goto attr_msg_full; prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP); if (!prop) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->max_win)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_BROADCAST, bc_mode)) goto prop_msg_full; if (bc_mode & BCLINK_MODE_SEL) if (nla_put_u32(msg->skb, TIPC_NLA_PROP_BROADCAST_RATIO, bc_ratio)) goto prop_msg_full; nla_nest_end(msg->skb, prop); err = __tipc_nl_add_bc_link_stat(msg->skb, &bcl->stats); if (err) goto attr_msg_full; tipc_bcast_unlock(net); 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: tipc_bcast_unlock(net); genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } void tipc_link_set_tolerance(struct tipc_link *l, u32 tol, struct sk_buff_head *xmitq) { l->tolerance = tol; if (l->bc_rcvlink) l->bc_rcvlink->tolerance = tol; if (link_is_up(l)) tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq); } void tipc_link_set_prio(struct tipc_link *l, u32 prio, struct sk_buff_head *xmitq) { l->priority = prio; tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, prio, xmitq); } void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit) { l->abort_limit = limit; } /** * tipc_link_dump - dump TIPC link data * @l: tipc link to be dumped * @dqueues: bitmask to decide if any link queue to be dumped? * - TIPC_DUMP_NONE: don't dump link queues * - TIPC_DUMP_TRANSMQ: dump link transmq queue * - TIPC_DUMP_BACKLOGQ: dump link backlog queue * - TIPC_DUMP_DEFERDQ: dump link deferd queue * - TIPC_DUMP_INPUTQ: dump link input queue * - TIPC_DUMP_WAKEUP: dump link wakeup queue * - TIPC_DUMP_ALL: dump all the link queues above * @buf: returned buffer of dump data in format */ int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf) { int i = 0; size_t sz = (dqueues) ? LINK_LMAX : LINK_LMIN; struct sk_buff_head *list; struct sk_buff *hskb, *tskb; u32 len; if (!l) { i += scnprintf(buf, sz, "link data: (null)\n"); return i; } i += scnprintf(buf, sz, "link data: %x", l->addr); i += scnprintf(buf + i, sz - i, " %x", l->state); i += scnprintf(buf + i, sz - i, " %u", l->in_session); i += scnprintf(buf + i, sz - i, " %u", l->session); i += scnprintf(buf + i, sz - i, " %u", l->peer_session); i += scnprintf(buf + i, sz - i, " %u", l->snd_nxt); i += scnprintf(buf + i, sz - i, " %u", l->rcv_nxt); i += scnprintf(buf + i, sz - i, " %u", l->snd_nxt_state); i += scnprintf(buf + i, sz - i, " %u", l->rcv_nxt_state); i += scnprintf(buf + i, sz - i, " %x", l->peer_caps); i += scnprintf(buf + i, sz - i, " %u", l->silent_intv_cnt); i += scnprintf(buf + i, sz - i, " %u", l->rst_cnt); i += scnprintf(buf + i, sz - i, " %u", 0); i += scnprintf(buf + i, sz - i, " %u", 0); i += scnprintf(buf + i, sz - i, " %u", l->acked); list = &l->transmq; len = skb_queue_len(list); hskb = skb_peek(list); tskb = skb_peek_tail(list); i += scnprintf(buf + i, sz - i, " | %u %u %u", len, (hskb) ? msg_seqno(buf_msg(hskb)) : 0, (tskb) ? msg_seqno(buf_msg(tskb)) : 0); list = &l->deferdq; len = skb_queue_len(list); hskb = skb_peek(list); tskb = skb_peek_tail(list); i += scnprintf(buf + i, sz - i, " | %u %u %u", len, (hskb) ? msg_seqno(buf_msg(hskb)) : 0, (tskb) ? msg_seqno(buf_msg(tskb)) : 0); list = &l->backlogq; len = skb_queue_len(list); hskb = skb_peek(list); tskb = skb_peek_tail(list); i += scnprintf(buf + i, sz - i, " | %u %u %u", len, (hskb) ? msg_seqno(buf_msg(hskb)) : 0, (tskb) ? msg_seqno(buf_msg(tskb)) : 0); list = l->inputq; len = skb_queue_len(list); hskb = skb_peek(list); tskb = skb_peek_tail(list); i += scnprintf(buf + i, sz - i, " | %u %u %u\n", len, (hskb) ? msg_seqno(buf_msg(hskb)) : 0, (tskb) ? msg_seqno(buf_msg(tskb)) : 0); if (dqueues & TIPC_DUMP_TRANSMQ) { i += scnprintf(buf + i, sz - i, "transmq: "); i += tipc_list_dump(&l->transmq, false, buf + i); } if (dqueues & TIPC_DUMP_BACKLOGQ) { i += scnprintf(buf + i, sz - i, "backlogq: <%u %u %u %u %u>, ", l->backlog[TIPC_LOW_IMPORTANCE].len, l->backlog[TIPC_MEDIUM_IMPORTANCE].len, l->backlog[TIPC_HIGH_IMPORTANCE].len, l->backlog[TIPC_CRITICAL_IMPORTANCE].len, l->backlog[TIPC_SYSTEM_IMPORTANCE].len); i += tipc_list_dump(&l->backlogq, false, buf + i); } if (dqueues & TIPC_DUMP_DEFERDQ) { i += scnprintf(buf + i, sz - i, "deferdq: "); i += tipc_list_dump(&l->deferdq, false, buf + i); } if (dqueues & TIPC_DUMP_INPUTQ) { i += scnprintf(buf + i, sz - i, "inputq: "); i += tipc_list_dump(l->inputq, false, buf + i); } if (dqueues & TIPC_DUMP_WAKEUP) { i += scnprintf(buf + i, sz - i, "wakeup: "); i += tipc_list_dump(&l->wakeupq, false, buf + i); } return i; } |
| 4821 4819 4819 4817 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 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-or-later /* * The "hash function" used as the core of the ChaCha stream cipher (RFC7539) * * Copyright (C) 2015 Martin Willi */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/bitops.h> #include <linux/string.h> #include <asm/unaligned.h> #include <crypto/chacha.h> static void chacha_permute(u32 *x, int nrounds) { int i; /* whitelist the allowed round counts */ WARN_ON_ONCE(nrounds != 20 && nrounds != 12); for (i = 0; i < nrounds; i += 2) { x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16); x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16); x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16); x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16); x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12); x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12); x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12); x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12); x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8); x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8); x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8); x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8); x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7); x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7); x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7); x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7); x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16); x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16); x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16); x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16); x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12); x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12); x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12); x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12); x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8); x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8); x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8); x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8); x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7); x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7); x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7); x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7); } } /** * chacha_block_generic - generate one keystream block and increment block counter * @state: input state matrix (16 32-bit words) * @stream: output keystream block (64 bytes) * @nrounds: number of rounds (20 or 12; 20 is recommended) * * This is the ChaCha core, a function from 64-byte strings to 64-byte strings. * The caller has already converted the endianness of the input. This function * also handles incrementing the block counter in the input matrix. */ void chacha_block_generic(u32 *state, u8 *stream, int nrounds) { u32 x[16]; int i; memcpy(x, state, 64); chacha_permute(x, nrounds); for (i = 0; i < ARRAY_SIZE(x); i++) put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]); state[12]++; } EXPORT_SYMBOL(chacha_block_generic); /** * hchacha_block_generic - abbreviated ChaCha core, for XChaCha * @state: input state matrix (16 32-bit words) * @stream: output (8 32-bit words) * @nrounds: number of rounds (20 or 12; 20 is recommended) * * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf). HChaCha * skips the final addition of the initial state, and outputs only certain words * of the state. It should not be used for streaming directly. */ void hchacha_block_generic(const u32 *state, u32 *stream, int nrounds) { u32 x[16]; memcpy(x, state, 64); chacha_permute(x, nrounds); memcpy(&stream[0], &x[0], 16); memcpy(&stream[4], &x[12], 16); } EXPORT_SYMBOL(hchacha_block_generic); |
| 45 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 | // SPDX-License-Identifier: GPL-2.0-only /* * Linux VM pressure * * Copyright 2012 Linaro Ltd. * Anton Vorontsov <anton.vorontsov@linaro.org> * * Based on ideas from Andrew Morton, David Rientjes, KOSAKI Motohiro, * Leonid Moiseichuk, Mel Gorman, Minchan Kim and Pekka Enberg. */ #include <linux/cgroup.h> #include <linux/fs.h> #include <linux/log2.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/eventfd.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/printk.h> #include <linux/vmpressure.h> #include <trace/hooks/mm.h> /* * The window size (vmpressure_win) is the number of scanned pages before * we try to analyze scanned/reclaimed ratio. So the window is used as a * rate-limit tunable for the "low" level notification, and also for * averaging the ratio for medium/critical levels. Using small window * sizes can cause lot of false positives, but too big window size will * delay the notifications. * * As the vmscan reclaimer logic works with chunks which are multiple of * SWAP_CLUSTER_MAX, it makes sense to use it for the window size as well. * * TODO: Make the window size depend on machine size, as we do for vmstat * thresholds. Currently we set it to 512 pages (2MB for 4KB pages). */ static const unsigned long vmpressure_win = SWAP_CLUSTER_MAX * 16; /* * These thresholds are used when we account memory pressure through * scanned/reclaimed ratio. The current values were chosen empirically. In * essence, they are percents: the higher the value, the more number * unsuccessful reclaims there were. */ static const unsigned int vmpressure_level_med = 60; static const unsigned int vmpressure_level_critical = 95; /* * When there are too little pages left to scan, vmpressure() may miss the * critical pressure as number of pages will be less than "window size". * However, in that case the vmscan priority will raise fast as the * reclaimer will try to scan LRUs more deeply. * * The vmscan logic considers these special priorities: * * prio == DEF_PRIORITY (12): reclaimer starts with that value * prio <= DEF_PRIORITY - 2 : kswapd becomes somewhat overwhelmed * prio == 0 : close to OOM, kernel scans every page in an lru * * Any value in this range is acceptable for this tunable (i.e. from 12 to * 0). Current value for the vmpressure_level_critical_prio is chosen * empirically, but the number, in essence, means that we consider * critical level when scanning depth is ~10% of the lru size (vmscan * scans 'lru_size >> prio' pages, so it is actually 12.5%, or one * eights). */ static const unsigned int vmpressure_level_critical_prio = ilog2(100 / 10); static struct vmpressure *work_to_vmpressure(struct work_struct *work) { return container_of(work, struct vmpressure, work); } static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr) { struct mem_cgroup *memcg = vmpressure_to_memcg(vmpr); memcg = parent_mem_cgroup(memcg); if (!memcg) return NULL; return memcg_to_vmpressure(memcg); } enum vmpressure_levels { VMPRESSURE_LOW = 0, VMPRESSURE_MEDIUM, VMPRESSURE_CRITICAL, VMPRESSURE_NUM_LEVELS, }; enum vmpressure_modes { VMPRESSURE_NO_PASSTHROUGH = 0, VMPRESSURE_HIERARCHY, VMPRESSURE_LOCAL, VMPRESSURE_NUM_MODES, }; static const char * const vmpressure_str_levels[] = { [VMPRESSURE_LOW] = "low", [VMPRESSURE_MEDIUM] = "medium", [VMPRESSURE_CRITICAL] = "critical", }; static const char * const vmpressure_str_modes[] = { [VMPRESSURE_NO_PASSTHROUGH] = "default", [VMPRESSURE_HIERARCHY] = "hierarchy", [VMPRESSURE_LOCAL] = "local", }; static enum vmpressure_levels vmpressure_level(unsigned long pressure) { if (pressure >= vmpressure_level_critical) return VMPRESSURE_CRITICAL; else if (pressure >= vmpressure_level_med) return VMPRESSURE_MEDIUM; return VMPRESSURE_LOW; } static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, unsigned long reclaimed) { unsigned long scale = scanned + reclaimed; unsigned long pressure = 0; /* * reclaimed can be greater than scanned for things such as reclaimed * slab pages. shrink_node() just adds reclaimed pages without a * related increment to scanned pages. */ if (reclaimed >= scanned) goto out; /* * We calculate the ratio (in percents) of how many pages were * scanned vs. reclaimed in a given time frame (window). Note that * time is in VM reclaimer's "ticks", i.e. number of pages * scanned. This makes it possible to set desired reaction time * and serves as a ratelimit. */ pressure = scale - (reclaimed * scale / scanned); pressure = pressure * 100 / scale; out: pr_debug("%s: %3lu (s: %lu r: %lu)\n", __func__, pressure, scanned, reclaimed); return vmpressure_level(pressure); } struct vmpressure_event { struct eventfd_ctx *efd; enum vmpressure_levels level; enum vmpressure_modes mode; struct list_head node; }; static bool vmpressure_event(struct vmpressure *vmpr, const enum vmpressure_levels level, bool ancestor, bool signalled) { struct vmpressure_event *ev; bool ret = false; mutex_lock(&vmpr->events_lock); list_for_each_entry(ev, &vmpr->events, node) { if (ancestor && ev->mode == VMPRESSURE_LOCAL) continue; if (signalled && ev->mode == VMPRESSURE_NO_PASSTHROUGH) continue; if (level < ev->level) continue; eventfd_signal(ev->efd, 1); ret = true; } mutex_unlock(&vmpr->events_lock); return ret; } static void vmpressure_work_fn(struct work_struct *work) { struct vmpressure *vmpr = work_to_vmpressure(work); unsigned long scanned; unsigned long reclaimed; enum vmpressure_levels level; bool ancestor = false; bool signalled = false; spin_lock(&vmpr->sr_lock); /* * Several contexts might be calling vmpressure(), so it is * possible that the work was rescheduled again before the old * work context cleared the counters. In that case we will run * just after the old work returns, but then scanned might be zero * here. No need for any locks here since we don't care if * vmpr->reclaimed is in sync. */ scanned = vmpr->tree_scanned; if (!scanned) { spin_unlock(&vmpr->sr_lock); return; } reclaimed = vmpr->tree_reclaimed; vmpr->tree_scanned = 0; vmpr->tree_reclaimed = 0; spin_unlock(&vmpr->sr_lock); level = vmpressure_calc_level(scanned, reclaimed); do { if (vmpressure_event(vmpr, level, ancestor, signalled)) signalled = true; ancestor = true; } while ((vmpr = vmpressure_parent(vmpr))); } /** * vmpressure() - Account memory pressure through scanned/reclaimed ratio * @gfp: reclaimer's gfp mask * @memcg: cgroup memory controller handle * @tree: legacy subtree mode * @scanned: number of pages scanned * @reclaimed: number of pages reclaimed * * This function should be called from the vmscan reclaim path to account * "instantaneous" memory pressure (scanned/reclaimed ratio). The raw * pressure index is then further refined and averaged over time. * * If @tree is set, vmpressure is in traditional userspace reporting * mode: @memcg is considered the pressure root and userspace is * notified of the entire subtree's reclaim efficiency. * * If @tree is not set, reclaim efficiency is recorded for @memcg, and * only in-kernel users are notified. * * This function does not return any value. */ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, unsigned long scanned, unsigned long reclaimed) { struct vmpressure *vmpr; bool bypass = false; if (mem_cgroup_disabled()) return; trace_android_vh_vmpressure(memcg, &bypass); if (bypass) return; /* * The in-kernel users only care about the reclaim efficiency * for this @memcg rather than the whole subtree, and there * isn't and won't be any in-kernel user in a legacy cgroup. */ if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !tree) return; vmpr = memcg_to_vmpressure(memcg); /* * Here we only want to account pressure that userland is able to * help us with. For example, suppose that DMA zone is under * pressure; if we notify userland about that kind of pressure, * then it will be mostly a waste as it will trigger unnecessary * freeing of memory by userland (since userland is more likely to * have HIGHMEM/MOVABLE pages instead of the DMA fallback). That * is why we include only movable, highmem and FS/IO pages. * Indirect reclaim (kswapd) sets sc->gfp_mask to GFP_KERNEL, so * we account it too. */ if (!(gfp & (__GFP_HIGHMEM | __GFP_MOVABLE | __GFP_IO | __GFP_FS))) return; /* * If we got here with no pages scanned, then that is an indicator * that reclaimer was unable to find any shrinkable LRUs at the * current scanning depth. But it does not mean that we should * report the critical pressure, yet. If the scanning priority * (scanning depth) goes too high (deep), we will be notified * through vmpressure_prio(). But so far, keep calm. */ if (!scanned) return; if (tree) { spin_lock(&vmpr->sr_lock); scanned = vmpr->tree_scanned += scanned; vmpr->tree_reclaimed += reclaimed; spin_unlock(&vmpr->sr_lock); if (scanned < vmpressure_win) return; schedule_work(&vmpr->work); } else { enum vmpressure_levels level; /* For now, no users for root-level efficiency */ if (!memcg || mem_cgroup_is_root(memcg)) return; spin_lock(&vmpr->sr_lock); scanned = vmpr->scanned += scanned; reclaimed = vmpr->reclaimed += reclaimed; if (scanned < vmpressure_win) { spin_unlock(&vmpr->sr_lock); return; } vmpr->scanned = vmpr->reclaimed = 0; spin_unlock(&vmpr->sr_lock); level = vmpressure_calc_level(scanned, reclaimed); if (level > VMPRESSURE_LOW) { /* * Let the socket buffer allocator know that * we are having trouble reclaiming LRU pages. * * For hysteresis keep the pressure state * asserted for a second in which subsequent * pressure events can occur. */ memcg->socket_pressure = jiffies + HZ; } } } /** * vmpressure_prio() - Account memory pressure through reclaimer priority level * @gfp: reclaimer's gfp mask * @memcg: cgroup memory controller handle * @prio: reclaimer's priority * * This function should be called from the reclaim path every time when * the vmscan's reclaiming priority (scanning depth) changes. * * This function does not return any value. */ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) { /* * We only use prio for accounting critical level. For more info * see comment for vmpressure_level_critical_prio variable above. */ if (prio > vmpressure_level_critical_prio) return; /* * OK, the prio is below the threshold, updating vmpressure * information before shrinker dives into long shrinking of long * range vmscan. Passing scanned = vmpressure_win, reclaimed = 0 * to the vmpressure() basically means that we signal 'critical' * level. */ vmpressure(gfp, memcg, true, vmpressure_win, 0); } #define MAX_VMPRESSURE_ARGS_LEN (strlen("critical") + strlen("hierarchy") + 2) /** * vmpressure_register_event() - Bind vmpressure notifications to an eventfd * @memcg: memcg that is interested in vmpressure notifications * @eventfd: eventfd context to link notifications with * @args: event arguments (pressure level threshold, optional mode) * * This function associates eventfd context with the vmpressure * infrastructure, so that the notifications will be delivered to the * @eventfd. The @args parameter is a comma-delimited string that denotes a * pressure level threshold (one of vmpressure_str_levels, i.e. "low", "medium", * or "critical") and an optional mode (one of vmpressure_str_modes, i.e. * "hierarchy" or "local"). * * To be used as memcg event method. * * Return: 0 on success, -ENOMEM on memory failure or -EINVAL if @args could * not be parsed. */ int vmpressure_register_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd, const char *args) { struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH; enum vmpressure_levels level; char *spec, *spec_orig; char *token; int ret = 0; spec_orig = spec = kstrndup(args, MAX_VMPRESSURE_ARGS_LEN, GFP_KERNEL); if (!spec) return -ENOMEM; /* Find required level */ token = strsep(&spec, ","); ret = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token); if (ret < 0) goto out; level = ret; /* Find optional mode */ token = strsep(&spec, ","); if (token) { ret = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token); if (ret < 0) goto out; mode = ret; } ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) { ret = -ENOMEM; goto out; } ev->efd = eventfd; ev->level = level; ev->mode = mode; mutex_lock(&vmpr->events_lock); list_add(&ev->node, &vmpr->events); mutex_unlock(&vmpr->events_lock); ret = 0; out: kfree(spec_orig); return ret; } /** * vmpressure_unregister_event() - Unbind eventfd from vmpressure * @memcg: memcg handle * @eventfd: eventfd context that was used to link vmpressure with the @cg * * This function does internal manipulations to detach the @eventfd from * the vmpressure notifications, and then frees internal resources * associated with the @eventfd (but the @eventfd itself is not freed). * * To be used as memcg event method. */ void vmpressure_unregister_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd) { struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; mutex_lock(&vmpr->events_lock); list_for_each_entry(ev, &vmpr->events, node) { if (ev->efd != eventfd) continue; list_del(&ev->node); kfree(ev); break; } mutex_unlock(&vmpr->events_lock); } /** * vmpressure_init() - Initialize vmpressure control structure * @vmpr: Structure to be initialized * * This function should be called on every allocated vmpressure structure * before any usage. */ void vmpressure_init(struct vmpressure *vmpr) { spin_lock_init(&vmpr->sr_lock); mutex_init(&vmpr->events_lock); INIT_LIST_HEAD(&vmpr->events); INIT_WORK(&vmpr->work, vmpressure_work_fn); } /** * vmpressure_cleanup() - shuts down vmpressure control structure * @vmpr: Structure to be cleaned up * * This function should be called before the structure in which it is * embedded is cleaned up. */ void vmpressure_cleanup(struct vmpressure *vmpr) { /* * Make sure there is no pending work before eventfd infrastructure * goes away. */ flush_work(&vmpr->work); } |
| 106 106 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 | // SPDX-License-Identifier: GPL-2.0-or-later /* * common UDP/RAW code * Linux INET implementation * * Authors: * Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> */ #include <linux/types.h> #include <linux/module.h> #include <linux/ip.h> #include <linux/in.h> #include <net/ip.h> #include <net/sock.h> #include <net/route.h> #include <net/tcp_states.h> #include <net/sock_reuseport.h> int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_in *usin = (struct sockaddr_in *) uaddr; struct flowi4 *fl4; struct rtable *rt; __be32 saddr; int oif; int err; if (addr_len < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) return -EAFNOSUPPORT; sk_dst_reset(sk); oif = sk->sk_bound_dev_if; saddr = inet->inet_saddr; if (ipv4_is_multicast(usin->sin_addr.s_addr)) { if (!oif || netif_index_is_l3_master(sock_net(sk), oif)) oif = inet->mc_index; if (!saddr) saddr = inet->mc_addr; } fl4 = &inet->cork.fl.u.ip4; rt = ip_route_connect(fl4, usin->sin_addr.s_addr, saddr, RT_CONN_FLAGS(sk), oif, sk->sk_protocol, inet->inet_sport, usin->sin_port, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); goto out; } if ((rt->rt_flags & RTCF_BROADCAST) && !sock_flag(sk, SOCK_BROADCAST)) { ip_rt_put(rt); err = -EACCES; goto out; } if (!inet->inet_saddr) inet->inet_saddr = fl4->saddr; /* Update source address */ if (!inet->inet_rcv_saddr) { inet->inet_rcv_saddr = fl4->saddr; if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); inet->inet_id = prandom_u32(); sk_dst_set(sk, &rt->dst); err = 0; out: return err; } EXPORT_SYMBOL(__ip4_datagram_connect); int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { int res; lock_sock(sk); res = __ip4_datagram_connect(sk, uaddr, addr_len); release_sock(sk); return res; } EXPORT_SYMBOL(ip4_datagram_connect); /* Because UDP xmit path can manipulate sk_dst_cache without holding * socket lock, we need to use sk_dst_set() here, * even if we own the socket lock. */ void ip4_datagram_release_cb(struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); const struct ip_options_rcu *inet_opt; __be32 daddr = inet->inet_daddr; struct dst_entry *dst; struct flowi4 fl4; struct rtable *rt; rcu_read_lock(); dst = __sk_dst_get(sk); if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) { rcu_read_unlock(); return; } inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); dst = !IS_ERR(rt) ? &rt->dst : NULL; sk_dst_set(sk, dst); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ip4_datagram_release_cb); |
| 3304 2152 3279 2265 3305 3304 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 | // SPDX-License-Identifier: GPL-2.0 OR MIT /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * * This is an implementation of the BLAKE2s hash and PRF functions. * * Information: https://blake2.net/ * */ #include <crypto/internal/blake2s.h> #include <linux/types.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/bug.h> static inline void blake2s_set_lastblock(struct blake2s_state *state) { state->f[0] = -1; } void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen) { const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; if (unlikely(!inlen)) return; if (inlen > fill) { memcpy(state->buf + state->buflen, in, fill); blake2s_compress(state, state->buf, 1, BLAKE2S_BLOCK_SIZE); state->buflen = 0; in += fill; inlen -= fill; } if (inlen > BLAKE2S_BLOCK_SIZE) { const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); blake2s_compress(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); } memcpy(state->buf + state->buflen, in, inlen); state->buflen += inlen; } EXPORT_SYMBOL(blake2s_update); void blake2s_final(struct blake2s_state *state, u8 *out) { WARN_ON(IS_ENABLED(DEBUG) && !out); blake2s_set_lastblock(state); memset(state->buf + state->buflen, 0, BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ blake2s_compress(state, state->buf, 1, state->buflen); cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); memcpy(out, state->h, state->outlen); memzero_explicit(state, sizeof(*state)); } EXPORT_SYMBOL(blake2s_final); static int __init blake2s_mod_init(void) { if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) && WARN_ON(!blake2s_selftest())) return -ENODEV; return 0; } module_init(blake2s_mod_init); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("BLAKE2s hash function"); MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>"); |
| 3621 3623 3617 3624 2573 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* CPU control. * (C) 2001, 2002, 2003, 2004 Rusty Russell * * This code is licenced under the GPL. */ #include <linux/sched/mm.h> #include <linux/proc_fs.h> #include <linux/smp.h> #include <linux/init.h> #include <linux/notifier.h> #include <linux/sched/signal.h> #include <linux/sched/hotplug.h> #include <linux/sched/isolation.h> #include <linux/sched/task.h> #include <linux/sched/smt.h> #include <linux/unistd.h> #include <linux/cpu.h> #include <linux/oom.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/bug.h> #include <linux/kthread.h> #include <linux/stop_machine.h> #include <linux/mutex.h> #include <linux/gfp.h> #include <linux/suspend.h> #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> #include <linux/nmi.h> #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> #include <linux/scs.h> #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> #include <linux/random.h> #include <uapi/linux/sched/types.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS #include <trace/events/cpuhp.h> #include "smpboot.h" /** * struct cpuhp_cpu_state - Per cpu hotplug state storage * @state: The current cpu state * @target: The target state * @fail: Current CPU hotplug callback state * @thread: Pointer to the hotplug thread * @should_run: Thread should execute * @rollback: Perform a rollback * @single: Single callback invocation * @bringup: Single callback bringup or teardown selector * @cpu: CPU number * @node: Remote CPU node; for multi-instance, do a * single entry callback for install/remove * @last: For multi-instance rollback, remember how far we got * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation * @done_up: Signal completion to the issuer of the task for cpu-up * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; bool rollback; bool single; bool bringup; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; int result; struct completion done_up; struct completion done_down; #endif }; static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { .fail = CPUHP_INVALID, }; #ifdef CONFIG_SMP cpumask_t cpus_booted_once_mask; #endif #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) static struct lockdep_map cpuhp_state_up_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); static struct lockdep_map cpuhp_state_down_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); static inline void cpuhp_lock_acquire(bool bringup) { lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } static inline void cpuhp_lock_release(bool bringup) { lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } #else static inline void cpuhp_lock_acquire(bool bringup) { } static inline void cpuhp_lock_release(bool bringup) { } #endif /** * struct cpuhp_step - Hotplug state machine step * @name: Name of the step * @startup: Startup function of the step * @teardown: Teardown function of the step * @cant_stop: Bringup/teardown can't be stopped at this step * @multi_instance: State has multiple instances which get added afterwards */ struct cpuhp_step { const char *name; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } startup; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } teardown; /* private: */ struct hlist_head list; /* public: */ bool cant_stop; bool multi_instance; }; static DEFINE_MUTEX(cpuhp_state_mutex); static struct cpuhp_step cpuhp_hp_states[]; static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) { return cpuhp_hp_states + state; } static bool cpuhp_step_empty(bool bringup, struct cpuhp_step *step) { return bringup ? !step->startup.single : !step->teardown.single; } /** * cpuhp_invoke_callback - Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked * @node: For multi-instance, do a single entry callback for install/remove * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. * * Return: %0 on success or a negative errno code */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node, struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); int (*cbm)(unsigned int cpu, struct hlist_node *node); int (*cb)(unsigned int cpu); int ret, cnt; if (st->fail == state) { st->fail = CPUHP_INVALID; return -EAGAIN; } if (cpuhp_step_empty(bringup, step)) { WARN_ON_ONCE(1); return 0; } if (!step->multi_instance) { WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; trace_cpuhp_enter(cpu, st->target, state, cb); ret = cb(cpu); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } cbm = bringup ? step->startup.multi : step->teardown.multi; /* Single invocation for instance add/remove */ if (node) { WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { if (lastp && node == *lastp) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); if (ret) { if (!lastp) goto err; *lastp = node; return ret; } cnt++; } if (lastp) *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ cbm = !bringup ? step->startup.multi : step->teardown.multi; if (!cbm) return ret; hlist_for_each(node, &step->list) { if (!cnt--) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); /* * Rollback must not fail, */ WARN_ON_ONCE(ret); } return ret; } #ifdef CONFIG_SMP static bool cpuhp_is_ap_state(enum cpuhp_state state) { /* * The extra check for CPUHP_TEARDOWN_CPU is only for documentation * purposes as that state is handled explicitly in cpu_down. */ return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU; } static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; wait_for_completion(done); } static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; complete(done); } /* * The former STARTING/DYING states, ran with IRQs disabled and must not fail. */ static bool cpuhp_is_atomic_state(enum cpuhp_state state) { return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; } /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen); /* * The following two APIs (cpu_maps_update_begin/done) must be used when * attempting to serialize the updates to cpu_online_mask & cpu_present_mask. */ void cpu_maps_update_begin(void) { mutex_lock(&cpu_add_remove_lock); } void cpu_maps_update_done(void) { mutex_unlock(&cpu_add_remove_lock); } /* * If set, cpu_up and cpu_down will return -EBUSY and do nothing. * Should always be manipulated under cpu_add_remove_lock */ static int cpu_hotplug_disabled; #ifdef CONFIG_HOTPLUG_CPU DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); void cpus_read_lock(void) { percpu_down_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_lock); int cpus_read_trylock(void) { return percpu_down_read_trylock(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_trylock); void cpus_read_unlock(void) { percpu_up_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_unlock); void cpus_write_lock(void) { percpu_down_write(&cpu_hotplug_lock); } void cpus_write_unlock(void) { percpu_up_write(&cpu_hotplug_lock); } void lockdep_assert_cpus_held(void) { /* * We can't have hotplug operations before userspace starts running, * and some init codepaths will knowingly not take the hotplug lock. * This is all valid, so mute lockdep until it makes sense to report * unheld locks. */ if (system_state < SYSTEM_RUNNING) return; percpu_rwsem_assert_held(&cpu_hotplug_lock); } #ifdef CONFIG_LOCKDEP int lockdep_is_cpus_held(void) { return percpu_rwsem_is_held(&cpu_hotplug_lock); } #endif static void lockdep_acquire_cpus_lock(void) { rwsem_acquire(&cpu_hotplug_lock.dep_map, 0, 0, _THIS_IP_); } static void lockdep_release_cpus_lock(void) { rwsem_release(&cpu_hotplug_lock.dep_map, _THIS_IP_); } /* * Wait for currently running CPU hotplug operations to complete (if any) and * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the * hotplug path before performing hotplug operations. So acquiring that lock * guarantees mutual exclusion from any currently running hotplug operations. */ void cpu_hotplug_disable(void) { cpu_maps_update_begin(); cpu_hotplug_disabled++; cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_disable); static void __cpu_hotplug_enable(void) { if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n")) return; cpu_hotplug_disabled--; } void cpu_hotplug_enable(void) { cpu_maps_update_begin(); __cpu_hotplug_enable(); cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #else static void lockdep_acquire_cpus_lock(void) { } static void lockdep_release_cpus_lock(void) { } #endif /* CONFIG_HOTPLUG_CPU */ /* * Architectures that need SMT-specific errata handling during SMT hotplug * should override this. */ void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; void __init cpu_smt_disable(bool force) { if (!cpu_smt_possible()) return; if (force) { pr_info("SMT: Force disabled\n"); cpu_smt_control = CPU_SMT_FORCE_DISABLED; } else { pr_info("SMT: disabled\n"); cpu_smt_control = CPU_SMT_DISABLED; } } /* * The decision whether SMT is supported can only be done after the full * CPU identification. Called from architecture code. */ void __init cpu_smt_check_topology(void) { if (!topology_smt_supported()) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; } static int __init smt_cmdline_disable(char *str) { cpu_smt_disable(str && !strcmp(str, "force")); return 0; } early_param("nosmt", smt_cmdline_disable); static inline bool cpu_smt_allowed(unsigned int cpu) { if (cpu_smt_control == CPU_SMT_ENABLED) return true; if (topology_is_primary_thread(cpu)) return true; /* * On x86 it's required to boot all logical CPUs at least once so * that the init code can get a chance to set CR4.MCE on each * CPU. Otherwise, a broadcasted MCE observing CR4.MCE=0b on any * core will shutdown the machine. */ return !cpumask_test_cpu(cpu, &cpus_booted_once_mask); } /* Returns true if SMT is not supported of forcefully (irreversibly) disabled */ bool cpu_smt_possible(void) { return cpu_smt_control != CPU_SMT_FORCE_DISABLED && cpu_smt_control != CPU_SMT_NOT_SUPPORTED; } EXPORT_SYMBOL_GPL(cpu_smt_possible); #else static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state cpuhp_set_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; bool bringup = st->state < target; st->rollback = false; st->last = NULL; st->target = target; st->single = false; st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); return prev_state; } static inline void cpuhp_reset_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) { bool bringup = !st->bringup; st->target = prev_state; /* * Already rolling back. No need invert the bringup value or to change * the current state. */ if (st->rollback) return; st->rollback = true; /* * If we have st->last we need to undo partial multi_instance of this * state first. Otherwise start undo at the previous state. */ if (!st->last) { if (st->bringup) st->state--; else st->state++; } st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); } /* Regular hotplug invocation of the AP hotplug thread */ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) { if (!st->single && st->state == st->target) return; st->result = 0; /* * Make sure the above stores are visible before should_run becomes * true. Paired with the mb() above in cpuhp_thread_fun() */ smp_mb(); st->should_run = true; wake_up_process(st->thread); wait_for_ap_thread(st, st->bringup); } static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state; int ret; prev_state = cpuhp_set_state(cpu, st, target); __cpuhp_kick_ap(st); if ((ret = st->result)) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } return ret; } static int bringup_wait_for_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; /* Unpark the hotplug thread of the target cpu */ kthread_unpark(st->thread); /* * SMT soft disabling on X86 requires to bring the CPU out of the * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The * CPU marked itself as booted_once in notify_cpu_starting() so the * cpu_smt_allowed() check will now return false if this is not the * primary sibling. */ if (!cpu_smt_allowed(cpu)) return -ECANCELED; if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(cpu, st, st->target); } static int bringup_cpu(unsigned int cpu) { struct task_struct *idle = idle_thread_get(cpu); int ret; /* * Reset stale stack state from the last time this CPU was online. */ scs_task_reset(idle); kasan_unpoison_task_stack(idle); /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * Prevent irq alloc/free across the bringup. */ irq_lock_sparse(); /* Arch-specific enabling code. */ ret = __cpu_up(cpu, idle); irq_unlock_sparse(); if (ret) return ret; return bringup_wait_for_ap(cpu); } static int finish_cpu(unsigned int cpu) { struct task_struct *idle = idle_thread_get(cpu); struct mm_struct *mm = idle->active_mm; /* * idle_task_exit() will have switched to &init_mm, now * clean up any remaining active_mm state. */ if (mm != &init_mm) idle->active_mm = &init_mm; mmdrop(mm); return 0; } /* * Hotplug state machine related functions */ /* * Get the next state to run. Empty ones will be skipped. Returns true if a * state must be run. * * st->state will be modified ahead of time, to match state_to_run, as if it * has already ran. */ static bool cpuhp_next_state(bool bringup, enum cpuhp_state *state_to_run, struct cpuhp_cpu_state *st, enum cpuhp_state target) { do { if (bringup) { if (st->state >= target) return false; *state_to_run = ++st->state; } else { if (st->state <= target) return false; *state_to_run = st->state--; } if (!cpuhp_step_empty(bringup, cpuhp_get_step(*state_to_run))) break; } while (true); return true; } static int __cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target, bool nofail) { enum cpuhp_state state; int ret = 0; while (cpuhp_next_state(bringup, &state, st, target)) { int err; err = cpuhp_invoke_callback(cpu, state, bringup, NULL, NULL); if (!err) continue; if (nofail) { pr_warn("CPU %u %s state %s (%d) failed (%d)\n", cpu, bringup ? "UP" : "DOWN", cpuhp_get_step(st->state)->name, st->state, err); ret = -1; } else { ret = err; break; } } return ret; } static inline int cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { return __cpuhp_invoke_callback_range(bringup, cpu, st, target, false); } static inline void cpuhp_invoke_callback_range_nofail(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { __cpuhp_invoke_callback_range(bringup, cpu, st, target, true); } static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) { if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) return true; /* * When CPU hotplug is disabled, then taking the CPU down is not * possible because takedown_cpu() and the architecture and * subsystem specific mechanisms are not available. So the CPU * which would be completely unplugged again needs to stay around * in the current state. */ return st->state <= CPUHP_BRINGUP_CPU; } static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(true, cpu, st, target); if (ret) { pr_debug("CPU UP failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (can_rollback_cpu(st)) WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, prev_state)); } return ret; } /* * The cpu hotplug threads manage the bringup and teardown of the cpus */ static void cpuhp_create(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); init_completion(&st->done_up); init_completion(&st->done_down); } static int cpuhp_should_run(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); return st->should_run; } /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. * * Each invocation of this function by the smpboot thread does a single AP * state callback. * * It has 3 modes of operation: * - single: runs st->cb_state * - up: runs ++st->state, while st->state < st->target * - down: runs st->state--, while st->state > st->target * * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); bool bringup = st->bringup; enum cpuhp_state state; if (WARN_ON_ONCE(!st->should_run)) return; /* * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures * that if we see ->should_run we also see the rest of the state. */ smp_mb(); /* * The BP holds the hotplug lock, but we're now running on the AP, * ensure that anybody asserting the lock is held, will actually find * it so. */ lockdep_acquire_cpus_lock(); cpuhp_lock_acquire(bringup); if (st->single) { state = st->cb_state; st->should_run = false; } else { st->should_run = cpuhp_next_state(bringup, &state, st, st->target); if (!st->should_run) goto end; } WARN_ON_ONCE(!cpuhp_is_ap_state(state)); if (cpuhp_is_atomic_state(state)) { local_irq_disable(); st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); local_irq_enable(); /* * STARTING/DYING must not fail! */ WARN_ON_ONCE(st->result); } else { st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); } if (st->result) { /* * If we fail on a rollback, we're up a creek without no * paddle, no way forward, no way back. We loose, thanks for * playing. */ WARN_ON_ONCE(st->rollback); st->should_run = false; } end: cpuhp_lock_release(bringup); lockdep_release_cpus_lock(); if (!st->should_run) complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int ret; if (!cpu_online(cpu)) return 0; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. */ if (!st->thread) return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); st->rollback = false; st->last = NULL; st->node = node; st->bringup = bringup; st->cb_state = state; st->single = true; __cpuhp_kick_ap(st); /* * If we failed and did a partial, do a rollback. */ if ((ret = st->result) && st->last) { st->rollback = true; st->bringup = !bringup; __cpuhp_kick_ap(st); } /* * Clean up the leftovers so the next hotplug operation wont use stale * data. */ st->node = st->last = NULL; return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state prev_state = st->state; int ret; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); ret = cpuhp_kick_ap(cpu, st, st->target); trace_cpuhp_exit(cpu, st->state, prev_state, ret); return ret; } static struct smp_hotplug_thread cpuhp_threads = { .store = &cpuhp_state.thread, .create = &cpuhp_create, .thread_should_run = cpuhp_should_run, .thread_fn = cpuhp_thread_fun, .thread_comm = "cpuhp/%u", .selfparking = true, }; void __init cpuhp_threads_init(void) { BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); kthread_unpark(this_cpu_read(cpuhp_state.thread)); } /* * * Serialize hotplug trainwrecks outside of the cpu_hotplug_lock * protected region. * * The operation is still serialized against concurrent CPU hotplug via * cpu_add_remove_lock, i.e. CPU map protection. But it is _not_ * serialized against other hotplug related activity like adding or * removing of state callbacks and state instances, which invoke either the * startup or the teardown callback of the affected state. * * This is required for subsystems which are unfixable vs. CPU hotplug and * evade lock inversion problems by scheduling work which has to be * completed _before_ cpu_up()/_cpu_down() returns. * * Don't even think about adding anything to this for any new code or even * drivers. It's only purpose is to keep existing lock order trainwrecks * working. * * For cpu_down() there might be valid reasons to finish cleanups which are * not required to be done under cpu_hotplug_lock, but that's a different * story and would be not invoked via this. */ static void cpu_up_down_serialize_trainwrecks(bool tasks_frozen) { /* * cpusets delegate hotplug operations to a worker to "solve" the * lock order problems. Wait for the worker, but only if tasks are * _not_ frozen (suspend, hibernate) as that would wait forever. * * The wait is required because otherwise the hotplug operation * returns with inconsistent state, which could even be observed in * user space when a new CPU is brought up. The CPU plug uevent * would be delivered and user space reacting on it would fail to * move tasks to the newly plugged CPU up to the point where the * work has finished because up to that point the newly plugged CPU * is not assignable in cpusets/cgroups. On unplug that's not * necessarily a visible issue, but it is still inconsistent state, * which is the real problem which needs to be "fixed". This can't * prevent the transient state between scheduling the work and * returning from waiting for it. */ if (!tasks_frozen) cpuset_wait_for_hotplug(); } #ifdef CONFIG_HOTPLUG_CPU #ifndef arch_clear_mm_cpumask_cpu #define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) #endif /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id * * This function walks all processes, finds a valid mm struct for each one and * then clears a corresponding bit in mm's cpumask. While this all sounds * trivial, there are various non-obvious corner cases, which this function * tries to solve in a safe manner. * * Also note that the function uses a somewhat relaxed locking scheme, so it may * be called only for an already offlined CPU. */ void clear_tasks_mm_cpumask(int cpu) { struct task_struct *p; /* * This function is called after the cpu is taken down and marked * offline, so its not like new tasks will ever get this cpu set in * their mm mask. -- Peter Zijlstra * Thus, we may use rcu_read_lock() here, instead of grabbing * full-fledged tasklist_lock. */ WARN_ON(cpu_online(cpu)); rcu_read_lock(); for_each_process(p) { struct task_struct *t; /* * Main thread might exit, but other threads may still have * a valid mm. Find one. */ t = find_lock_task_mm(p); if (!t) continue; arch_clear_mm_cpumask_cpu(cpu, t->mm); task_unlock(t); } rcu_read_unlock(); } /* Take this CPU down. */ static int take_cpu_down(void *_param) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); if (err < 0) return err; /* * Must be called from CPUHP_TEARDOWN_CPU, which means, as we are going * down, that the current state is CPUHP_TEARDOWN_CPU - 1. */ WARN_ON(st->state != (CPUHP_TEARDOWN_CPU - 1)); /* * Invoke the former CPU_DYING callbacks. DYING must not fail! */ cpuhp_invoke_callback_range_nofail(false, cpu, st, target); /* Give up timekeeping duties */ tick_handover_do_timer(); /* Remove CPU from timer broadcasting */ tick_offline_cpu(cpu); /* Park the stopper thread */ stop_machine_park(cpu); return 0; } static int takedown_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int err; /* Park the smpboot threads */ kthread_park(st->thread); /* * Prevent irq alloc/free while the dying cpu reorganizes the * interrupt affinities. */ irq_lock_sparse(); /* * So now all preempt/rcu users must observe !cpu_active(). */ err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU refused to die */ irq_unlock_sparse(); /* Unpark the hotplug thread so we can rollback there */ kthread_unpark(st->thread); return err; } BUG_ON(cpu_online(cpu)); /* * The teardown callback for CPUHP_AP_SCHED_STARTING will have removed * all runnable tasks from the CPU, there's only the idle task left now * that the migration thread is done doing the stop_machine thing. * * Wait for the stop thread to go away. */ wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ irq_unlock_sparse(); hotplug_cpu__broadcast_tick_pull(cpu); /* This actually kills the CPU. */ __cpu_die(cpu); tick_cleanup_dead_cpu(cpu); rcutree_migrate_callbacks(cpu); return 0; } static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); BUG_ON(st->state != CPUHP_AP_OFFLINE); rcu_report_dead(smp_processor_id()); st->state = CPUHP_AP_IDLE_DEAD; /* * We cannot call complete after rcu_report_dead() so we delegate it * to an online cpu. */ smp_call_function_single(cpumask_first(cpu_online_mask), cpuhp_complete_idle_dead, st, 0); } static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(false, cpu, st, target); if (ret) { pr_debug("CPU DOWN failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (st->state < prev_state) WARN_ON(cpuhp_invoke_callback_range(true, cpu, st, prev_state)); } return ret; } /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int prev_state, ret = 0; if (num_online_cpus() == 1) return -EBUSY; if (!cpu_present(cpu)) return -EINVAL; cpus_write_lock(); cpuhp_tasks_frozen = tasks_frozen; prev_state = cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; /* * We might have stopped still in the range of the AP hotplug * thread. Nothing to do anymore. */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state < prev_state) { if (st->state == CPUHP_TEARDOWN_CPU) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } else { WARN(1, "DEAD callback error for CPU%d", cpu); } } out: cpus_write_unlock(); /* * Do post unplug cleanup. This is still protected against * concurrent CPU hotplug via cpu_add_remove_lock. */ lockup_detector_cleanup(); arch_smt_update(); cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) { if (cpu_hotplug_disabled) return -EBUSY; return _cpu_down(cpu, 0, target); } static int cpu_down(unsigned int cpu, enum cpuhp_state target) { int err; cpu_maps_update_begin(); err = cpu_down_maps_locked(cpu, target); cpu_maps_update_done(); return err; } /** * cpu_device_down - Bring down a cpu device * @dev: Pointer to the cpu device to offline * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use remove_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_down(struct device *dev) { return cpu_down(dev->id, CPUHP_OFFLINE); } int remove_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_offline(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(remove_cpu); void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { unsigned int cpu; int error; cpu_maps_update_begin(); /* * Make certain the cpu I'm about to reboot on is online. * * This is inline to what migrate_to_reboot_cpu() already do. */ if (!cpu_online(primary_cpu)) primary_cpu = cpumask_first(cpu_online_mask); for_each_online_cpu(cpu) { if (cpu == primary_cpu) continue; error = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (error) { pr_err("Failed to offline CPU%d - error=%d", cpu, error); break; } } /* * Ensure all but the reboot CPU are offline. */ BUG_ON(num_online_cpus() > 1); /* * Make sure the CPUs won't be enabled by someone else after this * point. Kexec will reboot to a new kernel shortly resetting * everything along the way. */ cpu_hotplug_disabled++; cpu_maps_update_done(); } #else #define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU * @cpu: cpu that just started * * It must be called by the arch code on the new cpu, before the new cpu * enables interrupts and before the "boot" cpu returns from __cpu_up(). */ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ cpumask_set_cpu(cpu, &cpus_booted_once_mask); /* * STARTING must not fail! */ cpuhp_invoke_callback_range_nofail(true, cpu, st, target); } /* * Called from the idle task. Wake up the controlling task which brings the * hotplug thread of the upcoming CPU up and then delegates the rest of the * online bringup to the hotplug thread. */ void cpuhp_online_idle(enum cpuhp_state state) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); /* Happens for the boot cpu */ if (state != CPUHP_AP_ONLINE_IDLE) return; /* * Unpart the stopper thread before we start the idle loop (and start * scheduling); this ensures the stopper task is always available. */ stop_machine_unpark(smp_processor_id()); st->state = CPUHP_AP_ONLINE_IDLE; complete_ap_thread(st, true); } static int switch_to_rt_policy(void) { struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; unsigned int policy = current->policy; if (policy == SCHED_NORMAL) /* Switch to SCHED_FIFO from SCHED_NORMAL. */ return sched_setscheduler_nocheck(current, SCHED_FIFO, ¶m); else return 1; } static int switch_to_fair_policy(void) { struct sched_param param = { .sched_priority = 0 }; return sched_setscheduler_nocheck(current, SCHED_NORMAL, ¶m); } /* Requires cpu_add_remove_lock to be held */ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle; int ret = 0; cpus_write_lock(); if (!cpu_present(cpu)) { ret = -EINVAL; goto out; } /* * The caller of cpu_up() might have raced with another * caller. Nothing to do. */ if (st->state >= target) goto out; if (st->state == CPUHP_OFFLINE) { /* Let it fail before we try to bring the cpu up */ idle = idle_thread_get(cpu); if (IS_ERR(idle)) { ret = PTR_ERR(idle); goto out; } } cpuhp_tasks_frozen = tasks_frozen; cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. */ if (st->state > CPUHP_BRINGUP_CPU) { ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; } /* * Try to reach the target state. We max out on the BP at * CPUHP_BRINGUP_CPU. After that the AP hotplug thread is * responsible for bringing it up to the target state. */ target = min((int)target, CPUHP_BRINGUP_CPU); ret = cpuhp_up_callbacks(cpu, st, target); out: cpus_write_unlock(); arch_smt_update(); cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } static int cpu_up(unsigned int cpu, enum cpuhp_state target) { int err = 0; int switch_err; if (!cpu_possible(cpu)) { pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n", cpu); #if defined(CONFIG_IA64) pr_err("please check additional_cpus= boot parameter\n"); #endif return -EINVAL; } /* * CPU hotplug operations consists of many steps and each step * calls a callback of core kernel subsystem. CPU hotplug-in * operation may get preempted by other CFS tasks and whole * operation of cpu hotplug in CPU gets delayed. Switch the * current task to SCHED_FIFO from SCHED_NORMAL, so that * hotplug in operation may complete quickly in heavy loaded * conditions and new CPU will start handle the workload. */ switch_err = switch_to_rt_policy(); err = try_online_node(cpu_to_node(cpu)); if (err) goto switch_out; cpu_maps_update_begin(); if (cpu_hotplug_disabled) { err = -EBUSY; goto out; } if (!cpu_smt_allowed(cpu)) { err = -EPERM; goto out; } err = _cpu_up(cpu, 0, target); out: cpu_maps_update_done(); switch_out: if (!switch_err) { switch_err = switch_to_fair_policy(); if (switch_err) pr_err("Hotplug policy switch err=%d Task %s pid=%d\n", switch_err, current->comm, current->pid); } return err; } /** * cpu_device_up - Bring up a cpu device * @dev: Pointer to the cpu device to online * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use add_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_up(struct device *dev) { return cpu_up(dev->id, CPUHP_ONLINE); } int add_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_online(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(add_cpu); /** * bringup_hibernate_cpu - Bring up the CPU that we hibernated on * @sleep_cpu: The cpu we hibernated on and should be brought up. * * On some architectures like arm64, we can hibernate on any CPU, but on * wake up the CPU we hibernated on might be offline as a side effect of * using maxcpus= for example. * * Return: %0 on success or a negative errno code */ int bringup_hibernate_cpu(unsigned int sleep_cpu) { int ret; if (!cpu_online(sleep_cpu)) { pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n"); ret = cpu_up(sleep_cpu, CPUHP_ONLINE); if (ret) { pr_err("Failed to bring hibernate-CPU up!\n"); return ret; } } return 0; } void bringup_nonboot_cpus(unsigned int setup_max_cpus) { unsigned int cpu; for_each_present_cpu(cpu) { if (num_online_cpus() >= setup_max_cpus) break; if (!cpu_online(cpu)) cpu_up(cpu, CPUHP_ONLINE); } } #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; int freeze_secondary_cpus(int primary) { int cpu, error = 0; cpu_maps_update_begin(); if (primary == -1) { primary = cpumask_first(cpu_online_mask); if (!housekeeping_cpu(primary, HK_FLAG_TIMER)) primary = housekeeping_any_cpu(HK_FLAG_TIMER); } else { if (!cpu_online(primary)) primary = cpumask_first(cpu_online_mask); } /* * We take down all of the non-boot CPUs in one shot to avoid races * with the userspace trying to use the CPU hotplug at the same time */ cpumask_clear(frozen_cpus); pr_info("Disabling non-boot CPUs ...\n"); for_each_online_cpu(cpu) { if (cpu == primary) continue; if (pm_wakeup_pending()) { pr_info("Wakeup pending. Abort CPU freeze\n"); error = -EBUSY; break; } trace_suspend_resume(TPS("CPU_OFF"), cpu, true); error = _cpu_down(cpu, 1, CPUHP_OFFLINE); trace_suspend_resume(TPS("CPU_OFF"), cpu, false); if (!error) cpumask_set_cpu(cpu, frozen_cpus); else { pr_err("Error taking CPU%d down: %d\n", cpu, error); break; } } if (!error) BUG_ON(num_online_cpus() > 1); else pr_err("Non-boot CPUs are not disabled\n"); /* * Make sure the CPUs won't be enabled by someone else. We need to do * this even in case of failure as all freeze_secondary_cpus() users are * supposed to do thaw_secondary_cpus() on the failure path. */ cpu_hotplug_disabled++; cpu_maps_update_done(); return error; } void __weak arch_thaw_secondary_cpus_begin(void) { } void __weak arch_thaw_secondary_cpus_end(void) { } void thaw_secondary_cpus(void) { int cpu, error; /* Allow everyone to use the CPU hotplug again */ cpu_maps_update_begin(); __cpu_hotplug_enable(); if (cpumask_empty(frozen_cpus)) goto out; pr_info("Enabling non-boot CPUs ...\n"); arch_thaw_secondary_cpus_begin(); for_each_cpu(cpu, frozen_cpus) { trace_suspend_resume(TPS("CPU_ON"), cpu, true); error = _cpu_up(cpu, 1, CPUHP_ONLINE); trace_suspend_resume(TPS("CPU_ON"), cpu, false); if (!error) { pr_info("CPU%d is up\n", cpu); continue; } pr_warn("Error taking CPU%d up: %d\n", cpu, error); } arch_thaw_secondary_cpus_end(); cpumask_clear(frozen_cpus); out: cpu_maps_update_done(); } static int __init alloc_frozen_cpus(void) { if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO)) return -ENOMEM; return 0; } core_initcall(alloc_frozen_cpus); /* * When callbacks for CPU hotplug notifications are being executed, we must * ensure that the state of the system with respect to the tasks being frozen * or not, as reported by the notification, remains unchanged *throughout the * duration* of the execution of the callbacks. * Hence we need to prevent the freezer from racing with regular CPU hotplug. * * This synchronization is implemented by mutually excluding regular CPU * hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/ * Hibernate notifications. */ static int cpu_hotplug_pm_callback(struct notifier_block *nb, unsigned long action, void *ptr) { switch (action) { case PM_SUSPEND_PREPARE: case PM_HIBERNATION_PREPARE: cpu_hotplug_disable(); break; case PM_POST_SUSPEND: case PM_POST_HIBERNATION: cpu_hotplug_enable(); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static int __init cpu_hotplug_pm_sync_init(void) { /* * cpu_hotplug_pm_callback has higher priority than x86 * bsp_pm_callback which depends on cpu_hotplug_pm_callback * to disable cpu hotplug to avoid cpu hotplug race. */ pm_notifier(cpu_hotplug_pm_callback, 0); return 0; } core_initcall(cpu_hotplug_pm_sync_init); #endif /* CONFIG_PM_SLEEP_SMP */ int __boot_cpu_id; /* Horrific hacks because we can't add more to cpuhp_hp_states. */ static int random_and_perf_prepare_fusion(unsigned int cpu) { int (*fn)(unsigned int cpu); fn = perf_event_init_cpu; if (fn) fn(cpu); fn = random_prepare_cpu; if (fn) fn(cpu); return 0; } static int random_and_workqueue_online_fusion(unsigned int cpu) { int (*fn)(unsigned int cpu); fn = workqueue_online_cpu; if (fn) fn(cpu); fn = random_online_cpu; if (fn) fn(cpu); return 0; } #endif /* CONFIG_SMP */ /* Boot processor state steps */ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_OFFLINE] = { .name = "offline", .startup.single = NULL, .teardown.single = NULL, }, #ifdef CONFIG_SMP [CPUHP_CREATE_THREADS]= { .name = "threads:prepare", .startup.single = smpboot_create_threads, .teardown.single = NULL, .cant_stop = true, }, [CPUHP_PERF_PREPARE] = { .name = "perf:prepare", .startup.single = random_and_perf_prepare_fusion, .teardown.single = perf_event_exit_cpu, }, [CPUHP_WORKQUEUE_PREP] = { .name = "workqueue:prepare", .startup.single = workqueue_prepare_cpu, .teardown.single = NULL, }, [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, .teardown.single = hrtimers_dead_cpu, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", .startup.single = smpcfd_prepare_cpu, .teardown.single = smpcfd_dead_cpu, }, [CPUHP_RELAY_PREPARE] = { .name = "relay:prepare", .startup.single = relay_prepare_cpu, .teardown.single = NULL, }, [CPUHP_SLAB_PREPARE] = { .name = "slab:prepare", .startup.single = slab_prepare_cpu, .teardown.single = slab_dead_cpu, }, [CPUHP_RCUTREE_PREP] = { .name = "RCU/tree:prepare", .startup.single = rcutree_prepare_cpu, .teardown.single = rcutree_dead_cpu, }, /* * On the tear-down path, timers_dead_cpu() must be invoked * before blk_mq_queue_reinit_notify() from notify_dead(), * otherwise a RCU stall occurs. */ [CPUHP_TIMERS_PREPARE] = { .name = "timers:prepare", .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, /* Kicks the plugged cpu into life */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = bringup_cpu, .teardown.single = finish_cpu, .cant_stop = true, }, /* Final state before CPU kills itself */ [CPUHP_AP_IDLE_DEAD] = { .name = "idle:dead", }, /* * Last state before CPU enters the idle loop to die. Transient state * for synchronization. */ [CPUHP_AP_OFFLINE] = { .name = "ap:offline", .cant_stop = true, }, /* First state is scheduler control. Interrupts are disabled */ [CPUHP_AP_SCHED_STARTING] = { .name = "sched:starting", .startup.single = sched_cpu_starting, .teardown.single = sched_cpu_dying, }, [CPUHP_AP_RCUTREE_DYING] = { .name = "RCU/tree:dying", .startup.single = NULL, .teardown.single = rcutree_dying_cpu, }, [CPUHP_AP_SMPCFD_DYING] = { .name = "smpcfd:dying", .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { .name = "ap:online", }, /* * Handled on control processor until the plugged processor manages * this itself. */ [CPUHP_TEARDOWN_CPU] = { .name = "cpu:teardown", .startup.single = NULL, .teardown.single = takedown_cpu, .cant_stop = true, }, [CPUHP_AP_SCHED_WAIT_EMPTY] = { .name = "sched:waitempty", .startup.single = NULL, .teardown.single = sched_cpu_wait_empty, }, /* Handle smpboot threads park/unpark */ [CPUHP_AP_SMPBOOT_THREADS] = { .name = "smpboot/threads:online", .startup.single = smpboot_unpark_threads, .teardown.single = smpboot_park_threads, }, [CPUHP_AP_IRQ_AFFINITY_ONLINE] = { .name = "irq/affinity:online", .startup.single = irq_affinity_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_PERF_ONLINE] = { .name = "perf:online", .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, [CPUHP_AP_WATCHDOG_ONLINE] = { .name = "lockup_detector:online", .startup.single = lockup_detector_online_cpu, .teardown.single = lockup_detector_offline_cpu, }, [CPUHP_AP_WORKQUEUE_ONLINE] = { .name = "workqueue:online", .startup.single = random_and_workqueue_online_fusion, .teardown.single = workqueue_offline_cpu, }, [CPUHP_AP_RCUTREE_ONLINE] = { .name = "RCU/tree:online", .startup.single = rcutree_online_cpu, .teardown.single = rcutree_offline_cpu, }, #endif /* * The dynamically registered state space is here */ #ifdef CONFIG_SMP /* Last state is scheduler control setting the cpu active */ [CPUHP_AP_ACTIVE] = { .name = "sched:active", .startup.single = sched_cpu_activate, .teardown.single = sched_cpu_deactivate, }, #endif /* CPU is fully up and running. */ [CPUHP_ONLINE] = { .name = "online", .startup.single = NULL, .teardown.single = NULL, }, }; /* Sanity check for callbacks */ static int cpuhp_cb_check(enum cpuhp_state state) { if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE) return -EINVAL; return 0; } /* * Returns a free for dynamic slot assignment of the Online state. The states * are protected by the cpuhp_slot_states mutex and an empty slot is identified * by having no name assigned. */ static int cpuhp_reserve_state(enum cpuhp_state state) { enum cpuhp_state i, end; struct cpuhp_step *step; switch (state) { case CPUHP_AP_ONLINE_DYN: step = cpuhp_hp_states + CPUHP_AP_ONLINE_DYN; end = CPUHP_AP_ONLINE_DYN_END; break; case CPUHP_BP_PREPARE_DYN: step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN; end = CPUHP_BP_PREPARE_DYN_END; break; default: return -EINVAL; } for (i = state; i <= end; i++, step++) { if (!step->name) return i; } WARN(1, "No more dynamic states available for CPU hotplug\n"); return -ENOSPC; } static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { /* (Un)Install the callbacks for further cpu hotplug operations */ struct cpuhp_step *sp; int ret = 0; /* * If name is NULL, then the state gets removed. * * CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on * the first allocation from these dynamic ranges, so the removal * would trigger a new allocation and clear the wrong (already * empty) state, leaving the callbacks of the to be cleared state * dangling, which causes wreckage on the next hotplug operation. */ if (name && (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN)) { ret = cpuhp_reserve_state(state); if (ret < 0) return ret; state = ret; } sp = cpuhp_get_step(state); if (name && sp->name) return -EBUSY; sp->startup.single = startup; sp->teardown.single = teardown; sp->name = name; sp->multi_instance = multi_instance; INIT_HLIST_HEAD(&sp->list); return ret; } static void *cpuhp_get_teardown_cb(enum cpuhp_state state) { return cpuhp_get_step(state)->teardown.single; } /* * Call the startup/teardown function for a step either on the AP or * on the current CPU. */ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_step *sp = cpuhp_get_step(state); int ret; /* * If there's nothing to do, we done. * Relies on the union for multi_instance. */ if (cpuhp_step_empty(bringup, sp)) return 0; /* * The non AP bound callbacks can fail on bringup. On teardown * e.g. module removal we crash for now. */ #ifdef CONFIG_SMP if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #endif BUG_ON(ret && !bringup); return ret; } /* * Called from __cpuhp_setup_state on a recoverable failure. * * Note: The teardown callbacks for rollback are not allowed to fail! */ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state, struct hlist_node *node) { int cpu; /* Roll back the already executed steps on the other cpus */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpu >= failedcpu) break; /* Did we invoke the startup call on that cpu ? */ if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } } int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp; int cpu; int ret; lockdep_assert_cpus_held(); sp = cpuhp_get_step(state); if (sp->multi_instance == false) return -EINVAL; mutex_lock(&cpuhp_state_mutex); if (!invoke || !sp->startup.multi) goto add_node; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, node); if (ret) { if (sp->teardown.multi) cpuhp_rollback_install(cpu, state, node); goto unlock; } } add_node: ret = 0; hlist_add_head(node, &sp->list); unlock: mutex_unlock(&cpuhp_state_mutex); return ret; } int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { int ret; cpus_read_lock(); ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance); /** * __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state * @state: The state to setup * @name: Name of the step * @invoke: If true, the startup function is invoked for cpus where * cpu state >= @state * @startup: startup callback function * @teardown: teardown callback function * @multi_instance: State is set up for multiple instances which get * added afterwards. * * The caller needs to hold cpus read locked while calling this function. * Return: * On success: * Positive state number if @state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN; * 0 for all other states * On failure: proper (negative) error code */ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int cpu, ret = 0; bool dynstate; lockdep_assert_cpus_held(); if (cpuhp_cb_check(state) || !name) return -EINVAL; mutex_lock(&cpuhp_state_mutex); ret = cpuhp_store_callbacks(state, name, startup, teardown, multi_instance); dynstate = state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN; if (ret > 0 && dynstate) { state = ret; ret = 0; } if (ret || !invoke || !startup) goto out; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, NULL); if (ret) { if (teardown) cpuhp_rollback_install(cpu, state, NULL); cpuhp_store_callbacks(state, NULL, NULL, NULL, false); goto out; } } out: mutex_unlock(&cpuhp_state_mutex); /* * If the requested state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN, * return the dynamically allocated state in case of success. */ if (!ret && dynstate) return state; return ret; } EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked); int __cpuhp_setup_state(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int ret; cpus_read_lock(); ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup, teardown, multi_instance); cpus_read_unlock(); return ret; } EXPORT_SYMBOL(__cpuhp_setup_state); int __cpuhp_state_remove_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); if (!sp->multi_instance) return -EINVAL; cpus_read_lock(); mutex_lock(&cpuhp_state_mutex); if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } remove: hlist_del(node); mutex_unlock(&cpuhp_state_mutex); cpus_read_unlock(); return 0; } EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance); /** * __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state * @state: The state to remove * @invoke: If true, the teardown function is invoked for cpus where * cpu state >= @state * * The caller needs to hold cpus read locked while calling this function. * The teardown callback is currently not allowed to fail. Think * about module removal! */ void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); lockdep_assert_cpus_held(); mutex_lock(&cpuhp_state_mutex); if (sp->multi_instance) { WARN(!hlist_empty(&sp->list), "Error: Removing state %d which has instances left.\n", state); goto remove; } if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, NULL); } remove: cpuhp_store_callbacks(state, NULL, NULL, NULL, false); mutex_unlock(&cpuhp_state_mutex); } EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked); void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) { cpus_read_lock(); __cpuhp_remove_state_cpuslocked(state, invoke); cpus_read_unlock(); } EXPORT_SYMBOL(__cpuhp_remove_state); #ifdef CONFIG_HOTPLUG_SMT static void cpuhp_offline_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = true; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_OFFLINE); } static void cpuhp_online_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = false; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_ONLINE); } int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; cpu_maps_update_begin(); for_each_online_cpu(cpu) { if (topology_is_primary_thread(cpu)) continue; ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (ret) break; /* * As this needs to hold the cpu maps lock it's impossible * to call device_offline() because that ends up calling * cpu_down() which takes cpu maps lock. cpu maps lock * needs to be held as this might race against in kernel * abusers of the hotplug machinery (thermal management). * * So nothing would update device:offline state. That would * leave the sysfs entry stale and prevent onlining after * smt control has been changed to 'off' again. This is * called under the sysfs hotplug lock, so it is properly * serialized against the regular offline usage. */ cpuhp_offline_cpu_device(cpu); } if (!ret) cpu_smt_control = ctrlval; cpu_maps_update_done(); return ret; } int cpuhp_smt_enable(void) { int cpu, ret = 0; cpu_maps_update_begin(); cpu_smt_control = CPU_SMT_ENABLED; for_each_present_cpu(cpu) { /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) continue; ret = _cpu_up(cpu, 0, CPUHP_ONLINE); if (ret) break; /* See comment in cpuhp_smt_disable() */ cpuhp_online_cpu_device(cpu); } cpu_maps_update_done(); return ret; } #endif #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) static ssize_t state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->state); } static DEVICE_ATTR_RO(state); static ssize_t target_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int target, ret; ret = kstrtoint(buf, 10, &target); if (ret) return ret; #ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE) return -EINVAL; #else if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE) return -EINVAL; #endif ret = lock_device_hotplug_sysfs(); if (ret) return ret; mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(target); ret = !sp->name || sp->cant_stop ? -EINVAL : 0; mutex_unlock(&cpuhp_state_mutex); if (ret) goto out; if (st->state < target) ret = cpu_up(dev->id, target); else if (st->state > target) ret = cpu_down(dev->id, target); else if (WARN_ON(st->target != target)) st->target = target; out: unlock_device_hotplug(); return ret ? ret : count; } static ssize_t target_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->target); } static DEVICE_ATTR_RW(target); static ssize_t fail_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int fail, ret; ret = kstrtoint(buf, 10, &fail); if (ret) return ret; if (fail == CPUHP_INVALID) { st->fail = fail; return count; } if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE) return -EINVAL; /* * Cannot fail STARTING/DYING callbacks. */ if (cpuhp_is_atomic_state(fail)) return -EINVAL; /* * DEAD callbacks cannot fail... * ... neither can CPUHP_BRINGUP_CPU during hotunplug. The latter * triggering STARTING callbacks, a failure in this state would * hinder rollback. */ if (fail <= CPUHP_BRINGUP_CPU && st->state > CPUHP_BRINGUP_CPU) return -EINVAL; /* * Cannot fail anything that doesn't have callbacks. */ mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(fail); if (!sp->startup.single && !sp->teardown.single) ret = -EINVAL; mutex_unlock(&cpuhp_state_mutex); if (ret) return ret; st->fail = fail; return count; } static ssize_t fail_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->fail); } static DEVICE_ATTR_RW(fail); static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, &dev_attr_fail.attr, NULL }; static const struct attribute_group cpuhp_cpu_attr_group = { .attrs = cpuhp_cpu_attrs, .name = "hotplug", NULL }; static ssize_t states_show(struct device *dev, struct device_attribute *attr, char *buf) { ssize_t cur, res = 0; int i; mutex_lock(&cpuhp_state_mutex); for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) { struct cpuhp_step *sp = cpuhp_get_step(i); if (sp->name) { cur = sprintf(buf, "%3d: %s\n", i, sp->name); buf += cur; res += cur; } } mutex_unlock(&cpuhp_state_mutex); return res; } static DEVICE_ATTR_RO(states); static struct attribute *cpuhp_cpu_root_attrs[] = { &dev_attr_states.attr, NULL }; static const struct attribute_group cpuhp_cpu_root_attr_group = { .attrs = cpuhp_cpu_root_attrs, .name = "hotplug", NULL }; #ifdef CONFIG_HOTPLUG_SMT static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int ctrlval, ret; if (sysfs_streq(buf, "on")) ctrlval = CPU_SMT_ENABLED; else if (sysfs_streq(buf, "off")) ctrlval = CPU_SMT_DISABLED; else if (sysfs_streq(buf, "forceoff")) ctrlval = CPU_SMT_FORCE_DISABLED; else return -EINVAL; if (cpu_smt_control == CPU_SMT_FORCE_DISABLED) return -EPERM; if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return -ENODEV; ret = lock_device_hotplug_sysfs(); if (ret) return ret; if (ctrlval != cpu_smt_control) { switch (ctrlval) { case CPU_SMT_ENABLED: ret = cpuhp_smt_enable(); break; case CPU_SMT_DISABLED: case CPU_SMT_FORCE_DISABLED: ret = cpuhp_smt_disable(ctrlval); break; } } unlock_device_hotplug(); return ret ? ret : count; } #else /* !CONFIG_HOTPLUG_SMT */ static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return -ENODEV; } #endif /* CONFIG_HOTPLUG_SMT */ static const char *smt_states[] = { [CPU_SMT_ENABLED] = "on", [CPU_SMT_DISABLED] = "off", [CPU_SMT_FORCE_DISABLED] = "forceoff", [CPU_SMT_NOT_SUPPORTED] = "notsupported", [CPU_SMT_NOT_IMPLEMENTED] = "notimplemented", }; static ssize_t control_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *state = smt_states[cpu_smt_control]; return snprintf(buf, PAGE_SIZE - 2, "%s\n", state); } static ssize_t control_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return __store_smt_control(dev, attr, buf, count); } static DEVICE_ATTR_RW(control); static ssize_t active_show(struct device *dev, struct device_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active()); } static DEVICE_ATTR_RO(active); static struct attribute *cpuhp_smt_attrs[] = { &dev_attr_control.attr, &dev_attr_active.attr, NULL }; static const struct attribute_group cpuhp_smt_attr_group = { .attrs = cpuhp_smt_attrs, .name = "smt", NULL }; static int __init cpu_smt_sysfs_init(void) { return sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_smt_attr_group); } static int __init cpuhp_sysfs_init(void) { int cpu, ret; ret = cpu_smt_sysfs_init(); if (ret) return ret; ret = sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_cpu_root_attr_group); if (ret) return ret; for_each_possible_cpu(cpu) { struct device *dev = get_cpu_device(cpu); if (!dev) continue; ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group); if (ret) return ret; } return 0; } device_initcall(cpuhp_sysfs_init); #endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */ /* * cpu_bit_bitmap[] is a special, "compressed" data structure that * represents all NR_CPUS bits binary values of 1<<nr. * * It is used by cpumask_of() to get a constant address to a CPU * mask value that has a single bit set only. */ /* cpu_bit_bitmap[0] is empty - so we can back into it */ #define MASK_DECLARE_1(x) [x+1][0] = (1UL << (x)) #define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1) #define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2) #define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4) const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = { MASK_DECLARE_8(0), MASK_DECLARE_8(8), MASK_DECLARE_8(16), MASK_DECLARE_8(24), #if BITS_PER_LONG > 32 MASK_DECLARE_8(32), MASK_DECLARE_8(40), MASK_DECLARE_8(48), MASK_DECLARE_8(56), #endif }; EXPORT_SYMBOL_GPL(cpu_bit_bitmap); const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; EXPORT_SYMBOL(cpu_all_bits); #ifdef CONFIG_INIT_ALL_POSSIBLE struct cpumask __cpu_possible_mask __read_mostly = {CPU_BITS_ALL}; #else struct cpumask __cpu_possible_mask __read_mostly; #endif EXPORT_SYMBOL(__cpu_possible_mask); struct cpumask __cpu_online_mask __read_mostly; EXPORT_SYMBOL(__cpu_online_mask); struct cpumask __cpu_present_mask __read_mostly; EXPORT_SYMBOL(__cpu_present_mask); struct cpumask __cpu_active_mask __read_mostly; EXPORT_SYMBOL(__cpu_active_mask); struct cpumask __cpu_dying_mask __read_mostly; EXPORT_SYMBOL(__cpu_dying_mask); atomic_t __num_online_cpus __read_mostly; EXPORT_SYMBOL(__num_online_cpus); void init_cpu_present(const struct cpumask *src) { cpumask_copy(&__cpu_present_mask, src); } void init_cpu_possible(const struct cpumask *src) { cpumask_copy(&__cpu_possible_mask, src); } void init_cpu_online(const struct cpumask *src) { cpumask_copy(&__cpu_online_mask, src); } void set_cpu_online(unsigned int cpu, bool online) { /* * atomic_inc/dec() is required to handle the horrid abuse of this * function by the reboot and kexec code which invoke it from * IPI/NMI broadcasts when shutting down CPUs. Invocation from * regular CPU hotplug is properly serialized. * * Note, that the fact that __num_online_cpus is of type atomic_t * does not protect readers which are not serialized against * concurrent hotplug operations. */ if (online) { if (!cpumask_test_and_set_cpu(cpu, &__cpu_online_mask)) atomic_inc(&__num_online_cpus); } else { if (cpumask_test_and_clear_cpu(cpu, &__cpu_online_mask)) atomic_dec(&__num_online_cpus); } } /* * Activate the first processor. */ void __init boot_cpu_init(void) { int cpu = smp_processor_id(); /* Mark the boot cpu "present", "online" etc for SMP and UP case */ set_cpu_online(cpu, true); set_cpu_active(cpu, true); set_cpu_present(cpu, true); set_cpu_possible(cpu, true); #ifdef CONFIG_SMP __boot_cpu_id = cpu; #endif } /* * Must be called _AFTER_ setting up the per_cpu areas */ void __init boot_cpu_hotplug_init(void) { #ifdef CONFIG_SMP cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); } /* * These are used for a global "mitigations=" cmdline option for toggling * optional CPU mitigations. */ enum cpu_mitigations { CPU_MITIGATIONS_OFF, CPU_MITIGATIONS_AUTO, CPU_MITIGATIONS_AUTO_NOSMT, }; static enum cpu_mitigations cpu_mitigations __ro_after_init = IS_ENABLED(CONFIG_CPU_MITIGATIONS) ? CPU_MITIGATIONS_AUTO : CPU_MITIGATIONS_OFF; static int __init mitigations_parse_cmdline(char *arg) { if (!strcmp(arg, "off")) cpu_mitigations = CPU_MITIGATIONS_OFF; else if (!strcmp(arg, "auto")) cpu_mitigations = CPU_MITIGATIONS_AUTO; else if (!strcmp(arg, "auto,nosmt")) cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT; else pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n", arg); return 0; } early_param("mitigations", mitigations_parse_cmdline); /* mitigations=off */ bool cpu_mitigations_off(void) { return cpu_mitigations == CPU_MITIGATIONS_OFF; } EXPORT_SYMBOL_GPL(cpu_mitigations_off); /* mitigations=auto,nosmt */ bool cpu_mitigations_auto_nosmt(void) { return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; } EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); |
| 91 62 50 13 69 64 60 115 115 112 112 91 83 8 30 30 30 5 1 5 4 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV6 GSO/GRO offload support * Linux INET6 implementation */ #include <linux/kernel.h> #include <linux/socket.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/printk.h> #include <net/protocol.h> #include <net/ipv6.h> #include <net/inet_common.h> #include <net/tcp.h> #include <net/udp.h> #include <net/gro.h> #include "ip6_offload.h" /* All GRO functions are always builtin, except UDP over ipv6, which lays in * ipv6 module, as it depends on UDPv6 lookup function, so we need special care * when ipv6 is built as a module */ #if IS_BUILTIN(CONFIG_IPV6) #define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__) #else #define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__) #endif #define indirect_call_gro_receive_l4(f2, f1, cb, head, skb) \ ({ \ unlikely(gro_recursion_inc_test(skb)) ? \ NAPI_GRO_CB(skb)->flush |= 1, NULL : \ INDIRECT_CALL_L4(cb, f2, f1, head, skb); \ }) static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) { const struct net_offload *ops = NULL; for (;;) { struct ipv6_opt_hdr *opth; int len; if (proto != NEXTHDR_HOP) { ops = rcu_dereference(inet6_offloads[proto]); if (unlikely(!ops)) break; if (!(ops->flags & INET6_PROTO_GSO_EXTHDR)) break; } if (unlikely(!pskb_may_pull(skb, 8))) break; opth = (void *)skb->data; len = ipv6_optlen(opth); if (unlikely(!pskb_may_pull(skb, len))) break; opth = (void *)skb->data; proto = opth->nexthdr; __skb_pull(skb, len); } return proto; } static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct ipv6hdr *ipv6h; const struct net_offload *ops; int proto; struct frag_hdr *fptr; unsigned int payload_len; u8 *prevhdr; int offset = 0; bool encap, udpfrag; int nhoff; bool gso_partial; skb_reset_network_header(skb); nhoff = skb_network_header(skb) - skb_mac_header(skb); if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) goto out; encap = SKB_GSO_CB(skb)->encap_level > 0; if (encap) features &= skb->dev->hw_enc_features; SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h); ipv6h = ipv6_hdr(skb); __skb_pull(skb, sizeof(*ipv6h)); segs = ERR_PTR(-EPROTONOSUPPORT); proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); if (skb->encapsulation && skb_shinfo(skb)->gso_type & (SKB_GSO_IPXIP4 | SKB_GSO_IPXIP6)) udpfrag = proto == IPPROTO_UDP && encap && (skb_shinfo(skb)->gso_type & SKB_GSO_UDP); else udpfrag = proto == IPPROTO_UDP && !skb->encapsulation && (skb_shinfo(skb)->gso_type & SKB_GSO_UDP); ops = rcu_dereference(inet6_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { skb_reset_transport_header(skb); segs = ops->callbacks.gso_segment(skb, features); if (!segs) skb->network_header = skb_mac_header(skb) + nhoff - skb->head; } if (IS_ERR_OR_NULL(segs)) goto out; gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); for (skb = segs; skb; skb = skb->next) { ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff); if (gso_partial && skb_is_gso(skb)) payload_len = skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)(ipv6h + 1); else payload_len = skb->len - nhoff - sizeof(*ipv6h); ipv6h->payload_len = htons(payload_len); skb->network_header = (u8 *)ipv6h - skb->head; skb_reset_mac_len(skb); if (udpfrag) { int err = ip6_find_1stfragopt(skb, &prevhdr); if (err < 0) { kfree_skb_list(segs); return ERR_PTR(err); } fptr = (struct frag_hdr *)((u8 *)ipv6h + err); fptr->frag_off = htons(offset); if (skb->next) fptr->frag_off |= htons(IP6_MF); offset += (ntohs(ipv6h->payload_len) - sizeof(struct frag_hdr)); } if (encap) skb_reset_inner_headers(skb); } out: return segs; } /* Return the total length of all the extension hdrs, following the same * logic in ipv6_gso_pull_exthdrs() when parsing ext-hdrs. */ static int ipv6_exthdrs_len(struct ipv6hdr *iph, const struct net_offload **opps) { struct ipv6_opt_hdr *opth = (void *)iph; int len = 0, proto, optlen = sizeof(*iph); proto = iph->nexthdr; for (;;) { if (proto != NEXTHDR_HOP) { *opps = rcu_dereference(inet6_offloads[proto]); if (unlikely(!(*opps))) break; if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR)) break; } opth = (void *)opth + optlen; optlen = ipv6_optlen(opth); len += optlen; proto = opth->nexthdr; } return len; } INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, struct sk_buff *skb) { const struct net_offload *ops; struct sk_buff *pp = NULL; struct sk_buff *p; struct ipv6hdr *iph; unsigned int nlen; unsigned int hlen; unsigned int off; u16 flush = 1; int proto; off = skb_gro_offset(skb); hlen = off + sizeof(*iph); iph = skb_gro_header_fast(skb, off); if (skb_gro_header_hard(skb, hlen)) { iph = skb_gro_header_slow(skb, hlen, off); if (unlikely(!iph)) goto out; } skb_set_network_header(skb, off); skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); flush += ntohs(iph->payload_len) != skb_gro_len(skb); proto = iph->nexthdr; ops = rcu_dereference(inet6_offloads[proto]); if (!ops || !ops->callbacks.gro_receive) { __pskb_pull(skb, skb_gro_offset(skb)); skb_gro_frag0_invalidate(skb); proto = ipv6_gso_pull_exthdrs(skb, proto); skb_gro_pull(skb, -skb_transport_offset(skb)); skb_reset_transport_header(skb); __skb_push(skb, skb_gro_offset(skb)); ops = rcu_dereference(inet6_offloads[proto]); if (!ops || !ops->callbacks.gro_receive) goto out; iph = ipv6_hdr(skb); } NAPI_GRO_CB(skb)->proto = proto; flush--; nlen = skb_network_header_len(skb); list_for_each_entry(p, head, list) { const struct ipv6hdr *iph2; __be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */ if (!NAPI_GRO_CB(p)->same_flow) continue; iph2 = (struct ipv6hdr *)(p->data + off); first_word = *(__be32 *)iph ^ *(__be32 *)iph2; /* All fields must match except length and Traffic Class. * XXX skbs on the gro_list have all been parsed and pulled * already so we don't need to compare nlen * (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops))) * memcmp() alone below is sufficient, right? */ if ((first_word & htonl(0xF00FFFFF)) || !ipv6_addr_equal(&iph->saddr, &iph2->saddr) || !ipv6_addr_equal(&iph->daddr, &iph2->daddr) || *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) { not_same_flow: NAPI_GRO_CB(p)->same_flow = 0; continue; } if (unlikely(nlen > sizeof(struct ipv6hdr))) { if (memcmp(iph + 1, iph2 + 1, nlen - sizeof(struct ipv6hdr))) goto not_same_flow; } /* flush if Traffic Class fields are different */ NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000)); NAPI_GRO_CB(p)->flush |= flush; /* If the previous IP ID value was based on an atomic * datagram we can overwrite the value and ignore it. */ if (NAPI_GRO_CB(skb)->is_atomic) NAPI_GRO_CB(p)->flush_id = 0; } NAPI_GRO_CB(skb)->is_atomic = true; NAPI_GRO_CB(skb)->flush |= flush; skb_gro_postpull_rcsum(skb, iph, nlen); pp = indirect_call_gro_receive_l4(tcp6_gro_receive, udp6_gro_receive, ops->callbacks.gro_receive, head, skb); out: skb_gro_flush_final(skb, pp, flush); return pp; } static struct sk_buff *sit_ip6ip6_gro_receive(struct list_head *head, struct sk_buff *skb) { /* Common GRO receive for SIT and IP6IP6 */ if (NAPI_GRO_CB(skb)->encap_mark) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } NAPI_GRO_CB(skb)->encap_mark = 1; return ipv6_gro_receive(head, skb); } static struct sk_buff *ip4ip6_gro_receive(struct list_head *head, struct sk_buff *skb) { /* Common GRO receive for SIT and IP6IP6 */ if (NAPI_GRO_CB(skb)->encap_mark) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } NAPI_GRO_CB(skb)->encap_mark = 1; return inet_gro_receive(head, skb); } INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff) { const struct net_offload *ops; struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff); int err = -ENOSYS; if (skb->encapsulation) { skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6)); skb_set_inner_network_header(skb, nhoff); } iph->payload_len = htons(skb->len - nhoff - sizeof(*iph)); nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out; err = INDIRECT_CALL_L4(ops->callbacks.gro_complete, tcp6_gro_complete, udp6_gro_complete, skb, nhoff); out: return err; } static int sit_gro_complete(struct sk_buff *skb, int nhoff) { skb->encapsulation = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4; return ipv6_gro_complete(skb, nhoff); } static int ip6ip6_gro_complete(struct sk_buff *skb, int nhoff) { skb->encapsulation = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6; return ipv6_gro_complete(skb, nhoff); } static int ip4ip6_gro_complete(struct sk_buff *skb, int nhoff) { skb->encapsulation = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6; return inet_gro_complete(skb, nhoff); } static struct packet_offload ipv6_packet_offload __read_mostly = { .type = cpu_to_be16(ETH_P_IPV6), .callbacks = { .gso_segment = ipv6_gso_segment, .gro_receive = ipv6_gro_receive, .gro_complete = ipv6_gro_complete, }, }; static struct sk_buff *sit_gso_segment(struct sk_buff *skb, netdev_features_t features) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP4)) return ERR_PTR(-EINVAL); return ipv6_gso_segment(skb, features); } static struct sk_buff *ip4ip6_gso_segment(struct sk_buff *skb, netdev_features_t features) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP6)) return ERR_PTR(-EINVAL); return inet_gso_segment(skb, features); } static struct sk_buff *ip6ip6_gso_segment(struct sk_buff *skb, netdev_features_t features) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP6)) return ERR_PTR(-EINVAL); return ipv6_gso_segment(skb, features); } static const struct net_offload sit_offload = { .callbacks = { .gso_segment = sit_gso_segment, .gro_receive = sit_ip6ip6_gro_receive, .gro_complete = sit_gro_complete, }, }; static const struct net_offload ip4ip6_offload = { .callbacks = { .gso_segment = ip4ip6_gso_segment, .gro_receive = ip4ip6_gro_receive, .gro_complete = ip4ip6_gro_complete, }, }; static const struct net_offload ip6ip6_offload = { .callbacks = { .gso_segment = ip6ip6_gso_segment, .gro_receive = sit_ip6ip6_gro_receive, .gro_complete = ip6ip6_gro_complete, }, }; static int __init ipv6_offload_init(void) { if (tcpv6_offload_init() < 0) pr_crit("%s: Cannot add TCP protocol offload\n", __func__); if (ipv6_exthdrs_offload_init() < 0) pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__); dev_add_offload(&ipv6_packet_offload); inet_add_offload(&sit_offload, IPPROTO_IPV6); inet6_add_offload(&ip6ip6_offload, IPPROTO_IPV6); inet6_add_offload(&ip4ip6_offload, IPPROTO_IPIP); return 0; } fs_initcall(ipv6_offload_init); |
| 45 45 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 | // SPDX-License-Identifier: GPL-2.0 /* * Floating proportions with flexible aging period * * Copyright (C) 2011, SUSE, Jan Kara <jack@suse.cz> * * The goal of this code is: Given different types of event, measure proportion * of each type of event over time. The proportions are measured with * exponentially decaying history to give smooth transitions. A formula * expressing proportion of event of type 'j' is: * * p_{j} = (\Sum_{i>=0} x_{i,j}/2^{i+1})/(\Sum_{i>=0} x_i/2^{i+1}) * * Where x_{i,j} is j's number of events in i-th last time period and x_i is * total number of events in i-th last time period. * * Note that p_{j}'s are normalised, i.e. * * \Sum_{j} p_{j} = 1, * * This formula can be straightforwardly computed by maintaining denominator * (let's call it 'd') and for each event type its numerator (let's call it * 'n_j'). When an event of type 'j' happens, we simply need to do: * n_j++; d++; * * When a new period is declared, we could do: * d /= 2 * for each j * n_j /= 2 * * To avoid iteration over all event types, we instead shift numerator of event * j lazily when someone asks for a proportion of event j or when event j * occurs. This can bit trivially implemented by remembering last period in * which something happened with proportion of type j. */ #include <linux/flex_proportions.h> int fprop_global_init(struct fprop_global *p, gfp_t gfp) { int err; p->period = 0; /* Use 1 to avoid dealing with periods with 0 events... */ err = percpu_counter_init(&p->events, 1, gfp); if (err) return err; seqcount_init(&p->sequence); return 0; } void fprop_global_destroy(struct fprop_global *p) { percpu_counter_destroy(&p->events); } /* * Declare @periods new periods. It is upto the caller to make sure period * transitions cannot happen in parallel. * * The function returns true if the proportions are still defined and false * if aging zeroed out all events. This can be used to detect whether declaring * further periods has any effect. */ bool fprop_new_period(struct fprop_global *p, int periods) { s64 events; unsigned long flags; local_irq_save(flags); events = percpu_counter_sum(&p->events); /* * Don't do anything if there are no events. */ if (events <= 1) { local_irq_restore(flags); return false; } write_seqcount_begin(&p->sequence); if (periods < 64) events -= events >> periods; /* Use addition to avoid losing events happening between sum and set */ percpu_counter_add(&p->events, -events); p->period += periods; write_seqcount_end(&p->sequence); local_irq_restore(flags); return true; } /* * ---- SINGLE ---- */ int fprop_local_init_single(struct fprop_local_single *pl) { pl->events = 0; pl->period = 0; raw_spin_lock_init(&pl->lock); return 0; } void fprop_local_destroy_single(struct fprop_local_single *pl) { } static void fprop_reflect_period_single(struct fprop_global *p, struct fprop_local_single *pl) { unsigned int period = p->period; unsigned long flags; /* Fast path - period didn't change */ if (pl->period == period) return; raw_spin_lock_irqsave(&pl->lock, flags); /* Someone updated pl->period while we were spinning? */ if (pl->period >= period) { raw_spin_unlock_irqrestore(&pl->lock, flags); return; } /* Aging zeroed our fraction? */ if (period - pl->period < BITS_PER_LONG) pl->events >>= period - pl->period; else pl->events = 0; pl->period = period; raw_spin_unlock_irqrestore(&pl->lock, flags); } /* Event of type pl happened */ void __fprop_inc_single(struct fprop_global *p, struct fprop_local_single *pl) { fprop_reflect_period_single(p, pl); pl->events++; percpu_counter_add(&p->events, 1); } /* Return fraction of events of type pl */ void fprop_fraction_single(struct fprop_global *p, struct fprop_local_single *pl, unsigned long *numerator, unsigned long *denominator) { unsigned int seq; s64 num, den; do { seq = read_seqcount_begin(&p->sequence); fprop_reflect_period_single(p, pl); num = pl->events; den = percpu_counter_read_positive(&p->events); } while (read_seqcount_retry(&p->sequence, seq)); /* * Make fraction <= 1 and denominator > 0 even in presence of percpu * counter errors */ if (den <= num) { if (num) den = num; else den = 1; } *denominator = den; *numerator = num; } /* * ---- PERCPU ---- */ #define PROP_BATCH (8*(1+ilog2(nr_cpu_ids))) int fprop_local_init_percpu(struct fprop_local_percpu *pl, gfp_t gfp) { int err; err = percpu_counter_init(&pl->events, 0, gfp); if (err) return err; pl->period = 0; raw_spin_lock_init(&pl->lock); return 0; } void fprop_local_destroy_percpu(struct fprop_local_percpu *pl) { percpu_counter_destroy(&pl->events); } static void fprop_reflect_period_percpu(struct fprop_global *p, struct fprop_local_percpu *pl) { unsigned int period = p->period; unsigned long flags; /* Fast path - period didn't change */ if (pl->period == period) return; raw_spin_lock_irqsave(&pl->lock, flags); /* Someone updated pl->period while we were spinning? */ if (pl->period >= period) { raw_spin_unlock_irqrestore(&pl->lock, flags); return; } /* Aging zeroed our fraction? */ if (period - pl->period < BITS_PER_LONG) { s64 val = percpu_counter_read(&pl->events); if (val < (nr_cpu_ids * PROP_BATCH)) val = percpu_counter_sum(&pl->events); percpu_counter_add_batch(&pl->events, -val + (val >> (period-pl->period)), PROP_BATCH); } else percpu_counter_set(&pl->events, 0); pl->period = period; raw_spin_unlock_irqrestore(&pl->lock, flags); } /* Event of type pl happened */ void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl) { fprop_reflect_period_percpu(p, pl); percpu_counter_add_batch(&pl->events, 1, PROP_BATCH); percpu_counter_add(&p->events, 1); } void fprop_fraction_percpu(struct fprop_global *p, struct fprop_local_percpu *pl, unsigned long *numerator, unsigned long *denominator) { unsigned int seq; s64 num, den; do { seq = read_seqcount_begin(&p->sequence); fprop_reflect_period_percpu(p, pl); num = percpu_counter_read_positive(&pl->events); den = percpu_counter_read_positive(&p->events); } while (read_seqcount_retry(&p->sequence, seq)); /* * Make fraction <= 1 and denominator > 0 even in presence of percpu * counter errors */ if (den <= num) { if (num) den = num; else den = 1; } *denominator = den; *numerator = num; } /* * Like __fprop_inc_percpu() except that event is counted only if the given * type has fraction smaller than @max_frac/FPROP_FRAC_BASE */ void __fprop_inc_percpu_max(struct fprop_global *p, struct fprop_local_percpu *pl, int max_frac) { if (unlikely(max_frac < FPROP_FRAC_BASE)) { unsigned long numerator, denominator; fprop_fraction_percpu(p, pl, &numerator, &denominator); if (numerator > (((u64)denominator) * max_frac) >> FPROP_FRAC_SHIFT) return; } __fprop_inc_percpu(p, pl); } |
| 1143 1141 1143 1143 1140 1141 1142 1141 1143 1143 1143 1142 1143 1142 9 1142 1 1 16 15 1140 1142 1143 1142 1143 1145 1146 1145 1146 1146 1143 17 1146 1146 1143 1145 1146 1145 1146 1142 13 1140 5 14 14 4 14 1142 1145 1144 1142 30 1120 1142 1146 1141 1146 1142 1143 1142 1141 1142 1143 1142 1142 1143 1142 1141 1142 1143 1143 1140 1143 1143 1142 1139 1143 1141 1143 1146 123 1144 1143 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/printk.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Modified to make sys_syslog() more flexible: added commands to * return the last 4k of kernel messages, regardless of whether * they've been read or not. Added option to suppress kernel printk's * to the console. Added hook for sending the console messages * elsewhere, in preparation for a serial line console (someday). * Ted Ts'o, 2/11/93. * Modified for sysctl support, 1/8/97, Chris Horn. * Fixed SMP synchronization, 08/08/99, Manfred Spraul * manfred@colorfullife.com * Rewrote bits to get rid of console_lock * 01Mar01 Andrew Morton */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/mm.h> #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/console.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/nmi.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/delay.h> #include <linux/smp.h> #include <linux/security.h> #include <linux/memblock.h> #include <linux/syscalls.h> #include <linux/crash_core.h> #include <linux/ratelimit.h> #include <linux/kmsg_dump.h> #include <linux/syslog.h> #include <linux/cpu.h> #include <linux/rculist.h> #include <linux/poll.h> #include <linux/irq_work.h> #include <linux/ctype.h> #include <linux/uio.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/uaccess.h> #include <asm/sections.h> #include <trace/events/initcall.h> #define CREATE_TRACE_POINTS #include <trace/events/printk.h> #undef CREATE_TRACE_POINTS #include <trace/hooks/printk.h> #include <trace/hooks/logbuf.h> #include "printk_ringbuffer.h" #include "console_cmdline.h" #include "braille.h" #include "internal.h" int console_printk[4] = { CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */ MESSAGE_LOGLEVEL_DEFAULT, /* default_message_loglevel */ CONSOLE_LOGLEVEL_MIN, /* minimum_console_loglevel */ CONSOLE_LOGLEVEL_DEFAULT, /* default_console_loglevel */ }; EXPORT_SYMBOL_GPL(console_printk); atomic_t ignore_console_lock_warning __read_mostly = ATOMIC_INIT(0); EXPORT_SYMBOL(ignore_console_lock_warning); /* * Low level drivers may need that to know if they can schedule in * their unblank() callback or not. So let's export it. */ int oops_in_progress; EXPORT_SYMBOL(oops_in_progress); /* * console_sem protects the console_drivers list, and also * provides serialisation for access to the entire console * driver system. */ static DEFINE_SEMAPHORE(console_sem); struct console *console_drivers; EXPORT_SYMBOL_GPL(console_drivers); /* * System may need to suppress printk message under certain * circumstances, like after kernel panic happens. */ int __read_mostly suppress_printk; #ifdef CONFIG_LOCKDEP static struct lockdep_map console_lock_dep_map = { .name = "console_lock" }; #endif enum devkmsg_log_bits { __DEVKMSG_LOG_BIT_ON = 0, __DEVKMSG_LOG_BIT_OFF, __DEVKMSG_LOG_BIT_LOCK, }; enum devkmsg_log_masks { DEVKMSG_LOG_MASK_ON = BIT(__DEVKMSG_LOG_BIT_ON), DEVKMSG_LOG_MASK_OFF = BIT(__DEVKMSG_LOG_BIT_OFF), DEVKMSG_LOG_MASK_LOCK = BIT(__DEVKMSG_LOG_BIT_LOCK), }; /* Keep both the 'on' and 'off' bits clear, i.e. ratelimit by default: */ #define DEVKMSG_LOG_MASK_DEFAULT 0 static unsigned int __read_mostly devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; static int __control_devkmsg(char *str) { size_t len; if (!str) return -EINVAL; len = str_has_prefix(str, "on"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_ON; return len; } len = str_has_prefix(str, "off"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_OFF; return len; } len = str_has_prefix(str, "ratelimit"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; return len; } return -EINVAL; } static int __init control_devkmsg(char *str) { if (__control_devkmsg(str) < 0) { pr_warn("printk.devkmsg: bad option string '%s'\n", str); return 1; } /* * Set sysctl string accordingly: */ if (devkmsg_log == DEVKMSG_LOG_MASK_ON) strcpy(devkmsg_log_str, "on"); else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF) strcpy(devkmsg_log_str, "off"); /* else "ratelimit" which is set by default. */ /* * Sysctl cannot change it anymore. The kernel command line setting of * this parameter is to force the setting to be permanent throughout the * runtime of the system. This is a precation measure against userspace * trying to be a smarta** and attempting to change it up on us. */ devkmsg_log |= DEVKMSG_LOG_MASK_LOCK; return 1; } __setup("printk.devkmsg=", control_devkmsg); char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit"; int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char old_str[DEVKMSG_STR_MAX_SIZE]; unsigned int old; int err; if (write) { if (devkmsg_log & DEVKMSG_LOG_MASK_LOCK) return -EINVAL; old = devkmsg_log; strncpy(old_str, devkmsg_log_str, DEVKMSG_STR_MAX_SIZE); } err = proc_dostring(table, write, buffer, lenp, ppos); if (err) return err; if (write) { err = __control_devkmsg(devkmsg_log_str); /* * Do not accept an unknown string OR a known string with * trailing crap... */ if (err < 0 || (err + 1 != *lenp)) { /* ... and restore old setting. */ devkmsg_log = old; strncpy(devkmsg_log_str, old_str, DEVKMSG_STR_MAX_SIZE); return -EINVAL; } } return 0; } /* Number of registered extended console drivers. */ static int nr_ext_console_drivers; /* * Helper macros to handle lockdep when locking/unlocking console_sem. We use * macros instead of functions so that _RET_IP_ contains useful information. */ #define down_console_sem() do { \ down(&console_sem);\ mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);\ } while (0) static int __down_trylock_console_sem(unsigned long ip) { int lock_failed; unsigned long flags; /* * Here and in __up_console_sem() we need to be in safe mode, * because spindump/WARN/etc from under console ->lock will * deadlock in printk()->down_trylock_console_sem() otherwise. */ printk_safe_enter_irqsave(flags); lock_failed = down_trylock(&console_sem); printk_safe_exit_irqrestore(flags); if (lock_failed) return 1; mutex_acquire(&console_lock_dep_map, 0, 1, ip); return 0; } #define down_trylock_console_sem() __down_trylock_console_sem(_RET_IP_) static void __up_console_sem(unsigned long ip) { unsigned long flags; mutex_release(&console_lock_dep_map, ip); printk_safe_enter_irqsave(flags); up(&console_sem); printk_safe_exit_irqrestore(flags); } #define up_console_sem() __up_console_sem(_RET_IP_) /* * This is used for debugging the mess that is the VT code by * keeping track if we have the console semaphore held. It's * definitely not the perfect debug tool (we don't know if _WE_ * hold it and are racing, but it helps tracking those weird code * paths in the console code where we end up in places I want * locked without the console semaphore held). */ static int console_locked, console_suspended; /* * If exclusive_console is non-NULL then only this console is to be printed to. */ static struct console *exclusive_console; /* * Array of consoles built from command line options (console=) */ #define MAX_CMDLINECONSOLES 8 static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; static int preferred_console = -1; static bool has_preferred_console; int console_set_on_cmdline; EXPORT_SYMBOL(console_set_on_cmdline); /* Flag: console code may call schedule() */ static int console_may_schedule; enum con_msg_format_flags { MSG_FORMAT_DEFAULT = 0, MSG_FORMAT_SYSLOG = (1 << 0), }; static int console_msg_format = MSG_FORMAT_DEFAULT; /* * The printk log buffer consists of a sequenced collection of records, each * containing variable length message text. Every record also contains its * own meta-data (@info). * * Every record meta-data carries the timestamp in microseconds, as well as * the standard userspace syslog level and syslog facility. The usual kernel * messages use LOG_KERN; userspace-injected messages always carry a matching * syslog facility, by default LOG_USER. The origin of every message can be * reliably determined that way. * * The human readable log message of a record is available in @text, the * length of the message text in @text_len. The stored message is not * terminated. * * Optionally, a record can carry a dictionary of properties (key/value * pairs), to provide userspace with a machine-readable message context. * * Examples for well-defined, commonly used property names are: * DEVICE=b12:8 device identifier * b12:8 block dev_t * c127:3 char dev_t * n8 netdev ifindex * +sound:card0 subsystem:devname * SUBSYSTEM=pci driver-core subsystem name * * Valid characters in property names are [a-zA-Z0-9.-_]. Property names * and values are terminated by a '\0' character. * * Example of record values: * record.text_buf = "it's a line" (unterminated) * record.info.seq = 56 * record.info.ts_nsec = 36863 * record.info.text_len = 11 * record.info.facility = 0 (LOG_KERN) * record.info.flags = 0 * record.info.level = 3 (LOG_ERR) * record.info.caller_id = 299 (task 299) * record.info.dev_info.subsystem = "pci" (terminated) * record.info.dev_info.device = "+pci:0000:00:01.0" (terminated) * * The 'struct printk_info' buffer must never be directly exported to * userspace, it is a kernel-private implementation detail that might * need to be changed in the future, when the requirements change. * * /dev/kmsg exports the structured data in the following line format: * "<level>,<sequnum>,<timestamp>,<contflag>[,additional_values, ... ];<message text>\n" * * Users of the export format should ignore possible additional values * separated by ',', and find the message after the ';' character. * * The optional key/value pairs are attached as continuation lines starting * with a space character and terminated by a newline. All possible * non-prinatable characters are escaped in the "\xff" notation. */ /* syslog_lock protects syslog_* variables and write access to clear_seq. */ static DEFINE_MUTEX(syslog_lock); #ifdef CONFIG_PRINTK DECLARE_WAIT_QUEUE_HEAD(log_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ static u64 syslog_seq; static size_t syslog_partial; static bool syslog_time; /* All 3 protected by @console_sem. */ /* the next printk record to write to the console */ static u64 console_seq; static u64 exclusive_console_stop_seq; static unsigned long console_dropped; struct latched_seq { seqcount_latch_t latch; u64 val[2]; }; /* * The next printk record to read after the last 'clear' command. There are * two copies (updated with seqcount_latch) so that reads can locklessly * access a valid value. Writers are synchronized by @syslog_lock. */ static struct latched_seq clear_seq = { .latch = SEQCNT_LATCH_ZERO(clear_seq.latch), .val[0] = 0, .val[1] = 0, }; #ifdef CONFIG_PRINTK_CALLER #define PREFIX_MAX 48 #else #define PREFIX_MAX 32 #endif /* the maximum size of a formatted record (i.e. with prefix added per line) */ #define CONSOLE_LOG_MAX 1024 /* the maximum size allowed to be reserved for a record */ #define LOG_LINE_MAX (CONSOLE_LOG_MAX - PREFIX_MAX) #define LOG_LEVEL(v) ((v) & 0x07) #define LOG_FACILITY(v) ((v) >> 3 & 0xff) /* record buffer */ #define LOG_ALIGN __alignof__(unsigned long) #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) #define LOG_BUF_LEN_MAX ((u32)1 << 31) static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); static char *log_buf = __log_buf; static u32 log_buf_len = __LOG_BUF_LEN; /* * Define the average message size. This only affects the number of * descriptors that will be available. Underestimating is better than * overestimating (too many available descriptors is better than not enough). */ #define PRB_AVGBITS 5 /* 32 character average length */ #if CONFIG_LOG_BUF_SHIFT <= PRB_AVGBITS #error CONFIG_LOG_BUF_SHIFT value too small. #endif _DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS, PRB_AVGBITS, &__log_buf[0]); static struct printk_ringbuffer printk_rb_dynamic; static struct printk_ringbuffer *prb = &printk_rb_static; /* * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before * per_cpu_areas are initialised. This variable is set to true when * it's safe to access per-CPU data. */ static bool __printk_percpu_data_ready __read_mostly; bool printk_percpu_data_ready(void) { return __printk_percpu_data_ready; } /* Must be called under syslog_lock. */ static void latched_seq_write(struct latched_seq *ls, u64 val) { raw_write_seqcount_latch(&ls->latch); ls->val[0] = val; raw_write_seqcount_latch(&ls->latch); ls->val[1] = val; } /* Can be called from any context. */ static u64 latched_seq_read_nolock(struct latched_seq *ls) { unsigned int seq; unsigned int idx; u64 val; do { seq = raw_read_seqcount_latch(&ls->latch); idx = seq & 0x1; val = ls->val[idx]; } while (raw_read_seqcount_latch_retry(&ls->latch, seq)); return val; } /* Return log buffer address */ char *log_buf_addr_get(void) { return log_buf; } EXPORT_SYMBOL_GPL(log_buf_addr_get); /* Return log buffer size */ u32 log_buf_len_get(void) { return log_buf_len; } EXPORT_SYMBOL_GPL(log_buf_len_get); /* * Define how much of the log buffer we could take at maximum. The value * must be greater than two. Note that only half of the buffer is available * when the index points to the middle. */ #define MAX_LOG_TAKE_PART 4 static const char trunc_msg[] = "<truncated>"; static void truncate_msg(u16 *text_len, u16 *trunc_msg_len) { /* * The message should not take the whole buffer. Otherwise, it might * get removed too soon. */ u32 max_text_len = log_buf_len / MAX_LOG_TAKE_PART; if (*text_len > max_text_len) *text_len = max_text_len; /* enable the warning message (if there is room) */ *trunc_msg_len = strlen(trunc_msg); if (*text_len >= *trunc_msg_len) *text_len -= *trunc_msg_len; else *trunc_msg_len = 0; } int dmesg_restrict = IS_ENABLED(CONFIG_SECURITY_DMESG_RESTRICT); static int syslog_action_restricted(int type) { if (dmesg_restrict) return 1; /* * Unless restricted, we allow "read all" and "get buffer size" * for everybody. */ return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER; } static int check_syslog_permissions(int type, int source) { /* * If this is from /proc/kmsg and we've already opened it, then we've * already done the capabilities checks at open time. */ if (source == SYSLOG_FROM_PROC && type != SYSLOG_ACTION_OPEN) goto ok; if (syslog_action_restricted(type)) { if (capable(CAP_SYSLOG)) goto ok; /* * For historical reasons, accept CAP_SYS_ADMIN too, with * a warning. */ if (capable(CAP_SYS_ADMIN)) { pr_warn_once("%s (%d): Attempt to access syslog with " "CAP_SYS_ADMIN but no CAP_SYSLOG " "(deprecated).\n", current->comm, task_pid_nr(current)); goto ok; } return -EPERM; } ok: return security_syslog(type); } static void append_char(char **pp, char *e, char c) { if (*pp < e) *(*pp)++ = c; } static ssize_t info_print_ext_header(char *buf, size_t size, struct printk_info *info) { u64 ts_usec = info->ts_nsec; char caller[20]; #ifdef CONFIG_PRINTK_CALLER int vh_ret = 0; u32 id = info->caller_id; trace_android_vh_printk_ext_header(caller, sizeof(caller), id, &vh_ret); if (!vh_ret) snprintf(caller, sizeof(caller), ",caller=%c%u", id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); #else caller[0] = '\0'; #endif do_div(ts_usec, 1000); return scnprintf(buf, size, "%u,%llu,%llu,%c%s;", (info->facility << 3) | info->level, info->seq, ts_usec, info->flags & LOG_CONT ? 'c' : '-', caller); } static ssize_t msg_add_ext_text(char *buf, size_t size, const char *text, size_t text_len, unsigned char endc) { char *p = buf, *e = buf + size; size_t i; /* escape non-printable characters */ for (i = 0; i < text_len; i++) { unsigned char c = text[i]; if (c < ' ' || c >= 127 || c == '\\') p += scnprintf(p, e - p, "\\x%02x", c); else append_char(&p, e, c); } append_char(&p, e, endc); return p - buf; } static ssize_t msg_add_dict_text(char *buf, size_t size, const char *key, const char *val) { size_t val_len = strlen(val); ssize_t len; if (!val_len) return 0; len = msg_add_ext_text(buf, size, "", 0, ' '); /* dict prefix */ len += msg_add_ext_text(buf + len, size - len, key, strlen(key), '='); len += msg_add_ext_text(buf + len, size - len, val, val_len, '\n'); return len; } static ssize_t msg_print_ext_body(char *buf, size_t size, char *text, size_t text_len, struct dev_printk_info *dev_info) { ssize_t len; len = msg_add_ext_text(buf, size, text, text_len, '\n'); if (!dev_info) goto out; len += msg_add_dict_text(buf + len, size - len, "SUBSYSTEM", dev_info->subsystem); len += msg_add_dict_text(buf + len, size - len, "DEVICE", dev_info->device); out: return len; } /* /dev/kmsg - userspace message inject/listen interface */ struct devkmsg_user { atomic64_t seq; struct ratelimit_state rs; struct mutex lock; char buf[CONSOLE_EXT_LOG_MAX]; struct printk_info info; char text_buf[CONSOLE_EXT_LOG_MAX]; struct printk_record record; }; static __printf(3, 4) __cold int devkmsg_emit(int facility, int level, const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_emit(facility, level, NULL, fmt, args); va_end(args); return r; } static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) { char *buf, *line; int level = default_message_loglevel; int facility = 1; /* LOG_USER */ struct file *file = iocb->ki_filp; struct devkmsg_user *user = file->private_data; size_t len = iov_iter_count(from); ssize_t ret = len; if (!user || len > LOG_LINE_MAX) return -EINVAL; /* Ignore when user logging is disabled. */ if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) return len; /* Ratelimit when not explicitly enabled. */ if (!(devkmsg_log & DEVKMSG_LOG_MASK_ON)) { if (!___ratelimit(&user->rs, current->comm)) return ret; } buf = kmalloc(len+1, GFP_KERNEL); if (buf == NULL) return -ENOMEM; buf[len] = '\0'; if (!copy_from_iter_full(buf, len, from)) { kfree(buf); return -EFAULT; } /* * Extract and skip the syslog prefix <[0-9]*>. Coming from userspace * the decimal value represents 32bit, the lower 3 bit are the log * level, the rest are the log facility. * * If no prefix or no userspace facility is specified, we * enforce LOG_USER, to be able to reliably distinguish * kernel-generated messages from userspace-injected ones. */ line = buf; if (line[0] == '<') { char *endp = NULL; unsigned int u; u = simple_strtoul(line + 1, &endp, 10); if (endp && endp[0] == '>') { level = LOG_LEVEL(u); if (LOG_FACILITY(u) != 0) facility = LOG_FACILITY(u); endp++; line = endp; } } devkmsg_emit(facility, level, "%s", line); kfree(buf); return ret; } static ssize_t devkmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct devkmsg_user *user = file->private_data; struct printk_record *r = &user->record; size_t len; ssize_t ret; if (!user) return -EBADF; ret = mutex_lock_interruptible(&user->lock); if (ret) return ret; if (!prb_read_valid(prb, atomic64_read(&user->seq), r)) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; goto out; } /* * Guarantee this task is visible on the waitqueue before * checking the wake condition. * * The full memory barrier within set_current_state() of * prepare_to_wait_event() pairs with the full memory barrier * within wq_has_sleeper(). * * This pairs with __wake_up_klogd:A. */ ret = wait_event_interruptible(log_wait, prb_read_valid(prb, atomic64_read(&user->seq), r)); /* LMM(devkmsg_read:A) */ if (ret) goto out; } if (r->info->seq != atomic64_read(&user->seq)) { /* our last seen message is gone, return error and reset */ atomic64_set(&user->seq, r->info->seq); ret = -EPIPE; goto out; } len = info_print_ext_header(user->buf, sizeof(user->buf), r->info); len += msg_print_ext_body(user->buf + len, sizeof(user->buf) - len, &r->text_buf[0], r->info->text_len, &r->info->dev_info); atomic64_set(&user->seq, r->info->seq + 1); if (len > count) { ret = -EINVAL; goto out; } if (copy_to_user(buf, user->buf, len)) { ret = -EFAULT; goto out; } ret = len; out: mutex_unlock(&user->lock); return ret; } /* * Be careful when modifying this function!!! * * Only few operations are supported because the device works only with the * entire variable length messages (records). Non-standard values are * returned in the other cases and has been this way for quite some time. * User space applications might depend on this behavior. */ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) { struct devkmsg_user *user = file->private_data; loff_t ret = 0; if (!user) return -EBADF; if (offset) return -ESPIPE; switch (whence) { case SEEK_SET: /* the first record */ atomic64_set(&user->seq, prb_first_valid_seq(prb)); break; case SEEK_DATA: /* * The first record after the last SYSLOG_ACTION_CLEAR, * like issued by 'dmesg -c'. Reading /dev/kmsg itself * changes no global state, and does not clear anything. */ atomic64_set(&user->seq, latched_seq_read_nolock(&clear_seq)); break; case SEEK_END: /* after the last record */ atomic64_set(&user->seq, prb_next_seq(prb)); break; default: ret = -EINVAL; } return ret; } static __poll_t devkmsg_poll(struct file *file, poll_table *wait) { struct devkmsg_user *user = file->private_data; struct printk_info info; __poll_t ret = 0; if (!user) return EPOLLERR|EPOLLNVAL; poll_wait(file, &log_wait, wait); if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) { /* return error when data has vanished underneath us */ if (info.seq != atomic64_read(&user->seq)) ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI; else ret = EPOLLIN|EPOLLRDNORM; } return ret; } static int devkmsg_open(struct inode *inode, struct file *file) { struct devkmsg_user *user; int err; if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) return -EPERM; /* write-only does not need any file context */ if ((file->f_flags & O_ACCMODE) != O_WRONLY) { err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, SYSLOG_FROM_READER); if (err) return err; } user = kmalloc(sizeof(struct devkmsg_user), GFP_KERNEL); if (!user) return -ENOMEM; ratelimit_default_init(&user->rs); ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE); mutex_init(&user->lock); prb_rec_init_rd(&user->record, &user->info, &user->text_buf[0], sizeof(user->text_buf)); atomic64_set(&user->seq, prb_first_valid_seq(prb)); file->private_data = user; return 0; } static int devkmsg_release(struct inode *inode, struct file *file) { struct devkmsg_user *user = file->private_data; if (!user) return 0; ratelimit_state_exit(&user->rs); mutex_destroy(&user->lock); kfree(user); return 0; } const struct file_operations kmsg_fops = { .open = devkmsg_open, .read = devkmsg_read, .write_iter = devkmsg_write, .llseek = devkmsg_llseek, .poll = devkmsg_poll, .release = devkmsg_release, }; #ifdef CONFIG_CRASH_CORE /* * This appends the listed symbols to /proc/vmcore * * /proc/vmcore is used by various utilities, like crash and makedumpfile to * obtain access to symbols that are otherwise very difficult to locate. These * symbols are specifically used so that utilities can access and extract the * dmesg log from a vmcore file after a crash. */ void log_buf_vmcoreinfo_setup(void) { struct dev_printk_info *dev_info = NULL; VMCOREINFO_SYMBOL(prb); VMCOREINFO_SYMBOL(printk_rb_static); VMCOREINFO_SYMBOL(clear_seq); /* * Export struct size and field offsets. User space tools can * parse it and detect any changes to structure down the line. */ VMCOREINFO_STRUCT_SIZE(printk_ringbuffer); VMCOREINFO_OFFSET(printk_ringbuffer, desc_ring); VMCOREINFO_OFFSET(printk_ringbuffer, text_data_ring); VMCOREINFO_OFFSET(printk_ringbuffer, fail); VMCOREINFO_STRUCT_SIZE(prb_desc_ring); VMCOREINFO_OFFSET(prb_desc_ring, count_bits); VMCOREINFO_OFFSET(prb_desc_ring, descs); VMCOREINFO_OFFSET(prb_desc_ring, infos); VMCOREINFO_OFFSET(prb_desc_ring, head_id); VMCOREINFO_OFFSET(prb_desc_ring, tail_id); VMCOREINFO_STRUCT_SIZE(prb_desc); VMCOREINFO_OFFSET(prb_desc, state_var); VMCOREINFO_OFFSET(prb_desc, text_blk_lpos); VMCOREINFO_STRUCT_SIZE(prb_data_blk_lpos); VMCOREINFO_OFFSET(prb_data_blk_lpos, begin); VMCOREINFO_OFFSET(prb_data_blk_lpos, next); VMCOREINFO_STRUCT_SIZE(printk_info); VMCOREINFO_OFFSET(printk_info, seq); VMCOREINFO_OFFSET(printk_info, ts_nsec); VMCOREINFO_OFFSET(printk_info, text_len); VMCOREINFO_OFFSET(printk_info, caller_id); VMCOREINFO_OFFSET(printk_info, dev_info); VMCOREINFO_STRUCT_SIZE(dev_printk_info); VMCOREINFO_OFFSET(dev_printk_info, subsystem); VMCOREINFO_LENGTH(printk_info_subsystem, sizeof(dev_info->subsystem)); VMCOREINFO_OFFSET(dev_printk_info, device); VMCOREINFO_LENGTH(printk_info_device, sizeof(dev_info->device)); VMCOREINFO_STRUCT_SIZE(prb_data_ring); VMCOREINFO_OFFSET(prb_data_ring, size_bits); VMCOREINFO_OFFSET(prb_data_ring, data); VMCOREINFO_OFFSET(prb_data_ring, head_lpos); VMCOREINFO_OFFSET(prb_data_ring, tail_lpos); VMCOREINFO_SIZE(atomic_long_t); VMCOREINFO_TYPE_OFFSET(atomic_long_t, counter); VMCOREINFO_STRUCT_SIZE(latched_seq); VMCOREINFO_OFFSET(latched_seq, val); } #endif /* requested log_buf_len from kernel cmdline */ static unsigned long __initdata new_log_buf_len; /* we practice scaling the ring buffer by powers of 2 */ static void __init log_buf_len_update(u64 size) { if (size > (u64)LOG_BUF_LEN_MAX) { size = (u64)LOG_BUF_LEN_MAX; pr_err("log_buf over 2G is not supported.\n"); } if (size) size = roundup_pow_of_two(size); if (size > log_buf_len) new_log_buf_len = (unsigned long)size; } /* save requested log_buf_len since it's too early to process it */ static int __init log_buf_len_setup(char *str) { u64 size; if (!str) return -EINVAL; size = memparse(str, &str); log_buf_len_update(size); return 0; } early_param("log_buf_len", log_buf_len_setup); #ifdef CONFIG_SMP #define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT) static void __init log_buf_add_cpu(void) { unsigned int cpu_extra; /* * archs should set up cpu_possible_bits properly with * set_cpu_possible() after setup_arch() but just in * case lets ensure this is valid. */ if (num_possible_cpus() == 1) return; cpu_extra = (num_possible_cpus() - 1) * __LOG_CPU_MAX_BUF_LEN; /* by default this will only continue through for large > 64 CPUs */ if (cpu_extra <= __LOG_BUF_LEN / 2) return; pr_info("log_buf_len individual max cpu contribution: %d bytes\n", __LOG_CPU_MAX_BUF_LEN); pr_info("log_buf_len total cpu_extra contributions: %d bytes\n", cpu_extra); pr_info("log_buf_len min size: %d bytes\n", __LOG_BUF_LEN); log_buf_len_update(cpu_extra + __LOG_BUF_LEN); } #else /* !CONFIG_SMP */ static inline void log_buf_add_cpu(void) {} #endif /* CONFIG_SMP */ static void __init set_percpu_data_ready(void) { __printk_percpu_data_ready = true; } static unsigned int __init add_to_rb(struct printk_ringbuffer *rb, struct printk_record *r) { struct prb_reserved_entry e; struct printk_record dest_r; prb_rec_init_wr(&dest_r, r->info->text_len); if (!prb_reserve(&e, rb, &dest_r)) return 0; memcpy(&dest_r.text_buf[0], &r->text_buf[0], r->info->text_len); dest_r.info->text_len = r->info->text_len; dest_r.info->facility = r->info->facility; dest_r.info->level = r->info->level; dest_r.info->flags = r->info->flags; dest_r.info->ts_nsec = r->info->ts_nsec; dest_r.info->caller_id = r->info->caller_id; memcpy(&dest_r.info->dev_info, &r->info->dev_info, sizeof(dest_r.info->dev_info)); prb_final_commit(&e); return prb_record_text_space(&e); } static char setup_text_buf[LOG_LINE_MAX] __initdata; void __init setup_log_buf(int early) { struct printk_info *new_infos; unsigned int new_descs_count; struct prb_desc *new_descs; struct printk_info info; struct printk_record r; unsigned int text_size; size_t new_descs_size; size_t new_infos_size; unsigned long flags; char *new_log_buf; unsigned int free; u64 seq; /* * Some archs call setup_log_buf() multiple times - first is very * early, e.g. from setup_arch(), and second - when percpu_areas * are initialised. */ if (!early) set_percpu_data_ready(); if (log_buf != __log_buf) return; if (!early && !new_log_buf_len) log_buf_add_cpu(); if (!new_log_buf_len) return; new_descs_count = new_log_buf_len >> PRB_AVGBITS; if (new_descs_count == 0) { pr_err("new_log_buf_len: %lu too small\n", new_log_buf_len); return; } new_log_buf = memblock_alloc(new_log_buf_len, LOG_ALIGN); if (unlikely(!new_log_buf)) { pr_err("log_buf_len: %lu text bytes not available\n", new_log_buf_len); return; } new_descs_size = new_descs_count * sizeof(struct prb_desc); new_descs = memblock_alloc(new_descs_size, LOG_ALIGN); if (unlikely(!new_descs)) { pr_err("log_buf_len: %zu desc bytes not available\n", new_descs_size); goto err_free_log_buf; } new_infos_size = new_descs_count * sizeof(struct printk_info); new_infos = memblock_alloc(new_infos_size, LOG_ALIGN); if (unlikely(!new_infos)) { pr_err("log_buf_len: %zu info bytes not available\n", new_infos_size); goto err_free_descs; } prb_rec_init_rd(&r, &info, &setup_text_buf[0], sizeof(setup_text_buf)); prb_init(&printk_rb_dynamic, new_log_buf, ilog2(new_log_buf_len), new_descs, ilog2(new_descs_count), new_infos); local_irq_save(flags); log_buf_len = new_log_buf_len; log_buf = new_log_buf; new_log_buf_len = 0; free = __LOG_BUF_LEN; prb_for_each_record(0, &printk_rb_static, seq, &r) { text_size = add_to_rb(&printk_rb_dynamic, &r); if (text_size > free) free = 0; else free -= text_size; } prb = &printk_rb_dynamic; local_irq_restore(flags); /* * Copy any remaining messages that might have appeared from * NMI context after copying but before switching to the * dynamic buffer. */ prb_for_each_record(seq, &printk_rb_static, seq, &r) { text_size = add_to_rb(&printk_rb_dynamic, &r); if (text_size > free) free = 0; else free -= text_size; } if (seq != prb_next_seq(&printk_rb_static)) { pr_err("dropped %llu messages\n", prb_next_seq(&printk_rb_static) - seq); } pr_info("log_buf_len: %u bytes\n", log_buf_len); pr_info("early log buf free: %u(%u%%)\n", free, (free * 100) / __LOG_BUF_LEN); return; err_free_descs: memblock_free_ptr(new_descs, new_descs_size); err_free_log_buf: memblock_free_ptr(new_log_buf, new_log_buf_len); } static bool __read_mostly ignore_loglevel; static int __init ignore_loglevel_setup(char *str) { ignore_loglevel = true; pr_info("debug: ignoring loglevel setting.\n"); return 0; } early_param("ignore_loglevel", ignore_loglevel_setup); module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting (prints all kernel messages to the console)"); static bool suppress_message_printing(int level) { return (level >= console_loglevel && !ignore_loglevel); } #ifdef CONFIG_BOOT_PRINTK_DELAY static int boot_delay; /* msecs delay after each printk during bootup */ static unsigned long long loops_per_msec; /* based on boot_delay */ static int __init boot_delay_setup(char *str) { unsigned long lpj; lpj = preset_lpj ? preset_lpj : 1000000; /* some guess */ loops_per_msec = (unsigned long long)lpj / 1000 * HZ; get_option(&str, &boot_delay); if (boot_delay > 10 * 1000) boot_delay = 0; pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, " "HZ: %d, loops_per_msec: %llu\n", boot_delay, preset_lpj, lpj, HZ, loops_per_msec); return 0; } early_param("boot_delay", boot_delay_setup); static void boot_delay_msec(int level) { unsigned long long k; unsigned long timeout; if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING) || suppress_message_printing(level)) { return; } k = (unsigned long long)loops_per_msec * boot_delay; timeout = jiffies + msecs_to_jiffies(boot_delay); while (k) { k--; cpu_relax(); /* * use (volatile) jiffies to prevent * compiler reduction; loop termination via jiffies * is secondary and may or may not happen. */ if (time_after(jiffies, timeout)) break; touch_nmi_watchdog(); } } #else static inline void boot_delay_msec(int level) { } #endif static bool printk_time = IS_ENABLED(CONFIG_PRINTK_TIME); module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR); static size_t print_syslog(unsigned int level, char *buf) { return sprintf(buf, "<%u>", level); } static size_t print_time(u64 ts, char *buf) { unsigned long rem_nsec = do_div(ts, 1000000000); return sprintf(buf, "[%5lu.%06lu]", (unsigned long)ts, rem_nsec / 1000); } #ifdef CONFIG_PRINTK_CALLER static size_t print_caller(u32 id, char *buf) { char caller[12]; int vh_ret = 0; trace_android_vh_printk_caller(caller, sizeof(caller), id, &vh_ret); if (!vh_ret) snprintf(caller, sizeof(caller), "%c%u", id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); return sprintf(buf, "[%6s]", caller); } #else #define print_caller(id, buf) 0 #endif static size_t info_print_prefix(const struct printk_info *info, bool syslog, bool time, char *buf) { size_t len = 0; if (syslog) len = print_syslog((info->facility << 3) | info->level, buf); if (time) len += print_time(info->ts_nsec, buf + len); len += print_caller(info->caller_id, buf + len); if (IS_ENABLED(CONFIG_PRINTK_CALLER) || time) { buf[len++] = ' '; buf[len] = '\0'; } return len; } /* * Prepare the record for printing. The text is shifted within the given * buffer to avoid a need for another one. The following operations are * done: * * - Add prefix for each line. * - Drop truncated lines that no longer fit into the buffer. * - Add the trailing newline that has been removed in vprintk_store(). * - Add a string terminator. * * Since the produced string is always terminated, the maximum possible * return value is @r->text_buf_size - 1; * * Return: The length of the updated/prepared text, including the added * prefixes and the newline. The terminator is not counted. The dropped * line(s) are not counted. */ static size_t record_print_text(struct printk_record *r, bool syslog, bool time) { size_t text_len = r->info->text_len; size_t buf_size = r->text_buf_size; char *text = r->text_buf; char prefix[PREFIX_MAX]; bool truncated = false; size_t prefix_len; size_t line_len; size_t len = 0; char *next; /* * If the message was truncated because the buffer was not large * enough, treat the available text as if it were the full text. */ if (text_len > buf_size) text_len = buf_size; prefix_len = info_print_prefix(r->info, syslog, time, prefix); /* * @text_len: bytes of unprocessed text * @line_len: bytes of current line _without_ newline * @text: pointer to beginning of current line * @len: number of bytes prepared in r->text_buf */ for (;;) { next = memchr(text, '\n', text_len); if (next) { line_len = next - text; } else { /* Drop truncated line(s). */ if (truncated) break; line_len = text_len; } /* * Truncate the text if there is not enough space to add the * prefix and a trailing newline and a terminator. */ if (len + prefix_len + text_len + 1 + 1 > buf_size) { /* Drop even the current line if no space. */ if (len + prefix_len + line_len + 1 + 1 > buf_size) break; text_len = buf_size - len - prefix_len - 1 - 1; truncated = true; } memmove(text + prefix_len, text, text_len); memcpy(text, prefix, prefix_len); /* * Increment the prepared length to include the text and * prefix that were just moved+copied. Also increment for the * newline at the end of this line. If this is the last line, * there is no newline, but it will be added immediately below. */ len += prefix_len + line_len + 1; if (text_len == line_len) { /* * This is the last line. Add the trailing newline * removed in vprintk_store(). */ text[prefix_len + line_len] = '\n'; break; } /* * Advance beyond the added prefix and the related line with * its newline. */ text += prefix_len + line_len + 1; /* * The remaining text has only decreased by the line with its * newline. * * Note that @text_len can become zero. It happens when @text * ended with a newline (either due to truncation or the * original string ending with "\n\n"). The loop is correctly * repeated and (if not truncated) an empty line with a prefix * will be prepared. */ text_len -= line_len + 1; } /* * If a buffer was provided, it will be terminated. Space for the * string terminator is guaranteed to be available. The terminator is * not counted in the return value. */ if (buf_size > 0) r->text_buf[len] = 0; return len; } static size_t get_record_print_text_size(struct printk_info *info, unsigned int line_count, bool syslog, bool time) { char prefix[PREFIX_MAX]; size_t prefix_len; prefix_len = info_print_prefix(info, syslog, time, prefix); /* * Each line will be preceded with a prefix. The intermediate * newlines are already within the text, but a final trailing * newline will be added. */ return ((prefix_len * line_count) + info->text_len + 1); } /* * Beginning with @start_seq, find the first record where it and all following * records up to (but not including) @max_seq fit into @size. * * @max_seq is simply an upper bound and does not need to exist. If the caller * does not require an upper bound, -1 can be used for @max_seq. */ static u64 find_first_fitting_seq(u64 start_seq, u64 max_seq, size_t size, bool syslog, bool time) { struct printk_info info; unsigned int line_count; size_t len = 0; u64 seq; /* Determine the size of the records up to @max_seq. */ prb_for_each_info(start_seq, prb, seq, &info, &line_count) { if (info.seq >= max_seq) break; len += get_record_print_text_size(&info, line_count, syslog, time); } /* * Adjust the upper bound for the next loop to avoid subtracting * lengths that were never added. */ if (seq < max_seq) max_seq = seq; /* * Move first record forward until length fits into the buffer. Ignore * newest messages that were not counted in the above cycle. Messages * might appear and get lost in the meantime. This is a best effort * that prevents an infinite loop that could occur with a retry. */ prb_for_each_info(start_seq, prb, seq, &info, &line_count) { if (len <= size || info.seq >= max_seq) break; len -= get_record_print_text_size(&info, line_count, syslog, time); } return seq; } /* The caller is responsible for making sure @size is greater than 0. */ static int syslog_print(char __user *buf, int size) { struct printk_info info; struct printk_record r; char *text; int len = 0; u64 seq; text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); if (!text) return -ENOMEM; prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); mutex_lock(&syslog_lock); /* * Wait for the @syslog_seq record to be available. @syslog_seq may * change while waiting. */ do { seq = syslog_seq; mutex_unlock(&syslog_lock); /* * Guarantee this task is visible on the waitqueue before * checking the wake condition. * * The full memory barrier within set_current_state() of * prepare_to_wait_event() pairs with the full memory barrier * within wq_has_sleeper(). * * This pairs with __wake_up_klogd:A. */ len = wait_event_interruptible(log_wait, prb_read_valid(prb, seq, NULL)); /* LMM(syslog_print:A) */ mutex_lock(&syslog_lock); if (len) goto out; } while (syslog_seq != seq); /* * Copy records that fit into the buffer. The above cycle makes sure * that the first record is always available. */ do { size_t n; size_t skip; int err; if (!prb_read_valid(prb, syslog_seq, &r)) break; if (r.info->seq != syslog_seq) { /* message is gone, move to next valid one */ syslog_seq = r.info->seq; syslog_partial = 0; } /* * To keep reading/counting partial line consistent, * use printk_time value as of the beginning of a line. */ if (!syslog_partial) syslog_time = printk_time; skip = syslog_partial; n = record_print_text(&r, true, syslog_time); if (n - syslog_partial <= size) { /* message fits into buffer, move forward */ syslog_seq = r.info->seq + 1; n -= syslog_partial; syslog_partial = 0; } else if (!len){ /* partial read(), remember position */ n = size; syslog_partial += n; } else n = 0; if (!n) break; mutex_unlock(&syslog_lock); err = copy_to_user(buf, text + skip, n); mutex_lock(&syslog_lock); if (err) { if (!len) len = -EFAULT; break; } len += n; size -= n; buf += n; } while (size); out: mutex_unlock(&syslog_lock); kfree(text); return len; } static int syslog_print_all(char __user *buf, int size, bool clear) { struct printk_info info; struct printk_record r; char *text; int len = 0; u64 seq; bool time; text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); if (!text) return -ENOMEM; time = printk_time; /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. */ seq = find_first_fitting_seq(latched_seq_read_nolock(&clear_seq), -1, size, true, time); prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); len = 0; prb_for_each_record(seq, prb, seq, &r) { int textlen; textlen = record_print_text(&r, true, time); if (len + textlen > size) { seq--; break; } if (copy_to_user(buf + len, text, textlen)) len = -EFAULT; else len += textlen; if (len < 0) break; } if (clear) { mutex_lock(&syslog_lock); latched_seq_write(&clear_seq, seq); mutex_unlock(&syslog_lock); } kfree(text); return len; } static void syslog_clear(void) { mutex_lock(&syslog_lock); latched_seq_write(&clear_seq, prb_next_seq(prb)); mutex_unlock(&syslog_lock); } int do_syslog(int type, char __user *buf, int len, int source) { struct printk_info info; bool clear = false; static int saved_console_loglevel = LOGLEVEL_DEFAULT; int error; error = check_syslog_permissions(type, source); if (error) return error; switch (type) { case SYSLOG_ACTION_CLOSE: /* Close log */ break; case SYSLOG_ACTION_OPEN: /* Open log */ break; case SYSLOG_ACTION_READ: /* Read from log */ if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(buf, len)) return -EFAULT; error = syslog_print(buf, len); break; /* Read/clear last kernel messages */ case SYSLOG_ACTION_READ_CLEAR: clear = true; fallthrough; /* Read last kernel messages */ case SYSLOG_ACTION_READ_ALL: if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(buf, len)) return -EFAULT; error = syslog_print_all(buf, len, clear); break; /* Clear ring buffer */ case SYSLOG_ACTION_CLEAR: syslog_clear(); break; /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_OFF: if (saved_console_loglevel == LOGLEVEL_DEFAULT) saved_console_loglevel = console_loglevel; console_loglevel = minimum_console_loglevel; break; /* Enable logging to console */ case SYSLOG_ACTION_CONSOLE_ON: if (saved_console_loglevel != LOGLEVEL_DEFAULT) { console_loglevel = saved_console_loglevel; saved_console_loglevel = LOGLEVEL_DEFAULT; } break; /* Set level of messages printed to console */ case SYSLOG_ACTION_CONSOLE_LEVEL: if (len < 1 || len > 8) return -EINVAL; if (len < minimum_console_loglevel) len = minimum_console_loglevel; console_loglevel = len; /* Implicitly re-enable logging to console */ saved_console_loglevel = LOGLEVEL_DEFAULT; break; /* Number of chars in the log buffer */ case SYSLOG_ACTION_SIZE_UNREAD: mutex_lock(&syslog_lock); if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) { /* No unread messages. */ mutex_unlock(&syslog_lock); return 0; } if (info.seq != syslog_seq) { /* messages are gone, move to first one */ syslog_seq = info.seq; syslog_partial = 0; } if (source == SYSLOG_FROM_PROC) { /* * Short-cut for poll(/"proc/kmsg") which simply checks * for pending data, not the size; return the count of * records, not the length. */ error = prb_next_seq(prb) - syslog_seq; } else { bool time = syslog_partial ? syslog_time : printk_time; unsigned int line_count; u64 seq; prb_for_each_info(syslog_seq, prb, seq, &info, &line_count) { error += get_record_print_text_size(&info, line_count, true, time); time = printk_time; } error -= syslog_partial; } mutex_unlock(&syslog_lock); break; /* Size of the log buffer */ case SYSLOG_ACTION_SIZE_BUFFER: error = log_buf_len; break; default: error = -EINVAL; break; } return error; } SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) { return do_syslog(type, buf, len, SYSLOG_FROM_READER); } /* * Special console_lock variants that help to reduce the risk of soft-lockups. * They allow to pass console_lock to another printk() call using a busy wait. */ #ifdef CONFIG_LOCKDEP static struct lockdep_map console_owner_dep_map = { .name = "console_owner" }; #endif static DEFINE_RAW_SPINLOCK(console_owner_lock); static struct task_struct *console_owner; static bool console_waiter; /** * console_lock_spinning_enable - mark beginning of code where another * thread might safely busy wait * * This basically converts console_lock into a spinlock. This marks * the section where the console_lock owner can not sleep, because * there may be a waiter spinning (like a spinlock). Also it must be * ready to hand over the lock at the end of the section. */ static void console_lock_spinning_enable(void) { raw_spin_lock(&console_owner_lock); console_owner = current; raw_spin_unlock(&console_owner_lock); /* The waiter may spin on us after setting console_owner */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); } /** * console_lock_spinning_disable_and_check - mark end of code where another * thread was able to busy wait and check if there is a waiter * * This is called at the end of the section where spinning is allowed. * It has two functions. First, it is a signal that it is no longer * safe to start busy waiting for the lock. Second, it checks if * there is a busy waiter and passes the lock rights to her. * * Important: Callers lose the lock if there was a busy waiter. * They must not touch items synchronized by console_lock * in this case. * * Return: 1 if the lock rights were passed, 0 otherwise. */ static int console_lock_spinning_disable_and_check(void) { int waiter; raw_spin_lock(&console_owner_lock); waiter = READ_ONCE(console_waiter); console_owner = NULL; raw_spin_unlock(&console_owner_lock); if (!waiter) { spin_release(&console_owner_dep_map, _THIS_IP_); return 0; } /* The waiter is now free to continue */ WRITE_ONCE(console_waiter, false); spin_release(&console_owner_dep_map, _THIS_IP_); /* * Hand off console_lock to waiter. The waiter will perform * the up(). After this, the waiter is the console_lock owner. */ mutex_release(&console_lock_dep_map, _THIS_IP_); return 1; } /** * console_trylock_spinning - try to get console_lock by busy waiting * * This allows to busy wait for the console_lock when the current * owner is running in specially marked sections. It means that * the current owner is running and cannot reschedule until it * is ready to lose the lock. * * Return: 1 if we got the lock, 0 othrewise */ static int console_trylock_spinning(void) { struct task_struct *owner = NULL; bool waiter; bool spin = false; unsigned long flags; if (console_trylock()) return 1; printk_safe_enter_irqsave(flags); raw_spin_lock(&console_owner_lock); owner = READ_ONCE(console_owner); waiter = READ_ONCE(console_waiter); if (!waiter && owner && owner != current) { WRITE_ONCE(console_waiter, true); spin = true; } raw_spin_unlock(&console_owner_lock); /* * If there is an active printk() writing to the * consoles, instead of having it write our data too, * see if we can offload that load from the active * printer, and do some printing ourselves. * Go into a spin only if there isn't already a waiter * spinning, and there is an active printer, and * that active printer isn't us (recursive printk?). */ if (!spin) { printk_safe_exit_irqrestore(flags); return 0; } /* We spin waiting for the owner to release us */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); /* Owner will clear console_waiter on hand off */ while (READ_ONCE(console_waiter)) cpu_relax(); spin_release(&console_owner_dep_map, _THIS_IP_); printk_safe_exit_irqrestore(flags); /* * The owner passed the console lock to us. * Since we did not spin on console lock, annotate * this as a trylock. Otherwise lockdep will * complain. */ mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); /* * Update @console_may_schedule for trylock because the previous * owner may have been schedulable. */ console_may_schedule = 0; return 1; } /* * Call the console drivers, asking them to write out * log_buf[start] to log_buf[end - 1]. * The console_lock must be held. */ static void call_console_drivers(const char *ext_text, size_t ext_len, const char *text, size_t len) { static char dropped_text[64]; size_t dropped_len = 0; struct console *con; trace_console_rcuidle(text, len); if (!console_drivers) return; if (console_dropped) { dropped_len = snprintf(dropped_text, sizeof(dropped_text), "** %lu printk messages dropped **\n", console_dropped); console_dropped = 0; } for_each_console(con) { if (exclusive_console && con != exclusive_console) continue; if (!(con->flags & CON_ENABLED)) continue; if (!con->write) continue; if (!cpu_online(smp_processor_id()) && !(con->flags & CON_ANYTIME)) continue; if (con->flags & CON_EXTENDED) con->write(con, ext_text, ext_len); else { if (dropped_len) con->write(con, dropped_text, dropped_len); con->write(con, text, len); } } } /* * Recursion is tracked separately on each CPU. If NMIs are supported, an * additional NMI context per CPU is also separately tracked. Until per-CPU * is available, a separate "early tracking" is performed. */ static DEFINE_PER_CPU(u8, printk_count); static u8 printk_count_early; #ifdef CONFIG_HAVE_NMI static DEFINE_PER_CPU(u8, printk_count_nmi); static u8 printk_count_nmi_early; #endif /* * Recursion is limited to keep the output sane. printk() should not require * more than 1 level of recursion (allowing, for example, printk() to trigger * a WARN), but a higher value is used in case some printk-internal errors * exist, such as the ringbuffer validation checks failing. */ #define PRINTK_MAX_RECURSION 3 /* * Return a pointer to the dedicated counter for the CPU+context of the * caller. */ static u8 *__printk_recursion_counter(void) { #ifdef CONFIG_HAVE_NMI if (in_nmi()) { if (printk_percpu_data_ready()) return this_cpu_ptr(&printk_count_nmi); return &printk_count_nmi_early; } #endif if (printk_percpu_data_ready()) return this_cpu_ptr(&printk_count); return &printk_count_early; } /* * Enter recursion tracking. Interrupts are disabled to simplify tracking. * The caller must check the boolean return value to see if the recursion is * allowed. On failure, interrupts are not disabled. * * @recursion_ptr must be a variable of type (u8 *) and is the same variable * that is passed to printk_exit_irqrestore(). */ #define printk_enter_irqsave(recursion_ptr, flags) \ ({ \ bool success = true; \ \ typecheck(u8 *, recursion_ptr); \ local_irq_save(flags); \ (recursion_ptr) = __printk_recursion_counter(); \ if (*(recursion_ptr) > PRINTK_MAX_RECURSION) { \ local_irq_restore(flags); \ success = false; \ } else { \ (*(recursion_ptr))++; \ } \ success; \ }) /* Exit recursion tracking, restoring interrupts. */ #define printk_exit_irqrestore(recursion_ptr, flags) \ do { \ typecheck(u8 *, recursion_ptr); \ (*(recursion_ptr))--; \ local_irq_restore(flags); \ } while (0) int printk_delay_msec __read_mostly; static inline void printk_delay(void) { if (unlikely(printk_delay_msec)) { int m = printk_delay_msec; while (m--) { mdelay(1); touch_nmi_watchdog(); } } } static inline u32 printk_caller_id(void) { u32 caller_id = 0; trace_android_vh_printk_caller_id(&caller_id); if (caller_id) return caller_id; return in_task() ? task_pid_nr(current) : 0x80000000 + raw_smp_processor_id(); } /** * printk_parse_prefix - Parse level and control flags. * * @text: The terminated text message. * @level: A pointer to the current level value, will be updated. * @flags: A pointer to the current printk_info flags, will be updated. * * @level may be NULL if the caller is not interested in the parsed value. * Otherwise the variable pointed to by @level must be set to * LOGLEVEL_DEFAULT in order to be updated with the parsed value. * * @flags may be NULL if the caller is not interested in the parsed value. * Otherwise the variable pointed to by @flags will be OR'd with the parsed * value. * * Return: The length of the parsed level and control flags. */ u16 printk_parse_prefix(const char *text, int *level, enum printk_info_flags *flags) { u16 prefix_len = 0; int kern_level; while (*text) { kern_level = printk_get_level(text); if (!kern_level) break; switch (kern_level) { case '0' ... '7': if (level && *level == LOGLEVEL_DEFAULT) *level = kern_level - '0'; break; case 'c': /* KERN_CONT */ if (flags) *flags |= LOG_CONT; } prefix_len += 2; text += 2; } return prefix_len; } static u16 printk_sprint(char *text, u16 size, int facility, enum printk_info_flags *flags, const char *fmt, va_list args) { u16 text_len; text_len = vscnprintf(text, size, fmt, args); /* Mark and strip a trailing newline. */ if (text_len && text[text_len - 1] == '\n') { text_len--; *flags |= LOG_NEWLINE; } /* Strip log level and control flags. */ if (facility == 0) { u16 prefix_len; prefix_len = printk_parse_prefix(text, NULL, NULL); if (prefix_len) { text_len -= prefix_len; memmove(text, text + prefix_len, text_len); } } return text_len; } __printf(4, 0) int vprintk_store(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { const u32 caller_id = printk_caller_id(); struct prb_reserved_entry e; enum printk_info_flags flags = 0; struct printk_record r; unsigned long irqflags; u16 trunc_msg_len = 0; char prefix_buf[8]; u8 *recursion_ptr; u16 reserve_size; va_list args2; u16 text_len; int ret = 0; u64 ts_nsec; /* * Since the duration of printk() can vary depending on the message * and state of the ringbuffer, grab the timestamp now so that it is * close to the call of printk(). This provides a more deterministic * timestamp with respect to the caller. */ ts_nsec = local_clock(); if (!printk_enter_irqsave(recursion_ptr, irqflags)) return 0; /* * The sprintf needs to come first since the syslog prefix might be * passed in as a parameter. An extra byte must be reserved so that * later the vscnprintf() into the reserved buffer has room for the * terminating '\0', which is not counted by vsnprintf(). */ va_copy(args2, args); reserve_size = vsnprintf(&prefix_buf[0], sizeof(prefix_buf), fmt, args2) + 1; va_end(args2); if (reserve_size > LOG_LINE_MAX) reserve_size = LOG_LINE_MAX; /* Extract log level or control flags. */ if (facility == 0) printk_parse_prefix(&prefix_buf[0], &level, &flags); if (level == LOGLEVEL_DEFAULT) level = default_message_loglevel; if (dev_info) flags |= LOG_NEWLINE; if (flags & LOG_CONT) { prb_rec_init_wr(&r, reserve_size); if (prb_reserve_in_last(&e, prb, &r, caller_id, LOG_LINE_MAX)) { text_len = printk_sprint(&r.text_buf[r.info->text_len], reserve_size, facility, &flags, fmt, args); r.info->text_len += text_len; if (flags & LOG_NEWLINE) { r.info->flags |= LOG_NEWLINE; prb_final_commit(&e); } else { prb_commit(&e); } trace_android_vh_logbuf_pr_cont(&r, text_len); ret = text_len; goto out; } } /* * Explicitly initialize the record before every prb_reserve() call. * prb_reserve_in_last() and prb_reserve() purposely invalidate the * structure when they fail. */ prb_rec_init_wr(&r, reserve_size); if (!prb_reserve(&e, prb, &r)) { /* truncate the message if it is too long for empty buffer */ truncate_msg(&reserve_size, &trunc_msg_len); prb_rec_init_wr(&r, reserve_size + trunc_msg_len); if (!prb_reserve(&e, prb, &r)) goto out; } /* fill message */ text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &flags, fmt, args); if (trunc_msg_len) memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len); r.info->text_len = text_len + trunc_msg_len; r.info->facility = facility; r.info->level = level & 7; r.info->flags = flags & 0x1f; r.info->ts_nsec = ts_nsec; r.info->caller_id = caller_id; if (dev_info) memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info)); /* A message without a trailing newline can be continued. */ if (!(flags & LOG_NEWLINE)) prb_commit(&e); else prb_final_commit(&e); trace_android_vh_logbuf(prb, &r); ret = text_len + trunc_msg_len; out: printk_exit_irqrestore(recursion_ptr, irqflags); return ret; } asmlinkage int vprintk_emit(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { int printed_len; bool in_sched = false; /* Suppress unimportant messages after panic happens */ if (unlikely(suppress_printk)) return 0; if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; in_sched = true; } boot_delay_msec(level); printk_delay(); printed_len = vprintk_store(facility, level, dev_info, fmt, args); /* If called from the scheduler, we can not call up(). */ if (!in_sched) { /* * Disable preemption to avoid being preempted while holding * console_sem which would prevent anyone from printing to * console */ preempt_disable(); /* * Try to acquire and then immediately release the console * semaphore. The release will print out buffers and wake up * /dev/kmsg and syslog() users. */ if (console_trylock_spinning()) console_unlock(); preempt_enable(); } if (in_sched) defer_console_output(); else wake_up_klogd(); return printed_len; } EXPORT_SYMBOL(vprintk_emit); int vprintk_default(const char *fmt, va_list args) { return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args); } EXPORT_SYMBOL_GPL(vprintk_default); asmlinkage __visible int _printk(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk(fmt, args); va_end(args); return r; } EXPORT_SYMBOL(_printk); #else /* CONFIG_PRINTK */ #define CONSOLE_LOG_MAX 0 #define printk_time false #define prb_read_valid(rb, seq, r) false #define prb_first_valid_seq(rb) 0 static u64 syslog_seq; static u64 console_seq; static u64 exclusive_console_stop_seq; static unsigned long console_dropped; static size_t record_print_text(const struct printk_record *r, bool syslog, bool time) { return 0; } static ssize_t info_print_ext_header(char *buf, size_t size, struct printk_info *info) { return 0; } static ssize_t msg_print_ext_body(char *buf, size_t size, char *text, size_t text_len, struct dev_printk_info *dev_info) { return 0; } static void console_lock_spinning_enable(void) { } static int console_lock_spinning_disable_and_check(void) { return 0; } static void call_console_drivers(const char *ext_text, size_t ext_len, const char *text, size_t len) {} static bool suppress_message_printing(int level) { return false; } #endif /* CONFIG_PRINTK */ #ifdef CONFIG_EARLY_PRINTK struct console *early_console; asmlinkage __visible void early_printk(const char *fmt, ...) { va_list ap; char buf[512]; int n; if (!early_console) return; va_start(ap, fmt); n = vscnprintf(buf, sizeof(buf), fmt, ap); va_end(ap); early_console->write(early_console, buf, n); } #endif static int __add_preferred_console(char *name, int idx, char *options, char *brl_options, bool user_specified) { struct console_cmdline *c; int i; /* * See if this tty is not yet registered, and * if we have a slot free. */ for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && c->name[0]; i++, c++) { if (strcmp(c->name, name) == 0 && c->index == idx) { if (!brl_options) preferred_console = i; if (user_specified) c->user_specified = true; return 0; } } if (i == MAX_CMDLINECONSOLES) return -E2BIG; if (!brl_options) preferred_console = i; strlcpy(c->name, name, sizeof(c->name)); c->options = options; c->user_specified = user_specified; braille_set_options(c, brl_options); c->index = idx; return 0; } static int __init console_msg_format_setup(char *str) { if (!strcmp(str, "syslog")) console_msg_format = MSG_FORMAT_SYSLOG; if (!strcmp(str, "default")) console_msg_format = MSG_FORMAT_DEFAULT; return 1; } __setup("console_msg_format=", console_msg_format_setup); /* * Set up a console. Called via do_early_param() in init/main.c * for each "console=" parameter in the boot command line. */ static int __init console_setup(char *str) { char buf[sizeof(console_cmdline[0].name) + 4]; /* 4 for "ttyS" */ char *s, *options, *brl_options = NULL; int idx; /* * console="" or console=null have been suggested as a way to * disable console output. Use ttynull that has been created * for exactly this purpose. */ if (str[0] == 0 || strcmp(str, "null") == 0) { __add_preferred_console("ttynull", 0, NULL, NULL, true); return 1; } if (_braille_console_setup(&str, &brl_options)) return 1; /* * Decode str into name, index, options. */ if (str[0] >= '0' && str[0] <= '9') { strcpy(buf, "ttyS"); strncpy(buf + 4, str, sizeof(buf) - 5); } else { strncpy(buf, str, sizeof(buf) - 1); } buf[sizeof(buf) - 1] = 0; options = strchr(str, ','); if (options) *(options++) = 0; #ifdef __sparc__ if (!strcmp(str, "ttya")) strcpy(buf, "ttyS0"); if (!strcmp(str, "ttyb")) strcpy(buf, "ttyS1"); #endif for (s = buf; *s; s++) if (isdigit(*s) || *s == ',') break; idx = simple_strtoul(s, NULL, 10); *s = 0; __add_preferred_console(buf, idx, options, brl_options, true); console_set_on_cmdline = 1; return 1; } __setup("console=", console_setup); /** * add_preferred_console - add a device to the list of preferred consoles. * @name: device name * @idx: device index * @options: options for this console * * The last preferred console added will be used for kernel messages * and stdin/out/err for init. Normally this is used by console_setup * above to handle user-supplied console arguments; however it can also * be used by arch-specific code either to override the user or more * commonly to provide a default console (ie from PROM variables) when * the user has not supplied one. */ int add_preferred_console(char *name, int idx, char *options) { return __add_preferred_console(name, idx, options, NULL, false); } bool console_suspend_enabled = true; EXPORT_SYMBOL(console_suspend_enabled); static int __init console_suspend_disable(char *str) { console_suspend_enabled = false; return 1; } __setup("no_console_suspend", console_suspend_disable); module_param_named(console_suspend, console_suspend_enabled, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(console_suspend, "suspend console during suspend" " and hibernate operations"); static bool printk_console_no_auto_verbose; void console_verbose(void) { if (console_loglevel && !printk_console_no_auto_verbose) console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; } EXPORT_SYMBOL_GPL(console_verbose); module_param_named(console_no_auto_verbose, printk_console_no_auto_verbose, bool, 0644); MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to highest on oops/panic/etc"); /** * suspend_console - suspend the console subsystem * * This disables printk() while we go into suspend states */ void suspend_console(void) { if (!console_suspend_enabled) return; pr_info("Suspending console(s) (use no_console_suspend to debug)\n"); console_lock(); console_suspended = 1; up_console_sem(); } void resume_console(void) { if (!console_suspend_enabled) return; down_console_sem(); console_suspended = 0; console_unlock(); } /** * console_cpu_notify - print deferred console messages after CPU hotplug * @cpu: unused * * If printk() is called from a CPU that is not online yet, the messages * will be printed on the console only if there are CON_ANYTIME consoles. * This function is called when a new CPU comes online (or fails to come * up) or goes offline. */ static int console_cpu_notify(unsigned int cpu) { int flag = 0; trace_android_vh_printk_hotplug(&flag); if (flag) return 0; if (!cpuhp_tasks_frozen) { /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); } return 0; } /** * console_lock - lock the console system for exclusive use. * * Acquires a lock which guarantees that the caller has * exclusive access to the console system and the console_drivers list. * * Can sleep, returns nothing. */ void console_lock(void) { might_sleep(); down_console_sem(); if (console_suspended) return; console_locked = 1; console_may_schedule = 1; } EXPORT_SYMBOL(console_lock); /** * console_trylock - try to lock the console system for exclusive use. * * Try to acquire a lock which guarantees that the caller has exclusive * access to the console system and the console_drivers list. * * returns 1 on success, and 0 on failure to acquire the lock. */ int console_trylock(void) { if (down_trylock_console_sem()) return 0; if (console_suspended) { up_console_sem(); return 0; } console_locked = 1; console_may_schedule = 0; return 1; } EXPORT_SYMBOL(console_trylock); int is_console_locked(void) { return console_locked; } EXPORT_SYMBOL(is_console_locked); /* * Check if we have any console that is capable of printing while cpu is * booting or shutting down. Requires console_sem. */ static int have_callable_console(void) { struct console *con; for_each_console(con) if ((con->flags & CON_ENABLED) && (con->flags & CON_ANYTIME)) return 1; return 0; } /* * Can we actually use the console at this time on this cpu? * * Console drivers may assume that per-cpu resources have been allocated. So * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't * call them until this CPU is officially up. */ static inline int can_use_console(void) { return cpu_online(raw_smp_processor_id()) || have_callable_console(); } /** * console_unlock - unlock the console system * * Releases the console_lock which the caller holds on the console system * and the console driver list. * * While the console_lock was held, console output may have been buffered * by printk(). If this is the case, console_unlock(); emits * the output prior to releasing the lock. * * If there is output waiting, we wake /dev/kmsg and syslog() users. * * console_unlock(); may be called from any context. */ void console_unlock(void) { static char ext_text[CONSOLE_EXT_LOG_MAX]; static char text[CONSOLE_LOG_MAX]; unsigned long flags; bool do_cond_resched, retry; struct printk_info info; struct printk_record r; u64 __maybe_unused next_seq; if (console_suspended) { up_console_sem(); return; } prb_rec_init_rd(&r, &info, text, sizeof(text)); /* * Console drivers are called with interrupts disabled, so * @console_may_schedule should be cleared before; however, we may * end up dumping a lot of lines, for example, if called from * console registration path, and should invoke cond_resched() * between lines if allowable. Not doing so can cause a very long * scheduling stall on a slow console leading to RCU stall and * softlockup warnings which exacerbate the issue with more * messages practically incapacitating the system. * * console_trylock() is not able to detect the preemptive * context reliably. Therefore the value must be stored before * and cleared after the "again" goto label. */ do_cond_resched = console_may_schedule; again: console_may_schedule = 0; /* * We released the console_sem lock, so we need to recheck if * cpu is online and (if not) is there at least one CON_ANYTIME * console. */ if (!can_use_console()) { console_locked = 0; up_console_sem(); return; } for (;;) { size_t ext_len = 0; int handover; size_t len; skip: if (!prb_read_valid(prb, console_seq, &r)) break; if (console_seq != r.info->seq) { console_dropped += r.info->seq - console_seq; console_seq = r.info->seq; } if (suppress_message_printing(r.info->level)) { /* * Skip record we have buffered and already printed * directly to the console when we received it, and * record that has level above the console loglevel. */ console_seq++; goto skip; } /* Output to all consoles once old messages replayed. */ if (unlikely(exclusive_console && console_seq >= exclusive_console_stop_seq)) { exclusive_console = NULL; } /* * Handle extended console text first because later * record_print_text() will modify the record buffer in-place. */ if (nr_ext_console_drivers) { ext_len = info_print_ext_header(ext_text, sizeof(ext_text), r.info); ext_len += msg_print_ext_body(ext_text + ext_len, sizeof(ext_text) - ext_len, &r.text_buf[0], r.info->text_len, &r.info->dev_info); } len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); console_seq++; /* * While actively printing out messages, if another printk() * were to occur on another CPU, it may wait for this one to * finish. This task can not be preempted if there is a * waiter waiting to take over. * * Interrupts are disabled because the hand over to a waiter * must not be interrupted until the hand over is completed * (@console_waiter is cleared). */ printk_safe_enter_irqsave(flags); console_lock_spinning_enable(); stop_critical_timings(); /* don't trace print latency */ call_console_drivers(ext_text, ext_len, text, len); start_critical_timings(); handover = console_lock_spinning_disable_and_check(); printk_safe_exit_irqrestore(flags); if (handover) return; if (do_cond_resched) cond_resched(); } /* Get consistent value of the next-to-be-used sequence number. */ next_seq = console_seq; console_locked = 0; up_console_sem(); /* * Someone could have filled up the buffer again, so re-check if there's * something to flush. In case we cannot trylock the console_sem again, * there's a new owner and the console_unlock() from them will do the * flush, no worries. */ retry = prb_read_valid(prb, next_seq, NULL); if (retry && console_trylock()) goto again; } EXPORT_SYMBOL(console_unlock); /** * console_conditional_schedule - yield the CPU if required * * If the console code is currently allowed to sleep, and * if this CPU should yield the CPU to another task, do * so here. * * Must be called within console_lock();. */ void __sched console_conditional_schedule(void) { if (console_may_schedule) cond_resched(); } EXPORT_SYMBOL(console_conditional_schedule); void console_unblank(void) { struct console *c; /* * console_unblank can no longer be called in interrupt context unless * oops_in_progress is set to 1.. */ if (oops_in_progress) { if (down_trylock_console_sem() != 0) return; } else console_lock(); console_locked = 1; console_may_schedule = 0; for_each_console(c) if ((c->flags & CON_ENABLED) && c->unblank) c->unblank(); console_unlock(); } /** * console_flush_on_panic - flush console content on panic * @mode: flush all messages in buffer or just the pending ones * * Immediately output all pending messages no matter what. */ void console_flush_on_panic(enum con_flush_mode mode) { /* * If someone else is holding the console lock, trylock will fail * and may_schedule may be set. Ignore and proceed to unlock so * that messages are flushed out. As this can be called from any * context and we don't want to get preempted while flushing, * ensure may_schedule is cleared. */ console_trylock(); console_may_schedule = 0; if (mode == CONSOLE_REPLAY_ALL) console_seq = prb_first_valid_seq(prb); console_unlock(); } /* * Return the console tty driver structure and its associated index */ struct tty_driver *console_device(int *index) { struct console *c; struct tty_driver *driver = NULL; console_lock(); for_each_console(c) { if (!c->device) continue; driver = c->device(c, index); if (driver) break; } console_unlock(); return driver; } /* * Prevent further output on the passed console device so that (for example) * serial drivers can disable console output before suspending a port, and can * re-enable output afterwards. */ void console_stop(struct console *console) { console_lock(); console->flags &= ~CON_ENABLED; console_unlock(); } EXPORT_SYMBOL(console_stop); void console_start(struct console *console) { console_lock(); console->flags |= CON_ENABLED; console_unlock(); } EXPORT_SYMBOL(console_start); static int __read_mostly keep_bootcon; static int __init keep_bootcon_setup(char *str) { keep_bootcon = 1; pr_info("debug: skip boot console de-registration.\n"); return 0; } early_param("keep_bootcon", keep_bootcon_setup); static int console_call_setup(struct console *newcon, char *options) { int err; if (!newcon->setup) return 0; /* Synchronize with possible boot console. */ console_lock(); err = newcon->setup(newcon, options); console_unlock(); return err; } /* * This is called by register_console() to try to match * the newly registered console with any of the ones selected * by either the command line or add_preferred_console() and * setup/enable it. * * Care need to be taken with consoles that are statically * enabled such as netconsole */ static int try_enable_preferred_console(struct console *newcon, bool user_specified) { struct console_cmdline *c; int i, err; for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && c->name[0]; i++, c++) { if (c->user_specified != user_specified) continue; if (!newcon->match || newcon->match(newcon, c->name, c->index, c->options) != 0) { /* default matching */ BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name)); if (strcmp(c->name, newcon->name) != 0) continue; if (newcon->index >= 0 && newcon->index != c->index) continue; if (newcon->index < 0) newcon->index = c->index; if (_braille_register_console(newcon, c)) return 0; err = console_call_setup(newcon, c->options); if (err) return err; } newcon->flags |= CON_ENABLED; if (i == preferred_console) { newcon->flags |= CON_CONSDEV; has_preferred_console = true; } return 0; } /* * Some consoles, such as pstore and netconsole, can be enabled even * without matching. Accept the pre-enabled consoles only when match() * and setup() had a chance to be called. */ if (newcon->flags & CON_ENABLED && c->user_specified == user_specified) return 0; return -ENOENT; } /* Try to enable the console unconditionally */ static void try_enable_default_console(struct console *newcon) { if (newcon->index < 0) newcon->index = 0; if (console_call_setup(newcon, NULL) != 0) return; newcon->flags |= CON_ENABLED; if (newcon->device) { newcon->flags |= CON_CONSDEV; has_preferred_console = true; } } /* * The console driver calls this routine during kernel initialization * to register the console printing procedure with printk() and to * print any messages that were printed by the kernel before the * console driver was initialized. * * This can happen pretty early during the boot process (because of * early_printk) - sometimes before setup_arch() completes - be careful * of what kernel features are used - they may not be initialised yet. * * There are two types of consoles - bootconsoles (early_printk) and * "real" consoles (everything which is not a bootconsole) which are * handled differently. * - Any number of bootconsoles can be registered at any time. * - As soon as a "real" console is registered, all bootconsoles * will be unregistered automatically. * - Once a "real" console is registered, any attempt to register a * bootconsoles will be rejected */ void register_console(struct console *newcon) { struct console *bcon = NULL; int err; for_each_console(bcon) { if (WARN(bcon == newcon, "console '%s%d' already registered\n", bcon->name, bcon->index)) return; } /* * before we register a new CON_BOOT console, make sure we don't * already have a valid console */ if (newcon->flags & CON_BOOT) { for_each_console(bcon) { if (!(bcon->flags & CON_BOOT)) { pr_info("Too late to register bootconsole %s%d\n", newcon->name, newcon->index); return; } } } if (console_drivers && console_drivers->flags & CON_BOOT) bcon = console_drivers; if (!has_preferred_console || bcon || !console_drivers) has_preferred_console = preferred_console >= 0; /* * See if we want to use this console driver. If we * didn't select a console we take the first one * that registers here. */ if (!has_preferred_console) try_enable_default_console(newcon); /* See if this console matches one we selected on the command line */ err = try_enable_preferred_console(newcon, true); /* If not, try to match against the platform default(s) */ if (err == -ENOENT) err = try_enable_preferred_console(newcon, false); /* printk() messages are not printed to the Braille console. */ if (err || newcon->flags & CON_BRL) return; /* * If we have a bootconsole, and are switching to a real console, * don't print everything out again, since when the boot console, and * the real console are the same physical device, it's annoying to * see the beginning boot messages twice */ if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) newcon->flags &= ~CON_PRINTBUFFER; /* * Put this console in the list - keep the * preferred driver at the head of the list. */ console_lock(); if ((newcon->flags & CON_CONSDEV) || console_drivers == NULL) { newcon->next = console_drivers; console_drivers = newcon; if (newcon->next) newcon->next->flags &= ~CON_CONSDEV; /* Ensure this flag is always set for the head of the list */ newcon->flags |= CON_CONSDEV; } else { newcon->next = console_drivers->next; console_drivers->next = newcon; } if (newcon->flags & CON_EXTENDED) nr_ext_console_drivers++; if (newcon->flags & CON_PRINTBUFFER) { /* * console_unlock(); will print out the buffered messages * for us. * * We're about to replay the log buffer. Only do this to the * just-registered console to avoid excessive message spam to * the already-registered consoles. * * Set exclusive_console with disabled interrupts to reduce * race window with eventual console_flush_on_panic() that * ignores console_lock. */ exclusive_console = newcon; exclusive_console_stop_seq = console_seq; /* Get a consistent copy of @syslog_seq. */ mutex_lock(&syslog_lock); console_seq = syslog_seq; mutex_unlock(&syslog_lock); } console_unlock(); console_sysfs_notify(); /* * By unregistering the bootconsoles after we enable the real console * we get the "console xxx enabled" message on all the consoles - * boot consoles, real consoles, etc - this is to ensure that end * users know there might be something in the kernel's log buffer that * went to the bootconsole (that they do not see on the real console) */ pr_info("%sconsole [%s%d] enabled\n", (newcon->flags & CON_BOOT) ? "boot" : "" , newcon->name, newcon->index); if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) && !keep_bootcon) { /* We need to iterate through all boot consoles, to make * sure we print everything out, before we unregister them. */ for_each_console(bcon) if (bcon->flags & CON_BOOT) unregister_console(bcon); } } EXPORT_SYMBOL(register_console); int unregister_console(struct console *console) { struct console *con; int res; pr_info("%sconsole [%s%d] disabled\n", (console->flags & CON_BOOT) ? "boot" : "" , console->name, console->index); res = _braille_unregister_console(console); if (res < 0) return res; if (res > 0) return 0; res = -ENODEV; console_lock(); if (console_drivers == console) { console_drivers=console->next; res = 0; } else { for_each_console(con) { if (con->next == console) { con->next = console->next; res = 0; break; } } } if (res) goto out_disable_unlock; if (console->flags & CON_EXTENDED) nr_ext_console_drivers--; /* * If this isn't the last console and it has CON_CONSDEV set, we * need to set it on the next preferred console. */ if (console_drivers != NULL && console->flags & CON_CONSDEV) console_drivers->flags |= CON_CONSDEV; console->flags &= ~CON_ENABLED; console_unlock(); console_sysfs_notify(); if (console->exit) res = console->exit(console); return res; out_disable_unlock: console->flags &= ~CON_ENABLED; console_unlock(); return res; } EXPORT_SYMBOL(unregister_console); /* * Initialize the console device. This is called *early*, so * we can't necessarily depend on lots of kernel help here. * Just do some early initializations, and do the complex setup * later. */ void __init console_init(void) { int ret; initcall_t call; initcall_entry_t *ce; /* Setup the default TTY line discipline. */ n_tty_init(); /* * set up the console device so that later boot sequences can * inform about problems etc.. */ ce = __con_initcall_start; trace_initcall_level("console"); while (ce < __con_initcall_end) { call = initcall_from_entry(ce); trace_initcall_start(call); ret = call(); trace_initcall_finish(call, ret); ce++; } } /* * Some boot consoles access data that is in the init section and which will * be discarded after the initcalls have been run. To make sure that no code * will access this data, unregister the boot consoles in a late initcall. * * If for some reason, such as deferred probe or the driver being a loadable * module, the real console hasn't registered yet at this point, there will * be a brief interval in which no messages are logged to the console, which * makes it difficult to diagnose problems that occur during this time. * * To mitigate this problem somewhat, only unregister consoles whose memory * intersects with the init section. Note that all other boot consoles will * get unregistered when the real preferred console is registered. */ static int __init printk_late_init(void) { struct console *con; int ret; for_each_console(con) { if (!(con->flags & CON_BOOT)) continue; /* Check addresses that might be used for enabled consoles. */ if (init_section_intersects(con, sizeof(*con)) || init_section_contains(con->write, 0) || init_section_contains(con->read, 0) || init_section_contains(con->device, 0) || init_section_contains(con->unblank, 0) || init_section_contains(con->data, 0)) { /* * Please, consider moving the reported consoles out * of the init section. */ pr_warn("bootconsole [%s%d] uses init memory and must be disabled even before the real one is ready\n", con->name, con->index); unregister_console(con); } } ret = cpuhp_setup_state_nocalls(CPUHP_PRINTK_DEAD, "printk:dead", NULL, console_cpu_notify); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online", console_cpu_notify, NULL); WARN_ON(ret < 0); return 0; } late_initcall(printk_late_init); #if defined CONFIG_PRINTK /* * Delayed printk version, for scheduler-internal messages: */ #define PRINTK_PENDING_WAKEUP 0x01 #define PRINTK_PENDING_OUTPUT 0x02 static DEFINE_PER_CPU(int, printk_pending); static void wake_up_klogd_work_func(struct irq_work *irq_work) { int pending = this_cpu_xchg(printk_pending, 0); if (pending & PRINTK_PENDING_OUTPUT) { /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); } if (pending & PRINTK_PENDING_WAKEUP) wake_up_interruptible(&log_wait); } static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = IRQ_WORK_INIT_LAZY(wake_up_klogd_work_func); static void __wake_up_klogd(int val) { if (!printk_percpu_data_ready()) return; preempt_disable(); /* * Guarantee any new records can be seen by tasks preparing to wait * before this context checks if the wait queue is empty. * * The full memory barrier within wq_has_sleeper() pairs with the full * memory barrier within set_current_state() of * prepare_to_wait_event(), which is called after ___wait_event() adds * the waiter but before it has checked the wait condition. * * This pairs with devkmsg_read:A and syslog_print:A. */ if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */ (val & PRINTK_PENDING_OUTPUT)) { this_cpu_or(printk_pending, val); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); } preempt_enable(); } /** * wake_up_klogd - Wake kernel logging daemon * * Use this function when new records have been added to the ringbuffer * and the console printing of those records has already occurred or is * known to be handled by some other context. This function will only * wake the logging daemon. * * Context: Any context. */ void wake_up_klogd(void) { __wake_up_klogd(PRINTK_PENDING_WAKEUP); } /** * defer_console_output - Wake kernel logging daemon and trigger * console printing in a deferred context * * Use this function when new records have been added to the ringbuffer, * this context is responsible for console printing those records, but * the current context is not allowed to perform the console printing. * Trigger an irq_work context to perform the console printing. This * function also wakes the logging daemon. * * Context: Any context. */ void defer_console_output(void) { /* * New messages may have been added directly to the ringbuffer * using vprintk_store(), so wake any waiters as well. */ __wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT); } void printk_trigger_flush(void) { defer_console_output(); } int vprintk_deferred(const char *fmt, va_list args) { return vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args); } int _printk_deferred(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_deferred(fmt, args); va_end(args); return r; } EXPORT_SYMBOL_GPL(_printk_deferred); /* * printk rate limiting, lifted from the networking subsystem. * * This enforces a rate limit: not more than 10 kernel messages * every 5s to make a denial-of-service attack impossible. */ DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10); int __printk_ratelimit(const char *func) { return ___ratelimit(&printk_ratelimit_state, func); } EXPORT_SYMBOL(__printk_ratelimit); /** * printk_timed_ratelimit - caller-controlled printk ratelimiting * @caller_jiffies: pointer to caller's state * @interval_msecs: minimum interval between prints * * printk_timed_ratelimit() returns true if more than @interval_msecs * milliseconds have elapsed since the last time printk_timed_ratelimit() * returned true. */ bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msecs) { unsigned long elapsed = jiffies - *caller_jiffies; if (*caller_jiffies && elapsed <= msecs_to_jiffies(interval_msecs)) return false; *caller_jiffies = jiffies; return true; } EXPORT_SYMBOL(printk_timed_ratelimit); static DEFINE_SPINLOCK(dump_list_lock); static LIST_HEAD(dump_list); /** * kmsg_dump_register - register a kernel log dumper. * @dumper: pointer to the kmsg_dumper structure * * Adds a kernel log dumper to the system. The dump callback in the * structure will be called when the kernel oopses or panics and must be * set. Returns zero on success and %-EINVAL or %-EBUSY otherwise. */ int kmsg_dump_register(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EBUSY; /* The dump callback needs to be set */ if (!dumper->dump) return -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); /* Don't allow registering multiple times */ if (!dumper->registered) { dumper->registered = 1; list_add_tail_rcu(&dumper->list, &dump_list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_register); /** * kmsg_dump_unregister - unregister a kmsg dumper. * @dumper: pointer to the kmsg_dumper structure * * Removes a dump device from the system. Returns zero on success and * %-EINVAL otherwise. */ int kmsg_dump_unregister(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); if (dumper->registered) { dumper->registered = 0; list_del_rcu(&dumper->list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); synchronize_rcu(); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_unregister); static bool always_kmsg_dump; module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) { switch (reason) { case KMSG_DUMP_PANIC: return "Panic"; case KMSG_DUMP_OOPS: return "Oops"; case KMSG_DUMP_EMERG: return "Emergency"; case KMSG_DUMP_SHUTDOWN: return "Shutdown"; default: return "Unknown"; } } EXPORT_SYMBOL_GPL(kmsg_dump_reason_str); /** * kmsg_dump - dump kernel log to kernel message dumpers. * @reason: the reason (oops, panic etc) for dumping * * Call each of the registered dumper's dump() callback, which can * retrieve the kmsg records with kmsg_dump_get_line() or * kmsg_dump_get_buffer(). */ void kmsg_dump(enum kmsg_dump_reason reason) { struct kmsg_dumper *dumper; rcu_read_lock(); list_for_each_entry_rcu(dumper, &dump_list, list) { enum kmsg_dump_reason max_reason = dumper->max_reason; /* * If client has not provided a specific max_reason, default * to KMSG_DUMP_OOPS, unless always_kmsg_dump was set. */ if (max_reason == KMSG_DUMP_UNDEF) { max_reason = always_kmsg_dump ? KMSG_DUMP_MAX : KMSG_DUMP_OOPS; } if (reason > max_reason) continue; /* invoke dumper which will iterate over records */ dumper->dump(dumper, reason); } rcu_read_unlock(); } /** * kmsg_dump_get_line - retrieve one kmsg log line * @iter: kmsg dump iterator * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to * @size: maximum size of the buffer * @len: length of line placed into buffer * * Start at the beginning of the kmsg buffer, with the oldest kmsg * record, and copy one record into the provided buffer. * * Consecutive calls will return the next available record moving * towards the end of the buffer with the youngest messages. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, char *line, size_t size, size_t *len) { u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; unsigned int line_count; struct printk_record r; size_t l = 0; bool ret = false; if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; prb_rec_init_rd(&r, &info, line, size); /* Read text or count text lines? */ if (line) { if (!prb_read_valid(prb, iter->cur_seq, &r)) goto out; l = record_print_text(&r, syslog, printk_time); } else { if (!prb_read_valid_info(prb, iter->cur_seq, &info, &line_count)) { goto out; } l = get_record_print_text_size(&info, line_count, syslog, printk_time); } iter->cur_seq = r.info->seq + 1; ret = true; out: if (len) *len = l; return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_line); /** * kmsg_dump_get_buffer - copy kmsg log lines * @iter: kmsg dump iterator * @syslog: include the "<4>" prefixes * @buf: buffer to copy the line to * @size: maximum size of the buffer * @len_out: length of line placed into buffer * * Start at the end of the kmsg buffer and fill the provided buffer * with as many of the *youngest* kmsg records that fit into it. * If the buffer is large enough, all available kmsg records will be * copied with a single call. * * Consecutive calls will fill the buffer with the next block of * available older records, not including the earlier retrieved ones. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, char *buf, size_t size, size_t *len_out) { u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; struct printk_record r; u64 seq; u64 next_seq; size_t len = 0; bool ret = false; bool time = printk_time; if (!buf || !size) goto out; if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) { if (info.seq != iter->cur_seq) { /* messages are gone, move to first available one */ iter->cur_seq = info.seq; } } /* last entry */ if (iter->cur_seq >= iter->next_seq) goto out; /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. Pass in size-1 * because this function (by way of record_print_text()) will * not write more than size-1 bytes of text into @buf. */ seq = find_first_fitting_seq(iter->cur_seq, iter->next_seq, size - 1, syslog, time); /* * Next kmsg_dump_get_buffer() invocation will dump block of * older records stored right before this one. */ next_seq = seq; prb_rec_init_rd(&r, &info, buf, size); len = 0; prb_for_each_record(seq, prb, seq, &r) { if (r.info->seq >= iter->next_seq) break; len += record_print_text(&r, syslog, time); /* Adjust record to store to remaining buffer space. */ prb_rec_init_rd(&r, &info, buf + len, size - len); } iter->next_seq = next_seq; ret = true; out: if (len_out) *len_out = len; return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); /** * kmsg_dump_rewind - reset the iterator * @iter: kmsg dump iterator * * Reset the dumper's iterator so that kmsg_dump_get_line() and * kmsg_dump_get_buffer() can be called again and used multiple * times within the same dumper.dump() callback. */ void kmsg_dump_rewind(struct kmsg_dump_iter *iter) { iter->cur_seq = latched_seq_read_nolock(&clear_seq); iter->next_seq = prb_next_seq(prb); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); #endif #ifdef CONFIG_SMP static atomic_t printk_cpulock_owner = ATOMIC_INIT(-1); static atomic_t printk_cpulock_nested = ATOMIC_INIT(0); /** * __printk_wait_on_cpu_lock() - Busy wait until the printk cpu-reentrant * spinning lock is not owned by any CPU. * * Context: Any context. */ void __printk_wait_on_cpu_lock(void) { do { cpu_relax(); } while (atomic_read(&printk_cpulock_owner) != -1); } EXPORT_SYMBOL(__printk_wait_on_cpu_lock); /** * __printk_cpu_trylock() - Try to acquire the printk cpu-reentrant * spinning lock. * * If no processor has the lock, the calling processor takes the lock and * becomes the owner. If the calling processor is already the owner of the * lock, this function succeeds immediately. * * Context: Any context. Expects interrupts to be disabled. * Return: 1 on success, otherwise 0. */ int __printk_cpu_trylock(void) { int cpu; int old; cpu = smp_processor_id(); /* * Guarantee loads and stores from this CPU when it is the lock owner * are _not_ visible to the previous lock owner. This pairs with * __printk_cpu_unlock:B. * * Memory barrier involvement: * * If __printk_cpu_trylock:A reads from __printk_cpu_unlock:B, then * __printk_cpu_unlock:A can never read from __printk_cpu_trylock:B. * * Relies on: * * RELEASE from __printk_cpu_unlock:A to __printk_cpu_unlock:B * of the previous CPU * matching * ACQUIRE from __printk_cpu_trylock:A to __printk_cpu_trylock:B * of this CPU */ old = atomic_cmpxchg_acquire(&printk_cpulock_owner, -1, cpu); /* LMM(__printk_cpu_trylock:A) */ if (old == -1) { /* * This CPU is now the owner and begins loading/storing * data: LMM(__printk_cpu_trylock:B) */ return 1; } else if (old == cpu) { /* This CPU is already the owner. */ atomic_inc(&printk_cpulock_nested); return 1; } return 0; } EXPORT_SYMBOL(__printk_cpu_trylock); /** * __printk_cpu_unlock() - Release the printk cpu-reentrant spinning lock. * * The calling processor must be the owner of the lock. * * Context: Any context. Expects interrupts to be disabled. */ void __printk_cpu_unlock(void) { if (atomic_read(&printk_cpulock_nested)) { atomic_dec(&printk_cpulock_nested); return; } /* * This CPU is finished loading/storing data: * LMM(__printk_cpu_unlock:A) */ /* * Guarantee loads and stores from this CPU when it was the * lock owner are visible to the next lock owner. This pairs * with __printk_cpu_trylock:A. * * Memory barrier involvement: * * If __printk_cpu_trylock:A reads from __printk_cpu_unlock:B, * then __printk_cpu_trylock:B reads from __printk_cpu_unlock:A. * * Relies on: * * RELEASE from __printk_cpu_unlock:A to __printk_cpu_unlock:B * of this CPU * matching * ACQUIRE from __printk_cpu_trylock:A to __printk_cpu_trylock:B * of the next CPU */ atomic_set_release(&printk_cpulock_owner, -1); /* LMM(__printk_cpu_unlock:B) */ } EXPORT_SYMBOL(__printk_cpu_unlock); #endif /* CONFIG_SMP */ |
| 1 1 61 61 61 61 61 61 61 61 2685 2686 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Common Block IO controller cgroup interface * * Based on ideas and code from CFQ, CFS and BFQ: * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> * * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> * Paolo Valente <paolo.valente@unimore.it> * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> * * For policy-specific per-blkcg data: * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it> * Arianna Avanzini <avanzini.arianna@gmail.com> */ #include <linux/ioprio.h> #include <linux/kdev_t.h> #include <linux/module.h> #include <linux/sched/signal.h> #include <linux/err.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/slab.h> #include <linux/genhd.h> #include <linux/delay.h> #include <linux/atomic.h> #include <linux/ctype.h> #include <linux/blk-cgroup.h> #include <linux/tracehook.h> #include <linux/psi.h> #include "blk.h" #include "blk-ioprio.h" /* * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation. * blkcg_pol_register_mutex nests outside of it and synchronizes entire * policy [un]register operations including cgroup file additions / * removals. Putting cgroup file registration outside blkcg_pol_mutex * allows grabbing it from cgroup callbacks. */ static DEFINE_MUTEX(blkcg_pol_register_mutex); static DEFINE_MUTEX(blkcg_pol_mutex); struct blkcg blkcg_root; EXPORT_SYMBOL_GPL(blkcg_root); struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css; EXPORT_SYMBOL_GPL(blkcg_root_css); static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ bool blkcg_debug_stats = false; static struct workqueue_struct *blkcg_punt_bio_wq; #define BLKG_DESTROY_BATCH_SIZE 64 static bool blkcg_policy_enabled(struct request_queue *q, const struct blkcg_policy *pol) { return pol && test_bit(pol->plid, q->blkcg_pols); } /** * blkg_free - free a blkg * @blkg: blkg to free * * Free @blkg which may be partially allocated. */ static void blkg_free(struct blkcg_gq *blkg) { int i; if (!blkg) return; for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); free_percpu(blkg->iostat_cpu); percpu_ref_exit(&blkg->refcnt); kfree(blkg); } static void __blkg_release(struct rcu_head *rcu) { struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); WARN_ON(!bio_list_empty(&blkg->async_bios)); /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); if (blkg->parent) blkg_put(blkg->parent); blkg_free(blkg); } /* * A group is RCU protected, but having an rcu lock does not mean that one * can access all the fields of blkg and assume these are valid. For * example, don't try to follow throtl_data and request queue links. * * Having a reference to blkg under an rcu allows accesses to only values * local to groups like group stats and group rate limits. */ static void blkg_release(struct percpu_ref *ref) { struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt); call_rcu(&blkg->rcu_head, __blkg_release); } static void blkg_async_bio_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, async_bio_work); struct bio_list bios = BIO_EMPTY_LIST; struct bio *bio; struct blk_plug plug; bool need_plug = false; /* as long as there are pending bios, @blkg can't go away */ spin_lock_bh(&blkg->async_bio_lock); bio_list_merge(&bios, &blkg->async_bios); bio_list_init(&blkg->async_bios); spin_unlock_bh(&blkg->async_bio_lock); /* start plug only when bio_list contains at least 2 bios */ if (bios.head && bios.head->bi_next) { need_plug = true; blk_start_plug(&plug); } while ((bio = bio_list_pop(&bios))) submit_bio(bio); if (need_plug) blk_finish_plug(&plug); } /** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with * @q: request_queue the new blkg is associated with * @gfp_mask: allocation mask to use * * Allocate a new blkg assocating @blkcg and @q. */ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, gfp_t gfp_mask) { struct blkcg_gq *blkg; int i, cpu; /* alloc and init base part */ blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node); if (!blkg) return NULL; if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask)) goto err_free; blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask); if (!blkg->iostat_cpu) goto err_free; blkg->q = q; INIT_LIST_HEAD(&blkg->q_node); spin_lock_init(&blkg->async_bio_lock); bio_list_init(&blkg->async_bios); INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn); blkg->blkcg = blkcg; u64_stats_init(&blkg->iostat.sync); for_each_possible_cpu(cpu) u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkg_policy_data *pd; if (!blkcg_policy_enabled(q, pol)) continue; /* alloc per-policy data and attach it to blkg */ pd = pol->pd_alloc_fn(gfp_mask, q, blkcg); if (!pd) goto err_free; blkg->pd[i] = pd; pd->blkg = blkg; pd->plid = i; } return blkg; err_free: blkg_free(blkg); return NULL; } struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint) { struct blkcg_gq *blkg; /* * Hint didn't match. Look up from the radix tree. Note that the * hint can only be updated under queue_lock as otherwise @blkg * could have already been removed from blkg_tree. The caller is * responsible for grabbing queue_lock if @update_hint. */ blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id); if (blkg && blkg->q == q) { if (update_hint) { lockdep_assert_held(&q->queue_lock); rcu_assign_pointer(blkcg->blkg_hint, blkg); } return blkg; } return NULL; } EXPORT_SYMBOL_GPL(blkg_lookup_slowpath); /* * If @new_blkg is %NULL, this function tries to allocate a new one as * necessary using %GFP_NOWAIT. @new_blkg is always consumed on return. */ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct request_queue *q, struct blkcg_gq *new_blkg) { struct blkcg_gq *blkg; int i, ret; WARN_ON_ONCE(!rcu_read_lock_held()); lockdep_assert_held(&q->queue_lock); /* request_queue is dying, do not create/recreate a blkg */ if (blk_queue_dying(q)) { ret = -ENODEV; goto err_free_blkg; } /* blkg holds a reference to blkcg */ if (!css_tryget_online(&blkcg->css)) { ret = -ENODEV; goto err_free_blkg; } /* allocate */ if (!new_blkg) { new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto err_put_css; } } blkg = new_blkg; /* link parent */ if (blkcg_parent(blkcg)) { blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false); if (WARN_ON_ONCE(!blkg->parent)) { ret = -ENODEV; goto err_put_css; } blkg_get(blkg->parent); } /* invoke per-policy init */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_init_fn) pol->pd_init_fn(blkg->pd[i]); } /* insert */ spin_lock(&blkcg->lock); ret = radix_tree_insert(&blkcg->blkg_tree, q->id, blkg); if (likely(!ret)) { hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list); list_add(&blkg->q_node, &q->blkg_list); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_online_fn) pol->pd_online_fn(blkg->pd[i]); } } blkg->online = true; spin_unlock(&blkcg->lock); if (!ret) return blkg; /* @blkg failed fully initialized, use the usual release path */ blkg_put(blkg); return ERR_PTR(ret); err_put_css: css_put(&blkcg->css); err_free_blkg: blkg_free(new_blkg); return ERR_PTR(ret); } /** * blkg_lookup_create - lookup blkg, try to create one if not there * @blkcg: blkcg of interest * @q: request_queue of interest * * Lookup blkg for the @blkcg - @q pair. If it doesn't exist, try to * create one. blkg creation is performed recursively from blkcg_root such * that all non-root blkg's have access to the parent blkg. This function * should be called under RCU read lock and takes @q->queue_lock. * * Returns the blkg or the closest blkg if blkg_create() fails as it walks * down from root. */ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct request_queue *q) { struct blkcg_gq *blkg; unsigned long flags; WARN_ON_ONCE(!rcu_read_lock_held()); blkg = blkg_lookup(blkcg, q); if (blkg) return blkg; spin_lock_irqsave(&q->queue_lock, flags); blkg = __blkg_lookup(blkcg, q, true); if (blkg) goto found; /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. Returns the closest * blkg to the intended blkg should blkg_create() fail. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent = blkcg_parent(blkcg); struct blkcg_gq *ret_blkg = q->root_blkg; while (parent) { blkg = __blkg_lookup(parent, q, false); if (blkg) { /* remember closest blkg */ ret_blkg = blkg; break; } pos = parent; parent = blkcg_parent(parent); } blkg = blkg_create(pos, q, NULL); if (IS_ERR(blkg)) { blkg = ret_blkg; break; } if (pos == blkcg) break; } found: spin_unlock_irqrestore(&q->queue_lock, flags); return blkg; } static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; int i; lockdep_assert_held(&blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); /* Something wrong if we are trying to remove same group twice */ WARN_ON_ONCE(list_empty(&blkg->q_node)); WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node)); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[i]); } blkg->online = false; radix_tree_delete(&blkcg->blkg_tree, blkg->q->id); list_del_init(&blkg->q_node); hlist_del_init_rcu(&blkg->blkcg_node); /* * Both setting lookup hint to and clearing it from @blkg are done * under queue_lock. If it's not pointing to @blkg now, it never * will. Hint assignment itself can race safely. */ if (rcu_access_pointer(blkcg->blkg_hint) == blkg) rcu_assign_pointer(blkcg->blkg_hint, NULL); /* * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. */ percpu_ref_kill(&blkg->refcnt); } /** * blkg_destroy_all - destroy all blkgs associated with a request_queue * @q: request_queue of interest * * Destroy all blkgs associated with @q. */ static void blkg_destroy_all(struct request_queue *q) { struct blkcg_gq *blkg, *n; int count = BLKG_DESTROY_BATCH_SIZE; int i; restart: spin_lock_irq(&q->queue_lock); list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); blkg_destroy(blkg); spin_unlock(&blkcg->lock); /* * in order to avoid holding the spin lock for too long, release * it when a batch of blkgs are destroyed. */ if (!(--count)) { count = BLKG_DESTROY_BATCH_SIZE; spin_unlock_irq(&q->queue_lock); cond_resched(); goto restart; } } /* * Mark policy deactivated since policy offline has been done, and * the free is scheduled, so future blkcg_deactivate_policy() can * be bypassed */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (pol) __clear_bit(pol->plid, q->blkcg_pols); } q->root_blkg = NULL; spin_unlock_irq(&q->queue_lock); } static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; int i, cpu; mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); /* * Note that stat reset is racy - it doesn't synchronize against * stat updates. This is a debug feature which shouldn't exist * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { for_each_possible_cpu(cpu) { struct blkg_iostat_set *bis = per_cpu_ptr(blkg->iostat_cpu, cpu); memset(bis, 0, sizeof(*bis)); } memset(&blkg->iostat, 0, sizeof(blkg->iostat)); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_reset_stats_fn) pol->pd_reset_stats_fn(blkg->pd[i]); } } spin_unlock_irq(&blkcg->lock); mutex_unlock(&blkcg_pol_mutex); return 0; } const char *blkg_dev_name(struct blkcg_gq *blkg) { if (!blkg->q->disk || !blkg->q->disk->bdi->dev) return NULL; return bdi_dev_name(blkg->q->disk->bdi); } /** * blkcg_print_blkgs - helper for printing per-blkg data * @sf: seq_file to print to * @blkcg: blkcg of interest * @prfill: fill function to print out a blkg * @pol: policy in question * @data: data to be passed to @prfill * @show_total: to print out sum of prfill return values or not * * This function invokes @prfill on each blkg of @blkcg if pd for the * policy specified by @pol exists. @prfill is invoked with @sf, the * policy data and @data and the matching queue lock held. If @show_total * is %true, the sum of the return values from @prfill is printed with * "Total" label at the end. * * This is to be used to construct print functions for * cftype->read_seq_string method. */ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int), const struct blkcg_policy *pol, int data, bool show_total) { struct blkcg_gq *blkg; u64 total = 0; rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); if (blkcg_policy_enabled(blkg->q, pol)) total += prfill(sf, blkg->pd[pol->plid], data); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); if (show_total) seq_printf(sf, "Total %llu\n", (unsigned long long)total); } EXPORT_SYMBOL_GPL(blkcg_print_blkgs); /** * __blkg_prfill_u64 - prfill helper for a single u64 value * @sf: seq_file to print to * @pd: policy private data of interest * @v: value to print * * Print @v to @sf for the device assocaited with @pd. */ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v) { const char *dname = blkg_dev_name(pd->blkg); if (!dname) return 0; seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v); return v; } EXPORT_SYMBOL_GPL(__blkg_prfill_u64); /* Performs queue bypass and policy enabled checks then looks up blkg. */ static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg, const struct blkcg_policy *pol, struct request_queue *q) { WARN_ON_ONCE(!rcu_read_lock_held()); lockdep_assert_held(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) return ERR_PTR(-EOPNOTSUPP); return __blkg_lookup(blkcg, q, true /* update_hint */); } /** * blkcg_conf_open_bdev - parse and open bdev for per-blkg config update * @inputp: input string pointer * * Parse the device node prefix part, MAJ:MIN, of per-blkg config update * from @input and get and return the matching bdev. *@inputp is * updated to point past the device node prefix. Returns an ERR_PTR() * value on error. * * Use this function iff blkg_conf_prep() can't be used for some reason. */ struct block_device *blkcg_conf_open_bdev(char **inputp) { char *input = *inputp; unsigned int major, minor; struct block_device *bdev; int key_len; if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2) return ERR_PTR(-EINVAL); input += key_len; if (!isspace(*input)) return ERR_PTR(-EINVAL); input = skip_spaces(input); bdev = blkdev_get_no_open(MKDEV(major, minor)); if (!bdev) return ERR_PTR(-ENODEV); if (bdev_is_partition(bdev)) { blkdev_put_no_open(bdev); return ERR_PTR(-ENODEV); } *inputp = input; return bdev; } /** * blkg_conf_prep - parse and prepare for per-blkg config update * @blkcg: target block cgroup * @pol: target policy * @input: input string * @ctx: blkg_conf_ctx to be filled * * Parse per-blkg config update from @input and initialize @ctx with the * result. @ctx->blkg points to the blkg to be updated and @ctx->body the * part of @input following MAJ:MIN. This function returns with RCU read * lock and queue lock held and must be paired with blkg_conf_finish(). */ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx) __acquires(rcu) __acquires(&bdev->bd_disk->queue->queue_lock) { struct block_device *bdev; struct request_queue *q; struct blkcg_gq *blkg; int ret; bdev = blkcg_conf_open_bdev(&input); if (IS_ERR(bdev)) return PTR_ERR(bdev); q = bdev->bd_disk->queue; /* * blkcg_deactivate_policy() requires queue to be frozen, we can grab * q_usage_counter to prevent concurrent with blkcg_deactivate_policy(). */ ret = blk_queue_enter(q, 0); if (ret) goto fail; rcu_read_lock(); spin_lock_irq(&q->queue_lock); blkg = blkg_lookup_check(blkcg, pol, q); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); goto fail_unlock; } if (blkg) goto success; /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent; struct blkcg_gq *new_blkg; parent = blkcg_parent(blkcg); while (parent && !__blkg_lookup(parent, q, false)) { pos = parent; parent = blkcg_parent(parent); } /* Drop locks to do new blkg allocation with GFP_KERNEL. */ spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); new_blkg = blkg_alloc(pos, q, GFP_KERNEL); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto fail_exit_queue; } if (radix_tree_preload(GFP_KERNEL)) { blkg_free(new_blkg); ret = -ENOMEM; goto fail_exit_queue; } rcu_read_lock(); spin_lock_irq(&q->queue_lock); blkg = blkg_lookup_check(pos, pol, q); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); blkg_free(new_blkg); goto fail_preloaded; } if (blkg) { blkg_free(new_blkg); } else { blkg = blkg_create(pos, q, new_blkg); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); goto fail_preloaded; } } radix_tree_preload_end(); if (pos == blkcg) goto success; } success: blk_queue_exit(q); ctx->bdev = bdev; ctx->blkg = blkg; ctx->body = input; return 0; fail_preloaded: radix_tree_preload_end(); fail_unlock: spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); fail_exit_queue: blk_queue_exit(q); fail: blkdev_put_no_open(bdev); /* * If queue was bypassing, we should retry. Do so after a * short msleep(). It isn't strictly necessary but queue * can be bypassing for some time and it's always nice to * avoid busy looping. */ if (ret == -EBUSY) { msleep(10); ret = restart_syscall(); } return ret; } EXPORT_SYMBOL_GPL(blkg_conf_prep); /** * blkg_conf_finish - finish up per-blkg config update * @ctx: blkg_conf_ctx intiailized by blkg_conf_prep() * * Finish up after per-blkg config update. This function must be paired * with blkg_conf_prep(). */ void blkg_conf_finish(struct blkg_conf_ctx *ctx) __releases(&ctx->bdev->bd_disk->queue->queue_lock) __releases(rcu) { spin_unlock_irq(&ctx->bdev->bd_disk->queue->queue_lock); rcu_read_unlock(); blkdev_put_no_open(ctx->bdev); } EXPORT_SYMBOL_GPL(blkg_conf_finish); static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] = src->bytes[i]; dst->ios[i] = src->ios[i]; } } static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] += src->bytes[i]; dst->ios[i] += src->ios[i]; } } static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] -= src->bytes[i]; dst->ios[i] -= src->ios[i]; } } static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; /* Root-level stats are sourced from system-wide IO stats */ if (!cgroup_parent(css->cgroup)) return; rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { struct blkcg_gq *parent = blkg->parent; struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu); struct blkg_iostat cur, delta; unsigned long flags; unsigned int seq; /* fetch the current per-cpu values */ do { seq = u64_stats_fetch_begin(&bisc->sync); blkg_iostat_set(&cur, &bisc->cur); } while (u64_stats_fetch_retry(&bisc->sync, seq)); /* propagate percpu delta to global */ flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&delta, &cur); blkg_iostat_sub(&delta, &bisc->last); blkg_iostat_add(&blkg->iostat.cur, &delta); blkg_iostat_add(&bisc->last, &delta); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); /* propagate global delta to parent (unless that's root) */ if (parent && parent->parent) { flags = u64_stats_update_begin_irqsave(&parent->iostat.sync); blkg_iostat_set(&delta, &blkg->iostat.cur); blkg_iostat_sub(&delta, &blkg->iostat.last); blkg_iostat_add(&parent->iostat.cur, &delta); blkg_iostat_add(&blkg->iostat.last, &delta); u64_stats_update_end_irqrestore(&parent->iostat.sync, flags); } } rcu_read_unlock(); } /* * We source root cgroup stats from the system-wide stats to avoid * tracking the same information twice and incurring overhead when no * cgroups are defined. For that reason, cgroup_rstat_flush in * blkcg_print_stat does not actually fill out the iostat in the root * cgroup's blkcg_gq. * * However, we would like to re-use the printing code between the root and * non-root cgroups to the extent possible. For that reason, we simulate * flushing the root cgroup's stats by explicitly filling in the iostat * with disk level statistics. */ static void blkcg_fill_root_iostats(void) { struct class_dev_iter iter; struct device *dev; class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct block_device *bdev = dev_to_bdev(dev); struct blkcg_gq *blkg = blk_queue_root_blkg(bdev->bd_disk->queue); struct blkg_iostat tmp; int cpu; unsigned long flags; memset(&tmp, 0, sizeof(tmp)); for_each_possible_cpu(cpu) { struct disk_stats *cpu_dkstats; cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu); tmp.ios[BLKG_IOSTAT_READ] += cpu_dkstats->ios[STAT_READ]; tmp.ios[BLKG_IOSTAT_WRITE] += cpu_dkstats->ios[STAT_WRITE]; tmp.ios[BLKG_IOSTAT_DISCARD] += cpu_dkstats->ios[STAT_DISCARD]; // convert sectors to bytes tmp.bytes[BLKG_IOSTAT_READ] += cpu_dkstats->sectors[STAT_READ] << 9; tmp.bytes[BLKG_IOSTAT_WRITE] += cpu_dkstats->sectors[STAT_WRITE] << 9; tmp.bytes[BLKG_IOSTAT_DISCARD] += cpu_dkstats->sectors[STAT_DISCARD] << 9; } flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&blkg->iostat.cur, &tmp); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } class_dev_iter_exit(&iter); } static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) { struct blkg_iostat_set *bis = &blkg->iostat; u64 rbytes, wbytes, rios, wios, dbytes, dios; bool has_stats = false; const char *dname; unsigned seq; int i; if (!blkg->online) return; dname = blkg_dev_name(blkg); if (!dname) return; seq_printf(s, "%s ", dname); do { seq = u64_stats_fetch_begin(&bis->sync); rbytes = bis->cur.bytes[BLKG_IOSTAT_READ]; wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE]; dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD]; rios = bis->cur.ios[BLKG_IOSTAT_READ]; wios = bis->cur.ios[BLKG_IOSTAT_WRITE]; dios = bis->cur.ios[BLKG_IOSTAT_DISCARD]; } while (u64_stats_fetch_retry(&bis->sync, seq)); if (rbytes || wbytes || rios || wios) { has_stats = true; seq_printf(s, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", rbytes, wbytes, rios, wios, dbytes, dios); } if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { has_stats = true; seq_printf(s, " use_delay=%d delay_nsec=%llu", atomic_read(&blkg->use_delay), atomic64_read(&blkg->delay_nsec)); } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (!blkg->pd[i] || !pol->pd_stat_fn) continue; if (pol->pd_stat_fn(blkg->pd[i], s)) has_stats = true; } if (has_stats) seq_printf(s, "\n"); } static int blkcg_print_stat(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct blkcg_gq *blkg; if (!seq_css(sf)->parent) blkcg_fill_root_iostats(); else cgroup_rstat_flush(blkcg->css.cgroup); rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); blkcg_print_one_stat(blkg, sf); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); return 0; } static struct cftype blkcg_files[] = { { .name = "stat", .seq_show = blkcg_print_stat, }, { } /* terminate */ }; static struct cftype blkcg_legacy_files[] = { { .name = "reset_stats", .write_u64 = blkcg_reset_stats, }, { } /* terminate */ }; /* * blkcg destruction is a three-stage process. * * 1. Destruction starts. The blkcg_css_offline() callback is invoked * which offlines writeback. Here we tie the next stage of blkg destruction * to the completion of writeback associated with the blkcg. This lets us * avoid punting potentially large amounts of outstanding writeback to root * while maintaining any ongoing policies. The next stage is triggered when * the nr_cgwbs count goes to zero. * * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called * and handles the destruction of blkgs. Here the css reference held by * the blkg is put back eventually allowing blkcg_css_free() to be called. * This work may occur in cgwb_release_workfn() on the cgwb_release * workqueue. Any submitted ios that fail to get the blkg ref will be * punted to the root_blkg. * * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. * This finally frees the blkcg. */ /** * blkcg_css_offline - cgroup css_offline callback * @css: css of interest * * This function is called when @css is about to go away. Here the cgwbs are * offlined first and only once writeback associated with the blkcg has * finished do we start step 2 (see above). */ static void blkcg_css_offline(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); /* this prevents anyone from attaching or migrating to this blkcg */ wb_blkcg_offline(blkcg); /* put the base online pin allowing step 2 to be triggered */ blkcg_unpin_online(blkcg); } /** * blkcg_destroy_blkgs - responsible for shooting down blkgs * @blkcg: blkcg of interest * * blkgs should be removed while holding both q and blkcg locks. As blkcg lock * is nested inside q lock, this function performs reverse double lock dancing. * Destroying the blkgs releases the reference held on the blkcg's css allowing * blkcg_css_free to eventually be called. * * This is the blkcg counterpart of ioc_release_fn(). */ void blkcg_destroy_blkgs(struct blkcg *blkcg) { might_sleep(); spin_lock_irq(&blkcg->lock); while (!hlist_empty(&blkcg->blkg_list)) { struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first, struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; if (need_resched() || !spin_trylock(&q->queue_lock)) { /* * Given that the system can accumulate a huge number * of blkgs in pathological cases, check to see if we * need to rescheduling to avoid softlockup. */ spin_unlock_irq(&blkcg->lock); cond_resched(); spin_lock_irq(&blkcg->lock); continue; } blkg_destroy(blkg); spin_unlock(&q->queue_lock); } spin_unlock_irq(&blkcg->lock); } static void blkcg_css_free(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); int i; mutex_lock(&blkcg_pol_mutex); list_del(&blkcg->all_blkcgs_node); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); mutex_unlock(&blkcg_pol_mutex); kfree(blkcg); } static struct cgroup_subsys_state * blkcg_css_alloc(struct cgroup_subsys_state *parent_css) { struct blkcg *blkcg; struct cgroup_subsys_state *ret; int i; mutex_lock(&blkcg_pol_mutex); if (!parent_css) { blkcg = &blkcg_root; } else { blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL); if (!blkcg) { ret = ERR_PTR(-ENOMEM); goto unlock; } } for (i = 0; i < BLKCG_MAX_POLS ; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkcg_policy_data *cpd; /* * If the policy hasn't been attached yet, wait for it * to be attached before doing anything else. Otherwise, * check if the policy requires any specific per-cgroup * data: if it does, allocate and initialize it. */ if (!pol || !pol->cpd_alloc_fn) continue; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) { ret = ERR_PTR(-ENOMEM); goto free_pd_blkcg; } blkcg->cpd[i] = cpd; cpd->blkcg = blkcg; cpd->plid = i; if (pol->cpd_init_fn) pol->cpd_init_fn(cpd); } spin_lock_init(&blkcg->lock); refcount_set(&blkcg->online_pin, 1); INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN); INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); #endif list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs); mutex_unlock(&blkcg_pol_mutex); return &blkcg->css; free_pd_blkcg: for (i--; i >= 0; i--) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); if (blkcg != &blkcg_root) kfree(blkcg); unlock: mutex_unlock(&blkcg_pol_mutex); return ret; } static int blkcg_css_online(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg *parent = blkcg_parent(blkcg); /* * blkcg_pin_online() is used to delay blkcg offline so that blkgs * don't go offline while cgwbs are still active on them. Pin the * parent so that offline always happens towards the root. */ if (parent) blkcg_pin_online(parent); return 0; } /** * blkcg_init_queue - initialize blkcg part of request queue * @q: request_queue to initialize * * Called from blk_alloc_queue(). Responsible for initializing blkcg * part of new request_queue @q. * * RETURNS: * 0 on success, -errno on failure. */ int blkcg_init_queue(struct request_queue *q) { struct blkcg_gq *new_blkg, *blkg; bool preloaded; int ret; new_blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL); if (!new_blkg) return -ENOMEM; preloaded = !radix_tree_preload(GFP_KERNEL); /* Make sure the root blkg exists. */ rcu_read_lock(); spin_lock_irq(&q->queue_lock); blkg = blkg_create(&blkcg_root, q, new_blkg); if (IS_ERR(blkg)) goto err_unlock; q->root_blkg = blkg; spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); if (preloaded) radix_tree_preload_end(); ret = blk_ioprio_init(q); if (ret) goto err_destroy_all; ret = blk_throtl_init(q); if (ret) goto err_destroy_all; ret = blk_iolatency_init(q); if (ret) { blk_throtl_exit(q); blk_ioprio_exit(q); goto err_destroy_all; } return 0; err_destroy_all: blkg_destroy_all(q); return ret; err_unlock: spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); if (preloaded) radix_tree_preload_end(); return PTR_ERR(blkg); } /** * blkcg_exit_queue - exit and release blkcg part of request_queue * @q: request_queue being released * * Called from blk_exit_queue(). Responsible for exiting blkcg part. */ void blkcg_exit_queue(struct request_queue *q) { blkg_destroy_all(q); blk_throtl_exit(q); } static void blkcg_bind(struct cgroup_subsys_state *root_css) { int i; mutex_lock(&blkcg_pol_mutex); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkcg *blkcg; if (!pol || !pol->cpd_bind_fn) continue; list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) if (blkcg->cpd[pol->plid]) pol->cpd_bind_fn(blkcg->cpd[pol->plid]); } mutex_unlock(&blkcg_pol_mutex); } static void blkcg_exit(struct task_struct *tsk) { if (tsk->throttle_queue) blk_put_queue(tsk->throttle_queue); tsk->throttle_queue = NULL; } struct cgroup_subsys io_cgrp_subsys = { .css_alloc = blkcg_css_alloc, .css_online = blkcg_css_online, .css_offline = blkcg_css_offline, .css_free = blkcg_css_free, .css_rstat_flush = blkcg_rstat_flush, .bind = blkcg_bind, .dfl_cftypes = blkcg_files, .legacy_cftypes = blkcg_legacy_files, .legacy_name = "blkio", .exit = blkcg_exit, #ifdef CONFIG_MEMCG /* * This ensures that, if available, memcg is automatically enabled * together on the default hierarchy so that the owner cgroup can * be retrieved from writeback pages. */ .depends_on = 1 << memory_cgrp_id, #endif }; EXPORT_SYMBOL_GPL(io_cgrp_subsys); /** * blkcg_activate_policy - activate a blkcg policy on a request_queue * @q: request_queue of interest * @pol: blkcg policy to activate * * Activate @pol on @q. Requires %GFP_KERNEL context. @q goes through * bypass mode to populate its blkgs with policy_data for @pol. * * Activation happens with @q bypassed, so nobody would be accessing blkgs * from IO path. Update of each blkg is protected by both queue and blkcg * locks so that holding either lock and testing blkcg_policy_enabled() is * always enough for dereferencing policy data. * * The caller is responsible for synchronizing [de]activations and policy * [un]registerations. Returns 0 on success, -errno on failure. */ int blkcg_activate_policy(struct request_queue *q, const struct blkcg_policy *pol) { struct blkg_policy_data *pd_prealloc = NULL; struct blkcg_gq *blkg, *pinned_blkg = NULL; int ret; if (blkcg_policy_enabled(q, pol)) return 0; if (queue_is_mq(q)) blk_mq_freeze_queue(q); retry: spin_lock_irq(&q->queue_lock); /* blkg_list is pushed at the head, reverse walk to allocate parents first */ list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) { struct blkg_policy_data *pd; if (blkg->pd[pol->plid]) continue; /* If prealloc matches, use it; otherwise try GFP_NOWAIT */ if (blkg == pinned_blkg) { pd = pd_prealloc; pd_prealloc = NULL; } else { pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q, blkg->blkcg); } if (!pd) { /* * GFP_NOWAIT failed. Free the existing one and * prealloc for @blkg w/ GFP_KERNEL. */ if (pinned_blkg) blkg_put(pinned_blkg); blkg_get(blkg); pinned_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q, blkg->blkcg); if (pd_prealloc) goto retry; else goto enomem; } blkg->pd[pol->plid] = pd; pd->blkg = blkg; pd->plid = pol->plid; } /* all allocated, init in the same order */ if (pol->pd_init_fn) list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) pol->pd_init_fn(blkg->pd[pol->plid]); if (pol->pd_online_fn) list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) pol->pd_online_fn(blkg->pd[pol->plid]); __set_bit(pol->plid, q->blkcg_pols); ret = 0; spin_unlock_irq(&q->queue_lock); out: if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); if (pinned_blkg) blkg_put(pinned_blkg); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); return ret; enomem: /* alloc failed, nothing's initialized yet, free everything */ spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); ret = -ENOMEM; goto out; } EXPORT_SYMBOL_GPL(blkcg_activate_policy); /** * blkcg_deactivate_policy - deactivate a blkcg policy on a request_queue * @q: request_queue of interest * @pol: blkcg policy to deactivate * * Deactivate @pol on @q. Follows the same synchronization rules as * blkcg_activate_policy(). */ void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { struct blkcg_gq *blkg; if (!blkcg_policy_enabled(q, pol)) return; if (queue_is_mq(q)) blk_mq_freeze_queue(q); spin_lock_irq(&q->queue_lock); __clear_bit(pol->plid, q->blkcg_pols); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); } EXPORT_SYMBOL_GPL(blkcg_deactivate_policy); /** * blkcg_policy_register - register a blkcg policy * @pol: blkcg policy to register * * Register @pol with blkcg core. Might sleep and @pol may be modified on * successful registration. Returns 0 on success and -errno on failure. */ int blkcg_policy_register(struct blkcg_policy *pol) { struct blkcg *blkcg; int i, ret; mutex_lock(&blkcg_pol_register_mutex); mutex_lock(&blkcg_pol_mutex); /* find an empty slot */ ret = -ENOSPC; for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; if (i >= BLKCG_MAX_POLS) { pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); goto err_unlock; } /* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || (!pol->pd_alloc_fn ^ !pol->pd_free_fn)) goto err_unlock; /* register @pol */ pol->plid = i; blkcg_policy[pol->plid] = pol; /* allocate and install cpd's */ if (pol->cpd_alloc_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { struct blkcg_policy_data *cpd; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) goto err_free_cpds; blkcg->cpd[pol->plid] = cpd; cpd->blkcg = blkcg; cpd->plid = pol->plid; if (pol->cpd_init_fn) pol->cpd_init_fn(cpd); } } mutex_unlock(&blkcg_pol_mutex); /* everything is in place, add intf files for the new policy */ if (pol->dfl_cftypes) WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys, pol->dfl_cftypes)); if (pol->legacy_cftypes) WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys, pol->legacy_cftypes)); mutex_unlock(&blkcg_pol_register_mutex); return 0; err_free_cpds: if (pol->cpd_free_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { if (blkcg->cpd[pol->plid]) { pol->cpd_free_fn(blkcg->cpd[pol->plid]); blkcg->cpd[pol->plid] = NULL; } } } blkcg_policy[pol->plid] = NULL; err_unlock: mutex_unlock(&blkcg_pol_mutex); mutex_unlock(&blkcg_pol_register_mutex); return ret; } EXPORT_SYMBOL_GPL(blkcg_policy_register); /** * blkcg_policy_unregister - unregister a blkcg policy * @pol: blkcg policy to unregister * * Undo blkcg_policy_register(@pol). Might sleep. */ void blkcg_policy_unregister(struct blkcg_policy *pol) { struct blkcg *blkcg; mutex_lock(&blkcg_pol_register_mutex); if (WARN_ON(blkcg_policy[pol->plid] != pol)) goto out_unlock; /* kill the intf files first */ if (pol->dfl_cftypes) cgroup_rm_cftypes(pol->dfl_cftypes); if (pol->legacy_cftypes) cgroup_rm_cftypes(pol->legacy_cftypes); /* remove cpds and unregister */ mutex_lock(&blkcg_pol_mutex); if (pol->cpd_free_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { if (blkcg->cpd[pol->plid]) { pol->cpd_free_fn(blkcg->cpd[pol->plid]); blkcg->cpd[pol->plid] = NULL; } } } blkcg_policy[pol->plid] = NULL; mutex_unlock(&blkcg_pol_mutex); out_unlock: mutex_unlock(&blkcg_pol_register_mutex); } EXPORT_SYMBOL_GPL(blkcg_policy_unregister); bool __blkcg_punt_bio_submit(struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; /* consume the flag first */ bio->bi_opf &= ~REQ_CGROUP_PUNT; /* never bounce for the root cgroup */ if (!blkg->parent) return false; spin_lock_bh(&blkg->async_bio_lock); bio_list_add(&blkg->async_bios, bio); spin_unlock_bh(&blkg->async_bio_lock); queue_work(blkcg_punt_bio_wq, &blkg->async_bio_work); return true; } /* * Scale the accumulated delay based on how long it has been since we updated * the delay. We only call this when we are adding delay, in case it's been a * while since we added delay, and when we are checking to see if we need to * delay a task, to account for any delays that may have occurred. */ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now) { u64 old = atomic64_read(&blkg->delay_start); /* negative use_delay means no scaling, see blkcg_set_delay() */ if (atomic_read(&blkg->use_delay) < 0) return; /* * We only want to scale down every second. The idea here is that we * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain * time window. We only want to throttle tasks for recent delay that * has occurred, in 1 second time windows since that's the maximum * things can be throttled. We save the current delay window in * blkg->last_delay so we know what amount is still left to be charged * to the blkg from this point onward. blkg->last_use keeps track of * the use_delay counter. The idea is if we're unthrottling the blkg we * are ok with whatever is happening now, and we can take away more of * the accumulated delay as we've already throttled enough that * everybody is happy with their IO latencies. */ if (time_before64(old + NSEC_PER_SEC, now) && atomic64_cmpxchg(&blkg->delay_start, old, now) == old) { u64 cur = atomic64_read(&blkg->delay_nsec); u64 sub = min_t(u64, blkg->last_delay, now - old); int cur_use = atomic_read(&blkg->use_delay); /* * We've been unthrottled, subtract a larger chunk of our * accumulated delay. */ if (cur_use < blkg->last_use) sub = max_t(u64, sub, blkg->last_delay >> 1); /* * This shouldn't happen, but handle it anyway. Our delay_nsec * should only ever be growing except here where we subtract out * min(last_delay, 1 second), but lord knows bugs happen and I'd * rather not end up with negative numbers. */ if (unlikely(cur < sub)) { atomic64_set(&blkg->delay_nsec, 0); blkg->last_delay = 0; } else { atomic64_sub(sub, &blkg->delay_nsec); blkg->last_delay = cur - sub; } blkg->last_use = cur_use; } } /* * This is called when we want to actually walk up the hierarchy and check to * see if we need to throttle, and then actually throttle if there is some * accumulated delay. This should only be called upon return to user space so * we're not holding some lock that would induce a priority inversion. */ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay) { unsigned long pflags; bool clamp; u64 now = ktime_to_ns(ktime_get()); u64 exp; u64 delay_nsec = 0; int tok; while (blkg->parent) { int use_delay = atomic_read(&blkg->use_delay); if (use_delay) { u64 this_delay; blkcg_scale_delay(blkg, now); this_delay = atomic64_read(&blkg->delay_nsec); if (this_delay > delay_nsec) { delay_nsec = this_delay; clamp = use_delay > 0; } } blkg = blkg->parent; } if (!delay_nsec) return; /* * Let's not sleep for all eternity if we've amassed a huge delay. * Swapping or metadata IO can accumulate 10's of seconds worth of * delay, and we want userspace to be able to do _something_ so cap the * delays at 0.25s. If there's 10's of seconds worth of delay then the * tasks will be delayed for 0.25 second for every syscall. If * blkcg_set_delay() was used as indicated by negative use_delay, the * caller is responsible for regulating the range. */ if (clamp) delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC); if (use_memdelay) psi_memstall_enter(&pflags); exp = ktime_add_ns(now, delay_nsec); tok = io_schedule_prepare(); do { __set_current_state(TASK_KILLABLE); if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS)) break; } while (!fatal_signal_pending(current)); io_schedule_finish(tok); if (use_memdelay) psi_memstall_leave(&pflags); } /** * blkcg_maybe_throttle_current - throttle the current task if it has been marked * * This is only called if we've been marked with set_notify_resume(). Obviously * we can be set_notify_resume() for reasons other than blkcg throttling, so we * check to see if current->throttle_queue is set and if not this doesn't do * anything. This should only ever be called by the resume code, it's not meant * to be called by people willy-nilly as it will actually do the work to * throttle the task if it is setup for throttling. */ void blkcg_maybe_throttle_current(void) { struct request_queue *q = current->throttle_queue; struct cgroup_subsys_state *css; struct blkcg *blkcg; struct blkcg_gq *blkg; bool use_memdelay = current->use_memdelay; if (!q) return; current->throttle_queue = NULL; current->use_memdelay = false; rcu_read_lock(); css = kthread_blkcg(); if (css) blkcg = css_to_blkcg(css); else blkcg = css_to_blkcg(task_css(current, io_cgrp_id)); if (!blkcg) goto out; blkg = blkg_lookup(blkcg, q); if (!blkg) goto out; if (!blkg_tryget(blkg)) goto out; rcu_read_unlock(); blkcg_maybe_throttle_blkg(blkg, use_memdelay); blkg_put(blkg); blk_put_queue(q); return; out: rcu_read_unlock(); blk_put_queue(q); } /** * blkcg_schedule_throttle - this task needs to check for throttling * @q: the request queue IO was submitted on * @use_memdelay: do we charge this to memory delay for PSI * * This is called by the IO controller when we know there's delay accumulated * for the blkg for this task. We do not pass the blkg because there are places * we call this that may not have that information, the swapping code for * instance will only have a request_queue at that point. This set's the * notify_resume for the task to check and see if it requires throttling before * returning to user space. * * We will only schedule once per syscall. You can call this over and over * again and it will only do the check once upon return to user space, and only * throttle once. If the task needs to be throttled again it'll need to be * re-set at the next time we see the task. */ void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { if (unlikely(current->flags & PF_KTHREAD)) return; if (current->throttle_queue != q) { if (!blk_get_queue(q)) return; if (current->throttle_queue) blk_put_queue(current->throttle_queue); current->throttle_queue = q; } if (use_memdelay) current->use_memdelay = use_memdelay; set_notify_resume(current); } /** * blkcg_add_delay - add delay to this blkg * @blkg: blkg of interest * @now: the current time in nanoseconds * @delta: how many nanoseconds of delay to add * * Charge @delta to the blkg's current delay accumulation. This is used to * throttle tasks if an IO controller thinks we need more throttling. */ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta) { if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) return; blkcg_scale_delay(blkg, now); atomic64_add(delta, &blkg->delay_nsec); } /** * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @bio: target bio * @css: target css * * As the failure mode here is to walk up the blkg tree, this ensure that the * blkg->parent pointers are always valid. This returns the blkg that it ended * up taking a reference on or %NULL if no reference was taken. */ static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio, struct cgroup_subsys_state *css) { struct blkcg_gq *blkg, *ret_blkg = NULL; rcu_read_lock(); blkg = blkg_lookup_create(css_to_blkcg(css), bio->bi_bdev->bd_disk->queue); while (blkg) { if (blkg_tryget(blkg)) { ret_blkg = blkg; break; } blkg = blkg->parent; } rcu_read_unlock(); return ret_blkg; } /** * bio_associate_blkg_from_css - associate a bio with a specified css * @bio: target bio * @css: target css * * Associate @bio with the blkg found by combining the css's blkg and the * request_queue of the @bio. An association failure is handled by walking up * the blkg tree. Therefore, the blkg associated can be anything between @blkg * and q->root_blkg. This situation only happens when a cgroup is dying and * then the remaining bios will spill to the closest alive blkg. * * A reference will be taken on the blkg and will be released when @bio is * freed. */ void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { if (bio->bi_blkg) blkg_put(bio->bi_blkg); if (css && css->parent) { bio->bi_blkg = blkg_tryget_closest(bio, css); } else { blkg_get(bio->bi_bdev->bd_disk->queue->root_blkg); bio->bi_blkg = bio->bi_bdev->bd_disk->queue->root_blkg; } } EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); /** * bio_associate_blkg - associate a bio with a blkg * @bio: target bio * * Associate @bio with the blkg found from the bio's css and request_queue. * If one is not found, bio_lookup_blkg() creates the blkg. If a blkg is * already associated, the css is reused and association redone as the * request_queue may have changed. */ void bio_associate_blkg(struct bio *bio) { struct cgroup_subsys_state *css; rcu_read_lock(); if (bio->bi_blkg) css = &bio_blkcg(bio)->css; else css = blkcg_css(); bio_associate_blkg_from_css(bio, css); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(bio_associate_blkg); /** * bio_clone_blkg_association - clone blkg association from src to dst bio * @dst: destination bio * @src: source bio */ void bio_clone_blkg_association(struct bio *dst, struct bio *src) { if (src->bi_blkg) bio_associate_blkg_from_css(dst, &bio_blkcg(src)->css); } EXPORT_SYMBOL_GPL(bio_clone_blkg_association); static int blk_cgroup_io_type(struct bio *bio) { if (op_is_discard(bio->bi_opf)) return BLKG_IOSTAT_DISCARD; if (op_is_write(bio->bi_opf)) return BLKG_IOSTAT_WRITE; return BLKG_IOSTAT_READ; } void blk_cgroup_bio_start(struct bio *bio) { int rwd = blk_cgroup_io_type(bio), cpu; struct blkg_iostat_set *bis; unsigned long flags; cpu = get_cpu(); bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu); flags = u64_stats_update_begin_irqsave(&bis->sync); /* * If the bio is flagged with BIO_CGROUP_ACCT it means this is a split * bio and we would have already accounted for the size of the bio. */ if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { bio_set_flag(bio, BIO_CGROUP_ACCT); bis->cur.bytes[rwd] += bio->bi_iter.bi_size; } bis->cur.ios[rwd]++; u64_stats_update_end_irqrestore(&bis->sync, flags); if (cgroup_subsys_on_dfl(io_cgrp_subsys)) cgroup_rstat_updated(bio->bi_blkg->blkcg->css.cgroup, cpu); put_cpu(); } static int __init blkcg_init(void) { blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio", WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND | WQ_SYSFS, 0); if (!blkcg_punt_bio_wq) return -ENOMEM; return 0; } subsys_initcall(blkcg_init); module_param(blkcg_debug_stats, bool, 0644); MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not"); |
| 383 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/signalfd.h * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * */ #ifndef _LINUX_SIGNALFD_H #define _LINUX_SIGNALFD_H #include <uapi/linux/signalfd.h> #include <linux/sched/signal.h> #ifdef CONFIG_SIGNALFD /* * Deliver the signal to listening signalfd. */ static inline void signalfd_notify(struct task_struct *tsk, int sig) { if (unlikely(waitqueue_active(&tsk->sighand->signalfd_wqh))) wake_up(&tsk->sighand->signalfd_wqh); } extern void signalfd_cleanup(struct sighand_struct *sighand); #else /* CONFIG_SIGNALFD */ static inline void signalfd_notify(struct task_struct *tsk, int sig) { } static inline void signalfd_cleanup(struct sighand_struct *sighand) { } #endif /* CONFIG_SIGNALFD */ #endif /* _LINUX_SIGNALFD_H */ |
| 237 237 237 237 237 237 222 222 221 222 221 222 222 222 237 237 237 237 819 819 616 616 616 845 798 6 115 550 129 532 237 237 17 510 239 4 236 239 239 514 4 510 200 4 197 37 37 527 281 514 514 527 527 526 527 4 718 719 562 239 719 719 223 25 199 223 223 265 558 223 265 483 248 17 1 4 260 1 261 261 3 265 524 4 4 4 4 809 814 299 527 8 810 810 810 5 611 615 616 235 383 615 616 884 884 616 616 616 883 616 616 884 616 38 38 89 151 141 11 121 88 38 120 89 37 88 38 1934 1934 1933 481 481 481 481 481 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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 running seqcount 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 val, res; unsigned int i; if (is_vlan_dev(dev)) dev = vlan_dev_real_dev(dev); else if (netif_is_macvlan(dev)) dev = macvlan_dev_real_dev(dev); res = netdev_get_tx_queue(dev, 0)->trans_start; for (i = 1; i < dev->num_tx_queues; i++) { val = 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 dev_watchdog(struct timer_list *t) { struct net_device *dev = from_timer(dev, t, watchdog_timer); netif_tx_lock(dev); 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 = txq->trans_start; if (netif_xmit_stopped(txq) && time_after(jiffies, (trans_start + dev->watchdog_timeo))) { some_queue_timedout = 1; txq->trans_timeout++; break; } } if (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); dev->netdev_ops->ndo_tx_timeout(dev, i); } if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + dev->watchdog_timeo))) dev_hold(dev); } } netif_tx_unlock(dev); dev_put(dev); } 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))) dev_hold(dev); } } 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)) dev_put(dev); 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, .running = SEQCNT_ZERO(noop_qdisc.running), .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; static struct lock_class_key qdisc_running_key; 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); qdisc_skb_head_init(&sch->q); spin_lock_init(&sch->q.lock); if (ops->static_flags & TCQ_F_CPUSTATS) { sch->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); 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); seqcount_init(&sch->running); lockdep_set_class(&sch->running, dev->qdisc_running_key ?: &qdisc_running_key); sch->ops = ops; sch->flags = ops->static_flags; sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; dev_hold(dev); 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; struct sk_buff *skb, *tmp; trace_qdisc_reset(qdisc); if (ops->reset) ops->reset(qdisc); skb_queue_walk_safe(&qdisc->gso_skb, skb, tmp) { __skb_unlink(skb, &qdisc->gso_skb); kfree_skb_list(skb); } skb_queue_walk_safe(&qdisc->skb_bad_txq, skb, tmp) { __skb_unlink(skb, &qdisc->skb_bad_txq); kfree_skb_list(skb); } 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); dev_put(qdisc_dev(qdisc)); 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) { 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); } 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); static void mini_qdisc_rcu_func(struct rcu_head *head) { } 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); /* Wait for flying RCU callback before it is freed. */ rcu_barrier(); return; } miniq = !miniq_old || miniq_old == &miniqp->miniq2 ? &miniqp->miniq1 : &miniqp->miniq2; /* We need to make sure that readers won't see the miniq * we are about to modify. So wait until previous call_rcu callback * is done. */ rcu_barrier(); miniq->filter_list = tp_head; rcu_assign_pointer(*miniqp->p_miniq, miniq); if (miniq_old) /* This is counterpart of the rcu barriers above. We need to * block potential new user of miniq_old until all readers * are not seeing it. */ call_rcu(&miniq_old->rcu, mini_qdisc_rcu_func); } 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->p_miniq = p_miniq; } EXPORT_SYMBOL(mini_qdisc_pair_init); |
| 208 202 1 2 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 | // SPDX-License-Identifier: GPL-2.0-only /* * Support Intel/AMD RAPL energy consumption counters * Copyright (C) 2013 Google, Inc., Stephane Eranian * * Intel RAPL interface is specified in the IA-32 Manual Vol3b * section 14.7.1 (September 2013) * * AMD RAPL interface for Fam17h is described in the public PPR: * https://bugzilla.kernel.org/show_bug.cgi?id=206537 * * RAPL provides more controls than just reporting energy consumption * however here we only expose the 3 energy consumption free running * counters (pp0, pkg, dram). * * Each of those counters increments in a power unit defined by the * RAPL_POWER_UNIT MSR. On SandyBridge, this unit is 1/(2^16) Joules * but it can vary. * * Counter to rapl events mappings: * * pp0 counter: consumption of all physical cores (power plane 0) * event: rapl_energy_cores * perf code: 0x1 * * pkg counter: consumption of the whole processor package * event: rapl_energy_pkg * perf code: 0x2 * * dram counter: consumption of the dram domain (servers only) * event: rapl_energy_dram * perf code: 0x3 * * gpu counter: consumption of the builtin-gpu domain (client only) * event: rapl_energy_gpu * perf code: 0x4 * * psys counter: consumption of the builtin-psys domain (client only) * event: rapl_energy_psys * perf code: 0x5 * * We manage those counters as free running (read-only). They may be * use simultaneously by other tools, such as turbostat. * * The events only support system-wide mode counting. There is no * sampling support because it does not make sense and is not * supported by the RAPL hardware. * * Because we want to avoid floating-point operations in the kernel, * the events are all reported in fixed point arithmetic (32.32). * Tools must adjust the counts to convert them to Watts using * the duration of the measurement. Tools may use a function such as * ldexp(raw_count, -32); */ #define pr_fmt(fmt) "RAPL PMU: " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/perf_event.h> #include <linux/nospec.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include "perf_event.h" #include "probe.h" MODULE_LICENSE("GPL"); /* * RAPL energy status counters */ enum perf_rapl_events { PERF_RAPL_PP0 = 0, /* all cores */ PERF_RAPL_PKG, /* entire package */ PERF_RAPL_RAM, /* DRAM */ PERF_RAPL_PP1, /* gpu */ PERF_RAPL_PSYS, /* psys */ PERF_RAPL_MAX, NR_RAPL_DOMAINS = PERF_RAPL_MAX, }; static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { "pp0-core", "package", "dram", "pp1-gpu", "psys", }; /* * event code: LSB 8 bits, passed in attr->config * any other bit is reserved */ #define RAPL_EVENT_MASK 0xFFULL #define RAPL_CNTR_WIDTH 32 #define RAPL_EVENT_ATTR_STR(_name, v, str) \ static struct perf_pmu_events_attr event_attr_##v = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = str, \ }; struct rapl_pmu { raw_spinlock_t lock; int n_active; int cpu; struct list_head active_list; struct pmu *pmu; ktime_t timer_interval; struct hrtimer hrtimer; }; struct rapl_pmus { struct pmu pmu; unsigned int maxdie; struct rapl_pmu *pmus[]; }; enum rapl_unit_quirk { RAPL_UNIT_QUIRK_NONE, RAPL_UNIT_QUIRK_INTEL_HSW, RAPL_UNIT_QUIRK_INTEL_SPR, }; struct rapl_model { struct perf_msr *rapl_msrs; unsigned long events; unsigned int msr_power_unit; enum rapl_unit_quirk unit_quirk; }; /* 1/2^hw_unit Joule */ static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly; static struct rapl_pmus *rapl_pmus; static cpumask_t rapl_cpu_mask; static unsigned int rapl_cntr_mask; static u64 rapl_timer_ms; static struct perf_msr *rapl_msrs; static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) { unsigned int dieid = topology_logical_die_id(cpu); /* * The unsigned check also catches the '-1' return value for non * existent mappings in the topology map. */ return dieid < rapl_pmus->maxdie ? rapl_pmus->pmus[dieid] : NULL; } static inline u64 rapl_read_counter(struct perf_event *event) { u64 raw; rdmsrl(event->hw.event_base, raw); return raw; } static inline u64 rapl_scale(u64 v, int cfg) { if (cfg > NR_RAPL_DOMAINS) { pr_warn("Invalid domain %d, failed to scale data\n", cfg); return v; } /* * scale delta to smallest unit (1/2^32) * users must then scale back: count * 1/(1e9*2^32) to get Joules * or use ldexp(count, -32). * Watts = Joules/Time delta */ return v << (32 - rapl_hw_unit[cfg - 1]); } static u64 rapl_event_update(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; u64 prev_raw_count, new_raw_count; s64 delta, sdelta; int shift = RAPL_CNTR_WIDTH; again: prev_raw_count = local64_read(&hwc->prev_count); rdmsrl(event->hw.event_base, new_raw_count); if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) { cpu_relax(); goto again; } /* * Now we have the new raw value and have updated the prev * timestamp already. We can now calculate the elapsed delta * (event-)time and add that to the generic event. * * Careful, not all hw sign-extends above the physical width * of the count. */ delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; sdelta = rapl_scale(delta, event->hw.config); local64_add(sdelta, &event->count); return new_raw_count; } static void rapl_start_hrtimer(struct rapl_pmu *pmu) { hrtimer_start(&pmu->hrtimer, pmu->timer_interval, HRTIMER_MODE_REL_PINNED); } static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer) { struct rapl_pmu *pmu = container_of(hrtimer, struct rapl_pmu, hrtimer); struct perf_event *event; unsigned long flags; if (!pmu->n_active) return HRTIMER_NORESTART; raw_spin_lock_irqsave(&pmu->lock, flags); list_for_each_entry(event, &pmu->active_list, active_entry) rapl_event_update(event); raw_spin_unlock_irqrestore(&pmu->lock, flags); hrtimer_forward_now(hrtimer, pmu->timer_interval); return HRTIMER_RESTART; } static void rapl_hrtimer_init(struct rapl_pmu *pmu) { struct hrtimer *hr = &pmu->hrtimer; hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hr->function = rapl_hrtimer_handle; } static void __rapl_pmu_event_start(struct rapl_pmu *pmu, struct perf_event *event) { if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) return; event->hw.state = 0; list_add_tail(&event->active_entry, &pmu->active_list); local64_set(&event->hw.prev_count, rapl_read_counter(event)); pmu->n_active++; if (pmu->n_active == 1) rapl_start_hrtimer(pmu); } static void rapl_pmu_event_start(struct perf_event *event, int mode) { struct rapl_pmu *pmu = event->pmu_private; unsigned long flags; raw_spin_lock_irqsave(&pmu->lock, flags); __rapl_pmu_event_start(pmu, event); raw_spin_unlock_irqrestore(&pmu->lock, flags); } static void rapl_pmu_event_stop(struct perf_event *event, int mode) { struct rapl_pmu *pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; raw_spin_lock_irqsave(&pmu->lock, flags); /* mark event as deactivated and stopped */ if (!(hwc->state & PERF_HES_STOPPED)) { WARN_ON_ONCE(pmu->n_active <= 0); pmu->n_active--; if (pmu->n_active == 0) hrtimer_cancel(&pmu->hrtimer); list_del(&event->active_entry); WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; } /* check if update of sw counter is necessary */ if ((mode & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { /* * Drain the remaining delta count out of a event * that we are disabling: */ rapl_event_update(event); hwc->state |= PERF_HES_UPTODATE; } raw_spin_unlock_irqrestore(&pmu->lock, flags); } static int rapl_pmu_event_add(struct perf_event *event, int mode) { struct rapl_pmu *pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; raw_spin_lock_irqsave(&pmu->lock, flags); hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; if (mode & PERF_EF_START) __rapl_pmu_event_start(pmu, event); raw_spin_unlock_irqrestore(&pmu->lock, flags); return 0; } static void rapl_pmu_event_del(struct perf_event *event, int flags) { rapl_pmu_event_stop(event, PERF_EF_UPDATE); } static int rapl_pmu_event_init(struct perf_event *event) { u64 cfg = event->attr.config & RAPL_EVENT_MASK; int bit, ret = 0; struct rapl_pmu *pmu; /* only look at RAPL events */ if (event->attr.type != rapl_pmus->pmu.type) return -ENOENT; /* check only supported bits are set */ if (event->attr.config & ~RAPL_EVENT_MASK) return -EINVAL; if (event->cpu < 0) return -EINVAL; event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG; if (!cfg || cfg >= NR_RAPL_DOMAINS + 1) return -EINVAL; cfg = array_index_nospec((long)cfg, NR_RAPL_DOMAINS + 1); bit = cfg - 1; /* check event supported */ if (!(rapl_cntr_mask & (1 << bit))) return -EINVAL; /* unsupported modes and filters */ if (event->attr.sample_period) /* no sampling */ return -EINVAL; /* must be done before validate_group */ pmu = cpu_to_rapl_pmu(event->cpu); if (!pmu) return -EINVAL; event->cpu = pmu->cpu; event->pmu_private = pmu; event->hw.event_base = rapl_msrs[bit].msr; event->hw.config = cfg; event->hw.idx = bit; return ret; } static void rapl_pmu_event_read(struct perf_event *event) { rapl_event_update(event); } static ssize_t rapl_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf) { return cpumap_print_to_pagebuf(true, buf, &rapl_cpu_mask); } static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL); static struct attribute *rapl_pmu_attrs[] = { &dev_attr_cpumask.attr, NULL, }; static struct attribute_group rapl_pmu_attr_group = { .attrs = rapl_pmu_attrs, }; RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); RAPL_EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04"); RAPL_EVENT_ATTR_STR(energy-psys, rapl_psys, "event=0x05"); RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-psys.unit, rapl_psys_unit, "Joules"); /* * we compute in 0.23 nJ increments regardless of MSR */ RAPL_EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10"); /* * There are no default events, but we need to create * "events" group (with empty attrs) before updating * it with detected events. */ static struct attribute *attrs_empty[] = { NULL, }; static struct attribute_group rapl_pmu_events_group = { .name = "events", .attrs = attrs_empty, }; PMU_FORMAT_ATTR(event, "config:0-7"); static struct attribute *rapl_formats_attr[] = { &format_attr_event.attr, NULL, }; static struct attribute_group rapl_pmu_format_group = { .name = "format", .attrs = rapl_formats_attr, }; static const struct attribute_group *rapl_attr_groups[] = { &rapl_pmu_attr_group, &rapl_pmu_format_group, &rapl_pmu_events_group, NULL, }; static struct attribute *rapl_events_cores[] = { EVENT_PTR(rapl_cores), EVENT_PTR(rapl_cores_unit), EVENT_PTR(rapl_cores_scale), NULL, }; static struct attribute_group rapl_events_cores_group = { .name = "events", .attrs = rapl_events_cores, }; static struct attribute *rapl_events_pkg[] = { EVENT_PTR(rapl_pkg), EVENT_PTR(rapl_pkg_unit), EVENT_PTR(rapl_pkg_scale), NULL, }; static struct attribute_group rapl_events_pkg_group = { .name = "events", .attrs = rapl_events_pkg, }; static struct attribute *rapl_events_ram[] = { EVENT_PTR(rapl_ram), EVENT_PTR(rapl_ram_unit), EVENT_PTR(rapl_ram_scale), NULL, }; static struct attribute_group rapl_events_ram_group = { .name = "events", .attrs = rapl_events_ram, }; static struct attribute *rapl_events_gpu[] = { EVENT_PTR(rapl_gpu), EVENT_PTR(rapl_gpu_unit), EVENT_PTR(rapl_gpu_scale), NULL, }; static struct attribute_group rapl_events_gpu_group = { .name = "events", .attrs = rapl_events_gpu, }; static struct attribute *rapl_events_psys[] = { EVENT_PTR(rapl_psys), EVENT_PTR(rapl_psys_unit), EVENT_PTR(rapl_psys_scale), NULL, }; static struct attribute_group rapl_events_psys_group = { .name = "events", .attrs = rapl_events_psys, }; static bool test_msr(int idx, void *data) { return test_bit(idx, (unsigned long *) data); } /* Only lower 32bits of the MSR represents the energy counter */ #define RAPL_MSR_MASK 0xFFFFFFFF static struct perf_msr intel_rapl_msrs[] = { [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr, false, RAPL_MSR_MASK }, }; static struct perf_msr intel_rapl_spr_msrs[] = { [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr, true, RAPL_MSR_MASK }, }; /* * Force to PERF_RAPL_MAX size due to: * - perf_msr_probe(PERF_RAPL_MAX) * - want to use same event codes across both architectures */ static struct perf_msr amd_rapl_msrs[] = { [PERF_RAPL_PP0] = { 0, &rapl_events_cores_group, 0, false, 0 }, [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_RAM] = { 0, &rapl_events_ram_group, 0, false, 0 }, [PERF_RAPL_PP1] = { 0, &rapl_events_gpu_group, 0, false, 0 }, [PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group, 0, false, 0 }, }; static int rapl_cpu_offline(unsigned int cpu) { struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); int target; /* Check if exiting cpu is used for collecting rapl events */ if (!cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask)) return 0; pmu->cpu = -1; /* Find a new cpu to collect rapl events */ target = cpumask_any_but(topology_die_cpumask(cpu), cpu); /* Migrate rapl events to the new target */ if (target < nr_cpu_ids) { cpumask_set_cpu(target, &rapl_cpu_mask); pmu->cpu = target; perf_pmu_migrate_context(pmu->pmu, cpu, target); } return 0; } static int rapl_cpu_online(unsigned int cpu) { struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); int target; if (!pmu) { pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); if (!pmu) return -ENOMEM; raw_spin_lock_init(&pmu->lock); INIT_LIST_HEAD(&pmu->active_list); pmu->pmu = &rapl_pmus->pmu; pmu->timer_interval = ms_to_ktime(rapl_timer_ms); rapl_hrtimer_init(pmu); rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu; } /* * Check if there is an online cpu in the package which collects rapl * events already. */ target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu)); if (target < nr_cpu_ids) return 0; cpumask_set_cpu(cpu, &rapl_cpu_mask); pmu->cpu = cpu; return 0; } static int rapl_check_hw_unit(struct rapl_model *rm) { u64 msr_rapl_power_unit_bits; int i; /* protect rdmsrl() to handle virtualization */ if (rdmsrl_safe(rm->msr_power_unit, &msr_rapl_power_unit_bits)) return -1; for (i = 0; i < NR_RAPL_DOMAINS; i++) rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; switch (rm->unit_quirk) { /* * DRAM domain on HSW server and KNL has fixed energy unit which can be * different than the unit from power unit MSR. See * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2 * of 2. Datasheet, September 2014, Reference Number: 330784-001 " */ case RAPL_UNIT_QUIRK_INTEL_HSW: rapl_hw_unit[PERF_RAPL_RAM] = 16; break; /* * SPR shares the same DRAM domain energy unit as HSW, plus it * also has a fixed energy unit for Psys domain. */ case RAPL_UNIT_QUIRK_INTEL_SPR: rapl_hw_unit[PERF_RAPL_RAM] = 16; rapl_hw_unit[PERF_RAPL_PSYS] = 0; break; default: break; } /* * Calculate the timer rate: * Use reference of 200W for scaling the timeout to avoid counter * overflows. 200W = 200 Joules/sec * Divide interval by 2 to avoid lockstep (2 * 100) * if hw unit is 32, then we use 2 ms 1/200/2 */ rapl_timer_ms = 2; if (rapl_hw_unit[0] < 32) { rapl_timer_ms = (1000 / (2 * 100)); rapl_timer_ms *= (1ULL << (32 - rapl_hw_unit[0] - 1)); } return 0; } static void __init rapl_advertise(void) { int i; pr_info("API unit is 2^-32 Joules, %d fixed counters, %llu ms ovfl timer\n", hweight32(rapl_cntr_mask), rapl_timer_ms); for (i = 0; i < NR_RAPL_DOMAINS; i++) { if (rapl_cntr_mask & (1 << i)) { pr_info("hw unit of domain %s 2^-%d Joules\n", rapl_domain_names[i], rapl_hw_unit[i]); } } } static void cleanup_rapl_pmus(void) { int i; for (i = 0; i < rapl_pmus->maxdie; i++) kfree(rapl_pmus->pmus[i]); kfree(rapl_pmus); } static const struct attribute_group *rapl_attr_update[] = { &rapl_events_cores_group, &rapl_events_pkg_group, &rapl_events_ram_group, &rapl_events_gpu_group, &rapl_events_psys_group, NULL, }; static int __init init_rapl_pmus(void) { int maxdie = topology_max_packages() * topology_max_die_per_package(); size_t size; size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *); rapl_pmus = kzalloc(size, GFP_KERNEL); if (!rapl_pmus) return -ENOMEM; rapl_pmus->maxdie = maxdie; rapl_pmus->pmu.attr_groups = rapl_attr_groups; rapl_pmus->pmu.attr_update = rapl_attr_update; rapl_pmus->pmu.task_ctx_nr = perf_invalid_context; rapl_pmus->pmu.event_init = rapl_pmu_event_init; rapl_pmus->pmu.add = rapl_pmu_event_add; rapl_pmus->pmu.del = rapl_pmu_event_del; rapl_pmus->pmu.start = rapl_pmu_event_start; rapl_pmus->pmu.stop = rapl_pmu_event_stop; rapl_pmus->pmu.read = rapl_pmu_event_read; rapl_pmus->pmu.module = THIS_MODULE; rapl_pmus->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE; return 0; } static struct rapl_model model_snb = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_PP1), .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_snbep = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_hsw = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PP1), .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_hsx = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_HSW, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_knl = { .events = BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_HSW, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_skl = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PP1) | BIT(PERF_RAPL_PSYS), .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_spr = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PSYS), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_SPR, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_spr_msrs, }; static struct rapl_model model_amd_hygon = { .events = BIT(PERF_RAPL_PKG), .msr_power_unit = MSR_AMD_RAPL_POWER_UNIT, .rapl_msrs = amd_rapl_msrs, }; static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_FEATURE(X86_FEATURE_RAPL, &model_amd_hygon), X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &model_snb), X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &model_snbep), X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &model_snb), X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &model_snbep), X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &model_knl), X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &model_knl), X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr), {}, }; MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); static int __init rapl_pmu_init(void) { const struct x86_cpu_id *id; struct rapl_model *rm; int ret; id = x86_match_cpu(rapl_model_match); if (!id) return -ENODEV; rm = (struct rapl_model *) id->driver_data; rapl_msrs = rm->rapl_msrs; rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX, false, (void *) &rm->events); ret = rapl_check_hw_unit(rm); if (ret) return ret; ret = init_rapl_pmus(); if (ret) return ret; /* * Install callbacks. Core will call them for each online cpu. */ ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE, "perf/x86/rapl:online", rapl_cpu_online, rapl_cpu_offline); if (ret) goto out; ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1); if (ret) goto out1; rapl_advertise(); return 0; out1: cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE); out: pr_warn("Initialization failed (%d), disabled\n", ret); cleanup_rapl_pmus(); return ret; } module_init(rapl_pmu_init); static void __exit intel_rapl_exit(void) { cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE); perf_pmu_unregister(&rapl_pmus->pmu); cleanup_rapl_pmus(); } module_exit(intel_rapl_exit); |
| 921 394 510 397 348 87 6 397 46 343 342 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_IP_TUNNELS_H #define __NET_IP_TUNNELS_H 1 #include <linux/if_tunnel.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/types.h> #include <linux/u64_stats_sync.h> #include <linux/bitops.h> #include <net/dsfield.h> #include <net/gro_cells.h> #include <net/inet_ecn.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/lwtunnel.h> #include <net/dst_cache.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #endif /* Keep error state on tunnel for 30 sec */ #define IPTUNNEL_ERR_TIMEO (30*HZ) /* Used to memset ip_tunnel padding. */ #define IP_TUNNEL_KEY_SIZE offsetofend(struct ip_tunnel_key, tp_dst) /* Used to memset ipv4 address padding. */ #define IP_TUNNEL_KEY_IPV4_PAD offsetofend(struct ip_tunnel_key, u.ipv4.dst) #define IP_TUNNEL_KEY_IPV4_PAD_LEN \ (sizeof_field(struct ip_tunnel_key, u) - \ sizeof_field(struct ip_tunnel_key, u.ipv4)) struct ip_tunnel_key { __be64 tun_id; union { struct { __be32 src; __be32 dst; } ipv4; struct { struct in6_addr src; struct in6_addr dst; } ipv6; } u; __be16 tun_flags; u8 tos; /* TOS for IPv4, TC for IPv6 */ u8 ttl; /* TTL for IPv4, HL for IPv6 */ __be32 label; /* Flow Label for IPv6 */ __be16 tp_src; __be16 tp_dst; }; /* Flags for ip_tunnel_info mode. */ #define IP_TUNNEL_INFO_TX 0x01 /* represents tx tunnel parameters */ #define IP_TUNNEL_INFO_IPV6 0x02 /* key contains IPv6 addresses */ #define IP_TUNNEL_INFO_BRIDGE 0x04 /* represents a bridged tunnel id */ /* Maximum tunnel options length. */ #define IP_TUNNEL_OPTS_MAX \ GENMASK((sizeof_field(struct ip_tunnel_info, \ options_len) * BITS_PER_BYTE) - 1, 0) struct ip_tunnel_info { struct ip_tunnel_key key; #ifdef CONFIG_DST_CACHE struct dst_cache dst_cache; #endif u8 options_len; u8 mode; }; /* 6rd prefix/relay information */ #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd_parm { struct in6_addr prefix; __be32 relay_prefix; u16 prefixlen; u16 relay_prefixlen; }; #endif struct ip_tunnel_encap { u16 type; u16 flags; __be16 sport; __be16 dport; }; struct ip_tunnel_prl_entry { struct ip_tunnel_prl_entry __rcu *next; __be32 addr; u16 flags; struct rcu_head rcu_head; }; struct metadata_dst; struct ip_tunnel { struct ip_tunnel __rcu *next; struct hlist_node hash_node; struct net_device *dev; struct net *net; /* netns for packet i/o */ unsigned long err_time; /* Time when the last ICMP error * arrived */ int err_count; /* Number of arrived ICMP errors */ /* These four fields used only by GRE */ u32 i_seqno; /* The last seen seqno */ atomic_t o_seqno; /* The last output seqno */ int tun_hlen; /* Precalculated header length */ /* These four fields used only by ERSPAN */ u32 index; /* ERSPAN type II index */ u8 erspan_ver; /* ERSPAN version */ u8 dir; /* ERSPAN direction */ u16 hwid; /* ERSPAN hardware ID */ struct dst_cache dst_cache; struct ip_tunnel_parm parms; int mlink; int encap_hlen; /* Encap header length (FOU,GUE) */ int hlen; /* tun_hlen + encap_hlen */ struct ip_tunnel_encap encap; /* for SIT */ #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd_parm ip6rd; #endif struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */ unsigned int prl_count; /* # of entries in PRL */ unsigned int ip_tnl_net_id; struct gro_cells gro_cells; __u32 fwmark; bool collect_md; bool ignore_df; }; struct tnl_ptk_info { __be16 flags; __be16 proto; __be32 key; __be32 seq; int hdr_len; }; #define PACKET_RCVD 0 #define PACKET_REJECT 1 #define PACKET_NEXT 2 #define IP_TNL_HASH_BITS 7 #define IP_TNL_HASH_SIZE (1 << IP_TNL_HASH_BITS) struct ip_tunnel_net { struct net_device *fb_tunnel_dev; struct rtnl_link_ops *rtnl_link_ops; struct hlist_head tunnels[IP_TNL_HASH_SIZE]; struct ip_tunnel __rcu *collect_md_tun; int type; }; static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, __be32 saddr, __be32 daddr, u8 tos, u8 ttl, __be32 label, __be16 tp_src, __be16 tp_dst, __be64 tun_id, __be16 tun_flags) { key->tun_id = tun_id; key->u.ipv4.src = saddr; key->u.ipv4.dst = daddr; memset((unsigned char *)key + IP_TUNNEL_KEY_IPV4_PAD, 0, IP_TUNNEL_KEY_IPV4_PAD_LEN); key->tos = tos; key->ttl = ttl; key->label = label; key->tun_flags = tun_flags; /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of * the upper tunnel are used. * E.g: GRE over IPSEC, the tp_src and tp_port are zero. */ key->tp_src = tp_src; key->tp_dst = tp_dst; /* Clear struct padding. */ if (sizeof(*key) != IP_TUNNEL_KEY_SIZE) memset((unsigned char *)key + IP_TUNNEL_KEY_SIZE, 0, sizeof(*key) - IP_TUNNEL_KEY_SIZE); } static inline bool ip_tunnel_dst_cache_usable(const struct sk_buff *skb, const struct ip_tunnel_info *info) { if (skb->mark) return false; if (!info) return true; if (info->key.tun_flags & TUNNEL_NOCACHE) return false; return true; } static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info *tun_info) { return tun_info->mode & IP_TUNNEL_INFO_IPV6 ? AF_INET6 : AF_INET; } static inline __be64 key32_to_tunnel_id(__be32 key) { #ifdef __BIG_ENDIAN return (__force __be64)key; #else return (__force __be64)((__force u64)key << 32); #endif } /* Returns the least-significant 32 bits of a __be64. */ static inline __be32 tunnel_id_to_key32(__be64 tun_id) { #ifdef __BIG_ENDIAN return (__force __be32)tun_id; #else return (__force __be32)((__force u64)tun_id >> 32); #endif } #ifdef CONFIG_INET static inline void ip_tunnel_init_flow(struct flowi4 *fl4, int proto, __be32 daddr, __be32 saddr, __be32 key, __u8 tos, int oif, __u32 mark, __u32 tun_inner_hash) { memset(fl4, 0, sizeof(*fl4)); fl4->flowi4_oif = oif; fl4->daddr = daddr; fl4->saddr = saddr; fl4->flowi4_tos = tos; fl4->flowi4_proto = proto; fl4->fl4_gre_key = key; fl4->flowi4_mark = mark; fl4->flowi4_multipath_hash = tun_inner_hash; } int ip_tunnel_init(struct net_device *dev); void ip_tunnel_uninit(struct net_device *dev); void ip_tunnel_dellink(struct net_device *dev, struct list_head *head); struct net *ip_tunnel_get_link_net(const struct net_device *dev); int ip_tunnel_get_iflink(const struct net_device *dev); int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname); void ip_tunnel_delete_nets(struct list_head *list_net, unsigned int id, struct rtnl_link_ops *ops); void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, const u8 protocol); void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const u8 proto, int tunnel_hlen); int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, int link, __be16 flags, __be32 remote, __be32 local, __be32 key); int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p, __u32 fwmark); int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p, __u32 fwmark); void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); extern const struct header_ops ip_tunnel_header_ops; __be16 ip_tunnel_parse_protocol(const struct sk_buff *skb); struct ip_tunnel_encap_ops { size_t (*encap_hlen)(struct ip_tunnel_encap *e); int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi4 *fl4); int (*err_handler)(struct sk_buff *skb, u32 info); }; #define MAX_IPTUN_ENCAP_OPS 8 extern const struct ip_tunnel_encap_ops __rcu * iptun_encaps[MAX_IPTUN_ENCAP_OPS]; int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op, unsigned int num); int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op, unsigned int num); int ip_tunnel_encap_setup(struct ip_tunnel *t, struct ip_tunnel_encap *ipencap); static inline bool pskb_inet_may_pull(struct sk_buff *skb) { int nhlen; switch (skb->protocol) { #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): nhlen = sizeof(struct ipv6hdr); break; #endif case htons(ETH_P_IP): nhlen = sizeof(struct iphdr); break; default: nhlen = 0; } return pskb_network_may_pull(skb, nhlen); } /* Variant of pskb_inet_may_pull(). */ static inline bool skb_vlan_inet_prepare(struct sk_buff *skb, bool inner_proto_inherit) { int nhlen = 0, maclen = inner_proto_inherit ? 0 : ETH_HLEN; __be16 type = skb->protocol; /* Essentially this is skb_protocol(skb, true) * And we get MAC len. */ if (eth_type_vlan(type)) type = __vlan_get_protocol(skb, type, &maclen); switch (type) { #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): nhlen = sizeof(struct ipv6hdr); break; #endif case htons(ETH_P_IP): nhlen = sizeof(struct iphdr); break; } /* For ETH_P_IPV6/ETH_P_IP we make sure to pull * a base network header in skb->head. */ if (!pskb_may_pull(skb, maclen + nhlen)) return false; skb_set_network_header(skb, maclen); return true; } static inline int ip_encap_hlen(struct ip_tunnel_encap *e) { const struct ip_tunnel_encap_ops *ops; int hlen = -EINVAL; if (e->type == TUNNEL_ENCAP_NONE) return 0; if (e->type >= MAX_IPTUN_ENCAP_OPS) return -EINVAL; rcu_read_lock(); ops = rcu_dereference(iptun_encaps[e->type]); if (likely(ops && ops->encap_hlen)) hlen = ops->encap_hlen(e); rcu_read_unlock(); return hlen; } static inline int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t, u8 *protocol, struct flowi4 *fl4) { const struct ip_tunnel_encap_ops *ops; int ret = -EINVAL; if (t->encap.type == TUNNEL_ENCAP_NONE) return 0; if (t->encap.type >= MAX_IPTUN_ENCAP_OPS) return -EINVAL; rcu_read_lock(); ops = rcu_dereference(iptun_encaps[t->encap.type]); if (likely(ops && ops->build_header)) ret = ops->build_header(skb, &t->encap, protocol, fl4); rcu_read_unlock(); return ret; } /* Extract dsfield from inner protocol */ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, const struct sk_buff *skb) { __be16 payload_protocol = skb_protocol(skb, true); if (payload_protocol == htons(ETH_P_IP)) return iph->tos; else if (payload_protocol == htons(ETH_P_IPV6)) return ipv6_get_dsfield((const struct ipv6hdr *)iph); else return 0; } static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, const struct sk_buff *skb) { __be16 payload_protocol = skb_protocol(skb, true); if (payload_protocol == htons(ETH_P_IP)) return iph->ttl; else if (payload_protocol == htons(ETH_P_IPV6)) return ((const struct ipv6hdr *)iph)->hop_limit; else return 0; } /* Propogate ECN bits out */ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, const struct sk_buff *skb) { u8 inner = ip_tunnel_get_dsfield(iph, skb); return INET_ECN_encapsulate(tos, inner); } int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, bool raw_proto, bool xnet); static inline int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, bool xnet) { return __iptunnel_pull_header(skb, hdr_len, inner_proto, false, xnet); } void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, u8 proto, u8 tos, u8 ttl, __be16 df, bool xnet); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags); int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, int headroom, bool reply); int iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask); static inline int iptunnel_pull_offloads(struct sk_buff *skb) { if (skb_is_gso(skb)) { int err; err = skb_unclone(skb, GFP_ATOMIC); if (unlikely(err)) return err; skb_shinfo(skb)->gso_type &= ~(NETIF_F_GSO_ENCAP_ALL >> NETIF_F_GSO_SHIFT); } skb->encapsulation = 0; return 0; } static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) { if (pkt_len > 0) { struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += pkt_len; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); put_cpu_ptr(tstats); } else { struct net_device_stats *err_stats = &dev->stats; if (pkt_len < 0) { err_stats->tx_errors++; err_stats->tx_aborted_errors++; } else { err_stats->tx_dropped++; } } } static inline void *ip_tunnel_info_opts(struct ip_tunnel_info *info) { return info + 1; } static inline void ip_tunnel_info_opts_get(void *to, const struct ip_tunnel_info *info) { memcpy(to, info + 1, info->options_len); } static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, __be16 flags) { info->options_len = len; if (len > 0) { memcpy(ip_tunnel_info_opts(info), from, len); info->key.tun_flags |= flags; } } static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) { return (struct ip_tunnel_info *)lwtstate->data; } DECLARE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt); /* Returns > 0 if metadata should be collected */ static inline int ip_tunnel_collect_metadata(void) { return static_branch_unlikely(&ip_tunnel_metadata_cnt); } void __init ip_tunnel_core_init(void); void ip_tunnel_need_metadata(void); void ip_tunnel_unneed_metadata(void); #else /* CONFIG_INET */ static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) { return NULL; } static inline void ip_tunnel_need_metadata(void) { } static inline void ip_tunnel_unneed_metadata(void) { } static inline void ip_tunnel_info_opts_get(void *to, const struct ip_tunnel_info *info) { } static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, __be16 flags) { info->options_len = 0; } #endif /* CONFIG_INET */ #endif /* __NET_IP_TUNNELS_H */ |
| 4904 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * netprio_cgroup.h Control Group Priority set * * Authors: Neil Horman <nhorman@tuxdriver.com> */ #ifndef _NETPRIO_CGROUP_H #define _NETPRIO_CGROUP_H #include <linux/cgroup.h> #include <linux/hardirq.h> #include <linux/rcupdate.h> #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map { struct rcu_head rcu; u32 priomap_len; u32 priomap[]; }; static inline u32 task_netprioidx(struct task_struct *p) { struct cgroup_subsys_state *css; u32 idx; rcu_read_lock(); css = task_css(p, net_prio_cgrp_id); idx = css->id; rcu_read_unlock(); return idx; } static inline void sock_update_netprioidx(struct sock_cgroup_data *skcd) { if (in_interrupt()) return; sock_cgroup_set_prioidx(skcd, task_netprioidx(current)); } #else /* !CONFIG_CGROUP_NET_PRIO */ static inline u32 task_netprioidx(struct task_struct *p) { return 0; } static inline void sock_update_netprioidx(struct sock_cgroup_data *skcd) { } #endif /* CONFIG_CGROUP_NET_PRIO */ #endif /* _NET_CLS_CGROUP_H */ |
| 519 518 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 | // SPDX-License-Identifier: GPL-2.0-only /* * async.c: Asynchronous function calls for boot performance * * (C) Copyright 2009 Intel Corporation * Author: Arjan van de Ven <arjan@linux.intel.com> */ /* Goals and Theory of Operation The primary goal of this feature is to reduce the kernel boot time, by doing various independent hardware delays and discovery operations decoupled and not strictly serialized. More specifically, the asynchronous function call concept allows certain operations (primarily during system boot) to happen asynchronously, out of order, while these operations still have their externally visible parts happen sequentially and in-order. (not unlike how out-of-order CPUs retire their instructions in order) Key to the asynchronous function call implementation is the concept of a "sequence cookie" (which, although it has an abstracted type, can be thought of as a monotonically incrementing number). The async core will assign each scheduled event such a sequence cookie and pass this to the called functions. The asynchronously called function should before doing a globally visible operation, such as registering device numbers, call the async_synchronize_cookie() function and pass in its own cookie. The async_synchronize_cookie() function will make sure that all asynchronous operations that were scheduled prior to the operation corresponding with the cookie have completed. Subsystem/driver initialization code that scheduled asynchronous probe functions, but which shares global resources with other drivers/subsystems that do not use the asynchronous call feature, need to do a full synchronization with the async_synchronize_full() function, before returning from their init function. This is to maintain strict ordering between the asynchronous and synchronous parts of the kernel. */ #include <linux/async.h> #include <linux/atomic.h> #include <linux/ktime.h> #include <linux/export.h> #include <linux/wait.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/workqueue.h> #include "workqueue_internal.h" static async_cookie_t next_cookie = 1; #define MAX_WORK 32768 #define ASYNC_COOKIE_MAX ULLONG_MAX /* infinity cookie */ static LIST_HEAD(async_global_pending); /* pending from all registered doms */ static ASYNC_DOMAIN(async_dfl_domain); static DEFINE_SPINLOCK(async_lock); struct async_entry { struct list_head domain_list; struct list_head global_list; struct work_struct work; async_cookie_t cookie; async_func_t func; void *data; struct async_domain *domain; }; static DECLARE_WAIT_QUEUE_HEAD(async_done); static atomic_t entry_count; static long long microseconds_since(ktime_t start) { ktime_t now = ktime_get(); return ktime_to_ns(ktime_sub(now, start)) >> 10; } static async_cookie_t lowest_in_progress(struct async_domain *domain) { struct async_entry *first = NULL; async_cookie_t ret = ASYNC_COOKIE_MAX; unsigned long flags; spin_lock_irqsave(&async_lock, flags); if (domain) { if (!list_empty(&domain->pending)) first = list_first_entry(&domain->pending, struct async_entry, domain_list); } else { if (!list_empty(&async_global_pending)) first = list_first_entry(&async_global_pending, struct async_entry, global_list); } if (first) ret = first->cookie; spin_unlock_irqrestore(&async_lock, flags); return ret; } /* * pick the first pending entry and run it */ static void async_run_entry_fn(struct work_struct *work) { struct async_entry *entry = container_of(work, struct async_entry, work); unsigned long flags; ktime_t calltime; /* 1) run (and print duration) */ pr_debug("calling %lli_%pS @ %i\n", (long long)entry->cookie, entry->func, task_pid_nr(current)); calltime = ktime_get(); entry->func(entry->data, entry->cookie); pr_debug("initcall %lli_%pS returned after %lld usecs\n", (long long)entry->cookie, entry->func, microseconds_since(calltime)); /* 2) remove self from the pending queues */ spin_lock_irqsave(&async_lock, flags); list_del_init(&entry->domain_list); list_del_init(&entry->global_list); /* 3) free the entry */ kfree(entry); atomic_dec(&entry_count); spin_unlock_irqrestore(&async_lock, flags); /* 4) wake up any waiters */ wake_up(&async_done); } static async_cookie_t __async_schedule_node_domain(async_func_t func, void *data, int node, struct async_domain *domain, struct async_entry *entry) { async_cookie_t newcookie; unsigned long flags; INIT_LIST_HEAD(&entry->domain_list); INIT_LIST_HEAD(&entry->global_list); INIT_WORK(&entry->work, async_run_entry_fn); entry->func = func; entry->data = data; entry->domain = domain; spin_lock_irqsave(&async_lock, flags); /* allocate cookie and queue */ newcookie = entry->cookie = next_cookie++; list_add_tail(&entry->domain_list, &domain->pending); if (domain->registered) list_add_tail(&entry->global_list, &async_global_pending); atomic_inc(&entry_count); spin_unlock_irqrestore(&async_lock, flags); /* schedule for execution */ queue_work_node(node, system_unbound_wq, &entry->work); return newcookie; } /** * async_schedule_node_domain - NUMA specific version of async_schedule_domain * @func: function to execute asynchronously * @data: data pointer to pass to the function * @node: NUMA node that we want to schedule this on or close to * @domain: the domain * * Returns an async_cookie_t that may be used for checkpointing later. * @domain may be used in the async_synchronize_*_domain() functions to * wait within a certain synchronization domain rather than globally. * * Note: This function may be called from atomic or non-atomic contexts. * * The node requested will be honored on a best effort basis. If the node * has no CPUs associated with it then the work is distributed among all * available CPUs. */ async_cookie_t async_schedule_node_domain(async_func_t func, void *data, int node, struct async_domain *domain) { struct async_entry *entry; unsigned long flags; async_cookie_t newcookie; /* allow irq-off callers */ entry = kzalloc(sizeof(struct async_entry), GFP_ATOMIC); /* * If we're out of memory or if there's too much work * pending already, we execute synchronously. */ if (!entry || atomic_read(&entry_count) > MAX_WORK) { kfree(entry); spin_lock_irqsave(&async_lock, flags); newcookie = next_cookie++; spin_unlock_irqrestore(&async_lock, flags); /* low on memory.. run synchronously */ func(data, newcookie); return newcookie; } return __async_schedule_node_domain(func, data, node, domain, entry); } EXPORT_SYMBOL_GPL(async_schedule_node_domain); /** * async_schedule_node - NUMA specific version of async_schedule * @func: function to execute asynchronously * @data: data pointer to pass to the function * @node: NUMA node that we want to schedule this on or close to * * Returns an async_cookie_t that may be used for checkpointing later. * Note: This function may be called from atomic or non-atomic contexts. * * The node requested will be honored on a best effort basis. If the node * has no CPUs associated with it then the work is distributed among all * available CPUs. */ async_cookie_t async_schedule_node(async_func_t func, void *data, int node) { return async_schedule_node_domain(func, data, node, &async_dfl_domain); } EXPORT_SYMBOL_GPL(async_schedule_node); /** * async_schedule_dev_nocall - A simplified variant of async_schedule_dev() * @func: function to execute asynchronously * @dev: device argument to be passed to function * * @dev is used as both the argument for the function and to provide NUMA * context for where to run the function. * * If the asynchronous execution of @func is scheduled successfully, return * true. Otherwise, do nothing and return false, unlike async_schedule_dev() * that will run the function synchronously then. */ bool async_schedule_dev_nocall(async_func_t func, struct device *dev) { struct async_entry *entry; entry = kzalloc(sizeof(struct async_entry), GFP_KERNEL); /* Give up if there is no memory or too much work. */ if (!entry || atomic_read(&entry_count) > MAX_WORK) { kfree(entry); return false; } __async_schedule_node_domain(func, dev, dev_to_node(dev), &async_dfl_domain, entry); return true; } /** * async_synchronize_full - synchronize all asynchronous function calls * * This function waits until all asynchronous function calls have been done. */ void async_synchronize_full(void) { async_synchronize_full_domain(NULL); } EXPORT_SYMBOL_GPL(async_synchronize_full); /** * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain * @domain: the domain to synchronize * * This function waits until all asynchronous function calls for the * synchronization domain specified by @domain have been done. */ void async_synchronize_full_domain(struct async_domain *domain) { async_synchronize_cookie_domain(ASYNC_COOKIE_MAX, domain); } EXPORT_SYMBOL_GPL(async_synchronize_full_domain); /** * async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing * @cookie: async_cookie_t to use as checkpoint * @domain: the domain to synchronize (%NULL for all registered domains) * * This function waits until all asynchronous function calls for the * synchronization domain specified by @domain submitted prior to @cookie * have been done. */ void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *domain) { ktime_t starttime; pr_debug("async_waiting @ %i\n", task_pid_nr(current)); starttime = ktime_get(); wait_event(async_done, lowest_in_progress(domain) >= cookie); pr_debug("async_continuing @ %i after %lli usec\n", task_pid_nr(current), microseconds_since(starttime)); } EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain); /** * async_synchronize_cookie - synchronize asynchronous function calls with cookie checkpointing * @cookie: async_cookie_t to use as checkpoint * * This function waits until all asynchronous function calls prior to @cookie * have been done. */ void async_synchronize_cookie(async_cookie_t cookie) { async_synchronize_cookie_domain(cookie, &async_dfl_domain); } EXPORT_SYMBOL_GPL(async_synchronize_cookie); /** * current_is_async - is %current an async worker task? * * Returns %true if %current is an async worker task. */ bool current_is_async(void) { struct worker *worker = current_wq_worker(); return worker && worker->current_func == async_run_entry_fn; } EXPORT_SYMBOL_GPL(current_is_async); |
| 2680 1167 1167 1636 1931 2464 2465 2411 61 1636 871 1932 1931 1931 1878 68 1933 487 488 348 204 485 7 164 168 522 522 522 522 519 2143 353 1867 666 149 531 2466 2248 284 2330 168 2467 2464 1869 666 1877 663 2465 2465 2579 2574 2142 261 604 486 4 341 2463 2465 1868 665 4566 3328 1329 2060 2025 4599 3115 3422 507 15 77 77 473 1 25 25 15 39 25 15 50 2 48 239 239 7 7 7 7 7 7 7 7 7 7 7 7 7 171 167 7 8773 294 8705 102 8775 377 1536 294 1 1 7993 7991 8770 8773 8770 1138 8743 8734 8 8470 726 8735 8224 1186 8705 294 8739 543 7066 176 2579 977 7992 8525 8295 8303 8298 8292 8299 8293 8298 8299 884 2380 2380 1287 254 1817 1722 1722 791 1238 1902 1902 1300 244 1329 69 69 1477 1475 1477 1476 1476 1217 1216 1216 1 1263 1261 1263 2 1263 1262 1 1 1 1 1 1261 1261 1261 1262 1263 1263 1476 361 1215 1007 645 645 644 361 1216 1007 645 802 803 725 212 459 452 239 238 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/dcache.c * * Complete reimplementation * (C) 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ /* * Notes on the allocation strategy: * * The dcache is a master of the icache - whenever a dcache entry * exists, the inode will always exist. "iput()" is done either when * the dcache entry is deleted or garbage collected. */ #include <linux/ratelimit.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/cache.h> #include <linux/export.h> #include <linux/security.h> #include <linux/seqlock.h> #include <linux/memblock.h> #include <linux/bit_spinlock.h> #include <linux/rculist_bl.h> #include <linux/list_lru.h> #include "internal.h" #include "mount.h" /* * Usage: * dcache->d_inode->i_lock protects: * - i_dentry, d_u.d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_roots bl list spinlock protects: * - the s_roots list (see __d_drop) * dentry->d_sb->s_dentry_lru_lock protects: * - the dcache lru lists and counters * d_lock protects: * - d_flags * - d_name * - d_lru * - d_count * - d_unhashed() * - d_parent and d_subdirs * - childrens' d_child and d_parent * - d_u.d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock * dentry->d_lock * dentry->d_sb->s_dentry_lru_lock * dcache_hash_bucket lock * s_roots lock * * If there is an ancestor relationship: * dentry->d_parent->...->d_parent->d_lock * ... * dentry->d_parent->d_lock * dentry->d_lock * * If no ancestor relationship: * arbitrary, since it's serialized on rename_lock */ int sysctl_vfs_cache_pressure __read_mostly = 100; EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure); __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __read_mostly; const struct qstr empty_name = QSTR_INIT("", 0); EXPORT_SYMBOL(empty_name); const struct qstr slash_name = QSTR_INIT("/", 1); EXPORT_SYMBOL(slash_name); const struct qstr dotdot_name = QSTR_INIT("..", 2); EXPORT_SYMBOL(dotdot_name); /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try * to make this good - I've just made it work. * * This hash-function tries to avoid losing too many bits of hash * information, yet avoid using a prime hash-size or similar. */ static unsigned int d_hash_shift __read_mostly; static struct hlist_bl_head *dentry_hashtable __read_mostly; static inline struct hlist_bl_head *d_hash(unsigned int hash) { return dentry_hashtable + (hash >> d_hash_shift); } #define IN_LOOKUP_SHIFT 10 static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT]; static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent, unsigned int hash) { hash += (unsigned long) parent / L1_CACHE_BYTES; return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT); } /* Statistics gathering. */ struct dentry_stat_t dentry_stat = { .age_limit = 45, }; static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); static DEFINE_PER_CPU(long, nr_dentry_negative); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* * Here we resort to our own counters instead of using generic per-cpu counters * for consistency with what the vfs inode code does. We are expected to harvest * better code and performance by having our own specialized counters. * * Please note that the loop is done over all possible CPUs, not over all online * CPUs. The reason for this is that we don't want to play games with CPUs going * on and off. If one of them goes off, we will just keep their counters. * * glommer: See cffbc8a for details, and if you ever intend to change this, * please update all vfs counters to match. */ static long get_nr_dentry(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_unused, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_negative(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_negative, i); return sum < 0 ? 0 : sum; } int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif /* * Compare 2 name strings, return 0 if they match, otherwise non-zero. * The strings are both count bytes long, and count is non-zero. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> /* * NOTE! 'cs' and 'scount' come from a dentry, so it has a * aligned allocation for this particular component. We don't * strictly need the load_unaligned_zeropad() safety, but it * doesn't hurt either. * * In contrast, 'ct' and 'tcount' can be from a pathname, and do * need the careful unaligned handling. */ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { unsigned long a,b,mask; for (;;) { a = read_word_at_a_time(cs); b = load_unaligned_zeropad(ct); if (tcount < sizeof(unsigned long)) break; if (unlikely(a != b)) return 1; cs += sizeof(unsigned long); ct += sizeof(unsigned long); tcount -= sizeof(unsigned long); if (!tcount) return 0; } mask = bytemask_from_count(tcount); return unlikely(!!((a ^ b) & mask)); } #else static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { do { if (*cs != *ct) return 1; cs++; ct++; tcount--; } while (tcount); return 0; } #endif static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount) { /* * Be careful about RCU walk racing with rename: * use 'READ_ONCE' to fetch the name pointer. * * NOTE! Even if a rename will mean that the length * was not loaded atomically, we don't care. The * RCU walk will check the sequence count eventually, * and catch it. And we won't overrun the buffer, * because we're reading the name pointer atomically, * and a dentry name is guaranteed to be properly * terminated with a NUL byte. * * End result: even if 'len' is wrong, we'll exit * early because the data cannot match (there can * be no NUL in the ct/tcount data) */ const unsigned char *cs = READ_ONCE(dentry->d_name.name); return dentry_string_cmp(cs, ct, tcount); } struct external_name { union { atomic_t count; struct rcu_head head; } u; unsigned char name[]; }; static inline struct external_name *external_name(struct dentry *dentry) { return container_of(dentry->d_name.name, struct external_name, name[0]); } static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kmem_cache_free(dentry_cache, dentry); } static void __d_free_external(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); } static inline int dname_external(const struct dentry *dentry) { return dentry->d_name.name != dentry->d_iname; } void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { spin_lock(&dentry->d_lock); name->name = dentry->d_name; if (unlikely(dname_external(dentry))) { atomic_inc(&external_name(dentry)->u.count); } else { memcpy(name->inline_name, dentry->d_iname, dentry->d_name.len + 1); name->name.name = name->inline_name; } spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { if (unlikely(name->name.name != name->inline_name)) { struct external_name *p; p = container_of(name->name.name, struct external_name, name[0]); if (unlikely(atomic_dec_and_test(&p->u.count))) kfree_rcu(p, u.head); } } EXPORT_SYMBOL(release_dentry_name_snapshot); static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) { unsigned flags; dentry->d_inode = inode; flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); flags |= type_flags; smp_store_release(&dentry->d_flags, flags); } static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; /* * The negative counter only tracks dentries on the LRU. Don't inc if * d_lru is on another list. */ if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) { WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); if (likely(atomic_dec_and_test(&p->u.count))) { call_rcu(&dentry->d_u.d_rcu, __d_free_external); return; } } /* if dentry was never visible to RCU, immediate free is OK */ if (dentry->d_flags & DCACHE_NORCU) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } /* * Release the dentry's inode, using the filesystem * d_iput() operation if defined. */ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_lock) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) fsnotify_inoderemove(inode); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode); else iput(inode); } /* * The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry * is in use - which includes both the "real" per-superblock * LRU list _and_ the DCACHE_SHRINK_LIST use. * * The DCACHE_SHRINK_LIST bit is set whenever the dentry is * on the shrink list (ie not on the superblock LRU list). * * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * * The per-cpu "nr_dentry_negative" counters are only updated * when deleted from or added to the per-superblock LRU list, not * from/to the shrink list. That is to avoid an unneeded dec/inc * pair when moving from LRU to shrink list in select_collect(). * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ #define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x)) static void d_lru_add(struct dentry *dentry) { D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_lru_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_shrink_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); list_del_init(&dentry->d_lru); dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); this_cpu_dec(nr_dentry_unused); } static void d_shrink_add(struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, 0); list_add(&dentry->d_lru, list); dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); } /* * These can only be called under the global LRU lock, ie during the * callback for freeing the LRU list. "isolate" removes it from the * LRU lists entirely, while shrink_move moves it to the indicated * private list. */ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } static void ___d_drop(struct dentry *dentry) { struct hlist_bl_head *b; /* * Hashed dentries are normally on the dentry hashtable, * with the exception of those newly allocated by * d_obtain_root, which are always IS_ROOT: */ if (unlikely(IS_ROOT(dentry))) b = &dentry->d_sb->s_roots; else b = d_hash(dentry->d_name.hash); hlist_bl_lock(b); __hlist_bl_del(&dentry->d_hash); hlist_bl_unlock(b); } void __d_drop(struct dentry *dentry) { if (!d_unhashed(dentry)) { ___d_drop(dentry); dentry->d_hash.pprev = NULL; write_seqcount_invalidate(&dentry->d_seq); } } EXPORT_SYMBOL(__d_drop); /** * d_drop - drop a dentry * @dentry: dentry to drop * * d_drop() unhashes the entry from the parent dentry hashes, so that it won't * be found through a VFS lookup any more. Note that this is different from * deleting the dentry - d_delete will try to mark the dentry negative if * possible, giving a successful _negative_ lookup, while d_drop will * just make the cache lookup fail. * * d_drop() is used mainly for stuff that wants to invalidate a dentry for some * reason (NFS timeouts or autofs deletes). * * __d_drop requires dentry->d_lock * * ___d_drop doesn't mark dentry as "unhashed" * (dentry->d_hash.pprev will be LIST_POISON2, not NULL). */ void d_drop(struct dentry *dentry) { spin_lock(&dentry->d_lock); __d_drop(dentry); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL_NS(d_drop, ANDROID_GKI_VFS_EXPORT_ONLY); static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent) { struct dentry *next; /* * Inform d_walk() and shrink_dentry_list() that we are no longer * attached to the dentry tree */ dentry->d_flags |= DCACHE_DENTRY_KILLED; if (unlikely(list_empty(&dentry->d_child))) return; __list_del_entry(&dentry->d_child); /* * Cursors can move around the list of children. While we'd been * a normal list member, it didn't matter - ->d_child.next would've * been updated. However, from now on it won't be and for the * things like d_walk() it might end up with a nasty surprise. * Normally d_walk() doesn't care about cursors moving around - * ->d_lock on parent prevents that and since a cursor has no children * of its own, we get through it without ever unlocking the parent. * There is one exception, though - if we ascend from a child that * gets killed as soon as we unlock it, the next sibling is found * using the value left in its ->d_child.next. And if _that_ * pointed to a cursor, and cursor got moved (e.g. by lseek()) * before d_walk() regains parent->d_lock, we'll end up skipping * everything the cursor had been moved past. * * Solution: make sure that the pointer left behind in ->d_child.next * points to something that won't be moving around. I.e. skip the * cursors. */ while (dentry->d_child.next != &parent->d_subdirs) { next = list_entry(dentry->d_child.next, struct dentry, d_child); if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR))) break; dentry->d_child.next = next->d_child.next; } } static void __dentry_kill(struct dentry *dentry) { struct dentry *parent = NULL; bool can_free = true; if (!IS_ROOT(dentry)) parent = dentry->d_parent; /* * The dentry is now unrecoverably dead to the world. */ lockref_mark_dead(&dentry->d_lockref); /* * inform the fs via d_prune that this dentry is about to be * unhashed and destroyed. */ if (dentry->d_flags & DCACHE_OP_PRUNE) dentry->d_op->d_prune(dentry); if (dentry->d_flags & DCACHE_LRU_LIST) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) d_lru_del(dentry); } /* if it was on the hash then remove it */ __d_drop(dentry); dentry_unlist(dentry, parent); if (parent) spin_unlock(&parent->d_lock); if (dentry->d_inode) dentry_unlink_inode(dentry); else spin_unlock(&dentry->d_lock); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); spin_lock(&dentry->d_lock); if (dentry->d_flags & DCACHE_SHRINK_LIST) { dentry->d_flags |= DCACHE_MAY_FREE; can_free = false; } spin_unlock(&dentry->d_lock); if (likely(can_free)) dentry_free(dentry); cond_resched(); } static struct dentry *__lock_parent(struct dentry *dentry) { struct dentry *parent; rcu_read_lock(); spin_unlock(&dentry->d_lock); again: parent = READ_ONCE(dentry->d_parent); spin_lock(&parent->d_lock); /* * We can't blindly lock dentry until we are sure * that we won't violate the locking order. * Any changes of dentry->d_parent must have * been done with parent->d_lock held, so * spin_lock() above is enough of a barrier * for checking if it's still our child. */ if (unlikely(parent != dentry->d_parent)) { spin_unlock(&parent->d_lock); goto again; } rcu_read_unlock(); if (parent != dentry) spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); else parent = NULL; return parent; } static inline struct dentry *lock_parent(struct dentry *dentry) { struct dentry *parent = dentry->d_parent; if (IS_ROOT(dentry)) return NULL; if (likely(spin_trylock(&parent->d_lock))) return parent; return __lock_parent(dentry); } static inline bool retain_dentry(struct dentry *dentry) { WARN_ON(d_in_lookup(dentry)); /* Unreachable? Get rid of it */ if (unlikely(d_unhashed(dentry))) return false; if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED)) return false; if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) { if (dentry->d_op->d_delete(dentry)) return false; } if (unlikely(dentry->d_flags & DCACHE_DONTCACHE)) return false; /* retain; LRU fodder */ dentry->d_lockref.count--; if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST))) d_lru_add(dentry); else if (unlikely(!(dentry->d_flags & DCACHE_REFERENCED))) dentry->d_flags |= DCACHE_REFERENCED; return true; } void d_mark_dontcache(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); hlist_for_each_entry(de, &inode->i_dentry, d_u.d_alias) { spin_lock(&de->d_lock); de->d_flags |= DCACHE_DONTCACHE; spin_unlock(&de->d_lock); } inode->i_state |= I_DONTCACHE; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_mark_dontcache); /* * Finish off a dentry we've decided to kill. * dentry->d_lock must be held, returns with it unlocked. * Returns dentry requiring refcount drop, or NULL if we're done. */ static struct dentry *dentry_kill(struct dentry *dentry) __releases(dentry->d_lock) { struct inode *inode = dentry->d_inode; struct dentry *parent = NULL; if (inode && unlikely(!spin_trylock(&inode->i_lock))) goto slow_positive; if (!IS_ROOT(dentry)) { parent = dentry->d_parent; if (unlikely(!spin_trylock(&parent->d_lock))) { parent = __lock_parent(dentry); if (likely(inode || !dentry->d_inode)) goto got_locks; /* negative that became positive */ if (parent) spin_unlock(&parent->d_lock); inode = dentry->d_inode; goto slow_positive; } } __dentry_kill(dentry); return parent; slow_positive: spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); parent = lock_parent(dentry); got_locks: if (unlikely(dentry->d_lockref.count != 1)) { dentry->d_lockref.count--; } else if (likely(!retain_dentry(dentry))) { __dentry_kill(dentry); return parent; } /* we are keeping it, after all */ if (inode) spin_unlock(&inode->i_lock); if (parent) spin_unlock(&parent->d_lock); spin_unlock(&dentry->d_lock); return NULL; } /* * Try to do a lockless dput(), and return whether that was successful. * * If unsuccessful, we return false, having already taken the dentry lock. * * The caller needs to hold the RCU read lock, so that the dentry is * guaranteed to stay around even if the refcount goes down to zero! */ static inline bool fast_dput(struct dentry *dentry) { int ret; unsigned int d_flags; /* * If we have a d_op->d_delete() operation, we sould not * let the dentry count go to zero, so use "put_or_lock". */ if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) return lockref_put_or_lock(&dentry->d_lockref); /* * .. otherwise, we can try to just decrement the * lockref optimistically. */ ret = lockref_put_return(&dentry->d_lockref); /* * If the lockref_put_return() failed due to the lock being held * by somebody else, the fast path has failed. We will need to * get the lock, and then check the count again. */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } dentry->d_lockref.count--; goto locked; } /* * If we weren't the last ref, we're done. */ if (ret) return true; /* * Careful, careful. The reference count went down * to zero, but we don't hold the dentry lock, so * somebody else could get it again, and do another * dput(), and we need to not race with that. * * However, there is a very special and common case * where we don't care, because there is nothing to * do: the dentry is still hashed, it does not have * a 'delete' op, and it's referenced and already on * the LRU list. * * NOTE! Since we aren't locked, these values are * not "stable". However, it is sufficient that at * some point after we dropped the reference the * dentry was hashed and the flags had the proper * value. Other dentry users may have re-gotten * a reference to the dentry and change that, but * our work is done - we can leave the dentry * around with a zero refcount. * * Nevertheless, there are two cases that we should kill * the dentry anyway. * 1. free disconnected dentries as soon as their refcount * reached zero. * 2. free dentries if they should not be cached. */ smp_rmb(); d_flags = READ_ONCE(dentry->d_flags); d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | DCACHE_DISCONNECTED | DCACHE_DONTCACHE; /* Nothing to do? Dropping the reference was all we needed? */ if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry)) return true; /* * Not the fast normal case? Get the lock. We've already decremented * the refcount, but we'll need to re-check the situation after * getting the lock. */ spin_lock(&dentry->d_lock); /* * Did somebody else grab a reference to it in the meantime, and * we're no longer the last user after all? Alternatively, somebody * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ locked: if (dentry->d_lockref.count) { spin_unlock(&dentry->d_lock); return true; } /* * Re-get the reference we optimistically dropped. We hold the * lock, and we just tested that it was zero, so we can just * set it to 1. */ dentry->d_lockref.count = 1; return false; } /* * This is dput * * This is complicated by the fact that we do not want to put * dentries that are no longer on any hash chain on the unused * list: we'd much rather just get rid of them immediately. * * However, that implies that we have to traverse the dentry * tree upwards to the parents which might _also_ now be * scheduled for deletion (it may have been only waiting for * its last child to go away). * * This tail recursion is done by hand as we don't want to depend * on the compiler to always get this right (gcc generally doesn't). * Real recursion would eat up our stack space. */ /* * dput - release a dentry * @dentry: dentry to release * * Release a dentry. This will drop the usage count and if appropriate * call the dentry unlink method as well as removing it from the queues and * releasing its resources. If the parent dentries were scheduled for release * they too may now get deleted. */ void dput(struct dentry *dentry) { while (dentry) { might_sleep(); rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } /* Slow case: now with the dentry lock held */ rcu_read_unlock(); if (likely(retain_dentry(dentry))) { spin_unlock(&dentry->d_lock); return; } dentry = dentry_kill(dentry); } } EXPORT_SYMBOL(dput); static void __dput_to_list(struct dentry *dentry, struct list_head *list) __must_hold(&dentry->d_lock) { if (dentry->d_flags & DCACHE_SHRINK_LIST) { /* let the owner of the list it's on deal with it */ --dentry->d_lockref.count; } else { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); if (!--dentry->d_lockref.count) d_shrink_add(dentry, list); } } void dput_to_list(struct dentry *dentry, struct list_head *list) { rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } rcu_read_unlock(); if (!retain_dentry(dentry)) __dput_to_list(dentry, list); spin_unlock(&dentry->d_lock); } /* This must be called with d_lock held */ static inline void __dget_dlock(struct dentry *dentry) { dentry->d_lockref.count++; } static inline void __dget(struct dentry *dentry) { lockref_get(&dentry->d_lockref); } struct dentry *dget_parent(struct dentry *dentry) { int gotref; struct dentry *ret; unsigned seq; /* * Do optimistic parent lookup without any * locking. */ rcu_read_lock(); seq = raw_seqcount_begin(&dentry->d_seq); ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; dput(ret); } repeat: /* * Don't need rcu_dereference because we re-check it was correct under * the lock. */ rcu_read_lock(); ret = dentry->d_parent; spin_lock(&ret->d_lock); if (unlikely(ret != dentry->d_parent)) { spin_unlock(&ret->d_lock); rcu_read_unlock(); goto repeat; } rcu_read_unlock(); BUG_ON(!ret->d_lockref.count); ret->d_lockref.count++; spin_unlock(&ret->d_lock); return ret; } EXPORT_SYMBOL_NS(dget_parent, ANDROID_GKI_VFS_EXPORT_ONLY); static struct dentry * __d_find_any_alias(struct inode *inode) { struct dentry *alias; if (hlist_empty(&inode->i_dentry)) return NULL; alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); __dget(alias); return alias; } /** * d_find_any_alias - find any alias for a given inode * @inode: inode to find an alias for * * If any aliases exist for the given inode, take and return a * reference for one of them. If no aliases exist, return %NULL. */ struct dentry *d_find_any_alias(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); de = __d_find_any_alias(inode); spin_unlock(&inode->i_lock); return de; } EXPORT_SYMBOL(d_find_any_alias); static struct dentry *__d_find_alias(struct inode *inode) { struct dentry *alias; if (S_ISDIR(inode->i_mode)) return __d_find_any_alias(inode); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { __dget_dlock(alias); spin_unlock(&alias->d_lock); return alias; } spin_unlock(&alias->d_lock); } return NULL; } /** * d_find_alias - grab a hashed alias of inode * @inode: inode in question * * If inode has a hashed alias, or is a directory and has any alias, * acquire the reference to alias and return it. Otherwise return NULL. * Notice that if inode is a directory there can be only one alias and * it can be unhashed only if it has no children, or if it is the root * of a filesystem, or if the directory was renamed and d_revalidate * was the first vfs operation to notice. * * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer * any other hashed alias over that one. */ struct dentry *d_find_alias(struct inode *inode) { struct dentry *de = NULL; if (!hlist_empty(&inode->i_dentry)) { spin_lock(&inode->i_lock); de = __d_find_alias(inode); spin_unlock(&inode->i_lock); } return de; } EXPORT_SYMBOL(d_find_alias); /* * Caller MUST be holding rcu_read_lock() and be guaranteed * that inode won't get freed until rcu_read_unlock(). */ struct dentry *d_find_alias_rcu(struct inode *inode) { struct hlist_head *l = &inode->i_dentry; struct dentry *de = NULL; spin_lock(&inode->i_lock); // ->i_dentry and ->i_rcu are colocated, but the latter won't be // used without having I_FREEING set, which means no aliases left if (likely(!(inode->i_state & I_FREEING) && !hlist_empty(l))) { if (S_ISDIR(inode->i_mode)) { de = hlist_entry(l->first, struct dentry, d_u.d_alias); } else { hlist_for_each_entry(de, l, d_u.d_alias) if (!d_unhashed(de)) break; } } spin_unlock(&inode->i_lock); return de; } /* * Try to kill dentries associated with this inode. * WARNING: you must own a reference to inode. */ void d_prune_aliases(struct inode *inode) { struct dentry *dentry; restart: spin_lock(&inode->i_lock); hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_lockref.count) { struct dentry *parent = lock_parent(dentry); if (likely(!dentry->d_lockref.count)) { __dentry_kill(dentry); dput(parent); goto restart; } if (parent) spin_unlock(&parent->d_lock); } spin_unlock(&dentry->d_lock); } spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_prune_aliases); /* * Lock a dentry from shrink list. * Called under rcu_read_lock() and dentry->d_lock; the former * guarantees that nothing we access will be freed under us. * Note that dentry is *not* protected from concurrent dentry_kill(), * d_delete(), etc. * * Return false if dentry has been disrupted or grabbed, leaving * the caller to kick it off-list. Otherwise, return true and have * that dentry's inode and parent both locked. */ static bool shrink_lock_dentry(struct dentry *dentry) { struct inode *inode; struct dentry *parent; if (dentry->d_lockref.count) return false; inode = dentry->d_inode; if (inode && unlikely(!spin_trylock(&inode->i_lock))) { spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); if (unlikely(dentry->d_lockref.count)) goto out; /* changed inode means that somebody had grabbed it */ if (unlikely(inode != dentry->d_inode)) goto out; } parent = dentry->d_parent; if (IS_ROOT(dentry) || likely(spin_trylock(&parent->d_lock))) return true; spin_unlock(&dentry->d_lock); spin_lock(&parent->d_lock); if (unlikely(parent != dentry->d_parent)) { spin_unlock(&parent->d_lock); spin_lock(&dentry->d_lock); goto out; } spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); if (likely(!dentry->d_lockref.count)) return true; spin_unlock(&parent->d_lock); out: if (inode) spin_unlock(&inode->i_lock); return false; } void shrink_dentry_list(struct list_head *list) { while (!list_empty(list)) { struct dentry *dentry, *parent; dentry = list_entry(list->prev, struct dentry, d_lru); spin_lock(&dentry->d_lock); rcu_read_lock(); if (!shrink_lock_dentry(dentry)) { bool can_free = false; rcu_read_unlock(); d_shrink_del(dentry); if (dentry->d_lockref.count < 0) can_free = dentry->d_flags & DCACHE_MAY_FREE; spin_unlock(&dentry->d_lock); if (can_free) dentry_free(dentry); continue; } rcu_read_unlock(); d_shrink_del(dentry); parent = dentry->d_parent; if (parent != dentry) __dput_to_list(parent, list); __dentry_kill(dentry); } } static enum lru_status dentry_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; /* * Referenced dentries are still in use. If they have active * counts, just remove them from the LRU. Otherwise give them * another pass through the LRU. */ if (dentry->d_lockref.count) { d_lru_isolate(lru, dentry); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } if (dentry->d_flags & DCACHE_REFERENCED) { dentry->d_flags &= ~DCACHE_REFERENCED; spin_unlock(&dentry->d_lock); /* * The list move itself will be made by the common LRU code. At * this point, we've dropped the dentry->d_lock but keep the * lru lock. This is safe to do, since every list movement is * protected by the lru lock even if both locks are held. * * This is guaranteed by the fact that all LRU management * functions are intermediated by the LRU API calls like * list_lru_add and list_lru_del. List movement in this file * only ever occur through this functions or through callbacks * like this one, that are called from the LRU API. * * The only exceptions to this are functions like * shrink_dentry_list, and code that first checks for the * DCACHE_SHRINK_LIST flag. Those are guaranteed to be * operating only with stack provided lists after they are * properly isolated from the main list. It is thus, always a * local access. */ return LRU_ROTATE; } d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * prune_dcache_sb - shrink the dcache * @sb: superblock * @sc: shrink control, passed to list_lru_shrink_walk() * * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This * is done when we need more memory and called from the superblock shrinker * function. * * This function may fail to free any resources if all the dentries are in * use. */ long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(dispose); long freed; freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc, dentry_lru_isolate, &dispose); shrink_dentry_list(&dispose); return freed; } static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock * * Shrink the dcache for the specified super block. This is used to free * the dcache before unmounting a file system. */ void shrink_dcache_sb(struct super_block *sb) { do { LIST_HEAD(dispose); list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); shrink_dentry_list(&dispose); } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); /** * enum d_walk_ret - action to talke during tree walk * @D_WALK_CONTINUE: contrinue walk * @D_WALK_QUIT: quit walk * @D_WALK_NORETRY: quit when retry is needed * @D_WALK_SKIP: skip this dentry and its children */ enum d_walk_ret { D_WALK_CONTINUE, D_WALK_QUIT, D_WALK_NORETRY, D_WALK_SKIP, }; /** * d_walk - walk the dentry tree * @parent: start of walk * @data: data passed to @enter() and @finish() * @enter: callback when first entering the dentry * * The @enter() callbacks are called with d_lock held. */ static void d_walk(struct dentry *parent, void *data, enum d_walk_ret (*enter)(void *, struct dentry *)) { struct dentry *this_parent; struct list_head *next; unsigned seq = 0; enum d_walk_ret ret; bool retry = true; again: read_seqbegin_or_lock(&rename_lock, &seq); this_parent = parent; spin_lock(&this_parent->d_lock); ret = enter(data, this_parent); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: case D_WALK_SKIP: goto out_unlock; case D_WALK_NORETRY: retry = false; break; } repeat: next = this_parent->d_subdirs.next; resume: while (next != &this_parent->d_subdirs) { struct list_head *tmp = next; struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) continue; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); ret = enter(data, dentry); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: spin_unlock(&dentry->d_lock); goto out_unlock; case D_WALK_NORETRY: retry = false; break; case D_WALK_SKIP: spin_unlock(&dentry->d_lock); continue; } if (!list_empty(&dentry->d_subdirs)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, _RET_IP_); this_parent = dentry; spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; } spin_unlock(&dentry->d_lock); } /* * All done at this level ... ascend and resume the search. */ rcu_read_lock(); ascend: if (this_parent != parent) { struct dentry *child = this_parent; this_parent = child->d_parent; spin_unlock(&child->d_lock); spin_lock(&this_parent->d_lock); /* might go back up the wrong parent if we have had a rename. */ if (need_seqretry(&rename_lock, seq)) goto rename_retry; /* go into the first sibling still alive */ do { next = child->d_child.next; if (next == &this_parent->d_subdirs) goto ascend; child = list_entry(next, struct dentry, d_child); } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); rcu_read_unlock(); goto resume; } if (need_seqretry(&rename_lock, seq)) goto rename_retry; rcu_read_unlock(); out_unlock: spin_unlock(&this_parent->d_lock); done_seqretry(&rename_lock, seq); return; rename_retry: spin_unlock(&this_parent->d_lock); rcu_read_unlock(); BUG_ON(seq & 1); if (!retry) return; seq = 1; goto again; } struct check_mount { struct vfsmount *mnt; unsigned int mounted; }; static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry) { struct check_mount *info = data; struct path path = { .mnt = info->mnt, .dentry = dentry }; if (likely(!d_mountpoint(dentry))) return D_WALK_CONTINUE; if (__path_is_mountpoint(&path)) { info->mounted = 1; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * path_has_submounts - check for mounts over a dentry in the * current namespace. * @parent: path to check. * * Return true if the parent or its subdirectories contain * a mount point in the current namespace. */ int path_has_submounts(const struct path *parent) { struct check_mount data = { .mnt = parent->mnt, .mounted = 0 }; read_seqlock_excl(&mount_lock); d_walk(parent->dentry, &data, path_check_mount); read_sequnlock_excl(&mount_lock); return data.mounted; } EXPORT_SYMBOL(path_has_submounts); /* * Called by mount code to set a mountpoint and check if the mountpoint is * reachable (e.g. NFS can unhash a directory dentry and then the complete * subtree can become unreachable). * * Only one of d_invalidate() and d_set_mounted() must succeed. For * this reason take rename_lock and d_lock on dentry and ancestors. */ int d_set_mounted(struct dentry *dentry) { struct dentry *p; int ret = -ENOENT; write_seqlock(&rename_lock); for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) { /* Need exclusion wrt. d_invalidate() */ spin_lock(&p->d_lock); if (unlikely(d_unhashed(p))) { spin_unlock(&p->d_lock); goto out; } spin_unlock(&p->d_lock); } spin_lock(&dentry->d_lock); if (!d_unlinked(dentry)) { ret = -EBUSY; if (!d_mountpoint(dentry)) { dentry->d_flags |= DCACHE_MOUNTED; ret = 0; } } spin_unlock(&dentry->d_lock); out: write_sequnlock(&rename_lock); return ret; } /* * Search the dentry child list of the specified parent, * and move any unused dentries to the end of the unused * list for prune_dcache(). We descend to the next level * whenever the d_subdirs list is non-empty and continue * searching. * * It returns zero iff there are no unused children, * otherwise it returns the number of children moved to * the end of the unused list. This may not be the total * number of unused children, because select_parent can * drop the lock and return early due to latency * constraints. */ struct select_data { struct dentry *start; union { long found; struct dentry *victim; }; struct list_head dispose; }; static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { data->found++; } else { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); if (!dentry->d_lockref.count) { d_shrink_add(dentry, &data->dispose); data->found++; } } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { if (!dentry->d_lockref.count) { rcu_read_lock(); data->victim = dentry; return D_WALK_QUIT; } } else { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); if (!dentry->d_lockref.count) d_shrink_add(dentry, &data->dispose); } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } /** * shrink_dcache_parent - prune dcache * @parent: parent of entries to prune * * Prune the dcache to remove unused children of the parent dentry. */ void shrink_dcache_parent(struct dentry *parent) { for (;;) { struct select_data data = {.start = parent}; INIT_LIST_HEAD(&data.dispose); d_walk(parent, &data, select_collect); if (!list_empty(&data.dispose)) { shrink_dentry_list(&data.dispose); continue; } cond_resched(); if (!data.found) break; data.victim = NULL; d_walk(parent, &data, select_collect2); if (data.victim) { struct dentry *parent; spin_lock(&data.victim->d_lock); if (!shrink_lock_dentry(data.victim)) { spin_unlock(&data.victim->d_lock); rcu_read_unlock(); } else { rcu_read_unlock(); parent = data.victim->d_parent; if (parent != data.victim) __dput_to_list(parent, &data.dispose); __dentry_kill(data.victim); } } if (!list_empty(&data.dispose)) shrink_dentry_list(&data.dispose); } } EXPORT_SYMBOL(shrink_dcache_parent); static enum d_walk_ret umount_check(void *_data, struct dentry *dentry) { /* it has busy descendents; complain about those instead */ if (!list_empty(&dentry->d_subdirs)) return D_WALK_CONTINUE; /* root with refcount 1 is fine */ if (dentry == _data && dentry->d_lockref.count == 1) return D_WALK_CONTINUE; printk(KERN_ERR "BUG: Dentry %p{i=%lx,n=%pd} " " still in use (%d) [unmount of %s %s]\n", dentry, dentry->d_inode ? dentry->d_inode->i_ino : 0UL, dentry, dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); WARN_ON(1); return D_WALK_CONTINUE; } static void do_one_tree(struct dentry *dentry) { shrink_dcache_parent(dentry); d_walk(dentry, dentry, umount_check); d_drop(dentry); dput(dentry); } /* * destroy the dentries attached to a superblock on unmounting */ void shrink_dcache_for_umount(struct super_block *sb) { struct dentry *dentry; WARN(down_read_trylock(&sb->s_umount), "s_umount should've been locked"); dentry = sb->s_root; sb->s_root = NULL; do_one_tree(dentry); while (!hlist_bl_empty(&sb->s_roots)) { dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_roots), struct dentry, d_hash)); do_one_tree(dentry); } } static enum d_walk_ret find_submount(void *_data, struct dentry *dentry) { struct dentry **victim = _data; if (d_mountpoint(dentry)) { __dget_dlock(dentry); *victim = dentry; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * d_invalidate - detach submounts, prune dcache, and drop * @dentry: dentry to invalidate (aka detach, prune and drop) */ void d_invalidate(struct dentry *dentry) { bool had_submounts = false; spin_lock(&dentry->d_lock); if (d_unhashed(dentry)) { spin_unlock(&dentry->d_lock); return; } __d_drop(dentry); spin_unlock(&dentry->d_lock); /* Negative dentries can be dropped without further checks */ if (!dentry->d_inode) return; shrink_dcache_parent(dentry); for (;;) { struct dentry *victim = NULL; d_walk(dentry, &victim, find_submount); if (!victim) { if (had_submounts) shrink_dcache_parent(dentry); return; } had_submounts = true; detach_mounts(victim); dput(victim); } } EXPORT_SYMBOL(d_invalidate); /** * __d_alloc - allocate a dcache entry * @sb: filesystem it will belong to * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) { struct dentry *dentry; char *dname; int err; dentry = kmem_cache_alloc(dentry_cache, GFP_KERNEL); if (!dentry) return NULL; /* * We guarantee that the inline name is always NUL-terminated. * This way the memcpy() done by the name switching in rename * will still always have a NUL at the end, even if we might * be overwriting an internal NUL character */ dentry->d_iname[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { name = &slash_name; dname = dentry->d_iname; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT | __GFP_RECLAIMABLE); if (!p) { kmem_cache_free(dentry_cache, dentry); return NULL; } atomic_set(&p->u.count, 1); dname = p->name; } else { dname = dentry->d_iname; } dentry->d_name.len = name->len; dentry->d_name.hash = name->hash; memcpy(dname, name->name, name->len); dname[name->len] = 0; /* Make sure we always see the terminating NUL character */ smp_store_release(&dentry->d_name.name, dname); /* ^^^ */ dentry->d_lockref.count = 1; dentry->d_flags = 0; spin_lock_init(&dentry->d_lock); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; dentry->d_sb = sb; dentry->d_op = NULL; dentry->d_fsdata = NULL; INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_LIST_HEAD(&dentry->d_subdirs); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_LIST_HEAD(&dentry->d_child); d_set_d_op(dentry, dentry->d_sb->s_d_op); if (dentry->d_op && dentry->d_op->d_init) { err = dentry->d_op->d_init(dentry); if (err) { if (dname_external(dentry)) kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); return NULL; } } this_cpu_inc(nr_dentry); return dentry; } /** * d_alloc - allocate a dcache entry * @parent: parent of entry to allocate * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) { struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject * to concurrency here */ __dget_dlock(parent); dentry->d_parent = parent; list_add(&dentry->d_child, &parent->d_subdirs); spin_unlock(&parent->d_lock); return dentry; } EXPORT_SYMBOL(d_alloc); struct dentry *d_alloc_anon(struct super_block *sb) { return __d_alloc(sb, NULL); } EXPORT_SYMBOL(d_alloc_anon); struct dentry *d_alloc_cursor(struct dentry * parent) { struct dentry *dentry = d_alloc_anon(parent->d_sb); if (dentry) { dentry->d_flags |= DCACHE_DENTRY_CURSOR; dentry->d_parent = dget(parent); } return dentry; } /** * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems) * @sb: the superblock * @name: qstr of the name * * For a filesystem that just pins its dentries in memory and never * performs lookups at all, return an unhashed IS_ROOT dentry. * This is used for pipes, sockets et.al. - the stuff that should * never be anyone's children or parents. Unlike all other * dentries, these will not have RCU delay between dropping the * last reference and freeing them. * * The only user is alloc_file_pseudo() and that's what should * be considered a public interface. Don't use directly. */ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name) { struct dentry *dentry = __d_alloc(sb, name); if (likely(dentry)) dentry->d_flags |= DCACHE_NORCU; return dentry; } struct dentry *d_alloc_name(struct dentry *parent, const char *name) { struct qstr q; q.name = name; q.hash_len = hashlen_string(parent, name); return d_alloc(parent, &q); } EXPORT_SYMBOL(d_alloc_name); void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) { WARN_ON_ONCE(dentry->d_op); WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH | DCACHE_OP_COMPARE | DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE | DCACHE_OP_DELETE | DCACHE_OP_REAL)); dentry->d_op = op; if (!op) return; if (op->d_hash) dentry->d_flags |= DCACHE_OP_HASH; if (op->d_compare) dentry->d_flags |= DCACHE_OP_COMPARE; if (op->d_revalidate) dentry->d_flags |= DCACHE_OP_REVALIDATE; if (op->d_weak_revalidate) dentry->d_flags |= DCACHE_OP_WEAK_REVALIDATE; if (op->d_delete) dentry->d_flags |= DCACHE_OP_DELETE; if (op->d_prune) dentry->d_flags |= DCACHE_OP_PRUNE; if (op->d_real) dentry->d_flags |= DCACHE_OP_REAL; } EXPORT_SYMBOL_NS(d_set_d_op, ANDROID_GKI_VFS_EXPORT_ONLY); /* * d_set_fallthru - Mark a dentry as falling through to a lower layer * @dentry - The dentry to mark * * Mark a dentry as falling through to the lower layer (as set with * d_pin_lower()). This flag may be recorded on the medium. */ void d_set_fallthru(struct dentry *dentry) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_FALLTHRU; spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_set_fallthru); static unsigned d_flags_for_inode(struct inode *inode) { unsigned add_flags = DCACHE_REGULAR_TYPE; if (!inode) return DCACHE_MISS_TYPE; if (S_ISDIR(inode->i_mode)) { add_flags = DCACHE_DIRECTORY_TYPE; if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) { if (unlikely(!inode->i_op->lookup)) add_flags = DCACHE_AUTODIR_TYPE; else inode->i_opflags |= IOP_LOOKUP; } goto type_determined; } if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { if (unlikely(inode->i_op->get_link)) { add_flags = DCACHE_SYMLINK_TYPE; goto type_determined; } inode->i_opflags |= IOP_NOFOLLOW; } if (unlikely(!S_ISREG(inode->i_mode))) add_flags = DCACHE_SPECIAL_TYPE; type_determined: if (unlikely(IS_AUTOMOUNT(inode))) add_flags |= DCACHE_NEED_AUTOMOUNT; return add_flags; } static void __d_instantiate(struct dentry *dentry, struct inode *inode) { unsigned add_flags = d_flags_for_inode(inode); WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); /* * The negative counter only tracks dentries on the LRU. Don't dec if * d_lru is on another list. */ if ((dentry->d_flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); spin_unlock(&dentry->d_lock); } /** * d_instantiate - fill in inode information for a dentry * @entry: dentry to complete * @inode: inode to attach to this dentry * * Fill in inode information in the entry. * * This turns negative dentries into productive full members * of society. * * NOTE! This assumes that the inode count has been incremented * (or otherwise set) by the caller to indicate that it is now * in use by the dcache. */ void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_instantiate); /* * This should be equivalent to d_instantiate() + unlock_new_inode(), * with lockdep-related part of unlock_new_inode() done before * anything else. Use that instead of open-coding d_instantiate()/ * unlock_new_inode() combinations. */ void d_instantiate_new(struct dentry *entry, struct inode *inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); BUG_ON(!inode); lockdep_annotate_inode_mutex_key(inode); security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_instantiate_new); struct dentry *d_make_root(struct inode *root_inode) { struct dentry *res = NULL; if (root_inode) { res = d_alloc_anon(root_inode->i_sb); if (res) d_instantiate(res, root_inode); else iput(root_inode); } return res; } EXPORT_SYMBOL(d_make_root); static struct dentry *__d_instantiate_anon(struct dentry *dentry, struct inode *inode, bool disconnected) { struct dentry *res; unsigned add_flags; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); res = __d_find_any_alias(inode); if (res) { spin_unlock(&inode->i_lock); dput(dentry); goto out_iput; } /* attach a disconnected dentry */ add_flags = d_flags_for_inode(inode); if (disconnected) add_flags |= DCACHE_DISCONNECTED; spin_lock(&dentry->d_lock); __d_set_inode_and_type(dentry, inode, add_flags); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); if (!disconnected) { hlist_bl_lock(&dentry->d_sb->s_roots); hlist_bl_add_head(&dentry->d_hash, &dentry->d_sb->s_roots); hlist_bl_unlock(&dentry->d_sb->s_roots); } spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); return dentry; out_iput: iput(inode); return res; } struct dentry *d_instantiate_anon(struct dentry *dentry, struct inode *inode) { return __d_instantiate_anon(dentry, inode, true); } EXPORT_SYMBOL(d_instantiate_anon); static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected) { struct dentry *tmp; struct dentry *res; if (!inode) return ERR_PTR(-ESTALE); if (IS_ERR(inode)) return ERR_CAST(inode); res = d_find_any_alias(inode); if (res) goto out_iput; tmp = d_alloc_anon(inode->i_sb); if (!tmp) { res = ERR_PTR(-ENOMEM); goto out_iput; } return __d_instantiate_anon(tmp, inode, disconnected); out_iput: iput(inode); return res; } /** * d_obtain_alias - find or allocate a DISCONNECTED dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain a dentry for an inode resulting from NFS filehandle conversion or * similar open by handle operations. The returned dentry may be anonymous, * or may have a full name (if the inode was already in the cache). * * When called on a directory inode, we must ensure that the inode only ever * has one dentry. If a dentry is found, that is returned instead of * allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is released. * To make it easier to use in export operations a %NULL or IS_ERR inode may * be passed in and the error will be propagated to the return value, * with a %NULL @inode replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_alias(struct inode *inode) { return __d_obtain_alias(inode, true); } EXPORT_SYMBOL_NS(d_obtain_alias, ANDROID_GKI_VFS_EXPORT_ONLY); /** * d_obtain_root - find or allocate a dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain an IS_ROOT dentry for the root of a filesystem. * * We must ensure that directory inodes only ever have one dentry. If a * dentry is found, that is returned instead of allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is * released. A %NULL or IS_ERR inode may be passed in and will be the * error will be propagate to the return value, with a %NULL @inode * replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_root(struct inode *inode) { return __d_obtain_alias(inode, false); } EXPORT_SYMBOL(d_obtain_root); /** * d_add_ci - lookup or allocate new dentry with case-exact name * @inode: the inode case-insensitive lookup has found * @dentry: the negative dentry that was passed to the parent's lookup func * @name: the case-exact name to be associated with the returned dentry * * This is to avoid filling the dcache with case-insensitive names to the * same inode, only the actual correct case is stored in the dcache for * case-insensitive filesystems. * * For a case-insensitive lookup match and if the case-exact dentry * already exists in the dcache, use it and return it. * * If no entry exists with the exact case name, allocate new dentry with * the exact case, and return the spliced entry. */ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, struct qstr *name) { struct dentry *found, *res; /* * First check if a dentry matching the name already exists, * if not go ahead and create it now. */ found = d_hash_and_lookup(dentry->d_parent, name); if (found) { iput(inode); return found; } if (d_in_lookup(dentry)) { found = d_alloc_parallel(dentry->d_parent, name, dentry->d_wait); if (IS_ERR(found) || !d_in_lookup(found)) { iput(inode); return found; } } else { found = d_alloc(dentry->d_parent, name); if (!found) { iput(inode); return ERR_PTR(-ENOMEM); } } res = d_splice_alias(inode, found); if (res) { dput(found); return res; } return found; } EXPORT_SYMBOL_NS(d_add_ci, ANDROID_GKI_VFS_EXPORT_ONLY); static inline bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name) { if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) { if (dentry->d_name.len != name->len) return false; return dentry_cmp(dentry, name->name, name->len) == 0; } return parent->d_op->d_compare(dentry, dentry->d_name.len, dentry->d_name.name, name) == 0; } /** * __d_lookup_rcu - search for a dentry (racy, store-free) * @parent: parent dentry * @name: qstr of name we wish to find * @seqp: returns d_seq value at the point where the dentry was found * Returns: dentry, or NULL * * __d_lookup_rcu is the dcache lookup function for rcu-walk name * resolution (store-free path walking) design described in * Documentation/filesystems/path-lookup.txt. * * This is not to be used outside core vfs. * * __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock * held, and rcu_read_lock held. The returned dentry must not be stored into * without taking d_lock and checking d_seq sequence count against @seq * returned here. * * A refcount may be taken on the found dentry with the d_rcu_to_refcount * function. * * Alternatively, __d_lookup_rcu may be called again to look up the child of * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks * is formed, giving integrity down the path walk. * * NOTE! The caller *has* to check the resulting dentry against the sequence * number we've returned before using any of the resulting dentry state! */ struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; const unsigned char *str = name->name; struct hlist_bl_head *b = d_hash(hashlen_hash(hashlen)); struct hlist_bl_node *node; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ /* * The hash list is protected using RCU. * * Carefully use d_seq when comparing a candidate dentry, to avoid * races with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; seqretry: /* * The dentry sequence count protects us from concurrent * renames, and thus protects parent and name fields. * * The caller must perform a seqcount check in order * to do anything useful with the returned dentry. * * NOTE! We do a "raw" seqcount_begin here. That means that * we don't wait for the sequence count to stabilize if it * is in the middle of a sequence change. If we do the slow * dentry compare, we will do seqretries until it is stable, * and if we end up with a successful lookup, we actually * want to exit RCU lookup anyway. * * Note that raw_seqcount_begin still *does* smp_rmb(), so * we are still guaranteed NUL-termination of ->d_name.name. */ seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) { int tlen; const char *tname; if (dentry->d_name.hash != hashlen_hash(hashlen)) continue; tlen = dentry->d_name.len; tname = dentry->d_name.name; /* we want a consistent (name,len) pair */ if (read_seqcount_retry(&dentry->d_seq, seq)) { cpu_relax(); goto seqretry; } if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0) continue; } else { if (dentry->d_name.hash_len != hashlen) continue; if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) continue; } *seqp = seq; return dentry; } return NULL; } /** * d_lookup - search for a dentry * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * d_lookup searches the children of the parent dentry for the name in * question. If the dentry is found its reference count is incremented and the * dentry is returned. The caller must use dput to free the entry when it has * finished using it. %NULL is returned if the dentry does not exist. */ struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name) { struct dentry *dentry; unsigned seq; do { seq = read_seqbegin(&rename_lock); dentry = __d_lookup(parent, name); if (dentry) break; } while (read_seqretry(&rename_lock, seq)); return dentry; } EXPORT_SYMBOL(d_lookup); /** * __d_lookup - search for a dentry (racy) * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * __d_lookup is like d_lookup, however it may (rarely) return a * false-negative result due to unrelated rename activity. * * __d_lookup is slightly faster by avoiding rename_lock read seqlock, * however it must be used carefully, eg. with a following d_lookup in * the case of failure. * * __d_lookup callers must be commented. */ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) { unsigned int hash = name->hash; struct hlist_bl_head *b = d_hash(hash); struct hlist_bl_node *node; struct dentry *found = NULL; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ /* * The hash list is protected using RCU. * * Take d_lock when comparing a candidate dentry, to avoid races * with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ rcu_read_lock(); hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { if (dentry->d_name.hash != hash) continue; spin_lock(&dentry->d_lock); if (dentry->d_parent != parent) goto next; if (d_unhashed(dentry)) goto next; if (!d_same_name(dentry, parent, name)) goto next; dentry->d_lockref.count++; found = dentry; spin_unlock(&dentry->d_lock); break; next: spin_unlock(&dentry->d_lock); } rcu_read_unlock(); return found; } /** * d_hash_and_lookup - hash the qstr then search for a dentry * @dir: Directory to search in * @name: qstr of name we wish to find * * On lookup failure NULL is returned; on bad name - ERR_PTR(-error) */ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name) { /* * Check for a fs-specific hash function. Note that we must * calculate the standard hash first, as the d_op->d_hash() * routine may choose to leave the hash value unchanged. */ name->hash = full_name_hash(dir, name->name, name->len); if (dir->d_flags & DCACHE_OP_HASH) { int err = dir->d_op->d_hash(dir, name); if (unlikely(err < 0)) return ERR_PTR(err); } return d_lookup(dir, name); } EXPORT_SYMBOL(d_hash_and_lookup); /* * When a file is deleted, we have two options: * - turn this dentry into a negative dentry * - unhash this dentry and free it. * * Usually, we want to just turn this into * a negative dentry, but if anybody else is * currently using the dentry or the inode * we can't do that and we fall back on removing * it from the hash queues and waiting for * it to be deleted later when it has no users */ /** * d_delete - delete a dentry * @dentry: The dentry to delete * * Turn the dentry into a negative dentry if possible, otherwise * remove it from the hash queues so it can be deleted later */ void d_delete(struct dentry * dentry) { struct inode *inode = dentry->d_inode; spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); /* * Are we the only user? */ if (dentry->d_lockref.count == 1) { dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); } else { __d_drop(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_delete); static void __d_rehash(struct dentry *entry) { struct hlist_bl_head *b = d_hash(entry->d_name.hash); hlist_bl_lock(b); hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b); } /** * d_rehash - add an entry back to the hash * @entry: dentry to add to the hash * * Adds a dentry to the hash according to its name. */ void d_rehash(struct dentry * entry) { spin_lock(&entry->d_lock); __d_rehash(entry); spin_unlock(&entry->d_lock); } EXPORT_SYMBOL_NS(d_rehash, ANDROID_GKI_VFS_EXPORT_ONLY); static inline unsigned start_dir_add(struct inode *dir) { for (;;) { unsigned n = dir->i_dir_seq; if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) return n; cpu_relax(); } } static inline void end_dir_add(struct inode *dir, unsigned n) { smp_store_release(&dir->i_dir_seq, n + 2); } static void d_wait_lookup(struct dentry *dentry) { if (d_in_lookup(dentry)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue(dentry->d_wait, &wait); do { set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&dentry->d_lock); schedule(); spin_lock(&dentry->d_lock); } while (d_in_lookup(dentry)); } } struct dentry *d_alloc_parallel(struct dentry *parent, const struct qstr *name, wait_queue_head_t *wq) { unsigned int hash = name->hash; struct hlist_bl_head *b = in_lookup_hash(parent, hash); struct hlist_bl_node *node; struct dentry *new = d_alloc(parent, name); struct dentry *dentry; unsigned seq, r_seq, d_seq; if (unlikely(!new)) return ERR_PTR(-ENOMEM); retry: rcu_read_lock(); seq = smp_load_acquire(&parent->d_inode->i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } if (read_seqcount_retry(&dentry->d_seq, d_seq)) { rcu_read_unlock(); dput(dentry); goto retry; } rcu_read_unlock(); dput(new); return dentry; } if (unlikely(read_seqretry(&rename_lock, r_seq))) { rcu_read_unlock(); goto retry; } if (unlikely(seq & 1)) { rcu_read_unlock(); goto retry; } hlist_bl_lock(b); if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; } /* * No changes for the parent since the beginning of d_lookup(). * Since all removals from the chain happen with hlist_bl_lock(), * any potential in-lookup matches are going to stay here until * we unlock the chain. All fields are stable in everything * we encounter. */ hlist_bl_for_each_entry(dentry, node, b, d_u.d_in_lookup_hash) { if (dentry->d_name.hash != hash) continue; if (dentry->d_parent != parent) continue; if (!d_same_name(dentry, parent, name)) continue; hlist_bl_unlock(b); /* now we can try to grab a reference */ if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } rcu_read_unlock(); /* * somebody is likely to be still doing lookup for it; * wait for them to finish */ spin_lock(&dentry->d_lock); d_wait_lookup(dentry); /* * it's not in-lookup anymore; in principle we should repeat * everything from dcache lookup, but it's likely to be what * d_lookup() would've found anyway. If it is, just return it; * otherwise we really have to repeat the whole thing. */ if (unlikely(dentry->d_name.hash != hash)) goto mismatch; if (unlikely(dentry->d_parent != parent)) goto mismatch; if (unlikely(d_unhashed(dentry))) goto mismatch; if (unlikely(!d_same_name(dentry, parent, name))) goto mismatch; /* OK, it *is* a hashed match; return it */ spin_unlock(&dentry->d_lock); dput(new); return dentry; } rcu_read_unlock(); /* we can't take ->d_lock here; it's OK, though. */ new->d_flags |= DCACHE_PAR_LOOKUP; new->d_wait = wq; hlist_bl_add_head_rcu(&new->d_u.d_in_lookup_hash, b); hlist_bl_unlock(b); return new; mismatch: spin_unlock(&dentry->d_lock); dput(dentry); goto retry; } EXPORT_SYMBOL(d_alloc_parallel); void __d_lookup_done(struct dentry *dentry) { struct hlist_bl_head *b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash); hlist_bl_lock(b); dentry->d_flags &= ~DCACHE_PAR_LOOKUP; __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); wake_up_all(dentry->d_wait); dentry->d_wait = NULL; hlist_bl_unlock(b); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_LIST_HEAD(&dentry->d_lru); } EXPORT_SYMBOL(__d_lookup_done); /* inode->i_lock held if inode is non-NULL */ static inline void __d_add(struct dentry *dentry, struct inode *inode) { struct inode *dir = NULL; unsigned n; spin_lock(&dentry->d_lock); if (unlikely(d_in_lookup(dentry))) { dir = dentry->d_parent->d_inode; n = start_dir_add(dir); __d_lookup_done(dentry); } if (inode) { unsigned add_flags = d_flags_for_inode(inode); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); } __d_rehash(dentry); if (dir) end_dir_add(dir, n); spin_unlock(&dentry->d_lock); if (inode) spin_unlock(&inode->i_lock); } /** * d_add - add dentry to hash queues * @entry: dentry to add * @inode: The inode to attach to this dentry * * This adds the entry to the hash queues and initializes @inode. * The entry was actually filled in earlier during d_alloc(). */ void d_add(struct dentry *entry, struct inode *inode) { if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); } __d_add(entry, inode); } EXPORT_SYMBOL(d_add); /** * d_exact_alias - find and hash an exact unhashed alias * @entry: dentry to add * @inode: The inode to go with this dentry * * If an unhashed dentry with the same name/parent and desired * inode already exists, hash and return it. Otherwise, return * NULL. * * Parent directory should be locked. */ struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) { struct dentry *alias; unsigned int hash = entry->d_name.hash; spin_lock(&inode->i_lock); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or * parent changes, because the parent inode i_mutex is held. */ if (alias->d_name.hash != hash) continue; if (alias->d_parent != entry->d_parent) continue; if (!d_same_name(alias, entry->d_parent, &entry->d_name)) continue; spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { spin_unlock(&alias->d_lock); alias = NULL; } else { __dget_dlock(alias); __d_rehash(alias); spin_unlock(&alias->d_lock); } spin_unlock(&inode->i_lock); return alias; } spin_unlock(&inode->i_lock); return NULL; } EXPORT_SYMBOL(d_exact_alias); static void swap_names(struct dentry *dentry, struct dentry *target) { if (unlikely(dname_external(target))) { if (unlikely(dname_external(dentry))) { /* * Both external: swap the pointers */ swap(target->d_name.name, dentry->d_name.name); } else { /* * dentry:internal, target:external. Steal target's * storage and make target internal. */ memcpy(target->d_iname, dentry->d_name.name, dentry->d_name.len + 1); dentry->d_name.name = target->d_name.name; target->d_name.name = target->d_iname; } } else { if (unlikely(dname_external(dentry))) { /* * dentry:external, target:internal. Give dentry's * storage to target and make dentry internal */ memcpy(dentry->d_iname, target->d_name.name, target->d_name.len + 1); target->d_name.name = dentry->d_name.name; dentry->d_name.name = dentry->d_iname; } else { /* * Both are internal. */ unsigned int i; BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long))); for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) { swap(((long *) &dentry->d_iname)[i], ((long *) &target->d_iname)[i]); } } } swap(dentry->d_name.hash_len, target->d_name.hash_len); } static void copy_name(struct dentry *dentry, struct dentry *target) { struct external_name *old_name = NULL; if (unlikely(dname_external(dentry))) old_name = external_name(dentry); if (unlikely(dname_external(target))) { atomic_inc(&external_name(target)->u.count); dentry->d_name = target->d_name; } else { memcpy(dentry->d_iname, target->d_name.name, target->d_name.len + 1); dentry->d_name.name = dentry->d_iname; dentry->d_name.hash_len = target->d_name.hash_len; } if (old_name && likely(atomic_dec_and_test(&old_name->u.count))) kfree_rcu(old_name, u.head); } /* * __d_move - move a dentry * @dentry: entry to move * @target: new dentry * @exchange: exchange the two dentries * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. Caller must hold * rename_lock, the i_mutex of the source and target directories, * and the sb->s_vfs_rename_mutex if they differ. See lock_rename(). */ static void __d_move(struct dentry *dentry, struct dentry *target, bool exchange) { struct dentry *old_parent, *p; struct inode *dir = NULL; unsigned n; WARN_ON(!dentry->d_inode); if (WARN_ON(dentry == target)) return; BUG_ON(d_ancestor(target, dentry)); old_parent = dentry->d_parent; p = d_ancestor(old_parent, target); if (IS_ROOT(dentry)) { BUG_ON(p); spin_lock(&target->d_parent->d_lock); } else if (!p) { /* target is not a descendent of dentry->d_parent */ spin_lock(&target->d_parent->d_lock); spin_lock_nested(&old_parent->d_lock, DENTRY_D_LOCK_NESTED); } else { BUG_ON(p == dentry); spin_lock(&old_parent->d_lock); if (p != target) spin_lock_nested(&target->d_parent->d_lock, DENTRY_D_LOCK_NESTED); } spin_lock_nested(&dentry->d_lock, 2); spin_lock_nested(&target->d_lock, 3); if (unlikely(d_in_lookup(target))) { dir = target->d_parent->d_inode; n = start_dir_add(dir); __d_lookup_done(target); } write_seqcount_begin(&dentry->d_seq); write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED); /* unhash both */ if (!d_unhashed(dentry)) ___d_drop(dentry); if (!d_unhashed(target)) ___d_drop(target); /* ... and switch them in the tree */ dentry->d_parent = target->d_parent; if (!exchange) { copy_name(dentry, target); target->d_hash.pprev = NULL; dentry->d_parent->d_lockref.count++; if (dentry != old_parent) /* wasn't IS_ROOT */ WARN_ON(!--old_parent->d_lockref.count); } else { target->d_parent = old_parent; swap_names(dentry, target); list_move(&target->d_child, &target->d_parent->d_subdirs); __d_rehash(target); fsnotify_update_flags(target); } list_move(&dentry->d_child, &dentry->d_parent->d_subdirs); __d_rehash(dentry); fsnotify_update_flags(dentry); fscrypt_handle_d_move(dentry); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); if (dir) end_dir_add(dir, n); if (dentry->d_parent != old_parent) spin_unlock(&dentry->d_parent->d_lock); if (dentry != old_parent) spin_unlock(&old_parent->d_lock); spin_unlock(&target->d_lock); spin_unlock(&dentry->d_lock); } /* * d_move - move a dentry * @dentry: entry to move * @target: new dentry * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. See the locking * requirements for __d_move. */ void d_move(struct dentry *dentry, struct dentry *target) { write_seqlock(&rename_lock); __d_move(dentry, target, false); write_sequnlock(&rename_lock); } EXPORT_SYMBOL_NS(d_move, ANDROID_GKI_VFS_EXPORT_ONLY); /* * d_exchange - exchange two dentries * @dentry1: first dentry * @dentry2: second dentry */ void d_exchange(struct dentry *dentry1, struct dentry *dentry2) { write_seqlock(&rename_lock); WARN_ON(!dentry1->d_inode); WARN_ON(!dentry2->d_inode); WARN_ON(IS_ROOT(dentry1)); WARN_ON(IS_ROOT(dentry2)); __d_move(dentry1, dentry2, true); write_sequnlock(&rename_lock); } /** * d_ancestor - search for an ancestor * @p1: ancestor dentry * @p2: child dentry * * Returns the ancestor dentry of p2 which is a child of p1, if p1 is * an ancestor of p2, else NULL. */ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) { struct dentry *p; for (p = p2; !IS_ROOT(p); p = p->d_parent) { if (p->d_parent == p1) return p; } return NULL; } /* * This helper attempts to cope with remotely renamed directories * * It assumes that the caller is already holding * dentry->d_parent->d_inode->i_mutex, and rename_lock * * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... */ static int __d_unalias(struct inode *inode, struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL; struct rw_semaphore *m2 = NULL; int ret = -ESTALE; /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) goto out_unalias; /* See lock_rename() */ if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) goto out_err; m1 = &dentry->d_sb->s_vfs_rename_mutex; if (!inode_trylock_shared(alias->d_parent->d_inode)) goto out_err; m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: __d_move(alias, dentry, false); ret = 0; out_err: if (m2) up_read(m2); if (m1) mutex_unlock(m1); return ret; } /** * d_splice_alias - splice a disconnected dentry into the tree if one exists * @inode: the inode which may have a disconnected dentry * @dentry: a negative dentry which we want to point to the inode. * * If inode is a directory and has an IS_ROOT alias, then d_move that in * place of the given dentry and return it, else simply d_add the inode * to the dentry and return NULL. * * If a non-IS_ROOT directory is found, the filesystem is corrupt, and * we should error out: directories can't have multiple aliases. * * This is needed in the lookup routine of any filesystem that is exportable * (via knfsd) so that we can build dcache paths to directories effectively. * * If a dentry was found and moved, then it is returned. Otherwise NULL * is returned. This matches the expected return value of ->lookup. * * Cluster filesystems may call this function with a negative, hashed dentry. * In that case, we know that the inode will be a regular file, and also this * will only occur during atomic_open. So we need to check for the dentry * being already hashed only in the final case. */ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) { if (IS_ERR(inode)) return ERR_CAST(inode); BUG_ON(!d_unhashed(dentry)); if (!inode) goto out; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode)) { struct dentry *new = __d_find_any_alias(inode); if (unlikely(new)) { /* The reference to new ensures it remains an alias */ spin_unlock(&inode->i_lock); write_seqlock(&rename_lock); if (unlikely(d_ancestor(new, dentry))) { write_sequnlock(&rename_lock); dput(new); new = ERR_PTR(-ELOOP); pr_warn_ratelimited( "VFS: Lookup of '%s' in %s %s" " would have caused loop\n", dentry->d_name.name, inode->i_sb->s_type->name, inode->i_sb->s_id); } else if (!IS_ROOT(new)) { struct dentry *old_parent = dget(new->d_parent); int err = __d_unalias(inode, dentry, new); write_sequnlock(&rename_lock); if (err) { dput(new); new = ERR_PTR(err); } dput(old_parent); } else { __d_move(new, dentry, false); write_sequnlock(&rename_lock); } iput(inode); return new; } } out: __d_add(dentry, inode); return NULL; } EXPORT_SYMBOL_NS(d_splice_alias, ANDROID_GKI_VFS_EXPORT_ONLY); /* * Test whether new_dentry is a subdirectory of old_dentry. * * Trivially implemented using the dcache structure */ /** * is_subdir - is new dentry a subdirectory of old_dentry * @new_dentry: new dentry * @old_dentry: old dentry * * Returns true if new_dentry is a subdirectory of the parent (at any depth). * Returns false otherwise. * Caller must ensure that "new_dentry" is pinned before calling is_subdir() */ bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { bool subdir; unsigned seq; if (new_dentry == old_dentry) return true; /* Access d_parent under rcu as d_move() may change it. */ rcu_read_lock(); seq = read_seqbegin(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); /* Try lockless once... */ if (read_seqretry(&rename_lock, seq)) { /* ...else acquire lock for progress even on deep chains. */ read_seqlock_excl(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); read_sequnlock_excl(&rename_lock); } rcu_read_unlock(); return subdir; } EXPORT_SYMBOL(is_subdir); static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry) { struct dentry *root = data; if (dentry != root) { if (d_unhashed(dentry) || !dentry->d_inode) return D_WALK_SKIP; if (!(dentry->d_flags & DCACHE_GENOCIDE)) { dentry->d_flags |= DCACHE_GENOCIDE; dentry->d_lockref.count--; } } return D_WALK_CONTINUE; } void d_genocide(struct dentry *parent) { d_walk(parent, parent, d_genocide_kill); } EXPORT_SYMBOL(d_genocide); void d_tmpfile(struct dentry *dentry, struct inode *inode) { inode_dec_link_count(inode); BUG_ON(dentry->d_name.name != dentry->d_iname || !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry->d_name.len = sprintf(dentry->d_iname, "#%llu", (unsigned long long)inode->i_ino); spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); d_instantiate(dentry, inode); } EXPORT_SYMBOL(d_tmpfile); static __initdata unsigned long dhash_entries; static int __init set_dhash_entries(char *str) { if (!str) return 0; dhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("dhash_entries=", set_dhash_entries); static void __init dcache_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_EARLY | HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; } static void __init dcache_init(void) { /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature * of the dcache. */ dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT, d_iname); /* Hash may have been set up in dcache_init_early */ if (!hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; } /* SLAB cache for __getname() consumers */ struct kmem_cache *names_cachep __read_mostly; EXPORT_SYMBOL(names_cachep); void __init vfs_caches_init_early(void) { int i; for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++) INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]); dcache_init_early(); inode_init_early(); } void __init vfs_caches_init(void) { names_cachep = kmem_cache_create_usercopy("names_cache", PATH_MAX, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, 0, PATH_MAX, NULL); dcache_init(); inode_init(); files_init(); files_maxfiles_init(); mnt_init(); bdev_cache_init(); chrdev_init(); } |
| 508 508 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 | // SPDX-License-Identifier: GPL-2.0 /* * fs/signalfd.c * * Copyright (C) 2003 Linus Torvalds * * Mon Mar 5, 2007: Davide Libenzi <davidel@xmailserver.org> * Changed ->read() to return a siginfo strcture instead of signal number. * Fixed locking in ->poll(). * Added sighand-detach notification. * Added fd re-use in sys_signalfd() syscall. * Now using anonymous inode source. * Thanks to Oleg Nesterov for useful code review and suggestions. * More comments and suggestions from Arnd Bergmann. * Sat May 19, 2007: Davi E. M. Arnaut <davi@haxent.com.br> * Retrieve multiple signals with one read() call * Sun Jul 15, 2007: Davide Libenzi <davidel@xmailserver.org> * Attach to the sighand only during read() and poll(). */ #include <linux/file.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/signal.h> #include <linux/list.h> #include <linux/anon_inodes.h> #include <linux/signalfd.h> #include <linux/syscalls.h> #include <linux/proc_fs.h> #include <linux/compat.h> void signalfd_cleanup(struct sighand_struct *sighand) { wake_up_pollfree(&sighand->signalfd_wqh); } struct signalfd_ctx { sigset_t sigmask; }; static int signalfd_release(struct inode *inode, struct file *file) { kfree(file->private_data); return 0; } static __poll_t signalfd_poll(struct file *file, poll_table *wait) { struct signalfd_ctx *ctx = file->private_data; __poll_t events = 0; poll_wait(file, ¤t->sighand->signalfd_wqh, wait); spin_lock_irq(¤t->sighand->siglock); if (next_signal(¤t->pending, &ctx->sigmask) || next_signal(¤t->signal->shared_pending, &ctx->sigmask)) events |= EPOLLIN; spin_unlock_irq(¤t->sighand->siglock); return events; } /* * Copied from copy_siginfo_to_user() in kernel/signal.c */ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, kernel_siginfo_t const *kinfo) { struct signalfd_siginfo new; BUILD_BUG_ON(sizeof(struct signalfd_siginfo) != 128); /* * Unused members should be zero ... */ memset(&new, 0, sizeof(new)); /* * If you change siginfo_t structure, please be sure * this code is fixed accordingly. */ new.ssi_signo = kinfo->si_signo; new.ssi_errno = kinfo->si_errno; new.ssi_code = kinfo->si_code; switch (siginfo_layout(kinfo->si_signo, kinfo->si_code)) { case SIL_KILL: new.ssi_pid = kinfo->si_pid; new.ssi_uid = kinfo->si_uid; break; case SIL_TIMER: new.ssi_tid = kinfo->si_tid; new.ssi_overrun = kinfo->si_overrun; new.ssi_ptr = (long) kinfo->si_ptr; new.ssi_int = kinfo->si_int; break; case SIL_POLL: new.ssi_band = kinfo->si_band; new.ssi_fd = kinfo->si_fd; break; case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: case SIL_FAULT_PERF_EVENT: /* * Fall through to the SIL_FAULT case. SIL_FAULT_BNDERR, * SIL_FAULT_PKUERR, and SIL_FAULT_PERF_EVENT are only * generated by faults that deliver them synchronously to * userspace. In case someone injects one of these signals * and signalfd catches it treat it as SIL_FAULT. */ case SIL_FAULT: new.ssi_addr = (long) kinfo->si_addr; break; case SIL_FAULT_TRAPNO: new.ssi_addr = (long) kinfo->si_addr; new.ssi_trapno = kinfo->si_trapno; break; case SIL_FAULT_MCEERR: new.ssi_addr = (long) kinfo->si_addr; new.ssi_addr_lsb = (short) kinfo->si_addr_lsb; break; case SIL_CHLD: new.ssi_pid = kinfo->si_pid; new.ssi_uid = kinfo->si_uid; new.ssi_status = kinfo->si_status; new.ssi_utime = kinfo->si_utime; new.ssi_stime = kinfo->si_stime; break; case SIL_RT: /* * This case catches also the signals queued by sigqueue(). */ new.ssi_pid = kinfo->si_pid; new.ssi_uid = kinfo->si_uid; new.ssi_ptr = (long) kinfo->si_ptr; new.ssi_int = kinfo->si_int; break; case SIL_SYS: new.ssi_call_addr = (long) kinfo->si_call_addr; new.ssi_syscall = kinfo->si_syscall; new.ssi_arch = kinfo->si_arch; break; } if (copy_to_user(uinfo, &new, sizeof(struct signalfd_siginfo))) return -EFAULT; return sizeof(*uinfo); } static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info, int nonblock) { ssize_t ret; DECLARE_WAITQUEUE(wait, current); spin_lock_irq(¤t->sighand->siglock); ret = dequeue_signal(current, &ctx->sigmask, info); switch (ret) { case 0: if (!nonblock) break; ret = -EAGAIN; fallthrough; default: spin_unlock_irq(¤t->sighand->siglock); return ret; } add_wait_queue(¤t->sighand->signalfd_wqh, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); ret = dequeue_signal(current, &ctx->sigmask, info); if (ret != 0) break; if (signal_pending(current)) { ret = -ERESTARTSYS; break; } spin_unlock_irq(¤t->sighand->siglock); schedule(); spin_lock_irq(¤t->sighand->siglock); } spin_unlock_irq(¤t->sighand->siglock); remove_wait_queue(¤t->sighand->signalfd_wqh, &wait); __set_current_state(TASK_RUNNING); return ret; } /* * Returns a multiple of the size of a "struct signalfd_siginfo", or a negative * error code. The "count" parameter must be at least the size of a * "struct signalfd_siginfo". */ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct signalfd_ctx *ctx = file->private_data; struct signalfd_siginfo __user *siginfo; int nonblock = file->f_flags & O_NONBLOCK; ssize_t ret, total = 0; kernel_siginfo_t info; count /= sizeof(struct signalfd_siginfo); if (!count) return -EINVAL; siginfo = (struct signalfd_siginfo __user *) buf; do { ret = signalfd_dequeue(ctx, &info, nonblock); if (unlikely(ret <= 0)) break; ret = signalfd_copyinfo(siginfo, &info); if (ret < 0) break; siginfo++; total += ret; nonblock = 1; } while (--count); return total ? total: ret; } #ifdef CONFIG_PROC_FS static void signalfd_show_fdinfo(struct seq_file *m, struct file *f) { struct signalfd_ctx *ctx = f->private_data; sigset_t sigmask; sigmask = ctx->sigmask; signotset(&sigmask); render_sigset_t(m, "sigmask:\t", &sigmask); } #endif static const struct file_operations signalfd_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = signalfd_show_fdinfo, #endif .release = signalfd_release, .poll = signalfd_poll, .read = signalfd_read, .llseek = noop_llseek, }; static int do_signalfd4(int ufd, sigset_t *mask, int flags) { struct signalfd_ctx *ctx; /* Check the SFD_* constants for consistency. */ BUILD_BUG_ON(SFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(SFD_NONBLOCK != O_NONBLOCK); if (flags & ~(SFD_CLOEXEC | SFD_NONBLOCK)) return -EINVAL; sigdelsetmask(mask, sigmask(SIGKILL) | sigmask(SIGSTOP)); signotset(mask); if (ufd == -1) { ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->sigmask = *mask; /* * When we call this, the initialization must be complete, since * anon_inode_getfd() will install the fd. */ ufd = anon_inode_getfd("[signalfd]", &signalfd_fops, ctx, O_RDWR | (flags & (O_CLOEXEC | O_NONBLOCK))); if (ufd < 0) kfree(ctx); } else { struct fd f = fdget(ufd); if (!f.file) return -EBADF; ctx = f.file->private_data; if (f.file->f_op != &signalfd_fops) { fdput(f); return -EINVAL; } spin_lock_irq(¤t->sighand->siglock); ctx->sigmask = *mask; spin_unlock_irq(¤t->sighand->siglock); wake_up(¤t->sighand->signalfd_wqh); fdput(f); } return ufd; } SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, size_t, sizemask, int, flags) { sigset_t mask; if (sizemask != sizeof(sigset_t)) return -EINVAL; if (copy_from_user(&mask, user_mask, sizeof(mask))) return -EFAULT; return do_signalfd4(ufd, &mask, flags); } SYSCALL_DEFINE3(signalfd, int, ufd, sigset_t __user *, user_mask, size_t, sizemask) { sigset_t mask; if (sizemask != sizeof(sigset_t)) return -EINVAL; if (copy_from_user(&mask, user_mask, sizeof(mask))) return -EFAULT; return do_signalfd4(ufd, &mask, 0); } #ifdef CONFIG_COMPAT static long do_compat_signalfd4(int ufd, const compat_sigset_t __user *user_mask, compat_size_t sigsetsize, int flags) { sigset_t mask; if (sigsetsize != sizeof(compat_sigset_t)) return -EINVAL; if (get_compat_sigset(&mask, user_mask)) return -EFAULT; return do_signalfd4(ufd, &mask, flags); } COMPAT_SYSCALL_DEFINE4(signalfd4, int, ufd, const compat_sigset_t __user *, user_mask, compat_size_t, sigsetsize, int, flags) { return do_compat_signalfd4(ufd, user_mask, sigsetsize, flags); } COMPAT_SYSCALL_DEFINE3(signalfd, int, ufd, const compat_sigset_t __user *, user_mask, compat_size_t, sigsetsize) { return do_compat_signalfd4(ufd, user_mask, sigsetsize, 0); } #endif |
| 511 1454 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PARAVIRT_H #define _ASM_X86_PARAVIRT_H /* Various instructions on x86 need to be replaced for * para-virtualization: those hooks are defined here. */ #ifdef CONFIG_PARAVIRT #include <asm/pgtable_types.h> #include <asm/asm.h> #include <asm/nospec-branch.h> #include <asm/paravirt_types.h> #ifndef __ASSEMBLY__ #include <linux/bug.h> #include <linux/types.h> #include <linux/cpumask.h> #include <linux/static_call_types.h> #include <asm/frame.h> u64 dummy_steal_clock(int cpu); u64 dummy_sched_clock(void); DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock); DECLARE_STATIC_CALL(pv_sched_clock, dummy_sched_clock); void paravirt_set_sched_clock(u64 (*func)(void)); static inline u64 paravirt_sched_clock(void) { return static_call(pv_sched_clock)(); } struct static_key; extern struct static_key paravirt_steal_enabled; extern struct static_key paravirt_steal_rq_enabled; __visible void __native_queued_spin_unlock(struct qspinlock *lock); bool pv_is_native_spin_unlock(void); __visible bool __native_vcpu_is_preempted(long cpu); bool pv_is_native_vcpu_is_preempted(void); static inline u64 paravirt_steal_clock(int cpu) { return static_call(pv_steal_clock)(cpu); } #ifdef CONFIG_PARAVIRT_SPINLOCKS void __init paravirt_set_cap(void); #endif /* The paravirtualized I/O functions */ static inline void slow_down_io(void) { pv_ops.cpu.io_delay(); #ifdef REALLY_SLOW_IO pv_ops.cpu.io_delay(); pv_ops.cpu.io_delay(); pv_ops.cpu.io_delay(); #endif } void native_flush_tlb_local(void); void native_flush_tlb_global(void); void native_flush_tlb_one_user(unsigned long addr); void native_flush_tlb_multi(const struct cpumask *cpumask, const struct flush_tlb_info *info); static inline void __flush_tlb_local(void) { PVOP_VCALL0(mmu.flush_tlb_user); } static inline void __flush_tlb_global(void) { PVOP_VCALL0(mmu.flush_tlb_kernel); } static inline void __flush_tlb_one_user(unsigned long addr) { PVOP_VCALL1(mmu.flush_tlb_one_user, addr); } static inline void __flush_tlb_multi(const struct cpumask *cpumask, const struct flush_tlb_info *info) { PVOP_VCALL2(mmu.flush_tlb_multi, cpumask, info); } static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table) { PVOP_VCALL2(mmu.tlb_remove_table, tlb, table); } static inline void paravirt_arch_exit_mmap(struct mm_struct *mm) { PVOP_VCALL1(mmu.exit_mmap, mm); } #ifdef CONFIG_PARAVIRT_XXL static inline void load_sp0(unsigned long sp0) { PVOP_VCALL1(cpu.load_sp0, sp0); } /* The paravirtualized CPUID instruction. */ static inline void __cpuid(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) { PVOP_VCALL4(cpu.cpuid, eax, ebx, ecx, edx); } /* * These special macros can be used to get or set a debugging register */ static inline unsigned long paravirt_get_debugreg(int reg) { return PVOP_CALL1(unsigned long, cpu.get_debugreg, reg); } #define get_debugreg(var, reg) var = paravirt_get_debugreg(reg) static inline void set_debugreg(unsigned long val, int reg) { PVOP_VCALL2(cpu.set_debugreg, reg, val); } static inline unsigned long read_cr0(void) { return PVOP_CALL0(unsigned long, cpu.read_cr0); } static inline void write_cr0(unsigned long x) { PVOP_VCALL1(cpu.write_cr0, x); } static inline unsigned long read_cr2(void) { return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2, "mov %%cr2, %%rax;", ALT_NOT(X86_FEATURE_XENPV)); } static inline void write_cr2(unsigned long x) { PVOP_VCALL1(mmu.write_cr2, x); } static inline unsigned long __read_cr3(void) { return PVOP_ALT_CALL0(unsigned long, mmu.read_cr3, "mov %%cr3, %%rax;", ALT_NOT(X86_FEATURE_XENPV)); } static inline void write_cr3(unsigned long x) { PVOP_ALT_VCALL1(mmu.write_cr3, x, "mov %%rdi, %%cr3", ALT_NOT(X86_FEATURE_XENPV)); } static inline void __write_cr4(unsigned long x) { PVOP_VCALL1(cpu.write_cr4, x); } static inline void arch_safe_halt(void) { PVOP_VCALL0(irq.safe_halt); } static inline void halt(void) { PVOP_VCALL0(irq.halt); } static inline void wbinvd(void) { PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV)); } static inline u64 paravirt_read_msr(unsigned msr) { return PVOP_CALL1(u64, cpu.read_msr, msr); } static inline void paravirt_write_msr(unsigned msr, unsigned low, unsigned high) { PVOP_VCALL3(cpu.write_msr, msr, low, high); } static inline u64 paravirt_read_msr_safe(unsigned msr, int *err) { return PVOP_CALL2(u64, cpu.read_msr_safe, msr, err); } static inline int paravirt_write_msr_safe(unsigned msr, unsigned low, unsigned high) { return PVOP_CALL3(int, cpu.write_msr_safe, msr, low, high); } #define rdmsr(msr, val1, val2) \ do { \ u64 _l = paravirt_read_msr(msr); \ val1 = (u32)_l; \ val2 = _l >> 32; \ } while (0) #define wrmsr(msr, val1, val2) \ do { \ paravirt_write_msr(msr, val1, val2); \ } while (0) #define rdmsrl(msr, val) \ do { \ val = paravirt_read_msr(msr); \ } while (0) static inline void wrmsrl(unsigned msr, u64 val) { wrmsr(msr, (u32)val, (u32)(val>>32)); } #define wrmsr_safe(msr, a, b) paravirt_write_msr_safe(msr, a, b) /* rdmsr with exception handling */ #define rdmsr_safe(msr, a, b) \ ({ \ int _err; \ u64 _l = paravirt_read_msr_safe(msr, &_err); \ (*a) = (u32)_l; \ (*b) = _l >> 32; \ _err; \ }) static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) { int err; *p = paravirt_read_msr_safe(msr, &err); return err; } static inline unsigned long long paravirt_read_pmc(int counter) { return PVOP_CALL1(u64, cpu.read_pmc, counter); } #define rdpmc(counter, low, high) \ do { \ u64 _l = paravirt_read_pmc(counter); \ low = (u32)_l; \ high = _l >> 32; \ } while (0) #define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter)) static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) { PVOP_VCALL2(cpu.alloc_ldt, ldt, entries); } static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries) { PVOP_VCALL2(cpu.free_ldt, ldt, entries); } static inline void load_TR_desc(void) { PVOP_VCALL0(cpu.load_tr_desc); } static inline void load_gdt(const struct desc_ptr *dtr) { PVOP_VCALL1(cpu.load_gdt, dtr); } static inline void load_idt(const struct desc_ptr *dtr) { PVOP_VCALL1(cpu.load_idt, dtr); } static inline void set_ldt(const void *addr, unsigned entries) { PVOP_VCALL2(cpu.set_ldt, addr, entries); } static inline unsigned long paravirt_store_tr(void) { return PVOP_CALL0(unsigned long, cpu.store_tr); } #define store_tr(tr) ((tr) = paravirt_store_tr()) static inline void load_TLS(struct thread_struct *t, unsigned cpu) { PVOP_VCALL2(cpu.load_tls, t, cpu); } static inline void load_gs_index(unsigned int gs) { PVOP_VCALL1(cpu.load_gs_index, gs); } static inline void write_ldt_entry(struct desc_struct *dt, int entry, const void *desc) { PVOP_VCALL3(cpu.write_ldt_entry, dt, entry, desc); } static inline void write_gdt_entry(struct desc_struct *dt, int entry, void *desc, int type) { PVOP_VCALL4(cpu.write_gdt_entry, dt, entry, desc, type); } static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g) { PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g); } #ifdef CONFIG_X86_IOPL_IOPERM static inline void tss_invalidate_io_bitmap(void) { PVOP_VCALL0(cpu.invalidate_io_bitmap); } static inline void tss_update_io_bitmap(void) { PVOP_VCALL0(cpu.update_io_bitmap); } #endif static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { PVOP_VCALL2(mmu.activate_mm, prev, next); } static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { PVOP_VCALL2(mmu.dup_mmap, oldmm, mm); } static inline int paravirt_pgd_alloc(struct mm_struct *mm) { return PVOP_CALL1(int, mmu.pgd_alloc, mm); } static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) { PVOP_VCALL2(mmu.pgd_free, mm, pgd); } static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) { PVOP_VCALL2(mmu.alloc_pte, mm, pfn); } static inline void paravirt_release_pte(unsigned long pfn) { PVOP_VCALL1(mmu.release_pte, pfn); } static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) { PVOP_VCALL2(mmu.alloc_pmd, mm, pfn); } static inline void paravirt_release_pmd(unsigned long pfn) { PVOP_VCALL1(mmu.release_pmd, pfn); } static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) { PVOP_VCALL2(mmu.alloc_pud, mm, pfn); } static inline void paravirt_release_pud(unsigned long pfn) { PVOP_VCALL1(mmu.release_pud, pfn); } static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) { PVOP_VCALL2(mmu.alloc_p4d, mm, pfn); } static inline void paravirt_release_p4d(unsigned long pfn) { PVOP_VCALL1(mmu.release_p4d, pfn); } static inline pte_t __pte(pteval_t val) { return (pte_t) { PVOP_ALT_CALLEE1(pteval_t, mmu.make_pte, val, "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)) }; } static inline pteval_t pte_val(pte_t pte) { return PVOP_ALT_CALLEE1(pteval_t, mmu.pte_val, pte.pte, "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); } static inline pgd_t __pgd(pgdval_t val) { return (pgd_t) { PVOP_ALT_CALLEE1(pgdval_t, mmu.make_pgd, val, "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)) }; } static inline pgdval_t pgd_val(pgd_t pgd) { return PVOP_ALT_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd, "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pteval_t ret; ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, vma, addr, ptep); return (pte_t) { .pte = ret }; } static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { PVOP_VCALL4(mmu.ptep_modify_prot_commit, vma, addr, ptep, pte.pte); } static inline void set_pte(pte_t *ptep, pte_t pte) { PVOP_VCALL2(mmu.set_pte, ptep, pte.pte); } static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { PVOP_VCALL2(mmu.set_pmd, pmdp, native_pmd_val(pmd)); } static inline pmd_t __pmd(pmdval_t val) { return (pmd_t) { PVOP_ALT_CALLEE1(pmdval_t, mmu.make_pmd, val, "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)) }; } static inline pmdval_t pmd_val(pmd_t pmd) { return PVOP_ALT_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd, "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); } static inline void set_pud(pud_t *pudp, pud_t pud) { PVOP_VCALL2(mmu.set_pud, pudp, native_pud_val(pud)); } static inline pud_t __pud(pudval_t val) { pudval_t ret; ret = PVOP_ALT_CALLEE1(pudval_t, mmu.make_pud, val, "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); return (pud_t) { ret }; } static inline pudval_t pud_val(pud_t pud) { return PVOP_ALT_CALLEE1(pudval_t, mmu.pud_val, pud.pud, "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); } static inline void pud_clear(pud_t *pudp) { set_pud(pudp, native_make_pud(0)); } static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) { p4dval_t val = native_p4d_val(p4d); PVOP_VCALL2(mmu.set_p4d, p4dp, val); } #if CONFIG_PGTABLE_LEVELS >= 5 static inline p4d_t __p4d(p4dval_t val) { p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val, "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); return (p4d_t) { ret }; } static inline p4dval_t p4d_val(p4d_t p4d) { return PVOP_ALT_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d, "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); } static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd) { PVOP_VCALL2(mmu.set_pgd, pgdp, native_pgd_val(pgd)); } #define set_pgd(pgdp, pgdval) do { \ if (pgtable_l5_enabled()) \ __set_pgd(pgdp, pgdval); \ else \ set_p4d((p4d_t *)(pgdp), (p4d_t) { (pgdval).pgd }); \ } while (0) #define pgd_clear(pgdp) do { \ if (pgtable_l5_enabled()) \ set_pgd(pgdp, native_make_pgd(0)); \ } while (0) #endif /* CONFIG_PGTABLE_LEVELS == 5 */ static inline void p4d_clear(p4d_t *p4dp) { set_p4d(p4dp, native_make_p4d(0)); } static inline void set_pte_atomic(pte_t *ptep, pte_t pte) { set_pte(ptep, pte); } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { set_pte(ptep, native_make_pte(0)); } static inline void pmd_clear(pmd_t *pmdp) { set_pmd(pmdp, native_make_pmd(0)); } #define __HAVE_ARCH_START_CONTEXT_SWITCH static inline void arch_start_context_switch(struct task_struct *prev) { PVOP_VCALL1(cpu.start_context_switch, prev); } static inline void arch_end_context_switch(struct task_struct *next) { PVOP_VCALL1(cpu.end_context_switch, next); } #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE static inline void arch_enter_lazy_mmu_mode(void) { PVOP_VCALL0(mmu.lazy_mode.enter); } static inline void arch_leave_lazy_mmu_mode(void) { PVOP_VCALL0(mmu.lazy_mode.leave); } static inline void arch_flush_lazy_mmu_mode(void) { PVOP_VCALL0(mmu.lazy_mode.flush); } static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags) { pv_ops.mmu.set_fixmap(idx, phys, flags); } #endif #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) { PVOP_VCALL2(lock.queued_spin_lock_slowpath, lock, val); } static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock) { PVOP_ALT_VCALLEE1(lock.queued_spin_unlock, lock, "movb $0, (%%" _ASM_ARG1 ");", ALT_NOT(X86_FEATURE_PVUNLOCK)); } static __always_inline void pv_wait(u8 *ptr, u8 val) { PVOP_VCALL2(lock.wait, ptr, val); } static __always_inline void pv_kick(int cpu) { PVOP_VCALL1(lock.kick, cpu); } static __always_inline bool pv_vcpu_is_preempted(long cpu) { return PVOP_ALT_CALLEE1(bool, lock.vcpu_is_preempted, cpu, "xor %%" _ASM_AX ", %%" _ASM_AX ";", ALT_NOT(X86_FEATURE_VCPUPREEMPT)); } void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock); bool __raw_callee_save___native_vcpu_is_preempted(long cpu); #endif /* SMP && PARAVIRT_SPINLOCKS */ #ifdef CONFIG_X86_32 /* save and restore all caller-save registers, except return value */ #define PV_SAVE_ALL_CALLER_REGS "pushl %ecx;" #define PV_RESTORE_ALL_CALLER_REGS "popl %ecx;" #else /* save and restore all caller-save registers, except return value */ #define PV_SAVE_ALL_CALLER_REGS \ "push %rcx;" \ "push %rdx;" \ "push %rsi;" \ "push %rdi;" \ "push %r8;" \ "push %r9;" \ "push %r10;" \ "push %r11;" #define PV_RESTORE_ALL_CALLER_REGS \ "pop %r11;" \ "pop %r10;" \ "pop %r9;" \ "pop %r8;" \ "pop %rdi;" \ "pop %rsi;" \ "pop %rdx;" \ "pop %rcx;" #endif /* * Generate a thunk around a function which saves all caller-save * registers except for the return value. This allows C functions to * be called from assembler code where fewer than normal registers are * available. It may also help code generation around calls from C * code if the common case doesn't use many registers. * * When a callee is wrapped in a thunk, the caller can assume that all * arg regs and all scratch registers are preserved across the * call. The return value in rax/eax will not be saved, even for void * functions. */ #define PV_THUNK_NAME(func) "__raw_callee_save_" #func #define PV_CALLEE_SAVE_REGS_THUNK(func) \ extern typeof(func) __raw_callee_save_##func; \ \ asm(".pushsection .text;" \ ".globl " PV_THUNK_NAME(func) ";" \ ".type " PV_THUNK_NAME(func) ", @function;" \ PV_THUNK_NAME(func) ":" \ FRAME_BEGIN \ PV_SAVE_ALL_CALLER_REGS \ "call " #func ";" \ PV_RESTORE_ALL_CALLER_REGS \ FRAME_END \ ASM_RET \ ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";" \ ".popsection") /* Get a reference to a callee-save function */ #define PV_CALLEE_SAVE(func) \ ((struct paravirt_callee_save) { __raw_callee_save_##func }) /* Promise that "func" already uses the right calling convention */ #define __PV_IS_CALLEE_SAVE(func) \ ((struct paravirt_callee_save) { func }) #ifdef CONFIG_PARAVIRT_XXL static inline notrace unsigned long arch_local_save_flags(void) { return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;", ALT_NOT(X86_FEATURE_XENPV)); } static inline notrace void arch_local_irq_disable(void) { PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV)); } static inline notrace void arch_local_irq_enable(void) { PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV)); } static inline notrace unsigned long arch_local_irq_save(void) { unsigned long f; f = arch_local_save_flags(); arch_local_irq_disable(); return f; } #endif /* Make sure as little as possible of this mess escapes. */ #undef PARAVIRT_CALL #undef __PVOP_CALL #undef __PVOP_VCALL #undef PVOP_VCALL0 #undef PVOP_CALL0 #undef PVOP_VCALL1 #undef PVOP_CALL1 #undef PVOP_VCALL2 #undef PVOP_CALL2 #undef PVOP_VCALL3 #undef PVOP_CALL3 #undef PVOP_VCALL4 #undef PVOP_CALL4 extern void default_banner(void); #else /* __ASSEMBLY__ */ #define _PVSITE(ptype, ops, word, algn) \ 771:; \ ops; \ 772:; \ .pushsection .parainstructions,"a"; \ .align algn; \ word 771b; \ .byte ptype; \ .byte 772b-771b; \ .popsection #ifdef CONFIG_X86_64 #ifdef CONFIG_PARAVIRT_XXL #define PARA_PATCH(off) ((off) / 8) #define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8) #define PARA_INDIRECT(addr) *addr(%rip) #define INTERRUPT_RETURN \ ANNOTATE_RETPOLINE_SAFE; \ ALTERNATIVE_TERNARY("jmp *paravirt_iret(%rip);", \ X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;") #ifdef CONFIG_DEBUG_ENTRY .macro PARA_IRQ_save_fl PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), ANNOTATE_RETPOLINE_SAFE; call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);) .endm #define SAVE_FLAGS ALTERNATIVE "PARA_IRQ_save_fl;", "pushf; pop %rax;", \ ALT_NOT(X86_FEATURE_XENPV) #endif #endif /* CONFIG_PARAVIRT_XXL */ #endif /* CONFIG_X86_64 */ #endif /* __ASSEMBLY__ */ #else /* CONFIG_PARAVIRT */ # define default_banner x86_init_noop #endif /* !CONFIG_PARAVIRT */ #ifndef __ASSEMBLY__ #ifndef CONFIG_PARAVIRT_XXL static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { } #endif #ifndef CONFIG_PARAVIRT static inline void paravirt_arch_exit_mmap(struct mm_struct *mm) { } #endif #ifndef CONFIG_PARAVIRT_SPINLOCKS static inline void paravirt_set_cap(void) { } #endif #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PARAVIRT_H */ |
| 4520 1950 2503 1329 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_TASK_H #define _LINUX_SCHED_TASK_H /* * Interface between the scheduler and various task lifetime (fork()/exit()) * functionality: */ #include <linux/sched.h> #include <linux/uaccess.h> struct task_struct; struct rusage; union thread_union; struct css_set; /* All the bits taken by the old clone syscall. */ #define CLONE_LEGACY_FLAGS 0xffffffffULL struct kernel_clone_args { u64 flags; int __user *pidfd; int __user *child_tid; int __user *parent_tid; int exit_signal; unsigned long stack; unsigned long stack_size; unsigned long tls; pid_t *set_tid; /* Number of elements in *set_tid */ size_t set_tid_size; int cgroup; int io_thread; struct cgroup *cgrp; struct css_set *cset; }; /* * This serializes "schedule()" and also protects * the run-queue from deletions/modifications (but * _adding_ to the beginning of the run-queue has * a separate lock). */ extern rwlock_t tasklist_lock; extern spinlock_t mmlist_lock; extern union thread_union init_thread_union; extern struct task_struct init_task; extern int lockdep_tasklist_lock_is_held(void); extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); extern void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void sched_post_fork(struct task_struct *p); extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); void __noreturn make_task_dead(int signr); extern void mm_cache_init(void); extern void proc_caches_init(void); extern void fork_init(void); extern void release_task(struct task_struct * p); extern int copy_thread(unsigned long, unsigned long, unsigned long, struct task_struct *, unsigned long); extern void flush_thread(void); #ifdef CONFIG_HAVE_EXIT_THREAD extern void exit_thread(struct task_struct *tsk); #else static inline void exit_thread(struct task_struct *tsk) { } #endif extern void do_group_exit(int); extern void exit_files(struct task_struct *); extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); extern void free_task(struct task_struct *tsk); /* sched_exec is called by processes performing an exec */ #ifdef CONFIG_SMP extern void sched_exec(void); #else #define sched_exec() {} #endif static inline struct task_struct *get_task_struct(struct task_struct *t) { refcount_inc(&t->usage); return t; } extern void __put_task_struct(struct task_struct *t); extern void __put_task_struct_rcu_cb(struct rcu_head *rhp); static inline void put_task_struct(struct task_struct *t) { if (!refcount_dec_and_test(&t->usage)) return; /* * under PREEMPT_RT, we can't call put_task_struct * in atomic context because it will indirectly * acquire sleeping locks. * * call_rcu() will schedule delayed_put_task_struct_rcu() * to be called in process context. * * __put_task_struct() is called when * refcount_dec_and_test(&t->usage) succeeds. * * This means that it can't "conflict" with * put_task_struct_rcu_user() which abuses ->rcu the same * way; rcu_users has a reference so task->usage can't be * zero after rcu_users 1 -> 0 transition. * * delayed_free_task() also uses ->rcu, but it is only called * when it fails to fork a process. Therefore, there is no * way it can conflict with put_task_struct(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !preemptible()) call_rcu(&t->rcu, __put_task_struct_rcu_cb); else __put_task_struct(t); } static inline void put_task_struct_many(struct task_struct *t, int nr) { if (refcount_sub_and_test(nr, &t->usage)) __put_task_struct(t); } void put_task_struct_rcu_user(struct task_struct *task); #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT extern int arch_task_struct_size __read_mostly; #else # define arch_task_struct_size (sizeof(struct task_struct)) #endif #ifndef CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST /* * If an architecture has not declared a thread_struct whitelist we * must assume something there may need to be copied to userspace. */ static inline void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { *offset = 0; /* Handle dynamically sized thread_struct. */ *size = arch_task_struct_size - offsetof(struct task_struct, thread); } #endif #ifdef CONFIG_VMAP_STACK static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) { return t->stack_vm_area; } #else static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) { return NULL; } #endif /* * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also * pins the final release of task.io_context. Also protects ->cpuset and * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist. * * Nests both inside and outside of read_lock(&tasklist_lock). * It must not be nested with write_lock_irq(&tasklist_lock), * neither inside nor outside. */ static inline void task_lock(struct task_struct *p) { spin_lock(&p->alloc_lock); } static inline void task_unlock(struct task_struct *p) { spin_unlock(&p->alloc_lock); } #endif /* _LINUX_SCHED_TASK_H */ |
| 1836 29 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal.h: mm/ internal definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/tracepoint-defs.h> /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints * about IO, FS and watermark checking while ignoring placement * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_ATOMIC) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) /* Control allocation cpuset and node placement constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) void page_writeback_init(void); /* * This is a file-backed mapping, and is about to be memory mapped - invoke its * mmap hook and safely handle error conditions. On error, VMA hooks will be * mutated. * * @file: File which backs the mapping. * @vma: VMA which we are mapping. * * Returns: 0 if success, error otherwise. */ int mmap_file(struct file *file, struct vm_area_struct *vma); /* * If the VMA has a close hook then close it, and since closing it might leave * it in an inconsistent state which makes the use of any hooks suspect, clear * them down by installing dummy empty hooks. */ void vma_close(struct vm_area_struct *vma); vm_fault_t do_swap_page(struct vm_fault *vmf); void activate_page(struct page *page); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); static inline bool can_madv_lru_vma(struct vm_area_struct *vma) { return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)); } void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); void do_page_cache_ra(struct readahead_control *, unsigned long nr_to_read, unsigned long lookahead_size); void force_page_cache_ra(struct readahead_control *, unsigned long nr); static inline void force_page_cache_readahead(struct address_space *mapping, struct file *file, pgoff_t index, unsigned long nr_to_read) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index); force_page_cache_ra(&ractl, nr_to_read); } unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, pgoff_t end, struct pagevec *pvec, pgoff_t *indices); /** * page_evictable - test whether a page is evictable * @page: the page to test * * Test whether page is evictable--i.e., should be placed on active/inactive * lists vs unevictable list. * * Reasons page might not be evictable: * (1) page's mapping marked unevictable * (2) page is part of an mlocked VMA * */ static inline bool page_evictable(struct page *page) { bool ret; /* Prevent address_space of inode and swap cache from being freed */ rcu_read_lock(); ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page); rcu_read_unlock(); return ret; } /* * Turn a non-refcounted page (->_refcount == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_ref_count(page), page); set_page_count(page, 1); } extern unsigned long highest_memmap_pfn; /* * Maximum number of reclaim retries without progress before the OOM * killer is consider the only way forward. */ #define MAX_RECLAIM_RETRIES 16 /* * in mm/vmscan.c: */ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); /* * in mm/rmap.c: */ extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/memcontrol.c: */ extern bool cgroup_memory_nokmem; /* * in mm/page_alloc.c */ /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* * family of functions. * * nodemask, migratetype and highest_zoneidx are initialized only once in * __alloc_pages() and then never change. * * zonelist, preferred_zone and highest_zoneidx are set first in * __alloc_pages() for the fast path, and might be later changed * in __alloc_pages_slowpath(). All other functions pass the whole structure * by a const pointer. */ struct alloc_context { struct zonelist *zonelist; nodemask_t *nodemask; struct zoneref *preferred_zoneref; int migratetype; /* * highest_zoneidx represents highest usable zone index of * the allocation request. Due to the nature of the zone, * memory on lower zone than the highest_zoneidx will be * protected by lowmem_reserve[highest_zoneidx]. * * highest_zoneidx is also used by reclaim/compaction to limit * the target zone since higher zone than this index cannot be * usable for this allocation request. */ enum zone_type highest_zoneidx; bool spread_dirty_pages; }; /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * * 1) Any buddy B1 will have an order O twin B2 which satisfies * the following equation: * B2 = B1 ^ (1 << O) * For example, if the starting buddy (buddy2) is #8 its order * 1 buddy is #10: * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 * * 2) Any buddy B will have an order O+1 parent P which * satisfies the following equation: * P = B & ~(1 << O) * * Assumption: *_mem_map is contiguous at least up to MAX_ORDER */ static inline unsigned long __find_buddy_pfn(unsigned long page_pfn, unsigned int order) { return page_pfn ^ (1 << order); } extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone); static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone) { if (zone->contiguous) return pfn_to_page(start_pfn); return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); } extern int __isolate_free_page(struct page *page, unsigned int order); extern void __putback_isolated_page(struct page *page, unsigned int order, int mt); extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order); extern void prep_compound_page(struct page *page, unsigned int order); extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern int user_min_free_kbytes; extern void free_unref_page(struct page *page, unsigned int order); extern void free_unref_page_list(struct list_head *list); extern void zone_pcp_update(struct zone *zone, int cpu_online); extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, int nid, bool exact_nid); #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* * in mm/compaction.c */ /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts * at the end of a zone and migrate_pfn begins at the start. Movable pages * are moved to the end of a zone during a compaction run and the run * completes when free_pfn <= migrate_pfn */ struct compact_control { struct list_head freepages; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ /* * Acts as an in/out parameter to page isolation for migration. * isolate_migratepages uses it as a search base. * isolate_migratepages_block will update the value to the next pfn * after the last isolated one. */ unsigned long migrate_pfn; unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; unsigned long total_free_scanned; unsigned short fast_search_fail;/* failures to use free list searches */ short search_order; /* order to start a fast search at */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ const int highest_zoneidx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool no_set_skip_hint; /* Don't mark blocks for skipping */ bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ bool contended; /* Signal lock or sched contention */ bool rescan; /* Rescanning the same pageblock */ bool alloc_contig; /* alloc_contig_range allocation */ }; struct compact_control_ext { struct compact_control *cc; unsigned int nr_migrate_file_pages; /* Number of file pages to migrate */ }; /* * Used in direct compaction when a page should be taken from the freelists * immediately when one is created during the free path. */ struct capture_control { struct compact_control *cc; struct page *page; }; unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); #endif int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the * page from being allocated in parallel and returning garbage as the order. * If a caller does not hold page_zone(page)->lock, it must guarantee that the * page cannot be allocated or merged in parallel. Alternatively, it must * handle invalid values gracefully, and use buddy_order_unsafe() below. */ static inline unsigned int buddy_order(struct page *page) { /* PageBuddy() must be checked by the caller */ return page_private(page); } /* * Like buddy_order(), but for callers who cannot afford to hold the zone lock. * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ #define buddy_order_unsafe(page) READ_ONCE(page_private(page)) /* * These three helpers classifies VMAs for virtual memory accounting. */ /* * Executable code area - executable, not writable, not stack */ static inline bool is_exec_mapping(vm_flags_t flags) { return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; } /* * Stack area - automatically grows in one direction * * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: * do_mmap() forbids all other combinations. */ static inline bool is_stack_mapping(vm_flags_t flags) { return (flags & VM_STACK) == VM_STACK; } /* * Data area - private, writable, not stack */ static inline bool is_data_mapping(vm_flags_t flags) { return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; } /* mm/util.c */ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev); void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma); #ifdef CONFIG_MMU extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); extern long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool write, int *locked); extern void munlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); static inline void munlock_vma_pages_all(struct vm_area_struct *vma) { munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end); } /* * must be called with vma's mmap_lock held for read or write, and page locked. */ extern void mlock_vma_page(struct page *page); extern unsigned int munlock_vma_page(struct page *page); extern int mlock_future_check(struct mm_struct *mm, unsigned long flags, unsigned long len); /* * Clear the page's PageMlocked(). This can be useful in a situation where * we want to unconditionally remove a page from the pagecache -- e.g., * on truncation or freeing. * * It is legal to call this function for any page, mlocked or not. * If called for a page that is still mapped by mlocked vmas, all we do * is revert to lazy LRU behaviour -- semantics are not broken. */ extern void clear_page_mlock(struct page *page); extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /* * At what user virtual address is page expected in vma? * Returns -EFAULT if all of the page is outside the range of vma. * If page is a compound head, the entire compound page is considered. */ static inline unsigned long vma_address(struct page *page, struct vm_area_struct *vma) { pgoff_t pgoff; unsigned long address; VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ pgoff = page_to_pgoff(page); if (pgoff >= vma->vm_pgoff) { address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address >= vma->vm_end) address = -EFAULT; } else if (PageHead(page) && pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) { /* Test above avoids possibility of wrap to 0 on 32-bit */ address = vma->vm_start; } else { address = -EFAULT; } return address; } /* * Then at what user virtual address will none of the page be found in vma? * Assumes that vma_address() already returned a good starting address. * If page is a compound head, the entire compound page is considered. */ static inline unsigned long vma_address_end(struct page *page, struct vm_area_struct *vma) { pgoff_t pgoff; unsigned long address; VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ pgoff = page_to_pgoff(page) + compound_nr(page); address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address > vma->vm_end) address = vma->vm_end; return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, struct file *fpin) { int flags = vmf->flags; if (fpin) return fpin; /* * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or * anything, so we only pin the file and drop the mmap_lock if only * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt. */ if (fault_flag_allow_retry_first(flags) && !(flags & FAULT_FLAG_RETRY_NOWAIT)) { fpin = get_file(vmf->vma->vm_file); mmap_read_unlock(vmf->vma->vm_mm); } return fpin; } #else /* !CONFIG_MMU */ static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) { } #endif /* !CONFIG_MMU */ /* * Return the mem_map entry representing the 'offset' subpage within * the maximally aligned gigantic page 'base'. Handle any discontiguity * in the mem_map at MAX_ORDER_NR_PAGES boundaries. */ static inline struct page *mem_map_offset(struct page *base, int offset) { if (unlikely(offset >= MAX_ORDER_NR_PAGES)) return nth_page(base, offset); return base + offset; } /* * Iterator over all subpages within the maximally aligned gigantic * page 'base'. Handle any discontiguity in the mem_map. */ static inline struct page *mem_map_next(struct page *iter, struct page *base, int offset) { if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) { unsigned long pfn = page_to_pfn(base) + offset; if (!pfn_valid(pfn)) return NULL; return pfn_to_page(pfn); } return iter + 1; } /* Memory initialisation debug and verification */ enum mminit_level { MMINIT_WARNING, MMINIT_VERIFY, MMINIT_TRACE }; #ifdef CONFIG_DEBUG_MEMORY_INIT extern int mminit_loglevel; #define mminit_dprintk(level, prefix, fmt, arg...) \ do { \ if (level < mminit_loglevel) { \ if (level <= MMINIT_WARNING) \ pr_warn("mminit::" prefix " " fmt, ##arg); \ else \ printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ } \ } while (0) extern void mminit_verify_pageflags_layout(void); extern void mminit_verify_zonelist(void); #else static inline void mminit_dprintk(enum mminit_level level, const char *prefix, const char *fmt, ...) { } static inline void mminit_verify_pageflags_layout(void) { } static inline void mminit_verify_zonelist(void) { } #endif /* CONFIG_DEBUG_MEMORY_INIT */ /* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */ #if defined(CONFIG_SPARSEMEM) extern void mminit_validate_memmodel_limits(unsigned long *start_pfn, unsigned long *end_pfn); #else static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn, unsigned long *end_pfn) { } #endif /* CONFIG_SPARSEMEM */ #define NODE_RECLAIM_NOSCAN -2 #define NODE_RECLAIM_FULL -1 #define NODE_RECLAIM_SOME 0 #define NODE_RECLAIM_SUCCESS 1 #ifdef CONFIG_NUMA extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); extern int find_next_best_node(int node, nodemask_t *used_node_mask); #else static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, unsigned int order) { return NODE_RECLAIM_NOSCAN; } static inline int find_next_best_node(int node, nodemask_t *used_node_mask) { return NUMA_NO_NODE; } #endif extern int hwpoison_filter(struct page *p); extern u32 hwpoison_filter_dev_major; extern u32 hwpoison_filter_dev_minor; extern u64 hwpoison_filter_flags_mask; extern u64 hwpoison_filter_flags_value; extern u64 hwpoison_filter_memcg; extern u32 hwpoison_filter_enable; extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern void set_pageblock_order(void); unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *page_list); /* The ALLOC_WMARK bits are used as an index to zone->watermark */ #define ALLOC_WMARK_MIN WMARK_MIN #define ALLOC_WMARK_LOW WMARK_LOW #define ALLOC_WMARK_HIGH WMARK_HIGH #define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ /* Mask to get the watermark bits */ #define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) /* * Only MMU archs have async oom victim reclaim - aka oom_reaper so we * cannot assume a reduced access to memory reserves is sufficient for * !MMU */ #ifdef CONFIG_MMU #define ALLOC_OOM 0x08 #else #define ALLOC_OOM ALLOC_NO_WATERMARKS #endif #define ALLOC_HARDER 0x10 /* try to alloc harder */ #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ #ifdef CONFIG_ZONE_DMA32 #define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */ #else #define ALLOC_NOFRAGMENT 0x0 #endif #define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */ enum ttu_flags; struct tlbflush_unmap_batch; /* * only for MM internal work items which do not depend on * any allocations or locks which might depend on allocations */ extern struct workqueue_struct *mm_percpu_wq; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); void flush_tlb_batched_pending(struct mm_struct *mm); #else static inline void try_to_unmap_flush(void) { } static inline void try_to_unmap_flush_dirty(void) { } static inline void flush_tlb_batched_pending(struct mm_struct *mm) { } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; static inline bool is_migrate_highatomic(enum migratetype migratetype) { return migratetype == MIGRATE_HIGHATOMIC; } static inline bool is_migrate_highatomic_page(struct page *page) { return get_pageblock_migratetype(page) == MIGRATE_HIGHATOMIC; } void setup_zone_pageset(struct zone *zone); struct migration_target_control { int nid; /* preferred node id */ nodemask_t *nmask; gfp_t gfp_mask; }; /* * mm/vmalloc.c */ #ifdef CONFIG_MMU int vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); #else static inline int vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { return -EINVAL; } #endif void vunmap_range_noflush(unsigned long start, unsigned long end); int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags); #endif /* __MM_INTERNAL_H */ |
| 85 85 2215 73 85 2142 2298 2035 7 1807 751 750 2216 2214 354 1870 1740 1960 2033 2032 1 18 2011 2029 2225 3 1 2228 1 190 188 202 3 3 2 1 191 2 191 2 2 191 2 190 2325 2326 16 3 29 1 2009 1991 5 12 1 1874 1863 1 1 1 1 1 7 7 1687 7 1682 1878 2 3 1 1868 7 1115 54 346 120 246 1388 491 150 1723 5 5 391 1303 1690 12 1678 1691 5 340 1 12 1 1 273 261 12 1 363 1 1 343 3 1 15 2 355 274 2 272 2 1 1 85 2 2 1 78 1 1 58 2 7 66 17 2 3 1 1 1 1 2 1 5 6 6 1 1 147 2 2 2 138 2 119 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2017 Facebook */ #include <linux/bpf.h> #include <linux/btf_ids.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/etherdevice.h> #include <linux/filter.h> #include <linux/rcupdate_trace.h> #include <linux/sched/signal.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> #include <net/tcp.h> #include <net/net_namespace.h> #include <linux/error-injection.h> #include <linux/smp.h> #include <linux/sock_diag.h> #include <net/xdp.h> #define CREATE_TRACE_POINTS #include <trace/events/bpf_test_run.h> struct bpf_test_timer { enum { NO_PREEMPT, NO_MIGRATE } mode; u32 i; u64 time_start, time_spent; }; static void bpf_test_timer_enter(struct bpf_test_timer *t) __acquires(rcu) { rcu_read_lock(); if (t->mode == NO_PREEMPT) preempt_disable(); else migrate_disable(); t->time_start = ktime_get_ns(); } static void bpf_test_timer_leave(struct bpf_test_timer *t) __releases(rcu) { t->time_start = 0; if (t->mode == NO_PREEMPT) preempt_enable(); else migrate_enable(); rcu_read_unlock(); } static bool bpf_test_timer_continue(struct bpf_test_timer *t, u32 repeat, int *err, u32 *duration) __must_hold(rcu) { t->i++; if (t->i >= repeat) { /* We're done. */ t->time_spent += ktime_get_ns() - t->time_start; do_div(t->time_spent, t->i); *duration = t->time_spent > U32_MAX ? U32_MAX : (u32)t->time_spent; *err = 0; goto reset; } if (signal_pending(current)) { /* During iteration: we've been cancelled, abort. */ *err = -EINTR; goto reset; } if (need_resched()) { /* During iteration: we need to reschedule between runs. */ t->time_spent += ktime_get_ns() - t->time_start; bpf_test_timer_leave(t); cond_resched(); bpf_test_timer_enter(t); } /* Do another round. */ return true; reset: t->i = 0; return false; } static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *retval, u32 *time, bool xdp) { struct bpf_prog_array_item item = {.prog = prog}; struct bpf_run_ctx *old_ctx; struct bpf_cg_run_ctx run_ctx; struct bpf_test_timer t = { NO_MIGRATE }; enum bpf_cgroup_storage_type stype; int ret; for_each_cgroup_storage_type(stype) { item.cgroup_storage[stype] = bpf_cgroup_storage_alloc(prog, stype); if (IS_ERR(item.cgroup_storage[stype])) { item.cgroup_storage[stype] = NULL; for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(item.cgroup_storage[stype]); return -ENOMEM; } } if (!repeat) repeat = 1; bpf_test_timer_enter(&t); old_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); do { run_ctx.prog_item = &item; if (xdp) *retval = bpf_prog_run_xdp(prog, ctx); else *retval = bpf_prog_run(prog, ctx); } while (bpf_test_timer_continue(&t, repeat, &ret, time)); bpf_reset_run_ctx(old_ctx); bpf_test_timer_leave(&t); for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(item.cgroup_storage[stype]); return ret; } static int bpf_test_finish(const union bpf_attr *kattr, union bpf_attr __user *uattr, const void *data, u32 size, u32 retval, u32 duration) { void __user *data_out = u64_to_user_ptr(kattr->test.data_out); int err = -EFAULT; u32 copy_size = size; /* Clamp copy if the user has provided a size hint, but copy the full * buffer if not to retain old behaviour. */ if (kattr->test.data_size_out && copy_size > kattr->test.data_size_out) { copy_size = kattr->test.data_size_out; err = -ENOSPC; } if (data_out && copy_to_user(data_out, data, copy_size)) goto out; if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size))) goto out; if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval))) goto out; if (copy_to_user(&uattr->test.duration, &duration, sizeof(duration))) goto out; if (err != -ENOSPC) err = 0; out: trace_bpf_test_finish(&err); return err; } /* Integer types of various sizes and pointer combinations cover variety of * architecture dependent calling conventions. 7+ can be supported in the * future. */ __diag_push(); __diag_ignore(GCC, 8, "-Wmissing-prototypes", "Global functions as their definitions will be in vmlinux BTF"); int noinline bpf_fentry_test1(int a) { return a + 1; } int noinline bpf_fentry_test2(int a, u64 b) { return a + b; } int noinline bpf_fentry_test3(char a, int b, u64 c) { return a + b + c; } int noinline bpf_fentry_test4(void *a, char b, int c, u64 d) { return (long)a + b + c + d; } int noinline bpf_fentry_test5(u64 a, void *b, short c, int d, u64 e) { return a + (long)b + c + d + e; } int noinline bpf_fentry_test6(u64 a, void *b, short c, int d, void *e, u64 f) { return a + (long)b + c + d + (long)e + f; } struct bpf_fentry_test_t { struct bpf_fentry_test_t *a; }; int noinline bpf_fentry_test7(struct bpf_fentry_test_t *arg) { return (long)arg; } int noinline bpf_fentry_test8(struct bpf_fentry_test_t *arg) { return (long)arg->a; } int noinline bpf_modify_return_test(int a, int *b) { *b += 1; return a + *b; } u64 noinline bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d) { return a + b + c + d; } int noinline bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b) { return a + b; } struct sock * noinline bpf_kfunc_call_test3(struct sock *sk) { return sk; } __diag_pop(); ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO); BTF_SET_START(test_sk_kfunc_ids) BTF_ID(func, bpf_kfunc_call_test1) BTF_ID(func, bpf_kfunc_call_test2) BTF_ID(func, bpf_kfunc_call_test3) BTF_SET_END(test_sk_kfunc_ids) bool bpf_prog_test_check_kfunc_call(u32 kfunc_id) { return btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id); } static void *bpf_test_init(const union bpf_attr *kattr, u32 size, u32 headroom, u32 tailroom) { void __user *data_in = u64_to_user_ptr(kattr->test.data_in); u32 user_size = kattr->test.data_size_in; void *data; if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom) return ERR_PTR(-EINVAL); if (user_size > size) return ERR_PTR(-EMSGSIZE); size = SKB_DATA_ALIGN(size); data = kzalloc(size + headroom + tailroom, GFP_USER); if (!data) return ERR_PTR(-ENOMEM); if (copy_from_user(data + headroom, data_in, user_size)) { kfree(data); return ERR_PTR(-EFAULT); } return data; } int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { struct bpf_fentry_test_t arg = {}; u16 side_effect = 0, ret = 0; int b = 2, err = -EFAULT; u32 retval = 0; if (kattr->test.flags || kattr->test.cpu) return -EINVAL; switch (prog->expected_attach_type) { case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: if (bpf_fentry_test1(1) != 2 || bpf_fentry_test2(2, 3) != 5 || bpf_fentry_test3(4, 5, 6) != 15 || bpf_fentry_test4((void *)7, 8, 9, 10) != 34 || bpf_fentry_test5(11, (void *)12, 13, 14, 15) != 65 || bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111 || bpf_fentry_test7((struct bpf_fentry_test_t *)0) != 0 || bpf_fentry_test8(&arg) != 0) goto out; break; case BPF_MODIFY_RETURN: ret = bpf_modify_return_test(1, &b); if (b != 2) side_effect = 1; break; default: goto out; } retval = ((u32)side_effect << 16) | ret; if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval))) goto out; err = 0; out: trace_bpf_test_finish(&err); return err; } struct bpf_raw_tp_test_run_info { struct bpf_prog *prog; void *ctx; u32 retval; }; static void __bpf_prog_test_run_raw_tp(void *data) { struct bpf_raw_tp_test_run_info *info = data; struct bpf_trace_run_ctx run_ctx = {}; struct bpf_run_ctx *old_run_ctx; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); rcu_read_lock(); info->retval = bpf_prog_run(info->prog, info->ctx); rcu_read_unlock(); bpf_reset_run_ctx(old_run_ctx); } int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in); __u32 ctx_size_in = kattr->test.ctx_size_in; struct bpf_raw_tp_test_run_info info; int cpu = kattr->test.cpu, err = 0; int current_cpu; /* doesn't support data_in/out, ctx_out, duration, or repeat */ if (kattr->test.data_in || kattr->test.data_out || kattr->test.ctx_out || kattr->test.duration || kattr->test.repeat) return -EINVAL; if (ctx_size_in < prog->aux->max_ctx_offset || ctx_size_in > MAX_BPF_FUNC_ARGS * sizeof(u64)) return -EINVAL; if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 && cpu != 0) return -EINVAL; if (ctx_size_in) { info.ctx = kzalloc(ctx_size_in, GFP_USER); if (!info.ctx) return -ENOMEM; if (copy_from_user(info.ctx, ctx_in, ctx_size_in)) { err = -EFAULT; goto out; } } else { info.ctx = NULL; } info.prog = prog; current_cpu = get_cpu(); if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 || cpu == current_cpu) { __bpf_prog_test_run_raw_tp(&info); } else if (cpu >= nr_cpu_ids || !cpu_online(cpu)) { /* smp_call_function_single() also checks cpu_online() * after csd_lock(). However, since cpu is from user * space, let's do an extra quick check to filter out * invalid value before smp_call_function_single(). */ err = -ENXIO; } else { err = smp_call_function_single(cpu, __bpf_prog_test_run_raw_tp, &info, 1); } put_cpu(); if (!err && copy_to_user(&uattr->test.retval, &info.retval, sizeof(u32))) err = -EFAULT; out: kfree(info.ctx); return err; } static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size) { void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in); void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out); u32 size = kattr->test.ctx_size_in; void *data; int err; if (!data_in && !data_out) return NULL; data = kzalloc(max_size, GFP_USER); if (!data) return ERR_PTR(-ENOMEM); if (data_in) { err = bpf_check_uarg_tail_zero(USER_BPFPTR(data_in), max_size, size); if (err) { kfree(data); return ERR_PTR(err); } size = min_t(u32, max_size, size); if (copy_from_user(data, data_in, size)) { kfree(data); return ERR_PTR(-EFAULT); } } return data; } static int bpf_ctx_finish(const union bpf_attr *kattr, union bpf_attr __user *uattr, const void *data, u32 size) { void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out); int err = -EFAULT; u32 copy_size = size; if (!data || !data_out) return 0; if (copy_size > kattr->test.ctx_size_out) { copy_size = kattr->test.ctx_size_out; err = -ENOSPC; } if (copy_to_user(data_out, data, copy_size)) goto out; if (copy_to_user(&uattr->test.ctx_size_out, &size, sizeof(size))) goto out; if (err != -ENOSPC) err = 0; out: return err; } /** * range_is_zero - test whether buffer is initialized * @buf: buffer to check * @from: check from this position * @to: check up until (excluding) this position * * This function returns true if the there is a non-zero byte * in the buf in the range [from,to). */ static inline bool range_is_zero(void *buf, size_t from, size_t to) { return !memchr_inv((u8 *)buf + from, 0, to - from); } static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) { struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb; if (!__skb) return 0; /* make sure the fields we don't use are zeroed */ if (!range_is_zero(__skb, 0, offsetof(struct __sk_buff, mark))) return -EINVAL; /* mark is allowed */ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, mark), offsetof(struct __sk_buff, priority))) return -EINVAL; /* priority is allowed */ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, priority), offsetof(struct __sk_buff, ifindex))) return -EINVAL; /* ifindex is allowed */ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, ifindex), offsetof(struct __sk_buff, cb))) return -EINVAL; /* cb is allowed */ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, cb), offsetof(struct __sk_buff, tstamp))) return -EINVAL; /* tstamp is allowed */ /* wire_len is allowed */ /* gso_segs is allowed */ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, gso_segs), offsetof(struct __sk_buff, gso_size))) return -EINVAL; /* gso_size is allowed */ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, gso_size), sizeof(struct __sk_buff))) return -EINVAL; skb->mark = __skb->mark; skb->priority = __skb->priority; skb->tstamp = __skb->tstamp; memcpy(&cb->data, __skb->cb, QDISC_CB_PRIV_LEN); if (__skb->wire_len == 0) { cb->pkt_len = skb->len; } else { if (__skb->wire_len < skb->len || __skb->wire_len > GSO_MAX_SIZE) return -EINVAL; cb->pkt_len = __skb->wire_len; } if (__skb->gso_segs > GSO_MAX_SEGS) return -EINVAL; skb_shinfo(skb)->gso_segs = __skb->gso_segs; skb_shinfo(skb)->gso_size = __skb->gso_size; return 0; } static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb) { struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb; if (!__skb) return; __skb->mark = skb->mark; __skb->priority = skb->priority; __skb->ifindex = skb->dev->ifindex; __skb->tstamp = skb->tstamp; memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN); __skb->wire_len = cb->pkt_len; __skb->gso_segs = skb_shinfo(skb)->gso_segs; } static struct proto bpf_dummy_proto = { .name = "bpf_dummy", .owner = THIS_MODULE, .obj_size = sizeof(struct sock), }; int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { bool is_l2 = false, is_direct_pkt_access = false; struct net *net = current->nsproxy->net_ns; struct net_device *dev = net->loopback_dev; u32 size = kattr->test.data_size_in; u32 repeat = kattr->test.repeat; struct __sk_buff *ctx = NULL; u32 retval, duration; int hh_len = ETH_HLEN; struct sk_buff *skb; struct sock *sk; void *data; int ret; if (kattr->test.flags || kattr->test.cpu) return -EINVAL; data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN, SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); if (IS_ERR(data)) return PTR_ERR(data); ctx = bpf_ctx_init(kattr, sizeof(struct __sk_buff)); if (IS_ERR(ctx)) { kfree(data); return PTR_ERR(ctx); } switch (prog->type) { case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: is_l2 = true; fallthrough; case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_XMIT: is_direct_pkt_access = true; break; default: break; } sk = sk_alloc(net, AF_UNSPEC, GFP_USER, &bpf_dummy_proto, 1); if (!sk) { kfree(data); kfree(ctx); return -ENOMEM; } sock_init_data(NULL, sk); skb = build_skb(data, 0); if (!skb) { kfree(data); kfree(ctx); sk_free(sk); return -ENOMEM; } skb->sk = sk; skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); __skb_put(skb, size); if (ctx && ctx->ifindex > 1) { dev = dev_get_by_index(net, ctx->ifindex); if (!dev) { ret = -ENODEV; goto out; } } skb->protocol = eth_type_trans(skb, dev); skb_reset_network_header(skb); switch (skb->protocol) { case htons(ETH_P_IP): sk->sk_family = AF_INET; if (sizeof(struct iphdr) <= skb_headlen(skb)) { sk->sk_rcv_saddr = ip_hdr(skb)->saddr; sk->sk_daddr = ip_hdr(skb)->daddr; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): sk->sk_family = AF_INET6; if (sizeof(struct ipv6hdr) <= skb_headlen(skb)) { sk->sk_v6_rcv_saddr = ipv6_hdr(skb)->saddr; sk->sk_v6_daddr = ipv6_hdr(skb)->daddr; } break; #endif default: break; } if (is_l2) __skb_push(skb, hh_len); if (is_direct_pkt_access) bpf_compute_data_pointers(skb); ret = convert___skb_to_skb(skb, ctx); if (ret) goto out; ret = bpf_test_run(prog, skb, repeat, &retval, &duration, false); if (ret) goto out; if (!is_l2) { if (skb_headroom(skb) < hh_len) { int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb)); if (pskb_expand_head(skb, nhead, 0, GFP_USER)) { ret = -ENOMEM; goto out; } } memset(__skb_push(skb, hh_len), 0, hh_len); } convert_skb_to___skb(skb, ctx); size = skb->len; /* bpf program can never convert linear skb to non-linear */ if (WARN_ON_ONCE(skb_is_nonlinear(skb))) size = skb_headlen(skb); ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, ctx, sizeof(struct __sk_buff)); out: if (dev && dev != net->loopback_dev) dev_put(dev); kfree_skb(skb); sk_free(sk); kfree(ctx); return ret; } static int xdp_convert_md_to_buff(struct xdp_md *xdp_md, struct xdp_buff *xdp) { unsigned int ingress_ifindex, rx_queue_index; struct netdev_rx_queue *rxqueue; struct net_device *device; if (!xdp_md) return 0; if (xdp_md->egress_ifindex != 0) return -EINVAL; ingress_ifindex = xdp_md->ingress_ifindex; rx_queue_index = xdp_md->rx_queue_index; if (!ingress_ifindex && rx_queue_index) return -EINVAL; if (ingress_ifindex) { device = dev_get_by_index(current->nsproxy->net_ns, ingress_ifindex); if (!device) return -ENODEV; if (rx_queue_index >= device->real_num_rx_queues) goto free_dev; rxqueue = __netif_get_rx_queue(device, rx_queue_index); if (!xdp_rxq_info_is_reg(&rxqueue->xdp_rxq)) goto free_dev; xdp->rxq = &rxqueue->xdp_rxq; /* The device is now tracked in the xdp->rxq for later * dev_put() */ } xdp->data = xdp->data_meta + xdp_md->data; return 0; free_dev: dev_put(device); return -EINVAL; } static void xdp_convert_buff_to_md(struct xdp_buff *xdp, struct xdp_md *xdp_md) { if (!xdp_md) return; xdp_md->data = xdp->data - xdp->data_meta; xdp_md->data_end = xdp->data_end - xdp->data_meta; if (xdp_md->ingress_ifindex) dev_put(xdp->rxq->dev); } int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); u32 headroom = XDP_PACKET_HEADROOM; u32 size = kattr->test.data_size_in; u32 repeat = kattr->test.repeat; struct netdev_rx_queue *rxqueue; struct xdp_buff xdp = {}; u32 retval, duration; struct xdp_md *ctx; u32 max_data_sz; void *data; int ret = -EINVAL; if (prog->expected_attach_type == BPF_XDP_DEVMAP || prog->expected_attach_type == BPF_XDP_CPUMAP) return -EINVAL; ctx = bpf_ctx_init(kattr, sizeof(struct xdp_md)); if (IS_ERR(ctx)) return PTR_ERR(ctx); if (ctx) { /* There can't be user provided data before the meta data */ if (ctx->data_meta || ctx->data_end != size || ctx->data > ctx->data_end || unlikely(xdp_metalen_invalid(ctx->data))) goto free_ctx; /* Meta data is allocated from the headroom */ headroom -= ctx->data; } /* XDP have extra tailroom as (most) drivers use full page */ max_data_sz = 4096 - headroom - tailroom; data = bpf_test_init(kattr, max_data_sz, headroom, tailroom); if (IS_ERR(data)) { ret = PTR_ERR(data); goto free_ctx; } rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0); xdp_init_buff(&xdp, headroom + max_data_sz + tailroom, &rxqueue->xdp_rxq); xdp_prepare_buff(&xdp, data, headroom, size, true); ret = xdp_convert_md_to_buff(ctx, &xdp); if (ret) goto free_data; bpf_prog_change_xdp(NULL, prog); ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true); /* We convert the xdp_buff back to an xdp_md before checking the return * code so the reference count of any held netdevice will be decremented * even if the test run failed. */ xdp_convert_buff_to_md(&xdp, ctx); if (ret) goto out; if (xdp.data_meta != data + headroom || xdp.data_end != xdp.data_meta + size) size = xdp.data_end - xdp.data_meta; ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval, duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, ctx, sizeof(struct xdp_md)); out: bpf_prog_change_xdp(prog, NULL); free_data: kfree(data); free_ctx: kfree(ctx); return ret; } static int verify_user_bpf_flow_keys(struct bpf_flow_keys *ctx) { /* make sure the fields we don't use are zeroed */ if (!range_is_zero(ctx, 0, offsetof(struct bpf_flow_keys, flags))) return -EINVAL; /* flags is allowed */ if (!range_is_zero(ctx, offsetofend(struct bpf_flow_keys, flags), sizeof(struct bpf_flow_keys))) return -EINVAL; return 0; } int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { struct bpf_test_timer t = { NO_PREEMPT }; u32 size = kattr->test.data_size_in; struct bpf_flow_dissector ctx = {}; u32 repeat = kattr->test.repeat; struct bpf_flow_keys *user_ctx; struct bpf_flow_keys flow_keys; const struct ethhdr *eth; unsigned int flags = 0; u32 retval, duration; void *data; int ret; if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR) return -EINVAL; if (kattr->test.flags || kattr->test.cpu) return -EINVAL; if (size < ETH_HLEN) return -EINVAL; data = bpf_test_init(kattr, size, 0, 0); if (IS_ERR(data)) return PTR_ERR(data); eth = (struct ethhdr *)data; if (!repeat) repeat = 1; user_ctx = bpf_ctx_init(kattr, sizeof(struct bpf_flow_keys)); if (IS_ERR(user_ctx)) { kfree(data); return PTR_ERR(user_ctx); } if (user_ctx) { ret = verify_user_bpf_flow_keys(user_ctx); if (ret) goto out; flags = user_ctx->flags; } ctx.flow_keys = &flow_keys; ctx.data = data; ctx.data_end = (__u8 *)data + size; bpf_test_timer_enter(&t); do { retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN, size, flags); } while (bpf_test_timer_continue(&t, repeat, &ret, &duration)); bpf_test_timer_leave(&t); if (ret < 0) goto out; ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys), retval, duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(struct bpf_flow_keys)); out: kfree(user_ctx); kfree(data); return ret; } int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { struct bpf_test_timer t = { NO_PREEMPT }; struct bpf_prog_array *progs = NULL; struct bpf_sk_lookup_kern ctx = {}; u32 repeat = kattr->test.repeat; struct bpf_sk_lookup *user_ctx; u32 retval, duration; int ret = -EINVAL; if (prog->type != BPF_PROG_TYPE_SK_LOOKUP) return -EINVAL; if (kattr->test.flags || kattr->test.cpu) return -EINVAL; if (kattr->test.data_in || kattr->test.data_size_in || kattr->test.data_out || kattr->test.data_size_out) return -EINVAL; if (!repeat) repeat = 1; user_ctx = bpf_ctx_init(kattr, sizeof(*user_ctx)); if (IS_ERR(user_ctx)) return PTR_ERR(user_ctx); if (!user_ctx) return -EINVAL; if (user_ctx->sk) goto out; if (!range_is_zero(user_ctx, offsetofend(typeof(*user_ctx), local_port), sizeof(*user_ctx))) goto out; if (user_ctx->local_port > U16_MAX) { ret = -ERANGE; goto out; } ctx.family = (u16)user_ctx->family; ctx.protocol = (u16)user_ctx->protocol; ctx.dport = (u16)user_ctx->local_port; ctx.sport = user_ctx->remote_port; switch (ctx.family) { case AF_INET: ctx.v4.daddr = (__force __be32)user_ctx->local_ip4; ctx.v4.saddr = (__force __be32)user_ctx->remote_ip4; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: ctx.v6.daddr = (struct in6_addr *)user_ctx->local_ip6; ctx.v6.saddr = (struct in6_addr *)user_ctx->remote_ip6; break; #endif default: ret = -EAFNOSUPPORT; goto out; } progs = bpf_prog_array_alloc(1, GFP_KERNEL); if (!progs) { ret = -ENOMEM; goto out; } progs->items[0].prog = prog; bpf_test_timer_enter(&t); do { ctx.selected_sk = NULL; retval = BPF_PROG_SK_LOOKUP_RUN_ARRAY(progs, ctx, bpf_prog_run); } while (bpf_test_timer_continue(&t, repeat, &ret, &duration)); bpf_test_timer_leave(&t); if (ret < 0) goto out; user_ctx->cookie = 0; if (ctx.selected_sk) { if (ctx.selected_sk->sk_reuseport && !ctx.no_reuseport) { ret = -EOPNOTSUPP; goto out; } user_ctx->cookie = sock_gen_cookie(ctx.selected_sk); } ret = bpf_test_finish(kattr, uattr, NULL, 0, retval, duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(*user_ctx)); out: bpf_prog_array_free(progs); kfree(user_ctx); return ret; } int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in); __u32 ctx_size_in = kattr->test.ctx_size_in; void *ctx = NULL; u32 retval; int err = 0; /* doesn't support data_in/out, ctx_out, duration, or repeat or flags */ if (kattr->test.data_in || kattr->test.data_out || kattr->test.ctx_out || kattr->test.duration || kattr->test.repeat || kattr->test.flags) return -EINVAL; if (ctx_size_in < prog->aux->max_ctx_offset || ctx_size_in > U16_MAX) return -EINVAL; if (ctx_size_in) { ctx = kzalloc(ctx_size_in, GFP_USER); if (!ctx) return -ENOMEM; if (copy_from_user(ctx, ctx_in, ctx_size_in)) { err = -EFAULT; goto out; } } rcu_read_lock_trace(); retval = bpf_prog_run_pin_on_cpu(prog, ctx); rcu_read_unlock_trace(); if (copy_to_user(&uattr->test.retval, &retval, sizeof(u32))) { err = -EFAULT; goto out; } if (ctx_size_in) if (copy_to_user(ctx_in, ctx, ctx_size_in)) err = -EFAULT; out: kfree(ctx); return err; } |
| 569 569 568 569 2250 2250 1962 1963 1963 1963 2259 2259 1963 2258 569 569 569 569 2250 2251 1964 1964 1964 2259 2259 1964 2259 569 2221 2221 443 443 2304 1934 480 480 1934 1933 1931 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net-sysfs.c - network device class and attributes * * Copyright (c) 2003 Stephen Hemminger <shemminger@osdl.org> */ #include <linux/capability.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/sched/isolation.h> #include <linux/nsproxy.h> #include <net/sock.h> #include <net/net_namespace.h> #include <linux/rtnetlink.h> #include <linux/vmalloc.h> #include <linux/export.h> #include <linux/jiffies.h> #include <linux/pm_runtime.h> #include <linux/of.h> #include <linux/of_net.h> #include <linux/cpu.h> #include "net-sysfs.h" #ifdef CONFIG_SYSFS static const char fmt_hex[] = "%#x\n"; static const char fmt_dec[] = "%d\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; /* Caller holds RTNL or dev_base_lock */ static inline int dev_isalive(const struct net_device *dev) { return dev->reg_state <= NETREG_REGISTERED; } /* use same locking rules as GIF* ioctl's */ static ssize_t netdev_show(const struct device *dev, struct device_attribute *attr, char *buf, ssize_t (*format)(const struct net_device *, char *)) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; read_lock(&dev_base_lock); if (dev_isalive(ndev)) ret = (*format)(ndev, buf); read_unlock(&dev_base_lock); return ret; } /* generate a show function for simple field */ #define NETDEVICE_SHOW(field, format_string) \ static ssize_t format_##field(const struct net_device *dev, char *buf) \ { \ return sprintf(buf, format_string, dev->field); \ } \ static ssize_t field##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ return netdev_show(dev, attr, buf, format_##field); \ } \ #define NETDEVICE_SHOW_RO(field, format_string) \ NETDEVICE_SHOW(field, format_string); \ static DEVICE_ATTR_RO(field) #define NETDEVICE_SHOW_RW(field, format_string) \ NETDEVICE_SHOW(field, format_string); \ static DEVICE_ATTR_RW(field) /* use same locking and permission rules as SIF* ioctl's */ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len, int (*set)(struct net_device *, unsigned long)) { struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); unsigned long new; int ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = kstrtoul(buf, 0, &new); if (ret) goto err; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { ret = (*set)(netdev, new); if (ret == 0) ret = len; } rtnl_unlock(); err: return ret; } NETDEVICE_SHOW_RO(dev_id, fmt_hex); NETDEVICE_SHOW_RO(dev_port, fmt_dec); NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec); NETDEVICE_SHOW_RO(addr_len, fmt_dec); NETDEVICE_SHOW_RO(ifindex, fmt_dec); NETDEVICE_SHOW_RO(type, fmt_dec); NETDEVICE_SHOW_RO(link_mode, fmt_dec); static ssize_t iflink_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); return sprintf(buf, fmt_dec, dev_get_iflink(ndev)); } static DEVICE_ATTR_RO(iflink); static ssize_t format_name_assign_type(const struct net_device *dev, char *buf) { return sprintf(buf, fmt_dec, dev->name_assign_type); } static ssize_t name_assign_type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; if (ndev->name_assign_type != NET_NAME_UNKNOWN) ret = netdev_show(dev, attr, buf, format_name_assign_type); return ret; } static DEVICE_ATTR_RO(name_assign_type); /* use same locking rules as GIFHWADDR ioctl's */ static ssize_t address_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; read_lock(&dev_base_lock); if (dev_isalive(ndev)) ret = sysfs_format_mac(buf, ndev->dev_addr, ndev->addr_len); read_unlock(&dev_base_lock); return ret; } static DEVICE_ATTR_RO(address); static ssize_t broadcast_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); if (dev_isalive(ndev)) return sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len); return -EINVAL; } static DEVICE_ATTR_RO(broadcast); static int change_carrier(struct net_device *dev, unsigned long new_carrier) { if (!netif_running(dev)) return -EINVAL; return dev_change_carrier(dev, (bool)new_carrier); } static ssize_t carrier_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); /* The check is also done in change_carrier; this helps returning early * without hitting the trylock/restart in netdev_store. */ if (!netdev->netdev_ops->ndo_change_carrier) return -EOPNOTSUPP; return netdev_store(dev, attr, buf, len, change_carrier); } static ssize_t carrier_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); if (netif_running(netdev)) return sprintf(buf, fmt_dec, !!netif_carrier_ok(netdev)); return -EINVAL; } static DEVICE_ATTR_RW(carrier); static ssize_t speed_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; /* The check is also done in __ethtool_get_link_ksettings; this helps * returning early without hitting the trylock/restart below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; if (!rtnl_trylock()) return restart_syscall(); if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) ret = sprintf(buf, fmt_dec, cmd.base.speed); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(speed); static ssize_t duplex_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; /* The check is also done in __ethtool_get_link_ksettings; this helps * returning early without hitting the trylock/restart below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; if (!rtnl_trylock()) return restart_syscall(); if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) { const char *duplex; switch (cmd.base.duplex) { case DUPLEX_HALF: duplex = "half"; break; case DUPLEX_FULL: duplex = "full"; break; default: duplex = "unknown"; break; } ret = sprintf(buf, "%s\n", duplex); } } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(duplex); static ssize_t testing_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); if (netif_running(netdev)) return sprintf(buf, fmt_dec, !!netif_testing(netdev)); return -EINVAL; } static DEVICE_ATTR_RO(testing); static ssize_t dormant_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); if (netif_running(netdev)) return sprintf(buf, fmt_dec, !!netif_dormant(netdev)); return -EINVAL; } static DEVICE_ATTR_RO(dormant); static const char *const operstates[] = { "unknown", "notpresent", /* currently unused */ "down", "lowerlayerdown", "testing", "dormant", "up" }; static ssize_t operstate_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); unsigned char operstate; read_lock(&dev_base_lock); operstate = netdev->operstate; if (!netif_running(netdev)) operstate = IF_OPER_DOWN; read_unlock(&dev_base_lock); if (operstate >= ARRAY_SIZE(operstates)) return -EINVAL; /* should not happen */ return sprintf(buf, "%s\n", operstates[operstate]); } static DEVICE_ATTR_RO(operstate); static ssize_t carrier_changes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sprintf(buf, fmt_dec, atomic_read(&netdev->carrier_up_count) + atomic_read(&netdev->carrier_down_count)); } static DEVICE_ATTR_RO(carrier_changes); static ssize_t carrier_up_count_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sprintf(buf, fmt_dec, atomic_read(&netdev->carrier_up_count)); } static DEVICE_ATTR_RO(carrier_up_count); static ssize_t carrier_down_count_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sprintf(buf, fmt_dec, atomic_read(&netdev->carrier_down_count)); } static DEVICE_ATTR_RO(carrier_down_count); /* read-write attributes */ static int change_mtu(struct net_device *dev, unsigned long new_mtu) { return dev_set_mtu(dev, (int)new_mtu); } static ssize_t mtu_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_mtu); } NETDEVICE_SHOW_RW(mtu, fmt_dec); static int change_flags(struct net_device *dev, unsigned long new_flags) { return dev_change_flags(dev, (unsigned int)new_flags, NULL); } static ssize_t flags_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_flags); } NETDEVICE_SHOW_RW(flags, fmt_hex); static ssize_t tx_queue_len_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_store(dev, attr, buf, len, dev_change_tx_queue_len); } NETDEVICE_SHOW_RW(tx_queue_len, fmt_dec); static int change_gro_flush_timeout(struct net_device *dev, unsigned long val) { WRITE_ONCE(dev->gro_flush_timeout, val); return 0; } static ssize_t gro_flush_timeout_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_store(dev, attr, buf, len, change_gro_flush_timeout); } NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong); static int change_napi_defer_hard_irqs(struct net_device *dev, unsigned long val) { WRITE_ONCE(dev->napi_defer_hard_irqs, val); return 0; } static ssize_t napi_defer_hard_irqs_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_store(dev, attr, buf, len, change_napi_defer_hard_irqs); } NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_dec); static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); size_t count = len; ssize_t ret = 0; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; /* ignore trailing newline */ if (len > 0 && buf[len - 1] == '\n') --count; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { ret = dev_set_alias(netdev, buf, count); if (ret < 0) goto err; ret = len; netdev_state_change(netdev); } err: rtnl_unlock(); return ret; } static ssize_t ifalias_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); char tmp[IFALIASZ]; ssize_t ret = 0; ret = dev_get_alias(netdev, tmp, sizeof(tmp)); if (ret > 0) ret = sprintf(buf, "%s\n", tmp); return ret; } static DEVICE_ATTR_RW(ifalias); static int change_group(struct net_device *dev, unsigned long new_group) { dev_set_group(dev, (int)new_group); return 0; } static ssize_t group_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_group); } NETDEVICE_SHOW(group, fmt_dec); static DEVICE_ATTR(netdev_group, 0644, group_show, group_store); static int change_proto_down(struct net_device *dev, unsigned long proto_down) { return dev_change_proto_down(dev, (bool)proto_down); } static ssize_t proto_down_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); /* The check is also done in change_proto_down; this helps returning * early without hitting the trylock/restart in netdev_store. */ if (!netdev->netdev_ops->ndo_change_proto_down) return -EOPNOTSUPP; return netdev_store(dev, attr, buf, len, change_proto_down); } NETDEVICE_SHOW_RW(proto_down, fmt_dec); static ssize_t phys_port_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; /* The check is also done in dev_get_phys_port_id; this helps returning * early without hitting the trylock/restart below. */ if (!netdev->netdev_ops->ndo_get_phys_port_id) return -EOPNOTSUPP; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { struct netdev_phys_item_id ppid; ret = dev_get_phys_port_id(netdev, &ppid); if (!ret) ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_port_id); static ssize_t phys_port_name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; /* The checks are also done in dev_get_phys_port_name; this helps * returning early without hitting the trylock/restart below. */ if (!netdev->netdev_ops->ndo_get_phys_port_name && !netdev->netdev_ops->ndo_get_devlink_port) return -EOPNOTSUPP; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { char name[IFNAMSIZ]; ret = dev_get_phys_port_name(netdev, name, sizeof(name)); if (!ret) ret = sprintf(buf, "%s\n", name); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_port_name); static ssize_t phys_switch_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; /* The checks are also done in dev_get_phys_port_name; this helps * returning early without hitting the trylock/restart below. This works * because recurse is false when calling dev_get_port_parent_id. */ if (!netdev->netdev_ops->ndo_get_port_parent_id && !netdev->netdev_ops->ndo_get_devlink_port) return -EOPNOTSUPP; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { struct netdev_phys_item_id ppid = { }; ret = dev_get_port_parent_id(netdev, &ppid, false); if (!ret) ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_switch_id); static ssize_t threaded_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) ret = sprintf(buf, fmt_dec, netdev->threaded); rtnl_unlock(); return ret; } static int modify_napi_threaded(struct net_device *dev, unsigned long val) { int ret; if (list_empty(&dev->napi_list)) return -EOPNOTSUPP; if (val != 0 && val != 1) return -EOPNOTSUPP; ret = dev_set_threaded(dev, val); return ret; } static ssize_t threaded_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, modify_napi_threaded); } static DEVICE_ATTR_RW(threaded); static struct attribute *net_class_attrs[] __ro_after_init = { &dev_attr_netdev_group.attr, &dev_attr_type.attr, &dev_attr_dev_id.attr, &dev_attr_dev_port.attr, &dev_attr_iflink.attr, &dev_attr_ifindex.attr, &dev_attr_name_assign_type.attr, &dev_attr_addr_assign_type.attr, &dev_attr_addr_len.attr, &dev_attr_link_mode.attr, &dev_attr_address.attr, &dev_attr_broadcast.attr, &dev_attr_speed.attr, &dev_attr_duplex.attr, &dev_attr_dormant.attr, &dev_attr_testing.attr, &dev_attr_operstate.attr, &dev_attr_carrier_changes.attr, &dev_attr_ifalias.attr, &dev_attr_carrier.attr, &dev_attr_mtu.attr, &dev_attr_flags.attr, &dev_attr_tx_queue_len.attr, &dev_attr_gro_flush_timeout.attr, &dev_attr_napi_defer_hard_irqs.attr, &dev_attr_phys_port_id.attr, &dev_attr_phys_port_name.attr, &dev_attr_phys_switch_id.attr, &dev_attr_proto_down.attr, &dev_attr_carrier_up_count.attr, &dev_attr_carrier_down_count.attr, &dev_attr_threaded.attr, NULL, }; ATTRIBUTE_GROUPS(net_class); /* Show a given an attribute in the statistics group */ static ssize_t netstat_show(const struct device *d, struct device_attribute *attr, char *buf, unsigned long offset) { struct net_device *dev = to_net_dev(d); ssize_t ret = -EINVAL; WARN_ON(offset > sizeof(struct rtnl_link_stats64) || offset % sizeof(u64) != 0); read_lock(&dev_base_lock); if (dev_isalive(dev)) { struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); ret = sprintf(buf, fmt_u64, *(u64 *)(((u8 *)stats) + offset)); } read_unlock(&dev_base_lock); return ret; } /* generate a read-only statistics attribute */ #define NETSTAT_ENTRY(name) \ static ssize_t name##_show(struct device *d, \ struct device_attribute *attr, char *buf) \ { \ return netstat_show(d, attr, buf, \ offsetof(struct rtnl_link_stats64, name)); \ } \ static DEVICE_ATTR_RO(name) NETSTAT_ENTRY(rx_packets); NETSTAT_ENTRY(tx_packets); NETSTAT_ENTRY(rx_bytes); NETSTAT_ENTRY(tx_bytes); NETSTAT_ENTRY(rx_errors); NETSTAT_ENTRY(tx_errors); NETSTAT_ENTRY(rx_dropped); NETSTAT_ENTRY(tx_dropped); NETSTAT_ENTRY(multicast); NETSTAT_ENTRY(collisions); NETSTAT_ENTRY(rx_length_errors); NETSTAT_ENTRY(rx_over_errors); NETSTAT_ENTRY(rx_crc_errors); NETSTAT_ENTRY(rx_frame_errors); NETSTAT_ENTRY(rx_fifo_errors); NETSTAT_ENTRY(rx_missed_errors); NETSTAT_ENTRY(tx_aborted_errors); NETSTAT_ENTRY(tx_carrier_errors); NETSTAT_ENTRY(tx_fifo_errors); NETSTAT_ENTRY(tx_heartbeat_errors); NETSTAT_ENTRY(tx_window_errors); NETSTAT_ENTRY(rx_compressed); NETSTAT_ENTRY(tx_compressed); NETSTAT_ENTRY(rx_nohandler); static struct attribute *netstat_attrs[] __ro_after_init = { &dev_attr_rx_packets.attr, &dev_attr_tx_packets.attr, &dev_attr_rx_bytes.attr, &dev_attr_tx_bytes.attr, &dev_attr_rx_errors.attr, &dev_attr_tx_errors.attr, &dev_attr_rx_dropped.attr, &dev_attr_tx_dropped.attr, &dev_attr_multicast.attr, &dev_attr_collisions.attr, &dev_attr_rx_length_errors.attr, &dev_attr_rx_over_errors.attr, &dev_attr_rx_crc_errors.attr, &dev_attr_rx_frame_errors.attr, &dev_attr_rx_fifo_errors.attr, &dev_attr_rx_missed_errors.attr, &dev_attr_tx_aborted_errors.attr, &dev_attr_tx_carrier_errors.attr, &dev_attr_tx_fifo_errors.attr, &dev_attr_tx_heartbeat_errors.attr, &dev_attr_tx_window_errors.attr, &dev_attr_rx_compressed.attr, &dev_attr_tx_compressed.attr, &dev_attr_rx_nohandler.attr, NULL }; static const struct attribute_group netstat_group = { .name = "statistics", .attrs = netstat_attrs, }; #if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211) static struct attribute *wireless_attrs[] = { NULL }; static const struct attribute_group wireless_group = { .name = "wireless", .attrs = wireless_attrs, }; #endif #else /* CONFIG_SYSFS */ #define net_class_groups NULL #endif /* CONFIG_SYSFS */ #ifdef CONFIG_SYSFS #define to_rx_queue_attr(_attr) \ container_of(_attr, struct rx_queue_attribute, attr) #define to_rx_queue(obj) container_of(obj, struct netdev_rx_queue, kobj) static ssize_t rx_queue_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { const struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); struct netdev_rx_queue *queue = to_rx_queue(kobj); if (!attribute->show) return -EIO; return attribute->show(queue, buf); } static ssize_t rx_queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { const struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); struct netdev_rx_queue *queue = to_rx_queue(kobj); if (!attribute->store) return -EIO; return attribute->store(queue, buf, count); } static const struct sysfs_ops rx_queue_sysfs_ops = { .show = rx_queue_attr_show, .store = rx_queue_attr_store, }; #ifdef CONFIG_RPS static ssize_t show_rps_map(struct netdev_rx_queue *queue, char *buf) { struct rps_map *map; cpumask_var_t mask; int i, len; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; rcu_read_lock(); map = rcu_dereference(queue->rps_map); if (map) for (i = 0; i < map->len; i++) cpumask_set_cpu(map->cpus[i], mask); len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); rcu_read_unlock(); free_cpumask_var(mask); return len < PAGE_SIZE ? len : -EINVAL; } static ssize_t store_rps_map(struct netdev_rx_queue *queue, const char *buf, size_t len) { struct rps_map *old_map, *map; cpumask_var_t mask; int err, cpu, i, hk_flags; static DEFINE_MUTEX(rps_map_mutex); if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); if (err) { free_cpumask_var(mask); return err; } if (!cpumask_empty(mask)) { hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ; cpumask_and(mask, mask, housekeeping_cpumask(hk_flags)); if (cpumask_empty(mask)) { free_cpumask_var(mask); return -EINVAL; } } map = kzalloc(max_t(unsigned int, RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), GFP_KERNEL); if (!map) { free_cpumask_var(mask); return -ENOMEM; } i = 0; for_each_cpu_and(cpu, mask, cpu_online_mask) map->cpus[i++] = cpu; if (i) { map->len = i; } else { kfree(map); map = NULL; } mutex_lock(&rps_map_mutex); old_map = rcu_dereference_protected(queue->rps_map, mutex_is_locked(&rps_map_mutex)); rcu_assign_pointer(queue->rps_map, map); if (map) static_branch_inc(&rps_needed); if (old_map) static_branch_dec(&rps_needed); mutex_unlock(&rps_map_mutex); if (old_map) kfree_rcu(old_map, rcu); free_cpumask_var(mask); return len; } static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, char *buf) { struct rps_dev_flow_table *flow_table; unsigned long val = 0; rcu_read_lock(); flow_table = rcu_dereference(queue->rps_flow_table); if (flow_table) val = (unsigned long)flow_table->mask + 1; rcu_read_unlock(); return sprintf(buf, "%lu\n", val); } static void rps_dev_flow_table_release(struct rcu_head *rcu) { struct rps_dev_flow_table *table = container_of(rcu, struct rps_dev_flow_table, rcu); vfree(table); } static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, const char *buf, size_t len) { unsigned long mask, count; struct rps_dev_flow_table *table, *old_table; static DEFINE_SPINLOCK(rps_dev_flow_lock); int rc; if (!capable(CAP_NET_ADMIN)) return -EPERM; rc = kstrtoul(buf, 0, &count); if (rc < 0) return rc; if (count) { mask = count - 1; /* mask = roundup_pow_of_two(count) - 1; * without overflows... */ while ((mask | (mask >> 1)) != mask) mask |= (mask >> 1); /* On 64 bit arches, must check mask fits in table->mask (u32), * and on 32bit arches, must check * RPS_DEV_FLOW_TABLE_SIZE(mask + 1) doesn't overflow. */ #if BITS_PER_LONG > 32 if (mask > (unsigned long)(u32)mask) return -EINVAL; #else if (mask > (ULONG_MAX - RPS_DEV_FLOW_TABLE_SIZE(1)) / sizeof(struct rps_dev_flow)) { /* Enforce a limit to prevent overflow */ return -EINVAL; } #endif table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(mask + 1)); if (!table) return -ENOMEM; table->mask = mask; for (count = 0; count <= mask; count++) table->flows[count].cpu = RPS_NO_CPU; } else { table = NULL; } spin_lock(&rps_dev_flow_lock); old_table = rcu_dereference_protected(queue->rps_flow_table, lockdep_is_held(&rps_dev_flow_lock)); rcu_assign_pointer(queue->rps_flow_table, table); spin_unlock(&rps_dev_flow_lock); if (old_table) call_rcu(&old_table->rcu, rps_dev_flow_table_release); return len; } static struct rx_queue_attribute rps_cpus_attribute __ro_after_init = __ATTR(rps_cpus, 0644, show_rps_map, store_rps_map); static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute __ro_after_init = __ATTR(rps_flow_cnt, 0644, show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); #endif /* CONFIG_RPS */ static struct attribute *rx_queue_default_attrs[] __ro_after_init = { #ifdef CONFIG_RPS &rps_cpus_attribute.attr, &rps_dev_flow_table_cnt_attribute.attr, #endif NULL }; ATTRIBUTE_GROUPS(rx_queue_default); static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); #ifdef CONFIG_RPS struct rps_map *map; struct rps_dev_flow_table *flow_table; map = rcu_dereference_protected(queue->rps_map, 1); if (map) { RCU_INIT_POINTER(queue->rps_map, NULL); kfree_rcu(map, rcu); } flow_table = rcu_dereference_protected(queue->rps_flow_table, 1); if (flow_table) { RCU_INIT_POINTER(queue->rps_flow_table, NULL); call_rcu(&flow_table->rcu, rps_dev_flow_table_release); } #endif memset(kobj, 0, sizeof(*kobj)); dev_put(queue->dev); } static const void *rx_queue_namespace(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); struct device *dev = &queue->dev->dev; const void *ns = NULL; if (dev->class && dev->class->ns_type) ns = dev->class->namespace(dev); return ns; } static void rx_queue_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) { const struct net *net = rx_queue_namespace(kobj); net_ns_get_ownership(net, uid, gid); } static struct kobj_type rx_queue_ktype __ro_after_init = { .sysfs_ops = &rx_queue_sysfs_ops, .release = rx_queue_release, .default_groups = rx_queue_default_groups, .namespace = rx_queue_namespace, .get_ownership = rx_queue_get_ownership, }; static int rx_queue_add_kobject(struct net_device *dev, int index) { struct netdev_rx_queue *queue = dev->_rx + index; struct kobject *kobj = &queue->kobj; int error = 0; /* Kobject_put later will trigger rx_queue_release call which * decreases dev refcount: Take that reference here */ dev_hold(queue->dev); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) goto err; if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) goto err; } kobject_uevent(kobj, KOBJ_ADD); return error; err: kobject_put(kobj); return error; } static int rx_queue_change_owner(struct net_device *dev, int index, kuid_t kuid, kgid_t kgid) { struct netdev_rx_queue *queue = dev->_rx + index; struct kobject *kobj = &queue->kobj; int error; error = sysfs_change_owner(kobj, kuid, kgid); if (error) return error; if (dev->sysfs_rx_queue_group) error = sysfs_group_change_owner( kobj, dev->sysfs_rx_queue_group, kuid, kgid); return error; } #endif /* CONFIG_SYSFS */ int net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) { #ifdef CONFIG_SYSFS int i; int error = 0; #ifndef CONFIG_RPS if (!dev->sysfs_rx_queue_group) return 0; #endif for (i = old_num; i < new_num; i++) { error = rx_queue_add_kobject(dev, i); if (error) { new_num = old_num; break; } } while (--i >= new_num) { struct kobject *kobj = &dev->_rx[i].kobj; if (!refcount_read(&dev_net(dev)->ns.count)) kobj->uevent_suppress = 1; if (dev->sysfs_rx_queue_group) sysfs_remove_group(kobj, dev->sysfs_rx_queue_group); kobject_put(kobj); } return error; #else return 0; #endif } static int net_rx_queue_change_owner(struct net_device *dev, int num, kuid_t kuid, kgid_t kgid) { #ifdef CONFIG_SYSFS int error = 0; int i; #ifndef CONFIG_RPS if (!dev->sysfs_rx_queue_group) return 0; #endif for (i = 0; i < num; i++) { error = rx_queue_change_owner(dev, i, kuid, kgid); if (error) break; } return error; #else return 0; #endif } #ifdef CONFIG_SYSFS /* * netdev_queue sysfs structures and functions. */ struct netdev_queue_attribute { struct attribute attr; ssize_t (*show)(struct netdev_queue *queue, char *buf); ssize_t (*store)(struct netdev_queue *queue, const char *buf, size_t len); }; #define to_netdev_queue_attr(_attr) \ container_of(_attr, struct netdev_queue_attribute, attr) #define to_netdev_queue(obj) container_of(obj, struct netdev_queue, kobj) static ssize_t netdev_queue_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { const struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); struct netdev_queue *queue = to_netdev_queue(kobj); if (!attribute->show) return -EIO; return attribute->show(queue, buf); } static ssize_t netdev_queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { const struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); struct netdev_queue *queue = to_netdev_queue(kobj); if (!attribute->store) return -EIO; return attribute->store(queue, buf, count); } static const struct sysfs_ops netdev_queue_sysfs_ops = { .show = netdev_queue_attr_show, .store = netdev_queue_attr_store, }; static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf) { unsigned long trans_timeout; spin_lock_irq(&queue->_xmit_lock); trans_timeout = queue->trans_timeout; spin_unlock_irq(&queue->_xmit_lock); return sprintf(buf, fmt_ulong, trans_timeout); } static unsigned int get_netdev_queue_index(struct netdev_queue *queue) { struct net_device *dev = queue->dev; unsigned int i; i = queue - dev->_tx; BUG_ON(i >= dev->num_tx_queues); return i; } static ssize_t traffic_class_show(struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; int num_tc, tc; int index; if (!netif_is_multiqueue(dev)) return -ENOENT; if (!rtnl_trylock()) return restart_syscall(); index = get_netdev_queue_index(queue); /* If queue belongs to subordinate dev use its TC mapping */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; num_tc = dev->num_tc; tc = netdev_txq_to_tc(dev, index); rtnl_unlock(); if (tc < 0) return -EINVAL; /* We can report the traffic class one of two ways: * Subordinate device traffic classes are reported with the traffic * class first, and then the subordinate class so for example TC0 on * subordinate device 2 will be reported as "0-2". If the queue * belongs to the root device it will be reported with just the * traffic class, so just "0" for TC 0 for example. */ return num_tc < 0 ? sprintf(buf, "%d%d\n", tc, num_tc) : sprintf(buf, "%d\n", tc); } #ifdef CONFIG_XPS static ssize_t tx_maxrate_show(struct netdev_queue *queue, char *buf) { return sprintf(buf, "%lu\n", queue->tx_maxrate); } static ssize_t tx_maxrate_store(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; int err, index = get_netdev_queue_index(queue); u32 rate = 0; if (!capable(CAP_NET_ADMIN)) return -EPERM; /* The check is also done later; this helps returning early without * hitting the trylock/restart below. */ if (!dev->netdev_ops->ndo_set_tx_maxrate) return -EOPNOTSUPP; err = kstrtou32(buf, 10, &rate); if (err < 0) return err; if (!rtnl_trylock()) return restart_syscall(); err = -EOPNOTSUPP; if (dev->netdev_ops->ndo_set_tx_maxrate) err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate); rtnl_unlock(); if (!err) { queue->tx_maxrate = rate; return len; } return err; } static struct netdev_queue_attribute queue_tx_maxrate __ro_after_init = __ATTR_RW(tx_maxrate); #endif static struct netdev_queue_attribute queue_trans_timeout __ro_after_init = __ATTR_RO(tx_timeout); static struct netdev_queue_attribute queue_traffic_class __ro_after_init = __ATTR_RO(traffic_class); #ifdef CONFIG_BQL /* * Byte queue limits sysfs structures and functions. */ static ssize_t bql_show(char *buf, unsigned int value) { return sprintf(buf, "%u\n", value); } static ssize_t bql_set(const char *buf, const size_t count, unsigned int *pvalue) { unsigned int value; int err; if (!strcmp(buf, "max") || !strcmp(buf, "max\n")) { value = DQL_MAX_LIMIT; } else { err = kstrtouint(buf, 10, &value); if (err < 0) return err; if (value > DQL_MAX_LIMIT) return -EINVAL; } *pvalue = value; return count; } static ssize_t bql_show_hold_time(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sprintf(buf, "%u\n", jiffies_to_msecs(dql->slack_hold_time)); } static ssize_t bql_set_hold_time(struct netdev_queue *queue, const char *buf, size_t len) { struct dql *dql = &queue->dql; unsigned int value; int err; err = kstrtouint(buf, 10, &value); if (err < 0) return err; dql->slack_hold_time = msecs_to_jiffies(value); return len; } static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init = __ATTR(hold_time, 0644, bql_show_hold_time, bql_set_hold_time); static ssize_t bql_show_inflight(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sprintf(buf, "%u\n", dql->num_queued - dql->num_completed); } static struct netdev_queue_attribute bql_inflight_attribute __ro_after_init = __ATTR(inflight, 0444, bql_show_inflight, NULL); #define BQL_ATTR(NAME, FIELD) \ static ssize_t bql_show_ ## NAME(struct netdev_queue *queue, \ char *buf) \ { \ return bql_show(buf, queue->dql.FIELD); \ } \ \ static ssize_t bql_set_ ## NAME(struct netdev_queue *queue, \ const char *buf, size_t len) \ { \ return bql_set(buf, len, &queue->dql.FIELD); \ } \ \ static struct netdev_queue_attribute bql_ ## NAME ## _attribute __ro_after_init \ = __ATTR(NAME, 0644, \ bql_show_ ## NAME, bql_set_ ## NAME) BQL_ATTR(limit, limit); BQL_ATTR(limit_max, max_limit); BQL_ATTR(limit_min, min_limit); static struct attribute *dql_attrs[] __ro_after_init = { &bql_limit_attribute.attr, &bql_limit_max_attribute.attr, &bql_limit_min_attribute.attr, &bql_hold_time_attribute.attr, &bql_inflight_attribute.attr, NULL }; static const struct attribute_group dql_group = { .name = "byte_queue_limits", .attrs = dql_attrs, }; #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS static ssize_t xps_queue_show(struct net_device *dev, unsigned int index, int tc, char *buf, enum xps_map_type type) { struct xps_dev_maps *dev_maps; unsigned long *mask; unsigned int nr_ids; int j, len; rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_maps[type]); /* Default to nr_cpu_ids/dev->num_rx_queues and do not just return 0 * when dev_maps hasn't been allocated yet, to be backward compatible. */ nr_ids = dev_maps ? dev_maps->nr_ids : (type == XPS_CPUS ? nr_cpu_ids : dev->num_rx_queues); mask = bitmap_zalloc(nr_ids, GFP_NOWAIT); if (!mask) { rcu_read_unlock(); return -ENOMEM; } if (!dev_maps || tc >= dev_maps->num_tc) goto out_no_maps; for (j = 0; j < nr_ids; j++) { int i, tci = j * dev_maps->num_tc + tc; struct xps_map *map; map = rcu_dereference(dev_maps->attr_map[tci]); if (!map) continue; for (i = map->len; i--;) { if (map->queues[i] == index) { set_bit(j, mask); break; } } } out_no_maps: rcu_read_unlock(); len = bitmap_print_to_pagebuf(false, buf, mask, nr_ids); bitmap_free(mask); return len < PAGE_SIZE ? len : -EINVAL; } static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; int len, tc; if (!netif_is_multiqueue(dev)) return -ENOENT; index = get_netdev_queue_index(queue); if (!rtnl_trylock()) return restart_syscall(); /* If queue belongs to subordinate dev use its map */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; tc = netdev_txq_to_tc(dev, index); if (tc < 0) { rtnl_unlock(); return -EINVAL; } /* Make sure the subordinate device can't be freed */ get_device(&dev->dev); rtnl_unlock(); len = xps_queue_show(dev, index, tc, buf, XPS_CPUS); put_device(&dev->dev); return len; } static ssize_t xps_cpus_store(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; unsigned int index; cpumask_var_t mask; int err; if (!netif_is_multiqueue(dev)) return -ENOENT; if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; index = get_netdev_queue_index(queue); err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); if (err) { free_cpumask_var(mask); return err; } if (!rtnl_trylock()) { free_cpumask_var(mask); return restart_syscall(); } err = netif_set_xps_queue(dev, mask, index); rtnl_unlock(); free_cpumask_var(mask); return err ? : len; } static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init = __ATTR_RW(xps_cpus); static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; int tc; index = get_netdev_queue_index(queue); if (!rtnl_trylock()) return restart_syscall(); tc = netdev_txq_to_tc(dev, index); rtnl_unlock(); if (tc < 0) return -EINVAL; return xps_queue_show(dev, index, tc, buf, XPS_RXQS); } static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; struct net *net = dev_net(dev); unsigned long *mask; unsigned int index; int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; mask = bitmap_zalloc(dev->num_rx_queues, GFP_KERNEL); if (!mask) return -ENOMEM; index = get_netdev_queue_index(queue); err = bitmap_parse(buf, len, mask, dev->num_rx_queues); if (err) { bitmap_free(mask); return err; } if (!rtnl_trylock()) { bitmap_free(mask); return restart_syscall(); } cpus_read_lock(); err = __netif_set_xps_queue(dev, mask, index, XPS_RXQS); cpus_read_unlock(); rtnl_unlock(); bitmap_free(mask); return err ? : len; } static struct netdev_queue_attribute xps_rxqs_attribute __ro_after_init = __ATTR_RW(xps_rxqs); #endif /* CONFIG_XPS */ static struct attribute *netdev_queue_default_attrs[] __ro_after_init = { &queue_trans_timeout.attr, &queue_traffic_class.attr, #ifdef CONFIG_XPS &xps_cpus_attribute.attr, &xps_rxqs_attribute.attr, &queue_tx_maxrate.attr, #endif NULL }; ATTRIBUTE_GROUPS(netdev_queue_default); static void netdev_queue_release(struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); memset(kobj, 0, sizeof(*kobj)); dev_put(queue->dev); } static const void *netdev_queue_namespace(struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); struct device *dev = &queue->dev->dev; const void *ns = NULL; if (dev->class && dev->class->ns_type) ns = dev->class->namespace(dev); return ns; } static void netdev_queue_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) { const struct net *net = netdev_queue_namespace(kobj); net_ns_get_ownership(net, uid, gid); } static struct kobj_type netdev_queue_ktype __ro_after_init = { .sysfs_ops = &netdev_queue_sysfs_ops, .release = netdev_queue_release, .default_groups = netdev_queue_default_groups, .namespace = netdev_queue_namespace, .get_ownership = netdev_queue_get_ownership, }; static int netdev_queue_add_kobject(struct net_device *dev, int index) { struct netdev_queue *queue = dev->_tx + index; struct kobject *kobj = &queue->kobj; int error = 0; /* Kobject_put later will trigger netdev_queue_release call * which decreases dev refcount: Take that reference here */ dev_hold(queue->dev); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, "tx-%u", index); if (error) goto err; #ifdef CONFIG_BQL error = sysfs_create_group(kobj, &dql_group); if (error) goto err; #endif kobject_uevent(kobj, KOBJ_ADD); return 0; err: kobject_put(kobj); return error; } static int tx_queue_change_owner(struct net_device *ndev, int index, kuid_t kuid, kgid_t kgid) { struct netdev_queue *queue = ndev->_tx + index; struct kobject *kobj = &queue->kobj; int error; error = sysfs_change_owner(kobj, kuid, kgid); if (error) return error; #ifdef CONFIG_BQL error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid); #endif return error; } #endif /* CONFIG_SYSFS */ int netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) { #ifdef CONFIG_SYSFS int i; int error = 0; for (i = old_num; i < new_num; i++) { error = netdev_queue_add_kobject(dev, i); if (error) { new_num = old_num; break; } } while (--i >= new_num) { struct netdev_queue *queue = dev->_tx + i; if (!refcount_read(&dev_net(dev)->ns.count)) queue->kobj.uevent_suppress = 1; #ifdef CONFIG_BQL sysfs_remove_group(&queue->kobj, &dql_group); #endif kobject_put(&queue->kobj); } return error; #else return 0; #endif /* CONFIG_SYSFS */ } static int net_tx_queue_change_owner(struct net_device *dev, int num, kuid_t kuid, kgid_t kgid) { #ifdef CONFIG_SYSFS int error = 0; int i; for (i = 0; i < num; i++) { error = tx_queue_change_owner(dev, i, kuid, kgid); if (error) break; } return error; #else return 0; #endif /* CONFIG_SYSFS */ } static int register_queue_kobjects(struct net_device *dev) { int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS dev->queues_kset = kset_create_and_add("queues", NULL, &dev->dev.kobj); if (!dev->queues_kset) return -ENOMEM; real_rx = dev->real_num_rx_queues; #endif real_tx = dev->real_num_tx_queues; error = net_rx_queue_update_kobjects(dev, 0, real_rx); if (error) goto error; rxq = real_rx; error = netdev_queue_update_kobjects(dev, 0, real_tx); if (error) goto error; txq = real_tx; return 0; error: netdev_queue_update_kobjects(dev, txq, 0); net_rx_queue_update_kobjects(dev, rxq, 0); #ifdef CONFIG_SYSFS kset_unregister(dev->queues_kset); #endif return error; } static int queue_change_owner(struct net_device *ndev, kuid_t kuid, kgid_t kgid) { int error = 0, real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS if (ndev->queues_kset) { error = sysfs_change_owner(&ndev->queues_kset->kobj, kuid, kgid); if (error) return error; } real_rx = ndev->real_num_rx_queues; #endif real_tx = ndev->real_num_tx_queues; error = net_rx_queue_change_owner(ndev, real_rx, kuid, kgid); if (error) return error; error = net_tx_queue_change_owner(ndev, real_tx, kuid, kgid); if (error) return error; return 0; } static void remove_queue_kobjects(struct net_device *dev) { int real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS real_rx = dev->real_num_rx_queues; #endif real_tx = dev->real_num_tx_queues; net_rx_queue_update_kobjects(dev, real_rx, 0); netdev_queue_update_kobjects(dev, real_tx, 0); dev->real_num_rx_queues = 0; dev->real_num_tx_queues = 0; #ifdef CONFIG_SYSFS kset_unregister(dev->queues_kset); #endif } static bool net_current_may_mount(void) { struct net *net = current->nsproxy->net_ns; return ns_capable(net->user_ns, CAP_SYS_ADMIN); } static void *net_grab_current_ns(void) { struct net *ns = current->nsproxy->net_ns; #ifdef CONFIG_NET_NS if (ns) refcount_inc(&ns->passive); #endif return ns; } static const void *net_initial_ns(void) { return &init_net; } static const void *net_netlink_ns(struct sock *sk) { return sock_net(sk); } const struct kobj_ns_type_operations net_ns_type_operations = { .type = KOBJ_NS_TYPE_NET, .current_may_mount = net_current_may_mount, .grab_current_ns = net_grab_current_ns, .netlink_ns = net_netlink_ns, .initial_ns = net_initial_ns, .drop_ns = net_drop_ns, }; EXPORT_SYMBOL_GPL(net_ns_type_operations); static int netdev_uevent(struct device *d, struct kobj_uevent_env *env) { struct net_device *dev = to_net_dev(d); int retval; /* pass interface to uevent. */ retval = add_uevent_var(env, "INTERFACE=%s", dev->name); if (retval) goto exit; /* pass ifindex to uevent. * ifindex is useful as it won't change (interface name may change) * and is what RtNetlink uses natively. */ retval = add_uevent_var(env, "IFINDEX=%d", dev->ifindex); exit: return retval; } /* * netdev_release -- destroy and free a dead device. * Called when last reference to device kobject is gone. */ static void netdev_release(struct device *d) { struct net_device *dev = to_net_dev(d); BUG_ON(dev->reg_state != NETREG_RELEASED); /* no need to wait for rcu grace period: * device is dead and about to be freed. */ kfree(rcu_access_pointer(dev->ifalias)); netdev_freemem(dev); } static const void *net_namespace(struct device *d) { struct net_device *dev = to_net_dev(d); return dev_net(dev); } static void net_get_ownership(struct device *d, kuid_t *uid, kgid_t *gid) { struct net_device *dev = to_net_dev(d); const struct net *net = dev_net(dev); net_ns_get_ownership(net, uid, gid); } static struct class net_class __ro_after_init = { .name = "net", .dev_release = netdev_release, .dev_groups = net_class_groups, .dev_uevent = netdev_uevent, .ns_type = &net_ns_type_operations, .namespace = net_namespace, .get_ownership = net_get_ownership, }; #ifdef CONFIG_OF static int of_dev_node_match(struct device *dev, const void *data) { for (; dev; dev = dev->parent) { if (dev->of_node == data) return 1; } return 0; } /* * of_find_net_device_by_node - lookup the net device for the device node * @np: OF device node * * Looks up the net_device structure corresponding with the device node. * If successful, returns a pointer to the net_device with the embedded * struct device refcount incremented by one, or NULL on failure. The * refcount must be dropped when done with the net_device. */ struct net_device *of_find_net_device_by_node(struct device_node *np) { struct device *dev; dev = class_find_device(&net_class, NULL, np, of_dev_node_match); if (!dev) return NULL; return to_net_dev(dev); } EXPORT_SYMBOL(of_find_net_device_by_node); #endif /* Delete sysfs entries but hold kobject reference until after all * netdev references are gone. */ void netdev_unregister_kobject(struct net_device *ndev) { struct device *dev = &ndev->dev; if (!refcount_read(&dev_net(ndev)->ns.count)) dev_set_uevent_suppress(dev, 1); kobject_get(&dev->kobj); remove_queue_kobjects(ndev); pm_runtime_set_memalloc_noio(dev, false); device_del(dev); } /* Create sysfs entries for network device. */ int netdev_register_kobject(struct net_device *ndev) { struct device *dev = &ndev->dev; const struct attribute_group **groups = ndev->sysfs_groups; int error = 0; device_initialize(dev); dev->class = &net_class; dev->platform_data = ndev; dev->groups = groups; dev_set_name(dev, "%s", ndev->name); #ifdef CONFIG_SYSFS /* Allow for a device specific group */ if (*groups) groups++; *groups++ = &netstat_group; #if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211) if (ndev->ieee80211_ptr) *groups++ = &wireless_group; #if IS_ENABLED(CONFIG_WIRELESS_EXT) else if (ndev->wireless_handlers) *groups++ = &wireless_group; #endif #endif #endif /* CONFIG_SYSFS */ error = device_add(dev); if (error) return error; error = register_queue_kobjects(ndev); if (error) { device_del(dev); return error; } pm_runtime_set_memalloc_noio(dev, true); return error; } /* Change owner for sysfs entries when moving network devices across network * namespaces owned by different user namespaces. */ int netdev_change_owner(struct net_device *ndev, const struct net *net_old, const struct net *net_new) { kuid_t old_uid = GLOBAL_ROOT_UID, new_uid = GLOBAL_ROOT_UID; kgid_t old_gid = GLOBAL_ROOT_GID, new_gid = GLOBAL_ROOT_GID; struct device *dev = &ndev->dev; int error; net_ns_get_ownership(net_old, &old_uid, &old_gid); net_ns_get_ownership(net_new, &new_uid, &new_gid); /* The network namespace was changed but the owning user namespace is * identical so there's no need to change the owner of sysfs entries. */ if (uid_eq(old_uid, new_uid) && gid_eq(old_gid, new_gid)) return 0; error = device_change_owner(dev, new_uid, new_gid); if (error) return error; error = queue_change_owner(ndev, new_uid, new_gid); if (error) return error; return 0; } int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns) { return class_create_file_ns(&net_class, class_attr, ns); } EXPORT_SYMBOL(netdev_class_create_file_ns); void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const void *ns) { class_remove_file_ns(&net_class, class_attr, ns); } EXPORT_SYMBOL(netdev_class_remove_file_ns); int __init netdev_kobject_init(void) { kobj_ns_type_register(&net_ns_type_operations); return class_register(&net_class); } |
| 520 1422 1884 1353 1354 1422 1784 2412 1027 1027 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMU_NOTIFIER_H #define _LINUX_MMU_NOTIFIER_H #include <linux/list.h> #include <linux/spinlock.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/percpu-rwsem.h> #include <linux/slab.h> #include <linux/srcu.h> #include <linux/interval_tree.h> #include <linux/android_kabi.h> struct mmu_notifier_subscriptions; struct mmu_notifier; struct mmu_notifier_range; struct mmu_interval_notifier; /** * enum mmu_notifier_event - reason for the mmu notifier callback * @MMU_NOTIFY_UNMAP: either munmap() that unmap the range or a mremap() that * move the range * * @MMU_NOTIFY_CLEAR: clear page table entry (many reasons for this like * madvise() or replacing a page by another one, ...). * * @MMU_NOTIFY_PROTECTION_VMA: update is due to protection change for the range * ie using the vma access permission (vm_page_prot) to update the whole range * is enough no need to inspect changes to the CPU page table (mprotect() * syscall) * * @MMU_NOTIFY_PROTECTION_PAGE: update is due to change in read/write flag for * pages in the range so to mirror those changes the user must inspect the CPU * page table (from the end callback). * * @MMU_NOTIFY_SOFT_DIRTY: soft dirty accounting (still same page and same * access flags). User should soft dirty the page in the end callback to make * sure that anyone relying on soft dirtiness catch pages that might be written * through non CPU mappings. * * @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal * that the mm refcount is zero and the range is no longer accessible. * * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal * a device driver to possibly ignore the invalidation if the * owner field matches the driver's device private pgmap owner. * * @MMU_NOTIFY_EXCLUSIVE: to signal a device driver that the device will no * longer have exclusive access to the page. When sent during creation of an * exclusive range the owner will be initialised to the value provided by the * caller of make_device_exclusive_range(), otherwise the owner will be NULL. */ enum mmu_notifier_event { MMU_NOTIFY_UNMAP = 0, MMU_NOTIFY_CLEAR, MMU_NOTIFY_PROTECTION_VMA, MMU_NOTIFY_PROTECTION_PAGE, MMU_NOTIFY_SOFT_DIRTY, MMU_NOTIFY_RELEASE, MMU_NOTIFY_MIGRATE, MMU_NOTIFY_EXCLUSIVE, }; #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0) struct mmu_notifier_ops { /* * Called either by mmu_notifier_unregister or when the mm is * being destroyed by exit_mmap, always before all pages are * freed. This can run concurrently with other mmu notifier * methods (the ones invoked outside the mm context) and it * should tear down all secondary mmu mappings and freeze the * secondary mmu. If this method isn't implemented you've to * be sure that nothing could possibly write to the pages * through the secondary mmu by the time the last thread with * tsk->mm == mm exits. * * As side note: the pages freed after ->release returns could * be immediately reallocated by the gart at an alias physical * address with a different cache model, so if ->release isn't * implemented because all _software_ driven memory accesses * through the secondary mmu are terminated by the time the * last thread of this mm quits, you've also to be sure that * speculative _hardware_ operations can't allocate dirty * cachelines in the cpu that could not be snooped and made * coherent with the other read and write operations happening * through the gart alias address, so leading to memory * corruption. */ void (*release)(struct mmu_notifier *subscription, struct mm_struct *mm); /* * clear_flush_young is called after the VM is * test-and-clearing the young/accessed bitflag in the * pte. This way the VM will provide proper aging to the * accesses to the page through the secondary MMUs and not * only to the ones through the Linux pte. * Start-end is necessary in case the secondary MMU is mapping the page * at a smaller granularity than the primary MMU. */ int (*clear_flush_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * clear_young is a lightweight version of clear_flush_young. Like the * latter, it is supposed to test-and-clear the young/accessed bitflag * in the secondary pte, but it may omit flushing the secondary tlb. */ int (*clear_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * test_young is called to check the young/accessed bitflag in * the secondary pte. This is used to know if the page is * frequently used without actually clearing the flag or tearing * down the secondary mapping on the page. */ int (*test_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long address); /* * change_pte is called in cases that pte mapping to page is changed: * for example, when ksm remaps pte to point to a new shared page. */ void (*change_pte)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long address, pte_t pte); /* * invalidate_range_start() and invalidate_range_end() must be * paired and are called only when the mmap_lock and/or the * locks protecting the reverse maps are held. If the subsystem * can't guarantee that no additional references are taken to * the pages in the range, it has to implement the * invalidate_range() notifier to remove any references taken * after invalidate_range_start(). * * Invalidation of multiple concurrent ranges may be * optionally permitted by the driver. Either way the * establishment of sptes is forbidden in the range passed to * invalidate_range_begin/end for the whole duration of the * invalidate_range_begin/end critical section. * * invalidate_range_start() is called when all pages in the * range are still mapped and have at least a refcount of one. * * invalidate_range_end() is called when all pages in the * range have been unmapped and the pages have been freed by * the VM. * * The VM will remove the page table entries and potentially * the page between invalidate_range_start() and * invalidate_range_end(). If the page must not be freed * because of pending I/O or other circumstances then the * invalidate_range_start() callback (or the initial mapping * by the driver) must make sure that the refcount is kept * elevated. * * If the driver increases the refcount when the pages are * initially mapped into an address space then either * invalidate_range_start() or invalidate_range_end() may * decrease the refcount. If the refcount is decreased on * invalidate_range_start() then the VM can free pages as page * table entries are removed. If the refcount is only * dropped on invalidate_range_end() then the driver itself * will drop the last refcount but it must take care to flush * any secondary tlb before doing the final free on the * page. Pages will no longer be referenced by the linux * address space but may still be referenced by sptes until * the last refcount is dropped. * * If blockable argument is set to false then the callback cannot * sleep and has to return with -EAGAIN if sleeping would be required. * 0 should be returned otherwise. Please note that notifiers that can * fail invalidate_range_start are not allowed to implement * invalidate_range_end, as there is no mechanism for informing the * notifier that its start failed. */ int (*invalidate_range_start)(struct mmu_notifier *subscription, const struct mmu_notifier_range *range); void (*invalidate_range_end)(struct mmu_notifier *subscription, const struct mmu_notifier_range *range); /* * invalidate_range() is either called between * invalidate_range_start() and invalidate_range_end() when the * VM has to free pages that where unmapped, but before the * pages are actually freed, or outside of _start()/_end() when * a (remote) TLB is necessary. * * If invalidate_range() is used to manage a non-CPU TLB with * shared page-tables, it not necessary to implement the * invalidate_range_start()/end() notifiers, as * invalidate_range() already catches the points in time when an * external TLB range needs to be flushed. For more in depth * discussion on this see Documentation/vm/mmu_notifier.rst * * Note that this function might be called with just a sub-range * of what was passed to invalidate_range_start()/end(), if * called between those functions. */ void (*invalidate_range)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * These callbacks are used with the get/put interface to manage the * lifetime of the mmu_notifier memory. alloc_notifier() returns a new * notifier for use with the mm. * * free_notifier() is only called after the mmu_notifier has been * fully put, calls to any ops callback are prevented and no ops * callbacks are currently running. It is called from a SRCU callback * and cannot sleep. */ struct mmu_notifier *(*alloc_notifier)(struct mm_struct *mm); void (*free_notifier)(struct mmu_notifier *subscription); ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); }; /* * The notifier chains are protected by mmap_lock and/or the reverse map * semaphores. Notifier chains are only changed when all reverse maps and * the mmap_lock locks are taken. * * Therefore notifier chains can only be traversed when either * * 1. mmap_lock is held. * 2. One of the reverse map locks is held (i_mmap_rwsem or anon_vma->rwsem). * 3. No other concurrent thread can access the list (release) */ struct mmu_notifier { struct hlist_node hlist; const struct mmu_notifier_ops *ops; struct mm_struct *mm; struct rcu_head rcu; unsigned int users; ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); }; /** * struct mmu_interval_notifier_ops * @invalidate: Upon return the caller must stop using any SPTEs within this * range. This function can sleep. Return false only if sleeping * was required but mmu_notifier_range_blockable(range) is false. */ struct mmu_interval_notifier_ops { bool (*invalidate)(struct mmu_interval_notifier *interval_sub, const struct mmu_notifier_range *range, unsigned long cur_seq); }; struct mmu_interval_notifier { struct interval_tree_node interval_tree; const struct mmu_interval_notifier_ops *ops; struct mm_struct *mm; struct hlist_node deferred_item; unsigned long invalidate_seq; }; #ifdef CONFIG_MMU_NOTIFIER #ifdef CONFIG_LOCKDEP extern struct lockdep_map __mmu_notifier_invalidate_range_start_map; #endif struct mmu_notifier_range { struct vm_area_struct *vma; struct mm_struct *mm; unsigned long start; unsigned long end; unsigned flags; enum mmu_notifier_event event; void *owner; }; static inline int mm_has_notifiers(struct mm_struct *mm) { return unlikely(mm->notifier_subscriptions); } struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops, struct mm_struct *mm); static inline struct mmu_notifier * mmu_notifier_get(const struct mmu_notifier_ops *ops, struct mm_struct *mm) { struct mmu_notifier *ret; mmap_write_lock(mm); ret = mmu_notifier_get_locked(ops, mm); mmap_write_unlock(mm); return ret; } void mmu_notifier_put(struct mmu_notifier *subscription); void mmu_notifier_synchronize(void); extern int mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm); extern int __mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm); extern void mmu_notifier_unregister(struct mmu_notifier *subscription, struct mm_struct *mm); unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub); int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops); int mmu_interval_notifier_insert_locked( struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops); void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub); /** * mmu_interval_set_seq - Save the invalidation sequence * @interval_sub - The subscription passed to invalidate * @cur_seq - The cur_seq passed to the invalidate() callback * * This must be called unconditionally from the invalidate callback of a * struct mmu_interval_notifier_ops under the same lock that is used to call * mmu_interval_read_retry(). It updates the sequence number for later use by * mmu_interval_read_retry(). The provided cur_seq will always be odd. * * If the caller does not call mmu_interval_read_begin() or * mmu_interval_read_retry() then this call is not required. */ static inline void mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, unsigned long cur_seq) { WRITE_ONCE(interval_sub->invalidate_seq, cur_seq); } /** * mmu_interval_read_retry - End a read side critical section against a VA range * interval_sub: The subscription * seq: The return of the paired mmu_interval_read_begin() * * This MUST be called under a user provided lock that is also held * unconditionally by op->invalidate() when it calls mmu_interval_set_seq(). * * Each call should be paired with a single mmu_interval_read_begin() and * should be used to conclude the read side. * * Returns true if an invalidation collided with this critical section, and * the caller should retry. */ static inline bool mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub, unsigned long seq) { return interval_sub->invalidate_seq != seq; } /** * mmu_interval_check_retry - Test if a collision has occurred * interval_sub: The subscription * seq: The return of the matching mmu_interval_read_begin() * * This can be used in the critical section between mmu_interval_read_begin() * and mmu_interval_read_retry(). A return of true indicates an invalidation * has collided with this critical region and a future * mmu_interval_read_retry() will return true. * * False is not reliable and only suggests a collision may not have * occurred. It can be called many times and does not have to hold the user * provided lock. * * This call can be used as part of loops and other expensive operations to * expedite a retry. */ static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub, unsigned long seq) { /* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */ return READ_ONCE(interval_sub->invalidate_seq) != seq; } extern void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm); extern void __mmu_notifier_release(struct mm_struct *mm); extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end); extern int __mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end); extern int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); extern void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte); extern int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *r); extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r, bool only_end); extern void __mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end); extern bool mmu_notifier_range_update_to_read_only(const struct mmu_notifier_range *range); static inline bool mmu_notifier_range_blockable(const struct mmu_notifier_range *range) { return (range->flags & MMU_NOTIFIER_RANGE_BLOCKABLE); } static inline void mmu_notifier_release(struct mm_struct *mm) { if (mm_has_notifiers(mm)) __mmu_notifier_release(mm); } static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) return __mmu_notifier_clear_flush_young(mm, start, end); return 0; } static inline int mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) return __mmu_notifier_clear_young(mm, start, end); return 0; } static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { if (mm_has_notifiers(mm)) return __mmu_notifier_test_young(mm, address); return 0; } static inline void mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte) { if (mm_has_notifiers(mm)) __mmu_notifier_change_pte(mm, address, pte); } static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { might_sleep(); lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (mm_has_notifiers(range->mm)) { range->flags |= MMU_NOTIFIER_RANGE_BLOCKABLE; __mmu_notifier_invalidate_range_start(range); } lock_map_release(&__mmu_notifier_invalidate_range_start_map); } static inline int mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { int ret = 0; lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (mm_has_notifiers(range->mm)) { range->flags &= ~MMU_NOTIFIER_RANGE_BLOCKABLE; ret = __mmu_notifier_invalidate_range_start(range); } lock_map_release(&__mmu_notifier_invalidate_range_start_map); return ret; } static inline void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { if (mmu_notifier_range_blockable(range)) might_sleep(); if (mm_has_notifiers(range->mm)) __mmu_notifier_invalidate_range_end(range, false); } static inline void mmu_notifier_invalidate_range_only_end(struct mmu_notifier_range *range) { if (mm_has_notifiers(range->mm)) __mmu_notifier_invalidate_range_end(range, true); } static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) __mmu_notifier_invalidate_range(mm, start, end); } static inline bool mmu_notifier_subscriptions_init(struct mm_struct *mm) { #ifdef CONFIG_SPECULATIVE_PAGE_FAULT mm->mmu_notifier_lock = kzalloc(sizeof(struct percpu_rw_semaphore), GFP_KERNEL); if (!mm->mmu_notifier_lock) return false; if (percpu_init_rwsem(mm->mmu_notifier_lock)) { kfree(mm->mmu_notifier_lock); return false; } #endif mm->notifier_subscriptions = NULL; return true; } static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { if (mm_has_notifiers(mm)) __mmu_notifier_subscriptions_destroy(mm); #ifdef CONFIG_SPECULATIVE_PAGE_FAULT percpu_rwsem_async_destroy(mm->mmu_notifier_lock); #endif } static inline void mmu_notifier_range_init(struct mmu_notifier_range *range, enum mmu_notifier_event event, unsigned flags, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end) { range->vma = vma; range->event = event; range->mm = mm; range->start = start; range->end = end; range->flags = flags; } static inline void mmu_notifier_range_init_owner( struct mmu_notifier_range *range, enum mmu_notifier_event event, unsigned int flags, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end, void *owner) { mmu_notifier_range_init(range, event, flags, vma, mm, start, end); range->owner = owner; } #define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = ptep_clear_flush_young(___vma, ___address, __ptep); \ __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ ___address, \ ___address + \ PAGE_SIZE); \ __young; \ }) #define pmdp_clear_flush_young_notify(__vma, __address, __pmdp) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = pmdp_clear_flush_young(___vma, ___address, __pmdp); \ __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ ___address, \ ___address + \ PMD_SIZE); \ __young; \ }) #define ptep_clear_young_notify(__vma, __address, __ptep) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = ptep_test_and_clear_young(___vma, ___address, __ptep);\ __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ ___address + PAGE_SIZE); \ __young; \ }) #define pmdp_clear_young_notify(__vma, __address, __pmdp) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = pmdp_test_and_clear_young(___vma, ___address, __pmdp);\ __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ ___address + PMD_SIZE); \ __young; \ }) #define ptep_clear_flush_notify(__vma, __address, __ptep) \ ({ \ unsigned long ___addr = __address & PAGE_MASK; \ struct mm_struct *___mm = (__vma)->vm_mm; \ pte_t ___pte; \ \ ___pte = ptep_clear_flush(__vma, __address, __ptep); \ mmu_notifier_invalidate_range(___mm, ___addr, \ ___addr + PAGE_SIZE); \ \ ___pte; \ }) #define pmdp_huge_clear_flush_notify(__vma, __haddr, __pmd) \ ({ \ unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \ struct mm_struct *___mm = (__vma)->vm_mm; \ pmd_t ___pmd; \ \ ___pmd = pmdp_huge_clear_flush(__vma, __haddr, __pmd); \ mmu_notifier_invalidate_range(___mm, ___haddr, \ ___haddr + HPAGE_PMD_SIZE); \ \ ___pmd; \ }) #define pudp_huge_clear_flush_notify(__vma, __haddr, __pud) \ ({ \ unsigned long ___haddr = __haddr & HPAGE_PUD_MASK; \ struct mm_struct *___mm = (__vma)->vm_mm; \ pud_t ___pud; \ \ ___pud = pudp_huge_clear_flush(__vma, __haddr, __pud); \ mmu_notifier_invalidate_range(___mm, ___haddr, \ ___haddr + HPAGE_PUD_SIZE); \ \ ___pud; \ }) /* * set_pte_at_notify() sets the pte _after_ running the notifier. * This is safe to start by updating the secondary MMUs, because the primary MMU * pte invalidate must have already happened with a ptep_clear_flush() before * set_pte_at_notify() has been invoked. Updating the secondary MMUs first is * required when we change both the protection of the mapping from read-only to * read-write and the pfn (like during copy on write page faults). Otherwise the * old page would remain mapped readonly in the secondary MMUs after the new * page is already writable by some CPU through the primary MMU. */ #define set_pte_at_notify(__mm, __address, __ptep, __pte) \ ({ \ struct mm_struct *___mm = __mm; \ unsigned long ___address = __address; \ pte_t ___pte = __pte; \ \ mmu_notifier_change_pte(___mm, ___address, ___pte); \ set_pte_at(___mm, ___address, __ptep, ___pte); \ }) #else /* CONFIG_MMU_NOTIFIER */ struct mmu_notifier_range { unsigned long start; unsigned long end; }; static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range, unsigned long start, unsigned long end) { range->start = start; range->end = end; } #define mmu_notifier_range_init(range,event,flags,vma,mm,start,end) \ _mmu_notifier_range_init(range, start, end) #define mmu_notifier_range_init_owner(range, event, flags, vma, mm, start, \ end, owner) \ _mmu_notifier_range_init(range, start, end) static inline bool mmu_notifier_range_blockable(const struct mmu_notifier_range *range) { return true; } static inline int mm_has_notifiers(struct mm_struct *mm) { return 0; } static inline void mmu_notifier_release(struct mm_struct *mm) { } static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { return 0; } static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { return 0; } static inline void mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte) { } static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { } static inline int mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { return 0; } static inline void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { } static inline void mmu_notifier_invalidate_range_only_end(struct mmu_notifier_range *range) { } static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end) { } static inline bool mmu_notifier_subscriptions_init(struct mm_struct *mm) { return true; } static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { } #define mmu_notifier_range_update_to_read_only(r) false #define ptep_clear_flush_young_notify ptep_clear_flush_young #define pmdp_clear_flush_young_notify pmdp_clear_flush_young #define ptep_clear_young_notify ptep_test_and_clear_young #define pmdp_clear_young_notify pmdp_test_and_clear_young #define ptep_clear_flush_notify ptep_clear_flush #define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush #define pudp_huge_clear_flush_notify pudp_huge_clear_flush #define set_pte_at_notify set_pte_at static inline void mmu_notifier_synchronize(void) { } #endif /* CONFIG_MMU_NOTIFIER */ #if defined(CONFIG_MMU_NOTIFIER) && defined(CONFIG_SPECULATIVE_PAGE_FAULT) static inline bool mmu_notifier_trylock(struct mm_struct *mm) { return percpu_down_read_trylock(mm->mmu_notifier_lock); } static inline void mmu_notifier_unlock(struct mm_struct *mm) { percpu_up_read(mm->mmu_notifier_lock); } #else static inline bool mmu_notifier_trylock(struct mm_struct *mm) { return true; } static inline void mmu_notifier_unlock(struct mm_struct *mm) { } #endif #endif /* _LINUX_MMU_NOTIFIER_H */ |
| 2230 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 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(!READ_ONCE(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 */ |
| 14 16 175 1800 737 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Integer base 2 logarithm calculation * * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_LOG2_H #define _LINUX_LOG2_H #include <linux/types.h> #include <linux/bitops.h> /* * non-constant log of base 2 calculators * - the arch may override these in asm/bitops.h if they can be implemented * more efficiently than using fls() and fls64() * - the arch is not required to handle n==0 if implementing the fallback */ #ifndef CONFIG_ARCH_HAS_ILOG2_U32 static inline __attribute__((const)) int __ilog2_u32(u32 n) { return fls(n) - 1; } #endif #ifndef CONFIG_ARCH_HAS_ILOG2_U64 static inline __attribute__((const)) int __ilog2_u64(u64 n) { return fls64(n) - 1; } #endif /** * is_power_of_2() - check if a value is a power of two * @n: the value to check * * Determine whether some value is a power of two, where zero is * *not* considered a power of two. * Return: true if @n is a power of 2, otherwise false. */ static inline __attribute__((const)) bool is_power_of_2(unsigned long n) { return (n != 0 && ((n & (n - 1)) == 0)); } /** * __roundup_pow_of_two() - round up to nearest power of two * @n: value to round up */ static inline __attribute__((const)) unsigned long __roundup_pow_of_two(unsigned long n) { return 1UL << fls_long(n - 1); } /** * __rounddown_pow_of_two() - round down to nearest power of two * @n: value to round down */ static inline __attribute__((const)) unsigned long __rounddown_pow_of_two(unsigned long n) { return 1UL << (fls_long(n) - 1); } /** * const_ilog2 - log base 2 of 32-bit or a 64-bit constant unsigned value * @n: parameter * * Use this where sparse expects a true constant expression, e.g. for array * indices. */ #define const_ilog2(n) \ ( \ __builtin_constant_p(n) ? ( \ (n) < 2 ? 0 : \ (n) & (1ULL << 63) ? 63 : \ (n) & (1ULL << 62) ? 62 : \ (n) & (1ULL << 61) ? 61 : \ (n) & (1ULL << 60) ? 60 : \ (n) & (1ULL << 59) ? 59 : \ (n) & (1ULL << 58) ? 58 : \ (n) & (1ULL << 57) ? 57 : \ (n) & (1ULL << 56) ? 56 : \ (n) & (1ULL << 55) ? 55 : \ (n) & (1ULL << 54) ? 54 : \ (n) & (1ULL << 53) ? 53 : \ (n) & (1ULL << 52) ? 52 : \ (n) & (1ULL << 51) ? 51 : \ (n) & (1ULL << 50) ? 50 : \ (n) & (1ULL << 49) ? 49 : \ (n) & (1ULL << 48) ? 48 : \ (n) & (1ULL << 47) ? 47 : \ (n) & (1ULL << 46) ? 46 : \ (n) & (1ULL << 45) ? 45 : \ (n) & (1ULL << 44) ? 44 : \ (n) & (1ULL << 43) ? 43 : \ (n) & (1ULL << 42) ? 42 : \ (n) & (1ULL << 41) ? 41 : \ (n) & (1ULL << 40) ? 40 : \ (n) & (1ULL << 39) ? 39 : \ (n) & (1ULL << 38) ? 38 : \ (n) & (1ULL << 37) ? 37 : \ (n) & (1ULL << 36) ? 36 : \ (n) & (1ULL << 35) ? 35 : \ (n) & (1ULL << 34) ? 34 : \ (n) & (1ULL << 33) ? 33 : \ (n) & (1ULL << 32) ? 32 : \ (n) & (1ULL << 31) ? 31 : \ (n) & (1ULL << 30) ? 30 : \ (n) & (1ULL << 29) ? 29 : \ (n) & (1ULL << 28) ? 28 : \ (n) & (1ULL << 27) ? 27 : \ (n) & (1ULL << 26) ? 26 : \ (n) & (1ULL << 25) ? 25 : \ (n) & (1ULL << 24) ? 24 : \ (n) & (1ULL << 23) ? 23 : \ (n) & (1ULL << 22) ? 22 : \ (n) & (1ULL << 21) ? 21 : \ (n) & (1ULL << 20) ? 20 : \ (n) & (1ULL << 19) ? 19 : \ (n) & (1ULL << 18) ? 18 : \ (n) & (1ULL << 17) ? 17 : \ (n) & (1ULL << 16) ? 16 : \ (n) & (1ULL << 15) ? 15 : \ (n) & (1ULL << 14) ? 14 : \ (n) & (1ULL << 13) ? 13 : \ (n) & (1ULL << 12) ? 12 : \ (n) & (1ULL << 11) ? 11 : \ (n) & (1ULL << 10) ? 10 : \ (n) & (1ULL << 9) ? 9 : \ (n) & (1ULL << 8) ? 8 : \ (n) & (1ULL << 7) ? 7 : \ (n) & (1ULL << 6) ? 6 : \ (n) & (1ULL << 5) ? 5 : \ (n) & (1ULL << 4) ? 4 : \ (n) & (1ULL << 3) ? 3 : \ (n) & (1ULL << 2) ? 2 : \ 1) : \ -1) /** * ilog2 - log base 2 of 32-bit or a 64-bit unsigned value * @n: parameter * * constant-capable log of base 2 calculation * - this can be used to initialise global variables from constant data, hence * the massive ternary operator construction * * selects the appropriately-sized optimised version depending on sizeof(n) */ #define ilog2(n) \ ( \ __builtin_constant_p(n) ? \ ((n) < 2 ? 0 : \ 63 - __builtin_clzll(n)) : \ (sizeof(n) <= 4) ? \ __ilog2_u32(n) : \ __ilog2_u64(n) \ ) /** * roundup_pow_of_two - round the given value up to nearest power of two * @n: parameter * * round the given value up to the nearest power of two * - the result is undefined when n == 0 * - this can be used to initialise global variables from constant data */ #define roundup_pow_of_two(n) \ ( \ __builtin_constant_p(n) ? ( \ ((n) == 1) ? 1 : \ (1UL << (ilog2((n) - 1) + 1)) \ ) : \ __roundup_pow_of_two(n) \ ) /** * rounddown_pow_of_two - round the given value down to nearest power of two * @n: parameter * * round the given value down to the nearest power of two * - the result is undefined when n == 0 * - this can be used to initialise global variables from constant data */ #define rounddown_pow_of_two(n) \ ( \ __builtin_constant_p(n) ? ( \ (1UL << ilog2(n))) : \ __rounddown_pow_of_two(n) \ ) static inline __attribute_const__ int __order_base_2(unsigned long n) { return n > 1 ? ilog2(n - 1) + 1 : 0; } /** * order_base_2 - calculate the (rounded up) base 2 order of the argument * @n: parameter * * The first few values calculated by this routine: * ob2(0) = 0 * ob2(1) = 0 * ob2(2) = 1 * ob2(3) = 2 * ob2(4) = 2 * ob2(5) = 3 * ... and so on. */ #define order_base_2(n) \ ( \ __builtin_constant_p(n) ? ( \ ((n) == 0 || (n) == 1) ? 0 : \ ilog2((n) - 1) + 1) : \ __order_base_2(n) \ ) static inline __attribute__((const)) int __bits_per(unsigned long n) { if (n < 2) return 1; if (is_power_of_2(n)) return order_base_2(n) + 1; return order_base_2(n); } /** * bits_per - calculate the number of bits required for the argument * @n: parameter * * This is constant-capable and can be used for compile time * initializations, e.g bitfields. * * The first few values calculated by this routine: * bf(0) = 1 * bf(1) = 1 * bf(2) = 2 * bf(3) = 2 * bf(4) = 3 * ... and so on. */ #define bits_per(n) \ ( \ __builtin_constant_p(n) ? ( \ ((n) == 0 || (n) == 1) \ ? 1 : ilog2(n) + 1 \ ) : \ __bits_per(n) \ ) #endif /* _LINUX_LOG2_H */ |
| 73 70 70 13 1 6 1 5 2 2 3 4 2599 4 7 2 7 7 7 7 7 7 7 2 3 2 2 1 1 1 1 3 1 1 258 58 201 139 138 138 138 1 139 137 2 1 15 5 10 2 1 9 1 9 6 5 2 1 1 302 3 3 1 293 173 1 2 2 1 3 1 18 1 1 1 1 2 1 2 1 1 3 1 6 11 1 2 2 1 1 2 22 1 1 1 7 1 1 1 1 1 2 2 1 1 6 1 1 2 1 2 2 3 2 4 1 1 1 1 2 2 1 1 2 2 1 2 297 4904 2665 2507 4903 2592 3272 4900 4900 2593 263 2342 4898 2670 2508 4904 2595 2594 2594 2 2597 2593 2593 1696 934 2598 71 2590 2661 1769 932 2661 2658 2538 2662 4901 4903 2566 2568 2568 2474 2475 2476 2479 2473 755 755 73 73 138 2 136 136 135 136 87 41 6 39 2 2311 2310 2307 5 91 5 10 87 14 2292 443 183 183 1 183 20 38 515 516 451 451 239 383 79 78 1 698 622 87 741 704 90 90 742 321 321 321 2136 59 57 2 693 693 530 68 461 4898 3130 1876 2667 2505 4581 2795 1874 3071 3066 38 2809 3022 450 2898 190 3070 3069 74 74 3 7 135 128 17 111 128 128 127 2142 750 750 750 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Generic socket support routines. Memory allocators, socket lock/release * handler for protocols to use and generic option handler. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, <flla@stud.uni-sb.de> * Alan Cox, <A.Cox@swansea.ac.uk> * * Fixes: * Alan Cox : Numerous verify_area() problems * Alan Cox : Connecting on a connecting socket * now returns an error for tcp. * Alan Cox : sock->protocol is set correctly. * and is not sometimes left as 0. * Alan Cox : connect handles icmp errors on a * connect properly. Unfortunately there * is a restart syscall nasty there. I * can't match BSD without hacking the C * library. Ideas urgently sought! * Alan Cox : Disallow bind() to addresses that are * not ours - especially broadcast ones!! * Alan Cox : Socket 1024 _IS_ ok for users. (fencepost) * Alan Cox : sock_wfree/sock_rfree don't destroy sockets, * instead they leave that for the DESTROY timer. * Alan Cox : Clean up error flag in accept * Alan Cox : TCP ack handling is buggy, the DESTROY timer * was buggy. Put a remove_sock() in the handler * for memory when we hit 0. Also altered the timer * code. The ACK stuff can wait and needs major * TCP layer surgery. * Alan Cox : Fixed TCP ack bug, removed remove sock * and fixed timer/inet_bh race. * Alan Cox : Added zapped flag for TCP * Alan Cox : Move kfree_skb into skbuff.c and tidied up surplus code * Alan Cox : for new sk_buff allocations wmalloc/rmalloc now call alloc_skb * Alan Cox : kfree_s calls now are kfree_skbmem so we can track skb resources * Alan Cox : Supports socket option broadcast now as does udp. Packet and raw need fixing. * Alan Cox : Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so... * Rick Sladkey : Relaxed UDP rules for matching packets. * C.E.Hawkins : IFF_PROMISC/SIOCGHWADDR support * Pauline Middelink : identd support * Alan Cox : Fixed connect() taking signals I think. * Alan Cox : SO_LINGER supported * Alan Cox : Error reporting fixes * Anonymous : inet_create tidied up (sk->reuse setting) * Alan Cox : inet sockets don't set sk->type! * Alan Cox : Split socket option code * Alan Cox : Callbacks * Alan Cox : Nagle flag for Charles & Johannes stuff * Alex : Removed restriction on inet fioctl * Alan Cox : Splitting INET from NET core * Alan Cox : Fixed bogus SO_TYPE handling in getsockopt() * Adam Caldwell : Missing return in SO_DONTROUTE/SO_DEBUG code * Alan Cox : Split IP from generic code * Alan Cox : New kfree_skbmem() * Alan Cox : Make SO_DEBUG superuser only. * Alan Cox : Allow anyone to clear SO_DEBUG * (compatibility fix) * Alan Cox : Added optimistic memory grabbing for AF_UNIX throughput. * Alan Cox : Allocator for a socket is settable. * Alan Cox : SO_ERROR includes soft errors. * Alan Cox : Allow NULL arguments on some SO_ opts * Alan Cox : Generic socket allocation to make hooks * easier (suggested by Craig Metz). * Michael Pall : SO_ERROR returns positive errno again * Steve Whitehouse: Added default destructor to free * protocol private data. * Steve Whitehouse: Added various other default routines * common to several socket families. * Chris Evans : Call suser() check last on F_SETOWN * Jay Schulist : Added SO_ATTACH_FILTER and SO_DETACH_FILTER. * Andi Kleen : Add sock_kmalloc()/sock_kfree_s() * Andi Kleen : Fix write_space callback * Chris Evans : Security fixes - signedness again * Arnaldo C. Melo : cleanups, use skb_queue_purge * * To Fix: */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <asm/unaligned.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/errqueue.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/poll.h> #include <linux/tcp.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/user_namespace.h> #include <linux/static_key.h> #include <linux/memcontrol.h> #include <linux/prefetch.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <linux/netdevice.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.h> #include <linux/net_tstamp.h> #include <net/xfrm.h> #include <linux/ipsec.h> #include <net/cls_cgroup.h> #include <net/netprio_cgroup.h> #include <linux/sock_diag.h> #include <linux/filter.h> #include <net/sock_reuseport.h> #include <net/bpf_sk_storage.h> #include <trace/events/sock.h> #include <trace/hooks/sched.h> #include <trace/hooks/net.h> #include <net/tcp.h> #include <net/busy_poll.h> #include <linux/ethtool.h> static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); /** * sk_ns_capable - General socket capability test * @sk: Socket to use a capability on or through * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket had when the socket was * created and the current process has the capability @cap in the user * namespace @user_ns. */ bool sk_ns_capable(const struct sock *sk, struct user_namespace *user_ns, int cap) { return file_ns_capable(sk->sk_socket->file, user_ns, cap) && ns_capable(user_ns, cap); } EXPORT_SYMBOL(sk_ns_capable); /** * sk_capable - Socket global capability test * @sk: Socket to use a capability on or through * @cap: The global capability to use * * Test to see if the opener of the socket had when the socket was * created and the current process has the capability @cap in all user * namespaces. */ bool sk_capable(const struct sock *sk, int cap) { return sk_ns_capable(sk, &init_user_ns, cap); } EXPORT_SYMBOL(sk_capable); /** * sk_net_capable - Network namespace socket capability test * @sk: Socket to use a capability on or through * @cap: The capability to use * * Test to see if the opener of the socket had when the socket was created * and the current process has the capability @cap over the network namespace * the socket is a member of. */ bool sk_net_capable(const struct sock *sk, int cap) { return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); } EXPORT_SYMBOL(sk_net_capable); /* * Each address family might have different locking rules, so we have * one slock key per address family and separate keys for internal and * userspace sockets. */ static struct lock_class_key af_family_keys[AF_MAX]; static struct lock_class_key af_family_kern_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket * locks is fast): */ #define _sock_locks(x) \ x "AF_UNSPEC", x "AF_UNIX" , x "AF_INET" , \ x "AF_AX25" , x "AF_IPX" , x "AF_APPLETALK", \ x "AF_NETROM", x "AF_BRIDGE" , x "AF_ATMPVC" , \ x "AF_X25" , x "AF_INET6" , x "AF_ROSE" , \ x "AF_DECnet", x "AF_NETBEUI" , x "AF_SECURITY" , \ x "AF_KEY" , x "AF_NETLINK" , x "AF_PACKET" , \ x "AF_ASH" , x "AF_ECONET" , x "AF_ATMSVC" , \ x "AF_RDS" , x "AF_SNA" , x "AF_IRDA" , \ x "AF_PPPOX" , x "AF_WANPIPE" , x "AF_LLC" , \ x "27" , x "28" , x "AF_CAN" , \ x "AF_TIPC" , x "AF_BLUETOOTH", x "IUCV" , \ x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \ x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \ x "AF_MCTP" , \ x "AF_MAX" static const char *const af_family_key_strings[AF_MAX+1] = { _sock_locks("sk_lock-") }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { _sock_locks("slock-") }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { _sock_locks("clock-") }; static const char *const af_family_kern_key_strings[AF_MAX+1] = { _sock_locks("k-sk_lock-") }; static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = { _sock_locks("k-slock-") }; static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = { _sock_locks("k-clock-") }; static const char *const af_family_rlock_key_strings[AF_MAX+1] = { _sock_locks("rlock-") }; static const char *const af_family_wlock_key_strings[AF_MAX+1] = { _sock_locks("wlock-") }; static const char *const af_family_elock_key_strings[AF_MAX+1] = { _sock_locks("elock-") }; /* * sk_callback_lock and sk queues locking rules are per-address-family, * so split the lock classes by using a per-AF key: */ static struct lock_class_key af_callback_keys[AF_MAX]; static struct lock_class_key af_rlock_keys[AF_MAX]; static struct lock_class_key af_wlock_keys[AF_MAX]; static struct lock_class_key af_elock_keys[AF_MAX]; static struct lock_class_key af_kern_callback_keys[AF_MAX]; /* Run time adjustable parameters. */ __u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; EXPORT_SYMBOL(sysctl_wmem_max); __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; /* Maximal space eaten by iovec or ancillary data plus some space */ int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); int sysctl_tstamp_allow_data __read_mostly = 1; DEFINE_STATIC_KEY_FALSE(memalloc_socks_key); EXPORT_SYMBOL_GPL(memalloc_socks_key); /** * sk_set_memalloc - sets %SOCK_MEMALLOC * @sk: socket to set it on * * Set %SOCK_MEMALLOC on a socket for access to emergency reserves. * It's the responsibility of the admin to adjust min_free_kbytes * to meet the requirements */ void sk_set_memalloc(struct sock *sk) { sock_set_flag(sk, SOCK_MEMALLOC); sk->sk_allocation |= __GFP_MEMALLOC; static_branch_inc(&memalloc_socks_key); } EXPORT_SYMBOL_GPL(sk_set_memalloc); void sk_clear_memalloc(struct sock *sk) { sock_reset_flag(sk, SOCK_MEMALLOC); sk->sk_allocation &= ~__GFP_MEMALLOC; static_branch_dec(&memalloc_socks_key); /* * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward * progress of swapping. SOCK_MEMALLOC may be cleared while * it has rmem allocations due to the last swapfile being deactivated * but there is a risk that the socket is unusable due to exceeding * the rmem limits. Reclaim the reserves and obey rmem limits again. */ sk_mem_reclaim(sk); } EXPORT_SYMBOL_GPL(sk_clear_memalloc); int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { int ret; unsigned int noreclaim_flag; /* these should have been dropped before queueing */ BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); noreclaim_flag = memalloc_noreclaim_save(); ret = sk->sk_backlog_rcv(sk, skb); memalloc_noreclaim_restore(noreclaim_flag); return ret; } EXPORT_SYMBOL(__sk_backlog_rcv); void sk_error_report(struct sock *sk) { sk->sk_error_report(sk); switch (sk->sk_family) { case AF_INET: fallthrough; case AF_INET6: trace_inet_sk_error_report(sk); break; default: break; } } EXPORT_SYMBOL(sk_error_report); static int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; if (timeo == MAX_SCHEDULE_TIMEOUT) { tv.tv_sec = 0; tv.tv_usec = 0; } else { tv.tv_sec = timeo / HZ; tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ; } if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec }; *(struct old_timeval32 *)optval = tv32; return sizeof(tv32); } if (old_timeval) { struct __kernel_old_timeval old_tv; old_tv.tv_sec = tv.tv_sec; old_tv.tv_usec = tv.tv_usec; *(struct __kernel_old_timeval *)optval = old_tv; return sizeof(old_tv); } *(struct __kernel_sock_timeval *)optval = tv; return sizeof(tv); } static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, bool old_timeval) { struct __kernel_sock_timeval tv; if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; if (optlen < sizeof(tv32)) return -EINVAL; if (copy_from_sockptr(&tv32, optval, sizeof(tv32))) return -EFAULT; tv.tv_sec = tv32.tv_sec; tv.tv_usec = tv32.tv_usec; } else if (old_timeval) { struct __kernel_old_timeval old_tv; if (optlen < sizeof(old_tv)) return -EINVAL; if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv))) return -EFAULT; tv.tv_sec = old_tv.tv_sec; tv.tv_usec = old_tv.tv_usec; } else { if (optlen < sizeof(tv)) return -EINVAL; if (copy_from_sockptr(&tv, optval, sizeof(tv))) return -EFAULT; } if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; if (tv.tv_sec < 0) { static int warned __read_mostly; *timeo_p = 0; if (warned < 10 && net_ratelimit()) { warned++; pr_info("%s: `%s' (pid %d) tries to set negative timeout\n", __func__, current->comm, task_pid_nr(current)); } return 0; } *timeo_p = MAX_SCHEDULE_TIMEOUT; if (tv.tv_sec == 0 && tv.tv_usec == 0) return 0; if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ); return 0; } static bool sock_needs_netstamp(const struct sock *sk) { switch (sk->sk_family) { case AF_UNSPEC: case AF_UNIX: return false; default: return true; } } static void sock_disable_timestamp(struct sock *sk, unsigned long flags) { if (sk->sk_flags & flags) { sk->sk_flags &= ~flags; if (sock_needs_netstamp(sk) && !(sk->sk_flags & SK_FLAGS_TIMESTAMP)) net_disable_timestamp(); } } int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; if (atomic_read(&sk->sk_rmem_alloc) >= READ_ONCE(sk->sk_rcvbuf)) { atomic_inc(&sk->sk_drops); trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; } if (!sk_rmem_schedule(sk, skb, skb->truesize)) { atomic_inc(&sk->sk_drops); return -ENOBUFS; } skb->dev = NULL; skb_set_owner_r(skb, sk); /* we escape from rcu protected region, make sure we dont leak * a norefcounted dst */ skb_dst_force(skb); spin_lock_irqsave(&list->lock, flags); sock_skb_set_dropcount(sk, skb); __skb_queue_tail(list, skb); spin_unlock_irqrestore(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); return 0; } EXPORT_SYMBOL(__sock_queue_rcv_skb); int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err; err = sk_filter(sk, skb); if (err) return err; return __sock_queue_rcv_skb(sk, skb); } EXPORT_SYMBOL(sock_queue_rcv_skb); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, unsigned int trim_cap, bool refcounted) { int rc = NET_RX_SUCCESS; if (sk_filter_trim_cap(sk, skb, trim_cap)) goto discard_and_relse; skb->dev = NULL; if (sk_rcvqueues_full(sk, READ_ONCE(sk->sk_rcvbuf))) { atomic_inc(&sk->sk_drops); goto discard_and_relse; } if (nested) bh_lock_sock_nested(sk); else bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { /* * trylock + unlock semantics: */ mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_); rc = sk_backlog_rcv(sk, skb); mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) { bh_unlock_sock(sk); atomic_inc(&sk->sk_drops); goto discard_and_relse; } bh_unlock_sock(sk); out: if (refcounted) sock_put(sk); return rc; discard_and_relse: kfree_skb(skb); goto out; } EXPORT_SYMBOL(__sk_receive_skb); INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *, u32)); INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->obsolete && INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie) == NULL) { sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; } return dst; } EXPORT_SYMBOL(__sk_dst_check); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = sk_dst_get(sk); if (dst && dst->obsolete && INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie) == NULL) { sk_dst_reset(sk); dst_release(dst); return NULL; } return dst; } EXPORT_SYMBOL(sk_dst_check); static int sock_bindtoindex_locked(struct sock *sk, int ifindex) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); /* Sorry... */ ret = -EPERM; if (sk->sk_bound_dev_if && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out; ret = -EINVAL; if (ifindex < 0) goto out; sk->sk_bound_dev_if = ifindex; if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); sk_dst_reset(sk); ret = 0; out: #endif return ret; } int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk) { int ret; if (lock_sk) lock_sock(sk); ret = sock_bindtoindex_locked(sk, ifindex); if (lock_sk) release_sock(sk); return ret; } EXPORT_SYMBOL(sock_bindtoindex); static int sock_setbindtodevice(struct sock *sk, sockptr_t optval, int optlen) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); char devname[IFNAMSIZ]; int index; ret = -EINVAL; if (optlen < 0) goto out; /* Bind this socket to a particular device like "eth0", * as specified in the passed interface name. If the * name is "" or the option length is zero the socket * is not bound. */ if (optlen > IFNAMSIZ - 1) optlen = IFNAMSIZ - 1; memset(devname, 0, sizeof(devname)); ret = -EFAULT; if (copy_from_sockptr(devname, optval, optlen)) goto out; index = 0; if (devname[0] != '\0') { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_name_rcu(net, devname); if (dev) index = dev->ifindex; rcu_read_unlock(); ret = -ENODEV; if (!dev) goto out; } return sock_bindtoindex(sk, index, true); out: #endif return ret; } static int sock_getbindtodevice(struct sock *sk, sockptr_t optval, sockptr_t optlen, int len) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); char devname[IFNAMSIZ]; if (sk->sk_bound_dev_if == 0) { len = 0; goto zero; } ret = -EINVAL; if (len < IFNAMSIZ) goto out; ret = netdev_get_name(net, devname, sk->sk_bound_dev_if); if (ret) goto out; len = strlen(devname) + 1; ret = -EFAULT; if (copy_to_sockptr(optval, devname, len)) goto out; zero: ret = -EFAULT; if (copy_to_sockptr(optlen, &len, sizeof(int))) goto out; ret = 0; out: #endif return ret; } bool sk_mc_loop(struct sock *sk) { if (dev_recursion_level()) return false; if (!sk) return true; /* IPV6_ADDRFORM can change sk->sk_family under us. */ switch (READ_ONCE(sk->sk_family)) { case AF_INET: return inet_sk(sk)->mc_loop; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return inet6_sk(sk)->mc_loop; #endif } WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop); void sock_set_reuseaddr(struct sock *sk) { lock_sock(sk); sk->sk_reuse = SK_CAN_REUSE; release_sock(sk); } EXPORT_SYMBOL(sock_set_reuseaddr); void sock_set_reuseport(struct sock *sk) { lock_sock(sk); sk->sk_reuseport = true; release_sock(sk); } EXPORT_SYMBOL(sock_set_reuseport); void sock_no_linger(struct sock *sk) { lock_sock(sk); sk->sk_lingertime = 0; sock_set_flag(sk, SOCK_LINGER); release_sock(sk); } EXPORT_SYMBOL(sock_no_linger); void sock_set_priority(struct sock *sk, u32 priority) { lock_sock(sk); sk->sk_priority = priority; release_sock(sk); } EXPORT_SYMBOL(sock_set_priority); void sock_set_sndtimeo(struct sock *sk, s64 secs) { lock_sock(sk); if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1) sk->sk_sndtimeo = secs * HZ; else sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; release_sock(sk); } EXPORT_SYMBOL(sock_set_sndtimeo); static void __sock_set_timestamps(struct sock *sk, bool val, bool new, bool ns) { if (val) { sock_valbool_flag(sk, SOCK_TSTAMP_NEW, new); sock_valbool_flag(sk, SOCK_RCVTSTAMPNS, ns); sock_set_flag(sk, SOCK_RCVTSTAMP); sock_enable_timestamp(sk, SOCK_TIMESTAMP); } else { sock_reset_flag(sk, SOCK_RCVTSTAMP); sock_reset_flag(sk, SOCK_RCVTSTAMPNS); } } void sock_enable_timestamps(struct sock *sk) { lock_sock(sk); __sock_set_timestamps(sk, true, false, true); release_sock(sk); } EXPORT_SYMBOL(sock_enable_timestamps); void sock_set_timestamp(struct sock *sk, int optname, bool valbool) { switch (optname) { case SO_TIMESTAMP_OLD: __sock_set_timestamps(sk, valbool, false, false); break; case SO_TIMESTAMP_NEW: __sock_set_timestamps(sk, valbool, true, false); break; case SO_TIMESTAMPNS_OLD: __sock_set_timestamps(sk, valbool, false, true); break; case SO_TIMESTAMPNS_NEW: __sock_set_timestamps(sk, valbool, true, true); break; } } static int sock_timestamping_bind_phc(struct sock *sk, int phc_index) { struct net *net = sock_net(sk); struct net_device *dev = NULL; bool match = false; int *vclock_index; int i, num; if (sk->sk_bound_dev_if) dev = dev_get_by_index(net, sk->sk_bound_dev_if); if (!dev) { pr_err("%s: sock not bind to device\n", __func__); return -EOPNOTSUPP; } num = ethtool_get_phc_vclocks(dev, &vclock_index); dev_put(dev); for (i = 0; i < num; i++) { if (*(vclock_index + i) == phc_index) { match = true; break; } } if (num > 0) kfree(vclock_index); if (!match) return -EINVAL; sk->sk_bind_phc = phc_index; return 0; } int sock_set_timestamping(struct sock *sk, int optname, struct so_timestamping timestamping) { int val = timestamping.flags; int ret; if (val & ~SOF_TIMESTAMPING_MASK) return -EINVAL; if (val & SOF_TIMESTAMPING_OPT_ID && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { if (sk->sk_protocol == IPPROTO_TCP && sk->sk_type == SOCK_STREAM) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return -EINVAL; atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una); } else { atomic_set(&sk->sk_tskey, 0); } } if (val & SOF_TIMESTAMPING_OPT_STATS && !(val & SOF_TIMESTAMPING_OPT_TSONLY)) return -EINVAL; if (val & SOF_TIMESTAMPING_BIND_PHC) { ret = sock_timestamping_bind_phc(sk, timestamping.bind_phc); if (ret) return ret; } sk->sk_tsflags = val; sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); else sock_disable_timestamp(sk, (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); return 0; } void sock_set_keepalive(struct sock *sk) { lock_sock(sk); if (sk->sk_prot->keepalive) sk->sk_prot->keepalive(sk, true); sock_valbool_flag(sk, SOCK_KEEPOPEN, true); release_sock(sk); } EXPORT_SYMBOL(sock_set_keepalive); static void __sock_set_rcvbuf(struct sock *sk, int val) { /* Ensure val * 2 fits into an int, to prevent max_t() from treating it * as a negative value. */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; /* We double it on the way in to account for "struct sk_buff" etc. * overhead. Applications assume that the SO_RCVBUF setting they make * will allow that much actual data to be received on that socket. * * Applications are unaware that "struct sk_buff" and other overheads * allocate from the receive buffer during socket buffer allocation. * * And after considering the possible alternatives, returning the value * we actually used in getsockopt is the most desirable behavior. */ WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF)); } void sock_set_rcvbuf(struct sock *sk, int val) { lock_sock(sk); __sock_set_rcvbuf(sk, val); release_sock(sk); } EXPORT_SYMBOL(sock_set_rcvbuf); static void __sock_set_mark(struct sock *sk, u32 val) { if (val != sk->sk_mark) { sk->sk_mark = val; sk_dst_reset(sk); } } void sock_set_mark(struct sock *sk, u32 val) { lock_sock(sk); __sock_set_mark(sk, val); release_sock(sk); } EXPORT_SYMBOL(sock_set_mark); /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. */ int sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct so_timestamping timestamping; struct sock_txtime sk_txtime; struct sock *sk = sock->sk; int val; int valbool; struct linger ling; int ret = 0; /* * Options without arguments */ if (optname == SO_BINDTODEVICE) return sock_setbindtodevice(sk, optval, optlen); if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; valbool = val ? 1 : 0; lock_sock(sk); switch (optname) { case SO_DEBUG: if (val && !capable(CAP_NET_ADMIN)) ret = -EACCES; else sock_valbool_flag(sk, SOCK_DBG, valbool); break; case SO_REUSEADDR: sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); break; case SO_REUSEPORT: if (valbool && !sk_is_inet(sk)) ret = -EOPNOTSUPP; else sk->sk_reuseport = valbool; break; case SO_TYPE: case SO_PROTOCOL: case SO_DOMAIN: case SO_ERROR: ret = -ENOPROTOOPT; break; case SO_DONTROUTE: sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool); sk_dst_reset(sk); break; case SO_BROADCAST: sock_valbool_flag(sk, SOCK_BROADCAST, valbool); break; case SO_SNDBUF: /* Don't error on this BSD doesn't and if you think * about it this is right. Otherwise apps have to * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ val = min_t(u32, val, READ_ONCE(sysctl_wmem_max)); set_sndbuf: /* Ensure val * 2 fits into an int, to prevent max_t() * from treating it as a negative value. */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(sk->sk_sndbuf, max_t(int, val * 2, SOCK_MIN_SNDBUF)); /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; case SO_SNDBUFFORCE: if (!capable(CAP_NET_ADMIN)) { ret = -EPERM; break; } /* No negative values (to prevent underflow, as val will be * multiplied by 2). */ if (val < 0) val = 0; goto set_sndbuf; case SO_RCVBUF: /* Don't error on this BSD doesn't and if you think * about it this is right. Otherwise apps have to * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ __sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max))); break; case SO_RCVBUFFORCE: if (!capable(CAP_NET_ADMIN)) { ret = -EPERM; break; } /* No negative values (to prevent underflow, as val will be * multiplied by 2). */ __sock_set_rcvbuf(sk, max(val, 0)); break; case SO_KEEPALIVE: if (sk->sk_prot->keepalive) sk->sk_prot->keepalive(sk, valbool); sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); break; case SO_OOBINLINE: sock_valbool_flag(sk, SOCK_URGINLINE, valbool); break; case SO_NO_CHECK: sk->sk_no_check_tx = valbool; break; case SO_PRIORITY: if ((val >= 0 && val <= 6) || ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) sk->sk_priority = val; else ret = -EPERM; break; case SO_LINGER: if (optlen < sizeof(ling)) { ret = -EINVAL; /* 1003.1g */ break; } if (copy_from_sockptr(&ling, optval, sizeof(ling))) { ret = -EFAULT; break; } if (!ling.l_onoff) sock_reset_flag(sk, SOCK_LINGER); else { #if (BITS_PER_LONG == 32) if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ) sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT; else #endif sk->sk_lingertime = (unsigned int)ling.l_linger * HZ; sock_set_flag(sk, SOCK_LINGER); } break; case SO_BSDCOMPAT: break; case SO_PASSCRED: if (valbool) set_bit(SOCK_PASSCRED, &sock->flags); else clear_bit(SOCK_PASSCRED, &sock->flags); break; case SO_TIMESTAMP_OLD: case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: sock_set_timestamp(sk, optname, valbool); break; case SO_TIMESTAMPING_NEW: case SO_TIMESTAMPING_OLD: if (optlen == sizeof(timestamping)) { if (copy_from_sockptr(×tamping, optval, sizeof(timestamping))) { ret = -EFAULT; break; } } else { memset(×tamping, 0, sizeof(timestamping)); timestamping.flags = val; } ret = sock_set_timestamping(sk, optname, timestamping); break; case SO_RCVLOWAT: if (val < 0) val = INT_MAX; if (sock->ops->set_rcvlowat) ret = sock->ops->set_rcvlowat(sk, val); else WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen, optname == SO_RCVTIMEO_OLD); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen, optname == SO_SNDTIMEO_OLD); break; case SO_ATTACH_FILTER: { struct sock_fprog fprog; ret = copy_bpf_fprog_from_user(&fprog, optval, optlen); if (!ret) ret = sk_attach_filter(&fprog, sk); break; } case SO_ATTACH_BPF: ret = -EINVAL; if (optlen == sizeof(u32)) { u32 ufd; ret = -EFAULT; if (copy_from_sockptr(&ufd, optval, sizeof(ufd))) break; ret = sk_attach_bpf(ufd, sk); } break; case SO_ATTACH_REUSEPORT_CBPF: { struct sock_fprog fprog; ret = copy_bpf_fprog_from_user(&fprog, optval, optlen); if (!ret) ret = sk_reuseport_attach_filter(&fprog, sk); break; } case SO_ATTACH_REUSEPORT_EBPF: ret = -EINVAL; if (optlen == sizeof(u32)) { u32 ufd; ret = -EFAULT; if (copy_from_sockptr(&ufd, optval, sizeof(ufd))) break; ret = sk_reuseport_attach_bpf(ufd, sk); } break; case SO_DETACH_REUSEPORT_BPF: ret = reuseport_detach_prog(sk); break; case SO_DETACH_FILTER: ret = sk_detach_filter(sk); break; case SO_LOCK_FILTER: if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool) ret = -EPERM; else sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool); break; case SO_PASSSEC: if (valbool) set_bit(SOCK_PASSSEC, &sock->flags); else clear_bit(SOCK_PASSSEC, &sock->flags); break; case SO_MARK: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } __sock_set_mark(sk, val); break; case SO_RXQ_OVFL: sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); break; case SO_WIFI_STATUS: sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool); break; case SO_PEEK_OFF: if (sock->ops->set_peek_off) ret = sock->ops->set_peek_off(sk, val); else ret = -EOPNOTSUPP; break; case SO_NOFCS: sock_valbool_flag(sk, SOCK_NOFCS, valbool); break; case SO_SELECT_ERR_QUEUE: sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool); break; #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: /* allow unprivileged users to decrease the value */ if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN)) ret = -EPERM; else { if (val < 0) ret = -EINVAL; else WRITE_ONCE(sk->sk_ll_usec, val); } break; case SO_PREFER_BUSY_POLL: if (valbool && !capable(CAP_NET_ADMIN)) ret = -EPERM; else WRITE_ONCE(sk->sk_prefer_busy_poll, valbool); break; case SO_BUSY_POLL_BUDGET: if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) { ret = -EPERM; } else { if (val < 0 || val > U16_MAX) ret = -EINVAL; else WRITE_ONCE(sk->sk_busy_poll_budget, val); } break; #endif case SO_MAX_PACING_RATE: { unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val; if (sizeof(ulval) != sizeof(val) && optlen >= sizeof(ulval) && copy_from_sockptr(&ulval, optval, sizeof(ulval))) { ret = -EFAULT; break; } if (ulval != ~0UL) cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); /* Pairs with READ_ONCE() from sk_getsockopt() */ WRITE_ONCE(sk->sk_max_pacing_rate, ulval); sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval); break; } case SO_INCOMING_CPU: WRITE_ONCE(sk->sk_incoming_cpu, val); break; case SO_CNX_ADVICE: if (val == 1) dst_negative_advice(sk); break; case SO_ZEROCOPY: if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) { if (!((sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP) || (sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP))) ret = -ENOTSUPP; } else if (sk->sk_family != PF_RDS) { ret = -ENOTSUPP; } if (!ret) { if (val < 0 || val > 1) ret = -EINVAL; else sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool); } break; case SO_TXTIME: if (optlen != sizeof(struct sock_txtime)) { ret = -EINVAL; break; } else if (copy_from_sockptr(&sk_txtime, optval, sizeof(struct sock_txtime))) { ret = -EFAULT; break; } else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) { ret = -EINVAL; break; } /* CLOCK_MONOTONIC is only used by sch_fq, and this packet * scheduler has enough safe guards. */ if (sk_txtime.clockid != CLOCK_MONOTONIC && !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } sock_valbool_flag(sk, SOCK_TXTIME, true); sk->sk_clockid = sk_txtime.clockid; sk->sk_txtime_deadline_mode = !!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE); sk->sk_txtime_report_errors = !!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS); break; case SO_BINDTOIFINDEX: ret = sock_bindtoindex_locked(sk, val); break; case SO_BUF_LOCK: if (val & ~SOCK_BUF_LOCK_MASK) { ret = -EINVAL; break; } sk->sk_userlocks = val | (sk->sk_userlocks & ~SOCK_BUF_LOCK_MASK); break; default: ret = -ENOPROTOOPT; break; } release_sock(sk); return ret; } EXPORT_SYMBOL(sock_setsockopt); static const struct cred *sk_get_peer_cred(struct sock *sk) { const struct cred *cred; spin_lock(&sk->sk_peer_lock); cred = get_cred(sk->sk_peer_cred); spin_unlock(&sk->sk_peer_lock); return cred; } static void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred) { ucred->pid = pid_vnr(pid); ucred->uid = ucred->gid = -1; if (cred) { struct user_namespace *current_ns = current_user_ns(); ucred->uid = from_kuid_munged(current_ns, cred->euid); ucred->gid = from_kgid_munged(current_ns, cred->egid); } } static int groups_to_user(sockptr_t dst, const struct group_info *src) { struct user_namespace *user_ns = current_user_ns(); int i; for (i = 0; i < src->ngroups; i++) { gid_t gid = from_kgid_munged(user_ns, src->gid[i]); if (copy_to_sockptr_offset(dst, i * sizeof(gid), &gid, sizeof(gid))) return -EFAULT; } return 0; } static int sk_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen) { struct socket *sock = sk->sk_socket; union { int val; u64 val64; unsigned long ulval; struct linger ling; struct old_timeval32 tm32; struct __kernel_old_timeval tm; struct __kernel_sock_timeval stm; struct sock_txtime txtime; struct so_timestamping timestamping; } v; int lv = sizeof(int); int len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; memset(&v, 0, sizeof(v)); switch (optname) { case SO_DEBUG: v.val = sock_flag(sk, SOCK_DBG); break; case SO_DONTROUTE: v.val = sock_flag(sk, SOCK_LOCALROUTE); break; case SO_BROADCAST: v.val = sock_flag(sk, SOCK_BROADCAST); break; case SO_SNDBUF: v.val = READ_ONCE(sk->sk_sndbuf); break; case SO_RCVBUF: v.val = READ_ONCE(sk->sk_rcvbuf); break; case SO_REUSEADDR: v.val = sk->sk_reuse; break; case SO_REUSEPORT: v.val = sk->sk_reuseport; break; case SO_KEEPALIVE: v.val = sock_flag(sk, SOCK_KEEPOPEN); break; case SO_TYPE: v.val = sk->sk_type; break; case SO_PROTOCOL: v.val = sk->sk_protocol; break; case SO_DOMAIN: v.val = sk->sk_family; break; case SO_ERROR: v.val = -sock_error(sk); if (v.val == 0) v.val = xchg(&sk->sk_err_soft, 0); break; case SO_OOBINLINE: v.val = sock_flag(sk, SOCK_URGINLINE); break; case SO_NO_CHECK: v.val = sk->sk_no_check_tx; break; case SO_PRIORITY: v.val = sk->sk_priority; break; case SO_LINGER: lv = sizeof(v.ling); v.ling.l_onoff = sock_flag(sk, SOCK_LINGER); v.ling.l_linger = sk->sk_lingertime / HZ; break; case SO_BSDCOMPAT: break; case SO_TIMESTAMP_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && !sock_flag(sk, SOCK_TSTAMP_NEW) && !sock_flag(sk, SOCK_RCVTSTAMPNS); break; case SO_TIMESTAMPNS_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && !sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMP_NEW: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMPNS_NEW: v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMPING_OLD: case SO_TIMESTAMPING_NEW: lv = sizeof(v.timestamping); /* For the later-added case SO_TIMESTAMPING_NEW: Be strict about only * returning the flags when they were set through the same option. * Don't change the beviour for the old case SO_TIMESTAMPING_OLD. */ if (optname == SO_TIMESTAMPING_OLD || sock_flag(sk, SOCK_TSTAMP_NEW)) { v.timestamping.flags = sk->sk_tsflags; v.timestamping.bind_phc = sk->sk_bind_phc; } break; case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname); break; case SO_RCVLOWAT: v.val = READ_ONCE(sk->sk_rcvlowat); break; case SO_SNDLOWAT: v.val = 1; break; case SO_PASSCRED: v.val = !!test_bit(SOCK_PASSCRED, &sock->flags); break; case SO_PEERCRED: { struct ucred peercred; if (len > sizeof(peercred)) len = sizeof(peercred); spin_lock(&sk->sk_peer_lock); cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); spin_unlock(&sk->sk_peer_lock); if (copy_to_sockptr(optval, &peercred, len)) return -EFAULT; goto lenout; } case SO_PEERGROUPS: { const struct cred *cred; int ret, n; cred = sk_get_peer_cred(sk); if (!cred) return -ENODATA; n = cred->group_info->ngroups; if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); put_cred(cred); return copy_to_sockptr(optlen, &len, sizeof(int)) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); ret = groups_to_user(optval, cred->group_info); put_cred(cred); if (ret) return ret; goto lenout; } case SO_PEERNAME: { char address[128]; lv = sock->ops->getname(sock, (struct sockaddr *)address, 2); if (lv < 0) return -ENOTCONN; if (lv < len) return -EINVAL; if (copy_to_sockptr(optval, address, len)) return -EFAULT; goto lenout; } /* Dubious BSD thing... Probably nobody even uses it, but * the UNIX standard wants it for whatever reason... -DaveM */ case SO_ACCEPTCONN: v.val = sk->sk_state == TCP_LISTEN; break; case SO_PASSSEC: v.val = !!test_bit(SOCK_PASSSEC, &sock->flags); break; case SO_PEERSEC: return security_socket_getpeersec_stream(sock, optval.user, optlen.user, len); case SO_MARK: v.val = sk->sk_mark; break; case SO_RXQ_OVFL: v.val = sock_flag(sk, SOCK_RXQ_OVFL); break; case SO_WIFI_STATUS: v.val = sock_flag(sk, SOCK_WIFI_STATUS); break; case SO_PEEK_OFF: if (!sock->ops->set_peek_off) return -EOPNOTSUPP; v.val = READ_ONCE(sk->sk_peek_off); break; case SO_NOFCS: v.val = sock_flag(sk, SOCK_NOFCS); break; case SO_BINDTODEVICE: return sock_getbindtodevice(sk, optval, optlen, len); case SO_GET_FILTER: len = sk_get_filter(sk, optval, len); if (len < 0) return len; goto lenout; case SO_LOCK_FILTER: v.val = sock_flag(sk, SOCK_FILTER_LOCKED); break; case SO_BPF_EXTENSIONS: v.val = bpf_tell_extensions(); break; case SO_SELECT_ERR_QUEUE: v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); break; #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: v.val = READ_ONCE(sk->sk_ll_usec); break; case SO_PREFER_BUSY_POLL: v.val = READ_ONCE(sk->sk_prefer_busy_poll); break; #endif case SO_MAX_PACING_RATE: /* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */ if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) { lv = sizeof(v.ulval); v.ulval = READ_ONCE(sk->sk_max_pacing_rate); } else { /* 32bit version */ v.val = min_t(unsigned long, ~0U, READ_ONCE(sk->sk_max_pacing_rate)); } break; case SO_INCOMING_CPU: v.val = READ_ONCE(sk->sk_incoming_cpu); break; case SO_MEMINFO: { u32 meminfo[SK_MEMINFO_VARS]; sk_get_meminfo(sk, meminfo); len = min_t(unsigned int, len, sizeof(meminfo)); if (copy_to_sockptr(optval, &meminfo, len)) return -EFAULT; goto lenout; } #ifdef CONFIG_NET_RX_BUSY_POLL case SO_INCOMING_NAPI_ID: v.val = READ_ONCE(sk->sk_napi_id); /* aggregate non-NAPI IDs down to 0 */ if (v.val < MIN_NAPI_ID) v.val = 0; break; #endif case SO_COOKIE: lv = sizeof(u64); if (len < lv) return -EINVAL; v.val64 = sock_gen_cookie(sk); break; case SO_ZEROCOPY: v.val = sock_flag(sk, SOCK_ZEROCOPY); break; case SO_TXTIME: lv = sizeof(v.txtime); v.txtime.clockid = sk->sk_clockid; v.txtime.flags |= sk->sk_txtime_deadline_mode ? SOF_TXTIME_DEADLINE_MODE : 0; v.txtime.flags |= sk->sk_txtime_report_errors ? SOF_TXTIME_REPORT_ERRORS : 0; break; case SO_BINDTOIFINDEX: v.val = sk->sk_bound_dev_if; break; case SO_NETNS_COOKIE: lv = sizeof(u64); if (len != lv) return -EINVAL; v.val64 = sock_net(sk)->net_cookie; break; case SO_BUF_LOCK: v.val = sk->sk_userlocks & SOCK_BUF_LOCK_MASK; break; default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). */ return -ENOPROTOOPT; } if (len > lv) len = lv; if (copy_to_sockptr(optval, &v, len)) return -EFAULT; lenout: if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; return 0; } int sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { return sk_getsockopt(sock->sk, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); } /* * Initialize an sk_lock. * * (We also register the sk_lock with the lock validator.) */ static inline void sock_lock_init(struct sock *sk) { if (sk->sk_kern_sock) sock_lock_init_class_and_name( sk, af_family_kern_slock_key_strings[sk->sk_family], af_family_kern_slock_keys + sk->sk_family, af_family_kern_key_strings[sk->sk_family], af_family_kern_keys + sk->sk_family); else sock_lock_init_class_and_name( sk, af_family_slock_key_strings[sk->sk_family], af_family_slock_keys + sk->sk_family, af_family_key_strings[sk->sk_family], af_family_keys + sk->sk_family); } /* * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, * even temporarly, because of RCU lookups. sk_node should also be left as is. * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end */ static void sock_copy(struct sock *nsk, const struct sock *osk) { const struct proto *prot = READ_ONCE(osk->sk_prot); #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif /* If we move sk_tx_queue_mapping out of the private section, * we must check if sk_tx_queue_clear() is called after * sock_copy() in sk_clone_lock(). */ BUILD_BUG_ON(offsetof(struct sock, sk_tx_queue_mapping) < offsetof(struct sock, sk_dontcopy_begin) || offsetof(struct sock, sk_tx_queue_mapping) >= offsetof(struct sock, sk_dontcopy_end)); memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; security_sk_clone(osk, nsk); #endif } static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, int family) { struct sock *sk; struct kmem_cache *slab; slab = prot->slab; if (slab != NULL) { sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO); if (!sk) return sk; if (want_init_on_alloc(priority)) sk_prot_clear_nulls(sk, prot->obj_size); } else sk = kmalloc(prot->obj_size, priority); if (sk != NULL) { if (security_sk_alloc(sk, family, priority)) goto out_free; trace_android_rvh_sk_alloc(sk); if (!try_module_get(prot->owner)) goto out_free_sec; } return sk; out_free_sec: security_sk_free(sk); trace_android_rvh_sk_free(sk); out_free: if (slab != NULL) kmem_cache_free(slab, sk); else kfree(sk); return NULL; } static void sk_prot_free(struct proto *prot, struct sock *sk) { struct kmem_cache *slab; struct module *owner; owner = prot->owner; slab = prot->slab; cgroup_sk_free(&sk->sk_cgrp_data); mem_cgroup_sk_free(sk); security_sk_free(sk); trace_android_rvh_sk_free(sk); if (slab != NULL) kmem_cache_free(slab, sk); else kfree(sk); module_put(owner); } /** * sk_alloc - All socket objects are allocated here * @net: the applicable net namespace * @family: protocol family * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * @prot: struct proto associated with this new sock instance * @kern: is this to be a kernel socket? */ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern) { struct sock *sk; sk = sk_prot_alloc(prot, priority | __GFP_ZERO, family); if (sk) { sk->sk_family = family; /* * See comment in struct sock definition to understand * why we need sk_prot_creator -acme */ sk->sk_prot = sk->sk_prot_creator = prot; sk->sk_kern_sock = kern; sock_lock_init(sk); sk->sk_net_refcnt = kern ? 0 : 1; if (likely(sk->sk_net_refcnt)) { get_net(net); sock_inuse_add(net, 1); } sock_net_set(sk, net); refcount_set(&sk->sk_wmem_alloc, 1); mem_cgroup_sk_alloc(sk); cgroup_sk_alloc(&sk->sk_cgrp_data); sock_update_classid(&sk->sk_cgrp_data); sock_update_netprioidx(&sk->sk_cgrp_data); sk_tx_queue_clear(sk); } return sk; } EXPORT_SYMBOL(sk_alloc); /* Sockets having SOCK_RCU_FREE will call this function after one RCU * grace period. This is the case for UDP sockets and TCP listeners. */ static void __sk_destruct(struct rcu_head *head) { struct sock *sk = container_of(head, struct sock, sk_rcu); struct sk_filter *filter; if (sk->sk_destruct) sk->sk_destruct(sk); filter = rcu_dereference_check(sk->sk_filter, refcount_read(&sk->sk_wmem_alloc) == 0); if (filter) { sk_filter_uncharge(sk, filter); RCU_INIT_POINTER(sk->sk_filter, NULL); } sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); #ifdef CONFIG_BPF_SYSCALL bpf_sk_storage_free(sk); #endif if (atomic_read(&sk->sk_omem_alloc)) pr_debug("%s: optmem leakage (%d bytes) detected\n", __func__, atomic_read(&sk->sk_omem_alloc)); if (sk->sk_frag.page) { put_page(sk->sk_frag.page); sk->sk_frag.page = NULL; } /* We do not need to acquire sk->sk_peer_lock, we are the last user. */ put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); if (likely(sk->sk_net_refcnt)) put_net(sock_net(sk)); sk_prot_free(sk->sk_prot_creator, sk); } void sk_destruct(struct sock *sk) { bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE); if (rcu_access_pointer(sk->sk_reuseport_cb)) { reuseport_detach_sock(sk); use_call_rcu = true; } if (use_call_rcu) call_rcu(&sk->sk_rcu, __sk_destruct); else __sk_destruct(&sk->sk_rcu); } static void __sk_free(struct sock *sk) { if (likely(sk->sk_net_refcnt)) sock_inuse_add(sock_net(sk), -1); if (unlikely(sk->sk_net_refcnt && sock_diag_has_destroy_listeners(sk))) sock_diag_broadcast_destroy(sk); else sk_destruct(sk); } void sk_free(struct sock *sk) { /* * We subtract one from sk_wmem_alloc and can know if * some packets are still in some tx queue. * If not null, sock_wfree() will call __sk_free(sk) later */ if (refcount_dec_and_test(&sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sk_free); static void sk_init_common(struct sock *sk) { skb_queue_head_init(&sk->sk_receive_queue); skb_queue_head_init(&sk->sk_write_queue); skb_queue_head_init(&sk->sk_error_queue); rwlock_init(&sk->sk_callback_lock); lockdep_set_class_and_name(&sk->sk_receive_queue.lock, af_rlock_keys + sk->sk_family, af_family_rlock_key_strings[sk->sk_family]); lockdep_set_class_and_name(&sk->sk_write_queue.lock, af_wlock_keys + sk->sk_family, af_family_wlock_key_strings[sk->sk_family]); lockdep_set_class_and_name(&sk->sk_error_queue.lock, af_elock_keys + sk->sk_family, af_family_elock_key_strings[sk->sk_family]); lockdep_set_class_and_name(&sk->sk_callback_lock, af_callback_keys + sk->sk_family, af_family_clock_key_strings[sk->sk_family]); } /** * sk_clone_lock - clone a socket, and lock its clone * @sk: the socket to clone * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) */ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { struct proto *prot = READ_ONCE(sk->sk_prot); struct sk_filter *filter; bool is_charged = true; struct sock *newsk; newsk = sk_prot_alloc(prot, priority, sk->sk_family); if (!newsk) goto out; sock_copy(newsk, sk); newsk->sk_prot_creator = prot; /* SANITY */ if (likely(newsk->sk_net_refcnt)) { get_net(sock_net(newsk)); sock_inuse_add(sock_net(newsk), 1); } sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; newsk->sk_backlog.len = 0; atomic_set(&newsk->sk_rmem_alloc, 0); /* sk_wmem_alloc set to one (see sk_free() and sock_wfree()) */ refcount_set(&newsk->sk_wmem_alloc, 1); atomic_set(&newsk->sk_omem_alloc, 0); sk_init_common(newsk); newsk->sk_dst_cache = NULL; newsk->sk_dst_pending_confirm = 0; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; atomic_set(&newsk->sk_drops, 0); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; atomic_set(&newsk->sk_zckey, 0); sock_reset_flag(newsk, SOCK_DONE); /* sk->sk_memcg will be populated at accept() time */ newsk->sk_memcg = NULL; cgroup_sk_clone(&newsk->sk_cgrp_data); rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) /* though it's an empty new sock, the charging may fail * if sysctl_optmem_max was changed between creation of * original socket and cloning */ is_charged = sk_filter_charge(newsk, filter); RCU_INIT_POINTER(newsk->sk_filter, filter); rcu_read_unlock(); if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { /* We need to make sure that we don't uncharge the new * socket if we couldn't charge it in the first place * as otherwise we uncharge the parent's filter. */ if (!is_charged) RCU_INIT_POINTER(newsk->sk_filter, NULL); sk_free_unlock_clone(newsk); newsk = NULL; goto out; } RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); if (bpf_sk_storage_clone(sk, newsk)) { sk_free_unlock_clone(newsk); newsk = NULL; goto out; } /* Clear sk_user_data if parent had the pointer tagged * as not suitable for copying when cloning. */ if (sk_user_data_is_nocopy(newsk)) newsk->sk_user_data = NULL; newsk->sk_err = 0; newsk->sk_err_soft = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); /* Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.rst for details) */ smp_wmb(); refcount_set(&newsk->sk_refcnt, 2); /* Increment the counter in the same struct proto as the master * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that * is the same as sk->sk_prot->socks, as this field was copied * with memcpy). * * This _changes_ the previous behaviour, where * tcp_create_openreq_child always was incrementing the * equivalent to tcp_prot->socks (inet_sock_nr), so this have * to be taken into account in all callers. -acme */ sk_refcnt_debug_inc(newsk); sk_set_socket(newsk, NULL); sk_tx_queue_clear(newsk); RCU_INIT_POINTER(newsk->sk_wq, NULL); if (newsk->sk_prot->sockets_allocated) sk_sockets_allocated_inc(newsk); if (sock_needs_netstamp(sk) && newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); out: return newsk; } EXPORT_SYMBOL_GPL(sk_clone_lock); void sk_free_unlock_clone(struct sock *sk) { /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ sk->sk_destruct = NULL; bh_unlock_sock(sk); sk_free(sk); } EXPORT_SYMBOL_GPL(sk_free_unlock_clone); void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; sk->sk_route_caps &= ~sk->sk_route_nocaps; if (sk_can_gso(sk)) { if (dst->header_len && !xfrm_dst_offload_ok(dst)) { sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; sk->sk_gso_max_size = dst->dev->gso_max_size; max_segs = max_t(u32, dst->dev->gso_max_segs, 1); } } sk->sk_gso_max_segs = max_segs; sk_dst_set(sk, dst); } EXPORT_SYMBOL_GPL(sk_setup_caps); /* * Simple resource managers for sockets. */ /* * Write buffer destructor automatically called from kfree_skb. */ void sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; unsigned int len = skb->truesize; if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) { /* * Keep a reference on sk_wmem_alloc, this will be released * after sk_write_space() call */ WARN_ON(refcount_sub_and_test(len - 1, &sk->sk_wmem_alloc)); sk->sk_write_space(sk); len = 1; } /* * if sk_wmem_alloc reaches 0, we must finish what sk_free() * could not do because of in-flight packets */ if (refcount_sub_and_test(len, &sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sock_wfree); /* This variant of sock_wfree() is used by TCP, * since it sets SOCK_USE_WRITE_QUEUE. */ void __sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; if (refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)) __sk_free(sk); } void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); skb->sk = sk; #ifdef CONFIG_INET if (unlikely(!sk_fullsock(sk))) { skb->destructor = sock_edemux; sock_hold(sk); return; } #endif skb->destructor = sock_wfree; skb_set_hash_from_sk(skb, sk); /* * We used to take a refcount on sk, but following operation * is enough to guarantee sk_free() wont free this sock until * all in-flight packets are completed */ refcount_add(skb->truesize, &sk->sk_wmem_alloc); } EXPORT_SYMBOL(skb_set_owner_w); static bool can_skb_orphan_partial(const struct sk_buff *skb) { #ifdef CONFIG_TLS_DEVICE /* Drivers depend on in-order delivery for crypto offload, * partial orphan breaks out-of-order-OK logic. */ if (skb->decrypted) return false; #endif return (skb->destructor == sock_wfree || (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree)); } /* This helper is used by netem, as it can hold packets in its * delay queue. We want to allow the owner socket to send more * packets, as if they were already TX completed by a typical driver. * But we also want to keep skb->sk set because some packet schedulers * rely on it (sch_fq for example). */ void skb_orphan_partial(struct sk_buff *skb) { if (skb_is_tcp_pure_ack(skb)) return; if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk)) return; skb_orphan(skb); } EXPORT_SYMBOL(skb_orphan_partial); /* * Read buffer destructor automatically called from kfree_skb. */ void sock_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; unsigned int len = skb->truesize; atomic_sub(len, &sk->sk_rmem_alloc); sk_mem_uncharge(sk, len); } EXPORT_SYMBOL(sock_rfree); /* * Buffer destructor for skbs that are not used directly in read or write * path, e.g. for error handler skbs. Automatically called from kfree_skb. */ void sock_efree(struct sk_buff *skb) { sock_put(skb->sk); } EXPORT_SYMBOL(sock_efree); /* Buffer destructor for prefetch/receive path where reference count may * not be held, e.g. for listen sockets. */ #ifdef CONFIG_INET void sock_pfree(struct sk_buff *skb) { if (sk_is_refcounted(skb->sk)) sock_gen_put(skb->sk); } EXPORT_SYMBOL(sock_pfree); #endif /* CONFIG_INET */ kuid_t sock_i_uid(struct sock *sk) { kuid_t uid; read_lock_bh(&sk->sk_callback_lock); uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : GLOBAL_ROOT_UID; read_unlock_bh(&sk->sk_callback_lock); return uid; } EXPORT_SYMBOL(sock_i_uid); unsigned long __sock_i_ino(struct sock *sk) { unsigned long ino; read_lock(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; read_unlock(&sk->sk_callback_lock); return ino; } EXPORT_SYMBOL(__sock_i_ino); unsigned long sock_i_ino(struct sock *sk) { unsigned long ino; local_bh_disable(); ino = __sock_i_ino(sk); local_bh_enable(); return ino; } EXPORT_SYMBOL(sock_i_ino); /* * Allocate a skb from the socket's send buffer. */ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { if (force || refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) { struct sk_buff *skb = alloc_skb(size, priority); if (skb) { skb_set_owner_w(skb, sk); return skb; } } return NULL; } EXPORT_SYMBOL(sock_wmalloc); static void sock_ofree(struct sk_buff *skb) { struct sock *sk = skb->sk; atomic_sub(skb->truesize, &sk->sk_omem_alloc); } struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, gfp_t priority) { struct sk_buff *skb; /* small safe race: SKB_TRUESIZE may differ from final skb->truesize */ if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) > READ_ONCE(sysctl_optmem_max)) return NULL; skb = alloc_skb(size, priority); if (!skb) return NULL; atomic_add(skb->truesize, &sk->sk_omem_alloc); skb->sk = sk; skb->destructor = sock_ofree; return skb; } /* * Allocate a memory block from the socket's option memory buffer. */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) { int optmem_max = READ_ONCE(sysctl_optmem_max); if ((unsigned int)size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { void *mem; /* First do the add, to avoid the race if kmalloc * might sleep. */ atomic_add(size, &sk->sk_omem_alloc); mem = kmalloc(size, priority); if (mem) return mem; atomic_sub(size, &sk->sk_omem_alloc); } return NULL; } EXPORT_SYMBOL(sock_kmalloc); /* Free an option memory block. Note, we actually want the inline * here as this allows gcc to detect the nullify and fold away the * condition entirely. */ static inline void __sock_kfree_s(struct sock *sk, void *mem, int size, const bool nullify) { if (WARN_ON_ONCE(!mem)) return; if (nullify) kfree_sensitive(mem); else kfree(mem); atomic_sub(size, &sk->sk_omem_alloc); } void sock_kfree_s(struct sock *sk, void *mem, int size) { __sock_kfree_s(sk, mem, size, false); } EXPORT_SYMBOL(sock_kfree_s); void sock_kzfree_s(struct sock *sk, void *mem, int size) { __sock_kfree_s(sk, mem, size, true); } EXPORT_SYMBOL(sock_kzfree_s); /* It is almost wait_for_tcp_memory minus release_sock/lock_sock. I think, these locks should be removed for datagram sockets. */ static long sock_wait_for_wmem(struct sock *sk, long timeo) { DEFINE_WAIT(wait); sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); for (;;) { if (!timeo) break; if (signal_pending(current)) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) break; if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) break; if (READ_ONCE(sk->sk_err)) break; timeo = schedule_timeout(timeo); } finish_wait(sk_sleep(sk), &wait); return timeo; } /* * Generic send/receive buffer handlers */ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, int *errcode, int max_page_order) { struct sk_buff *skb; long timeo; int err; timeo = sock_sndtimeo(sk, noblock); for (;;) { err = sock_error(sk); if (err != 0) goto failure; err = -EPIPE; if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) goto failure; if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf)) break; sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); err = -EAGAIN; if (!timeo) goto failure; if (signal_pending(current)) goto interrupted; timeo = sock_wait_for_wmem(sk, timeo); } skb = alloc_skb_with_frags(header_len, data_len, max_page_order, errcode, sk->sk_allocation); if (skb) skb_set_owner_w(skb, sk); return skb; interrupted: err = sock_intr_errno(timeo); failure: *errcode = err; return NULL; } EXPORT_SYMBOL(sock_alloc_send_pskb); struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode) { return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0); } EXPORT_SYMBOL(sock_alloc_send_skb); int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, struct sockcm_cookie *sockc) { u32 tsflags; switch (cmsg->cmsg_type) { case SO_MARK: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; sockc->mark = *(u32 *)CMSG_DATA(cmsg); break; case SO_TIMESTAMPING_OLD: case SO_TIMESTAMPING_NEW: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; tsflags = *(u32 *)CMSG_DATA(cmsg); if (tsflags & ~SOF_TIMESTAMPING_TX_RECORD_MASK) return -EINVAL; sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK; sockc->tsflags |= tsflags; break; case SCM_TXTIME: if (!sock_flag(sk, SOCK_TXTIME)) return -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64))) return -EINVAL; sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg)); break; /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ case SCM_RIGHTS: case SCM_CREDENTIALS: break; default: return -EINVAL; } return 0; } EXPORT_SYMBOL(__sock_cmsg_send); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc) { struct cmsghdr *cmsg; int ret; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_SOCKET) continue; ret = __sock_cmsg_send(sk, msg, cmsg, sockc); if (ret) return ret; } return 0; } EXPORT_SYMBOL(sock_cmsg_send); static void sk_enter_memory_pressure(struct sock *sk) { if (!sk->sk_prot->enter_memory_pressure) return; sk->sk_prot->enter_memory_pressure(sk); } static void sk_leave_memory_pressure(struct sock *sk) { if (sk->sk_prot->leave_memory_pressure) { sk->sk_prot->leave_memory_pressure(sk); } else { unsigned long *memory_pressure = sk->sk_prot->memory_pressure; if (memory_pressure && READ_ONCE(*memory_pressure)) WRITE_ONCE(*memory_pressure, 0); } } DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); /** * skb_page_frag_refill - check that a page_frag contains enough room * @sz: minimum size of the fragment we want to get * @pfrag: pointer to page_frag * @gfp: priority for memory allocation * * Note: While this allocator tries to use high order pages, there is * no guarantee that allocations succeed. Therefore, @sz MUST be * less or equal than PAGE_SIZE. */ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp) { if (pfrag->page) { if (page_ref_count(pfrag->page) == 1) { pfrag->offset = 0; return true; } if (pfrag->offset + sz <= pfrag->size) return true; put_page(pfrag->page); } pfrag->offset = 0; if (SKB_FRAG_PAGE_ORDER && !static_branch_unlikely(&net_high_order_alloc_disable_key)) { /* Avoid direct reclaim but allow kswapd to wake */ pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; return true; } } pfrag->page = alloc_page(gfp); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE; return true; } return false; } EXPORT_SYMBOL(skb_page_frag_refill); bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) { if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation))) return true; sk_enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); return false; } EXPORT_SYMBOL(sk_page_frag_refill); void __lock_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait, TASK_UNINTERRUPTIBLE); spin_unlock_bh(&sk->sk_lock.slock); schedule(); spin_lock_bh(&sk->sk_lock.slock); if (!sock_owned_by_user(sk)) break; } finish_wait(&sk->sk_lock.wq, &wait); } void __release_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) { struct sk_buff *skb, *next; while ((skb = sk->sk_backlog.head) != NULL) { sk->sk_backlog.head = sk->sk_backlog.tail = NULL; spin_unlock_bh(&sk->sk_lock.slock); do { next = skb->next; prefetch(next); WARN_ON_ONCE(skb_dst_is_noref(skb)); skb_mark_not_on_list(skb); sk_backlog_rcv(sk, skb); cond_resched(); skb = next; } while (skb != NULL); spin_lock_bh(&sk->sk_lock.slock); } /* * Doing the zeroing here guarantee we can not loop forever * while a wild producer attempts to flood us. */ sk->sk_backlog.len = 0; } void __sk_flush_backlog(struct sock *sk) { spin_lock_bh(&sk->sk_lock.slock); __release_sock(sk); spin_unlock_bh(&sk->sk_lock.slock); } /** * sk_wait_data - wait for data to arrive at sk_receive_queue * @sk: sock to wait on * @timeo: for how long * @skb: last skb seen on sk_receive_queue * * Now socket state including sk->sk_err is changed only under lock, * hence we may omit checks after joining wait queue. * We check receive queue before schedule() only as optimization; * it is very likely that release_sock() added new data. */ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb) { DEFINE_WAIT_FUNC(wait, woken_wake_function); int rc; add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb, &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); return rc; } EXPORT_SYMBOL(sk_wait_data); /** * __sk_mem_raise_allocated - increase memory_allocated * @sk: socket * @size: memory size to allocate * @amt: pages to allocate * @kind: allocation type * * Similar to __sk_mem_schedule(), but does not update sk_forward_alloc */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { struct proto *prot = sk->sk_prot; long allocated = sk_memory_allocated_add(sk, amt); bool memcg_charge = mem_cgroup_sockets_enabled && sk->sk_memcg; bool charged = true; if (memcg_charge && !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt, gfp_memcg_charge()))) goto suppress_allocation; /* Under limit. */ if (allocated <= sk_prot_mem_limits(sk, 0)) { sk_leave_memory_pressure(sk); return 1; } /* Under pressure. */ if (allocated > sk_prot_mem_limits(sk, 1)) sk_enter_memory_pressure(sk); /* Over hard limit. */ if (allocated > sk_prot_mem_limits(sk, 2)) goto suppress_allocation; /* guarantee minimum buffer size under pressure */ if (kind == SK_MEM_RECV) { if (atomic_read(&sk->sk_rmem_alloc) < sk_get_rmem0(sk, prot)) return 1; } else { /* SK_MEM_SEND */ int wmem0 = sk_get_wmem0(sk, prot); if (sk->sk_type == SOCK_STREAM) { if (sk->sk_wmem_queued < wmem0) return 1; } else if (refcount_read(&sk->sk_wmem_alloc) < wmem0) { return 1; } } if (sk_has_memory_pressure(sk)) { u64 alloc; if (!sk_under_memory_pressure(sk)) return 1; alloc = sk_sockets_allocated_read_positive(sk); if (sk_prot_mem_limits(sk, 2) > alloc * sk_mem_pages(sk->sk_wmem_queued + atomic_read(&sk->sk_rmem_alloc) + sk->sk_forward_alloc)) return 1; } suppress_allocation: if (kind == SK_MEM_SEND && sk->sk_type == SOCK_STREAM) { sk_stream_moderate_sndbuf(sk); /* Fail only if socket is _under_ its sndbuf. * In this case we cannot block, so that we have to fail. */ if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) { /* Force charge with __GFP_NOFAIL */ if (memcg_charge && !charged) { mem_cgroup_charge_skmem(sk->sk_memcg, amt, gfp_memcg_charge() | __GFP_NOFAIL); } return 1; } } if (kind == SK_MEM_SEND || (kind == SK_MEM_RECV && charged)) trace_sock_exceed_buf_limit(sk, prot, allocated, kind); sk_memory_allocated_sub(sk, amt); if (memcg_charge && charged) mem_cgroup_uncharge_skmem(sk->sk_memcg, amt); return 0; } EXPORT_SYMBOL(__sk_mem_raise_allocated); /** * __sk_mem_schedule - increase sk_forward_alloc and memory_allocated * @sk: socket * @size: memory size to allocate * @kind: allocation type * * If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means * rmem allocation. This function assumes that protocols which have * memory_pressure use sk_wmem_queued as write buffer accounting. */ int __sk_mem_schedule(struct sock *sk, int size, int kind) { int ret, amt = sk_mem_pages(size); sk->sk_forward_alloc += amt << SK_MEM_QUANTUM_SHIFT; ret = __sk_mem_raise_allocated(sk, size, amt, kind); if (!ret) sk->sk_forward_alloc -= amt << SK_MEM_QUANTUM_SHIFT; return ret; } EXPORT_SYMBOL(__sk_mem_schedule); /** * __sk_mem_reduce_allocated - reclaim memory_allocated * @sk: socket * @amount: number of quanta * * Similar to __sk_mem_reclaim(), but does not update sk_forward_alloc */ void __sk_mem_reduce_allocated(struct sock *sk, int amount) { sk_memory_allocated_sub(sk, amount); if (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_uncharge_skmem(sk->sk_memcg, amount); if (sk_under_global_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); } EXPORT_SYMBOL(__sk_mem_reduce_allocated); /** * __sk_mem_reclaim - reclaim sk_forward_alloc and memory_allocated * @sk: socket * @amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple) */ void __sk_mem_reclaim(struct sock *sk, int amount) { amount >>= SK_MEM_QUANTUM_SHIFT; sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT; __sk_mem_reduce_allocated(sk, amount); } EXPORT_SYMBOL(__sk_mem_reclaim); int sk_set_peek_off(struct sock *sk, int val) { WRITE_ONCE(sk->sk_peek_off, val); return 0; } EXPORT_SYMBOL_GPL(sk_set_peek_off); /* * Set of default routines for initialising struct proto_ops when * the protocol does not support a particular function. In certain * cases where it makes no sense for a protocol to have a "do nothing" * function, some default processing is provided. */ int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_bind); int sock_no_connect(struct socket *sock, struct sockaddr *saddr, int len, int flags) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_connect); int sock_no_socketpair(struct socket *sock1, struct socket *sock2) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_socketpair); int sock_no_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_accept); int sock_no_getname(struct socket *sock, struct sockaddr *saddr, int peer) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_getname); int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_ioctl); int sock_no_listen(struct socket *sock, int backlog) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_listen); int sock_no_shutdown(struct socket *sock, int how) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_shutdown); int sock_no_sendmsg(struct socket *sock, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_sendmsg); int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_sendmsg_locked); int sock_no_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_recvmsg); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { /* Mirror missing mmap method error code */ return -ENODEV; } EXPORT_SYMBOL(sock_no_mmap); /* * When a file is received (via SCM_RIGHTS, etc), we must bump the * various sock-based usage counts. */ void __receive_sock(struct file *file) { struct socket *sock; sock = sock_from_file(file); if (sock) { sock_update_netprioidx(&sock->sk->sk_cgrp_data); sock_update_classid(&sock->sk->sk_cgrp_data); } } ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { ssize_t res; struct msghdr msg = {.msg_flags = flags}; struct kvec iov; char *kaddr = kmap(page); iov.iov_base = kaddr + offset; iov.iov_len = size; res = kernel_sendmsg(sock, &msg, &iov, 1, size); kunmap(page); return res; } EXPORT_SYMBOL(sock_no_sendpage); ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { ssize_t res; struct msghdr msg = {.msg_flags = flags}; struct kvec iov; char *kaddr = kmap(page); iov.iov_base = kaddr + offset; iov.iov_len = size; res = kernel_sendmsg_locked(sk, &msg, &iov, 1, size); kunmap(page); return res; } EXPORT_SYMBOL(sock_no_sendpage_locked); /* * Default Socket Callbacks */ static void sock_def_wakeup(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_all(&wq->wait); rcu_read_unlock(); } static void sock_def_error_report(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_poll(&wq->wait, EPOLLERR); sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); rcu_read_unlock(); } void sock_def_readable(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) { int done = 0; trace_android_vh_do_wake_up_sync(&wq->wait, &done); if (done) goto out; wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI | EPOLLRDNORM | EPOLLRDBAND); } out: sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } static void sock_def_write_space(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } static void sock_def_destruct(struct sock *sk) { } void sk_send_sigurg(struct sock *sk) { if (sk->sk_socket && sk->sk_socket->file) if (send_sigurg(&sk->sk_socket->file->f_owner)) sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI); } EXPORT_SYMBOL(sk_send_sigurg); void sk_reset_timer(struct sock *sk, struct timer_list* timer, unsigned long expires) { if (!mod_timer(timer, expires)) sock_hold(sk); } EXPORT_SYMBOL(sk_reset_timer); void sk_stop_timer(struct sock *sk, struct timer_list* timer) { if (del_timer(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer); void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer) { if (del_timer_sync(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer_sync); void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid) { sk_init_common(sk); sk->sk_send_head = NULL; timer_setup(&sk->sk_timer, NULL, 0); sk->sk_allocation = GFP_KERNEL; sk->sk_rcvbuf = READ_ONCE(sysctl_rmem_default); sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); sk->sk_state = TCP_CLOSE; sk_set_socket(sk, sock); sock_set_flag(sk, SOCK_ZAPPED); if (sock) { sk->sk_type = sock->type; RCU_INIT_POINTER(sk->sk_wq, &sock->wq); sock->sk = sk; } else { RCU_INIT_POINTER(sk->sk_wq, NULL); } sk->sk_uid = uid; rwlock_init(&sk->sk_callback_lock); if (sk->sk_kern_sock) lockdep_set_class_and_name( &sk->sk_callback_lock, af_kern_callback_keys + sk->sk_family, af_family_kern_clock_key_strings[sk->sk_family]); else lockdep_set_class_and_name( &sk->sk_callback_lock, af_callback_keys + sk->sk_family, af_family_clock_key_strings[sk->sk_family]); sk->sk_state_change = sock_def_wakeup; sk->sk_data_ready = sock_def_readable; sk->sk_write_space = sock_def_write_space; sk->sk_error_report = sock_def_error_report; sk->sk_destruct = sock_def_destruct; sk->sk_frag.page = NULL; sk->sk_frag.offset = 0; sk->sk_peek_off = -1; sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; spin_lock_init(&sk->sk_peer_lock); sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_stamp = SK_DEFAULT_STAMP; #if BITS_PER_LONG==32 seqlock_init(&sk->sk_stamp_seq); #endif atomic_set(&sk->sk_zckey, 0); #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; sk->sk_ll_usec = READ_ONCE(sysctl_net_busy_read); #endif sk->sk_max_pacing_rate = ~0UL; sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; sk_rx_queue_clear(sk); /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.rst for details) */ smp_wmb(); refcount_set(&sk->sk_refcnt, 1); atomic_set(&sk->sk_drops, 0); } EXPORT_SYMBOL(sock_init_data_uid); void sock_init_data(struct socket *sock, struct sock *sk) { kuid_t uid = sock ? SOCK_INODE(sock)->i_uid : make_kuid(sock_net(sk)->user_ns, 0); sock_init_data_uid(sock, sk, uid); } EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) { /* The sk_lock has mutex_lock() semantics here. */ mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); might_sleep(); spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_lock.owned) __lock_sock(sk); sk->sk_lock.owned = 1; spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(lock_sock_nested); void release_sock(struct sock *sk) { spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_backlog.tail) __release_sock(sk); /* Warning : release_cb() might need to release sk ownership, * ie call sock_release_ownership(sk) before us. */ if (sk->sk_prot->release_cb) sk->sk_prot->release_cb(sk); sock_release_ownership(sk); if (waitqueue_active(&sk->sk_lock.wq)) wake_up(&sk->sk_lock.wq); spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(release_sock); bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) { might_sleep(); spin_lock_bh(&sk->sk_lock.slock); if (!sk->sk_lock.owned) { /* * Fast path return with bottom halves disabled and * sock::sk_lock.slock held. * * The 'mutex' is not contended and holding * sock::sk_lock.slock prevents all other lockers to * proceed so the corresponding unlock_sock_fast() can * avoid the slow path of release_sock() completely and * just release slock. * * From a semantical POV this is equivalent to 'acquiring' * the 'mutex', hence the corresponding lockdep * mutex_release() has to happen in the fast path of * unlock_sock_fast(). */ return false; } __lock_sock(sk); sk->sk_lock.owned = 1; __acquire(&sk->sk_lock.slock); spin_unlock_bh(&sk->sk_lock.slock); return true; } EXPORT_SYMBOL(__lock_sock_fast); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32) { struct sock *sk = sock->sk; struct timespec64 ts; sock_enable_timestamp(sk, SOCK_TIMESTAMP); ts = ktime_to_timespec64(sock_read_timestamp(sk)); if (ts.tv_sec == -1) return -ENOENT; if (ts.tv_sec == 0) { ktime_t kt = ktime_get_real(); sock_write_timestamp(sk, kt); ts = ktime_to_timespec64(kt); } if (timeval) ts.tv_nsec /= 1000; #ifdef CONFIG_COMPAT_32BIT_TIME if (time32) return put_old_timespec32(&ts, userstamp); #endif #ifdef CONFIG_SPARC64 /* beware of padding in sparc64 timeval */ if (timeval && !in_compat_syscall()) { struct __kernel_old_timeval __user tv = { .tv_sec = ts.tv_sec, .tv_usec = ts.tv_nsec, }; if (copy_to_user(userstamp, &tv, sizeof(tv))) return -EFAULT; return 0; } #endif return put_timespec64(&ts, userstamp); } EXPORT_SYMBOL(sock_gettstamp); void sock_enable_timestamp(struct sock *sk, enum sock_flags flag) { if (!sock_flag(sk, flag)) { unsigned long previous_flags = sk->sk_flags; sock_set_flag(sk, flag); /* * we just set one of the two flags which require net * time stamping, but time stamping might have been on * already because of the other one */ if (sock_needs_netstamp(sk) && !(previous_flags & SK_FLAGS_TIMESTAMP)) net_enable_timestamp(); } } int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type) { struct sock_exterr_skb *serr; struct sk_buff *skb; int copied, err; err = -EAGAIN; skb = sock_dequeue_err_skb(sk); if (skb == NULL) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free_skb; sock_recv_timestamp(msg, sk, skb); serr = SKB_EXT_ERR(skb); put_cmsg(msg, level, type, sizeof(serr->ee), &serr->ee); msg->msg_flags |= MSG_ERRQUEUE; err = copied; out_free_skb: kfree_skb(skb); out: return err; } EXPORT_SYMBOL(sock_recv_errqueue); /* * Get a socket option on an socket. * * FIX: POSIX 1003.1g is very ambiguous here. It states that * asynchronous errors should be reported by getsockopt. We assume * this means if you specify SO_ERROR (otherwise whats the point of it). */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_common_getsockopt); int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; int addr_len = 0; int err; err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT, flags & ~MSG_DONTWAIT, &addr_len); if (err >= 0) msg->msg_namelen = addr_len; return err; } EXPORT_SYMBOL(sock_common_recvmsg); /* * Set socket options on an inet socket. */ int sock_common_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_common_setsockopt); void sk_common_release(struct sock *sk) { if (sk->sk_prot->destroy) sk->sk_prot->destroy(sk); /* * Observation: when sk_common_release is called, processes have * no access to socket. But net still has. * Step one, detach it from networking: * * A. Remove from hash tables. */ sk->sk_prot->unhash(sk); if (sk->sk_socket) sk->sk_socket->sk = NULL; /* * In this point socket cannot receive new packets, but it is possible * that some packets are in flight because some CPU runs receiver and * did hash table lookup before we unhashed socket. They will achieve * receive queue and will be purged by socket destructor. * * Also we still have packets pending on receive queue and probably, * our own packets waiting in device queues. sock_destroy will drain * receive queue, but transmitted packets will delay socket destruction * until the last reference will be released. */ sock_orphan(sk); xfrm_sk_free_policy(sk); sk_refcnt_debug_release(sk); sock_put(sk); } EXPORT_SYMBOL(sk_common_release); void sk_get_meminfo(const struct sock *sk, u32 *mem) { memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS); mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf); mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf); mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued); mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); } #ifdef CONFIG_PROC_FS #define PROTO_INUSE_NR 64 /* should be enough for the first time */ struct prot_inuse { int val[PROTO_INUSE_NR]; }; static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR); void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) { __this_cpu_add(net->core.prot_inuse->val[prot->inuse_idx], val); } EXPORT_SYMBOL_GPL(sock_prot_inuse_add); int sock_prot_inuse_get(struct net *net, struct proto *prot) { int cpu, idx = prot->inuse_idx; int res = 0; for_each_possible_cpu(cpu) res += per_cpu_ptr(net->core.prot_inuse, cpu)->val[idx]; return res >= 0 ? res : 0; } EXPORT_SYMBOL_GPL(sock_prot_inuse_get); int sock_inuse_get(struct net *net) { int cpu, res = 0; for_each_possible_cpu(cpu) res += *per_cpu_ptr(net->core.sock_inuse, cpu); return res; } EXPORT_SYMBOL_GPL(sock_inuse_get); static int __net_init sock_inuse_init_net(struct net *net) { net->core.prot_inuse = alloc_percpu(struct prot_inuse); if (net->core.prot_inuse == NULL) return -ENOMEM; net->core.sock_inuse = alloc_percpu(int); if (net->core.sock_inuse == NULL) goto out; return 0; out: free_percpu(net->core.prot_inuse); return -ENOMEM; } static void __net_exit sock_inuse_exit_net(struct net *net) { free_percpu(net->core.prot_inuse); free_percpu(net->core.sock_inuse); } static struct pernet_operations net_inuse_ops = { .init = sock_inuse_init_net, .exit = sock_inuse_exit_net, }; static __init int net_inuse_init(void) { if (register_pernet_subsys(&net_inuse_ops)) panic("Cannot initialize net inuse counters"); return 0; } core_initcall(net_inuse_init); static int assign_proto_idx(struct proto *prot) { prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR); if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) { pr_err("PROTO_INUSE_NR exhausted\n"); return -ENOSPC; } set_bit(prot->inuse_idx, proto_inuse_idx); return 0; } static void release_proto_idx(struct proto *prot) { if (prot->inuse_idx != PROTO_INUSE_NR - 1) clear_bit(prot->inuse_idx, proto_inuse_idx); } #else static inline int assign_proto_idx(struct proto *prot) { return 0; } static inline void release_proto_idx(struct proto *prot) { } #endif static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot) { if (!twsk_prot) return; kfree(twsk_prot->twsk_slab_name); twsk_prot->twsk_slab_name = NULL; kmem_cache_destroy(twsk_prot->twsk_slab); twsk_prot->twsk_slab = NULL; } static int tw_prot_init(const struct proto *prot) { struct timewait_sock_ops *twsk_prot = prot->twsk_prot; if (!twsk_prot) return 0; twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name); if (!twsk_prot->twsk_slab_name) return -ENOMEM; twsk_prot->twsk_slab = kmem_cache_create(twsk_prot->twsk_slab_name, twsk_prot->twsk_obj_size, 0, SLAB_ACCOUNT | prot->slab_flags, NULL); if (!twsk_prot->twsk_slab) { pr_crit("%s: Can't create timewait sock SLAB cache!\n", prot->name); return -ENOMEM; } return 0; } static void req_prot_cleanup(struct request_sock_ops *rsk_prot) { if (!rsk_prot) return; kfree(rsk_prot->slab_name); rsk_prot->slab_name = NULL; kmem_cache_destroy(rsk_prot->slab); rsk_prot->slab = NULL; } static int req_prot_init(const struct proto *prot) { struct request_sock_ops *rsk_prot = prot->rsk_prot; if (!rsk_prot) return 0; rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s", prot->name); if (!rsk_prot->slab_name) return -ENOMEM; rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name, rsk_prot->obj_size, 0, SLAB_ACCOUNT | prot->slab_flags, NULL); if (!rsk_prot->slab) { pr_crit("%s: Can't create request sock SLAB cache!\n", prot->name); return -ENOMEM; } return 0; } int proto_register(struct proto *prot, int alloc_slab) { int ret = -ENOBUFS; if (alloc_slab) { prot->slab = kmem_cache_create_usercopy(prot->name, prot->obj_size, 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT | prot->slab_flags, prot->useroffset, prot->usersize, NULL); if (prot->slab == NULL) { pr_crit("%s: Can't create sock SLAB cache!\n", prot->name); goto out; } if (req_prot_init(prot)) goto out_free_request_sock_slab; if (tw_prot_init(prot)) goto out_free_timewait_sock_slab; } mutex_lock(&proto_list_mutex); ret = assign_proto_idx(prot); if (ret) { mutex_unlock(&proto_list_mutex); goto out_free_timewait_sock_slab; } list_add(&prot->node, &proto_list); mutex_unlock(&proto_list_mutex); return ret; out_free_timewait_sock_slab: if (alloc_slab) tw_prot_cleanup(prot->twsk_prot); out_free_request_sock_slab: if (alloc_slab) { req_prot_cleanup(prot->rsk_prot); kmem_cache_destroy(prot->slab); prot->slab = NULL; } out: return ret; } EXPORT_SYMBOL(proto_register); void proto_unregister(struct proto *prot) { mutex_lock(&proto_list_mutex); release_proto_idx(prot); list_del(&prot->node); mutex_unlock(&proto_list_mutex); kmem_cache_destroy(prot->slab); prot->slab = NULL; req_prot_cleanup(prot->rsk_prot); tw_prot_cleanup(prot->twsk_prot); } EXPORT_SYMBOL(proto_unregister); int sock_load_diag_module(int family, int protocol) { if (!protocol) { if (!sock_is_registered(family)) return -ENOENT; return request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, NETLINK_SOCK_DIAG, family); } #ifdef CONFIG_INET if (family == AF_INET && protocol != IPPROTO_RAW && protocol < MAX_INET_PROTOS && !rcu_access_pointer(inet_protos[protocol])) return -ENOENT; #endif return request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, NETLINK_SOCK_DIAG, family, protocol); } EXPORT_SYMBOL(sock_load_diag_module); #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) __acquires(proto_list_mutex) { mutex_lock(&proto_list_mutex); return seq_list_start_head(&proto_list, *pos); } static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &proto_list, pos); } static void proto_seq_stop(struct seq_file *seq, void *v) __releases(proto_list_mutex) { mutex_unlock(&proto_list_mutex); } static char proto_method_implemented(const void *method) { return method == NULL ? 'n' : 'y'; } static long sock_prot_memory_allocated(struct proto *proto) { return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L; } static const char *sock_prot_memory_pressure(struct proto *proto) { return proto->memory_pressure != NULL ? proto_memory_pressure(proto) ? "yes" : "no" : "NI"; } static void proto_seq_printf(struct seq_file *seq, struct proto *proto) { seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s " "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n", proto->name, proto->obj_size, sock_prot_inuse_get(seq_file_net(seq), proto), sock_prot_memory_allocated(proto), sock_prot_memory_pressure(proto), proto->max_header, proto->slab == NULL ? "no" : "yes", module_name(proto->owner), proto_method_implemented(proto->close), proto_method_implemented(proto->connect), proto_method_implemented(proto->disconnect), proto_method_implemented(proto->accept), proto_method_implemented(proto->ioctl), proto_method_implemented(proto->init), proto_method_implemented(proto->destroy), proto_method_implemented(proto->shutdown), proto_method_implemented(proto->setsockopt), proto_method_implemented(proto->getsockopt), proto_method_implemented(proto->sendmsg), proto_method_implemented(proto->recvmsg), proto_method_implemented(proto->sendpage), proto_method_implemented(proto->bind), proto_method_implemented(proto->backlog_rcv), proto_method_implemented(proto->hash), proto_method_implemented(proto->unhash), proto_method_implemented(proto->get_port), proto_method_implemented(proto->enter_memory_pressure)); } static int proto_seq_show(struct seq_file *seq, void *v) { if (v == &proto_list) seq_printf(seq, "%-9s %-4s %-8s %-6s %-5s %-7s %-4s %-10s %s", "protocol", "size", "sockets", "memory", "press", "maxhdr", "slab", "module", "cl co di ac io in de sh ss gs se re sp bi br ha uh gp em\n"); else proto_seq_printf(seq, list_entry(v, struct proto, node)); return 0; } static const struct seq_operations proto_seq_ops = { .start = proto_seq_start, .next = proto_seq_next, .stop = proto_seq_stop, .show = proto_seq_show, }; static __net_init int proto_init_net(struct net *net) { if (!proc_create_net("protocols", 0444, net->proc_net, &proto_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } static __net_exit void proto_exit_net(struct net *net) { remove_proc_entry("protocols", net->proc_net); } static __net_initdata struct pernet_operations proto_net_ops = { .init = proto_init_net, .exit = proto_exit_net, }; static int __init proto_init(void) { return register_pernet_subsys(&proto_net_ops); } subsys_initcall(proto_init); #endif /* PROC_FS */ #ifdef CONFIG_NET_RX_BUSY_POLL bool sk_busy_loop_end(void *p, unsigned long start_time) { struct sock *sk = p; return !skb_queue_empty_lockless(&sk->sk_receive_queue) || sk_busy_loop_timeout(sk, start_time); } EXPORT_SYMBOL(sk_busy_loop_end); #endif /* CONFIG_NET_RX_BUSY_POLL */ int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len) { if (!sk->sk_prot->bind_add) return -EOPNOTSUPP; return sk->sk_prot->bind_add(sk, addr, addr_len); } EXPORT_SYMBOL(sock_bind_add); |
| 750 750 750 750 750 750 1986 1986 1986 541 541 541 3353 3359 3216 1934 1934 61 61 61 481 481 750 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 | // SPDX-License-Identifier: GPL-2.0-only /* * net/core/fib_rules.c Generic Routing Rules * * Authors: Thomas Graf <tgraf@suug.ch> */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/module.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/fib_rules.h> #include <net/ip_tunnels.h> #include <linux/indirect_call_wrapper.h> #if defined(CONFIG_IPV6) && defined(CONFIG_IPV6_MULTIPLE_TABLES) #ifdef CONFIG_IP_MULTIPLE_TABLES #define INDIRECT_CALL_MT(f, f2, f1, ...) \ INDIRECT_CALL_INET(f, f2, f1, __VA_ARGS__) #else #define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__) #endif #elif defined(CONFIG_IP_MULTIPLE_TABLES) #define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) #else #define INDIRECT_CALL_MT(f, f2, f1, ...) f(__VA_ARGS__) #endif static const struct fib_kuid_range fib_kuid_range_unset = { KUIDT_INIT(0), KUIDT_INIT(~0), }; bool fib_rule_matchall(const struct fib_rule *rule) { if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id || rule->flags) return false; if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1) return false; if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) || !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end)) return false; if (fib_rule_port_range_set(&rule->sport_range)) return false; if (fib_rule_port_range_set(&rule->dport_range)) return false; return true; } EXPORT_SYMBOL_GPL(fib_rule_matchall); int fib_default_rule_add(struct fib_rules_ops *ops, u32 pref, u32 table, u32 flags) { struct fib_rule *r; r = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); if (r == NULL) return -ENOMEM; refcount_set(&r->refcnt, 1); r->action = FR_ACT_TO_TBL; r->pref = pref; r->table = table; r->flags = flags; r->proto = RTPROT_KERNEL; r->fr_net = ops->fro_net; r->uid_range = fib_kuid_range_unset; r->suppress_prefixlen = -1; r->suppress_ifgroup = -1; /* The lock is not required here, the list in unreacheable * at the moment this function is called */ list_add_tail(&r->list, &ops->rules_list); return 0; } EXPORT_SYMBOL(fib_default_rule_add); static u32 fib_default_rule_pref(struct fib_rules_ops *ops) { struct list_head *pos; struct fib_rule *rule; if (!list_empty(&ops->rules_list)) { pos = ops->rules_list.next; if (pos->next != &ops->rules_list) { rule = list_entry(pos->next, struct fib_rule, list); if (rule->pref) return rule->pref - 1; } } return 0; } static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid); static struct fib_rules_ops *lookup_rules_ops(struct net *net, int family) { struct fib_rules_ops *ops; rcu_read_lock(); list_for_each_entry_rcu(ops, &net->rules_ops, list) { if (ops->family == family) { if (!try_module_get(ops->owner)) ops = NULL; rcu_read_unlock(); return ops; } } rcu_read_unlock(); return NULL; } static void rules_ops_put(struct fib_rules_ops *ops) { if (ops) module_put(ops->owner); } static void flush_route_cache(struct fib_rules_ops *ops) { if (ops->flush_cache) ops->flush_cache(ops); } static int __fib_rules_register(struct fib_rules_ops *ops) { int err = -EEXIST; struct fib_rules_ops *o; struct net *net; net = ops->fro_net; if (ops->rule_size < sizeof(struct fib_rule)) return -EINVAL; if (ops->match == NULL || ops->configure == NULL || ops->compare == NULL || ops->fill == NULL || ops->action == NULL) return -EINVAL; spin_lock(&net->rules_mod_lock); list_for_each_entry(o, &net->rules_ops, list) if (ops->family == o->family) goto errout; list_add_tail_rcu(&ops->list, &net->rules_ops); err = 0; errout: spin_unlock(&net->rules_mod_lock); return err; } struct fib_rules_ops * fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net) { struct fib_rules_ops *ops; int err; ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL); if (ops == NULL) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&ops->rules_list); ops->fro_net = net; err = __fib_rules_register(ops); if (err) { kfree(ops); ops = ERR_PTR(err); } return ops; } EXPORT_SYMBOL_GPL(fib_rules_register); static void fib_rules_cleanup_ops(struct fib_rules_ops *ops) { struct fib_rule *rule, *tmp; list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) { list_del_rcu(&rule->list); if (ops->delete) ops->delete(rule); fib_rule_put(rule); } } void fib_rules_unregister(struct fib_rules_ops *ops) { struct net *net = ops->fro_net; spin_lock(&net->rules_mod_lock); list_del_rcu(&ops->list); spin_unlock(&net->rules_mod_lock); fib_rules_cleanup_ops(ops); kfree_rcu(ops, rcu); } EXPORT_SYMBOL_GPL(fib_rules_unregister); static int uid_range_set(struct fib_kuid_range *range) { return uid_valid(range->start) && uid_valid(range->end); } static struct fib_kuid_range nla_get_kuid_range(struct nlattr **tb) { struct fib_rule_uid_range *in; struct fib_kuid_range out; in = (struct fib_rule_uid_range *)nla_data(tb[FRA_UID_RANGE]); out.start = make_kuid(current_user_ns(), in->start); out.end = make_kuid(current_user_ns(), in->end); return out; } static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range) { struct fib_rule_uid_range out = { from_kuid_munged(current_user_ns(), range->start), from_kuid_munged(current_user_ns(), range->end) }; return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out); } static int nla_get_port_range(struct nlattr *pattr, struct fib_rule_port_range *port_range) { const struct fib_rule_port_range *pr = nla_data(pattr); if (!fib_rule_port_range_valid(pr)) return -EINVAL; port_range->start = pr->start; port_range->end = pr->end; return 0; } static int nla_put_port_range(struct sk_buff *skb, int attrtype, struct fib_rule_port_range *range) { return nla_put(skb, attrtype, sizeof(*range), range); } static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg) { int ret = 0; if (rule->iifindex && (rule->iifindex != fl->flowi_iif)) goto out; if (rule->oifindex && (rule->oifindex != fl->flowi_oif)) goto out; if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask) goto out; if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id)) goto out; if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg)) goto out; if (uid_lt(fl->flowi_uid, rule->uid_range.start) || uid_gt(fl->flowi_uid, rule->uid_range.end)) goto out; ret = INDIRECT_CALL_MT(ops->match, fib6_rule_match, fib4_rule_match, rule, fl, flags); out: return (rule->flags & FIB_RULE_INVERT) ? !ret : ret; } int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg) { struct fib_rule *rule; int err; rcu_read_lock(); list_for_each_entry_rcu(rule, &ops->rules_list, list) { jumped: if (!fib_rule_match(rule, ops, fl, flags, arg)) continue; if (rule->action == FR_ACT_GOTO) { struct fib_rule *target; target = rcu_dereference(rule->ctarget); if (target == NULL) { continue; } else { rule = target; goto jumped; } } else if (rule->action == FR_ACT_NOP) continue; else err = INDIRECT_CALL_MT(ops->action, fib6_rule_action, fib4_rule_action, rule, fl, flags, arg); if (!err && ops->suppress && INDIRECT_CALL_MT(ops->suppress, fib6_rule_suppress, fib4_rule_suppress, rule, flags, arg)) continue; if (err != -EAGAIN) { if ((arg->flags & FIB_LOOKUP_NOREF) || likely(refcount_inc_not_zero(&rule->refcnt))) { arg->rule = rule; goto out; } break; } } err = -ESRCH; out: rcu_read_unlock(); return err; } EXPORT_SYMBOL_GPL(fib_rules_lookup); static int call_fib_rule_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_rule *rule, int family, struct netlink_ext_ack *extack) { struct fib_rule_notifier_info info = { .info.family = family, .info.extack = extack, .rule = rule, }; return call_fib_notifier(nb, event_type, &info.info); } static int call_fib_rule_notifiers(struct net *net, enum fib_event_type event_type, struct fib_rule *rule, struct fib_rules_ops *ops, struct netlink_ext_ack *extack) { struct fib_rule_notifier_info info = { .info.family = ops->family, .info.extack = extack, .rule = rule, }; ops->fib_rules_seq++; return call_fib_notifiers(net, event_type, &info.info); } /* Called with rcu_read_lock() */ int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, struct netlink_ext_ack *extack) { struct fib_rules_ops *ops; struct fib_rule *rule; int err = 0; ops = lookup_rules_ops(net, family); if (!ops) return -EAFNOSUPPORT; list_for_each_entry_rcu(rule, &ops->rules_list, list) { err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD, rule, family, extack); if (err) break; } rules_ops_put(ops); return err; } EXPORT_SYMBOL_GPL(fib_rules_dump); unsigned int fib_rules_seq_read(struct net *net, int family) { unsigned int fib_rules_seq; struct fib_rules_ops *ops; ASSERT_RTNL(); ops = lookup_rules_ops(net, family); if (!ops) return 0; fib_rules_seq = ops->fib_rules_seq; rules_ops_put(ops); return fib_rules_seq; } EXPORT_SYMBOL_GPL(fib_rules_seq_read); static struct fib_rule *rule_find(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, struct nlattr **tb, struct fib_rule *rule, bool user_priority) { struct fib_rule *r; list_for_each_entry(r, &ops->rules_list, list) { if (rule->action && r->action != rule->action) continue; if (rule->table && r->table != rule->table) continue; if (user_priority && r->pref != rule->pref) continue; if (rule->iifname[0] && memcmp(r->iifname, rule->iifname, IFNAMSIZ)) continue; if (rule->oifname[0] && memcmp(r->oifname, rule->oifname, IFNAMSIZ)) continue; if (rule->mark && r->mark != rule->mark) continue; if (rule->suppress_ifgroup != -1 && r->suppress_ifgroup != rule->suppress_ifgroup) continue; if (rule->suppress_prefixlen != -1 && r->suppress_prefixlen != rule->suppress_prefixlen) continue; if (rule->mark_mask && r->mark_mask != rule->mark_mask) continue; if (rule->tun_id && r->tun_id != rule->tun_id) continue; if (r->fr_net != rule->fr_net) continue; if (rule->l3mdev && r->l3mdev != rule->l3mdev) continue; if (uid_range_set(&rule->uid_range) && (!uid_eq(r->uid_range.start, rule->uid_range.start) || !uid_eq(r->uid_range.end, rule->uid_range.end))) continue; if (rule->ip_proto && r->ip_proto != rule->ip_proto) continue; if (rule->proto && r->proto != rule->proto) continue; if (fib_rule_port_range_set(&rule->sport_range) && !fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) continue; if (fib_rule_port_range_set(&rule->dport_range) && !fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; if (!ops->compare(r, frh, tb)) continue; return r; } return NULL; } #ifdef CONFIG_NET_L3_MASTER_DEV static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, struct netlink_ext_ack *extack) { nlrule->l3mdev = nla_get_u8(nla); if (nlrule->l3mdev != 1) { NL_SET_ERR_MSG(extack, "Invalid l3mdev attribute"); return -1; } return 0; } #else static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "l3mdev support is not enabled in kernel"); return -1; } #endif static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, struct fib_rules_ops *ops, struct nlattr *tb[], struct fib_rule **rule, bool *user_priority) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rule *nlrule = NULL; int err = -EINVAL; if (frh->src_len) if (!tb[FRA_SRC] || frh->src_len > (ops->addr_size * 8) || nla_len(tb[FRA_SRC]) != ops->addr_size) { NL_SET_ERR_MSG(extack, "Invalid source address"); goto errout; } if (frh->dst_len) if (!tb[FRA_DST] || frh->dst_len > (ops->addr_size * 8) || nla_len(tb[FRA_DST]) != ops->addr_size) { NL_SET_ERR_MSG(extack, "Invalid dst address"); goto errout; } nlrule = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); if (!nlrule) { err = -ENOMEM; goto errout; } refcount_set(&nlrule->refcnt, 1); nlrule->fr_net = net; if (tb[FRA_PRIORITY]) { nlrule->pref = nla_get_u32(tb[FRA_PRIORITY]); *user_priority = true; } else { nlrule->pref = fib_default_rule_pref(ops); } nlrule->proto = tb[FRA_PROTOCOL] ? nla_get_u8(tb[FRA_PROTOCOL]) : RTPROT_UNSPEC; if (tb[FRA_IIFNAME]) { struct net_device *dev; nlrule->iifindex = -1; nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); dev = __dev_get_by_name(net, nlrule->iifname); if (dev) nlrule->iifindex = dev->ifindex; } if (tb[FRA_OIFNAME]) { struct net_device *dev; nlrule->oifindex = -1; nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); dev = __dev_get_by_name(net, nlrule->oifname); if (dev) nlrule->oifindex = dev->ifindex; } if (tb[FRA_FWMARK]) { nlrule->mark = nla_get_u32(tb[FRA_FWMARK]); if (nlrule->mark) /* compatibility: if the mark value is non-zero all bits * are compared unless a mask is explicitly specified. */ nlrule->mark_mask = 0xFFFFFFFF; } if (tb[FRA_FWMASK]) nlrule->mark_mask = nla_get_u32(tb[FRA_FWMASK]); if (tb[FRA_TUN_ID]) nlrule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); err = -EINVAL; if (tb[FRA_L3MDEV] && fib_nl2rule_l3mdev(tb[FRA_L3MDEV], nlrule, extack) < 0) goto errout_free; nlrule->action = frh->action; nlrule->flags = frh->flags; nlrule->table = frh_get_table(frh, tb); if (tb[FRA_SUPPRESS_PREFIXLEN]) nlrule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); else nlrule->suppress_prefixlen = -1; if (tb[FRA_SUPPRESS_IFGROUP]) nlrule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); else nlrule->suppress_ifgroup = -1; if (tb[FRA_GOTO]) { if (nlrule->action != FR_ACT_GOTO) { NL_SET_ERR_MSG(extack, "Unexpected goto"); goto errout_free; } nlrule->target = nla_get_u32(tb[FRA_GOTO]); /* Backward jumps are prohibited to avoid endless loops */ if (nlrule->target <= nlrule->pref) { NL_SET_ERR_MSG(extack, "Backward goto not supported"); goto errout_free; } } else if (nlrule->action == FR_ACT_GOTO) { NL_SET_ERR_MSG(extack, "Missing goto target for action goto"); goto errout_free; } if (nlrule->l3mdev && nlrule->table) { NL_SET_ERR_MSG(extack, "l3mdev and table are mutually exclusive"); goto errout_free; } if (tb[FRA_UID_RANGE]) { if (current_user_ns() != net->user_ns) { err = -EPERM; NL_SET_ERR_MSG(extack, "No permission to set uid"); goto errout_free; } nlrule->uid_range = nla_get_kuid_range(tb); if (!uid_range_set(&nlrule->uid_range) || !uid_lte(nlrule->uid_range.start, nlrule->uid_range.end)) { NL_SET_ERR_MSG(extack, "Invalid uid range"); goto errout_free; } } else { nlrule->uid_range = fib_kuid_range_unset; } if (tb[FRA_IP_PROTO]) nlrule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]); if (tb[FRA_SPORT_RANGE]) { err = nla_get_port_range(tb[FRA_SPORT_RANGE], &nlrule->sport_range); if (err) { NL_SET_ERR_MSG(extack, "Invalid sport range"); goto errout_free; } } if (tb[FRA_DPORT_RANGE]) { err = nla_get_port_range(tb[FRA_DPORT_RANGE], &nlrule->dport_range); if (err) { NL_SET_ERR_MSG(extack, "Invalid dport range"); goto errout_free; } } *rule = nlrule; return 0; errout_free: kfree(nlrule); errout: return err; } static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, struct nlattr **tb, struct fib_rule *rule) { struct fib_rule *r; list_for_each_entry(r, &ops->rules_list, list) { if (r->action != rule->action) continue; if (r->table != rule->table) continue; if (r->pref != rule->pref) continue; if (memcmp(r->iifname, rule->iifname, IFNAMSIZ)) continue; if (memcmp(r->oifname, rule->oifname, IFNAMSIZ)) continue; if (r->mark != rule->mark) continue; if (r->suppress_ifgroup != rule->suppress_ifgroup) continue; if (r->suppress_prefixlen != rule->suppress_prefixlen) continue; if (r->mark_mask != rule->mark_mask) continue; if (r->tun_id != rule->tun_id) continue; if (r->fr_net != rule->fr_net) continue; if (r->l3mdev != rule->l3mdev) continue; if (!uid_eq(r->uid_range.start, rule->uid_range.start) || !uid_eq(r->uid_range.end, rule->uid_range.end)) continue; if (r->ip_proto != rule->ip_proto) continue; if (r->proto != rule->proto) continue; if (!fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) continue; if (!fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; if (!ops->compare(r, frh, tb)) continue; return 1; } return 0; } int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; struct fib_rule *rule = NULL, *r, *last = NULL; struct nlattr *tb[FRA_MAX + 1]; int err = -EINVAL, unresolved = 0; bool user_priority = false; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid msg length"); goto errout; } ops = lookup_rules_ops(net, frh->family); if (!ops) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Rule family not supported"); goto errout; } err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; } err = fib_nl2rule(skb, nlh, extack, ops, tb, &rule, &user_priority); if (err) goto errout; if ((nlh->nlmsg_flags & NLM_F_EXCL) && rule_exists(ops, frh, tb, rule)) { err = -EEXIST; goto errout_free; } err = ops->configure(rule, skb, frh, tb, extack); if (err < 0) goto errout_free; err = call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops, extack); if (err < 0) goto errout_free; list_for_each_entry(r, &ops->rules_list, list) { if (r->pref == rule->target) { RCU_INIT_POINTER(rule->ctarget, r); break; } } if (rcu_dereference_protected(rule->ctarget, 1) == NULL) unresolved = 1; list_for_each_entry(r, &ops->rules_list, list) { if (r->pref > rule->pref) break; last = r; } if (last) list_add_rcu(&rule->list, &last->list); else list_add_rcu(&rule->list, &ops->rules_list); if (ops->unresolved_rules) { /* * There are unresolved goto rules in the list, check if * any of them are pointing to this new rule. */ list_for_each_entry(r, &ops->rules_list, list) { if (r->action == FR_ACT_GOTO && r->target == rule->pref && rtnl_dereference(r->ctarget) == NULL) { rcu_assign_pointer(r->ctarget, rule); if (--ops->unresolved_rules == 0) break; } } } if (rule->action == FR_ACT_GOTO) ops->nr_goto_rules++; if (unresolved) ops->unresolved_rules++; if (rule->tun_id) ip_tunnel_need_metadata(); notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); flush_route_cache(ops); rules_ops_put(ops); return 0; errout_free: kfree(rule); errout: rules_ops_put(ops); return err; } EXPORT_SYMBOL_GPL(fib_nl_newrule); int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; struct fib_rule *rule = NULL, *r, *nlrule = NULL; struct nlattr *tb[FRA_MAX+1]; int err = -EINVAL; bool user_priority = false; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid msg length"); goto errout; } ops = lookup_rules_ops(net, frh->family); if (ops == NULL) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Rule family not supported"); goto errout; } err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; } err = fib_nl2rule(skb, nlh, extack, ops, tb, &nlrule, &user_priority); if (err) goto errout; rule = rule_find(ops, frh, tb, nlrule, user_priority); if (!rule) { err = -ENOENT; goto errout; } if (rule->flags & FIB_RULE_PERMANENT) { err = -EPERM; goto errout; } if (ops->delete) { err = ops->delete(rule); if (err) goto errout; } if (rule->tun_id) ip_tunnel_unneed_metadata(); list_del_rcu(&rule->list); if (rule->action == FR_ACT_GOTO) { ops->nr_goto_rules--; if (rtnl_dereference(rule->ctarget) == NULL) ops->unresolved_rules--; } /* * Check if this rule is a target to any of them. If so, * adjust to the next one with the same preference or * disable them. As this operation is eventually very * expensive, it is only performed if goto rules, except * current if it is goto rule, have actually been added. */ if (ops->nr_goto_rules > 0) { struct fib_rule *n; n = list_next_entry(rule, list); if (&n->list == &ops->rules_list || n->pref != rule->pref) n = NULL; list_for_each_entry(r, &ops->rules_list, list) { if (rtnl_dereference(r->ctarget) != rule) continue; rcu_assign_pointer(r->ctarget, n); if (!n) ops->unresolved_rules++; } } call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, NULL); notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).portid); fib_rule_put(rule); flush_route_cache(ops); rules_ops_put(ops); kfree(nlrule); return 0; errout: kfree(nlrule); rules_ops_put(ops); return err; } EXPORT_SYMBOL_GPL(fib_nl_delrule); static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, struct fib_rule *rule) { size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)) + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */ + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ + nla_total_size(4) /* FRA_PRIORITY */ + nla_total_size(4) /* FRA_TABLE */ + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */ + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ + nla_total_size(4) /* FRA_FWMARK */ + nla_total_size(4) /* FRA_FWMASK */ + nla_total_size_64bit(8) /* FRA_TUN_ID */ + nla_total_size(sizeof(struct fib_kuid_range)) + nla_total_size(1) /* FRA_PROTOCOL */ + nla_total_size(1) /* FRA_IP_PROTO */ + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_SPORT_RANGE */ + nla_total_size(sizeof(struct fib_rule_port_range)); /* FRA_DPORT_RANGE */ if (ops->nlmsg_payload) payload += ops->nlmsg_payload(rule); return payload; } static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, u32 pid, u32 seq, int type, int flags, struct fib_rules_ops *ops) { struct nlmsghdr *nlh; struct fib_rule_hdr *frh; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*frh), flags); if (nlh == NULL) return -EMSGSIZE; frh = nlmsg_data(nlh); frh->family = ops->family; frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) goto nla_put_failure; frh->res1 = 0; frh->res2 = 0; frh->action = rule->action; frh->flags = rule->flags; if (nla_put_u8(skb, FRA_PROTOCOL, rule->proto)) goto nla_put_failure; if (rule->action == FR_ACT_GOTO && rcu_access_pointer(rule->ctarget) == NULL) frh->flags |= FIB_RULE_UNRESOLVED; if (rule->iifname[0]) { if (nla_put_string(skb, FRA_IIFNAME, rule->iifname)) goto nla_put_failure; if (rule->iifindex == -1) frh->flags |= FIB_RULE_IIF_DETACHED; } if (rule->oifname[0]) { if (nla_put_string(skb, FRA_OIFNAME, rule->oifname)) goto nla_put_failure; if (rule->oifindex == -1) frh->flags |= FIB_RULE_OIF_DETACHED; } if ((rule->pref && nla_put_u32(skb, FRA_PRIORITY, rule->pref)) || (rule->mark && nla_put_u32(skb, FRA_FWMARK, rule->mark)) || ((rule->mark_mask || rule->mark) && nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) || (rule->target && nla_put_u32(skb, FRA_GOTO, rule->target)) || (rule->tun_id && nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) || (rule->l3mdev && nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) || (uid_range_set(&rule->uid_range) && nla_put_uid_range(skb, &rule->uid_range)) || (fib_rule_port_range_set(&rule->sport_range) && nla_put_port_range(skb, FRA_SPORT_RANGE, &rule->sport_range)) || (fib_rule_port_range_set(&rule->dport_range) && nla_put_port_range(skb, FRA_DPORT_RANGE, &rule->dport_range)) || (rule->ip_proto && nla_put_u8(skb, FRA_IP_PROTO, rule->ip_proto))) goto nla_put_failure; if (rule->suppress_ifgroup != -1) { if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup)) goto nla_put_failure; } if (ops->fill(rule, skb, frh) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, struct fib_rules_ops *ops) { int idx = 0; struct fib_rule *rule; int err = 0; rcu_read_lock(); list_for_each_entry_rcu(rule, &ops->rules_list, list) { if (idx < cb->args[1]) goto skip; err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWRULE, NLM_F_MULTI, ops); if (err) break; skip: idx++; } rcu_read_unlock(); cb->args[1] = idx; rules_ops_put(ops); return err; } static int fib_valid_dumprule_req(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib_rule_hdr *frh; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid header for fib rule dump request"); return -EINVAL; } frh = nlmsg_data(nlh); if (frh->dst_len || frh->src_len || frh->tos || frh->table || frh->res1 || frh->res2 || frh->action || frh->flags) { NL_SET_ERR_MSG(extack, "Invalid values in header for fib rule dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid data after header in fib rule dump request"); return -EINVAL; } return 0; } static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct fib_rules_ops *ops; int idx = 0, family; if (cb->strict_check) { int err = fib_valid_dumprule_req(nlh, cb->extack); if (err < 0) return err; } family = rtnl_msg_family(nlh); if (family != AF_UNSPEC) { /* Protocol specific dump request */ ops = lookup_rules_ops(net, family); if (ops == NULL) return -EAFNOSUPPORT; dump_rules(skb, cb, ops); return skb->len; } rcu_read_lock(); list_for_each_entry_rcu(ops, &net->rules_ops, list) { if (idx < cb->args[0] || !try_module_get(ops->owner)) goto skip; if (dump_rules(skb, cb, ops) < 0) break; cb->args[1] = 0; skip: idx++; } rcu_read_unlock(); cb->args[0] = idx; return skb->len; } static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid) { struct net *net; struct sk_buff *skb; int err = -ENOMEM; net = ops->fro_net; skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL); if (skb == NULL) goto errout; err = fib_nl_fill_rule(skb, rule, pid, nlh->nlmsg_seq, event, 0, ops); if (err < 0) { /* -EMSGSIZE implies BUG in fib_rule_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL); return; errout: if (err < 0) rtnl_set_sk_err(net, ops->nlgroup, err); } static void attach_rules(struct list_head *rules, struct net_device *dev) { struct fib_rule *rule; list_for_each_entry(rule, rules, list) { if (rule->iifindex == -1 && strcmp(dev->name, rule->iifname) == 0) rule->iifindex = dev->ifindex; if (rule->oifindex == -1 && strcmp(dev->name, rule->oifname) == 0) rule->oifindex = dev->ifindex; } } static void detach_rules(struct list_head *rules, struct net_device *dev) { struct fib_rule *rule; list_for_each_entry(rule, rules, list) { if (rule->iifindex == dev->ifindex) rule->iifindex = -1; if (rule->oifindex == dev->ifindex) rule->oifindex = -1; } } static int fib_rules_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct fib_rules_ops *ops; ASSERT_RTNL(); switch (event) { case NETDEV_REGISTER: list_for_each_entry(ops, &net->rules_ops, list) attach_rules(&ops->rules_list, dev); break; case NETDEV_CHANGENAME: list_for_each_entry(ops, &net->rules_ops, list) { detach_rules(&ops->rules_list, dev); attach_rules(&ops->rules_list, dev); } break; case NETDEV_UNREGISTER: list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); break; } return NOTIFY_DONE; } static struct notifier_block fib_rules_notifier = { .notifier_call = fib_rules_event, }; static int __net_init fib_rules_net_init(struct net *net) { INIT_LIST_HEAD(&net->rules_ops); spin_lock_init(&net->rules_mod_lock); return 0; } static void __net_exit fib_rules_net_exit(struct net *net) { WARN_ON_ONCE(!list_empty(&net->rules_ops)); } static struct pernet_operations fib_rules_net_ops = { .init = fib_rules_net_init, .exit = fib_rules_net_exit, }; static int __init fib_rules_init(void) { int err; rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, 0); err = register_pernet_subsys(&fib_rules_net_ops); if (err < 0) goto fail; err = register_netdevice_notifier(&fib_rules_notifier); if (err < 0) goto fail_unregister; return 0; fail_unregister: unregister_pernet_subsys(&fib_rules_net_ops); fail: rtnl_unregister(PF_UNSPEC, RTM_NEWRULE); rtnl_unregister(PF_UNSPEC, RTM_DELRULE); rtnl_unregister(PF_UNSPEC, RTM_GETRULE); return err; } subsys_initcall(fib_rules_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 | /* SPDX-License-Identifier: GPL-2.0 */ /* * descriptor table internals; you almost certainly want file.h instead. */ #ifndef __LINUX_FDTABLE_H #define __LINUX_FDTABLE_H #include <linux/posix_types.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/atomic.h> /* * The default fd array needs to be at least BITS_PER_LONG, * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG struct fdtable { unsigned int max_fds; struct file __rcu **fd; /* current fd array */ unsigned long *close_on_exec; unsigned long *open_fds; unsigned long *full_fds_bits; struct rcu_head rcu; }; static inline bool close_on_exec(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->close_on_exec); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * Open file table structure */ struct files_struct { /* * read mostly part */ atomic_t count; bool resize_in_progress; wait_queue_head_t resize_wait; struct fdtable __rcu *fdt; struct fdtable fdtab; /* * written part on a separate cache line in SMP */ spinlock_t file_lock ____cacheline_aligned_in_smp; unsigned int next_fd; unsigned long close_on_exec_init[1]; unsigned long open_fds_init[1]; unsigned long full_fds_bits_init[1]; struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; struct file_operations; struct vfsmount; struct dentry; #define rcu_dereference_check_fdtable(files, fdtfd) \ rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock)) #define files_fdtable(files) \ rcu_dereference_check_fdtable((files), (files)->fdt) /* * The caller must ensure that fd table isn't shared or hold rcu or file lock */ static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = rcu_dereference_raw(files->fdt); if (fd < fdt->max_fds) { fd = array_index_nospec(fd, fdt->max_fds); return rcu_dereference_raw(fdt->fd[fd]); } return NULL; } static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!lockdep_is_held(&files->file_lock), "suspicious rcu_dereference_check() usage"); return files_lookup_fd_raw(files, fd); } static inline struct file *files_lookup_fd_rcu(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious rcu_dereference_check() usage"); return files_lookup_fd_raw(files, fd); } static inline struct file *lookup_fd_rcu(unsigned int fd) { return files_lookup_fd_rcu(current->files, fd); } struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd); struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *fd); struct task_struct; void put_files_struct(struct files_struct *fs); int unshare_files(void); struct fd_range { unsigned int from, to; }; struct files_struct *dup_fd(struct files_struct *, struct fd_range *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), const void *); extern int close_fd(unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); extern int close_fd_get_file(unsigned int fd, struct file **res); extern struct kmem_cache *files_cachep; #endif /* __LINUX_FDTABLE_H */ |
| 26 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/drivers/base/map.c * * (C) Copyright Al Viro 2002,2003 * * NOTE: data structure needs to be changed. It works, but for large dev_t * it will be too slow. It is isolated, though, so these changes will be * local to that file. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/kdev_t.h> #include <linux/kobject.h> #include <linux/kobj_map.h> struct kobj_map { struct probe { struct probe *next; dev_t dev; unsigned long range; struct module *owner; kobj_probe_t *get; int (*lock)(dev_t, void *); void *data; } *probes[255]; struct mutex *lock; }; int kobj_map(struct kobj_map *domain, dev_t dev, unsigned long range, struct module *module, kobj_probe_t *probe, int (*lock)(dev_t, void *), void *data) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *p; if (n > 255) n = 255; p = kmalloc_array(n, sizeof(struct probe), GFP_KERNEL); if (p == NULL) return -ENOMEM; for (i = 0; i < n; i++, p++) { p->owner = module; p->get = probe; p->lock = lock; p->dev = dev; p->range = range; p->data = data; } mutex_lock(domain->lock); for (i = 0, p -= n; i < n; i++, p++, index++) { struct probe **s = &domain->probes[index % 255]; while (*s && (*s)->range < range) s = &(*s)->next; p->next = *s; *s = p; } mutex_unlock(domain->lock); return 0; } void kobj_unmap(struct kobj_map *domain, dev_t dev, unsigned long range) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *found = NULL; if (n > 255) n = 255; mutex_lock(domain->lock); for (i = 0; i < n; i++, index++) { struct probe **s; for (s = &domain->probes[index % 255]; *s; s = &(*s)->next) { struct probe *p = *s; if (p->dev == dev && p->range == range) { *s = p->next; if (!found) found = p; break; } } } mutex_unlock(domain->lock); kfree(found); } struct kobject *kobj_lookup(struct kobj_map *domain, dev_t dev, int *index) { struct kobject *kobj; struct probe *p; unsigned long best = ~0UL; retry: mutex_lock(domain->lock); for (p = domain->probes[MAJOR(dev) % 255]; p; p = p->next) { struct kobject *(*probe)(dev_t, int *, void *); struct module *owner; void *data; if (p->dev > dev || p->dev + p->range - 1 < dev) continue; if (p->range - 1 >= best) break; if (!try_module_get(p->owner)) continue; owner = p->owner; data = p->data; probe = p->get; best = p->range - 1; *index = dev - p->dev; if (p->lock && p->lock(dev, data) < 0) { module_put(owner); continue; } mutex_unlock(domain->lock); kobj = probe(dev, index, data); /* Currently ->owner protects _only_ ->probe() itself. */ module_put(owner); if (kobj) return kobj; goto retry; } mutex_unlock(domain->lock); return NULL; } struct kobj_map *kobj_map_init(kobj_probe_t *base_probe, struct mutex *lock) { struct kobj_map *p = kmalloc(sizeof(struct kobj_map), GFP_KERNEL); struct probe *base = kzalloc(sizeof(*base), GFP_KERNEL); int i; if ((p == NULL) || (base == NULL)) { kfree(p); kfree(base); return NULL; } base->dev = 1; base->range = ~0; base->get = base_probe; for (i = 0; i < 255; i++) p->probes[i] = base; p->lock = lock; return p; } |
| 2544 2633 708 913 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 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-only */ /* * kref.h - library routines for handling generic reference counted objects * * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Corp. * * based on kobject.h which was: * Copyright (C) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (C) 2002-2003 Open Source Development Labs */ #ifndef _KREF_H_ #define _KREF_H_ #include <linux/spinlock.h> #include <linux/refcount.h> struct kref { refcount_t refcount; }; #define KREF_INIT(n) { .refcount = REFCOUNT_INIT(n), } /** * kref_init - initialize object. * @kref: object in question. */ static inline void kref_init(struct kref *kref) { refcount_set(&kref->refcount, 1); } static inline unsigned int kref_read(const struct kref *kref) { return refcount_read(&kref->refcount); } /** * kref_get - increment refcount for object. * @kref: object. */ static inline void kref_get(struct kref *kref) { refcount_inc(&kref->refcount); } /** * kref_put - decrement refcount for object. * @kref: object. * @release: pointer to the function that will clean up the object when the * last reference to the object is released. * This pointer is required, and it is not acceptable to pass kfree * in as this function. * * Decrement the refcount, and if 0, call release(). * Return 1 if the object was removed, otherwise return 0. Beware, if this * function returns 0, you still can not count on the kref from remaining in * memory. Only use the return value if you want to see if the kref is now * gone, not present. */ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) { if (refcount_dec_and_test(&kref->refcount)) { release(kref); return 1; } return 0; } static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *lock) { if (refcount_dec_and_mutex_lock(&kref->refcount, lock)) { release(kref); return 1; } return 0; } static inline int kref_put_lock(struct kref *kref, void (*release)(struct kref *kref), spinlock_t *lock) { if (refcount_dec_and_lock(&kref->refcount, lock)) { release(kref); return 1; } return 0; } /** * kref_get_unless_zero - Increment refcount for object unless it is zero. * @kref: object. * * Return non-zero if the increment succeeded. Otherwise return 0. * * This function is intended to simplify locking around refcounting for * objects that can be looked up from a lookup structure, and which are * removed from that lookup structure in the object destructor. * Operations on such objects require at least a read lock around * lookup + kref_get, and a write lock around kref_put + remove from lookup * structure. Furthermore, RCU implementations become extremely tricky. * With a lookup followed by a kref_get_unless_zero *with return value check* * locking in the kref_put path can be deferred to the actual removal from * the lookup structure and RCU lookups become trivial. */ static inline int __must_check kref_get_unless_zero(struct kref *kref) { return refcount_inc_not_zero(&kref->refcount); } #endif /* _KREF_H_ */ |
| 12500 12634 8618 9275 3558 3561 6618 6630 6626 6631 3999 4003 2264 3685 3998 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 | // SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/cpumask.h> #include <linux/export.h> #include <linux/memblock.h> #include <linux/numa.h> /** * cpumask_next - get the next cpu in a cpumask * @n: the cpu prior to the place to search (ie. return will be > @n) * @srcp: the cpumask pointer * * Returns >= nr_cpu_ids if no further cpus set. */ unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); } EXPORT_SYMBOL(cpumask_next); /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (ie. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Returns >= nr_cpu_ids if no further cpus set in both. */ int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits, n + 1); } EXPORT_SYMBOL(cpumask_next_and); /** * cpumask_any_but - return a "random" in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. * Returns >= nr_cpu_ids if no cpus set. */ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; cpumask_check(cpu); for_each_cpu(i, mask) if (i != cpu) break; return i; } EXPORT_SYMBOL(cpumask_any_but); /** * cpumask_next_wrap - helper to implement for_each_cpu_wrap * @n: the cpu prior to the place to search * @mask: the cpumask pointer * @start: the start point of the iteration * @wrap: assume @n crossing @start terminates the iteration * * Returns >= nr_cpu_ids on completion * * Note: the @wrap argument is required for the start condition when * we cannot assume @start is set in @mask. */ int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { int next; again: next = cpumask_next(n, mask); if (wrap && n < start && next >= start) { return nr_cpumask_bits; } else if (next >= nr_cpumask_bits) { wrap = true; n = -1; goto again; } return next; } EXPORT_SYMBOL(cpumask_next_wrap); /* These are not inline because of header tangles. */ #ifdef CONFIG_CPUMASK_OFFSTACK /** * alloc_cpumask_var_node - allocate a struct cpumask on a given node * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>) * Returns TRUE if memory allocation succeeded, FALSE otherwise. * * In addition, mask will be NULL if this fails. Note that gcc is * usually smart enough to know that mask can never be NULL if * CONFIG_CPUMASK_OFFSTACK=n, so does code elimination in that case * too. */ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { *mask = kmalloc_node(cpumask_size(), flags, node); #ifdef CONFIG_DEBUG_PER_CPU_MAPS if (!*mask) { printk(KERN_ERR "=> alloc_cpumask_var: failed!\n"); dump_stack(); } #endif return *mask != NULL; } EXPORT_SYMBOL(alloc_cpumask_var_node); bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); } EXPORT_SYMBOL(zalloc_cpumask_var_node); /** * alloc_cpumask_var - allocate a struct cpumask * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * See alloc_cpumask_var_node. */ bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } EXPORT_SYMBOL(alloc_cpumask_var); bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); } EXPORT_SYMBOL(zalloc_cpumask_var); /** * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena. * @mask: pointer to cpumask_var_t where the cpumask is returned * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop (in <linux/cpumask.h>). * Either returns an allocated (zero-filled) cpumask, or causes the * system to panic. */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { *mask = memblock_alloc(cpumask_size(), SMP_CACHE_BYTES); if (!*mask) panic("%s: Failed to allocate %u bytes\n", __func__, cpumask_size()); } /** * free_cpumask_var - frees memory allocated for a struct cpumask. * @mask: cpumask to free * * This is safe on a NULL mask. */ void free_cpumask_var(cpumask_var_t mask) { kfree(mask); } EXPORT_SYMBOL(free_cpumask_var); /** * free_bootmem_cpumask_var - frees result of alloc_bootmem_cpumask_var * @mask: cpumask to free */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { memblock_free(__pa(mask), cpumask_size()); } #endif /** * cpumask_local_spread - select the i'th cpu with local numa cpu's first * @i: index number * @node: local numa_node * * This function selects an online CPU according to a numa aware policy; * local cpus are returned first, followed by non-local ones, then it * wraps around. * * It's not very efficient, but useful for setup. */ unsigned int cpumask_local_spread(unsigned int i, int node) { int cpu; /* Wrap: we always want a cpu. */ i %= num_online_cpus(); if (node == NUMA_NO_NODE) { for_each_cpu(cpu, cpu_online_mask) if (i-- == 0) return cpu; } else { /* NUMA first. */ for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask) if (i-- == 0) return cpu; for_each_cpu(cpu, cpu_online_mask) { /* Skip NUMA nodes, done above. */ if (cpumask_test_cpu(cpu, cpumask_of_node(node))) continue; if (i-- == 0) return cpu; } } BUG(); } EXPORT_SYMBOL(cpumask_local_spread); static DEFINE_PER_CPU(int, distribute_cpu_mask_prev); /** * Returns an arbitrary cpu within srcp1 & srcp2. * * Iterated calls using the same srcp1 and srcp2 will be distributed within * their intersection. * * Returns >= nr_cpu_ids if the intersection is empty. */ int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { int next, prev; /* NOTE: our first selection will skip 0. */ prev = __this_cpu_read(distribute_cpu_mask_prev); next = cpumask_next_and(prev, src1p, src2p); if (next >= nr_cpu_ids) next = cpumask_first_and(src1p, src2p); if (next < nr_cpu_ids) __this_cpu_write(distribute_cpu_mask_prev, next); return next; } EXPORT_SYMBOL(cpumask_any_and_distribute); int cpumask_any_distribute(const struct cpumask *srcp) { int next, prev; /* NOTE: our first selection will skip 0. */ prev = __this_cpu_read(distribute_cpu_mask_prev); next = cpumask_next(prev, srcp); if (next >= nr_cpu_ids) next = cpumask_first(srcp); if (next < nr_cpu_ids) __this_cpu_write(distribute_cpu_mask_prev, next); return next; } EXPORT_SYMBOL(cpumask_any_distribute); |
| 1 1 90 89 75 5 12 34 7 10 14 102 3 5 4 8 39 4 43 39 6 53 37 83 4 4 2 6 6 1 2 8 7 1 44 1134 90 1205 1135 90 90 89 97 1279 84 84 84 84 75 9 84 75 9 163 163 2337 268 2336 269 2335 84 22 84 84 2338 2336 760 23 220 41 61 97 79 13 8 50 1364 1265 161 1264 16 116 1279 67 134 82 98 99 5 72 28 2 9 8 1 2 101 2 100 7 3 6 10 10 2 4 1752 102 1033 118 37 28 575 2 19 151 80 88 73 82 2 44 34 169 1211 868 246 595 2339 831 390 32 23 50 4 351 364 449 4 507 390 409 410 410 554 555 38 38 38 552 552 555 94 1 80 2 7 1 1 1 1 1 370 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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 <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/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); } 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) { struct flow_dissector_key_ports_range *key_ports_range = NULL; struct flow_dissector_key_ports *key_ports = NULL; __be32 ports; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) key_ports_range = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE, target_container); if (!key_ports && !key_ports_range) return; ports = __skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen); if (key_ports) key_ports->ports = ports; if (key_ports_range) key_ports_range->tp.ports = ports; } 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_range *key_ports_range = NULL; 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); key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) { key_ports_range = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE, target_container); key_ports_range->tp.src = flow_keys->sport; key_ports_range->tp.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); } } bool 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 == BPF_OK; } /** * __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; 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); ret = bpf_flow_dissect(prog, &ctx, n_proto, nhoff, hlen, flags); __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); return ret; } 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, ð->h_dest, sizeof(*key_eth_addrs)); } 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_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; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } proto = hdr->proto; nhoff += PPPOE_SES_HLEN; switch (proto) { case htons(PPP_IP): proto = htons(ETH_P_IP); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case htons(PPP_IPV6): proto = htons(ETH_P_IPV6); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; default: fdret = FLOW_DISSECT_RET_OUT_BAD; break; } 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 += sizeof(struct ptp_header); fdret = FLOW_DISSECT_RET_OUT_GOOD; 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: 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: 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: 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; 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_key_t hashrnd __read_mostly; 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, 0); 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); |
| 326 325 326 325 2615 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | /* SPDX-License-Identifier: GPL-2.0 */ /* * An extensible bitmap is a bitmap that supports an * arbitrary number of bits. Extensible bitmaps are * used to represent sets of values, such as types, * roles, categories, and classes. * * Each extensible bitmap is implemented as a linked * list of bitmap nodes, where each bitmap node has * an explicitly specified starting bit position within * the total bitmap. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ #ifndef _SS_EBITMAP_H_ #define _SS_EBITMAP_H_ #include <net/netlabel.h> #ifdef CONFIG_64BIT #define EBITMAP_NODE_SIZE 64 #else #define EBITMAP_NODE_SIZE 32 #endif #define EBITMAP_UNIT_NUMS ((EBITMAP_NODE_SIZE-sizeof(void *)-sizeof(u32))\ / sizeof(unsigned long)) #define EBITMAP_UNIT_SIZE BITS_PER_LONG #define EBITMAP_SIZE (EBITMAP_UNIT_NUMS * EBITMAP_UNIT_SIZE) #define EBITMAP_BIT 1ULL #define EBITMAP_SHIFT_UNIT_SIZE(x) \ (((x) >> EBITMAP_UNIT_SIZE / 2) >> EBITMAP_UNIT_SIZE / 2) struct ebitmap_node { struct ebitmap_node *next; unsigned long maps[EBITMAP_UNIT_NUMS]; u32 startbit; }; struct ebitmap { struct ebitmap_node *node; /* first node in the bitmap */ u32 highbit; /* highest position in the total bitmap */ }; #define ebitmap_length(e) ((e)->highbit) static inline unsigned int ebitmap_start_positive(struct ebitmap *e, struct ebitmap_node **n) { unsigned int ofs; for (*n = e->node; *n; *n = (*n)->next) { ofs = find_first_bit((*n)->maps, EBITMAP_SIZE); if (ofs < EBITMAP_SIZE) return (*n)->startbit + ofs; } return ebitmap_length(e); } static inline void ebitmap_init(struct ebitmap *e) { memset(e, 0, sizeof(*e)); } static inline unsigned int ebitmap_next_positive(struct ebitmap *e, struct ebitmap_node **n, unsigned int bit) { unsigned int ofs; ofs = find_next_bit((*n)->maps, EBITMAP_SIZE, bit - (*n)->startbit + 1); if (ofs < EBITMAP_SIZE) return ofs + (*n)->startbit; for (*n = (*n)->next; *n; *n = (*n)->next) { ofs = find_first_bit((*n)->maps, EBITMAP_SIZE); if (ofs < EBITMAP_SIZE) return ofs + (*n)->startbit; } return ebitmap_length(e); } #define EBITMAP_NODE_INDEX(node, bit) \ (((bit) - (node)->startbit) / EBITMAP_UNIT_SIZE) #define EBITMAP_NODE_OFFSET(node, bit) \ (((bit) - (node)->startbit) % EBITMAP_UNIT_SIZE) static inline int ebitmap_node_get_bit(struct ebitmap_node *n, unsigned int bit) { unsigned int index = EBITMAP_NODE_INDEX(n, bit); unsigned int ofs = EBITMAP_NODE_OFFSET(n, bit); BUG_ON(index >= EBITMAP_UNIT_NUMS); if ((n->maps[index] & (EBITMAP_BIT << ofs))) return 1; return 0; } static inline void ebitmap_node_set_bit(struct ebitmap_node *n, unsigned int bit) { unsigned int index = EBITMAP_NODE_INDEX(n, bit); unsigned int ofs = EBITMAP_NODE_OFFSET(n, bit); BUG_ON(index >= EBITMAP_UNIT_NUMS); n->maps[index] |= (EBITMAP_BIT << ofs); } static inline void ebitmap_node_clr_bit(struct ebitmap_node *n, unsigned int bit) { unsigned int index = EBITMAP_NODE_INDEX(n, bit); unsigned int ofs = EBITMAP_NODE_OFFSET(n, bit); BUG_ON(index >= EBITMAP_UNIT_NUMS); n->maps[index] &= ~(EBITMAP_BIT << ofs); } #define ebitmap_for_each_positive_bit(e, n, bit) \ for (bit = ebitmap_start_positive(e, &n); \ bit < ebitmap_length(e); \ bit = ebitmap_next_positive(e, &n, bit)) \ int ebitmap_cmp(struct ebitmap *e1, struct ebitmap *e2); int ebitmap_cpy(struct ebitmap *dst, struct ebitmap *src); int ebitmap_and(struct ebitmap *dst, struct ebitmap *e1, struct ebitmap *e2); int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2, u32 last_e2bit); int ebitmap_get_bit(struct ebitmap *e, unsigned long bit); int ebitmap_set_bit(struct ebitmap *e, unsigned long bit, int value); void ebitmap_destroy(struct ebitmap *e); int ebitmap_read(struct ebitmap *e, void *fp); int ebitmap_write(struct ebitmap *e, void *fp); u32 ebitmap_hash(const struct ebitmap *e, u32 hash); #ifdef CONFIG_NETLABEL int ebitmap_netlbl_export(struct ebitmap *ebmap, struct netlbl_lsm_catmap **catmap); int ebitmap_netlbl_import(struct ebitmap *ebmap, struct netlbl_lsm_catmap *catmap); #else static inline int ebitmap_netlbl_export(struct ebitmap *ebmap, struct netlbl_lsm_catmap **catmap) { return -ENOMEM; } static inline int ebitmap_netlbl_import(struct ebitmap *ebmap, struct netlbl_lsm_catmap *catmap) { return -ENOMEM; } #endif #endif /* _SS_EBITMAP_H_ */ |
| 11561 11979 436 61 61 61 1747 1749 1748 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Common capabilities, needed by capability.o. */ #include <linux/capability.h> #include <linux/audit.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/lsm_hooks.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/ptrace.h> #include <linux/xattr.h> #include <linux/hugetlb.h> #include <linux/mount.h> #include <linux/sched.h> #include <linux/prctl.h> #include <linux/securebits.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/personality.h> #include <linux/mnt_idmapping.h> /* * If a non-root user executes a setuid-root binary in * !secure(SECURE_NOROOT) mode, then we raise capabilities. * However if fE is also set, then the intent is for only * the file capabilities to be applied, and the setuid-root * bit is left on either to change the uid (plausible) or * to get full privilege on a kernel without file capabilities * support. So in that case we do not raise capabilities. * * Warn if that happens, once per boot. */ static void warn_setuid_and_fcaps_mixed(const char *fname) { static int warned; if (!warned) { printk(KERN_INFO "warning: `%s' has both setuid-root and" " effective capabilities. Therefore not raising all" " capabilities.\n", fname); warned = 1; } } /** * cap_capable - Determine whether a task has a particular effective capability * @cred: The credentials to use * @targ_ns: The user namespace in which we need the capability * @cap: The capability to check for * @opts: Bitmask of options defined in include/linux/security.h * * Determine whether the nominated task has the specified capability amongst * its effective set, returning 0 if it does, -ve if it does not. * * NOTE WELL: cap_has_capability() cannot be used like the kernel's capable() * and has_capability() functions. That is, it has the reverse semantics: * cap_has_capability() returns 0 when a task has a capability, but the * kernel's capable() and has_capability() returns 1 for this case. */ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, int cap, unsigned int opts) { struct user_namespace *ns = targ_ns; /* See if cred has the capability in the target user namespace * by examining the target user namespace and all of the target * user namespace's parents. */ for (;;) { /* Do we have the necessary capabilities? */ if (ns == cred->user_ns) return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; /* * If we're already at a lower level than we're looking for, * we're done searching. */ if (ns->level <= cred->user_ns->level) return -EPERM; /* * The owner of the user namespace in the parent of the * user namespace has all caps. */ if ((ns->parent == cred->user_ns) && uid_eq(ns->owner, cred->euid)) return 0; /* * If you have a capability in a parent user ns, then you have * it over all children user namespaces as well. */ ns = ns->parent; } /* We never get here */ } /** * cap_settime - Determine whether the current process may set the system clock * @ts: The time to set * @tz: The timezone to set * * Determine whether the current process may set the system clock and timezone * information, returning 0 if permission granted, -ve if denied. */ int cap_settime(const struct timespec64 *ts, const struct timezone *tz) { if (!capable(CAP_SYS_TIME)) return -EPERM; return 0; } /** * cap_ptrace_access_check - Determine whether the current process may access * another * @child: The process to be accessed * @mode: The mode of attachment. * * If we are in the same or an ancestor user_ns and have all the target * task's capabilities, then ptrace access is allowed. * If we have the ptrace capability to the target user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether a process may access another, returning 0 if permission * granted, -ve if denied. */ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; const struct cred *cred, *child_cred; const kernel_cap_t *caller_caps; rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); if (mode & PTRACE_MODE_FSCREDS) caller_caps = &cred->cap_effective; else caller_caps = &cred->cap_permitted; if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, *caller_caps)) goto out; if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_ptrace_traceme - Determine whether another process may trace the current * @parent: The task proposed to be the tracer * * If parent is in the same or an ancestor user_ns and has all current's * capabilities, then ptrace access is allowed. * If parent has the ptrace capability to current's user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether the nominated task is permitted to trace the current * process, returning 0 if permission is granted, -ve if denied. */ int cap_ptrace_traceme(struct task_struct *parent) { int ret = 0; const struct cred *cred, *child_cred; rcu_read_lock(); cred = __task_cred(parent); child_cred = current_cred(); if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) goto out; if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_capget - Retrieve a task's capability sets * @target: The task from which to retrieve the capability sets * @effective: The place to record the effective set * @inheritable: The place to record the inheritable set * @permitted: The place to record the permitted set * * This function retrieves the capabilities of the nominated task and returns * them to the caller. */ int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { const struct cred *cred; /* Derived from kernel/capability.c:sys_capget. */ rcu_read_lock(); cred = __task_cred(target); *effective = cred->cap_effective; *inheritable = cred->cap_inheritable; *permitted = cred->cap_permitted; rcu_read_unlock(); return 0; } /* * Determine whether the inheritable capabilities are limited to the old * permitted set. Returns 1 if they are limited, 0 if they are not. */ static inline int cap_inh_is_capped(void) { /* they are so limited unless the current task has the CAP_SETPCAP * capability */ if (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) == 0) return 0; return 1; } /** * cap_capset - Validate and apply proposed changes to current's capabilities * @new: The proposed new credentials; alterations should be made here * @old: The current task's current credentials * @effective: A pointer to the proposed new effective capabilities set * @inheritable: A pointer to the proposed new inheritable capabilities set * @permitted: A pointer to the proposed new permitted capabilities set * * This function validates and applies a proposed mass change to the current * process's capability sets. The changes are made to the proposed new * credentials, and assuming no error, will be committed by the caller of LSM. */ int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { if (cap_inh_is_capped() && !cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_permitted))) /* incapable of using this inheritable set */ return -EPERM; if (!cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_bset))) /* no new pI capabilities outside bounding set */ return -EPERM; /* verify restrictions on target's new Permitted set */ if (!cap_issubset(*permitted, old->cap_permitted)) return -EPERM; /* verify the _new_Effective_ is a subset of the _new_Permitted_ */ if (!cap_issubset(*effective, *permitted)) return -EPERM; new->cap_effective = *effective; new->cap_inheritable = *inheritable; new->cap_permitted = *permitted; /* * Mask off ambient bits that are no longer both permitted and * inheritable. */ new->cap_ambient = cap_intersect(new->cap_ambient, cap_intersect(*permitted, *inheritable)); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EINVAL; return 0; } /** * cap_inode_need_killpriv - Determine if inode change affects privileges * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV * * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV * affects the security markings on that inode, and if it is, should * inode_killpriv() be invoked or the change rejected. * * Return: 1 if security.capability has a value, meaning inode_killpriv() * is required, 0 otherwise, meaning inode_killpriv() is not required. */ int cap_inode_need_killpriv(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); int error; error = __vfs_getxattr(dentry, inode, XATTR_NAME_CAPS, NULL, 0); return error > 0; } /** * cap_inode_killpriv - Erase the security markings on an inode * * @mnt_userns: user namespace of the mount the inode was found from * @dentry: The inode/dentry to alter * * Erase the privilege-enhancing security markings on an inode. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. * * Return: 0 if successful, -ve on error. */ int cap_inode_killpriv(struct user_namespace *mnt_userns, struct dentry *dentry) { int error; error = __vfs_removexattr(mnt_userns, dentry, XATTR_NAME_CAPS); if (error == -EOPNOTSUPP) error = 0; return error; } static bool rootid_owns_currentns(kuid_t kroot) { struct user_namespace *ns; if (!uid_valid(kroot)) return false; for (ns = current_user_ns(); ; ns = ns->parent) { if (from_kuid(ns, kroot) == 0) return true; if (ns == &init_user_ns) break; } return false; } static __u32 sansflags(__u32 m) { return m & ~VFS_CAP_FLAGS_EFFECTIVE; } static bool is_v2header(size_t size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_2) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_2; } static bool is_v3header(size_t size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_3) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_3; } /* * getsecurity: We are called for security.* before any attempt to read the * xattr from the inode itself. * * This gives us a chance to read the on-disk value and convert it. If we * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler. * * Note we are not called by vfs_getxattr_alloc(), but that is only called * by the integrity subsystem, which really wants the unconverted values - * so that's good. */ int cap_inode_getsecurity(struct user_namespace *mnt_userns, struct inode *inode, const char *name, void **buffer, bool alloc) { int size, ret; kuid_t kroot; u32 nsmagic, magic; uid_t root, mappedroot; char *tmpbuf = NULL; struct vfs_cap_data *cap; struct vfs_ns_cap_data *nscap = NULL; struct dentry *dentry; struct user_namespace *fs_ns; if (strcmp(name, "capability") != 0) return -EOPNOTSUPP; dentry = d_find_any_alias(inode); if (!dentry) return -EINVAL; size = sizeof(struct vfs_ns_cap_data); ret = (int)vfs_getxattr_alloc(mnt_userns, dentry, XATTR_NAME_CAPS, &tmpbuf, size, GFP_NOFS); dput(dentry); if (ret < 0 || !tmpbuf) { size = ret; goto out_free; } fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; if (is_v2header((size_t) ret, cap)) { root = 0; } else if (is_v3header((size_t) ret, cap)) { nscap = (struct vfs_ns_cap_data *) tmpbuf; root = le32_to_cpu(nscap->rootid); } else { size = -EINVAL; goto out_free; } kroot = make_kuid(fs_ns, root); /* If this is an idmapped mount shift the kuid. */ kroot = mapped_kuid_fs(mnt_userns, fs_ns, kroot); /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ mappedroot = from_kuid(current_user_ns(), kroot); if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) { size = sizeof(struct vfs_ns_cap_data); if (alloc) { if (!nscap) { /* v2 -> v3 conversion */ nscap = kzalloc(size, GFP_ATOMIC); if (!nscap) { size = -ENOMEM; goto out_free; } nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); nscap->magic_etc = cpu_to_le32(nsmagic); } else { /* use allocated v3 buffer */ tmpbuf = NULL; } nscap->rootid = cpu_to_le32(mappedroot); *buffer = nscap; } goto out_free; } if (!rootid_owns_currentns(kroot)) { size = -EOVERFLOW; goto out_free; } /* This comes from a parent namespace. Return as a v2 capability */ size = sizeof(struct vfs_cap_data); if (alloc) { if (nscap) { /* v3 -> v2 conversion */ cap = kzalloc(size, GFP_ATOMIC); if (!cap) { size = -ENOMEM; goto out_free; } magic = VFS_CAP_REVISION_2; nsmagic = le32_to_cpu(nscap->magic_etc); if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE) magic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); cap->magic_etc = cpu_to_le32(magic); } else { /* use unconverted v2 */ tmpbuf = NULL; } *buffer = cap; } out_free: kfree(tmpbuf); return size; } /** * rootid_from_xattr - translate root uid of vfs caps * * @value: vfs caps value which may be modified by this function * @size: size of @ivalue * @task_ns: user namespace of the caller * @mnt_userns: user namespace of the mount the inode was found from * @fs_userns: user namespace of the filesystem * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. */ static kuid_t rootid_from_xattr(const void *value, size_t size, struct user_namespace *task_ns, struct user_namespace *mnt_userns, struct user_namespace *fs_userns) { const struct vfs_ns_cap_data *nscap = value; kuid_t rootkid; uid_t rootid = 0; if (size == XATTR_CAPS_SZ_3) rootid = le32_to_cpu(nscap->rootid); rootkid = make_kuid(task_ns, rootid); return mapped_kuid_user(mnt_userns, fs_userns, rootkid); } static bool validheader(size_t size, const struct vfs_cap_data *cap) { return is_v2header(size, cap) || is_v3header(size, cap); } /** * cap_convert_nscap - check vfs caps * * @mnt_userns: user namespace of the mount the inode was found from * @dentry: used to retrieve inode to check permissions on * @ivalue: vfs caps value which may be modified by this function * @size: size of @ivalue * * User requested a write of security.capability. If needed, update the * xattr to change from v2 to v3, or to fixup the v3 rootid. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. * * Return: On success, return the new size; on error, return < 0. */ int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, const void **ivalue, size_t size) { struct vfs_ns_cap_data *nscap; uid_t nsrootid; const struct vfs_cap_data *cap = *ivalue; __u32 magic, nsmagic; struct inode *inode = d_backing_inode(dentry); struct user_namespace *task_ns = current_user_ns(), *fs_ns = inode->i_sb->s_user_ns; kuid_t rootid; size_t newsize; if (!*ivalue) return -EINVAL; if (!validheader(size, cap)) return -EINVAL; if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP)) return -EPERM; if (size == XATTR_CAPS_SZ_2 && (mnt_userns == fs_ns)) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size; rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns, fs_ns); if (!uid_valid(rootid)) return -EINVAL; nsrootid = from_kuid(fs_ns, rootid); if (nsrootid == -1) return -EINVAL; newsize = sizeof(struct vfs_ns_cap_data); nscap = kmalloc(newsize, GFP_ATOMIC); if (!nscap) return -ENOMEM; nscap->rootid = cpu_to_le32(nsrootid); nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; nscap->magic_etc = cpu_to_le32(nsmagic); memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); *ivalue = nscap; return newsize; } /* * Calculate the new process capability sets from the capability sets attached * to a file. */ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, struct linux_binprm *bprm, bool *effective, bool *has_fcap) { struct cred *new = bprm->cred; unsigned i; int ret = 0; if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE) *effective = true; if (caps->magic_etc & VFS_CAP_REVISION_MASK) *has_fcap = true; CAP_FOR_EACH_U32(i) { __u32 permitted = caps->permitted.cap[i]; __u32 inheritable = caps->inheritable.cap[i]; /* * pP' = (X & fP) | (pI & fI) * The addition of pA' is handled later. */ new->cap_permitted.cap[i] = (new->cap_bset.cap[i] & permitted) | (new->cap_inheritable.cap[i] & inheritable); if (permitted & ~new->cap_permitted.cap[i]) /* insufficient to execute correctly */ ret = -EPERM; } /* * For legacy apps, with no internal support for recognizing they * do not have enough capabilities, we return an error if they are * missing some "forced" (aka file-permitted) capabilities. */ return *effective ? ret : 0; } /** * get_vfs_caps_from_disk - retrieve vfs caps from disk * * @mnt_userns: user namespace of the mount the inode was found from * @dentry: dentry from which @inode is retrieved * @cpu_caps: vfs capabilities * * Extract the on-exec-apply capability sets for an executable file. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. */ int get_vfs_caps_from_disk(struct user_namespace *mnt_userns, const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) { struct inode *inode = d_backing_inode(dentry); __u32 magic_etc; unsigned tocopy, i; int size; struct vfs_ns_cap_data data, *nscaps = &data; struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; kuid_t rootkuid; struct user_namespace *fs_ns; memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); if (!inode) return -ENODATA; fs_ns = inode->i_sb->s_user_ns; size = __vfs_getxattr((struct dentry *)dentry, inode, XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ); if (size == -ENODATA || size == -EOPNOTSUPP) /* no data, that's ok */ return -ENODATA; if (size < 0) return size; if (size < sizeof(magic_etc)) return -EINVAL; cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc); rootkuid = make_kuid(fs_ns, 0); switch (magic_etc & VFS_CAP_REVISION_MASK) { case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) return -EINVAL; tocopy = VFS_CAP_U32_1; break; case VFS_CAP_REVISION_2: if (size != XATTR_CAPS_SZ_2) return -EINVAL; tocopy = VFS_CAP_U32_2; break; case VFS_CAP_REVISION_3: if (size != XATTR_CAPS_SZ_3) return -EINVAL; tocopy = VFS_CAP_U32_3; rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid)); break; default: return -EINVAL; } /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ rootkuid = mapped_kuid_fs(mnt_userns, fs_ns, rootkuid); if (!rootid_owns_currentns(rootkuid)) return -ENODATA; CAP_FOR_EACH_U32(i) { if (i >= tocopy) break; cpu_caps->permitted.cap[i] = le32_to_cpu(caps->data[i].permitted); cpu_caps->inheritable.cap[i] = le32_to_cpu(caps->data[i].inheritable); } cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; cpu_caps->rootid = rootkuid; return 0; } /* * Attempt to get the on-exec apply capability sets for an executable file from * its xattrs and, if present, apply them to the proposed credentials being * constructed by execve(). */ static int get_file_caps(struct linux_binprm *bprm, struct file *file, bool *effective, bool *has_fcap) { int rc = 0; struct cpu_vfs_cap_data vcaps; cap_clear(bprm->cred->cap_permitted); if (!file_caps_enabled) return 0; if (!mnt_may_suid(file->f_path.mnt)) return 0; /* * This check is redundant with mnt_may_suid() but is kept to make * explicit that capability bits are limited to s_user_ns and its * descendants. */ if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns)) return 0; rc = get_vfs_caps_from_disk(file_mnt_user_ns(file), file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) printk(KERN_NOTICE "Invalid argument reading file caps for %s\n", bprm->filename); else if (rc == -ENODATA) rc = 0; goto out; } rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_fcap); out: if (rc) cap_clear(bprm->cred->cap_permitted); return rc; } static inline bool root_privileged(void) { return !issecure(SECURE_NOROOT); } static inline bool __is_real(kuid_t uid, struct cred *cred) { return uid_eq(cred->uid, uid); } static inline bool __is_eff(kuid_t uid, struct cred *cred) { return uid_eq(cred->euid, uid); } static inline bool __is_suid(kuid_t uid, struct cred *cred) { return !__is_real(uid, cred) && __is_eff(uid, cred); } /* * handle_privileged_root - Handle case of privileged root * @bprm: The execution parameters, including the proposed creds * @has_fcap: Are any file capabilities set? * @effective: Do we have effective root privilege? * @root_uid: This namespace' root UID WRT initial USER namespace * * Handle the case where root is privileged and hasn't been neutered by * SECURE_NOROOT. If file capabilities are set, they won't be combined with * set UID root and nothing is changed. If we are root, cap_permitted is * updated. If we have become set UID root, the effective bit is set. */ static void handle_privileged_root(struct linux_binprm *bprm, bool has_fcap, bool *effective, kuid_t root_uid) { const struct cred *old = current_cred(); struct cred *new = bprm->cred; if (!root_privileged()) return; /* * If the legacy file capability is set, then don't set privs * for a setuid root binary run by a non-root user. Do set it * for a root user just to cause least surprise to an admin. */ if (has_fcap && __is_suid(root_uid, new)) { warn_setuid_and_fcaps_mixed(bprm->filename); return; } /* * To support inheritance of root-permissions and suid-root * executables under compatibility mode, we override the * capability sets for the file. */ if (__is_eff(root_uid, new) || __is_real(root_uid, new)) { /* pP' = (cap_bset & ~0) | (pI & ~0) */ new->cap_permitted = cap_combine(old->cap_bset, old->cap_inheritable); } /* * If only the real uid is 0, we do not set the effective bit. */ if (__is_eff(root_uid, new)) *effective = true; } #define __cap_gained(field, target, source) \ !cap_issubset(target->cap_##field, source->cap_##field) #define __cap_grew(target, source, cred) \ !cap_issubset(cred->cap_##target, cred->cap_##source) #define __cap_full(field, cred) \ cap_issubset(CAP_FULL_SET, cred->cap_##field) static inline bool __is_setuid(struct cred *new, const struct cred *old) { return !uid_eq(new->euid, old->uid); } static inline bool __is_setgid(struct cred *new, const struct cred *old) { return !gid_eq(new->egid, old->gid); } /* * 1) Audit candidate if current->cap_effective is set * * We do not bother to audit if 3 things are true: * 1) cap_effective has all caps * 2) we became root *OR* are were already root * 3) root is supposed to have all caps (SECURE_NOROOT) * Since this is just a normal root execing a process. * * Number 1 above might fail if you don't have a full bset, but I think * that is interesting information to audit. * * A number of other conditions require logging: * 2) something prevented setuid root getting all caps * 3) non-setuid root gets fcaps * 4) non-setuid root gets ambient */ static inline bool nonroot_raised_pE(struct cred *new, const struct cred *old, kuid_t root, bool has_fcap) { bool ret = false; if ((__cap_grew(effective, ambient, new) && !(__cap_full(effective, new) && (__is_eff(root, new) || __is_real(root, new)) && root_privileged())) || (root_privileged() && __is_suid(root, new) && !__cap_full(effective, new)) || (!__is_setuid(new, old) && ((has_fcap && __cap_gained(permitted, new, old)) || __cap_gained(ambient, new, old)))) ret = true; return ret; } /** * cap_bprm_creds_from_file - Set up the proposed credentials for execve(). * @bprm: The execution parameters, including the proposed creds * @file: The file to pull the credentials from * * Set up the proposed credentials for a new execution context being * constructed by execve(). The proposed creds in @bprm->cred is altered, * which won't take effect immediately. * * Return: 0 if successful, -ve on error. */ int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file) { /* Process setpcap binaries and capabilities for uid 0 */ const struct cred *old = current_cred(); struct cred *new = bprm->cred; bool effective = false, has_fcap = false, is_setid; int ret; kuid_t root_uid; if (WARN_ON(!cap_ambient_invariant_ok(old))) return -EPERM; ret = get_file_caps(bprm, file, &effective, &has_fcap); if (ret < 0) return ret; root_uid = make_kuid(new->user_ns, 0); handle_privileged_root(bprm, has_fcap, &effective, root_uid); /* if we have fs caps, clear dangerous personality flags */ if (__cap_gained(permitted, new, old)) bprm->per_clear |= PER_CLEAR_ON_SETID; /* Don't let someone trace a set[ug]id/setpcap binary with the revised * credentials unless they have the appropriate permit. * * In addition, if NO_NEW_PRIVS, then ensure we get no new privs. */ is_setid = __is_setuid(new, old) || __is_setgid(new, old); if ((is_setid || __cap_gained(permitted, new, old)) && ((bprm->unsafe & ~LSM_UNSAFE_PTRACE) || !ptracer_capable(current, new->user_ns))) { /* downgrade; they get no more than they had, and maybe less */ if (!ns_capable(new->user_ns, CAP_SETUID) || (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) { new->euid = new->uid; new->egid = new->gid; } new->cap_permitted = cap_intersect(new->cap_permitted, old->cap_permitted); } new->suid = new->fsuid = new->euid; new->sgid = new->fsgid = new->egid; /* File caps or setid cancels ambient. */ if (has_fcap || is_setid) cap_clear(new->cap_ambient); /* * Now that we've computed pA', update pP' to give: * pP' = (X & fP) | (pI & fI) | pA' */ new->cap_permitted = cap_combine(new->cap_permitted, new->cap_ambient); /* * Set pE' = (fE ? pP' : pA'). Because pA' is zero if fE is set, * this is the same as pE' = (fE ? pP' : 0) | pA'. */ if (effective) new->cap_effective = new->cap_permitted; else new->cap_effective = new->cap_ambient; if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; if (nonroot_raised_pE(new, old, root_uid, has_fcap)) { ret = audit_log_bprm_fcaps(bprm, new, old); if (ret < 0) return ret; } new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; /* Check for privilege-elevated exec. */ if (is_setid || (!__is_real(root_uid, new) && (effective || __cap_grew(permitted, ambient, new)))) bprm->secureexec = 1; return 0; } /** * cap_inode_setxattr - Determine whether an xattr may be altered * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * @value: The value that the xattr will be changed to * @size: The size of value * @flags: The replacement flag * * Determine whether an xattr may be altered or set on an inode, returning 0 if * permission is granted, -ve if denied. * * This is used to make sure security xattrs don't get updated or set by those * who aren't privileged to do so. */ int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; /* * For XATTR_NAME_CAPS the check will be done in * cap_convert_nscap(), called by setxattr() */ if (strcmp(name, XATTR_NAME_CAPS) == 0) return 0; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /** * cap_inode_removexattr - Determine whether an xattr may be removed * * @mnt_userns: User namespace of the mount the inode was found from * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * * Determine whether an xattr may be removed from an inode, returning 0 if * permission is granted, -ve if denied. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. * * This is used to make sure security xattrs don't get removed by those who * aren't privileged to remove them. */ int cap_inode_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry, const char *name) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; if (strcmp(name, XATTR_NAME_CAPS) == 0) { /* security.capability gets namespaced */ struct inode *inode = d_backing_inode(dentry); if (!inode) return -EINVAL; if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP)) return -EPERM; return 0; } if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * cap_emulate_setxuid() fixes the effective / permitted capabilities of * a process after a call to setuid, setreuid, or setresuid. * * 1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of * {r,e,s}uid != 0, the permitted and effective capabilities are * cleared. * * 2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective * capabilities of the process are cleared. * * 3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective * capabilities are set to the permitted capabilities. * * fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should * never happen. * * -astor * * cevans - New behaviour, Oct '99 * A process may, via prctl(), elect to keep its capabilities when it * calls setuid() and switches away from uid==0. Both permitted and * effective sets will be retained. * Without this change, it was impossible for a daemon to drop only some * of its privilege. The call to setuid(!=0) would drop all privileges! * Keeping uid 0 is not an option because uid 0 owns too many vital * files.. * Thanks to Olaf Kirch and Peter Benie for spotting this. */ static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old) { kuid_t root_uid = make_kuid(old->user_ns, 0); if ((uid_eq(old->uid, root_uid) || uid_eq(old->euid, root_uid) || uid_eq(old->suid, root_uid)) && (!uid_eq(new->uid, root_uid) && !uid_eq(new->euid, root_uid) && !uid_eq(new->suid, root_uid))) { if (!issecure(SECURE_KEEP_CAPS)) { cap_clear(new->cap_permitted); cap_clear(new->cap_effective); } /* * Pre-ambient programs expect setresuid to nonroot followed * by exec to drop capabilities. We should make sure that * this remains the case. */ cap_clear(new->cap_ambient); } if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid)) cap_clear(new->cap_effective); if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid)) new->cap_effective = new->cap_permitted; } /** * cap_task_fix_setuid - Fix up the results of setuid() call * @new: The proposed credentials * @old: The current task's current credentials * @flags: Indications of what has changed * * Fix up the results of setuid() call before the credential changes are * actually applied. * * Return: 0 to grant the changes, -ve to deny them. */ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { switch (flags) { case LSM_SETID_RE: case LSM_SETID_ID: case LSM_SETID_RES: /* juggle the capabilities to follow [RES]UID changes unless * otherwise suppressed */ if (!issecure(SECURE_NO_SETUID_FIXUP)) cap_emulate_setxuid(new, old); break; case LSM_SETID_FS: /* juggle the capabilties to follow FSUID changes, unless * otherwise suppressed * * FIXME - is fsuser used for all CAP_FS_MASK capabilities? * if not, we might be a bit too harsh here. */ if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(old->user_ns, 0); if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_drop_fs_set(new->cap_effective); if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_raise_fs_set(new->cap_effective, new->cap_permitted); } break; default: return -EINVAL; } return 0; } /* * Rationale: code calling task_setscheduler, task_setioprio, and * task_setnice, assumes that * . if capable(cap_sys_nice), then those actions should be allowed * . if not capable(cap_sys_nice), but acting on your own processes, * then those actions should be allowed * This is insufficient now since you can call code without suid, but * yet with increased caps. * So we check for increased caps on the target process. */ static int cap_safe_nice(struct task_struct *p) { int is_subset, ret = 0; rcu_read_lock(); is_subset = cap_issubset(__task_cred(p)->cap_permitted, current_cred()->cap_permitted); if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) ret = -EPERM; rcu_read_unlock(); return ret; } /** * cap_task_setscheduler - Detemine if scheduler policy change is permitted * @p: The task to affect * * Detemine if the requested scheduler policy change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setscheduler(struct task_struct *p) { return cap_safe_nice(p); } /** * cap_task_setioprio - Detemine if I/O priority change is permitted * @p: The task to affect * @ioprio: The I/O priority to set * * Detemine if the requested I/O priority change is permitted for the specified * task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setioprio(struct task_struct *p, int ioprio) { return cap_safe_nice(p); } /** * cap_task_setnice - Detemine if task priority change is permitted * @p: The task to affect * @nice: The nice value to set * * Detemine if the requested task priority change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setnice(struct task_struct *p, int nice) { return cap_safe_nice(p); } /* * Implement PR_CAPBSET_DROP. Attempt to remove the specified capability from * the current task's bounding set. Returns 0 on success, -ve on error. */ static int cap_prctl_drop(unsigned long cap) { struct cred *new; if (!ns_capable(current_user_ns(), CAP_SETPCAP)) return -EPERM; if (!cap_valid(cap)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_lower(new->cap_bset, cap); return commit_creds(new); } /** * cap_task_prctl - Implement process control functions for this security module * @option: The process control function requested * @arg2: The argument data for this function * @arg3: The argument data for this function * @arg4: The argument data for this function * @arg5: The argument data for this function * * Allow process control functions (sys_prctl()) to alter capabilities; may * also deny access to other functions not otherwise implemented here. * * Return: 0 or +ve on success, -ENOSYS if this function is not implemented * here, other -ve on error. If -ENOSYS is returned, sys_prctl() and other LSM * modules will consider performing the function. */ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { const struct cred *old = current_cred(); struct cred *new; switch (option) { case PR_CAPBSET_READ: if (!cap_valid(arg2)) return -EINVAL; return !!cap_raised(old->cap_bset, arg2); case PR_CAPBSET_DROP: return cap_prctl_drop(arg2); /* * The next four prctl's remain to assist with transitioning a * system from legacy UID=0 based privilege (when filesystem * capabilities are not in use) to a system using filesystem * capabilities only - as the POSIX.1e draft intended. * * Note: * * PR_SET_SECUREBITS = * issecure_mask(SECURE_KEEP_CAPS_LOCKED) * | issecure_mask(SECURE_NOROOT) * | issecure_mask(SECURE_NOROOT_LOCKED) * | issecure_mask(SECURE_NO_SETUID_FIXUP) * | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED) * * will ensure that the current process and all of its * children will be locked into a pure * capability-based-privilege environment. */ case PR_SET_SECUREBITS: if ((((old->securebits & SECURE_ALL_LOCKS) >> 1) & (old->securebits ^ arg2)) /*[1]*/ || ((old->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ || (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) != 0) /*[4]*/ /* * [1] no changing of bits that are locked * [2] no unlocking of locks * [3] no setting of unsupported bits * [4] doing anything requires privilege (go read about * the "sendmail capabilities bug") */ ) /* cannot change a locked bit */ return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; new->securebits = arg2; return commit_creds(new); case PR_GET_SECUREBITS: return old->securebits; case PR_GET_KEEPCAPS: return !!issecure(SECURE_KEEP_CAPS); case PR_SET_KEEPCAPS: if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */ return -EINVAL; if (issecure(SECURE_KEEP_CAPS_LOCKED)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2) new->securebits |= issecure_mask(SECURE_KEEP_CAPS); else new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); return commit_creds(new); case PR_CAP_AMBIENT: if (arg2 == PR_CAP_AMBIENT_CLEAR_ALL) { if (arg3 | arg4 | arg5) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_clear(new->cap_ambient); return commit_creds(new); } if (((!cap_valid(arg3)) | arg4 | arg5)) return -EINVAL; if (arg2 == PR_CAP_AMBIENT_IS_SET) { return !!cap_raised(current_cred()->cap_ambient, arg3); } else if (arg2 != PR_CAP_AMBIENT_RAISE && arg2 != PR_CAP_AMBIENT_LOWER) { return -EINVAL; } else { if (arg2 == PR_CAP_AMBIENT_RAISE && (!cap_raised(current_cred()->cap_permitted, arg3) || !cap_raised(current_cred()->cap_inheritable, arg3) || issecure(SECURE_NO_CAP_AMBIENT_RAISE))) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2 == PR_CAP_AMBIENT_RAISE) cap_raise(new->cap_ambient, arg3); else cap_lower(new->cap_ambient, arg3); return commit_creds(new); } default: /* No functionality available - continue with default */ return -ENOSYS; } } /** * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted * @mm: The VM space in which the new mapping is to be made * @pages: The size of the mapping * * Determine whether the allocation of a new virtual mapping by the current * task is permitted. * * Return: 1 if permission is granted, 0 if not. */ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { int cap_sys_admin = 0; if (cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) == 0) cap_sys_admin = 1; return cap_sys_admin; } /** * cap_mmap_addr - check if able to map given addr * @addr: address attempting to be mapped * * If the process is attempting to map memory below dac_mmap_min_addr they need * CAP_SYS_RAWIO. The other parameters to this function are unused by the * capability security module. * * Return: 0 if this mapping should be allowed or -EPERM if not. */ int cap_mmap_addr(unsigned long addr) { int ret = 0; if (addr < dac_mmap_min_addr) { ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO, CAP_OPT_NONE); /* set PF_SUPERPRIV if it turns out we allow the low mmap */ if (ret == 0) current->flags |= PF_SUPERPRIV; } return ret; } int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { return 0; } #ifdef CONFIG_SECURITY static struct security_hook_list capability_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(capable, cap_capable), LSM_HOOK_INIT(settime, cap_settime), LSM_HOOK_INIT(ptrace_access_check, cap_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, cap_ptrace_traceme), LSM_HOOK_INIT(capget, cap_capget), LSM_HOOK_INIT(capset, cap_capset), LSM_HOOK_INIT(bprm_creds_from_file, cap_bprm_creds_from_file), LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv), LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), LSM_HOOK_INIT(mmap_file, cap_mmap_file), LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid), LSM_HOOK_INIT(task_prctl, cap_task_prctl), LSM_HOOK_INIT(task_setscheduler, cap_task_setscheduler), LSM_HOOK_INIT(task_setioprio, cap_task_setioprio), LSM_HOOK_INIT(task_setnice, cap_task_setnice), LSM_HOOK_INIT(vm_enough_memory, cap_vm_enough_memory), }; static int __init capability_init(void) { security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks), "capability"); return 0; } DEFINE_LSM(capability) = { .name = "capability", .order = LSM_ORDER_FIRST, .init = capability_init, }; #endif /* CONFIG_SECURITY */ |
| 61 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 | #ifndef LLC_H #define LLC_H /* * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rculist_nulls.h> #include <linux/hash.h> #include <linux/jhash.h> #include <linux/atomic.h> struct net_device; struct packet_type; struct sk_buff; struct llc_addr { unsigned char lsap; unsigned char mac[IFHWADDRLEN]; }; #define LLC_SAP_STATE_INACTIVE 1 #define LLC_SAP_STATE_ACTIVE 2 #define LLC_SK_DEV_HASH_BITS 6 #define LLC_SK_DEV_HASH_ENTRIES (1<<LLC_SK_DEV_HASH_BITS) #define LLC_SK_LADDR_HASH_BITS 6 #define LLC_SK_LADDR_HASH_ENTRIES (1<<LLC_SK_LADDR_HASH_BITS) /** * struct llc_sap - Defines the SAP component * * @station - station this sap belongs to * @state - sap state * @p_bit - only lowest-order bit used * @f_bit - only lowest-order bit used * @laddr - SAP value in this 'lsap' * @node - entry in station sap_list * @sk_list - LLC sockets this one manages */ struct llc_sap { unsigned char state; unsigned char p_bit; unsigned char f_bit; refcount_t refcnt; int (*rcv_func)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); struct llc_addr laddr; struct list_head node; spinlock_t sk_lock; int sk_count; struct hlist_nulls_head sk_laddr_hash[LLC_SK_LADDR_HASH_ENTRIES]; struct hlist_head sk_dev_hash[LLC_SK_DEV_HASH_ENTRIES]; struct rcu_head rcu; }; static inline struct hlist_head *llc_sk_dev_hash(struct llc_sap *sap, int ifindex) { u32 bucket = hash_32(ifindex, LLC_SK_DEV_HASH_BITS); return &sap->sk_dev_hash[bucket]; } static inline u32 llc_sk_laddr_hashfn(struct llc_sap *sap, const struct llc_addr *laddr) { return hash_32(jhash(laddr->mac, sizeof(laddr->mac), 0), LLC_SK_LADDR_HASH_BITS); } static inline struct hlist_nulls_head *llc_sk_laddr_hash(struct llc_sap *sap, const struct llc_addr *laddr) { return &sap->sk_laddr_hash[llc_sk_laddr_hashfn(sap, laddr)]; } #define LLC_DEST_INVALID 0 /* Invalid LLC PDU type */ #define LLC_DEST_SAP 1 /* Type 1 goes here */ #define LLC_DEST_CONN 2 /* Type 2 goes here */ extern struct list_head llc_sap_list; int llc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); int llc_mac_hdr_init(struct sk_buff *skb, const unsigned char *sa, const unsigned char *da); void llc_add_pack(int type, void (*handler)(struct llc_sap *sap, struct sk_buff *skb)); void llc_remove_pack(int type); void llc_set_station_handler(void (*handler)(struct sk_buff *skb)); struct llc_sap *llc_sap_open(unsigned char lsap, int (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)); static inline void llc_sap_hold(struct llc_sap *sap) { refcount_inc(&sap->refcnt); } static inline bool llc_sap_hold_safe(struct llc_sap *sap) { return refcount_inc_not_zero(&sap->refcnt); } void llc_sap_close(struct llc_sap *sap); static inline void llc_sap_put(struct llc_sap *sap) { if (refcount_dec_and_test(&sap->refcnt)) llc_sap_close(sap); } struct llc_sap *llc_sap_find(unsigned char sap_value); int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, unsigned char *dmac, unsigned char dsap); void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_station_init(void); void llc_station_exit(void); #ifdef CONFIG_PROC_FS int llc_proc_init(void); void llc_proc_exit(void); #else #define llc_proc_init() (0) #define llc_proc_exit() do { } while(0) #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL int llc_sysctl_init(void); void llc_sysctl_exit(void); extern int sysctl_llc2_ack_timeout; extern int sysctl_llc2_busy_timeout; extern int sysctl_llc2_p_timeout; extern int sysctl_llc2_rej_timeout; #else #define llc_sysctl_init() (0) #define llc_sysctl_exit() do { } while(0) #endif /* CONFIG_SYSCTL */ #endif /* LLC_H */ |
| 954 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 | /* * net/tipc/bearer.h: Include file for TIPC bearer code * * Copyright (c) 1996-2006, 2013-2016, 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. */ #ifndef _TIPC_BEARER_H #define _TIPC_BEARER_H #include "netlink.h" #include "core.h" #include "msg.h" #include <net/genetlink.h> #define MAX_MEDIA 3 /* Identifiers associated with TIPC message header media address info * - address info field is 32 bytes long * - the field's actual content and length is defined per media * - remaining unused bytes in the field are set to zero */ #define TIPC_MEDIA_INFO_SIZE 32 #define TIPC_MEDIA_TYPE_OFFSET 3 #define TIPC_MEDIA_ADDR_OFFSET 4 /* * Identifiers of supported TIPC media types */ #define TIPC_MEDIA_TYPE_ETH 1 #define TIPC_MEDIA_TYPE_IB 2 #define TIPC_MEDIA_TYPE_UDP 3 /* Minimum bearer MTU */ #define TIPC_MIN_BEARER_MTU (MAX_H_SIZE + INT_H_SIZE) /* Identifiers for distinguishing between broadcast/multicast and replicast */ #define TIPC_BROADCAST_SUPPORT 1 #define TIPC_REPLICAST_SUPPORT 2 /** * struct tipc_media_addr - destination address used by TIPC bearers * @value: address info (format defined by media) * @media_id: TIPC media type identifier * @broadcast: non-zero if address is a broadcast address */ struct tipc_media_addr { u8 value[TIPC_MEDIA_INFO_SIZE]; u8 media_id; u8 broadcast; }; struct tipc_bearer; /** * struct tipc_media - Media specific info exposed to generic bearer layer * @send_msg: routine which handles buffer transmission * @enable_media: routine which enables a media * @disable_media: routine which disables a media * @addr2str: convert media address format to string * @addr2msg: convert from media addr format to discovery msg addr format * @msg2addr: convert from discovery msg addr format to media addr format * @raw2addr: convert from raw addr format to media addr format * @priority: default link (and bearer) priority * @tolerance: default time (in ms) before declaring link failure * @min_win: minimum window (in packets) before declaring link congestion * @max_win: maximum window (in packets) before declaring link congestion * @mtu: max packet size bearer can support for media type not dependent on * underlying device MTU * @type_id: TIPC media identifier * @hwaddr_len: TIPC media address len * @name: media name */ struct tipc_media { int (*send_msg)(struct net *net, struct sk_buff *buf, struct tipc_bearer *b, struct tipc_media_addr *dest); int (*enable_media)(struct net *net, struct tipc_bearer *b, struct nlattr *attr[]); void (*disable_media)(struct tipc_bearer *b); int (*addr2str)(struct tipc_media_addr *addr, char *strbuf, int bufsz); int (*addr2msg)(char *msg, struct tipc_media_addr *addr); int (*msg2addr)(struct tipc_bearer *b, struct tipc_media_addr *addr, char *msg); int (*raw2addr)(struct tipc_bearer *b, struct tipc_media_addr *addr, char *raw); u32 priority; u32 tolerance; u32 min_win; u32 max_win; u32 mtu; u32 type_id; u32 hwaddr_len; char name[TIPC_MAX_MEDIA_NAME]; }; /** * struct tipc_bearer - Generic TIPC bearer structure * @media_ptr: pointer to additional media-specific information about bearer * @mtu: max packet size bearer can support * @addr: media-specific address associated with bearer * @name: bearer name (format = media:interface) * @media: ptr to media structure associated with bearer * @bcast_addr: media address used in broadcasting * @pt: packet type for bearer * @rcu: rcu struct for tipc_bearer * @priority: default link priority for bearer * @min_win: minimum window (in packets) before declaring link congestion * @max_win: maximum window (in packets) before declaring link congestion * @tolerance: default link tolerance for bearer * @domain: network domain to which links can be established * @identity: array index of this bearer within TIPC bearer array * @disc: ptr to link setup request * @net_plane: network plane ('A' through 'H') currently associated with bearer * @up: bearer up flag (bit 0) * @refcnt: tipc_bearer reference counter * * Note: media-specific code is responsible for initialization of the fields * indicated below when a bearer is enabled; TIPC's generic bearer code takes * care of initializing all other fields. */ struct tipc_bearer { void __rcu *media_ptr; /* initialized by media */ u32 mtu; /* initialized by media */ struct tipc_media_addr addr; /* initialized by media */ char name[TIPC_MAX_BEARER_NAME]; struct tipc_media *media; struct tipc_media_addr bcast_addr; struct packet_type pt; struct rcu_head rcu; u32 priority; u32 min_win; u32 max_win; u32 tolerance; u32 domain; u32 identity; struct tipc_discoverer *disc; char net_plane; unsigned long up; refcount_t refcnt; }; struct tipc_bearer_names { char media_name[TIPC_MAX_MEDIA_NAME]; char if_name[TIPC_MAX_IF_NAME]; }; /* * TIPC routines available to supported media types */ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b); /* * Routines made available to TIPC by supported media types */ extern struct tipc_media eth_media_info; #ifdef CONFIG_TIPC_MEDIA_IB extern struct tipc_media ib_media_info; #endif #ifdef CONFIG_TIPC_MEDIA_UDP extern struct tipc_media udp_media_info; #endif int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info); int tipc_media_set_priority(const char *name, u32 new_value); int tipc_media_set_window(const char *name, u32 new_value); int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a); int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, struct nlattr *attrs[]); bool tipc_bearer_hold(struct tipc_bearer *b); void tipc_bearer_put(struct tipc_bearer *b); void tipc_disable_l2_media(struct tipc_bearer *b); int tipc_l2_send_msg(struct net *net, struct sk_buff *buf, struct tipc_bearer *b, struct tipc_media_addr *dest); void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest); void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest); struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name); int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id); struct tipc_media *tipc_media_find(const char *name); int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); int tipc_bearer_mtu(struct net *net, u32 bearer_id); bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id); void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, struct tipc_media_addr *dest); void tipc_bearer_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq, struct tipc_media_addr *dst, struct tipc_node *__dnode); void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq); void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts); int tipc_attach_loopback(struct net *net); void tipc_detach_loopback(struct net *net); static inline void tipc_loopback_trace(struct net *net, struct sk_buff_head *pkts) { if (unlikely(dev_nit_active(net->loopback_dev))) tipc_clone_to_loopback(net, pkts); } /* check if device MTU is too low for tipc headers */ static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve) { if (dev->mtu >= TIPC_MIN_BEARER_MTU + reserve) return false; netdev_warn(dev, "MTU too low for tipc bearer\n"); return true; } #endif /* _TIPC_BEARER_H */ |
| 137 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic address resultion entity * * Authors: * net_random Alan Cox * net_ratelimit Andi Kleen * in{4,6}_pton YOSHIFUJI Hideaki, Copyright (C)2006 USAGI/WIDE Project * * Created by Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/ctype.h> #include <linux/inet.h> #include <linux/mm.h> #include <linux/net.h> #include <linux/string.h> #include <linux/types.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/ratelimit.h> #include <linux/socket.h> #include <net/sock.h> #include <net/net_ratelimit.h> #include <net/ipv6.h> #include <asm/byteorder.h> #include <linux/uaccess.h> DEFINE_RATELIMIT_STATE(net_ratelimit_state, 5 * HZ, 10); /* * All net warning printk()s should be guarded by this function. */ int net_ratelimit(void) { return __ratelimit(&net_ratelimit_state); } EXPORT_SYMBOL(net_ratelimit); /* * Convert an ASCII string to binary IP. * This is outside of net/ipv4/ because various code that uses IP addresses * is otherwise not dependent on the TCP/IP stack. */ __be32 in_aton(const char *str) { unsigned int l; unsigned int val; int i; l = 0; for (i = 0; i < 4; i++) { l <<= 8; if (*str != '\0') { val = 0; while (*str != '\0' && *str != '.' && *str != '\n') { val *= 10; val += *str - '0'; str++; } l |= val; if (*str != '\0') str++; } } return htonl(l); } EXPORT_SYMBOL(in_aton); #define IN6PTON_XDIGIT 0x00010000 #define IN6PTON_DIGIT 0x00020000 #define IN6PTON_COLON_MASK 0x00700000 #define IN6PTON_COLON_1 0x00100000 /* single : requested */ #define IN6PTON_COLON_2 0x00200000 /* second : requested */ #define IN6PTON_COLON_1_2 0x00400000 /* :: requested */ #define IN6PTON_DOT 0x00800000 /* . */ #define IN6PTON_DELIM 0x10000000 #define IN6PTON_NULL 0x20000000 /* first/tail */ #define IN6PTON_UNKNOWN 0x40000000 static inline int xdigit2bin(char c, int delim) { int val; if (c == delim || c == '\0') return IN6PTON_DELIM; if (c == ':') return IN6PTON_COLON_MASK; if (c == '.') return IN6PTON_DOT; val = hex_to_bin(c); if (val >= 0) return val | IN6PTON_XDIGIT | (val < 10 ? IN6PTON_DIGIT : 0); if (delim == -1) return IN6PTON_DELIM; return IN6PTON_UNKNOWN; } /** * in4_pton - convert an IPv4 address from literal to binary representation * @src: the start of the IPv4 address string * @srclen: the length of the string, -1 means strlen(src) * @dst: the binary (u8[4] array) representation of the IPv4 address * @delim: the delimiter of the IPv4 address in @src, -1 means no delimiter * @end: A pointer to the end of the parsed string will be placed here * * Return one on success, return zero when any error occurs * and @end will point to the end of the parsed string. * */ int in4_pton(const char *src, int srclen, u8 *dst, int delim, const char **end) { const char *s; u8 *d; u8 dbuf[4]; int ret = 0; int i; int w = 0; if (srclen < 0) srclen = strlen(src); s = src; d = dbuf; i = 0; while (1) { int c; c = xdigit2bin(srclen > 0 ? *s : '\0', delim); if (!(c & (IN6PTON_DIGIT | IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK))) { goto out; } if (c & (IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK)) { if (w == 0) goto out; *d++ = w & 0xff; w = 0; i++; if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { if (i != 4) goto out; break; } goto cont; } w = (w * 10) + c; if ((w & 0xffff) > 255) { goto out; } cont: if (i >= 4) goto out; s++; srclen--; } ret = 1; memcpy(dst, dbuf, sizeof(dbuf)); out: if (end) *end = s; return ret; } EXPORT_SYMBOL(in4_pton); /** * in6_pton - convert an IPv6 address from literal to binary representation * @src: the start of the IPv6 address string * @srclen: the length of the string, -1 means strlen(src) * @dst: the binary (u8[16] array) representation of the IPv6 address * @delim: the delimiter of the IPv6 address in @src, -1 means no delimiter * @end: A pointer to the end of the parsed string will be placed here * * Return one on success, return zero when any error occurs * and @end will point to the end of the parsed string. * */ int in6_pton(const char *src, int srclen, u8 *dst, int delim, const char **end) { const char *s, *tok = NULL; u8 *d, *dc = NULL; u8 dbuf[16]; int ret = 0; int i; int state = IN6PTON_COLON_1_2 | IN6PTON_XDIGIT | IN6PTON_NULL; int w = 0; memset(dbuf, 0, sizeof(dbuf)); s = src; d = dbuf; if (srclen < 0) srclen = strlen(src); while (1) { int c; c = xdigit2bin(srclen > 0 ? *s : '\0', delim); if (!(c & state)) goto out; if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { /* process one 16-bit word */ if (!(state & IN6PTON_NULL)) { *d++ = (w >> 8) & 0xff; *d++ = w & 0xff; } w = 0; if (c & IN6PTON_DELIM) { /* We've processed last word */ break; } /* * COLON_1 => XDIGIT * COLON_2 => XDIGIT|DELIM * COLON_1_2 => COLON_2 */ switch (state & IN6PTON_COLON_MASK) { case IN6PTON_COLON_2: dc = d; state = IN6PTON_XDIGIT | IN6PTON_DELIM; if (dc - dbuf >= sizeof(dbuf)) state |= IN6PTON_NULL; break; case IN6PTON_COLON_1|IN6PTON_COLON_1_2: state = IN6PTON_XDIGIT | IN6PTON_COLON_2; break; case IN6PTON_COLON_1: state = IN6PTON_XDIGIT; break; case IN6PTON_COLON_1_2: state = IN6PTON_COLON_2; break; default: state = 0; } tok = s + 1; goto cont; } if (c & IN6PTON_DOT) { ret = in4_pton(tok ? tok : s, srclen + (int)(s - tok), d, delim, &s); if (ret > 0) { d += 4; break; } goto out; } w = (w << 4) | (0xff & c); state = IN6PTON_COLON_1 | IN6PTON_DELIM; if (!(w & 0xf000)) { state |= IN6PTON_XDIGIT; } if (!dc && d + 2 < dbuf + sizeof(dbuf)) { state |= IN6PTON_COLON_1_2; state &= ~IN6PTON_DELIM; } if (d + 2 >= dbuf + sizeof(dbuf)) { state &= ~(IN6PTON_COLON_1|IN6PTON_COLON_1_2); } cont: if ((dc && d + 4 < dbuf + sizeof(dbuf)) || d + 4 == dbuf + sizeof(dbuf)) { state |= IN6PTON_DOT; } if (d >= dbuf + sizeof(dbuf)) { state &= ~(IN6PTON_XDIGIT|IN6PTON_COLON_MASK); } s++; srclen--; } i = 15; d--; if (dc) { while (d >= dc) dst[i--] = *d--; while (i >= dc - dbuf) dst[i--] = 0; while (i >= 0) dst[i--] = *d--; } else memcpy(dst, dbuf, sizeof(dbuf)); ret = 1; out: if (end) *end = s; return ret; } EXPORT_SYMBOL(in6_pton); static int inet4_pton(const char *src, u16 port_num, struct sockaddr_storage *addr) { struct sockaddr_in *addr4 = (struct sockaddr_in *)addr; int srclen = strlen(src); if (srclen > INET_ADDRSTRLEN) return -EINVAL; if (in4_pton(src, srclen, (u8 *)&addr4->sin_addr.s_addr, '\n', NULL) == 0) return -EINVAL; addr4->sin_family = AF_INET; addr4->sin_port = htons(port_num); return 0; } static int inet6_pton(struct net *net, const char *src, u16 port_num, struct sockaddr_storage *addr) { struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)addr; const char *scope_delim; int srclen = strlen(src); if (srclen > INET6_ADDRSTRLEN) return -EINVAL; if (in6_pton(src, srclen, (u8 *)&addr6->sin6_addr.s6_addr, '%', &scope_delim) == 0) return -EINVAL; if (ipv6_addr_type(&addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL && src + srclen != scope_delim && *scope_delim == '%') { struct net_device *dev; char scope_id[16]; size_t scope_len = min_t(size_t, sizeof(scope_id) - 1, src + srclen - scope_delim - 1); memcpy(scope_id, scope_delim + 1, scope_len); scope_id[scope_len] = '\0'; dev = dev_get_by_name(net, scope_id); if (dev) { addr6->sin6_scope_id = dev->ifindex; dev_put(dev); } else if (kstrtouint(scope_id, 0, &addr6->sin6_scope_id)) { return -EINVAL; } } addr6->sin6_family = AF_INET6; addr6->sin6_port = htons(port_num); return 0; } /** * inet_pton_with_scope - convert an IPv4/IPv6 and port to socket address * @net: net namespace (used for scope handling) * @af: address family, AF_INET, AF_INET6 or AF_UNSPEC for either * @src: the start of the address string * @port: the start of the port string (or NULL for none) * @addr: output socket address * * Return zero on success, return errno when any error occurs. */ int inet_pton_with_scope(struct net *net, __kernel_sa_family_t af, const char *src, const char *port, struct sockaddr_storage *addr) { u16 port_num; int ret = -EINVAL; if (port) { if (kstrtou16(port, 0, &port_num)) return -EINVAL; } else { port_num = 0; } switch (af) { case AF_INET: ret = inet4_pton(src, port_num, addr); break; case AF_INET6: ret = inet6_pton(net, src, port_num, addr); break; case AF_UNSPEC: ret = inet4_pton(src, port_num, addr); if (ret) ret = inet6_pton(net, src, port_num, addr); break; default: pr_err("unexpected address family %d\n", af); } return ret; } EXPORT_SYMBOL(inet_pton_with_scope); bool inet_addr_is_any(struct sockaddr *addr) { if (addr->sa_family == AF_INET6) { struct sockaddr_in6 *in6 = (struct sockaddr_in6 *)addr; const struct sockaddr_in6 in6_any = { .sin6_addr = IN6ADDR_ANY_INIT }; if (!memcmp(in6->sin6_addr.s6_addr, in6_any.sin6_addr.s6_addr, 16)) return true; } else if (addr->sa_family == AF_INET) { struct sockaddr_in *in = (struct sockaddr_in *)addr; if (in->sin_addr.s_addr == htonl(INADDR_ANY)) return true; } else { pr_warn("unexpected address family %u\n", addr->sa_family); } return false; } EXPORT_SYMBOL(inet_addr_is_any); void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr) { if (skb->ip_summed != CHECKSUM_PARTIAL) { csum_replace4(sum, from, to); if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) skb->csum = ~csum_add(csum_sub(~(skb->csum), (__force __wsum)from), (__force __wsum)to); } else if (pseudohdr) *sum = ~csum_fold(csum_add(csum_sub(csum_unfold(*sum), (__force __wsum)from), (__force __wsum)to)); } EXPORT_SYMBOL(inet_proto_csum_replace4); /** * inet_proto_csum_replace16 - update layer 4 header checksum field * @sum: Layer 4 header checksum field * @skb: sk_buff for the packet * @from: old IPv6 address * @to: new IPv6 address * @pseudohdr: True if layer 4 header checksum includes pseudoheader * * Update layer 4 header as per the update in IPv6 src/dst address. * * There is no need to update skb->csum in this function, because update in two * fields a.) IPv6 src/dst address and b.) L4 header checksum cancels each other * for skb->csum calculation. Whereas inet_proto_csum_replace4 function needs to * update skb->csum, because update in 3 fields a.) IPv4 src/dst address, * b.) IPv4 Header checksum and c.) L4 header checksum results in same diff as * L4 Header checksum for skb->csum calculation. */ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, const __be32 *from, const __be32 *to, bool pseudohdr) { __be32 diff[] = { ~from[0], ~from[1], ~from[2], ~from[3], to[0], to[1], to[2], to[3], }; if (skb->ip_summed != CHECKSUM_PARTIAL) { *sum = csum_fold(csum_partial(diff, sizeof(diff), ~csum_unfold(*sum))); } else if (pseudohdr) *sum = ~csum_fold(csum_partial(diff, sizeof(diff), csum_unfold(*sum))); } EXPORT_SYMBOL(inet_proto_csum_replace16); void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, __wsum diff, bool pseudohdr) { if (skb->ip_summed != CHECKSUM_PARTIAL) { *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum))); if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) skb->csum = ~csum_add(diff, ~skb->csum); } else if (pseudohdr) { *sum = ~csum_fold(csum_add(diff, csum_unfold(*sum))); } } EXPORT_SYMBOL(inet_proto_csum_replace_by_diff); |
| 84 84 84 736 736 6 4 2 6 756 753 3 750 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * RAW sockets for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Adapted from linux/net/ipv4/raw.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI,H.@USAGI : raw checksum (RFC2292(bis) compliance) * Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/slab.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/skbuff.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> #include <net/transp_v6.h> #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif #include <linux/mroute6.h> #include <net/raw.h> #include <net/rawv6.h> #include <net/xfrm.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/export.h> #define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */ struct raw_hashinfo raw_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock), }; EXPORT_SYMBOL_GPL(raw_v6_hashinfo); struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, unsigned short num, const struct in6_addr *loc_addr, const struct in6_addr *rmt_addr, int dif, int sdif) { bool is_multicast = ipv6_addr_is_multicast(loc_addr); sk_for_each_from(sk) if (inet_sk(sk)->inet_num == num) { if (!net_eq(sock_net(sk), net)) continue; if (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) continue; if (!raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) continue; if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { if (ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) goto found; if (is_multicast && inet6_mc_check(sk, loc_addr, rmt_addr)) goto found; continue; } goto found; } sk = NULL; found: return sk; } EXPORT_SYMBOL_GPL(__raw_v6_lookup); /* * 0 - deliver * 1 - block */ static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) { struct icmp6hdr _hdr; const struct icmp6hdr *hdr; /* We require only the four bytes of the ICMPv6 header, not any * additional bytes of message body in "struct icmp6hdr". */ hdr = skb_header_pointer(skb, skb_transport_offset(skb), ICMPV6_HDRLEN, &_hdr); if (hdr) { const __u32 *data = &raw6_sk(sk)->filter.data[0]; unsigned int type = hdr->icmp6_type; return (data[type >> 5] & (1U << (type & 31))) != 0; } return 1; } #if IS_ENABLED(CONFIG_IPV6_MIP6) typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb); static mh_filter_t __rcu *mh_filter __read_mostly; int rawv6_mh_filter_register(mh_filter_t filter) { rcu_assign_pointer(mh_filter, filter); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_register); int rawv6_mh_filter_unregister(mh_filter_t filter) { RCU_INIT_POINTER(mh_filter, NULL); synchronize_rcu(); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_unregister); #endif /* * demultiplex raw sockets. * (should consider queueing the skb in the sock receive_queue * without calling rawv6.c) * * Caller owns SKB so we must make clones. */ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { const struct in6_addr *saddr; const struct in6_addr *daddr; struct sock *sk; bool delivered = false; __u8 hash; struct net *net; saddr = &ipv6_hdr(skb)->saddr; daddr = saddr + 1; hash = nexthdr & (RAW_HTABLE_SIZE - 1); read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); if (!sk) goto out; net = dev_net(skb->dev); sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb)); while (sk) { int filtered; delivered = true; switch (nexthdr) { case IPPROTO_ICMPV6: filtered = icmpv6_filter(sk, skb); break; #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: { /* XXX: To validate MH only once for each packet, * this is placed here. It should be after checking * xfrm policy, however it doesn't. The checking xfrm * policy is placed in rawv6_rcv() because it is * required for each socket. */ mh_filter_t *filter; filter = rcu_dereference(mh_filter); filtered = filter ? (*filter)(sk, skb) : 0; break; } #endif default: filtered = 0; break; } if (filtered < 0) break; if (filtered == 0) { struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); /* Not releasing hash table! */ if (clone) { nf_reset_ct(clone); rawv6_rcv(sk, clone); } } sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb)); } out: read_unlock(&raw_v6_hashinfo.lock); return delivered; } bool raw6_local_deliver(struct sk_buff *skb, int nexthdr) { struct sock *raw_sk; raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (RAW_HTABLE_SIZE - 1)]); if (raw_sk && !ipv6_raw_deliver(skb, nexthdr)) raw_sk = NULL; return raw_sk != NULL; } /* This cleans up af_inet6 a bit. -DaveM */ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr; __be32 v4addr = 0; int addr_type; int err; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (addr->sin6_family != AF_INET6) return -EINVAL; addr_type = ipv6_addr_type(&addr->sin6_addr); /* Raw sockets are IPv6 only */ if (addr_type == IPV6_ADDR_MAPPED) return -EADDRNOTAVAIL; lock_sock(sk); err = -EINVAL; if (sk->sk_state != TCP_CLOSE) goto out; rcu_read_lock(); /* Check if the address belongs to the host. */ if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && addr->sin6_scope_id) { /* Override any existing binding, if another * one is supplied by user. */ sk->sk_bound_dev_if = addr->sin6_scope_id; } /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) goto out_unlock; } if (sk->sk_bound_dev_if) { err = -ENODEV; dev = dev_get_by_index_rcu(sock_net(sk), sk->sk_bound_dev_if); if (!dev) goto out_unlock; } /* ipv4 addr of the socket is invalid. Only the * unspecified and mapped address have a v4 equivalent. */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST) && !ipv6_can_nonlocal_bind(sock_net(sk), inet)) { err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { goto out_unlock; } } } inet->inet_rcv_saddr = inet->inet_saddr = v4addr; sk->sk_v6_rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; err = 0; out_unlock: rcu_read_unlock(); out: release_sock(sk); return err; } static void rawv6_err(struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); int err; int harderr; /* Report error on raw socket, if: 1. User requested recverr. 2. Socket is connected (otherwise the error indication is useless without recverr and error is hard. */ if (!np->recverr && sk->sk_state != TCP_ESTABLISHED) return; harderr = icmpv6_err_convert(type, code, &err); if (type == ICMPV6_PKT_TOOBIG) { ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); } if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); return; } if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) payload += offset; ipv6_icmp_error(sk, skb, err, 0, ntohl(info), payload); } if (np->recverr || harderr) { sk->sk_err = err; sk_error_report(sk); } } void raw6_icmp_error(struct sk_buff *skb, int nexthdr, u8 type, u8 code, int inner_offset, __be32 info) { struct sock *sk; int hash; const struct in6_addr *saddr, *daddr; struct net *net; hash = nexthdr & (RAW_HTABLE_SIZE - 1); read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); if (sk) { /* Note: ipv6_hdr(skb) != skb->data */ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; saddr = &ip6h->saddr; daddr = &ip6h->daddr; net = dev_net(skb->dev); while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr, inet6_iif(skb), inet6_iif(skb)))) { rawv6_err(sk, skb, NULL, type, code, inner_offset, info); sk = sk_next(sk); } } read_unlock(&raw_v6_hashinfo.lock); } static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) { if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } /* Charge it to the socket. */ skb_dst_drop(skb); if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } return 0; } /* * This is next to useless... * if we demultiplex in network layer we don't need the extra call * just to queue the skb... * maybe we could have the network decide upon a hint if it * should call raw_rcv for demultiplexing */ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) { struct inet_sock *inet = inet_sk(sk); struct raw6_sock *rp = raw6_sk(sk); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } if (!rp->checksum) skb->ip_summed = CHECKSUM_UNNECESSARY; if (skb->ip_summed == CHECKSUM_COMPLETE) { skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); if (!csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; } if (!skb_csum_unnecessary(skb)) skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, 0)); if (inet->hdrincl) { if (skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } } rawv6_rcv_skb(sk, skb); return 0; } /* * This should be easy, if there is something there * we return it, otherwise we block. */ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct sk_buff *skb; size_t copied; int err; if (flags & MSG_OOB) return -EOPNOTSUPP; if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) return ipv6_recv_rxpmtu(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } if (skb_csum_unnecessary(skb)) { err = skb_copy_datagram_msg(skb, 0, msg, copied); } else if (msg->msg_flags&MSG_TRUNC) { if (__skb_checksum_complete(skb)) goto csum_copy_err; err = skb_copy_datagram_msg(skb, 0, msg, copied); } else { err = skb_copy_and_csum_datagram_msg(skb, 0, msg); if (err == -EINVAL) goto csum_copy_err; } if (err) goto out_free; /* Copy the address. */ if (sin6) { sin6->sin6_family = AF_INET6; sin6->sin6_port = 0; sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, inet6_iif(skb)); *addr_len = sizeof(*sin6); } sock_recv_ts_and_drops(msg, sk, skb); if (np->rxopt.all) ip6_datagram_recv_ctl(sk, msg, skb); err = copied; if (flags & MSG_TRUNC) err = skb->len; out_free: skb_free_datagram(sk, skb); out: return err; csum_copy_err: skb_kill_datagram(sk, skb, flags); /* Error for blocking case is chosen to masquerade as some normal condition. */ err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH; goto out; } static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { struct ipv6_txoptions *opt; struct sk_buff *skb; int err = 0; int offset; int len; int total_len; __wsum tmp_csum; __sum16 csum; if (!rp->checksum) goto send; skb = skb_peek(&sk->sk_write_queue); if (!skb) goto out; offset = rp->offset; total_len = inet_sk(sk)->cork.base.length; opt = inet6_sk(sk)->cork.opt; total_len -= opt ? opt->opt_flen : 0; if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); goto out; } /* should be check HW csum miyazawa */ if (skb_queue_len(&sk->sk_write_queue) == 1) { /* * Only one fragment on the socket. */ tmp_csum = skb->csum; } else { struct sk_buff *csum_skb = NULL; tmp_csum = 0; skb_queue_walk(&sk->sk_write_queue, skb) { tmp_csum = csum_add(tmp_csum, skb->csum); if (csum_skb) continue; len = skb->len - skb_transport_offset(skb); if (offset >= len) { offset -= len; continue; } csum_skb = skb; } skb = csum_skb; } offset += skb_transport_offset(skb); err = skb_copy_bits(skb, offset, &csum, 2); if (err < 0) { ip6_flush_pending_frames(sk); goto out; } /* in case cksum was not initialized */ if (unlikely(csum)) tmp_csum = csum_sub(tmp_csum, csum_unfold(csum)); csum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, total_len, fl6->flowi6_proto, tmp_csum); if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP) csum = CSUM_MANGLED_0; BUG_ON(skb_store_bits(skb, offset, &csum, 2)); send: err = ip6_push_pending_frames(sk); out: return err; } static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, struct flowi6 *fl6, struct dst_entry **dstp, unsigned int flags, const struct sockcm_cookie *sockc) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6hdr *iph; struct sk_buff *skb; int err; struct rt6_info *rt = (struct rt6_info *)*dstp; int hlen = LL_RESERVED_SPACE(rt->dst.dev); int tlen = rt->dst.dev->needed_tailroom; if (length > rt->dst.dev->mtu) { ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu); return -EMSGSIZE; } if (length < sizeof(struct ipv6hdr)) return -EINVAL; if (flags&MSG_PROBE) goto out; skb = sock_alloc_send_skb(sk, length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (!skb) goto error; skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); skb->priority = sk->sk_priority; skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; skb_put(skb, length); skb_reset_network_header(skb); iph = ipv6_hdr(skb); skb->ip_summed = CHECKSUM_NONE; skb_setup_tx_timestamp(skb, sockc->tsflags); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); skb->transport_header = skb->network_header; err = memcpy_from_msg(iph, msg, length); if (err) { err = -EFAULT; kfree_skb(skb); goto error; } skb_dst_set(skb, &rt->dst); *dstp = NULL; /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out(sk, skb); if (unlikely(!skb)) return 0; /* Acquire rcu_read_lock() in case we need to use rt->rt6i_idev * in the error path. Since skb has been freed, the dst could * have been queued for deletion. */ rcu_read_lock(); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) { IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); goto error_check; } rcu_read_unlock(); out: return 0; error: IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); error_check: if (err == -ENOBUFS && !np->recverr) err = 0; return err; } struct raw6_frag_vec { struct msghdr *msg; int hlen; char c[4]; }; static int rawv6_probe_proto_opt(struct raw6_frag_vec *rfv, struct flowi6 *fl6) { int err = 0; switch (fl6->flowi6_proto) { case IPPROTO_ICMPV6: rfv->hlen = 2; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) { fl6->fl6_icmp_type = rfv->c[0]; fl6->fl6_icmp_code = rfv->c[1]; } break; case IPPROTO_MH: rfv->hlen = 4; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) fl6->fl6_mh_type = rfv->c[2]; } return err; } static int raw6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct raw6_frag_vec *rfv = from; if (offset < rfv->hlen) { int copy = min(rfv->hlen - offset, len); if (skb->ip_summed == CHECKSUM_PARTIAL) memcpy(to, rfv->c + offset, copy); else skb->csum = csum_block_add( skb->csum, csum_partial_copy_nocheck(rfv->c + offset, to, copy), odd); odd = 0; offset += copy; to += copy; len -= copy; if (!len) return 0; } offset -= rfv->hlen; return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb); } static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions *opt_to_free = NULL; struct ipv6_txoptions opt_space; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct raw6_sock *rp = raw6_sk(sk); struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; struct raw6_frag_vec rfv; struct flowi6 fl6; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; int hdrincl; u16 proto; int err; /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ if (len > INT_MAX) return -EMSGSIZE; /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; /* hdrincl should be READ_ONCE(inet->hdrincl) * but READ_ONCE() doesn't work with bit fields. * Doing this indirectly yields the same result. */ hdrincl = inet->hdrincl; hdrincl = READ_ONCE(hdrincl); /* * Get and verify the address. */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_mark = sk->sk_mark; fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); ipc6.sockc.tsflags = sk->sk_tsflags; ipc6.sockc.mark = sk->sk_mark; if (sin6) { if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (sin6->sin6_family && sin6->sin6_family != AF_INET6) return -EAFNOSUPPORT; /* port is the proto value [0..255] carried in nexthdr */ proto = ntohs(sin6->sin6_port); if (!proto) proto = inet->inet_num; else if (proto != inet->inet_num && inet->inet_num != IPPROTO_RAW) return -EINVAL; if (proto > 255) return -EINVAL; daddr = &sin6->sin6_addr; if (np->sndflow) { fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } } /* * Otherwise it will be difficult to maintain * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) fl6.flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; proto = inet->inet_num; daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; } if (fl6.flowi6_oif == 0) fl6.flowi6_oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); ipc6.opt = opt; err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); if (err < 0) { fl6_sock_release(flowlabel); return err; } if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; } if (!opt) { opt = txopt_get(np); opt_to_free = opt; } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); fl6.flowi6_proto = proto; fl6.flowi6_mark = ipc6.sockc.mark; if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; err = rawv6_probe_proto_opt(&rfv, &fl6); if (err) goto out; } if (!ipv6_addr_any(daddr)) fl6.daddr = *daddr; else fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) fl6.saddr = np->saddr; final_p = fl6_update_dst(&fl6, opt, &final); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = np->mcast_oif; else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); if (hdrincl) fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH; if (ipc6.tclass < 0) ipc6.tclass = np->tclass; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; } if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); if (ipc6.dontfrag < 0) ipc6.dontfrag = np->dontfrag; if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: if (hdrincl) err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags, &ipc6.sockc); else { ipc6.opt = opt; lock_sock(sk); err = ip6_append_data(sk, raw6_getfrag, &rfv, len, 0, &ipc6, &fl6, (struct rt6_info *)dst, msg->msg_flags); if (err) ip6_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) err = rawv6_push_pending_frames(sk, &fl6, rp); release_sock(sk); } done: dst_release(dst); out: fl6_sock_release(flowlabel); txopt_put(opt_to_free); return err < 0 ? err : len; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(dst, &fl6.daddr); if (!(msg->msg_flags & MSG_PROBE) || len) goto back_from_confirm; err = 0; goto done; } static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, sockptr_t optval, int optlen) { switch (optname) { case ICMPV6_FILTER: if (optlen > sizeof(struct icmp6_filter)) optlen = sizeof(struct icmp6_filter); if (copy_from_sockptr(&raw6_sk(sk)->filter, optval, optlen)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { int len; switch (optname) { case ICMPV6_FILTER: if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; if (len > sizeof(struct icmp6_filter)) len = sizeof(struct icmp6_filter); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &raw6_sk(sk)->filter, len)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (optname) { case IPV6_HDRINCL: if (sk->sk_type != SOCK_RAW) return -EINVAL; inet_sk(sk)->hdrincl = !!val; return 0; case IPV6_CHECKSUM: if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && level == IPPROTO_IPV6) { /* * RFC3542 tells that IPV6_CHECKSUM socket * option in the IPPROTO_IPV6 level is not * allowed on ICMPv6 sockets. * If you want to set it, use IPPROTO_RAW * level IPV6_CHECKSUM socket option * (Linux extension). */ return -EINVAL; } /* You may get strange result with a positive odd offset; RFC2292bis agrees with me. */ if (val > 0 && (val&1)) return -EINVAL; if (val < 0) { rp->checksum = 0; } else { rp->checksum = 1; rp->offset = val; } return 0; default: return -ENOPROTOOPT; } } static int rawv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; fallthrough; default: return ipv6_setsockopt(sk, level, optname, optval, optlen); } return do_rawv6_setsockopt(sk, level, optname, optval, optlen); } static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct raw6_sock *rp = raw6_sk(sk); int val, len; if (get_user(len, optlen)) return -EFAULT; switch (optname) { case IPV6_HDRINCL: val = inet_sk(sk)->hdrincl; break; case IPV6_CHECKSUM: /* * We allow getsockopt() for IPPROTO_IPV6-level * IPV6_CHECKSUM socket option on ICMPv6 sockets * since RFC3542 is silent about it. */ if (rp->checksum == 0) val = -1; else val = rp->offset; break; default: return -ENOPROTOOPT; } len = min_t(unsigned int, sizeof(int), len); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; fallthrough; default: return ipv6_getsockopt(sk, level, optname, optval, optlen); } return do_rawv6_getsockopt(sk, level, optname, optval, optlen); } static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); return put_user(amount, (int __user *)arg); } case SIOCINQ: { struct sk_buff *skb; int amount = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } default: #ifdef CONFIG_IPV6_MROUTE return ip6mr_ioctl(sk, cmd, (void __user *)arg); #else return -ENOIOCTLCMD; #endif } } #ifdef CONFIG_COMPAT static int compat_rawv6_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: case SIOCINQ: return -ENOIOCTLCMD; default: #ifdef CONFIG_IPV6_MROUTE return ip6mr_compat_ioctl(sk, cmd, compat_ptr(arg)); #else return -ENOIOCTLCMD; #endif } } #endif static void rawv6_close(struct sock *sk, long timeout) { if (inet_sk(sk)->inet_num == IPPROTO_RAW) ip6_ra_control(sk, -1); ip6mr_sk_done(sk); sk_common_release(sk); } static void raw6_destroy(struct sock *sk) { lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); } static int rawv6_init_sk(struct sock *sk) { struct raw6_sock *rp = raw6_sk(sk); switch (inet_sk(sk)->inet_num) { case IPPROTO_ICMPV6: rp->checksum = 1; rp->offset = 2; break; case IPPROTO_MH: rp->checksum = 1; rp->offset = 4; break; default: break; } return 0; } struct proto rawv6_prot = { .name = "RAWv6", .owner = THIS_MODULE, .close = rawv6_close, .destroy = raw6_destroy, .connect = ip6_datagram_connect_v6_only, .disconnect = __udp_disconnect, .ioctl = rawv6_ioctl, .init = rawv6_init_sk, .setsockopt = rawv6_setsockopt, .getsockopt = rawv6_getsockopt, .sendmsg = rawv6_sendmsg, .recvmsg = rawv6_recvmsg, .bind = rawv6_bind, .backlog_rcv = rawv6_rcv_skb, .hash = raw_hash_sk, .unhash = raw_unhash_sk, .obj_size = sizeof(struct raw6_sock), .useroffset = offsetof(struct raw6_sock, filter), .usersize = sizeof_field(struct raw6_sock, filter), .h.raw_hash = &raw_v6_hashinfo, #ifdef CONFIG_COMPAT .compat_ioctl = compat_rawv6_ioctl, #endif .diag_destroy = raw_abort, }; #ifdef CONFIG_PROC_FS static int raw6_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); } else { struct sock *sp = v; __u16 srcp = inet_sk(sp)->inet_num; ip6_dgram_sock_seq_show(seq, v, srcp, 0, raw_seq_private(seq)->bucket); } return 0; } static const struct seq_operations raw6_seq_ops = { .start = raw_seq_start, .next = raw_seq_next, .stop = raw_seq_stop, .show = raw6_seq_show, }; static int __net_init raw6_init_net(struct net *net) { if (!proc_create_net_data("raw6", 0444, net->proc_net, &raw6_seq_ops, sizeof(struct raw_iter_state), &raw_v6_hashinfo)) return -ENOMEM; return 0; } static void __net_exit raw6_exit_net(struct net *net) { remove_proc_entry("raw6", net->proc_net); } static struct pernet_operations raw6_net_ops = { .init = raw6_init_net, .exit = raw6_exit_net, }; int __init raw6_proc_init(void) { return register_pernet_subsys(&raw6_net_ops); } void raw6_proc_exit(void) { unregister_pernet_subsys(&raw6_net_ops); } #endif /* CONFIG_PROC_FS */ /* Same as inet6_dgram_ops, sans udp_poll. */ const struct proto_ops inet6_sockraw_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, .connect = inet_dgram_connect, /* ok */ .socketpair = sock_no_socketpair, /* a do nothing */ .accept = sock_no_accept, /* a do nothing */ .getname = inet6_getname, .poll = datagram_poll, /* ok */ .ioctl = inet6_ioctl, /* must change */ .gettstamp = sock_gettstamp, .listen = sock_no_listen, /* ok */ .shutdown = inet_shutdown, /* ok */ .setsockopt = sock_common_setsockopt, /* ok */ .getsockopt = sock_common_getsockopt, /* ok */ .sendmsg = inet_sendmsg, /* ok */ .recvmsg = sock_common_recvmsg, /* ok */ .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif }; static struct inet_protosw rawv6_protosw = { .type = SOCK_RAW, .protocol = IPPROTO_IP, /* wild card */ .prot = &rawv6_prot, .ops = &inet6_sockraw_ops, .flags = INET_PROTOSW_REUSE, }; int __init rawv6_init(void) { return inet6_register_protosw(&rawv6_protosw); } void rawv6_exit(void) { inet6_unregister_protosw(&rawv6_protosw); } |
| 889 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H #include <linux/sched/coredump.h> #include <linux/mm_types.h> #include <linux/fs.h> /* only for vma_is_dax() */ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); void huge_pmd_set_accessed(struct vm_fault *vmf); int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, struct vm_area_struct *vma); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud); #else static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) { } #endif vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf); struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags); bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long next); int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr); int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr); bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd); int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, unsigned long cp_flags); vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, pgprot_t pgprot, bool write); /** * vmf_insert_pfn_pmd - insert a pmd size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert * @pgprot: page protection to use * @write: whether it's a write fault * * Insert a pmd size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ static inline vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write) { return vmf_insert_pfn_pmd_prot(vmf, pfn, vmf->vma->vm_page_prot, write); } vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn, pgprot_t pgprot, bool write); /** * vmf_insert_pfn_pud - insert a pud size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert * @pgprot: page protection to use * @write: whether it's a write fault * * Insert a pud size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ static inline vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write) { return vmf_insert_pfn_pud_prot(vmf, pfn, vmf->vma->vm_page_prot, write); } enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_NEVER_DAX, TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG, }; struct kobject; struct kobj_attribute; ssize_t single_hugepage_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag); ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define HPAGE_PMD_SHIFT PMD_SHIFT #define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) #define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1)) #define HPAGE_PUD_SHIFT PUD_SHIFT #define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) #define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1)) extern unsigned long transparent_hugepage_flags; static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, unsigned long haddr) { /* Don't have to check pgoff for anonymous vma */ if (!vma_is_anonymous(vma)) { if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, HPAGE_PMD_NR)) return false; } if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) return false; return true; } static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, unsigned long vm_flags) { /* Explicitly disabled through madvise. */ if ((vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) return false; return true; } /* * to be used on vmas which are known to support THP. * Use transparent_hugepage_active otherwise */ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { /* * If the hardware/firmware marked hugepage support disabled. */ if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) return false; if (!transhuge_vma_enabled(vma, vma->vm_flags)) return false; if (vma_is_temporary_stack(vma)) return false; if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) return true; if (vma_is_dax(vma)) return true; if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)) return !!(vma->vm_flags & VM_HUGEPAGE); return false; } bool transparent_hugepage_active(struct vm_area_struct *vma); #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); void prep_transhuge_page(struct page *page); void free_transhuge_page(struct page *page); bool is_transparent_hugepage(struct page *page); bool can_split_huge_page(struct page *page, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { return split_huge_page_to_list(page, NULL); } void deferred_split_huge_page(struct page *page); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct page *page); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ pmd_t *____pmd = (__pmd); \ if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd) \ || pmd_devmap(*____pmd)) \ __split_huge_pmd(__vma, __pmd, __address, \ false, NULL); \ } while (0) void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page); void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address); #define split_huge_pud(__vma, __pud, __address) \ do { \ pud_t *____pud = (__pud); \ if (pud_trans_huge(*____pud) \ || pud_devmap(*____pud)) \ __split_huge_pud(__vma, __pud, __address); \ } while (0) int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice); void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma); static inline int is_swap_pmd(pmd_t pmd) { return !pmd_none(pmd) && !pmd_present(pmd); } /* mmap_lock must be held on entry */ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma); else return NULL; } static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { if (pud_trans_huge(*pud) || pud_devmap(*pud)) return __pud_trans_huge_lock(pud, vma); else return NULL; } /** * thp_head - Head page of a transparent huge page. * @page: Any page (tail, head or regular) found in the page cache. */ static inline struct page *thp_head(struct page *page) { return compound_head(page); } /** * thp_order - Order of a transparent huge page. * @page: Head page of a transparent huge page. */ static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); if (PageHead(page)) return HPAGE_PMD_ORDER; return 0; } /** * thp_nr_pages - The number of regular pages in this huge page. * @page: The head page of a huge page. */ static inline int thp_nr_pages(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); if (PageHead(page)) return HPAGE_PMD_NR; return 1; } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap); struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap); vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf); extern struct page *huge_zero_page; extern unsigned long huge_zero_pfn; static inline bool is_huge_zero_page(struct page *page) { return READ_ONCE(huge_zero_page) == page; } static inline bool is_huge_zero_pmd(pmd_t pmd) { return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd); } static inline bool is_huge_zero_pud(pud_t pud) { return false; } struct page *mm_get_huge_zero_page(struct mm_struct *mm); void mm_put_huge_zero_page(struct mm_struct *mm); #define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) static inline bool thp_migration_supported(void) { return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); } static inline struct list_head *page_deferred_list(struct page *page) { /* * Global or memcg deferred list in the second tail pages is * occupied by compound_head. */ return &page[2].deferred_list; } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) static inline struct page *thp_head(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return page; } static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return 0; } static inline int thp_nr_pages(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return 1; } static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { return false; } static inline bool transparent_hugepage_active(struct vm_area_struct *vma) { return false; } static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, unsigned long haddr) { return false; } static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, unsigned long vm_flags) { return false; } static inline void prep_transhuge_page(struct page *page) {} static inline bool is_transparent_hugepage(struct page *page) { return false; } #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL static inline bool can_split_huge_page(struct page *page, int *pextra_pins) { BUILD_BUG(); return false; } static inline int split_huge_page_to_list(struct page *page, struct list_head *list) { return 0; } static inline int split_huge_page(struct page *page) { return 0; } static inline void deferred_split_huge_page(struct page *page) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct page *page) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page) {} #define split_huge_pud(__vma, __pmd, __address) \ do { } while (0) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { BUG(); return 0; } static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next) { } static inline int is_swap_pmd(pmd_t pmd) { return 0; } static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { return NULL; } static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { return NULL; } static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { return 0; } static inline bool is_huge_zero_page(struct page *page) { return false; } static inline bool is_huge_zero_pmd(pmd_t pmd) { return false; } static inline bool is_huge_zero_pud(pud_t pud) { return false; } static inline void mm_put_huge_zero_page(struct mm_struct *mm) { return; } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline bool thp_migration_supported(void) { return false; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /** * thp_size - Size of a transparent huge page. * @page: Head page of a transparent huge page. * * Return: Number of bytes in this page. */ static inline unsigned long thp_size(struct page *page) { return PAGE_SIZE << thp_order(page); } #endif /* _LINUX_HUGE_MM_H */ |
| 1544 15866 15870 15866 1378 1206 779 1378 198 198 198 197 14687 14691 14710 14687 14691 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.h> static DEFINE_SPINLOCK(cgroup_rstat_lock); static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock); static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) { return per_cpu_ptr(cgrp->rstat_cpu, cpu); } /** * cgroup_rstat_updated - keep track of updated rstat_cpu * @cgrp: target cgroup * @cpu: cpu on which rstat_cpu was updated * * @cgrp's rstat_cpu on @cpu was updated. Put it on the parent's matching * rstat_cpu->updated_children list. See the comment on top of * cgroup_rstat_cpu definition for details. */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); unsigned long flags; /* * Speculative already-on-list test. This may race leading to * temporary inaccuracies, which is fine. * * Because @parent's updated_children is terminated with @parent * instead of NULL, we can tell whether @cgrp is on the list by * testing the next pointer for NULL. */ if (cgroup_rstat_cpu(cgrp, cpu)->updated_next) return; raw_spin_lock_irqsave(cpu_lock, flags); /* put @cgrp and all ancestors on the corresponding updated lists */ while (true) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *prstatc; /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; /* Root has no parent to link it to, but mark it busy */ if (!parent) { rstatc->updated_next = cgrp; break; } prstatc = cgroup_rstat_cpu(parent, cpu); rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = cgrp; cgrp = parent; } raw_spin_unlock_irqrestore(cpu_lock, flags); } /** * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree * @pos: current position * @root: root of the tree to traversal * @cpu: target cpu * * Walks the updated rstat_cpu tree on @cpu from @root. %NULL @pos starts * the traversal and %NULL return indicates the end. During traversal, * each returned cgroup is unlinked from the tree. Must be called with the * matching cgroup_rstat_cpu_lock held. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, if a child is visited, its parent is * guaranteed to be visited afterwards. */ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, struct cgroup *root, int cpu) { struct cgroup_rstat_cpu *rstatc; if (pos == root) return NULL; /* * We're gonna walk down to the first leaf and visit/remove it. We * can pick whatever unvisited node as the starting point. */ if (!pos) pos = root; else pos = cgroup_parent(pos); /* walk down to the first leaf */ while (true) { rstatc = cgroup_rstat_cpu(pos, cpu); if (rstatc->updated_children == pos) break; pos = rstatc->updated_children; } /* * Unlink @pos from the tree. As the updated_children list is * singly linked, we have to walk it to find the removal point. * However, due to the way we traverse, @pos will be the first * child in most cases. The only exception is @root. */ if (rstatc->updated_next) { struct cgroup *parent = cgroup_parent(pos); if (parent) { struct cgroup_rstat_cpu *prstatc; struct cgroup **nextp; prstatc = cgroup_rstat_cpu(parent, cpu); nextp = &prstatc->updated_children; while (true) { struct cgroup_rstat_cpu *nrstatc; nrstatc = cgroup_rstat_cpu(*nextp, cpu); if (*nextp == pos) break; WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; } rstatc->updated_next = NULL; return pos; } /* only happens for @root */ return NULL; } /* see cgroup_rstat_flush() */ static void cgroup_rstat_flush_locked(struct cgroup *cgrp) __releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock) { int cpu; lockdep_assert_held(&cgroup_rstat_lock); for_each_possible_cpu(cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup *pos = NULL; raw_spin_lock(cpu_lock); while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { struct cgroup_subsys_state *css; cgroup_base_stat_flush(pos, cpu); rcu_read_lock(); list_for_each_entry_rcu(css, &pos->rstat_css_list, rstat_css_node) css->ss->css_rstat_flush(css, cpu); rcu_read_unlock(); } raw_spin_unlock(cpu_lock); /* play nice and yield if necessary */ if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) { spin_unlock_irq(&cgroup_rstat_lock); if (!cond_resched()) cpu_relax(); spin_lock_irq(&cgroup_rstat_lock); } } } /** * cgroup_rstat_flush - flush stats in @cgrp's subtree * @cgrp: target cgroup * * Collect all per-cpu stats in @cgrp's subtree into the global counters * and propagate them upwards. After this function returns, all cgroups in * the subtree have up-to-date ->stat. * * This also gets all cgroups in the subtree including @cgrp off the * ->updated_children lists. * * This function may block. */ void cgroup_rstat_flush(struct cgroup *cgrp) { might_sleep(); spin_lock_irq(&cgroup_rstat_lock); cgroup_rstat_flush_locked(cgrp); spin_unlock_irq(&cgroup_rstat_lock); } /** * cgroup_rstat_flush_hold - flush stats in @cgrp's subtree and hold * @cgrp: target cgroup * * Flush stats in @cgrp's subtree and prevent further flushes. Must be * paired with cgroup_rstat_flush_release(). * * This function may block. */ void cgroup_rstat_flush_hold(struct cgroup *cgrp) __acquires(&cgroup_rstat_lock) { might_sleep(); spin_lock_irq(&cgroup_rstat_lock); cgroup_rstat_flush_locked(cgrp); } /** * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold() */ void cgroup_rstat_flush_release(void) __releases(&cgroup_rstat_lock) { spin_unlock_irq(&cgroup_rstat_lock); } int cgroup_rstat_init(struct cgroup *cgrp) { int cpu; /* the root cgrp has rstat_cpu preallocated */ if (!cgrp->rstat_cpu) { cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu); if (!cgrp->rstat_cpu) return -ENOMEM; } /* ->updated_children list is self terminated */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); rstatc->updated_children = cgrp; u64_stats_init(&rstatc->bsync); } return 0; } void cgroup_rstat_exit(struct cgroup *cgrp) { int cpu; cgroup_rstat_flush(cgrp); /* sanity check */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); if (WARN_ON_ONCE(rstatc->updated_children != cgrp) || WARN_ON_ONCE(rstatc->updated_next)) return; } free_percpu(cgrp->rstat_cpu); cgrp->rstat_cpu = NULL; } void __init cgroup_rstat_boot(void) { int cpu; for_each_possible_cpu(cpu) raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu)); } /* * Functions for cgroup basic resource statistics implemented on top of * rstat. */ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; } static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime -= src_bstat->cputime.utime; dst_bstat->cputime.stime -= src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_base_stat cur, delta; unsigned seq; /* Root-level stats are sourced from system-wide CPU stats */ if (!parent) return; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatc->bsync); cur.cputime = rstatc->bstat.cputime; } while (__u64_stats_fetch_retry(&rstatc->bsync, seq)); /* propagate percpu delta to global */ delta = cur; cgroup_base_stat_sub(&delta, &rstatc->last_bstat); cgroup_base_stat_add(&cgrp->bstat, &delta); cgroup_base_stat_add(&rstatc->last_bstat, &delta); /* propagate global delta to parent (unless that's root) */ if (cgroup_parent(parent)) { delta = cgrp->bstat; cgroup_base_stat_sub(&delta, &cgrp->last_bstat); cgroup_base_stat_add(&parent->bstat, &delta); cgroup_base_stat_add(&cgrp->last_bstat, &delta); } } static struct cgroup_rstat_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags) { struct cgroup_rstat_cpu *rstatc; rstatc = get_cpu_ptr(cgrp->rstat_cpu); *flags = u64_stats_update_begin_irqsave(&rstatc->bsync); return rstatc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_cpu *rstatc, unsigned long flags) { u64_stats_update_end_irqrestore(&rstatc->bsync, flags); cgroup_rstat_updated(cgrp, smp_processor_id()); put_cpu_ptr(rstatc); } void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; unsigned long flags; rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); rstatc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; unsigned long flags; rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); switch (index) { case CPUTIME_USER: case CPUTIME_NICE: rstatc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatc->bstat.cputime.stime += delta_exec; break; default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } /* * compute the cputime for the root cgroup by getting the per cpu data * at a global level, then categorizing the fields in a manner consistent * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup. */ static void root_cgroup_cputime(struct task_cputime *cputime) { int i; cputime->stime = 0; cputime->utime = 0; cputime->sum_exec_runtime = 0; for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u64 user = 0; u64 sys = 0; kcpustat_cpu_fetch(&kcpustat, i); user += cpustat[CPUTIME_USER]; user += cpustat[CPUTIME_NICE]; cputime->utime += user; sys += cpustat[CPUTIME_SYSTEM]; sys += cpustat[CPUTIME_IRQ]; sys += cpustat[CPUTIME_SOFTIRQ]; cputime->stime += sys; cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL]; } } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; u64 usage, utime, stime; struct task_cputime cputime; if (cgroup_parent(cgrp)) { cgroup_rstat_flush_hold(cgrp); usage = cgrp->bstat.cputime.sum_exec_runtime; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime); cgroup_rstat_flush_release(); } else { root_cgroup_cputime(&cputime); usage = cputime.sum_exec_runtime; utime = cputime.utime; stime = cputime.stime; } do_div(usage, NSEC_PER_USEC); do_div(utime, NSEC_PER_USEC); do_div(stime, NSEC_PER_USEC); seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n", usage, utime, stime); } |
| 75 76 76 750 750 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * NETLINK Generic Netlink Family * * Authors: Jamal Hadi Salim * Thomas Graf <tgraf@suug.ch> * Johannes Berg <johannes@sipsolutions.net> */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/string.h> #include <linux/skbuff.h> #include <linux/mutex.h> #include <linux/bitmap.h> #include <linux/rwsem.h> #include <linux/idr.h> #include <net/sock.h> #include <net/genetlink.h> static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */ static DECLARE_RWSEM(cb_lock); atomic_t genl_sk_destructing_cnt = ATOMIC_INIT(0); DECLARE_WAIT_QUEUE_HEAD(genl_sk_destructing_waitq); void genl_lock(void) { mutex_lock(&genl_mutex); } EXPORT_SYMBOL(genl_lock); void genl_unlock(void) { mutex_unlock(&genl_mutex); } EXPORT_SYMBOL(genl_unlock); static void genl_lock_all(void) { down_write(&cb_lock); genl_lock(); } static void genl_unlock_all(void) { genl_unlock(); up_write(&cb_lock); } static DEFINE_IDR(genl_fam_idr); /* * Bitmap of multicast groups that are currently in use. * * To avoid an allocation at boot of just one unsigned long, * declare it global instead. * Bit 0 is marked as already used since group 0 is invalid. * Bit 1 is marked as already used since the drop-monitor code * abuses the API and thinks it can statically use group 1. * That group will typically conflict with other groups that * any proper users use. * Bit 16 is marked as used since it's used for generic netlink * and the code no longer marks pre-reserved IDs as used. * Bit 17 is marked as already used since the VFS quota code * also abused this API and relied on family == group ID, we * cater to that by giving it a static family and group ID. * Bit 18 is marked as already used since the PMCRAID driver * did the same thing as the VFS quota code (maybe copied?) */ static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_CTRL) | BIT(GENL_ID_VFS_DQUOT) | BIT(GENL_ID_PMCRAID); static unsigned long *mc_groups = &mc_group_start; static unsigned long mc_groups_longs = 1; static int genl_ctrl_event(int event, const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id); static const struct genl_family *genl_family_find_byid(unsigned int id) { return idr_find(&genl_fam_idr, id); } static const struct genl_family *genl_family_find_byname(char *name) { const struct genl_family *family; unsigned int id; idr_for_each_entry(&genl_fam_idr, family, id) if (strcmp(family->name, name) == 0) return family; return NULL; } static int genl_get_cmd_cnt(const struct genl_family *family) { return family->n_ops + family->n_small_ops; } static void genl_op_from_full(const struct genl_family *family, unsigned int i, struct genl_ops *op) { *op = family->ops[i]; if (!op->maxattr) op->maxattr = family->maxattr; if (!op->policy) op->policy = family->policy; } static int genl_get_cmd_full(u32 cmd, const struct genl_family *family, struct genl_ops *op) { int i; for (i = 0; i < family->n_ops; i++) if (family->ops[i].cmd == cmd) { genl_op_from_full(family, i, op); return 0; } return -ENOENT; } static void genl_op_from_small(const struct genl_family *family, unsigned int i, struct genl_ops *op) { memset(op, 0, sizeof(*op)); op->doit = family->small_ops[i].doit; op->dumpit = family->small_ops[i].dumpit; op->cmd = family->small_ops[i].cmd; op->internal_flags = family->small_ops[i].internal_flags; op->flags = family->small_ops[i].flags; op->validate = family->small_ops[i].validate; op->maxattr = family->maxattr; op->policy = family->policy; } static int genl_get_cmd_small(u32 cmd, const struct genl_family *family, struct genl_ops *op) { int i; for (i = 0; i < family->n_small_ops; i++) if (family->small_ops[i].cmd == cmd) { genl_op_from_small(family, i, op); return 0; } return -ENOENT; } static int genl_get_cmd(u32 cmd, const struct genl_family *family, struct genl_ops *op) { if (!genl_get_cmd_full(cmd, family, op)) return 0; return genl_get_cmd_small(cmd, family, op); } static void genl_get_cmd_by_index(unsigned int i, const struct genl_family *family, struct genl_ops *op) { if (i < family->n_ops) genl_op_from_full(family, i, op); else if (i < family->n_ops + family->n_small_ops) genl_op_from_small(family, i - family->n_ops, op); else WARN_ON_ONCE(1); } static int genl_allocate_reserve_groups(int n_groups, int *first_id) { unsigned long *new_groups; int start = 0; int i; int id; bool fits; do { if (start == 0) id = find_first_zero_bit(mc_groups, mc_groups_longs * BITS_PER_LONG); else id = find_next_zero_bit(mc_groups, mc_groups_longs * BITS_PER_LONG, start); fits = true; for (i = id; i < min_t(int, id + n_groups, mc_groups_longs * BITS_PER_LONG); i++) { if (test_bit(i, mc_groups)) { start = i; fits = false; break; } } if (id + n_groups > mc_groups_longs * BITS_PER_LONG) { unsigned long new_longs = mc_groups_longs + BITS_TO_LONGS(n_groups); size_t nlen = new_longs * sizeof(unsigned long); if (mc_groups == &mc_group_start) { new_groups = kzalloc(nlen, GFP_KERNEL); if (!new_groups) return -ENOMEM; mc_groups = new_groups; *mc_groups = mc_group_start; } else { new_groups = krealloc(mc_groups, nlen, GFP_KERNEL); if (!new_groups) return -ENOMEM; mc_groups = new_groups; for (i = 0; i < BITS_TO_LONGS(n_groups); i++) mc_groups[mc_groups_longs + i] = 0; } mc_groups_longs = new_longs; } } while (!fits); for (i = id; i < id + n_groups; i++) set_bit(i, mc_groups); *first_id = id; return 0; } static struct genl_family genl_ctrl; static int genl_validate_assign_mc_groups(struct genl_family *family) { int first_id; int n_groups = family->n_mcgrps; int err = 0, i; bool groups_allocated = false; if (!n_groups) return 0; for (i = 0; i < n_groups; i++) { const struct genl_multicast_group *grp = &family->mcgrps[i]; if (WARN_ON(grp->name[0] == '\0')) return -EINVAL; if (WARN_ON(memchr(grp->name, '\0', GENL_NAMSIZ) == NULL)) return -EINVAL; } /* special-case our own group and hacks */ if (family == &genl_ctrl) { first_id = GENL_ID_CTRL; BUG_ON(n_groups != 1); } else if (strcmp(family->name, "NET_DM") == 0) { first_id = 1; BUG_ON(n_groups != 1); } else if (family->id == GENL_ID_VFS_DQUOT) { first_id = GENL_ID_VFS_DQUOT; BUG_ON(n_groups != 1); } else if (family->id == GENL_ID_PMCRAID) { first_id = GENL_ID_PMCRAID; BUG_ON(n_groups != 1); } else { groups_allocated = true; err = genl_allocate_reserve_groups(n_groups, &first_id); if (err) return err; } family->mcgrp_offset = first_id; /* if still initializing, can't and don't need to realloc bitmaps */ if (!init_net.genl_sock) return 0; if (family->netnsok) { struct net *net; netlink_table_grab(); rcu_read_lock(); for_each_net_rcu(net) { err = __netlink_change_ngroups(net->genl_sock, mc_groups_longs * BITS_PER_LONG); if (err) { /* * No need to roll back, can only fail if * memory allocation fails and then the * number of _possible_ groups has been * increased on some sockets which is ok. */ break; } } rcu_read_unlock(); netlink_table_ungrab(); } else { err = netlink_change_ngroups(init_net.genl_sock, mc_groups_longs * BITS_PER_LONG); } if (groups_allocated && err) { for (i = 0; i < family->n_mcgrps; i++) clear_bit(family->mcgrp_offset + i, mc_groups); } return err; } static void genl_unregister_mc_groups(const struct genl_family *family) { struct net *net; int i; netlink_table_grab(); rcu_read_lock(); for_each_net_rcu(net) { for (i = 0; i < family->n_mcgrps; i++) __netlink_clear_multicast_users( net->genl_sock, family->mcgrp_offset + i); } rcu_read_unlock(); netlink_table_ungrab(); for (i = 0; i < family->n_mcgrps; i++) { int grp_id = family->mcgrp_offset + i; if (grp_id != 1) clear_bit(grp_id, mc_groups); genl_ctrl_event(CTRL_CMD_DELMCAST_GRP, family, &family->mcgrps[i], grp_id); } } static int genl_validate_ops(const struct genl_family *family) { int i, j; if (WARN_ON(family->n_ops && !family->ops) || WARN_ON(family->n_small_ops && !family->small_ops)) return -EINVAL; for (i = 0; i < genl_get_cmd_cnt(family); i++) { struct genl_ops op; genl_get_cmd_by_index(i, family, &op); if (op.dumpit == NULL && op.doit == NULL) return -EINVAL; for (j = i + 1; j < genl_get_cmd_cnt(family); j++) { struct genl_ops op2; genl_get_cmd_by_index(j, family, &op2); if (op.cmd == op2.cmd) return -EINVAL; } } return 0; } /** * genl_register_family - register a generic netlink family * @family: generic netlink family * * Registers the specified family after validating it first. Only one * family may be registered with the same family name or identifier. * * The family's ops, multicast groups and module pointer must already * be assigned. * * Return 0 on success or a negative error code. */ int genl_register_family(struct genl_family *family) { int err, i; int start = GENL_START_ALLOC, end = GENL_MAX_ID; err = genl_validate_ops(family); if (err) return err; genl_lock_all(); if (genl_family_find_byname(family->name)) { err = -EEXIST; goto errout_locked; } /* * Sadly, a few cases need to be special-cased * due to them having previously abused the API * and having used their family ID also as their * multicast group ID, so we use reserved IDs * for both to be sure we can do that mapping. */ if (family == &genl_ctrl) { /* and this needs to be special for initial family lookups */ start = end = GENL_ID_CTRL; } else if (strcmp(family->name, "pmcraid") == 0) { start = end = GENL_ID_PMCRAID; } else if (strcmp(family->name, "VFS_DQUOT") == 0) { start = end = GENL_ID_VFS_DQUOT; } family->id = idr_alloc_cyclic(&genl_fam_idr, family, start, end + 1, GFP_KERNEL); if (family->id < 0) { err = family->id; goto errout_locked; } err = genl_validate_assign_mc_groups(family); if (err) goto errout_remove; genl_unlock_all(); /* send all events */ genl_ctrl_event(CTRL_CMD_NEWFAMILY, family, NULL, 0); for (i = 0; i < family->n_mcgrps; i++) genl_ctrl_event(CTRL_CMD_NEWMCAST_GRP, family, &family->mcgrps[i], family->mcgrp_offset + i); return 0; errout_remove: idr_remove(&genl_fam_idr, family->id); errout_locked: genl_unlock_all(); return err; } EXPORT_SYMBOL(genl_register_family); /** * genl_unregister_family - unregister generic netlink family * @family: generic netlink family * * Unregisters the specified family. * * Returns 0 on success or a negative error code. */ int genl_unregister_family(const struct genl_family *family) { genl_lock_all(); if (!genl_family_find_byid(family->id)) { genl_unlock_all(); return -ENOENT; } genl_unregister_mc_groups(family); idr_remove(&genl_fam_idr, family->id); up_write(&cb_lock); wait_event(genl_sk_destructing_waitq, atomic_read(&genl_sk_destructing_cnt) == 0); genl_unlock(); genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0); return 0; } EXPORT_SYMBOL(genl_unregister_family); /** * genlmsg_put - Add generic netlink header to netlink message * @skb: socket buffer holding the message * @portid: netlink portid the message is addressed to * @seq: sequence number (usually the one of the sender) * @family: generic netlink family * @flags: netlink message flags * @cmd: generic netlink command * * Returns pointer to user specific header */ void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, const struct genl_family *family, int flags, u8 cmd) { struct nlmsghdr *nlh; struct genlmsghdr *hdr; nlh = nlmsg_put(skb, portid, seq, family->id, GENL_HDRLEN + family->hdrsize, flags); if (nlh == NULL) return NULL; hdr = nlmsg_data(nlh); hdr->cmd = cmd; hdr->version = family->version; hdr->reserved = 0; return (char *) hdr + GENL_HDRLEN; } EXPORT_SYMBOL(genlmsg_put); static struct genl_dumpit_info *genl_dumpit_info_alloc(void) { return kmalloc(sizeof(struct genl_dumpit_info), GFP_KERNEL); } static void genl_dumpit_info_free(const struct genl_dumpit_info *info) { kfree(info); } static struct nlattr ** genl_family_rcv_msg_attrs_parse(const struct genl_family *family, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, const struct genl_ops *ops, int hdrlen, enum genl_validate_flags no_strict_flag) { enum netlink_validation validate = ops->validate & no_strict_flag ? NL_VALIDATE_LIBERAL : NL_VALIDATE_STRICT; struct nlattr **attrbuf; int err; if (!ops->maxattr) return NULL; attrbuf = kmalloc_array(ops->maxattr + 1, sizeof(struct nlattr *), GFP_KERNEL); if (!attrbuf) return ERR_PTR(-ENOMEM); err = __nlmsg_parse(nlh, hdrlen, attrbuf, ops->maxattr, ops->policy, validate, extack); if (err) { kfree(attrbuf); return ERR_PTR(err); } return attrbuf; } static void genl_family_rcv_msg_attrs_free(struct nlattr **attrbuf) { kfree(attrbuf); } struct genl_start_context { const struct genl_family *family; struct nlmsghdr *nlh; struct netlink_ext_ack *extack; const struct genl_ops *ops; int hdrlen; }; static int genl_start(struct netlink_callback *cb) { struct genl_start_context *ctx = cb->data; const struct genl_ops *ops = ctx->ops; struct genl_dumpit_info *info; struct nlattr **attrs = NULL; int rc = 0; if (ops->validate & GENL_DONT_VALIDATE_DUMP) goto no_attrs; if (ctx->nlh->nlmsg_len < nlmsg_msg_size(ctx->hdrlen)) return -EINVAL; attrs = genl_family_rcv_msg_attrs_parse(ctx->family, ctx->nlh, ctx->extack, ops, ctx->hdrlen, GENL_DONT_VALIDATE_DUMP_STRICT); if (IS_ERR(attrs)) return PTR_ERR(attrs); no_attrs: info = genl_dumpit_info_alloc(); if (!info) { genl_family_rcv_msg_attrs_free(attrs); return -ENOMEM; } info->family = ctx->family; info->op = *ops; info->attrs = attrs; cb->data = info; if (ops->start) { if (!ctx->family->parallel_ops) genl_lock(); rc = ops->start(cb); if (!ctx->family->parallel_ops) genl_unlock(); } if (rc) { genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); cb->data = NULL; } return rc; } static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { const struct genl_ops *ops = &genl_dumpit_info(cb)->op; int rc; genl_lock(); rc = ops->dumpit(skb, cb); genl_unlock(); return rc; } static int genl_lock_done(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); const struct genl_ops *ops = &info->op; int rc = 0; if (ops->done) { genl_lock(); rc = ops->done(cb); genl_unlock(); } genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); return rc; } static int genl_parallel_done(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); const struct genl_ops *ops = &info->op; int rc = 0; if (ops->done) rc = ops->done(cb); genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); return rc; } static int genl_family_rcv_msg_dumpit(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, const struct genl_ops *ops, int hdrlen, struct net *net) { struct genl_start_context ctx; int err; if (!ops->dumpit) return -EOPNOTSUPP; ctx.family = family; ctx.nlh = nlh; ctx.extack = extack; ctx.ops = ops; ctx.hdrlen = hdrlen; if (!family->parallel_ops) { struct netlink_dump_control c = { .module = family->module, .data = &ctx, .start = genl_start, .dump = genl_lock_dumpit, .done = genl_lock_done, }; genl_unlock(); err = __netlink_dump_start(net->genl_sock, skb, nlh, &c); genl_lock(); } else { struct netlink_dump_control c = { .module = family->module, .data = &ctx, .start = genl_start, .dump = ops->dumpit, .done = genl_parallel_done, }; err = __netlink_dump_start(net->genl_sock, skb, nlh, &c); } return err; } static int genl_family_rcv_msg_doit(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, const struct genl_ops *ops, int hdrlen, struct net *net) { struct nlattr **attrbuf; struct genl_info info; int err; if (!ops->doit) return -EOPNOTSUPP; attrbuf = genl_family_rcv_msg_attrs_parse(family, nlh, extack, ops, hdrlen, GENL_DONT_VALIDATE_STRICT); if (IS_ERR(attrbuf)) return PTR_ERR(attrbuf); info.snd_seq = nlh->nlmsg_seq; info.snd_portid = NETLINK_CB(skb).portid; info.nlhdr = nlh; info.genlhdr = nlmsg_data(nlh); info.userhdr = nlmsg_data(nlh) + GENL_HDRLEN; info.attrs = attrbuf; info.extack = extack; genl_info_net_set(&info, net); memset(&info.user_ptr, 0, sizeof(info.user_ptr)); if (family->pre_doit) { err = family->pre_doit(ops, skb, &info); if (err) goto out; } err = ops->doit(skb, &info); if (family->post_doit) family->post_doit(ops, skb, &info); out: genl_family_rcv_msg_attrs_free(attrbuf); return err; } static int genl_family_rcv_msg(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct genlmsghdr *hdr = nlmsg_data(nlh); struct genl_ops op; int hdrlen; /* this family doesn't exist in this netns */ if (!family->netnsok && !net_eq(net, &init_net)) return -ENOENT; hdrlen = GENL_HDRLEN + family->hdrsize; if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) return -EINVAL; if (genl_get_cmd(hdr->cmd, family, &op)) return -EOPNOTSUPP; if ((op.flags & GENL_ADMIN_PERM) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if ((op.flags & GENL_UNS_ADMIN_PERM) && !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) return genl_family_rcv_msg_dumpit(family, skb, nlh, extack, &op, hdrlen, net); else return genl_family_rcv_msg_doit(family, skb, nlh, extack, &op, hdrlen, net); } static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { const struct genl_family *family; int err; family = genl_family_find_byid(nlh->nlmsg_type); if (family == NULL) return -ENOENT; if (!family->parallel_ops) genl_lock(); err = genl_family_rcv_msg(family, skb, nlh, extack); if (!family->parallel_ops) genl_unlock(); return err; } static void genl_rcv(struct sk_buff *skb) { down_read(&cb_lock); netlink_rcv_skb(skb, &genl_rcv_msg); up_read(&cb_lock); } /************************************************************************** * Controller **************************************************************************/ static struct genl_family genl_ctrl; static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); if (hdr == NULL) return -1; if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, family->name) || nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id) || nla_put_u32(skb, CTRL_ATTR_VERSION, family->version) || nla_put_u32(skb, CTRL_ATTR_HDRSIZE, family->hdrsize) || nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr)) goto nla_put_failure; if (genl_get_cmd_cnt(family)) { struct nlattr *nla_ops; int i; nla_ops = nla_nest_start_noflag(skb, CTRL_ATTR_OPS); if (nla_ops == NULL) goto nla_put_failure; for (i = 0; i < genl_get_cmd_cnt(family); i++) { struct nlattr *nest; struct genl_ops op; u32 op_flags; genl_get_cmd_by_index(i, family, &op); op_flags = op.flags; if (op.dumpit) op_flags |= GENL_CMD_CAP_DUMP; if (op.doit) op_flags |= GENL_CMD_CAP_DO; if (op.policy) op_flags |= GENL_CMD_CAP_HASPOL; nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; if (nla_put_u32(skb, CTRL_ATTR_OP_ID, op.cmd) || nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, op_flags)) goto nla_put_failure; nla_nest_end(skb, nest); } nla_nest_end(skb, nla_ops); } if (family->n_mcgrps) { struct nlattr *nla_grps; int i; nla_grps = nla_nest_start_noflag(skb, CTRL_ATTR_MCAST_GROUPS); if (nla_grps == NULL) goto nla_put_failure; for (i = 0; i < family->n_mcgrps; i++) { struct nlattr *nest; const struct genl_multicast_group *grp; grp = &family->mcgrps[i]; nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, family->mcgrp_offset + i) || nla_put_string(skb, CTRL_ATTR_MCAST_GRP_NAME, grp->name)) goto nla_put_failure; nla_nest_end(skb, nest); } nla_nest_end(skb, nla_grps); } genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int ctrl_fill_mcgrp_info(const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; struct nlattr *nla_grps; struct nlattr *nest; hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); if (hdr == NULL) return -1; if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, family->name) || nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id)) goto nla_put_failure; nla_grps = nla_nest_start_noflag(skb, CTRL_ATTR_MCAST_GROUPS); if (nla_grps == NULL) goto nla_put_failure; nest = nla_nest_start_noflag(skb, 1); if (nest == NULL) goto nla_put_failure; if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, grp_id) || nla_put_string(skb, CTRL_ATTR_MCAST_GRP_NAME, grp->name)) goto nla_put_failure; nla_nest_end(skb, nest); nla_nest_end(skb, nla_grps); genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) { int n = 0; struct genl_family *rt; struct net *net = sock_net(skb->sk); int fams_to_skip = cb->args[0]; unsigned int id; idr_for_each_entry(&genl_fam_idr, rt, id) { if (!rt->netnsok && !net_eq(net, &init_net)) continue; if (n++ < fams_to_skip) continue; if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, skb, CTRL_CMD_NEWFAMILY) < 0) { n--; break; } } cb->args[0] = n; return skb->len; } static struct sk_buff *ctrl_build_family_msg(const struct genl_family *family, u32 portid, int seq, u8 cmd) { struct sk_buff *skb; int err; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb == NULL) return ERR_PTR(-ENOBUFS); err = ctrl_fill_info(family, portid, seq, 0, skb, cmd); if (err < 0) { nlmsg_free(skb); return ERR_PTR(err); } return skb; } static struct sk_buff * ctrl_build_mcgrp_msg(const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id, u32 portid, int seq, u8 cmd) { struct sk_buff *skb; int err; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb == NULL) return ERR_PTR(-ENOBUFS); err = ctrl_fill_mcgrp_info(family, grp, grp_id, portid, seq, 0, skb, cmd); if (err < 0) { nlmsg_free(skb); return ERR_PTR(err); } return skb; } static const struct nla_policy ctrl_policy_family[] = { [CTRL_ATTR_FAMILY_ID] = { .type = NLA_U16 }, [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_NUL_STRING, .len = GENL_NAMSIZ - 1 }, }; static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; const struct genl_family *res = NULL; int err = -EINVAL; if (info->attrs[CTRL_ATTR_FAMILY_ID]) { u16 id = nla_get_u16(info->attrs[CTRL_ATTR_FAMILY_ID]); res = genl_family_find_byid(id); err = -ENOENT; } if (info->attrs[CTRL_ATTR_FAMILY_NAME]) { char *name; name = nla_data(info->attrs[CTRL_ATTR_FAMILY_NAME]); res = genl_family_find_byname(name); #ifdef CONFIG_MODULES if (res == NULL) { genl_unlock(); up_read(&cb_lock); request_module("net-pf-%d-proto-%d-family-%s", PF_NETLINK, NETLINK_GENERIC, name); down_read(&cb_lock); genl_lock(); res = genl_family_find_byname(name); } #endif err = -ENOENT; } if (res == NULL) return err; if (!res->netnsok && !net_eq(genl_info_net(info), &init_net)) { /* family doesn't exist here */ return -ENOENT; } msg = ctrl_build_family_msg(res, info->snd_portid, info->snd_seq, CTRL_CMD_NEWFAMILY); if (IS_ERR(msg)) return PTR_ERR(msg); return genlmsg_reply(msg, info); } static int genl_ctrl_event(int event, const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id) { struct sk_buff *msg; /* genl is still initialising */ if (!init_net.genl_sock) return 0; switch (event) { case CTRL_CMD_NEWFAMILY: case CTRL_CMD_DELFAMILY: WARN_ON(grp); msg = ctrl_build_family_msg(family, 0, 0, event); break; case CTRL_CMD_NEWMCAST_GRP: case CTRL_CMD_DELMCAST_GRP: BUG_ON(!grp); msg = ctrl_build_mcgrp_msg(family, grp, grp_id, 0, 0, event); break; default: return -EINVAL; } if (IS_ERR(msg)) return PTR_ERR(msg); if (!family->netnsok) { genlmsg_multicast_netns(&genl_ctrl, &init_net, msg, 0, 0, GFP_KERNEL); } else { rcu_read_lock(); genlmsg_multicast_allns(&genl_ctrl, msg, 0, 0, GFP_ATOMIC); rcu_read_unlock(); } return 0; } struct ctrl_dump_policy_ctx { struct netlink_policy_dump_state *state; const struct genl_family *rt; unsigned int opidx; u32 op; u16 fam_id; u8 policies:1, single_op:1; }; static const struct nla_policy ctrl_policy_policy[] = { [CTRL_ATTR_FAMILY_ID] = { .type = NLA_U16 }, [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_NUL_STRING, .len = GENL_NAMSIZ - 1 }, [CTRL_ATTR_OP] = { .type = NLA_U32 }, }; static int ctrl_dumppolicy_start(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; struct nlattr **tb = info->attrs; const struct genl_family *rt; struct genl_ops op; int err, i; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); if (!tb[CTRL_ATTR_FAMILY_ID] && !tb[CTRL_ATTR_FAMILY_NAME]) return -EINVAL; if (tb[CTRL_ATTR_FAMILY_ID]) { ctx->fam_id = nla_get_u16(tb[CTRL_ATTR_FAMILY_ID]); } else { rt = genl_family_find_byname( nla_data(tb[CTRL_ATTR_FAMILY_NAME])); if (!rt) return -ENOENT; ctx->fam_id = rt->id; } rt = genl_family_find_byid(ctx->fam_id); if (!rt) return -ENOENT; ctx->rt = rt; if (tb[CTRL_ATTR_OP]) { ctx->single_op = true; ctx->op = nla_get_u32(tb[CTRL_ATTR_OP]); err = genl_get_cmd(ctx->op, rt, &op); if (err) { NL_SET_BAD_ATTR(cb->extack, tb[CTRL_ATTR_OP]); return err; } if (!op.policy) return -ENODATA; return netlink_policy_dump_add_policy(&ctx->state, op.policy, op.maxattr); } for (i = 0; i < genl_get_cmd_cnt(rt); i++) { genl_get_cmd_by_index(i, rt, &op); if (op.policy) { err = netlink_policy_dump_add_policy(&ctx->state, op.policy, op.maxattr); if (err) goto err_free_state; } } if (!ctx->state) return -ENODATA; return 0; err_free_state: netlink_policy_dump_free(ctx->state); return err; } static void *ctrl_dumppolicy_prep(struct sk_buff *skb, struct netlink_callback *cb) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; void *hdr; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &genl_ctrl, NLM_F_MULTI, CTRL_CMD_GETPOLICY); if (!hdr) return NULL; if (nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, ctx->fam_id)) return NULL; return hdr; } static int ctrl_dumppolicy_put_op(struct sk_buff *skb, struct netlink_callback *cb, struct genl_ops *op) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; struct nlattr *nest_pol, *nest_op; void *hdr; int idx; /* skip if we have nothing to show */ if (!op->policy) return 0; if (!op->doit && (!op->dumpit || op->validate & GENL_DONT_VALIDATE_DUMP)) return 0; hdr = ctrl_dumppolicy_prep(skb, cb); if (!hdr) return -ENOBUFS; nest_pol = nla_nest_start(skb, CTRL_ATTR_OP_POLICY); if (!nest_pol) goto err; nest_op = nla_nest_start(skb, op->cmd); if (!nest_op) goto err; /* for now both do/dump are always the same */ idx = netlink_policy_dump_get_policy_idx(ctx->state, op->policy, op->maxattr); if (op->doit && nla_put_u32(skb, CTRL_ATTR_POLICY_DO, idx)) goto err; if (op->dumpit && !(op->validate & GENL_DONT_VALIDATE_DUMP) && nla_put_u32(skb, CTRL_ATTR_POLICY_DUMP, idx)) goto err; nla_nest_end(skb, nest_op); nla_nest_end(skb, nest_pol); genlmsg_end(skb, hdr); return 0; err: genlmsg_cancel(skb, hdr); return -ENOBUFS; } static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; void *hdr; if (!ctx->policies) { while (ctx->opidx < genl_get_cmd_cnt(ctx->rt)) { struct genl_ops op; if (ctx->single_op) { int err; err = genl_get_cmd(ctx->op, ctx->rt, &op); if (WARN_ON(err)) return skb->len; /* break out of the loop after this one */ ctx->opidx = genl_get_cmd_cnt(ctx->rt); } else { genl_get_cmd_by_index(ctx->opidx, ctx->rt, &op); } if (ctrl_dumppolicy_put_op(skb, cb, &op)) return skb->len; ctx->opidx++; } /* completed with the per-op policy index list */ ctx->policies = true; } while (netlink_policy_dump_loop(ctx->state)) { struct nlattr *nest; hdr = ctrl_dumppolicy_prep(skb, cb); if (!hdr) goto nla_put_failure; nest = nla_nest_start(skb, CTRL_ATTR_POLICY); if (!nest) goto nla_put_failure; if (netlink_policy_dump_write(skb, ctx->state)) goto nla_put_failure; nla_nest_end(skb, nest); genlmsg_end(skb, hdr); } return skb->len; nla_put_failure: genlmsg_cancel(skb, hdr); return skb->len; } static int ctrl_dumppolicy_done(struct netlink_callback *cb) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; netlink_policy_dump_free(ctx->state); return 0; } static const struct genl_ops genl_ctrl_ops[] = { { .cmd = CTRL_CMD_GETFAMILY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .policy = ctrl_policy_family, .maxattr = ARRAY_SIZE(ctrl_policy_family) - 1, .doit = ctrl_getfamily, .dumpit = ctrl_dumpfamily, }, { .cmd = CTRL_CMD_GETPOLICY, .policy = ctrl_policy_policy, .maxattr = ARRAY_SIZE(ctrl_policy_policy) - 1, .start = ctrl_dumppolicy_start, .dumpit = ctrl_dumppolicy, .done = ctrl_dumppolicy_done, }, }; static const struct genl_multicast_group genl_ctrl_groups[] = { { .name = "notify", }, }; static struct genl_family genl_ctrl __ro_after_init = { .module = THIS_MODULE, .ops = genl_ctrl_ops, .n_ops = ARRAY_SIZE(genl_ctrl_ops), .mcgrps = genl_ctrl_groups, .n_mcgrps = ARRAY_SIZE(genl_ctrl_groups), .id = GENL_ID_CTRL, .name = "nlctrl", .version = 0x2, .netnsok = true, }; static int genl_bind(struct net *net, int group) { const struct genl_family *family; unsigned int id; int ret = 0; genl_lock_all(); idr_for_each_entry(&genl_fam_idr, family, id) { const struct genl_multicast_group *grp; int i; if (family->n_mcgrps == 0) continue; i = group - family->mcgrp_offset; if (i < 0 || i >= family->n_mcgrps) continue; grp = &family->mcgrps[i]; if ((grp->flags & GENL_UNS_ADMIN_PERM) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) ret = -EPERM; break; } genl_unlock_all(); return ret; } static int __net_init genl_pernet_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = genl_rcv, .flags = NL_CFG_F_NONROOT_RECV, .bind = genl_bind, }; /* we'll bump the group number right afterwards */ net->genl_sock = netlink_kernel_create(net, NETLINK_GENERIC, &cfg); if (!net->genl_sock && net_eq(net, &init_net)) panic("GENL: Cannot initialize generic netlink\n"); if (!net->genl_sock) return -ENOMEM; return 0; } static void __net_exit genl_pernet_exit(struct net *net) { netlink_kernel_release(net->genl_sock); net->genl_sock = NULL; } static struct pernet_operations genl_pernet_ops = { .init = genl_pernet_init, .exit = genl_pernet_exit, }; static int __init genl_init(void) { int err; err = genl_register_family(&genl_ctrl); if (err < 0) goto problem; err = register_pernet_subsys(&genl_pernet_ops); if (err) goto problem; return 0; problem: panic("GENL: Cannot register controller: %d\n", err); } core_initcall(genl_init); static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group, gfp_t flags) { struct sk_buff *tmp; struct net *net, *prev = NULL; bool delivered = false; int err; for_each_net_rcu(net) { if (prev) { tmp = skb_clone(skb, flags); if (!tmp) { err = -ENOMEM; goto error; } err = nlmsg_multicast(prev->genl_sock, tmp, portid, group, flags); if (!err) delivered = true; else if (err != -ESRCH) goto error; } prev = net; } err = nlmsg_multicast(prev->genl_sock, skb, portid, group, flags); if (!err) delivered = true; else if (err != -ESRCH) return err; return delivered ? 0 : -ESRCH; error: kfree_skb(skb); return err; } int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return genlmsg_mcast(skb, portid, group, flags); } EXPORT_SYMBOL(genlmsg_multicast_allns); void genl_notify(const struct genl_family *family, struct sk_buff *skb, struct genl_info *info, u32 group, gfp_t flags) { struct net *net = genl_info_net(info); struct sock *sk = net->genl_sock; if (WARN_ON_ONCE(group >= family->n_mcgrps)) return; group = family->mcgrp_offset + group; nlmsg_notify(sk, skb, info->snd_portid, group, nlmsg_report(info->nlhdr), flags); } EXPORT_SYMBOL(genl_notify); |
| 395 395 394 393 390 12 379 2 392 390 393 393 392 338 64 394 394 1 1 1 58 1 57 56 1 56 1 57 337 336 337 337 337 337 337 338 337 1 333 59 336 337 337 337 337 337 337 62 337 280 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * The Internet Protocol (IP) output module. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Donald Becker, <becker@super.org> * Alan Cox, <Alan.Cox@linux.org> * Richard Underwood * Stefan Becker, <stefanb@yello.ping.de> * Jorge Cwik, <jorge@laser.satlink.net> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Hirokazu Takahashi, <taka@valinux.co.jp> * * See ip_input.c for original log * * Fixes: * Alan Cox : Missing nonblock feature in ip_build_xmit. * Mike Kilburn : htons() missing in ip_build_xmit. * Bradford Johnson: Fix faulty handling of some frames when * no route is found. * Alexander Demenshin: Missing sk/skb free in ip_queue_xmit * (in case if packet not accepted by * output firewall rules) * Mike McLagan : Routing by source * Alexey Kuznetsov: use new route cache * Andi Kleen: Fix broken PMTU recovery and remove * some redundant tests. * Vitaly E. Lavrov : Transparent proxy revived after year coma. * Andi Kleen : Replace ip_reply with ip_send_reply. * Andi Kleen : Split fast and slow ip_build_xmit path * for decreased register pressure on x86 * and more readability. * Marc Boucher : When call_out_firewall returns FW_QUEUE, * silently drop skb instead of failing with -EPERM. * Detlev Wengorz : Copy protocol for fragments. * Hirokazu Takahashi: HW checksumming for outgoing UDP * datagrams. * Hirokazu Takahashi: sendfile() on UDP works now. */ #include <linux/uaccess.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/init.h> #include <net/snmp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/xfrm.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/arp.h> #include <net/icmp.h> #include <net/checksum.h> #include <net/inetpeer.h> #include <net/inet_ecn.h> #include <net/lwtunnel.h> #include <linux/bpf-cgroup.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> #include <linux/netlink.h> #include <linux/tcp.h> static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, int (*output)(struct net *, struct sock *, struct sk_buff *)); /* Generate a checksum for an outgoing IP datagram. */ void ip_send_check(struct iphdr *iph) { iph->check = 0; iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } EXPORT_SYMBOL(ip_send_check); int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); iph->tot_len = htons(skb->len); ip_send_check(iph); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip_out(sk, skb); if (unlikely(!skb)) return 0; skb->protocol = htons(ETH_P_IP); return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); } int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = __ip_local_out(net, sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } EXPORT_SYMBOL_GPL(ip_local_out); static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) { int ttl = inet->uc_ttl; if (ttl < 0) ttl = ip4_dst_hoplimit(dst); return ttl; } /* * Add an ip header to a skbuff and send it out. * */ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options_rcu *opt, u8 tos) { struct inet_sock *inet = inet_sk(sk); struct rtable *rt = skb_rtable(skb); struct net *net = sock_net(sk); struct iphdr *iph; /* Build the IP header. */ skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = tos; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; /* Do not bother generating IPID for small packets (eg SYNACK) */ if (skb->len <= IPV4_MIN_MTU || ip_dont_fragment(sk, &rt->dst)) { iph->frag_off = htons(IP_DF); iph->id = 0; } else { iph->frag_off = 0; /* TCP packets here are SYNACK with fat IPv4/TCP options. * Avoid using the hashed IP ident generator. */ if (sk->sk_protocol == IPPROTO_TCP) iph->id = (__force __be16)prandom_u32(); else __ip_select_ident(net, iph, 1); } if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; ip_options_build(skb, &opt->opt, daddr, rt, 0); } skb->priority = sk->sk_priority; if (!skb->mark) skb->mark = sk->sk_mark; /* Send it out. */ return ip_local_out(net, skb->sk, skb); } EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = (struct rtable *)dst; struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; if (rt->rt_type == RTN_MULTICAST) { IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len); } else if (rt->rt_type == RTN_BROADCAST) IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) return -ENOMEM; } if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); if (res != LWTUNNEL_XMIT_CONTINUE) return res; } rcu_read_lock_bh(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int res; sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ res = neigh_output(neigh, skb, is_v6gw); rcu_read_unlock_bh(); return res; } rcu_read_unlock_bh(); net_dbg_ratelimited("%s: No header cache and no neighbour!\n", __func__); kfree_skb(skb); return -EINVAL; } static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { struct sk_buff *segs, *nskb; netdev_features_t features; int ret = 0; /* common case: seglen is <= mtu */ if (skb_gso_validate_network_len(skb, mtu)) return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length exceeds the egress MTU. * * This can happen in several cases: * - Forwarding of a TCP GRO skb, when DF flag is not set. * - Forwarding of an skb that arrived on a virtualization interface * (virtio-net/vhost/tap) with TSO/GSO size set by other network * stack. * - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an * interface with a smaller MTU. * - Arriving GRO skb (or GSO skb in a virtualized environment) that is * bridged to a NETIF_F_TSO tunnel stacked over an interface with an * insufficient MTU. */ features = netif_skb_features(skb); BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); return -ENOMEM; } consume_skb(skb); skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); err = ip_fragment(net, sk, segs, mtu, ip_finish_output2); if (err && ret == 0) ret = err; } return ret; } static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { IPCB(skb)->flags |= IPSKB_REROUTED; return dst_output(net, sk, skb); } #endif mtu = ip_skb_dst_mtu(sk, skb); if (skb_is_gso(skb)) return ip_finish_output_gso(net, sk, skb, mtu); if (skb->len > mtu || IPCB(skb)->frag_max_size) return ip_fragment(net, sk, skb, mtu, ip_finish_output2); return ip_finish_output2(net, sk, skb); } static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { int ret; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_SUCCESS: return __ip_finish_output(net, sk, skb); case NET_XMIT_CN: return __ip_finish_output(net, sk, skb) ? : ret; default: kfree_skb(skb); return ret; } } static int ip_mc_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *new_rt; bool do_cn = false; int ret, err; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_CN: do_cn = true; fallthrough; case NET_XMIT_SUCCESS: break; default: kfree_skb(skb); return ret; } /* Reset rt_iif so that inet_iif() will return skb->skb_iif. Setting * this to non-zero causes ipi_ifindex in in_pktinfo to be overwritten, * see ipv4_pktinfo_prepare(). */ new_rt = rt_dst_clone(net->loopback_dev, skb_rtable(skb)); if (new_rt) { new_rt->rt_iif = 0; skb_dst_drop(skb); skb_dst_set(skb, &new_rt->dst); } err = dev_loopback_xmit(net, sk, skb); return (do_cn && err) ? ret : err; } int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->dst.dev; /* * If the indicated interface is up and running, send the packet. */ IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); /* * Multicasts are looped back for other local users */ if (rt->rt_flags&RTCF_MULTICAST) { if (sk_mc_loop(sk) #ifdef CONFIG_IP_MROUTE /* Small optimization: do not loopback not local frames, which returned after forwarding; they will be dropped by ip_mr_input in any case. Note, that local frames are looped back to be delivered to local recipients. This check is duplicated in ip_mr_input at the moment. */ && ((rt->rt_flags & RTCF_LOCAL) || !(IPCB(skb)->flags & IPSKB_FORWARDED)) #endif ) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, ip_mc_finish_output); } /* Multicasts with ttl 0 must not go beyond the host */ if (ip_hdr(skb)->ttl == 0) { kfree_skb(skb); return 0; } } if (rt->rt_flags&RTCF_BROADCAST) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, ip_mc_finish_output); } return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev; IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, indev, dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } EXPORT_SYMBOL(ip_output); /* * copy saddr and daddr, possibly using 64bit load/stores * Equivalent to : * iph->saddr = fl4->saddr; * iph->daddr = fl4->daddr; */ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) { BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) != offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr)); iph->saddr = fl4->saddr; iph->daddr = fl4->daddr; } /* Note: skb->sk can be different from sk, in case of tunnels */ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, __u8 tos) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options_rcu *inet_opt; struct flowi4 *fl4; struct rtable *rt; struct iphdr *iph; int res; /* Skip all of this if the packet is already routed, * f.e. by something like SCTP. */ rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); fl4 = &fl->u.ip4; rt = skb_rtable(skb); if (rt) goto packet_routed; /* Make sure we can route this packet. */ rt = (struct rtable *)__sk_dst_check(sk, 0); if (!rt) { __be32 daddr; /* Use correct destination address if we have options. */ daddr = inet->inet_daddr; if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ rt = ip_route_output_ports(net, fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS_TOS(sk, tos), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; sk_setup_caps(sk, &rt->dst); } skb_dst_set_noref(skb, &rt->dst); packet_routed: if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway) goto no_route; /* OK, we know where to send it, allocate and build IP header. */ skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (tos & 0xff)); if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); /* Transport layer set skb->h.foo itself. */ if (inet_opt && inet_opt->opt.optlen) { iph->ihl += inet_opt->opt.optlen >> 2; ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } ip_select_ident_segs(net, skb, sk, skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; res = ip_local_out(net, sk, skb); rcu_read_unlock(); return res; no_route: rcu_read_unlock(); IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EHOSTUNREACH; } EXPORT_SYMBOL(__ip_queue_xmit); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) { return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos); } EXPORT_SYMBOL(ip_queue_xmit); static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) { to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; to->skb_iif = from->skb_iif; skb_dst_drop(to); skb_dst_copy(to, from); to->dev = from->dev; to->mark = from->mark; skb_copy_hash(to, from); #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif nf_copy(to, from); skb_ext_copy(to, from); #if IS_ENABLED(CONFIG_IP_VS) to->ipvs_property = from->ipvs_property; #endif skb_copy_secmark(to, from); } static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph = ip_hdr(skb); if ((iph->frag_off & htons(IP_DF)) == 0) return ip_do_fragment(net, sk, skb, output); if (unlikely(!skb->ignore_df || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); kfree_skb(skb); return -EMSGSIZE; } return ip_do_fragment(net, sk, skb, output); } void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, unsigned int hlen, struct ip_fraglist_iter *iter) { unsigned int first_len = skb_pagelen(skb); iter->frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); iter->offset = 0; iter->iph = iph; iter->hlen = hlen; skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; iph->tot_len = htons(first_len); iph->frag_off = htons(IP_MF); ip_send_check(iph); } EXPORT_SYMBOL(ip_fraglist_init); void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) { unsigned int hlen = iter->hlen; struct iphdr *iph = iter->iph; struct sk_buff *frag; frag = iter->frag; frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), iph, hlen); iter->iph = ip_hdr(frag); iph = iter->iph; iph->tot_len = htons(frag->len); ip_copy_metadata(frag, skb); iter->offset += skb->len - hlen; iph->frag_off = htons(iter->offset >> 3); if (frag->next) iph->frag_off |= htons(IP_MF); /* Ready, complete checksum */ ip_send_check(iph); } EXPORT_SYMBOL(ip_fraglist_prepare); void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs, unsigned int mtu, bool DF, struct ip_frag_state *state) { struct iphdr *iph = ip_hdr(skb); state->DF = DF; state->hlen = hlen; state->ll_rs = ll_rs; state->mtu = mtu; state->left = skb->len - hlen; /* Space per frame */ state->ptr = hlen; /* Where to start from */ state->offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3; state->not_last_frag = iph->frag_off & htons(IP_MF); } EXPORT_SYMBOL(ip_frag_init); static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, bool first_frag) { /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; /* ANK: dirty, but effective trick. Upgrade options only if * the segment to be fragmented was THE FIRST (otherwise, * options are already fixed) and make it ONCE * on the initial skb, so that all the following fragments * will inherit fixed options. */ if (first_frag) ip_options_fragment(from); } struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state) { unsigned int len = state->left; struct sk_buff *skb2; struct iphdr *iph; len = state->left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > state->mtu) len = state->mtu; /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < state->left) { len &= ~7; } /* Allocate buffer */ skb2 = alloc_skb(len + state->hlen + state->ll_rs, GFP_ATOMIC); if (!skb2) return ERR_PTR(-ENOMEM); /* * Set up data on packet */ ip_copy_metadata(skb2, skb); skb_reserve(skb2, state->ll_rs); skb_put(skb2, len + state->hlen); skb_reset_network_header(skb2); skb2->transport_header = skb2->network_header + state->hlen; /* * Charge the memory for the fragment to any owner * it might possess */ if (skb->sk) skb_set_owner_w(skb2, skb->sk); /* * Copy the packet header into the new buffer. */ skb_copy_from_linear_data(skb, skb_network_header(skb2), state->hlen); /* * Copy a block of the IP datagram. */ if (skb_copy_bits(skb, state->ptr, skb_transport_header(skb2), len)) BUG(); state->left -= len; /* * Fill in the new header fields. */ iph = ip_hdr(skb2); iph->frag_off = htons((state->offset >> 3)); if (state->DF) iph->frag_off |= htons(IP_DF); /* * Added AC : If we are fragmenting a fragment that's not the * last fragment then keep MF on each bit */ if (state->left > 0 || state->not_last_frag) iph->frag_off |= htons(IP_MF); state->ptr += len; state->offset += len; iph->tot_len = htons(len + state->hlen); ip_send_check(iph); return skb2; } EXPORT_SYMBOL(ip_frag_next); /* * This IP datagram is too large to be sent in one piece. Break it up into * smaller pieces (each of size equal to IP header plus * a block of the data of the original IP data part) that will yet fit in a * single device frame, and queue such a frame for sending. */ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph; struct sk_buff *skb2; struct rtable *rt = skb_rtable(skb); unsigned int mtu, hlen, ll_rs; struct ip_fraglist_iter iter; ktime_t tstamp = skb->tstamp; struct ip_frag_state state; int err = 0; /* for offloaded checksums cleanup checksum before fragmentation */ if (skb->ip_summed == CHECKSUM_PARTIAL && (err = skb_checksum_help(skb))) goto fail; /* * Point into the IP datagram header. */ iph = ip_hdr(skb); mtu = ip_skb_dst_mtu(sk, skb); if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu) mtu = IPCB(skb)->frag_max_size; /* * Setup starting values. */ hlen = iph->ihl * 4; mtu = mtu - hlen; /* Size of data space */ IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE; ll_rs = LL_RESERVED_SPACE(rt->dst.dev); /* When frag_list is given, use it. First, check its validity: * some transformers could create wrong frag_list or break existing * one, it is not prohibited. In this case fall back to copying. * * LATER: this step can be merged to real generation of fragments, * we can switch to copy when see the first bad fragment. */ if (skb_has_frag_list(skb)) { struct sk_buff *frag, *frag2; unsigned int first_len = skb_pagelen(skb); if (first_len - hlen > mtu || ((first_len - hlen) & 7) || ip_is_fragment(iph) || skb_cloned(skb) || skb_headroom(skb) < ll_rs) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen + ll_rs) goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } skb->truesize -= frag->truesize; } /* Everything is OK. Generate! */ ip_fraglist_init(skb, iph, hlen, &iter); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (iter.frag) { bool first_frag = (iter.offset == 0); IPCB(iter.frag)->flags = IPCB(skb)->flags; ip_fraglist_prepare(skb, &iter); if (first_frag && IPCB(skb)->opt.optlen) { /* ipcb->opt is not populated for frags * coming from __ip_make_skb(), * ip_options_fragment() needs optlen */ IPCB(iter.frag)->opt.optlen = IPCB(skb)->opt.optlen; ip_options_fragment(iter.frag); ip_send_check(iter.iph); } } skb->tstamp = tstamp; err = output(net, sk, skb); if (!err) IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); if (err || !iter.frag) break; skb = ip_fraglist_next(&iter); } if (err == 0) { IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return 0; } kfree_skb_list(iter.frag); IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; slow_path_clean: skb_walk_frags(skb, frag2) { if (frag2 == frag) break; frag2->sk = NULL; frag2->destructor = NULL; skb->truesize += frag2->truesize; } } slow_path: /* * Fragment the datagram. */ ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU, &state); /* * Keep copying data until we run out. */ while (state.left > 0) { bool first_frag = (state.offset == 0); skb2 = ip_frag_next(skb, &state); if (IS_ERR(skb2)) { err = PTR_ERR(skb2); goto fail; } ip_frag_ipcb(skb, skb2, first_frag); /* * Put this fragment into the sending queue. */ skb2->tstamp = tstamp; err = output(net, sk, skb2); if (err) goto fail; IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); } consume_skb(skb); IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return err; fail: kfree_skb(skb); IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; } EXPORT_SYMBOL(ip_do_fragment); int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct msghdr *msg = from; if (skb->ip_summed == CHECKSUM_PARTIAL) { if (!copy_from_iter_full(to, len, &msg->msg_iter)) return -EFAULT; } else { __wsum csum = 0; if (!csum_and_copy_from_iter_full(to, len, &csum, &msg->msg_iter)) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, odd); } return 0; } EXPORT_SYMBOL(ip_generic_getfrag); static inline __wsum csum_page(struct page *page, int offset, int copy) { char *kaddr; __wsum csum; kaddr = kmap(page); csum = csum_partial(kaddr + offset, copy, 0); kunmap(page); return csum; } static int __ip_append_data(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; struct ip_options *opt = cork->opt; int hh_len; int exthdrlen; int mtu; int copy; int err; int offset = 0; unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; unsigned int wmem_alloc_delta = 0; bool paged, extra_uref = false; u32 tskey = 0; skb = skb_peek_tail(queue); exthdrlen = !skb ? rt->dst.header_len : 0; mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size; if (cork->tx_flags & SKBTX_ANY_TSTAMP && sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) tskey = atomic_inc_return(&sk->sk_tskey) - 1; hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; maxnonfragsize = ip_sk_ignore_df(sk) ? IP_MAX_MTU : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu - (opt ? opt->optlen : 0)); return -EMSGSIZE; } /* * transhdrlen > 0 means that this is the first fragment and we wish * it won't be fragmented in the future. */ if (transhdrlen && length + fragheaderlen <= mtu && rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) && (!(flags & MSG_MORE) || cork->gso_size) && (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM))) csummode = CHECKSUM_PARTIAL; if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) { uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ if (rt->dst.dev->features & NETIF_F_SG && csummode == CHECKSUM_PARTIAL) { paged = true; } else { uarg->zerocopy = 0; skb_zcopy_set(skb, uarg, &extra_uref); } } cork->length += length; /* So, what's going on in the loop below? * * We use calculated fragment length to generate chained skb, * each of segments is IP fragment ready for sending to network after * adding appropriate IP header. */ if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ copy = mtu - skb->len; if (copy < length) copy = maxfraglen - skb->len; if (copy <= 0) { char *data; unsigned int datalen; unsigned int fraglen; unsigned int fraggap; unsigned int alloclen, alloc_extra; unsigned int pagedlen; struct sk_buff *skb_prev; alloc_new_skb: skb_prev = skb; if (skb_prev) fraggap = skb_prev->len - maxfraglen; else fraggap = 0; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; if (datalen > mtu - fragheaderlen) datalen = maxfraglen - fragheaderlen; fraglen = datalen + fragheaderlen; pagedlen = 0; alloc_extra = hh_len + 15; alloc_extra += exthdrlen; /* The last fragment gets additional space at tail. * Note, with MSG_MORE we overallocate on fragments, * because we have no idea what fragment will be * the last. */ if (datalen == length + fraggap) alloc_extra += rt->dst.trailer_len; if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else if (!paged && (fraglen + alloc_extra < SKB_MAX_ALLOC || !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = min_t(int, fraglen, MAX_HEADER); pagedlen = fraglen - alloclen; } alloclen += alloc_extra; if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; } if (!skb) goto error; /* * Fill in the control structures */ skb->ip_summed = csummode; skb->csum = 0; skb_reserve(skb, hh_len); /* * Find where to start putting bytes. */ data = skb_put(skb, fraglen + exthdrlen - pagedlen); skb_set_network_header(skb, exthdrlen); skb->transport_header = (skb->network_header + fragheaderlen); data += fragheaderlen + exthdrlen; if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, data + transhdrlen, fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; pskb_trim_unique(skb_prev, maxfraglen); } copy = datalen - transhdrlen - fraggap - pagedlen; if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; } offset += copy; length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; csummode = CHECKSUM_NONE; /* only the initial fragment is time stamped */ skb_shinfo(skb)->tx_flags = cork->tx_flags; cork->tx_flags = 0; skb_shinfo(skb)->tskey = tskey; tskey = 0; skb_zcopy_set(skb, uarg, &extra_uref); if ((flags & MSG_CONFIRM) && !skb_prev) skb_set_dst_pending_confirm(skb, 1); /* * Put the packet on the pending queue. */ if (!skb->destructor) { skb->destructor = sock_wfree; skb->sk = sk; wmem_alloc_delta += skb->truesize; } __skb_queue_tail(queue, skb); continue; } if (copy > length) copy = length; if (!(rt->dst.dev->features&NETIF_F_SG) && skb_tailroom(skb) >= copy) { unsigned int off; off = skb->len; if (getfrag(from, skb_put(skb, copy), offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; } } else if (!uarg || !uarg->zerocopy) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; if (i == MAX_SKB_FRAGS) goto error; __skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, 0); skb_shinfo(skb)->nr_frags = ++i; get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (getfrag(from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; pfrag->offset += copy; skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; wmem_alloc_delta += copy; } else { err = skb_zerocopy_iter_dgram(skb, from, copy); if (err < 0) goto error; } offset += copy; length -= copy; } if (wmem_alloc_delta) refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return 0; error_efault: err = -EFAULT; error: net_zcopy_put_abort(uarg, extra_uref); cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return err; } static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, struct ipcm_cookie *ipc, struct rtable **rtp) { struct ip_options_rcu *opt; struct rtable *rt; rt = *rtp; if (unlikely(!rt)) return -EFAULT; cork->fragsize = ip_sk_use_pmtu(sk) ? dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); if (!inetdev_valid_mtu(cork->fragsize)) return -ENETUNREACH; /* * setup for corking. */ opt = ipc->opt; if (opt) { if (!cork->opt) { cork->opt = kmalloc(sizeof(struct ip_options) + 40, sk->sk_allocation); if (unlikely(!cork->opt)) return -ENOBUFS; } memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen); cork->flags |= IPCORK_OPT; cork->addr = ipc->addr; } cork->gso_size = ipc->gso_size; cork->dst = &rt->dst; /* We stole this route, caller should not release it. */ *rtp = NULL; cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; cork->mark = ipc->sockc.mark; cork->priority = ipc->priority; cork->transmit_time = ipc->sockc.transmit_time; cork->tx_flags = 0; sock_tx_timestamp(sk, ipc->sockc.tsflags, &cork->tx_flags); return 0; } /* * ip_append_data() and ip_append_page() can make one large IP datagram * from many pieces of data. Each pieces will be holded on the socket * until ip_push_pending_frames() is called. Each piece can be a page * or non-page data. * * Not only UDP, other transport protocols - e.g. raw sockets - can use * this interface potentially. * * LATER: length must be adjusted by pad at tail, when it is required. */ int ip_append_data(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); int err; if (flags&MSG_PROBE) return 0; if (skb_queue_empty(&sk->sk_write_queue)) { err = ip_setup_cork(sk, &inet->cork.base, ipc, rtp); if (err) return err; } else { transhdrlen = 0; } return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base, sk_page_frag(sk), getfrag, from, length, transhdrlen, flags); } ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, int offset, size_t size, int flags) { struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; struct rtable *rt; struct ip_options *opt = NULL; struct inet_cork *cork; int hh_len; int mtu; int len; int err; unsigned int maxfraglen, fragheaderlen, fraggap, maxnonfragsize; if (inet->hdrincl) return -EPERM; if (flags&MSG_PROBE) return 0; if (skb_queue_empty(&sk->sk_write_queue)) return -EINVAL; cork = &inet->cork.base; rt = (struct rtable *)cork->dst; if (cork->flags & IPCORK_OPT) opt = cork->opt; if (!(rt->dst.dev->features & NETIF_F_SG)) return -EOPNOTSUPP; hh_len = LL_RESERVED_SPACE(rt->dst.dev); mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu; if (cork->length + size > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu - (opt ? opt->optlen : 0)); return -EMSGSIZE; } skb = skb_peek_tail(&sk->sk_write_queue); if (!skb) return -EINVAL; cork->length += size; while (size > 0) { /* Check if the remaining data fits into current packet. */ len = mtu - skb->len; if (len < size) len = maxfraglen - skb->len; if (len <= 0) { struct sk_buff *skb_prev; int alloclen; skb_prev = skb; fraggap = skb_prev->len - maxfraglen; alloclen = fragheaderlen + hh_len + fraggap + 15; skb = sock_wmalloc(sk, alloclen, 1, sk->sk_allocation); if (unlikely(!skb)) { err = -ENOBUFS; goto error; } /* * Fill in the control structures */ skb->ip_summed = CHECKSUM_NONE; skb->csum = 0; skb_reserve(skb, hh_len); /* * Find where to start putting bytes. */ skb_put(skb, fragheaderlen + fraggap); skb_reset_network_header(skb); skb->transport_header = (skb->network_header + fragheaderlen); if (fraggap) { skb->csum = skb_copy_and_csum_bits(skb_prev, maxfraglen, skb_transport_header(skb), fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); pskb_trim_unique(skb_prev, maxfraglen); } /* * Put the packet on the pending queue. */ __skb_queue_tail(&sk->sk_write_queue, skb); continue; } if (len > size) len = size; if (skb_append_pagefrags(skb, page, offset, len)) { err = -EMSGSIZE; goto error; } if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum; csum = csum_page(page, offset, len); skb->csum = csum_block_add(skb->csum, csum, skb->len); } skb->len += len; skb->data_len += len; skb->truesize += len; refcount_add(len, &sk->sk_wmem_alloc); offset += len; size -= len; } return 0; error: cork->length -= size; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); return err; } static void ip_cork_release(struct inet_cork *cork) { cork->flags &= ~IPCORK_OPT; kfree(cork->opt); cork->opt = NULL; dst_release(cork->dst); cork->dst = NULL; } /* * Combined all pending IP fragments on the socket as one IP datagram * and push them out. */ struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork) { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options *opt = NULL; struct rtable *rt = (struct rtable *)cork->dst; struct iphdr *iph; __be16 df = 0; __u8 ttl; skb = __skb_dequeue(queue); if (!skb) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); /* move skb->data to ip header from ext header */ if (skb->data < skb_network_header(skb)) __skb_pull(skb, skb_network_offset(skb)); while ((tmp_skb = __skb_dequeue(queue)) != NULL) { __skb_pull(tmp_skb, skb_network_header_len(skb)); *tail_skb = tmp_skb; tail_skb = &(tmp_skb->next); skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } /* Unless user demanded real pmtu discovery (IP_PMTUDISC_DO), we allow * to fragment the frame generated here. No matter, what transforms * how transforms change size of the packet, it will come out. */ skb->ignore_df = ip_sk_ignore_df(sk); /* DF bit is set when we want to see DF on outgoing frames. * If ignore_df is set too, we still allow to fragment this frame * locally. */ if (inet->pmtudisc == IP_PMTUDISC_DO || inet->pmtudisc == IP_PMTUDISC_PROBE || (skb->len <= dst_mtu(&rt->dst) && ip_dont_fragment(sk, &rt->dst))) df = htons(IP_DF); if (cork->flags & IPCORK_OPT) opt = cork->opt; if (cork->ttl != 0) ttl = cork->ttl; else if (rt->rt_type == RTN_MULTICAST) ttl = inet->mc_ttl; else ttl = ip_select_ttl(inet, &rt->dst); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = (cork->tos != -1) ? cork->tos : inet->tos; iph->frag_off = df; iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); ip_select_ident(net, skb, sk); if (opt) { iph->ihl += opt->optlen >> 2; ip_options_build(skb, opt, cork->addr, rt, 0); } skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority; skb->mark = cork->mark; skb->tstamp = cork->transmit_time; /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount */ cork->dst = NULL; skb_dst_set(skb, &rt->dst); if (iph->protocol == IPPROTO_ICMP) { u8 icmp_type; /* For such sockets, transhdrlen is zero when do ip_append_data(), * so icmphdr does not in skb linear region and can not get icmp_type * by icmp_hdr(skb)->type. */ if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; icmp_out_count(net, icmp_type); } ip_cork_release(cork); out: return skb; } int ip_send_skb(struct net *net, struct sk_buff *skb) { int err; err = ip_local_out(net, skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); if (err) IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); } return err; } int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4) { struct sk_buff *skb; skb = ip_finish_skb(sk, fl4); if (!skb) return 0; /* Netfilter gets whole the not fragmented skb. */ return ip_send_skb(sock_net(sk), skb); } /* * Throw away all pending data on the socket. */ static void __ip_flush_pending_frames(struct sock *sk, struct sk_buff_head *queue, struct inet_cork *cork) { struct sk_buff *skb; while ((skb = __skb_dequeue_tail(queue)) != NULL) kfree_skb(skb); ip_cork_release(cork); } void ip_flush_pending_frames(struct sock *sk) { __ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base); } struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, struct inet_cork *cork, unsigned int flags) { struct sk_buff_head queue; int err; if (flags & MSG_PROBE) return NULL; __skb_queue_head_init(&queue); cork->flags = 0; cork->addr = 0; cork->opt = NULL; err = ip_setup_cork(sk, cork, ipc, rtp); if (err) return ERR_PTR(err); err = __ip_append_data(sk, fl4, &queue, cork, ¤t->task_frag, getfrag, from, length, transhdrlen, flags); if (err) { __ip_flush_pending_frames(sk, &queue, cork); return ERR_PTR(err); } return __ip_make_skb(sk, fl4, &queue, cork); } /* * Fetch data from kernel space and fill in checksum if needed. */ static int ip_reply_glue_bits(void *dptr, char *to, int offset, int len, int odd, struct sk_buff *skb) { __wsum csum; csum = csum_partial_copy_nocheck(dptr+offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); return 0; } /* * Generic function to send a packet as reply to another packet. * Used to send some TCP resets/acks so far. */ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len, u64 transmit_time) { struct ip_options_data replyopts; struct ipcm_cookie ipc; struct flowi4 fl4; struct rtable *rt = skb_rtable(skb); struct net *net = sock_net(sk); struct sk_buff *nskb; int err; int oif; if (__ip_options_echo(net, &replyopts.opt.opt, skb, sopt)) return; ipcm_init(&ipc); ipc.addr = daddr; ipc.sockc.transmit_time = transmit_time; if (replyopts.opt.opt.optlen) { ipc.opt = &replyopts.opt; if (replyopts.opt.opt.srr) daddr = replyopts.opt.opt.faddr; } oif = arg->bound_dev_if; if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) oif = skb->skb_iif; flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark, RT_TOS(arg->tos), RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, ip_reply_arg_flowi_flags(arg), daddr, saddr, tcp_hdr(skb)->source, tcp_hdr(skb)->dest, arg->uid); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) return; inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); ipc.sockc.mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if (unlikely(err)) { ip_flush_pending_frames(sk); goto out; } nskb = skb_peek(&sk->sk_write_queue); if (nskb) { if (arg->csumoffset >= 0) *((__sum16 *)skb_transport_header(nskb) + arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; ip_push_pending_frames(sk, &fl4); } out: ip_rt_put(rt); } void __init ip_init(void) { ip_rt_init(); inet_initpeers(); #if defined(CONFIG_IP_MULTICAST) igmp_mc_init(); #endif } |
| 2066 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM kmem #if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KMEM_H #include <linux/types.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> DECLARE_EVENT_CLASS(kmem_alloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( gfp_t, gfp_flags ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = gfp_flags; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); DEFINE_EVENT(kmem_alloc, kmalloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags) ); DEFINE_EVENT(kmem_alloc, kmem_cache_alloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags) ); DECLARE_EVENT_CLASS(kmem_alloc_node, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( gfp_t, gfp_flags ) __field( int, node ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = gfp_flags; __entry->node = node; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node) ); DEFINE_EVENT(kmem_alloc_node, kmalloc_node, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node) ); DEFINE_EVENT(kmem_alloc_node, kmem_cache_alloc_node, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node) ); TRACE_EVENT(kfree, TP_PROTO(unsigned long call_site, const void *ptr), TP_ARGS(call_site, ptr), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; ), TP_printk("call_site=%pS ptr=%p", (void *)__entry->call_site, __entry->ptr) ); TRACE_EVENT(kmem_cache_free, TP_PROTO(unsigned long call_site, const void *ptr, const char *name), TP_ARGS(call_site, ptr, name), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __string( name, name ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __assign_str(name, name); ), TP_printk("call_site=%pS ptr=%p name=%s", (void *)__entry->call_site, __entry->ptr, __get_str(name)) ); TRACE_EVENT(mm_page_free, TP_PROTO(struct page *page, unsigned int order), TP_ARGS(page, order), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->order = order; ), TP_printk("page=%p pfn=0x%lx order=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order) ); TRACE_EVENT(mm_page_free_batched, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field( unsigned long, pfn ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); ), TP_printk("page=%p pfn=0x%lx order=0", pfn_to_page(__entry->pfn), __entry->pfn) ); TRACE_EVENT(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype), TP_ARGS(page, order, gfp_flags, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( gfp_t, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->gfp_flags = gfp_flags; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d gfp_flags=%s", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, show_gfp_flags(__entry->gfp_flags)) ); DECLARE_EVENT_CLASS(mm_page, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, __entry->order == 0) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype) ); TRACE_EVENT(mm_page_pcpu_drain, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order, __entry->migratetype) ); TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( int, alloc_order ) __field( int, fallback_order ) __field( int, alloc_migratetype ) __field( int, fallback_migratetype ) __field( int, change_ownership ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->alloc_order = alloc_order; __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; __entry->change_ownership = (alloc_migratetype == get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=0x%lx alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->alloc_order, __entry->fallback_order, pageblock_order, __entry->alloc_migratetype, __entry->fallback_migratetype, __entry->fallback_order < pageblock_order, __entry->change_ownership) ); /* * Required for uniquely and securely identifying mm in rss_stat tracepoint. */ #ifndef __PTR_TO_HASHVAL static unsigned int __maybe_unused mm_ptr_to_hash(const void *ptr) { int ret; unsigned long hashval; ret = ptr_to_hashval(ptr, &hashval); if (ret) return 0; /* The hashed value is only 32-bit */ return (unsigned int)hashval; } #define __PTR_TO_HASHVAL #endif #define TRACE_MM_PAGES \ EM(MM_FILEPAGES) \ EM(MM_ANONPAGES) \ EM(MM_SWAPENTS) \ EMe(MM_SHMEMPAGES) #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); TRACE_MM_PAGES #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } TRACE_EVENT(rss_stat, TP_PROTO(struct mm_struct *mm, int member, long count), TP_ARGS(mm, member, count), TP_STRUCT__entry( __field(unsigned int, mm_id) __field(unsigned int, curr) __field(int, member) __field(long, size) ), TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); __entry->curr = !!(current->mm == mm); __entry->member = member; __entry->size = (count << PAGE_SHIFT); ), TP_printk("mm_id=%u curr=%d type=%s size=%ldB", __entry->mm_id, __entry->curr, __print_symbolic(__entry->member, TRACE_MM_PAGES), __entry->size) ); #endif /* _TRACE_KMEM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 4 4 4 4 4 4 1 3 4 4 65 65 65 65 99 1 99 99 5 2 2 1 3 3 5 4 1 5 4 4 3 4 2 70 4 4 4 7 7 7 2 1 1 1 1 161 160 161 161 161 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 | // SPDX-License-Identifier: GPL-2.0-or-later /* -*- linux-c -*- * INET 802.1Q VLAN * Ethernet-type device handling. * * Authors: Ben Greear <greearb@candelatech.com> * Please send support related email to: netdev@vger.kernel.org * VLAN Home Page: http://www.candelatech.com/~greear/vlan.html * * Fixes: Mar 22 2001: Martin Bokaemper <mbokaemper@unispherenetworks.com> * - reset skb->pkt_type on incoming packets when MAC was changed * - see that changed MAC is saddr for outgoing packets * Oct 20, 2001: Ard van Breeman: * - Fix MC-list, finally. * - Flush MC-list on VLAN destroy. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/net_tstamp.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/phy.h> #include <net/arp.h> #include "vlan.h" #include "vlanproc.h" #include <linux/if_vlan.h> #include <linux/netpoll.h> /* * Create the VLAN header for an arbitrary protocol layer * * saddr=NULL means use device source address * daddr=NULL means leave destination address (eg unresolved arp) * * This is called when the SKB is moving down the stack towards the * physical devices. */ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct vlan_hdr *vhdr; unsigned int vhdrlen = 0; u16 vlan_tci = 0; int rc; if (!(vlan->flags & VLAN_FLAG_REORDER_HDR)) { vhdr = skb_push(skb, VLAN_HLEN); vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority); vhdr->h_vlan_TCI = htons(vlan_tci); /* * Set the protocol type. For a packet of type ETH_P_802_3/2 we * put the length in here instead. */ if (type != ETH_P_802_3 && type != ETH_P_802_2) vhdr->h_vlan_encapsulated_proto = htons(type); else vhdr->h_vlan_encapsulated_proto = htons(len); skb->protocol = vlan->vlan_proto; type = ntohs(vlan->vlan_proto); vhdrlen = VLAN_HLEN; } /* Before delegating work to the lower layer, enter our MAC-address */ if (saddr == NULL) saddr = dev->dev_addr; /* Now make the underlying real hard header */ dev = vlan->real_dev; rc = dev_hard_header(skb, dev, type, daddr, saddr, len + vhdrlen); if (rc > 0) rc += vhdrlen; return rc; } static inline netdev_tx_t vlan_netpoll_send_skb(struct vlan_dev_priv *vlan, struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER return netpoll_send_skb(vlan->netpoll, skb); #else BUG(); return NETDEV_TX_OK; #endif } static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data); unsigned int len; int ret; /* Handle non-VLAN frames if they are sent to us, for example by DHCP. * * NOTE: THIS ASSUMES DIX ETHERNET, SPECIFICALLY NOT SUPPORTING * OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs... */ if (vlan->flags & VLAN_FLAG_REORDER_HDR || veth->h_vlan_proto != vlan->vlan_proto) { u16 vlan_tci; vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority); __vlan_hwaccel_put_tag(skb, vlan->vlan_proto, vlan_tci); } skb->dev = vlan->real_dev; len = skb->len; if (unlikely(netpoll_tx_running(dev))) return vlan_netpoll_send_skb(vlan, skb); ret = dev_queue_xmit(skb); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct vlan_pcpu_stats *stats; stats = this_cpu_ptr(vlan->vlan_pcpu_stats); u64_stats_update_begin(&stats->syncp); stats->tx_packets++; stats->tx_bytes += len; u64_stats_update_end(&stats->syncp); } else { this_cpu_inc(vlan->vlan_pcpu_stats->tx_dropped); } return ret; } static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; unsigned int max_mtu = real_dev->mtu; if (netif_reduces_vlan_mtu(real_dev)) max_mtu -= VLAN_HLEN; if (max_mtu < new_mtu) return -ERANGE; dev->mtu = new_mtu; return 0; } void vlan_dev_set_ingress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); if (vlan->ingress_priority_map[vlan_prio & 0x7] && !skb_prio) vlan->nr_ingress_mappings--; else if (!vlan->ingress_priority_map[vlan_prio & 0x7] && skb_prio) vlan->nr_ingress_mappings++; vlan->ingress_priority_map[vlan_prio & 0x7] = skb_prio; } int vlan_dev_set_egress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct vlan_priority_tci_mapping *mp = NULL; struct vlan_priority_tci_mapping *np; u32 vlan_qos = (vlan_prio << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK; /* See if a priority mapping exists.. */ mp = vlan->egress_priority_map[skb_prio & 0xF]; while (mp) { if (mp->priority == skb_prio) { if (mp->vlan_qos && !vlan_qos) vlan->nr_egress_mappings--; else if (!mp->vlan_qos && vlan_qos) vlan->nr_egress_mappings++; mp->vlan_qos = vlan_qos; return 0; } mp = mp->next; } /* Create a new mapping then. */ mp = vlan->egress_priority_map[skb_prio & 0xF]; np = kmalloc(sizeof(struct vlan_priority_tci_mapping), GFP_KERNEL); if (!np) return -ENOBUFS; np->next = mp; np->priority = skb_prio; np->vlan_qos = vlan_qos; /* Before inserting this element in hash table, make sure all its fields * are committed to memory. * coupled with smp_rmb() in vlan_dev_get_egress_qos_mask() */ smp_wmb(); vlan->egress_priority_map[skb_prio & 0xF] = np; if (vlan_qos) vlan->nr_egress_mappings++; return 0; } /* Flags are defined in the vlan_flags enum in * include/uapi/linux/if_vlan.h file. */ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); u32 old_flags = vlan->flags; if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP | VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP | VLAN_FLAG_BRIDGE_BINDING)) return -EINVAL; vlan->flags = (old_flags & ~mask) | (flags & mask); if (netif_running(dev) && (vlan->flags ^ old_flags) & VLAN_FLAG_GVRP) { if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_join(dev); else vlan_gvrp_request_leave(dev); } if (netif_running(dev) && (vlan->flags ^ old_flags) & VLAN_FLAG_MVRP) { if (vlan->flags & VLAN_FLAG_MVRP) vlan_mvrp_request_join(dev); else vlan_mvrp_request_leave(dev); } return 0; } void vlan_dev_get_realdev_name(const struct net_device *dev, char *result, size_t size) { strscpy_pad(result, vlan_dev_priv(dev)->real_dev->name, size); } bool vlan_dev_inherit_address(struct net_device *dev, struct net_device *real_dev) { if (dev->addr_assign_type != NET_ADDR_STOLEN) return false; eth_hw_addr_set(dev, real_dev->dev_addr); call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return true; } static int vlan_dev_open(struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; int err; if (!(real_dev->flags & IFF_UP) && !(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) return -ENETDOWN; if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr) && !vlan_dev_inherit_address(dev, real_dev)) { err = dev_uc_add(real_dev, dev->dev_addr); if (err < 0) goto out; } ether_addr_copy(vlan->real_dev_addr, real_dev->dev_addr); if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_join(dev); if (vlan->flags & VLAN_FLAG_MVRP) vlan_mvrp_request_join(dev); if (netif_carrier_ok(real_dev) && !(vlan->flags & VLAN_FLAG_BRIDGE_BINDING)) netif_carrier_on(dev); return 0; out: netif_carrier_off(dev); return err; } static int vlan_dev_stop(struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; dev_mc_unsync(real_dev, dev); dev_uc_unsync(real_dev, dev); if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) dev_uc_del(real_dev, dev->dev_addr); if (!(vlan->flags & VLAN_FLAG_BRIDGE_BINDING)) netif_carrier_off(dev); return 0; } static int vlan_dev_set_mac_address(struct net_device *dev, void *p) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; struct sockaddr *addr = p; int err; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; if (!(dev->flags & IFF_UP)) goto out; if (!ether_addr_equal(addr->sa_data, real_dev->dev_addr)) { err = dev_uc_add(real_dev, addr->sa_data); if (err < 0) return err; } if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) dev_uc_del(real_dev, dev->dev_addr); out: eth_hw_addr_set(dev, addr->sa_data); return 0; } static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; struct ifreq ifrr; int err = -EOPNOTSUPP; strscpy_pad(ifrr.ifr_name, real_dev->name, IFNAMSIZ); ifrr.ifr_ifru = ifr->ifr_ifru; switch (cmd) { case SIOCSHWTSTAMP: if (!net_eq(dev_net(dev), dev_net(real_dev))) break; fallthrough; case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: case SIOCGHWTSTAMP: if (netif_device_present(real_dev) && ops->ndo_eth_ioctl) err = ops->ndo_eth_ioctl(real_dev, &ifrr, cmd); break; } if (!err) ifr->ifr_ifru = ifrr.ifr_ifru; return err; } static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int err = 0; if (netif_device_present(real_dev) && ops->ndo_neigh_setup) err = ops->ndo_neigh_setup(real_dev, pa); return err; } #if IS_ENABLED(CONFIG_FCOE) static int vlan_dev_fcoe_ddp_setup(struct net_device *dev, u16 xid, struct scatterlist *sgl, unsigned int sgc) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int rc = 0; if (ops->ndo_fcoe_ddp_setup) rc = ops->ndo_fcoe_ddp_setup(real_dev, xid, sgl, sgc); return rc; } static int vlan_dev_fcoe_ddp_done(struct net_device *dev, u16 xid) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int len = 0; if (ops->ndo_fcoe_ddp_done) len = ops->ndo_fcoe_ddp_done(real_dev, xid); return len; } static int vlan_dev_fcoe_enable(struct net_device *dev) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int rc = -EINVAL; if (ops->ndo_fcoe_enable) rc = ops->ndo_fcoe_enable(real_dev); return rc; } static int vlan_dev_fcoe_disable(struct net_device *dev) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int rc = -EINVAL; if (ops->ndo_fcoe_disable) rc = ops->ndo_fcoe_disable(real_dev); return rc; } static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid, struct scatterlist *sgl, unsigned int sgc) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int rc = 0; if (ops->ndo_fcoe_ddp_target) rc = ops->ndo_fcoe_ddp_target(real_dev, xid, sgl, sgc); return rc; } #endif #ifdef NETDEV_FCOE_WWNN static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int rc = -EINVAL; if (ops->ndo_fcoe_get_wwn) rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type); return rc; } #endif static void vlan_dev_change_rx_flags(struct net_device *dev, int change) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; if (change & IFF_ALLMULTI) dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1); if (change & IFF_PROMISC) dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1); } static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) { dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); } /* * vlan network devices have devices nesting below it, and are a special * "super class" of normal network devices; split their locks off into a * separate class since they always nest. */ static struct lock_class_key vlan_netdev_xmit_lock_key; static struct lock_class_key vlan_netdev_addr_lock_key; static void vlan_dev_set_lockdep_one(struct net_device *dev, struct netdev_queue *txq, void *unused) { lockdep_set_class(&txq->_xmit_lock, &vlan_netdev_xmit_lock_key); } static void vlan_dev_set_lockdep_class(struct net_device *dev) { lockdep_set_class(&dev->addr_list_lock, &vlan_netdev_addr_lock_key); netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, NULL); } static __be16 vlan_parse_protocol(const struct sk_buff *skb) { struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data); return __vlan_get_protocol(skb, veth->h_vlan_proto, NULL); } static const struct header_ops vlan_header_ops = { .create = vlan_dev_hard_header, .parse = eth_header_parse, .parse_protocol = vlan_parse_protocol, }; static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; if (saddr == NULL) saddr = dev->dev_addr; return dev_hard_header(skb, real_dev, type, daddr, saddr, len); } static const struct header_ops vlan_passthru_header_ops = { .create = vlan_passthru_hard_header, .parse = eth_header_parse, .parse_protocol = vlan_parse_protocol, }; static struct device_type vlan_type = { .name = "vlan", }; static const struct net_device_ops vlan_netdev_ops; static int vlan_dev_init(struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; netif_carrier_off(dev); /* IFF_BROADCAST|IFF_MULTICAST; ??? */ dev->flags = real_dev->flags & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_MASTER | IFF_SLAVE); dev->state = (real_dev->state & ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))) | (1<<__LINK_STATE_PRESENT); if (vlan->flags & VLAN_FLAG_BRIDGE_BINDING) dev->state |= (1 << __LINK_STATE_NOCARRIER); dev->hw_features = NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC | NETIF_F_ALL_FCOE; dev->features |= dev->hw_features | NETIF_F_LLTX; dev->gso_max_size = real_dev->gso_max_size; dev->gso_max_segs = real_dev->gso_max_segs; if (dev->features & NETIF_F_VLAN_FEATURES) netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n"); dev->vlan_features = real_dev->vlan_features & ~NETIF_F_ALL_FCOE; dev->hw_enc_features = vlan_tnl_features(real_dev); dev->mpls_features = real_dev->mpls_features; /* ipv6 shared card related stuff */ dev->dev_id = real_dev->dev_id; if (is_zero_ether_addr(dev->dev_addr)) { eth_hw_addr_set(dev, real_dev->dev_addr); dev->addr_assign_type = NET_ADDR_STOLEN; } if (is_zero_ether_addr(dev->broadcast)) memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len); #if IS_ENABLED(CONFIG_FCOE) dev->fcoe_ddp_xid = real_dev->fcoe_ddp_xid; #endif dev->needed_headroom = real_dev->needed_headroom; if (vlan_hw_offload_capable(real_dev->features, vlan->vlan_proto)) { dev->header_ops = &vlan_passthru_header_ops; dev->hard_header_len = real_dev->hard_header_len; } else { dev->header_ops = &vlan_header_ops; dev->hard_header_len = real_dev->hard_header_len + VLAN_HLEN; } dev->netdev_ops = &vlan_netdev_ops; SET_NETDEV_DEVTYPE(dev, &vlan_type); vlan_dev_set_lockdep_class(dev); vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->vlan_pcpu_stats) return -ENOMEM; /* Get vlan's reference to real_dev */ dev_hold(real_dev); return 0; } /* Note: this function might be called multiple times for the same device. */ void vlan_dev_free_egress_priority(const struct net_device *dev) { struct vlan_priority_tci_mapping *pm; struct vlan_dev_priv *vlan = vlan_dev_priv(dev); int i; for (i = 0; i < ARRAY_SIZE(vlan->egress_priority_map); i++) { while ((pm = vlan->egress_priority_map[i]) != NULL) { vlan->egress_priority_map[i] = pm->next; kfree(pm); } } } static void vlan_dev_uninit(struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); vlan_dev_free_egress_priority(dev); /* Get rid of the vlan's reference to real_dev */ dev_put(vlan->real_dev); } static netdev_features_t vlan_dev_fix_features(struct net_device *dev, netdev_features_t features) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; netdev_features_t old_features = features; netdev_features_t lower_features; lower_features = netdev_intersect_features((real_dev->vlan_features | NETIF_F_RXCSUM), real_dev->features); /* Add HW_CSUM setting to preserve user ability to control * checksum offload on the vlan device. */ if (lower_features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) lower_features |= NETIF_F_HW_CSUM; features = netdev_intersect_features(features, lower_features); features |= old_features & (NETIF_F_SOFT_FEATURES | NETIF_F_GSO_SOFTWARE); features |= NETIF_F_LLTX; return features; } static int vlan_ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { const struct vlan_dev_priv *vlan = vlan_dev_priv(dev); return __ethtool_get_link_ksettings(vlan->real_dev, cmd); } static void vlan_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, vlan_fullname, sizeof(info->driver)); strlcpy(info->version, vlan_version, sizeof(info->version)); strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); } static int vlan_ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { const struct vlan_dev_priv *vlan = vlan_dev_priv(dev); const struct ethtool_ops *ops = vlan->real_dev->ethtool_ops; struct phy_device *phydev = vlan->real_dev->phydev; if (phy_has_tsinfo(phydev)) { return phy_ts_info(phydev, info); } else if (ops->get_ts_info) { return ops->get_ts_info(vlan->real_dev, info); } else { info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_SOFTWARE; info->phc_index = -1; } return 0; } static void vlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct vlan_pcpu_stats *p; u32 rx_errors = 0, tx_dropped = 0; int i; for_each_possible_cpu(i) { u64 rxpackets, rxbytes, rxmulticast, txpackets, txbytes; unsigned int start; p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i); do { start = u64_stats_fetch_begin_irq(&p->syncp); rxpackets = p->rx_packets; rxbytes = p->rx_bytes; rxmulticast = p->rx_multicast; txpackets = p->tx_packets; txbytes = p->tx_bytes; } while (u64_stats_fetch_retry_irq(&p->syncp, start)); stats->rx_packets += rxpackets; stats->rx_bytes += rxbytes; stats->multicast += rxmulticast; stats->tx_packets += txpackets; stats->tx_bytes += txbytes; /* rx_errors & tx_dropped are u32 */ rx_errors += p->rx_errors; tx_dropped += p->tx_dropped; } stats->rx_errors = rx_errors; stats->tx_dropped = tx_dropped; } #ifdef CONFIG_NET_POLL_CONTROLLER static void vlan_dev_poll_controller(struct net_device *dev) { return; } static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; struct netpoll *netpoll; int err = 0; netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); err = -ENOMEM; if (!netpoll) goto out; err = __netpoll_setup(netpoll, real_dev); if (err) { kfree(netpoll); goto out; } vlan->netpoll = netpoll; out: return err; } static void vlan_dev_netpoll_cleanup(struct net_device *dev) { struct vlan_dev_priv *vlan= vlan_dev_priv(dev); struct netpoll *netpoll = vlan->netpoll; if (!netpoll) return; vlan->netpoll = NULL; __netpoll_free(netpoll); } #endif /* CONFIG_NET_POLL_CONTROLLER */ static int vlan_dev_get_iflink(const struct net_device *dev) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; return real_dev->ifindex; } static int vlan_dev_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct vlan_dev_priv *vlan = vlan_dev_priv(ctx->dev); path->type = DEV_PATH_VLAN; path->encap.id = vlan->vlan_id; path->encap.proto = vlan->vlan_proto; path->dev = ctx->dev; ctx->dev = vlan->real_dev; if (ctx->num_vlans >= ARRAY_SIZE(ctx->vlan)) return -ENOSPC; ctx->vlan[ctx->num_vlans].id = vlan->vlan_id; ctx->vlan[ctx->num_vlans].proto = vlan->vlan_proto; ctx->num_vlans++; return 0; } static const struct ethtool_ops vlan_ethtool_ops = { .get_link_ksettings = vlan_ethtool_get_link_ksettings, .get_drvinfo = vlan_ethtool_get_drvinfo, .get_link = ethtool_op_get_link, .get_ts_info = vlan_ethtool_get_ts_info, }; static const struct net_device_ops vlan_netdev_ops = { .ndo_change_mtu = vlan_dev_change_mtu, .ndo_init = vlan_dev_init, .ndo_uninit = vlan_dev_uninit, .ndo_open = vlan_dev_open, .ndo_stop = vlan_dev_stop, .ndo_start_xmit = vlan_dev_hard_start_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = vlan_dev_set_mac_address, .ndo_set_rx_mode = vlan_dev_set_rx_mode, .ndo_change_rx_flags = vlan_dev_change_rx_flags, .ndo_eth_ioctl = vlan_dev_ioctl, .ndo_neigh_setup = vlan_dev_neigh_setup, .ndo_get_stats64 = vlan_dev_get_stats64, #if IS_ENABLED(CONFIG_FCOE) .ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup, .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, .ndo_fcoe_enable = vlan_dev_fcoe_enable, .ndo_fcoe_disable = vlan_dev_fcoe_disable, .ndo_fcoe_ddp_target = vlan_dev_fcoe_ddp_target, #endif #ifdef NETDEV_FCOE_WWNN .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn, #endif #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = vlan_dev_poll_controller, .ndo_netpoll_setup = vlan_dev_netpoll_setup, .ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup, #endif .ndo_fix_features = vlan_dev_fix_features, .ndo_get_iflink = vlan_dev_get_iflink, .ndo_fill_forward_path = vlan_dev_fill_forward_path, }; static void vlan_dev_free(struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); free_percpu(vlan->vlan_pcpu_stats); vlan->vlan_pcpu_stats = NULL; } void vlan_setup(struct net_device *dev) { ether_setup(dev); dev->priv_flags |= IFF_802_1Q_VLAN | IFF_NO_QUEUE; dev->priv_flags |= IFF_UNICAST_FLT; dev->priv_flags &= ~IFF_TX_SKB_SHARING; netif_keep_dst(dev); dev->netdev_ops = &vlan_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = vlan_dev_free; dev->ethtool_ops = &vlan_ethtool_ops; dev->min_mtu = 0; dev->max_mtu = ETH_MAX_MTU; eth_zero_addr(dev->broadcast); } |
| 528 528 527 528 528 528 528 528 528 528 528 528 528 528 528 528 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2002,2003 by Andreas Gruenbacher <a.gruenbacher@computer.org> * * Fixes from William Schumacher incorporated on 15 March 2001. * (Reported by Charles Bertsch, <CBertsch@microtest.com>). */ /* * This file contains generic functions for manipulating * POSIX 1003.1e draft standard 17 ACLs. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/atomic.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/xattr.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/mnt_idmapping.h> static struct posix_acl **acl_by_type(struct inode *inode, int type) { switch (type) { case ACL_TYPE_ACCESS: return &inode->i_acl; case ACL_TYPE_DEFAULT: return &inode->i_default_acl; default: BUG(); } } struct posix_acl *get_cached_acl(struct inode *inode, int type) { struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *acl; for (;;) { rcu_read_lock(); acl = rcu_dereference(*p); if (!acl || is_uncached_acl(acl) || refcount_inc_not_zero(&acl->a_refcount)) break; rcu_read_unlock(); cpu_relax(); } rcu_read_unlock(); return acl; } EXPORT_SYMBOL(get_cached_acl); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type) { struct posix_acl *acl = rcu_dereference(*acl_by_type(inode, type)); if (acl == ACL_DONT_CACHE) { struct posix_acl *ret; ret = inode->i_op->get_acl(inode, type, LOOKUP_RCU); if (!IS_ERR(ret)) acl = ret; } return acl; } EXPORT_SYMBOL(get_cached_acl_rcu); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl) { struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *old; old = xchg(p, posix_acl_dup(acl)); if (!is_uncached_acl(old)) posix_acl_release(old); } EXPORT_SYMBOL(set_cached_acl); static void __forget_cached_acl(struct posix_acl **p) { struct posix_acl *old; old = xchg(p, ACL_NOT_CACHED); if (!is_uncached_acl(old)) posix_acl_release(old); } void forget_cached_acl(struct inode *inode, int type) { __forget_cached_acl(acl_by_type(inode, type)); } EXPORT_SYMBOL(forget_cached_acl); void forget_all_cached_acls(struct inode *inode) { __forget_cached_acl(&inode->i_acl); __forget_cached_acl(&inode->i_default_acl); } EXPORT_SYMBOL(forget_all_cached_acls); struct posix_acl *get_acl(struct inode *inode, int type) { void *sentinel; struct posix_acl **p; struct posix_acl *acl; /* * The sentinel is used to detect when another operation like * set_cached_acl() or forget_cached_acl() races with get_acl(). * It is guaranteed that is_uncached_acl(sentinel) is true. */ acl = get_cached_acl(inode, type); if (!is_uncached_acl(acl)) return acl; if (!IS_POSIXACL(inode)) return NULL; sentinel = uncached_acl_sentinel(current); p = acl_by_type(inode, type); /* * If the ACL isn't being read yet, set our sentinel. Otherwise, the * current value of the ACL will not be ACL_NOT_CACHED and so our own * sentinel will not be set; another task will update the cache. We * could wait for that other task to complete its job, but it's easier * to just call ->get_acl to fetch the ACL ourself. (This is going to * be an unlikely race.) */ if (cmpxchg(p, ACL_NOT_CACHED, sentinel) != ACL_NOT_CACHED) /* fall through */ ; /* * Normally, the ACL returned by ->get_acl will be cached. * A filesystem can prevent that by calling * forget_cached_acl(inode, type) in ->get_acl. * * If the filesystem doesn't have a get_acl() function at all, we'll * just create the negative cache entry. */ if (!inode->i_op->get_acl) { set_cached_acl(inode, type, NULL); return NULL; } acl = inode->i_op->get_acl(inode, type, false); if (IS_ERR(acl)) { /* * Remove our sentinel so that we don't block future attempts * to cache the ACL. */ cmpxchg(p, sentinel, ACL_NOT_CACHED); return acl; } /* * Cache the result, but only if our sentinel is still in place. */ posix_acl_dup(acl); if (unlikely(cmpxchg(p, sentinel, acl) != sentinel)) posix_acl_release(acl); return acl; } EXPORT_SYMBOL(get_acl); /* * Init a fresh posix_acl */ void posix_acl_init(struct posix_acl *acl, int count) { refcount_set(&acl->a_refcount, 1); acl->a_count = count; } EXPORT_SYMBOL(posix_acl_init); /* * Allocate a new ACL with the specified number of entries. */ struct posix_acl * posix_acl_alloc(int count, gfp_t flags) { const size_t size = sizeof(struct posix_acl) + count * sizeof(struct posix_acl_entry); struct posix_acl *acl = kmalloc(size, flags); if (acl) posix_acl_init(acl, count); return acl; } EXPORT_SYMBOL(posix_acl_alloc); /* * Clone an ACL. */ static struct posix_acl * posix_acl_clone(const struct posix_acl *acl, gfp_t flags) { struct posix_acl *clone = NULL; if (acl) { int size = sizeof(struct posix_acl) + acl->a_count * sizeof(struct posix_acl_entry); clone = kmemdup(acl, size, flags); if (clone) refcount_set(&clone->a_refcount, 1); } return clone; } /* * Check if an acl is valid. Returns 0 if it is, or -E... otherwise. */ int posix_acl_valid(struct user_namespace *user_ns, const struct posix_acl *acl) { const struct posix_acl_entry *pa, *pe; int state = ACL_USER_OBJ; int needs_mask = 0; FOREACH_ACL_ENTRY(pa, acl, pe) { if (pa->e_perm & ~(ACL_READ|ACL_WRITE|ACL_EXECUTE)) return -EINVAL; switch (pa->e_tag) { case ACL_USER_OBJ: if (state == ACL_USER_OBJ) { state = ACL_USER; break; } return -EINVAL; case ACL_USER: if (state != ACL_USER) return -EINVAL; if (!kuid_has_mapping(user_ns, pa->e_uid)) return -EINVAL; needs_mask = 1; break; case ACL_GROUP_OBJ: if (state == ACL_USER) { state = ACL_GROUP; break; } return -EINVAL; case ACL_GROUP: if (state != ACL_GROUP) return -EINVAL; if (!kgid_has_mapping(user_ns, pa->e_gid)) return -EINVAL; needs_mask = 1; break; case ACL_MASK: if (state != ACL_GROUP) return -EINVAL; state = ACL_OTHER; break; case ACL_OTHER: if (state == ACL_OTHER || (state == ACL_GROUP && !needs_mask)) { state = 0; break; } return -EINVAL; default: return -EINVAL; } } if (state == 0) return 0; return -EINVAL; } EXPORT_SYMBOL(posix_acl_valid); /* * Returns 0 if the acl can be exactly represented in the traditional * file mode permission bits, or else 1. Returns -E... on error. */ int posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p) { const struct posix_acl_entry *pa, *pe; umode_t mode = 0; int not_equiv = 0; /* * A null ACL can always be presented as mode bits. */ if (!acl) return 0; FOREACH_ACL_ENTRY(pa, acl, pe) { switch (pa->e_tag) { case ACL_USER_OBJ: mode |= (pa->e_perm & S_IRWXO) << 6; break; case ACL_GROUP_OBJ: mode |= (pa->e_perm & S_IRWXO) << 3; break; case ACL_OTHER: mode |= pa->e_perm & S_IRWXO; break; case ACL_MASK: mode = (mode & ~S_IRWXG) | ((pa->e_perm & S_IRWXO) << 3); not_equiv = 1; break; case ACL_USER: case ACL_GROUP: not_equiv = 1; break; default: return -EINVAL; } } if (mode_p) *mode_p = (*mode_p & ~S_IRWXUGO) | mode; return not_equiv; } EXPORT_SYMBOL(posix_acl_equiv_mode); /* * Create an ACL representing the file mode permission bits of an inode. */ struct posix_acl * posix_acl_from_mode(umode_t mode, gfp_t flags) { struct posix_acl *acl = posix_acl_alloc(3, flags); if (!acl) return ERR_PTR(-ENOMEM); acl->a_entries[0].e_tag = ACL_USER_OBJ; acl->a_entries[0].e_perm = (mode & S_IRWXU) >> 6; acl->a_entries[1].e_tag = ACL_GROUP_OBJ; acl->a_entries[1].e_perm = (mode & S_IRWXG) >> 3; acl->a_entries[2].e_tag = ACL_OTHER; acl->a_entries[2].e_perm = (mode & S_IRWXO); return acl; } EXPORT_SYMBOL(posix_acl_from_mode); /* * Return 0 if current is granted want access to the inode * by the acl. Returns -E... otherwise. */ int posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, const struct posix_acl *acl, int want) { const struct posix_acl_entry *pa, *pe, *mask_obj; int found = 0; kuid_t uid; kgid_t gid; want &= MAY_READ | MAY_WRITE | MAY_EXEC; FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: /* (May have been checked already) */ uid = i_uid_into_mnt(mnt_userns, inode); if (uid_eq(uid, current_fsuid())) goto check_perm; break; case ACL_USER: uid = mapped_kuid_fs(mnt_userns, i_user_ns(inode), pa->e_uid); if (uid_eq(uid, current_fsuid())) goto mask; break; case ACL_GROUP_OBJ: gid = i_gid_into_mnt(mnt_userns, inode); if (in_group_p(gid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; } break; case ACL_GROUP: gid = mapped_kgid_fs(mnt_userns, i_user_ns(inode), pa->e_gid); if (in_group_p(gid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; } break; case ACL_MASK: break; case ACL_OTHER: if (found) return -EACCES; else goto check_perm; default: return -EIO; } } return -EIO; mask: for (mask_obj = pa+1; mask_obj != pe; mask_obj++) { if (mask_obj->e_tag == ACL_MASK) { if ((pa->e_perm & mask_obj->e_perm & want) == want) return 0; return -EACCES; } } check_perm: if ((pa->e_perm & want) == want) return 0; return -EACCES; } /* * Modify acl when creating a new inode. The caller must ensure the acl is * only referenced once. * * mode_p initially must contain the mode parameter to the open() / creat() * system calls. All permissions that are not granted by the acl are removed. * The permissions in the acl are changed to reflect the mode_p parameter. */ static int posix_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) { struct posix_acl_entry *pa, *pe; struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; umode_t mode = *mode_p; int not_equiv = 0; /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: pa->e_perm &= (mode >> 6) | ~S_IRWXO; mode &= (pa->e_perm << 6) | ~S_IRWXU; break; case ACL_USER: case ACL_GROUP: not_equiv = 1; break; case ACL_GROUP_OBJ: group_obj = pa; break; case ACL_OTHER: pa->e_perm &= mode | ~S_IRWXO; mode &= pa->e_perm | ~S_IRWXO; break; case ACL_MASK: mask_obj = pa; not_equiv = 1; break; default: return -EIO; } } if (mask_obj) { mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (mask_obj->e_perm << 3) | ~S_IRWXG; } else { if (!group_obj) return -EIO; group_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (group_obj->e_perm << 3) | ~S_IRWXG; } *mode_p = (*mode_p & ~S_IRWXUGO) | mode; return not_equiv; } /* * Modify the ACL for the chmod syscall. */ static int __posix_acl_chmod_masq(struct posix_acl *acl, umode_t mode) { struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; struct posix_acl_entry *pa, *pe; /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: pa->e_perm = (mode & S_IRWXU) >> 6; break; case ACL_USER: case ACL_GROUP: break; case ACL_GROUP_OBJ: group_obj = pa; break; case ACL_MASK: mask_obj = pa; break; case ACL_OTHER: pa->e_perm = (mode & S_IRWXO); break; default: return -EIO; } } if (mask_obj) { mask_obj->e_perm = (mode & S_IRWXG) >> 3; } else { if (!group_obj) return -EIO; group_obj->e_perm = (mode & S_IRWXG) >> 3; } return 0; } int __posix_acl_create(struct posix_acl **acl, gfp_t gfp, umode_t *mode_p) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; if (clone) { err = posix_acl_create_masq(clone, mode_p); if (err < 0) { posix_acl_release(clone); clone = NULL; } } posix_acl_release(*acl); *acl = clone; return err; } EXPORT_SYMBOL(__posix_acl_create); int __posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, umode_t mode) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; if (clone) { err = __posix_acl_chmod_masq(clone, mode); if (err) { posix_acl_release(clone); clone = NULL; } } posix_acl_release(*acl); *acl = clone; return err; } EXPORT_SYMBOL(__posix_acl_chmod); /** * posix_acl_chmod - chmod a posix acl * * @mnt_userns: user namespace of the mount @inode was found from * @inode: inode to check permissions on * @mode: the new mode of @inode * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. */ int posix_acl_chmod(struct user_namespace *mnt_userns, struct inode *inode, umode_t mode) { struct posix_acl *acl; int ret = 0; if (!IS_POSIXACL(inode)) return 0; if (!inode->i_op->set_acl) return -EOPNOTSUPP; acl = get_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR_OR_NULL(acl)) { if (acl == ERR_PTR(-EOPNOTSUPP)) return 0; return PTR_ERR(acl); } ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode); if (ret) return ret; ret = inode->i_op->set_acl(mnt_userns, inode, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); return ret; } EXPORT_SYMBOL(posix_acl_chmod); int posix_acl_create(struct inode *dir, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl) { struct posix_acl *p; struct posix_acl *clone; int ret; *acl = NULL; *default_acl = NULL; if (S_ISLNK(*mode) || !IS_POSIXACL(dir)) return 0; p = get_acl(dir, ACL_TYPE_DEFAULT); if (!p || p == ERR_PTR(-EOPNOTSUPP)) { *mode &= ~current_umask(); return 0; } if (IS_ERR(p)) return PTR_ERR(p); ret = -ENOMEM; clone = posix_acl_clone(p, GFP_NOFS); if (!clone) goto err_release; ret = posix_acl_create_masq(clone, mode); if (ret < 0) goto err_release_clone; if (ret == 0) posix_acl_release(clone); else *acl = clone; if (!S_ISDIR(*mode)) posix_acl_release(p); else *default_acl = p; return 0; err_release_clone: posix_acl_release(clone); err_release: posix_acl_release(p); return ret; } EXPORT_SYMBOL_GPL(posix_acl_create); /** * posix_acl_update_mode - update mode in set_acl * @mnt_userns: user namespace of the mount @inode was found from * @inode: target inode * @mode_p: mode (pointer) for update * @acl: acl pointer * * Update the file mode when setting an ACL: compute the new file permission * bits based on the ACL. In addition, if the ACL is equivalent to the new * file mode, set *@acl to NULL to indicate that no ACL should be set. * * As with chmod, clear the setgid bit if the caller is not in the owning group * or capable of CAP_FSETID (see inode_change_ok). * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. * * Called from set_acl inode operations. */ int posix_acl_update_mode(struct user_namespace *mnt_userns, struct inode *inode, umode_t *mode_p, struct posix_acl **acl) { umode_t mode = inode->i_mode; int error; error = posix_acl_equiv_mode(*acl, &mode); if (error < 0) return error; if (error == 0) *acl = NULL; if (!in_group_p(i_gid_into_mnt(mnt_userns, inode)) && !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) mode &= ~S_ISGID; *mode_p = mode; return 0; } EXPORT_SYMBOL(posix_acl_update_mode); /* * Fix up the uids and gids in posix acl extended attributes in place. */ static void posix_acl_fix_xattr_userns( struct user_namespace *to, struct user_namespace *from, struct user_namespace *mnt_userns, void *value, size_t size, bool from_user) { struct posix_acl_xattr_header *header = value; struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end; int count; kuid_t uid; kgid_t gid; if (!value) return; if (size < sizeof(struct posix_acl_xattr_header)) return; if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION)) return; count = posix_acl_xattr_count(size); if (count < 0) return; if (count == 0) return; for (end = entry + count; entry != end; entry++) { switch(le16_to_cpu(entry->e_tag)) { case ACL_USER: uid = make_kuid(from, le32_to_cpu(entry->e_id)); if (from_user) uid = mapped_kuid_user(mnt_userns, &init_user_ns, uid); else uid = mapped_kuid_fs(mnt_userns, &init_user_ns, uid); entry->e_id = cpu_to_le32(from_kuid(to, uid)); break; case ACL_GROUP: gid = make_kgid(from, le32_to_cpu(entry->e_id)); if (from_user) gid = mapped_kgid_user(mnt_userns, &init_user_ns, gid); else gid = mapped_kgid_fs(mnt_userns, &init_user_ns, gid); entry->e_id = cpu_to_le32(from_kgid(to, gid)); break; default: break; } } } void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, struct inode *inode, void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); /* Leave ids untouched on non-idmapped mounts. */ if (no_idmapping(mnt_userns, i_user_ns(inode))) mnt_userns = &init_user_ns; if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; posix_acl_fix_xattr_userns(&init_user_ns, user_ns, mnt_userns, value, size, true); } void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, struct inode *inode, void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); /* Leave ids untouched on non-idmapped mounts. */ if (no_idmapping(mnt_userns, i_user_ns(inode))) mnt_userns = &init_user_ns; if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; posix_acl_fix_xattr_userns(user_ns, &init_user_ns, mnt_userns, value, size, false); } /* * Convert from extended attribute to in-memory representation. */ struct posix_acl * posix_acl_from_xattr(struct user_namespace *user_ns, const void *value, size_t size) { const struct posix_acl_xattr_header *header = value; const struct posix_acl_xattr_entry *entry = (const void *)(header + 1), *end; int count; struct posix_acl *acl; struct posix_acl_entry *acl_e; if (!value) return NULL; if (size < sizeof(struct posix_acl_xattr_header)) return ERR_PTR(-EINVAL); if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION)) return ERR_PTR(-EOPNOTSUPP); count = posix_acl_xattr_count(size); if (count < 0) return ERR_PTR(-EINVAL); if (count == 0) return NULL; acl = posix_acl_alloc(count, GFP_NOFS); if (!acl) return ERR_PTR(-ENOMEM); acl_e = acl->a_entries; for (end = entry + count; entry != end; acl_e++, entry++) { acl_e->e_tag = le16_to_cpu(entry->e_tag); acl_e->e_perm = le16_to_cpu(entry->e_perm); switch(acl_e->e_tag) { case ACL_USER_OBJ: case ACL_GROUP_OBJ: case ACL_MASK: case ACL_OTHER: break; case ACL_USER: acl_e->e_uid = make_kuid(user_ns, le32_to_cpu(entry->e_id)); if (!uid_valid(acl_e->e_uid)) goto fail; break; case ACL_GROUP: acl_e->e_gid = make_kgid(user_ns, le32_to_cpu(entry->e_id)); if (!gid_valid(acl_e->e_gid)) goto fail; break; default: goto fail; } } return acl; fail: posix_acl_release(acl); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL (posix_acl_from_xattr); /* * Convert from in-memory to extended attribute representation. */ int posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl, void *buffer, size_t size) { struct posix_acl_xattr_header *ext_acl = buffer; struct posix_acl_xattr_entry *ext_entry; int real_size, n; real_size = posix_acl_xattr_size(acl->a_count); if (!buffer) return real_size; if (real_size > size) return -ERANGE; ext_entry = (void *)(ext_acl + 1); ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION); for (n=0; n < acl->a_count; n++, ext_entry++) { const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext_entry->e_tag = cpu_to_le16(acl_e->e_tag); ext_entry->e_perm = cpu_to_le16(acl_e->e_perm); switch(acl_e->e_tag) { case ACL_USER: ext_entry->e_id = cpu_to_le32(from_kuid(user_ns, acl_e->e_uid)); break; case ACL_GROUP: ext_entry->e_id = cpu_to_le32(from_kgid(user_ns, acl_e->e_gid)); break; default: ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); break; } } return real_size; } EXPORT_SYMBOL (posix_acl_to_xattr); static int posix_acl_xattr_get(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *value, size_t size) { struct posix_acl *acl; int error; if (!IS_POSIXACL(inode)) return -EOPNOTSUPP; if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; acl = get_acl(inode, handler->flags); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl == NULL) return -ENODATA; error = posix_acl_to_xattr(&init_user_ns, acl, value, size); posix_acl_release(acl); return error; } int set_posix_acl(struct user_namespace *mnt_userns, struct inode *inode, int type, struct posix_acl *acl) { if (!IS_POSIXACL(inode)) return -EOPNOTSUPP; if (!inode->i_op->set_acl) return -EOPNOTSUPP; if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; if (!inode_owner_or_capable(mnt_userns, inode)) return -EPERM; if (acl) { int ret = posix_acl_valid(inode->i_sb->s_user_ns, acl); if (ret) return ret; } return inode->i_op->set_acl(mnt_userns, inode, acl, type); } EXPORT_SYMBOL(set_posix_acl); static int posix_acl_xattr_set(const struct xattr_handler *handler, struct user_namespace *mnt_userns, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct posix_acl *acl = NULL; int ret; if (value) { acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); } ret = set_posix_acl(mnt_userns, inode, handler->flags, acl); posix_acl_release(acl); return ret; } static bool posix_acl_xattr_list(struct dentry *dentry) { return IS_POSIXACL(d_backing_inode(dentry)); } const struct xattr_handler posix_acl_access_xattr_handler = { .name = XATTR_NAME_POSIX_ACL_ACCESS, .flags = ACL_TYPE_ACCESS, .list = posix_acl_xattr_list, .get = posix_acl_xattr_get, .set = posix_acl_xattr_set, }; EXPORT_SYMBOL_GPL(posix_acl_access_xattr_handler); const struct xattr_handler posix_acl_default_xattr_handler = { .name = XATTR_NAME_POSIX_ACL_DEFAULT, .flags = ACL_TYPE_DEFAULT, .list = posix_acl_xattr_list, .get = posix_acl_xattr_get, .set = posix_acl_xattr_set, }; EXPORT_SYMBOL_GPL(posix_acl_default_xattr_handler); int simple_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type) { int error; if (type == ACL_TYPE_ACCESS) { error = posix_acl_update_mode(mnt_userns, inode, &inode->i_mode, &acl); if (error) return error; } inode->i_ctime = current_time(inode); set_cached_acl(inode, type, acl); return 0; } int simple_acl_create(struct inode *dir, struct inode *inode) { struct posix_acl *default_acl, *acl; int error; error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); if (error) return error; set_cached_acl(inode, ACL_TYPE_DEFAULT, default_acl); set_cached_acl(inode, ACL_TYPE_ACCESS, acl); if (default_acl) posix_acl_release(default_acl); if (acl) posix_acl_release(acl); return 0; } |
| 742 741 740 740 20 20 20 18 20 17 20 15 17 12 203 203 203 203 203 934 94 887 888 888 1326 1324 1326 1326 720 722 720 721 1325 653 886 888 888 888 18 873 120 564 20 585 27 27 26 1 27 27 27 27 27 255 255 585 586 585 586 585 586 586 586 27 586 586 387 585 585 586 888 888 888 739 742 740 740 740 740 739 742 203 203 204 203 12 204 204 12 203 203 332 361 361 332 333 333 333 271 271 271 140 130 1937 1936 1937 1937 1936 504 504 504 741 98 741 742 741 741 742 1989 1988 1986 1986 1989 1986 1986 1989 564 564 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic address resolution entity * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * * Fixes: * Vitaly E. Lavrov releasing NULL neighbor in neigh_add. * Harald Welte Add neighbour cache statistics like rtstat */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/slab.h> #include <linux/kmemleak.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/socket.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/times.h> #include <net/net_namespace.h> #include <net/neighbour.h> #include <net/arp.h> #include <net/dst.h> #include <net/sock.h> #include <net/netevent.h> #include <net/netlink.h> #include <linux/rtnetlink.h> #include <linux/random.h> #include <linux/string.h> #include <linux/log2.h> #include <linux/inetdevice.h> #include <net/addrconf.h> #include <trace/events/neigh.h> #define NEIGH_DEBUG 1 #define neigh_dbg(level, fmt, ...) \ do { \ if (level <= NEIGH_DEBUG) \ pr_debug(fmt, ##__VA_ARGS__); \ } while (0) #define PNEIGH_HASHMASK 0xF static void neigh_timer_handler(struct timer_list *t); static void __neigh_notify(struct neighbour *n, int type, int flags, u32 pid); static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid); static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, struct net_device *dev); #ifdef CONFIG_PROC_FS static const struct seq_operations neigh_stat_seq_ops; #endif /* Neighbour hash table buckets are protected with rwlock tbl->lock. - All the scans/updates to hash buckets MUST be made under this lock. - NOTHING clever should be made under this lock: no callbacks to protocol backends, no attempts to send something to network. It will result in deadlocks, if backend/driver wants to use neighbour cache. - If the entry requires some non-trivial actions, increase its reference count and release table lock. Neighbour entries are protected: - with reference count. - with rwlock neigh->lock Reference count prevents destruction. neigh->lock mainly serializes ll address data and its validity state. However, the same lock is used to protect another entry fields: - timer - resolution queue Again, nothing clever shall be made under neigh->lock, the most complicated procedure, which we allow is dev->hard_header. It is supposed, that dev->hard_header is simplistic and does not make callbacks to neighbour tables. */ static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb) { kfree_skb(skb); return -ENETDOWN; } static void neigh_cleanup_and_release(struct neighbour *neigh) { trace_neigh_cleanup_and_release(neigh, 0); __neigh_notify(neigh, RTM_DELNEIGH, 0, 0); call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); neigh_release(neigh); } /* * It is random distribution in the interval (1/2)*base...(3/2)*base. * It corresponds to default IPv6 settings and is not overridable, * because it is really reasonable choice. */ unsigned long neigh_rand_reach_time(unsigned long base) { return base ? (prandom_u32() % base) + (base >> 1) : 0; } EXPORT_SYMBOL(neigh_rand_reach_time); static void neigh_mark_dead(struct neighbour *n) { n->dead = 1; if (!list_empty(&n->gc_list)) { list_del_init(&n->gc_list); atomic_dec(&n->tbl->gc_entries); } } static void neigh_update_gc_list(struct neighbour *n) { bool on_gc_list, exempt_from_gc; write_lock_bh(&n->tbl->lock); write_lock(&n->lock); if (n->dead) goto out; /* remove from the gc list if new state is permanent or if neighbor * is externally learned; otherwise entry should be on the gc list */ exempt_from_gc = n->nud_state & NUD_PERMANENT || n->flags & NTF_EXT_LEARNED; on_gc_list = !list_empty(&n->gc_list); if (exempt_from_gc && on_gc_list) { list_del_init(&n->gc_list); atomic_dec(&n->tbl->gc_entries); } else if (!exempt_from_gc && !on_gc_list) { /* add entries to the tail; cleaning removes from the front */ list_add_tail(&n->gc_list, &n->tbl->gc_list); atomic_inc(&n->tbl->gc_entries); } out: write_unlock(&n->lock); write_unlock_bh(&n->tbl->lock); } static bool neigh_update_ext_learned(struct neighbour *neigh, u32 flags, int *notify) { bool rc = false; u8 ndm_flags; if (!(flags & NEIGH_UPDATE_F_ADMIN)) return rc; ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) { if (ndm_flags & NTF_EXT_LEARNED) neigh->flags |= NTF_EXT_LEARNED; else neigh->flags &= ~NTF_EXT_LEARNED; rc = true; *notify = 1; } return rc; } static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np, struct neigh_table *tbl) { bool retval = false; write_lock(&n->lock); if (refcount_read(&n->refcnt) == 1) { struct neighbour *neigh; neigh = rcu_dereference_protected(n->next, lockdep_is_held(&tbl->lock)); rcu_assign_pointer(*np, neigh); neigh_mark_dead(n); retval = true; } write_unlock(&n->lock); if (retval) neigh_cleanup_and_release(n); return retval; } bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl) { struct neigh_hash_table *nht; void *pkey = ndel->primary_key; u32 hash_val; struct neighbour *n; struct neighbour __rcu **np; nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); hash_val = tbl->hash(pkey, ndel->dev, nht->hash_rnd); hash_val = hash_val >> (32 - nht->hash_shift); np = &nht->hash_buckets[hash_val]; while ((n = rcu_dereference_protected(*np, lockdep_is_held(&tbl->lock)))) { if (n == ndel) return neigh_del(n, np, tbl); np = &n->next; } return false; } static int neigh_forced_gc(struct neigh_table *tbl) { int max_clean = atomic_read(&tbl->gc_entries) - READ_ONCE(tbl->gc_thresh2); u64 tmax = ktime_get_ns() + NSEC_PER_MSEC; unsigned long tref = jiffies - 5 * HZ; struct neighbour *n, *tmp; int shrunk = 0; int loop = 0; NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs); write_lock_bh(&tbl->lock); list_for_each_entry_safe(n, tmp, &tbl->gc_list, gc_list) { if (refcount_read(&n->refcnt) == 1) { bool remove = false; write_lock(&n->lock); if ((n->nud_state == NUD_FAILED) || (n->nud_state == NUD_NOARP) || (tbl->is_multicast && tbl->is_multicast(n->primary_key)) || !time_in_range(n->updated, tref, jiffies)) remove = true; write_unlock(&n->lock); if (remove && neigh_remove_one(n, tbl)) shrunk++; if (shrunk >= max_clean) break; if (++loop == 16) { if (ktime_get_ns() > tmax) goto unlock; loop = 0; } } } WRITE_ONCE(tbl->last_flush, jiffies); unlock: write_unlock_bh(&tbl->lock); return shrunk; } static void neigh_add_timer(struct neighbour *n, unsigned long when) { /* Use safe distance from the jiffies - LONG_MAX point while timer * is running in DELAY/PROBE state but still show to user space * large times in the past. */ unsigned long mint = jiffies - (LONG_MAX - 86400 * HZ); neigh_hold(n); if (!time_in_range(n->confirmed, mint, jiffies)) n->confirmed = mint; if (time_before(n->used, n->confirmed)) n->used = n->confirmed; if (unlikely(mod_timer(&n->timer, when))) { printk("NEIGH: BUG, double timer add, state is %x\n", n->nud_state); dump_stack(); } } static int neigh_del_timer(struct neighbour *n) { if ((n->nud_state & NUD_IN_TIMER) && del_timer(&n->timer)) { neigh_release(n); return 1; } return 0; } static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) { struct sk_buff_head tmp; unsigned long flags; struct sk_buff *skb; skb_queue_head_init(&tmp); spin_lock_irqsave(&list->lock, flags); skb = skb_peek(list); while (skb != NULL) { struct sk_buff *skb_next = skb_peek_next(skb, list); if (net == NULL || net_eq(dev_net(skb->dev), net)) { __skb_unlink(skb, list); __skb_queue_tail(&tmp, skb); } skb = skb_next; } spin_unlock_irqrestore(&list->lock, flags); while ((skb = __skb_dequeue(&tmp))) { dev_put(skb->dev); kfree_skb(skb); } } static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev, bool skip_perm) { int i; struct neigh_hash_table *nht; nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); for (i = 0; i < (1 << nht->hash_shift); i++) { struct neighbour *n; struct neighbour __rcu **np = &nht->hash_buckets[i]; while ((n = rcu_dereference_protected(*np, lockdep_is_held(&tbl->lock))) != NULL) { if (dev && n->dev != dev) { np = &n->next; continue; } if (skip_perm && n->nud_state & NUD_PERMANENT) { np = &n->next; continue; } rcu_assign_pointer(*np, rcu_dereference_protected(n->next, lockdep_is_held(&tbl->lock))); write_lock(&n->lock); neigh_del_timer(n); neigh_mark_dead(n); if (refcount_read(&n->refcnt) != 1) { /* The most unpleasant situation. We must destroy neighbour entry, but someone still uses it. The destroy will be delayed until the last user releases us, but we must kill timers etc. and move it to safe state. */ __skb_queue_purge(&n->arp_queue); n->arp_queue_len_bytes = 0; n->output = neigh_blackhole; if (n->nud_state & NUD_VALID) n->nud_state = NUD_NOARP; else n->nud_state = NUD_NONE; neigh_dbg(2, "neigh %p is stray\n", n); } write_unlock(&n->lock); neigh_cleanup_and_release(n); } } } void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev) { write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, false); write_unlock_bh(&tbl->lock); } EXPORT_SYMBOL(neigh_changeaddr); static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, bool skip_perm) { write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); pneigh_ifdown_and_unlock(tbl, dev); pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL); if (skb_queue_empty_lockless(&tbl->proxy_queue)) del_timer_sync(&tbl->proxy_timer); return 0; } int neigh_carrier_down(struct neigh_table *tbl, struct net_device *dev) { __neigh_ifdown(tbl, dev, true); return 0; } EXPORT_SYMBOL(neigh_carrier_down); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) { __neigh_ifdown(tbl, dev, false); return 0; } EXPORT_SYMBOL(neigh_ifdown); static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device *dev, u8 flags, bool exempt_from_gc) { struct neighbour *n = NULL; unsigned long now = jiffies; int entries, gc_thresh3; if (exempt_from_gc) goto do_alloc; entries = atomic_inc_return(&tbl->gc_entries) - 1; gc_thresh3 = READ_ONCE(tbl->gc_thresh3); if (entries >= gc_thresh3 || (entries >= READ_ONCE(tbl->gc_thresh2) && time_after(now, READ_ONCE(tbl->last_flush) + 5 * HZ))) { if (!neigh_forced_gc(tbl) && entries >= gc_thresh3) { net_info_ratelimited("%s: neighbor table overflow!\n", tbl->id); NEIGH_CACHE_STAT_INC(tbl, table_fulls); goto out_entries; } } do_alloc: n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC); if (!n) goto out_entries; __skb_queue_head_init(&n->arp_queue); rwlock_init(&n->lock); seqlock_init(&n->ha_lock); n->updated = n->used = now; n->nud_state = NUD_NONE; n->output = neigh_blackhole; n->flags = flags; seqlock_init(&n->hh.hh_lock); n->parms = neigh_parms_clone(&tbl->parms); timer_setup(&n->timer, neigh_timer_handler, 0); NEIGH_CACHE_STAT_INC(tbl, allocs); n->tbl = tbl; refcount_set(&n->refcnt, 1); n->dead = 1; INIT_LIST_HEAD(&n->gc_list); atomic_inc(&tbl->entries); out: return n; out_entries: if (!exempt_from_gc) atomic_dec(&tbl->gc_entries); goto out; } static void neigh_get_hash_rnd(u32 *x) { *x = get_random_u32() | 1; } static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) { size_t size = (1 << shift) * sizeof(struct neighbour *); struct neigh_hash_table *ret; struct neighbour __rcu **buckets; int i; ret = kmalloc(sizeof(*ret), GFP_ATOMIC); if (!ret) return NULL; if (size <= PAGE_SIZE) { buckets = kzalloc(size, GFP_ATOMIC); } else { buckets = (struct neighbour __rcu **) __get_free_pages(GFP_ATOMIC | __GFP_ZERO, get_order(size)); kmemleak_alloc(buckets, size, 1, GFP_ATOMIC); } if (!buckets) { kfree(ret); return NULL; } ret->hash_buckets = buckets; ret->hash_shift = shift; for (i = 0; i < NEIGH_NUM_HASH_RND; i++) neigh_get_hash_rnd(&ret->hash_rnd[i]); return ret; } static void neigh_hash_free_rcu(struct rcu_head *head) { struct neigh_hash_table *nht = container_of(head, struct neigh_hash_table, rcu); size_t size = (1 << nht->hash_shift) * sizeof(struct neighbour *); struct neighbour __rcu **buckets = nht->hash_buckets; if (size <= PAGE_SIZE) { kfree(buckets); } else { kmemleak_free(buckets); free_pages((unsigned long)buckets, get_order(size)); } kfree(nht); } static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl, unsigned long new_shift) { unsigned int i, hash; struct neigh_hash_table *new_nht, *old_nht; NEIGH_CACHE_STAT_INC(tbl, hash_grows); old_nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); new_nht = neigh_hash_alloc(new_shift); if (!new_nht) return old_nht; for (i = 0; i < (1 << old_nht->hash_shift); i++) { struct neighbour *n, *next; for (n = rcu_dereference_protected(old_nht->hash_buckets[i], lockdep_is_held(&tbl->lock)); n != NULL; n = next) { hash = tbl->hash(n->primary_key, n->dev, new_nht->hash_rnd); hash >>= (32 - new_nht->hash_shift); next = rcu_dereference_protected(n->next, lockdep_is_held(&tbl->lock)); rcu_assign_pointer(n->next, rcu_dereference_protected( new_nht->hash_buckets[hash], lockdep_is_held(&tbl->lock))); rcu_assign_pointer(new_nht->hash_buckets[hash], n); } } rcu_assign_pointer(tbl->nht, new_nht); call_rcu(&old_nht->rcu, neigh_hash_free_rcu); return new_nht; } struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { struct neighbour *n; NEIGH_CACHE_STAT_INC(tbl, lookups); rcu_read_lock_bh(); n = __neigh_lookup_noref(tbl, pkey, dev); if (n) { if (!refcount_inc_not_zero(&n->refcnt)) n = NULL; NEIGH_CACHE_STAT_INC(tbl, hits); } rcu_read_unlock_bh(); return n; } EXPORT_SYMBOL(neigh_lookup); static struct neighbour * ___neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, u8 flags, bool exempt_from_gc, bool want_ref) { u32 hash_val, key_len = tbl->key_len; struct neighbour *n1, *rc, *n; struct neigh_hash_table *nht; int error; n = neigh_alloc(tbl, dev, flags, exempt_from_gc); trace_neigh_create(tbl, dev, pkey, n, exempt_from_gc); if (!n) { rc = ERR_PTR(-ENOBUFS); goto out; } memcpy(n->primary_key, pkey, key_len); n->dev = dev; dev_hold(dev); /* Protocol specific setup. */ if (tbl->constructor && (error = tbl->constructor(n)) < 0) { rc = ERR_PTR(error); goto out_neigh_release; } if (dev->netdev_ops->ndo_neigh_construct) { error = dev->netdev_ops->ndo_neigh_construct(dev, n); if (error < 0) { rc = ERR_PTR(error); goto out_neigh_release; } } /* Device specific setup. */ if (n->parms->neigh_setup && (error = n->parms->neigh_setup(n)) < 0) { rc = ERR_PTR(error); goto out_neigh_release; } n->confirmed = jiffies - (NEIGH_VAR(n->parms, BASE_REACHABLE_TIME) << 1); write_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); if (atomic_read(&tbl->entries) > (1 << nht->hash_shift)) nht = neigh_hash_grow(tbl, nht->hash_shift + 1); hash_val = tbl->hash(n->primary_key, dev, nht->hash_rnd) >> (32 - nht->hash_shift); if (n->parms->dead) { rc = ERR_PTR(-EINVAL); goto out_tbl_unlock; } for (n1 = rcu_dereference_protected(nht->hash_buckets[hash_val], lockdep_is_held(&tbl->lock)); n1 != NULL; n1 = rcu_dereference_protected(n1->next, lockdep_is_held(&tbl->lock))) { if (dev == n1->dev && !memcmp(n1->primary_key, n->primary_key, key_len)) { if (want_ref) neigh_hold(n1); rc = n1; goto out_tbl_unlock; } } n->dead = 0; if (!exempt_from_gc) list_add_tail(&n->gc_list, &n->tbl->gc_list); if (want_ref) neigh_hold(n); rcu_assign_pointer(n->next, rcu_dereference_protected(nht->hash_buckets[hash_val], lockdep_is_held(&tbl->lock))); rcu_assign_pointer(nht->hash_buckets[hash_val], n); write_unlock_bh(&tbl->lock); neigh_dbg(2, "neigh %p is created\n", n); rc = n; out: return rc; out_tbl_unlock: write_unlock_bh(&tbl->lock); out_neigh_release: if (!exempt_from_gc) atomic_dec(&tbl->gc_entries); neigh_release(n); goto out; } struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, bool want_ref) { return ___neigh_create(tbl, pkey, dev, 0, false, want_ref); } EXPORT_SYMBOL(__neigh_create); static u32 pneigh_hash(const void *pkey, unsigned int key_len) { u32 hash_val = *(u32 *)(pkey + key_len - 4); hash_val ^= (hash_val >> 16); hash_val ^= hash_val >> 8; hash_val ^= hash_val >> 4; hash_val &= PNEIGH_HASHMASK; return hash_val; } static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n, struct net *net, const void *pkey, unsigned int key_len, struct net_device *dev) { while (n) { if (!memcmp(n->key, pkey, key_len) && net_eq(pneigh_net(n), net) && (n->dev == dev || !n->dev)) return n; n = n->next; } return NULL; } struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *pkey, struct net_device *dev) { unsigned int key_len = tbl->key_len; u32 hash_val = pneigh_hash(pkey, key_len); return __pneigh_lookup_1(tbl->phash_buckets[hash_val], net, pkey, key_len, dev); } EXPORT_SYMBOL_GPL(__pneigh_lookup); struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *pkey, struct net_device *dev, int creat) { struct pneigh_entry *n; unsigned int key_len = tbl->key_len; u32 hash_val = pneigh_hash(pkey, key_len); read_lock_bh(&tbl->lock); n = __pneigh_lookup_1(tbl->phash_buckets[hash_val], net, pkey, key_len, dev); read_unlock_bh(&tbl->lock); if (n || !creat) goto out; ASSERT_RTNL(); n = kzalloc(sizeof(*n) + key_len, GFP_KERNEL); if (!n) goto out; write_pnet(&n->net, net); memcpy(n->key, pkey, key_len); n->dev = dev; dev_hold(dev); if (tbl->pconstructor && tbl->pconstructor(n)) { dev_put(dev); kfree(n); n = NULL; goto out; } write_lock_bh(&tbl->lock); n->next = tbl->phash_buckets[hash_val]; tbl->phash_buckets[hash_val] = n; write_unlock_bh(&tbl->lock); out: return n; } EXPORT_SYMBOL(pneigh_lookup); int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey, struct net_device *dev) { struct pneigh_entry *n, **np; unsigned int key_len = tbl->key_len; u32 hash_val = pneigh_hash(pkey, key_len); write_lock_bh(&tbl->lock); for (np = &tbl->phash_buckets[hash_val]; (n = *np) != NULL; np = &n->next) { if (!memcmp(n->key, pkey, key_len) && n->dev == dev && net_eq(pneigh_net(n), net)) { *np = n->next; write_unlock_bh(&tbl->lock); if (tbl->pdestructor) tbl->pdestructor(n); dev_put(n->dev); kfree(n); return 0; } } write_unlock_bh(&tbl->lock); return -ENOENT; } static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, struct net_device *dev) { struct pneigh_entry *n, **np, *freelist = NULL; u32 h; for (h = 0; h <= PNEIGH_HASHMASK; h++) { np = &tbl->phash_buckets[h]; while ((n = *np) != NULL) { if (!dev || n->dev == dev) { *np = n->next; n->next = freelist; freelist = n; continue; } np = &n->next; } } write_unlock_bh(&tbl->lock); while ((n = freelist)) { freelist = n->next; n->next = NULL; if (tbl->pdestructor) tbl->pdestructor(n); dev_put(n->dev); kfree(n); } return -ENOENT; } static void neigh_parms_destroy(struct neigh_parms *parms); static inline void neigh_parms_put(struct neigh_parms *parms) { if (refcount_dec_and_test(&parms->refcnt)) neigh_parms_destroy(parms); } /* * neighbour must already be out of the table; * */ void neigh_destroy(struct neighbour *neigh) { struct net_device *dev = neigh->dev; NEIGH_CACHE_STAT_INC(neigh->tbl, destroys); if (!neigh->dead) { pr_warn("Destroying alive neighbour %p\n", neigh); dump_stack(); return; } if (neigh_del_timer(neigh)) pr_warn("Impossible event\n"); write_lock_bh(&neigh->lock); __skb_queue_purge(&neigh->arp_queue); write_unlock_bh(&neigh->lock); neigh->arp_queue_len_bytes = 0; if (dev->netdev_ops->ndo_neigh_destroy) dev->netdev_ops->ndo_neigh_destroy(dev, neigh); dev_put(dev); neigh_parms_put(neigh->parms); neigh_dbg(2, "neigh %p is destroyed\n", neigh); atomic_dec(&neigh->tbl->entries); kfree_rcu(neigh, rcu); } EXPORT_SYMBOL(neigh_destroy); /* Neighbour state is suspicious; disable fast path. Called with write_locked neigh. */ static void neigh_suspect(struct neighbour *neigh) { neigh_dbg(2, "neigh %p is suspected\n", neigh); neigh->output = neigh->ops->output; } /* Neighbour state is OK; enable fast path. Called with write_locked neigh. */ static void neigh_connect(struct neighbour *neigh) { neigh_dbg(2, "neigh %p is connected\n", neigh); neigh->output = neigh->ops->connected_output; } static void neigh_periodic_work(struct work_struct *work) { struct neigh_table *tbl = container_of(work, struct neigh_table, gc_work.work); struct neighbour *n; struct neighbour __rcu **np; unsigned int i; struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs); write_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); /* * periodically recompute ReachableTime from random function */ if (time_after(jiffies, tbl->last_rand + 300 * HZ)) { struct neigh_parms *p; WRITE_ONCE(tbl->last_rand, jiffies); list_for_each_entry(p, &tbl->parms_list, list) p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } if (atomic_read(&tbl->entries) < READ_ONCE(tbl->gc_thresh1)) goto out; for (i = 0 ; i < (1 << nht->hash_shift); i++) { np = &nht->hash_buckets[i]; while ((n = rcu_dereference_protected(*np, lockdep_is_held(&tbl->lock))) != NULL) { unsigned int state; write_lock(&n->lock); state = n->nud_state; if ((state & (NUD_PERMANENT | NUD_IN_TIMER)) || (n->flags & NTF_EXT_LEARNED)) { write_unlock(&n->lock); goto next_elt; } if (time_before(n->used, n->confirmed) && time_is_before_eq_jiffies(n->confirmed)) n->used = n->confirmed; if (refcount_read(&n->refcnt) == 1 && (state == NUD_FAILED || !time_in_range_open(jiffies, n->used, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { rcu_assign_pointer(*np, rcu_dereference_protected(n->next, lockdep_is_held(&tbl->lock))); neigh_mark_dead(n); write_unlock(&n->lock); neigh_cleanup_and_release(n); continue; } write_unlock(&n->lock); next_elt: np = &n->next; } /* * It's fine to release lock here, even if hash table * grows while we are preempted. */ write_unlock_bh(&tbl->lock); cond_resched(); write_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); } out: /* Cycle through all hash buckets every BASE_REACHABLE_TIME/2 ticks. * ARP entry timeouts range from 1/2 BASE_REACHABLE_TIME to 3/2 * BASE_REACHABLE_TIME. */ queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME) >> 1); write_unlock_bh(&tbl->lock); } static __inline__ int neigh_max_probes(struct neighbour *n) { struct neigh_parms *p = n->parms; return NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) + (n->nud_state & NUD_PROBE ? NEIGH_VAR(p, MCAST_REPROBES) : NEIGH_VAR(p, MCAST_PROBES)); } static void neigh_invalidate(struct neighbour *neigh) __releases(neigh->lock) __acquires(neigh->lock) { struct sk_buff *skb; NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed); neigh_dbg(2, "neigh %p is failed\n", neigh); neigh->updated = jiffies; /* It is very thin place. report_unreachable is very complicated routine. Particularly, it can hit the same neighbour entry! So that, we try to be accurate and avoid dead loop. --ANK */ while (neigh->nud_state == NUD_FAILED && (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { write_unlock(&neigh->lock); neigh->ops->error_report(neigh, skb); write_lock(&neigh->lock); } __skb_queue_purge(&neigh->arp_queue); neigh->arp_queue_len_bytes = 0; } static void neigh_probe(struct neighbour *neigh) __releases(neigh->lock) { struct sk_buff *skb = skb_peek_tail(&neigh->arp_queue); /* keep skb alive even if arp_queue overflows */ if (skb) skb = skb_clone(skb, GFP_ATOMIC); write_unlock(&neigh->lock); if (neigh->ops->solicit) neigh->ops->solicit(neigh, skb); atomic_inc(&neigh->probes); consume_skb(skb); } /* Called when a timer expires for a neighbour entry. */ static void neigh_timer_handler(struct timer_list *t) { unsigned long now, next; struct neighbour *neigh = from_timer(neigh, t, timer); unsigned int state; int notify = 0; write_lock(&neigh->lock); state = neigh->nud_state; now = jiffies; next = now + HZ; if (!(state & NUD_IN_TIMER)) goto out; if (state & NUD_REACHABLE) { if (time_before_eq(now, neigh->confirmed + neigh->parms->reachable_time)) { neigh_dbg(2, "neigh %p is still alive\n", neigh); next = neigh->confirmed + neigh->parms->reachable_time; } else if (time_before_eq(now, neigh->used + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; neigh_suspect(neigh); next = now + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME); } else { neigh_dbg(2, "neigh %p is suspected\n", neigh); neigh->nud_state = NUD_STALE; neigh->updated = jiffies; neigh_suspect(neigh); notify = 1; } } else if (state & NUD_DELAY) { if (time_before_eq(now, neigh->confirmed + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { neigh_dbg(2, "neigh %p is now reachable\n", neigh); neigh->nud_state = NUD_REACHABLE; neigh->updated = jiffies; neigh_connect(neigh); notify = 1; next = neigh->confirmed + neigh->parms->reachable_time; } else { neigh_dbg(2, "neigh %p is probed\n", neigh); neigh->nud_state = NUD_PROBE; neigh->updated = jiffies; atomic_set(&neigh->probes, 0); notify = 1; next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), HZ/100); } } else { /* NUD_PROBE|NUD_INCOMPLETE */ next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), HZ/100); } if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) && atomic_read(&neigh->probes) >= neigh_max_probes(neigh)) { neigh->nud_state = NUD_FAILED; notify = 1; neigh_invalidate(neigh); goto out; } if (neigh->nud_state & NUD_IN_TIMER) { if (time_before(next, jiffies + HZ/100)) next = jiffies + HZ/100; if (!mod_timer(&neigh->timer, next)) neigh_hold(neigh); } if (neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) { neigh_probe(neigh); } else { out: write_unlock(&neigh->lock); } if (notify) neigh_update_notify(neigh, 0); trace_neigh_timer_handler(neigh, 0); neigh_release(neigh); } int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { int rc; bool immediate_probe = false; write_lock_bh(&neigh->lock); rc = 0; if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE)) goto out_unlock_bh; if (neigh->dead) goto out_dead; if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) { if (NEIGH_VAR(neigh->parms, MCAST_PROBES) + NEIGH_VAR(neigh->parms, APP_PROBES)) { unsigned long next, now = jiffies; atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES)); neigh_del_timer(neigh); neigh->nud_state = NUD_INCOMPLETE; neigh->updated = now; next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), HZ/100); neigh_add_timer(neigh, next); immediate_probe = true; } else { neigh->nud_state = NUD_FAILED; neigh->updated = jiffies; write_unlock_bh(&neigh->lock); kfree_skb(skb); return 1; } } else if (neigh->nud_state & NUD_STALE) { neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh_del_timer(neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; neigh_add_timer(neigh, jiffies + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME)); } if (neigh->nud_state == NUD_INCOMPLETE) { if (skb) { while (neigh->arp_queue_len_bytes + skb->truesize > NEIGH_VAR(neigh->parms, QUEUE_LEN_BYTES)) { struct sk_buff *buff; buff = __skb_dequeue(&neigh->arp_queue); if (!buff) break; neigh->arp_queue_len_bytes -= buff->truesize; kfree_skb(buff); NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards); } skb_dst_force(skb); __skb_queue_tail(&neigh->arp_queue, skb); neigh->arp_queue_len_bytes += skb->truesize; } rc = 1; } out_unlock_bh: if (immediate_probe) neigh_probe(neigh); else write_unlock(&neigh->lock); local_bh_enable(); trace_neigh_event_send_done(neigh, rc); return rc; out_dead: if (neigh->nud_state & NUD_STALE) goto out_unlock_bh; write_unlock_bh(&neigh->lock); kfree_skb(skb); trace_neigh_event_send_dead(neigh, 1); return 1; } EXPORT_SYMBOL(__neigh_event_send); static void neigh_update_hhs(struct neighbour *neigh) { struct hh_cache *hh; void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *) = NULL; if (neigh->dev->header_ops) update = neigh->dev->header_ops->cache_update; if (update) { hh = &neigh->hh; if (READ_ONCE(hh->hh_len)) { write_seqlock_bh(&hh->hh_lock); update(hh, neigh->dev, neigh->ha); write_sequnlock_bh(&hh->hh_lock); } } } /* Generic update routine. -- lladdr is new lladdr or NULL, if it is not supplied. -- new is new state. -- flags NEIGH_UPDATE_F_OVERRIDE allows to override existing lladdr, if it is different. NEIGH_UPDATE_F_WEAK_OVERRIDE will suspect existing "connected" lladdr instead of overriding it if it is different. NEIGH_UPDATE_F_ADMIN means that the change is administrative. NEIGH_UPDATE_F_USE means that the entry is user triggered. NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing NTF_ROUTER flag. NEIGH_UPDATE_F_ISROUTER indicates if the neighbour is known as a router. Caller MUST hold reference count on the entry. */ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid, struct netlink_ext_ack *extack) { bool ext_learn_change = false; u8 old; int err; int notify = 0; struct net_device *dev; int update_isrouter = 0; trace_neigh_update(neigh, lladdr, new, flags, nlmsg_pid); write_lock_bh(&neigh->lock); dev = neigh->dev; old = neigh->nud_state; err = -EPERM; if (neigh->dead) { NL_SET_ERR_MSG(extack, "Neighbor entry is now dead"); new = old; goto out; } if (!(flags & NEIGH_UPDATE_F_ADMIN) && (old & (NUD_NOARP | NUD_PERMANENT))) goto out; ext_learn_change = neigh_update_ext_learned(neigh, flags, ¬ify); if (flags & NEIGH_UPDATE_F_USE) { new = old & ~NUD_PERMANENT; neigh->nud_state = new; err = 0; goto out; } if (!(new & NUD_VALID)) { neigh_del_timer(neigh); if (old & NUD_CONNECTED) neigh_suspect(neigh); neigh->nud_state = new; err = 0; notify = old & NUD_VALID; if ((old & (NUD_INCOMPLETE | NUD_PROBE)) && (new & NUD_FAILED)) { neigh_invalidate(neigh); notify = 1; } goto out; } /* Compare new lladdr with cached one */ if (!dev->addr_len) { /* First case: device needs no address. */ lladdr = neigh->ha; } else if (lladdr) { /* The second case: if something is already cached and a new address is proposed: - compare new & old - if they are different, check override flag */ if ((old & NUD_VALID) && !memcmp(lladdr, neigh->ha, dev->addr_len)) lladdr = neigh->ha; } else { /* No address is supplied; if we know something, use it, otherwise discard the request. */ err = -EINVAL; if (!(old & NUD_VALID)) { NL_SET_ERR_MSG(extack, "No link layer address given"); goto out; } lladdr = neigh->ha; } /* Update confirmed timestamp for neighbour entry after we * received ARP packet even if it doesn't change IP to MAC binding. */ if (new & NUD_CONNECTED) neigh->confirmed = jiffies; /* If entry was valid and address is not changed, do not change entry state, if new one is STALE. */ err = 0; update_isrouter = flags & NEIGH_UPDATE_F_OVERRIDE_ISROUTER; if (old & NUD_VALID) { if (lladdr != neigh->ha && !(flags & NEIGH_UPDATE_F_OVERRIDE)) { update_isrouter = 0; if ((flags & NEIGH_UPDATE_F_WEAK_OVERRIDE) && (old & NUD_CONNECTED)) { lladdr = neigh->ha; new = NUD_STALE; } else goto out; } else { if (lladdr == neigh->ha && new == NUD_STALE && !(flags & NEIGH_UPDATE_F_ADMIN)) new = old; } } /* Update timestamp only once we know we will make a change to the * neighbour entry. Otherwise we risk to move the locktime window with * noop updates and ignore relevant ARP updates. */ if (new != old || lladdr != neigh->ha) neigh->updated = jiffies; if (new != old) { neigh_del_timer(neigh); if (new & NUD_PROBE) atomic_set(&neigh->probes, 0); if (new & NUD_IN_TIMER) neigh_add_timer(neigh, (jiffies + ((new & NUD_REACHABLE) ? neigh->parms->reachable_time : 0))); neigh->nud_state = new; notify = 1; } if (lladdr != neigh->ha) { write_seqlock(&neigh->ha_lock); memcpy(&neigh->ha, lladdr, dev->addr_len); write_sequnlock(&neigh->ha_lock); neigh_update_hhs(neigh); if (!(new & NUD_CONNECTED)) neigh->confirmed = jiffies - (NEIGH_VAR(neigh->parms, BASE_REACHABLE_TIME) << 1); notify = 1; } if (new == old) goto out; if (new & NUD_CONNECTED) neigh_connect(neigh); else neigh_suspect(neigh); if (!(old & NUD_VALID)) { struct sk_buff *skb; /* Again: avoid dead loop if something went wrong */ while (neigh->nud_state & NUD_VALID && (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { struct dst_entry *dst = skb_dst(skb); struct neighbour *n2, *n1 = neigh; write_unlock_bh(&neigh->lock); rcu_read_lock(); /* Why not just use 'neigh' as-is? The problem is that * things such as shaper, eql, and sch_teql can end up * using alternative, different, neigh objects to output * the packet in the output path. So what we need to do * here is re-lookup the top-level neigh in the path so * we can reinject the packet there. */ n2 = NULL; if (dst && dst->obsolete != DST_OBSOLETE_DEAD) { n2 = dst_neigh_lookup_skb(dst, skb); if (n2) n1 = n2; } n1->output(n1, skb); if (n2) neigh_release(n2); rcu_read_unlock(); write_lock_bh(&neigh->lock); } __skb_queue_purge(&neigh->arp_queue); neigh->arp_queue_len_bytes = 0; } out: if (update_isrouter) neigh_update_is_router(neigh, flags, ¬ify); write_unlock_bh(&neigh->lock); if (((new ^ old) & NUD_PERMANENT) || ext_learn_change) neigh_update_gc_list(neigh); if (notify) neigh_update_notify(neigh, nlmsg_pid); trace_neigh_update_done(neigh, err); return err; } int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid) { return __neigh_update(neigh, lladdr, new, flags, nlmsg_pid, NULL); } EXPORT_SYMBOL(neigh_update); /* Update the neigh to listen temporarily for probe responses, even if it is * in a NUD_FAILED state. The caller has to hold neigh->lock for writing. */ void __neigh_set_probe_once(struct neighbour *neigh) { if (neigh->dead) return; neigh->updated = jiffies; if (!(neigh->nud_state & NUD_FAILED)) return; neigh->nud_state = NUD_INCOMPLETE; atomic_set(&neigh->probes, neigh_max_probes(neigh)); neigh_add_timer(neigh, jiffies + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), HZ/100)); } EXPORT_SYMBOL(__neigh_set_probe_once); struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, struct net_device *dev) { struct neighbour *neigh = __neigh_lookup(tbl, saddr, dev, lladdr || !dev->addr_len); if (neigh) neigh_update(neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_OVERRIDE, 0); return neigh; } EXPORT_SYMBOL(neigh_event_ns); /* called with read_lock_bh(&n->lock); */ static void neigh_hh_init(struct neighbour *n) { struct net_device *dev = n->dev; __be16 prot = n->tbl->protocol; struct hh_cache *hh = &n->hh; write_lock_bh(&n->lock); /* Only one thread can come in here and initialize the * hh_cache entry. */ if (!hh->hh_len) dev->header_ops->cache(n, hh, prot); write_unlock_bh(&n->lock); } /* Slow and careful. */ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb) { int rc = 0; if (!neigh_event_send(neigh, skb)) { int err; struct net_device *dev = neigh->dev; unsigned int seq; if (dev->header_ops->cache && !READ_ONCE(neigh->hh.hh_len)) neigh_hh_init(neigh); do { __skb_pull(skb, skb_network_offset(skb)); seq = read_seqbegin(&neigh->ha_lock); err = dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, NULL, skb->len); } while (read_seqretry(&neigh->ha_lock, seq)); if (err >= 0) rc = dev_queue_xmit(skb); else goto out_kfree_skb; } out: return rc; out_kfree_skb: rc = -EINVAL; kfree_skb(skb); goto out; } EXPORT_SYMBOL(neigh_resolve_output); /* As fast as possible without hh cache */ int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb) { struct net_device *dev = neigh->dev; unsigned int seq; int err; do { __skb_pull(skb, skb_network_offset(skb)); seq = read_seqbegin(&neigh->ha_lock); err = dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, NULL, skb->len); } while (read_seqretry(&neigh->ha_lock, seq)); if (err >= 0) err = dev_queue_xmit(skb); else { err = -EINVAL; kfree_skb(skb); } return err; } EXPORT_SYMBOL(neigh_connected_output); int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb) { return dev_queue_xmit(skb); } EXPORT_SYMBOL(neigh_direct_output); static void neigh_proxy_process(struct timer_list *t) { struct neigh_table *tbl = from_timer(tbl, t, proxy_timer); long sched_next = 0; unsigned long now = jiffies; struct sk_buff *skb, *n; spin_lock(&tbl->proxy_queue.lock); skb_queue_walk_safe(&tbl->proxy_queue, skb, n) { long tdif = NEIGH_CB(skb)->sched_next - now; if (tdif <= 0) { struct net_device *dev = skb->dev; __skb_unlink(skb, &tbl->proxy_queue); if (tbl->proxy_redo && netif_running(dev)) { rcu_read_lock(); tbl->proxy_redo(skb); rcu_read_unlock(); } else { kfree_skb(skb); } dev_put(dev); } else if (!sched_next || tdif < sched_next) sched_next = tdif; } del_timer(&tbl->proxy_timer); if (sched_next) mod_timer(&tbl->proxy_timer, jiffies + sched_next); spin_unlock(&tbl->proxy_queue.lock); } void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb) { unsigned long sched_next = jiffies + prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY)); if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) { kfree_skb(skb); return; } NEIGH_CB(skb)->sched_next = sched_next; NEIGH_CB(skb)->flags |= LOCALLY_ENQUEUED; spin_lock(&tbl->proxy_queue.lock); if (del_timer(&tbl->proxy_timer)) { if (time_before(tbl->proxy_timer.expires, sched_next)) sched_next = tbl->proxy_timer.expires; } skb_dst_drop(skb); dev_hold(skb->dev); __skb_queue_tail(&tbl->proxy_queue, skb); mod_timer(&tbl->proxy_timer, sched_next); spin_unlock(&tbl->proxy_queue.lock); } EXPORT_SYMBOL(pneigh_enqueue); static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl, struct net *net, int ifindex) { struct neigh_parms *p; list_for_each_entry(p, &tbl->parms_list, list) { if ((p->dev && p->dev->ifindex == ifindex && net_eq(neigh_parms_net(p), net)) || (!p->dev && !ifindex && net_eq(net, &init_net))) return p; } return NULL; } struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct neigh_table *tbl) { struct neigh_parms *p; struct net *net = dev_net(dev); const struct net_device_ops *ops = dev->netdev_ops; p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL); if (p) { p->tbl = tbl; refcount_set(&p->refcnt, 1); p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); dev_hold(dev); p->dev = dev; write_pnet(&p->net, net); p->sysctl_table = NULL; if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { dev_put(dev); kfree(p); return NULL; } write_lock_bh(&tbl->lock); list_add(&p->list, &tbl->parms.list); write_unlock_bh(&tbl->lock); neigh_parms_data_state_cleanall(p); } return p; } EXPORT_SYMBOL(neigh_parms_alloc); static void neigh_rcu_free_parms(struct rcu_head *head) { struct neigh_parms *parms = container_of(head, struct neigh_parms, rcu_head); neigh_parms_put(parms); } void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms) { if (!parms || parms == &tbl->parms) return; write_lock_bh(&tbl->lock); list_del(&parms->list); parms->dead = 1; write_unlock_bh(&tbl->lock); dev_put(parms->dev); call_rcu(&parms->rcu_head, neigh_rcu_free_parms); } EXPORT_SYMBOL(neigh_parms_release); static void neigh_parms_destroy(struct neigh_parms *parms) { kfree(parms); } static struct lock_class_key neigh_table_proxy_queue_class; static struct neigh_table *neigh_tables[NEIGH_NR_TABLES] __read_mostly; void neigh_table_init(int index, struct neigh_table *tbl) { unsigned long now = jiffies; unsigned long phsize; INIT_LIST_HEAD(&tbl->parms_list); INIT_LIST_HEAD(&tbl->gc_list); list_add(&tbl->parms.list, &tbl->parms_list); write_pnet(&tbl->parms.net, &init_net); refcount_set(&tbl->parms.refcnt, 1); tbl->parms.reachable_time = neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME)); tbl->stats = alloc_percpu(struct neigh_statistics); if (!tbl->stats) panic("cannot create neighbour cache statistics"); #ifdef CONFIG_PROC_FS if (!proc_create_seq_data(tbl->id, 0, init_net.proc_net_stat, &neigh_stat_seq_ops, tbl)) panic("cannot create neighbour proc dir entry"); #endif RCU_INIT_POINTER(tbl->nht, neigh_hash_alloc(3)); phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *); tbl->phash_buckets = kzalloc(phsize, GFP_KERNEL); if (!tbl->nht || !tbl->phash_buckets) panic("cannot allocate neighbour cache hashes"); if (!tbl->entry_size) tbl->entry_size = ALIGN(offsetof(struct neighbour, primary_key) + tbl->key_len, NEIGH_PRIV_ALIGN); else WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); rwlock_init(&tbl->lock); INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, tbl->parms.reachable_time); timer_setup(&tbl->proxy_timer, neigh_proxy_process, 0); skb_queue_head_init_class(&tbl->proxy_queue, &neigh_table_proxy_queue_class); tbl->last_flush = now; tbl->last_rand = now + tbl->parms.reachable_time * 20; neigh_tables[index] = tbl; } EXPORT_SYMBOL(neigh_table_init); int neigh_table_clear(int index, struct neigh_table *tbl) { neigh_tables[index] = NULL; /* It is not clean... Fix it to unload IPv6 module safely */ cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue, NULL); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) pr_crit("neighbour leakage\n"); call_rcu(&rcu_dereference_protected(tbl->nht, 1)->rcu, neigh_hash_free_rcu); tbl->nht = NULL; kfree(tbl->phash_buckets); tbl->phash_buckets = NULL; remove_proc_entry(tbl->id, init_net.proc_net_stat); free_percpu(tbl->stats); tbl->stats = NULL; return 0; } EXPORT_SYMBOL(neigh_table_clear); static struct neigh_table *neigh_find_table(int family) { struct neigh_table *tbl = NULL; switch (family) { case AF_INET: tbl = neigh_tables[NEIGH_ARP_TABLE]; break; case AF_INET6: tbl = neigh_tables[NEIGH_ND_TABLE]; break; } return tbl; } const struct nla_policy nda_policy[NDA_MAX+1] = { [NDA_UNSPEC] = { .strict_start_type = NDA_NH_ID }, [NDA_DST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [NDA_LLADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [NDA_CACHEINFO] = { .len = sizeof(struct nda_cacheinfo) }, [NDA_PROBES] = { .type = NLA_U32 }, [NDA_VLAN] = { .type = NLA_U16 }, [NDA_PORT] = { .type = NLA_U16 }, [NDA_VNI] = { .type = NLA_U32 }, [NDA_IFINDEX] = { .type = NLA_U32 }, [NDA_MASTER] = { .type = NLA_U32 }, [NDA_PROTOCOL] = { .type = NLA_U8 }, [NDA_NH_ID] = { .type = NLA_U32 }, [NDA_FDB_EXT_ATTRS] = { .type = NLA_NESTED }, }; static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *dst_attr; struct neigh_table *tbl; struct neighbour *neigh; struct net_device *dev = NULL; int err = -EINVAL; ASSERT_RTNL(); if (nlmsg_len(nlh) < sizeof(*ndm)) goto out; dst_attr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_DST); if (!dst_attr) { NL_SET_ERR_MSG(extack, "Network address not specified"); goto out; } ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex) { dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { err = -ENODEV; goto out; } } tbl = neigh_find_table(ndm->ndm_family); if (tbl == NULL) return -EAFNOSUPPORT; if (nla_len(dst_attr) < (int)tbl->key_len) { NL_SET_ERR_MSG(extack, "Invalid network address"); goto out; } if (ndm->ndm_flags & NTF_PROXY) { err = pneigh_delete(tbl, net, nla_data(dst_attr), dev); goto out; } if (dev == NULL) goto out; neigh = neigh_lookup(tbl, nla_data(dst_attr), dev); if (neigh == NULL) { err = -ENOENT; goto out; } err = __neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN, NETLINK_CB(skb).portid, extack); write_lock_bh(&tbl->lock); neigh_release(neigh); neigh_remove_one(neigh, tbl); write_unlock_bh(&tbl->lock); out: return err; } static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_OVERRIDE_ISROUTER; struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; struct neigh_table *tbl; struct net_device *dev = NULL; struct neighbour *neigh; void *dst, *lladdr; u8 protocol = 0; int err; ASSERT_RTNL(); err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX, nda_policy, extack); if (err < 0) goto out; err = -EINVAL; if (!tb[NDA_DST]) { NL_SET_ERR_MSG(extack, "Network address not specified"); goto out; } ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex) { dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { err = -ENODEV; goto out; } if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len) { NL_SET_ERR_MSG(extack, "Invalid link address"); goto out; } } tbl = neigh_find_table(ndm->ndm_family); if (tbl == NULL) return -EAFNOSUPPORT; if (nla_len(tb[NDA_DST]) < (int)tbl->key_len) { NL_SET_ERR_MSG(extack, "Invalid network address"); goto out; } dst = nla_data(tb[NDA_DST]); lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL; if (tb[NDA_PROTOCOL]) protocol = nla_get_u8(tb[NDA_PROTOCOL]); if (ndm->ndm_flags & NTF_PROXY) { struct pneigh_entry *pn; err = -ENOBUFS; pn = pneigh_lookup(tbl, net, dst, dev, 1); if (pn) { pn->flags = ndm->ndm_flags; if (protocol) pn->protocol = protocol; err = 0; } goto out; } if (!dev) { NL_SET_ERR_MSG(extack, "Device not specified"); goto out; } if (tbl->allow_add && !tbl->allow_add(dev, extack)) { err = -EINVAL; goto out; } neigh = neigh_lookup(tbl, dst, dev); if (neigh == NULL) { bool exempt_from_gc; if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { err = -ENOENT; goto out; } exempt_from_gc = ndm->ndm_state & NUD_PERMANENT || ndm->ndm_flags & NTF_EXT_LEARNED; neigh = ___neigh_create(tbl, dst, dev, ndm->ndm_flags & NTF_EXT_LEARNED, exempt_from_gc, true); if (IS_ERR(neigh)) { err = PTR_ERR(neigh); goto out; } } else { if (nlh->nlmsg_flags & NLM_F_EXCL) { err = -EEXIST; neigh_release(neigh); goto out; } if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) flags &= ~(NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_OVERRIDE_ISROUTER); } if (protocol) neigh->protocol = protocol; if (ndm->ndm_flags & NTF_EXT_LEARNED) flags |= NEIGH_UPDATE_F_EXT_LEARNED; if (ndm->ndm_flags & NTF_ROUTER) flags |= NEIGH_UPDATE_F_ISROUTER; if (ndm->ndm_flags & NTF_USE) flags |= NEIGH_UPDATE_F_USE; err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, NETLINK_CB(skb).portid, extack); if (!err && ndm->ndm_flags & NTF_USE) { neigh_event_send(neigh, NULL); err = 0; } neigh_release(neigh); out: return err; } static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, NDTA_PARMS); if (nest == NULL) return -ENOBUFS; if ((parms->dev && nla_put_u32(skb, NDTPA_IFINDEX, parms->dev->ifindex)) || nla_put_u32(skb, NDTPA_REFCNT, refcount_read(&parms->refcnt)) || nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, NEIGH_VAR(parms, QUEUE_LEN_BYTES)) || /* approximative value for deprecated QUEUE_LEN (in packets) */ nla_put_u32(skb, NDTPA_QUEUE_LEN, NEIGH_VAR(parms, QUEUE_LEN_BYTES) / SKB_TRUESIZE(ETH_FRAME_LEN)) || nla_put_u32(skb, NDTPA_PROXY_QLEN, NEIGH_VAR(parms, PROXY_QLEN)) || nla_put_u32(skb, NDTPA_APP_PROBES, NEIGH_VAR(parms, APP_PROBES)) || nla_put_u32(skb, NDTPA_UCAST_PROBES, NEIGH_VAR(parms, UCAST_PROBES)) || nla_put_u32(skb, NDTPA_MCAST_PROBES, NEIGH_VAR(parms, MCAST_PROBES)) || nla_put_u32(skb, NDTPA_MCAST_REPROBES, NEIGH_VAR(parms, MCAST_REPROBES)) || nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time, NDTPA_PAD) || nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME, NEIGH_VAR(parms, BASE_REACHABLE_TIME), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_GC_STALETIME, NEIGH_VAR(parms, GC_STALETIME), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_DELAY_PROBE_TIME, NEIGH_VAR(parms, DELAY_PROBE_TIME), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_RETRANS_TIME, NEIGH_VAR(parms, RETRANS_TIME), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_ANYCAST_DELAY, NEIGH_VAR(parms, ANYCAST_DELAY), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_PROXY_DELAY, NEIGH_VAR(parms, PROXY_DELAY), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_LOCKTIME, NEIGH_VAR(parms, LOCKTIME), NDTPA_PAD)) goto nla_put_failure; return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, u32 pid, u32 seq, int type, int flags) { struct nlmsghdr *nlh; struct ndtmsg *ndtmsg; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags); if (nlh == NULL) return -EMSGSIZE; ndtmsg = nlmsg_data(nlh); read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; if (nla_put_string(skb, NDTA_NAME, tbl->id) || nla_put_msecs(skb, NDTA_GC_INTERVAL, READ_ONCE(tbl->gc_interval), NDTA_PAD) || nla_put_u32(skb, NDTA_THRESH1, READ_ONCE(tbl->gc_thresh1)) || nla_put_u32(skb, NDTA_THRESH2, READ_ONCE(tbl->gc_thresh2)) || nla_put_u32(skb, NDTA_THRESH3, READ_ONCE(tbl->gc_thresh3))) goto nla_put_failure; { unsigned long now = jiffies; long flush_delta = now - READ_ONCE(tbl->last_flush); long rand_delta = now - READ_ONCE(tbl->last_rand); struct neigh_hash_table *nht; struct ndt_config ndc = { .ndtc_key_len = tbl->key_len, .ndtc_entry_size = tbl->entry_size, .ndtc_entries = atomic_read(&tbl->entries), .ndtc_last_flush = jiffies_to_msecs(flush_delta), .ndtc_last_rand = jiffies_to_msecs(rand_delta), .ndtc_proxy_qlen = READ_ONCE(tbl->proxy_queue.qlen), }; rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); ndc.ndtc_hash_rnd = nht->hash_rnd[0]; ndc.ndtc_hash_mask = ((1 << nht->hash_shift) - 1); rcu_read_unlock_bh(); if (nla_put(skb, NDTA_CONFIG, sizeof(ndc), &ndc)) goto nla_put_failure; } { int cpu; struct ndt_stats ndst; memset(&ndst, 0, sizeof(ndst)); for_each_possible_cpu(cpu) { struct neigh_statistics *st; st = per_cpu_ptr(tbl->stats, cpu); ndst.ndts_allocs += READ_ONCE(st->allocs); ndst.ndts_destroys += READ_ONCE(st->destroys); ndst.ndts_hash_grows += READ_ONCE(st->hash_grows); ndst.ndts_res_failed += READ_ONCE(st->res_failed); ndst.ndts_lookups += READ_ONCE(st->lookups); ndst.ndts_hits += READ_ONCE(st->hits); ndst.ndts_rcv_probes_mcast += READ_ONCE(st->rcv_probes_mcast); ndst.ndts_rcv_probes_ucast += READ_ONCE(st->rcv_probes_ucast); ndst.ndts_periodic_gc_runs += READ_ONCE(st->periodic_gc_runs); ndst.ndts_forced_gc_runs += READ_ONCE(st->forced_gc_runs); ndst.ndts_table_fulls += READ_ONCE(st->table_fulls); } if (nla_put_64bit(skb, NDTA_STATS, sizeof(ndst), &ndst, NDTA_PAD)) goto nla_put_failure; } BUG_ON(tbl->parms.dev); if (neightbl_fill_parms(skb, &tbl->parms) < 0) goto nla_put_failure; read_unlock_bh(&tbl->lock); nlmsg_end(skb, nlh); return 0; nla_put_failure: read_unlock_bh(&tbl->lock); nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int neightbl_fill_param_info(struct sk_buff *skb, struct neigh_table *tbl, struct neigh_parms *parms, u32 pid, u32 seq, int type, unsigned int flags) { struct ndtmsg *ndtmsg; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags); if (nlh == NULL) return -EMSGSIZE; ndtmsg = nlmsg_data(nlh); read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; if (nla_put_string(skb, NDTA_NAME, tbl->id) < 0 || neightbl_fill_parms(skb, parms) < 0) goto errout; read_unlock_bh(&tbl->lock); nlmsg_end(skb, nlh); return 0; errout: read_unlock_bh(&tbl->lock); nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static const struct nla_policy nl_neightbl_policy[NDTA_MAX+1] = { [NDTA_NAME] = { .type = NLA_STRING }, [NDTA_THRESH1] = { .type = NLA_U32 }, [NDTA_THRESH2] = { .type = NLA_U32 }, [NDTA_THRESH3] = { .type = NLA_U32 }, [NDTA_GC_INTERVAL] = { .type = NLA_U64 }, [NDTA_PARMS] = { .type = NLA_NESTED }, }; static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = { [NDTPA_IFINDEX] = { .type = NLA_U32 }, [NDTPA_QUEUE_LEN] = { .type = NLA_U32 }, [NDTPA_QUEUE_LENBYTES] = { .type = NLA_U32 }, [NDTPA_PROXY_QLEN] = { .type = NLA_U32 }, [NDTPA_APP_PROBES] = { .type = NLA_U32 }, [NDTPA_UCAST_PROBES] = { .type = NLA_U32 }, [NDTPA_MCAST_PROBES] = { .type = NLA_U32 }, [NDTPA_MCAST_REPROBES] = { .type = NLA_U32 }, [NDTPA_BASE_REACHABLE_TIME] = { .type = NLA_U64 }, [NDTPA_GC_STALETIME] = { .type = NLA_U64 }, [NDTPA_DELAY_PROBE_TIME] = { .type = NLA_U64 }, [NDTPA_RETRANS_TIME] = { .type = NLA_U64 }, [NDTPA_ANYCAST_DELAY] = { .type = NLA_U64 }, [NDTPA_PROXY_DELAY] = { .type = NLA_U64 }, [NDTPA_LOCKTIME] = { .type = NLA_U64 }, }; static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct neigh_table *tbl; struct ndtmsg *ndtmsg; struct nlattr *tb[NDTA_MAX+1]; bool found = false; int err, tidx; err = nlmsg_parse_deprecated(nlh, sizeof(*ndtmsg), tb, NDTA_MAX, nl_neightbl_policy, extack); if (err < 0) goto errout; if (tb[NDTA_NAME] == NULL) { err = -EINVAL; goto errout; } ndtmsg = nlmsg_data(nlh); for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) { tbl = neigh_tables[tidx]; if (!tbl) continue; if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family) continue; if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0) { found = true; break; } } if (!found) return -ENOENT; /* * We acquire tbl->lock to be nice to the periodic timers and * make sure they always see a consistent set of values. */ write_lock_bh(&tbl->lock); if (tb[NDTA_PARMS]) { struct nlattr *tbp[NDTPA_MAX+1]; struct neigh_parms *p; int i, ifindex = 0; err = nla_parse_nested_deprecated(tbp, NDTPA_MAX, tb[NDTA_PARMS], nl_ntbl_parm_policy, extack); if (err < 0) goto errout_tbl_lock; if (tbp[NDTPA_IFINDEX]) ifindex = nla_get_u32(tbp[NDTPA_IFINDEX]); p = lookup_neigh_parms(tbl, net, ifindex); if (p == NULL) { err = -ENOENT; goto errout_tbl_lock; } for (i = 1; i <= NDTPA_MAX; i++) { if (tbp[i] == NULL) continue; switch (i) { case NDTPA_QUEUE_LEN: NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, nla_get_u32(tbp[i]) * SKB_TRUESIZE(ETH_FRAME_LEN)); break; case NDTPA_QUEUE_LENBYTES: NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, nla_get_u32(tbp[i])); break; case NDTPA_PROXY_QLEN: NEIGH_VAR_SET(p, PROXY_QLEN, nla_get_u32(tbp[i])); break; case NDTPA_APP_PROBES: NEIGH_VAR_SET(p, APP_PROBES, nla_get_u32(tbp[i])); break; case NDTPA_UCAST_PROBES: NEIGH_VAR_SET(p, UCAST_PROBES, nla_get_u32(tbp[i])); break; case NDTPA_MCAST_PROBES: NEIGH_VAR_SET(p, MCAST_PROBES, nla_get_u32(tbp[i])); break; case NDTPA_MCAST_REPROBES: NEIGH_VAR_SET(p, MCAST_REPROBES, nla_get_u32(tbp[i])); break; case NDTPA_BASE_REACHABLE_TIME: NEIGH_VAR_SET(p, BASE_REACHABLE_TIME, nla_get_msecs(tbp[i])); /* update reachable_time as well, otherwise, the change will * only be effective after the next time neigh_periodic_work * decides to recompute it (can be multiple minutes) */ p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); break; case NDTPA_GC_STALETIME: NEIGH_VAR_SET(p, GC_STALETIME, nla_get_msecs(tbp[i])); break; case NDTPA_DELAY_PROBE_TIME: NEIGH_VAR_SET(p, DELAY_PROBE_TIME, nla_get_msecs(tbp[i])); call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p); break; case NDTPA_RETRANS_TIME: NEIGH_VAR_SET(p, RETRANS_TIME, nla_get_msecs(tbp[i])); break; case NDTPA_ANYCAST_DELAY: NEIGH_VAR_SET(p, ANYCAST_DELAY, nla_get_msecs(tbp[i])); break; case NDTPA_PROXY_DELAY: NEIGH_VAR_SET(p, PROXY_DELAY, nla_get_msecs(tbp[i])); break; case NDTPA_LOCKTIME: NEIGH_VAR_SET(p, LOCKTIME, nla_get_msecs(tbp[i])); break; } } } err = -ENOENT; if ((tb[NDTA_THRESH1] || tb[NDTA_THRESH2] || tb[NDTA_THRESH3] || tb[NDTA_GC_INTERVAL]) && !net_eq(net, &init_net)) goto errout_tbl_lock; if (tb[NDTA_THRESH1]) WRITE_ONCE(tbl->gc_thresh1, nla_get_u32(tb[NDTA_THRESH1])); if (tb[NDTA_THRESH2]) WRITE_ONCE(tbl->gc_thresh2, nla_get_u32(tb[NDTA_THRESH2])); if (tb[NDTA_THRESH3]) WRITE_ONCE(tbl->gc_thresh3, nla_get_u32(tb[NDTA_THRESH3])); if (tb[NDTA_GC_INTERVAL]) WRITE_ONCE(tbl->gc_interval, nla_get_msecs(tb[NDTA_GC_INTERVAL])); err = 0; errout_tbl_lock: write_unlock_bh(&tbl->lock); errout: return err; } static int neightbl_valid_dump_info(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct ndtmsg *ndtm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndtm))) { NL_SET_ERR_MSG(extack, "Invalid header for neighbor table dump request"); return -EINVAL; } ndtm = nlmsg_data(nlh); if (ndtm->ndtm_pad1 || ndtm->ndtm_pad2) { NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor table dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ndtm))) { NL_SET_ERR_MSG(extack, "Invalid data after header in neighbor table dump request"); return -EINVAL; } return 0; } static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); int family, tidx, nidx = 0; int tbl_skip = cb->args[0]; int neigh_skip = cb->args[1]; struct neigh_table *tbl; if (cb->strict_check) { int err = neightbl_valid_dump_info(nlh, cb->extack); if (err < 0) return err; } family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family; for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) { struct neigh_parms *p; tbl = neigh_tables[tidx]; if (!tbl) continue; if (tidx < tbl_skip || (family && tbl->family != family)) continue; if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNEIGHTBL, NLM_F_MULTI) < 0) break; nidx = 0; p = list_next_entry(&tbl->parms, list); list_for_each_entry_from(p, &tbl->parms_list, list) { if (!net_eq(neigh_parms_net(p), net)) continue; if (nidx < neigh_skip) goto next; if (neightbl_fill_param_info(skb, tbl, p, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNEIGHTBL, NLM_F_MULTI) < 0) goto out; next: nidx++; } neigh_skip = 0; } out: cb->args[0] = tidx; cb->args[1] = nidx; return skb->len; } static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, u32 pid, u32 seq, int type, unsigned int flags) { unsigned long now = jiffies; struct nda_cacheinfo ci; struct nlmsghdr *nlh; struct ndmsg *ndm; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) return -EMSGSIZE; ndm = nlmsg_data(nlh); ndm->ndm_family = neigh->ops->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; ndm->ndm_flags = neigh->flags; ndm->ndm_type = neigh->type; ndm->ndm_ifindex = neigh->dev->ifindex; if (nla_put(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key)) goto nla_put_failure; read_lock_bh(&neigh->lock); ndm->ndm_state = neigh->nud_state; if (neigh->nud_state & NUD_VALID) { char haddr[MAX_ADDR_LEN]; neigh_ha_snapshot(haddr, neigh, neigh->dev); if (nla_put(skb, NDA_LLADDR, neigh->dev->addr_len, haddr) < 0) { read_unlock_bh(&neigh->lock); goto nla_put_failure; } } ci.ndm_used = jiffies_to_clock_t(now - neigh->used); ci.ndm_confirmed = jiffies_to_clock_t(now - neigh->confirmed); ci.ndm_updated = jiffies_to_clock_t(now - neigh->updated); ci.ndm_refcnt = refcount_read(&neigh->refcnt) - 1; read_unlock_bh(&neigh->lock); if (nla_put_u32(skb, NDA_PROBES, atomic_read(&neigh->probes)) || nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; if (neigh->protocol && nla_put_u8(skb, NDA_PROTOCOL, neigh->protocol)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, u32 pid, u32 seq, int type, unsigned int flags, struct neigh_table *tbl) { struct nlmsghdr *nlh; struct ndmsg *ndm; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) return -EMSGSIZE; ndm = nlmsg_data(nlh); ndm->ndm_family = tbl->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; ndm->ndm_flags = pn->flags | NTF_PROXY; ndm->ndm_type = RTN_UNICAST; ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0; ndm->ndm_state = NUD_NONE; if (nla_put(skb, NDA_DST, tbl->key_len, pn->key)) goto nla_put_failure; if (pn->protocol && nla_put_u8(skb, NDA_PROTOCOL, pn->protocol)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid) { call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); __neigh_notify(neigh, RTM_NEWNEIGH, 0, nlmsg_pid); } static bool neigh_master_filtered(struct net_device *dev, int master_idx) { struct net_device *master; if (!master_idx) return false; master = dev ? netdev_master_upper_dev_get(dev) : NULL; /* 0 is already used to denote NDA_MASTER wasn't passed, therefore need another * invalid value for ifindex to denote "no master". */ if (master_idx == -1) return !!master; if (!master || master->ifindex != master_idx) return true; return false; } static bool neigh_ifindex_filtered(struct net_device *dev, int filter_idx) { if (filter_idx && (!dev || dev->ifindex != filter_idx)) return true; return false; } struct neigh_dump_filter { int master_idx; int dev_idx; }; static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb, struct neigh_dump_filter *filter) { struct net *net = sock_net(skb->sk); struct neighbour *n; int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; struct neigh_hash_table *nht; unsigned int flags = NLM_F_MULTI; if (filter->dev_idx || filter->master_idx) flags |= NLM_F_DUMP_FILTERED; rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); for (h = s_h; h < (1 << nht->hash_shift); h++) { if (h > s_h) s_idx = 0; for (n = rcu_dereference_bh(nht->hash_buckets[h]), idx = 0; n != NULL; n = rcu_dereference_bh(n->next)) { if (idx < s_idx || !net_eq(dev_net(n->dev), net)) goto next; if (neigh_ifindex_filtered(n->dev, filter->dev_idx) || neigh_master_filtered(n->dev, filter->master_idx)) goto next; if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, flags) < 0) { rc = -1; goto out; } next: idx++; } } rc = skb->len; out: rcu_read_unlock_bh(); cb->args[1] = h; cb->args[2] = idx; return rc; } static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb, struct neigh_dump_filter *filter) { struct pneigh_entry *n; struct net *net = sock_net(skb->sk); int rc, h, s_h = cb->args[3]; int idx, s_idx = idx = cb->args[4]; unsigned int flags = NLM_F_MULTI; if (filter->dev_idx || filter->master_idx) flags |= NLM_F_DUMP_FILTERED; read_lock_bh(&tbl->lock); for (h = s_h; h <= PNEIGH_HASHMASK; h++) { if (h > s_h) s_idx = 0; for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) { if (idx < s_idx || pneigh_net(n) != net) goto next; if (neigh_ifindex_filtered(n->dev, filter->dev_idx) || neigh_master_filtered(n->dev, filter->master_idx)) goto next; if (pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, flags, tbl) < 0) { read_unlock_bh(&tbl->lock); rc = -1; goto out; } next: idx++; } } read_unlock_bh(&tbl->lock); rc = skb->len; out: cb->args[3] = h; cb->args[4] = idx; return rc; } static int neigh_valid_dump_req(const struct nlmsghdr *nlh, bool strict_check, struct neigh_dump_filter *filter, struct netlink_ext_ack *extack) { struct nlattr *tb[NDA_MAX + 1]; int err, i; if (strict_check) { struct ndmsg *ndm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) { NL_SET_ERR_MSG(extack, "Invalid header for neighbor dump request"); return -EINVAL; } ndm = nlmsg_data(nlh); if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_ifindex || ndm->ndm_state || ndm->ndm_type) { NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor dump request"); return -EINVAL; } if (ndm->ndm_flags & ~NTF_PROXY) { NL_SET_ERR_MSG(extack, "Invalid flags in header for neighbor dump request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX, nda_policy, extack); } else { err = nlmsg_parse_deprecated(nlh, sizeof(struct ndmsg), tb, NDA_MAX, nda_policy, extack); } if (err < 0) return err; for (i = 0; i <= NDA_MAX; ++i) { if (!tb[i]) continue; /* all new attributes should require strict_check */ switch (i) { case NDA_IFINDEX: filter->dev_idx = nla_get_u32(tb[i]); break; case NDA_MASTER: filter->master_idx = nla_get_u32(tb[i]); break; default: if (strict_check) { NL_SET_ERR_MSG(extack, "Unsupported attribute in neighbor dump request"); return -EINVAL; } } } return 0; } static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct neigh_dump_filter filter = {}; struct neigh_table *tbl; int t, family, s_t; int proxy = 0; int err; family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family; /* check for full ndmsg structure presence, family member is * the same for both structures */ if (nlmsg_len(nlh) >= sizeof(struct ndmsg) && ((struct ndmsg *)nlmsg_data(nlh))->ndm_flags == NTF_PROXY) proxy = 1; err = neigh_valid_dump_req(nlh, cb->strict_check, &filter, cb->extack); if (err < 0 && cb->strict_check) return err; err = 0; s_t = cb->args[0]; for (t = 0; t < NEIGH_NR_TABLES; t++) { tbl = neigh_tables[t]; if (!tbl) continue; if (t < s_t || (family && tbl->family != family)) continue; if (t > s_t) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (proxy) err = pneigh_dump_table(tbl, skb, cb, &filter); else err = neigh_dump_table(tbl, skb, cb, &filter); if (err < 0) break; } cb->args[0] = t; return skb->len; } static int neigh_valid_get_req(const struct nlmsghdr *nlh, struct neigh_table **tbl, void **dst, int *dev_idx, u8 *ndm_flags, struct netlink_ext_ack *extack) { struct nlattr *tb[NDA_MAX + 1]; struct ndmsg *ndm; int err, i; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) { NL_SET_ERR_MSG(extack, "Invalid header for neighbor get request"); return -EINVAL; } ndm = nlmsg_data(nlh); if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_state || ndm->ndm_type) { NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor get request"); return -EINVAL; } if (ndm->ndm_flags & ~NTF_PROXY) { NL_SET_ERR_MSG(extack, "Invalid flags in header for neighbor get request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX, nda_policy, extack); if (err < 0) return err; *ndm_flags = ndm->ndm_flags; *dev_idx = ndm->ndm_ifindex; *tbl = neigh_find_table(ndm->ndm_family); if (*tbl == NULL) { NL_SET_ERR_MSG(extack, "Unsupported family in header for neighbor get request"); return -EAFNOSUPPORT; } for (i = 0; i <= NDA_MAX; ++i) { if (!tb[i]) continue; switch (i) { case NDA_DST: if (nla_len(tb[i]) != (int)(*tbl)->key_len) { NL_SET_ERR_MSG(extack, "Invalid network address in neighbor get request"); return -EINVAL; } *dst = nla_data(tb[i]); break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in neighbor get request"); return -EINVAL; } } return 0; } static inline size_t neigh_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */ + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */ + nla_total_size(sizeof(struct nda_cacheinfo)) + nla_total_size(4) /* NDA_PROBES */ + nla_total_size(1); /* NDA_PROTOCOL */ } static int neigh_get_reply(struct net *net, struct neighbour *neigh, u32 pid, u32 seq) { struct sk_buff *skb; int err = 0; skb = nlmsg_new(neigh_nlmsg_size(), GFP_KERNEL); if (!skb) return -ENOBUFS; err = neigh_fill_info(skb, neigh, pid, seq, RTM_NEWNEIGH, 0); if (err) { kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, pid); errout: return err; } static inline size_t pneigh_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */ + nla_total_size(1); /* NDA_PROTOCOL */ } static int pneigh_get_reply(struct net *net, struct pneigh_entry *neigh, u32 pid, u32 seq, struct neigh_table *tbl) { struct sk_buff *skb; int err = 0; skb = nlmsg_new(pneigh_nlmsg_size(), GFP_KERNEL); if (!skb) return -ENOBUFS; err = pneigh_fill_info(skb, neigh, pid, seq, RTM_NEWNEIGH, 0, tbl); if (err) { kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, pid); errout: return err; } static int neigh_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct net_device *dev = NULL; struct neigh_table *tbl = NULL; struct neighbour *neigh; void *dst = NULL; u8 ndm_flags = 0; int dev_idx = 0; int err; err = neigh_valid_get_req(nlh, &tbl, &dst, &dev_idx, &ndm_flags, extack); if (err < 0) return err; if (dev_idx) { dev = __dev_get_by_index(net, dev_idx); if (!dev) { NL_SET_ERR_MSG(extack, "Unknown device ifindex"); return -ENODEV; } } if (!dst) { NL_SET_ERR_MSG(extack, "Network address not specified"); return -EINVAL; } if (ndm_flags & NTF_PROXY) { struct pneigh_entry *pn; pn = pneigh_lookup(tbl, net, dst, dev, 0); if (!pn) { NL_SET_ERR_MSG(extack, "Proxy neighbour entry not found"); return -ENOENT; } return pneigh_get_reply(net, pn, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, tbl); } if (!dev) { NL_SET_ERR_MSG(extack, "No device specified"); return -EINVAL; } neigh = neigh_lookup(tbl, dst, dev); if (!neigh) { NL_SET_ERR_MSG(extack, "Neighbour entry not found"); return -ENOENT; } err = neigh_get_reply(net, neigh, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq); neigh_release(neigh); return err; } void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie) { int chain; struct neigh_hash_table *nht; rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); read_lock(&tbl->lock); /* avoid resizes */ for (chain = 0; chain < (1 << nht->hash_shift); chain++) { struct neighbour *n; for (n = rcu_dereference_bh(nht->hash_buckets[chain]); n != NULL; n = rcu_dereference_bh(n->next)) cb(n, cookie); } read_unlock(&tbl->lock); rcu_read_unlock_bh(); } EXPORT_SYMBOL(neigh_for_each); /* The tbl->lock must be held as a writer and BH disabled. */ void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)) { int chain; struct neigh_hash_table *nht; nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); for (chain = 0; chain < (1 << nht->hash_shift); chain++) { struct neighbour *n; struct neighbour __rcu **np; np = &nht->hash_buckets[chain]; while ((n = rcu_dereference_protected(*np, lockdep_is_held(&tbl->lock))) != NULL) { int release; write_lock(&n->lock); release = cb(n); if (release) { rcu_assign_pointer(*np, rcu_dereference_protected(n->next, lockdep_is_held(&tbl->lock))); neigh_mark_dead(n); } else np = &n->next; write_unlock(&n->lock); if (release) neigh_cleanup_and_release(n); } } } EXPORT_SYMBOL(__neigh_for_each_release); int neigh_xmit(int index, struct net_device *dev, const void *addr, struct sk_buff *skb) { int err = -EAFNOSUPPORT; if (likely(index < NEIGH_NR_TABLES)) { struct neigh_table *tbl; struct neighbour *neigh; tbl = neigh_tables[index]; if (!tbl) goto out; rcu_read_lock_bh(); if (index == NEIGH_ARP_TABLE) { u32 key = *((u32 *)addr); neigh = __ipv4_neigh_lookup_noref(dev, key); } else { neigh = __neigh_lookup_noref(tbl, addr, dev); } if (!neigh) neigh = __neigh_create(tbl, addr, dev, false); err = PTR_ERR(neigh); if (IS_ERR(neigh)) { rcu_read_unlock_bh(); goto out_kfree_skb; } err = neigh->output(neigh, skb); rcu_read_unlock_bh(); } else if (index == NEIGH_LINK_TABLE) { err = dev_hard_header(skb, dev, ntohs(skb->protocol), addr, NULL, skb->len); if (err < 0) goto out_kfree_skb; err = dev_queue_xmit(skb); } out: return err; out_kfree_skb: kfree_skb(skb); goto out; } EXPORT_SYMBOL(neigh_xmit); #ifdef CONFIG_PROC_FS static struct neighbour *neigh_get_first(struct seq_file *seq) { struct neigh_seq_state *state = seq->private; struct net *net = seq_file_net(seq); struct neigh_hash_table *nht = state->nht; struct neighbour *n = NULL; int bucket; state->flags &= ~NEIGH_SEQ_IS_PNEIGH; for (bucket = 0; bucket < (1 << nht->hash_shift); bucket++) { n = rcu_dereference_bh(nht->hash_buckets[bucket]); while (n) { if (!net_eq(dev_net(n->dev), net)) goto next; if (state->neigh_sub_iter) { loff_t fakep = 0; void *v; v = state->neigh_sub_iter(state, n, &fakep); if (!v) goto next; } if (!(state->flags & NEIGH_SEQ_SKIP_NOARP)) break; if (n->nud_state & ~NUD_NOARP) break; next: n = rcu_dereference_bh(n->next); } if (n) break; } state->bucket = bucket; return n; } static struct neighbour *neigh_get_next(struct seq_file *seq, struct neighbour *n, loff_t *pos) { struct neigh_seq_state *state = seq->private; struct net *net = seq_file_net(seq); struct neigh_hash_table *nht = state->nht; if (state->neigh_sub_iter) { void *v = state->neigh_sub_iter(state, n, pos); if (v) return n; } n = rcu_dereference_bh(n->next); while (1) { while (n) { if (!net_eq(dev_net(n->dev), net)) goto next; if (state->neigh_sub_iter) { void *v = state->neigh_sub_iter(state, n, pos); if (v) return n; goto next; } if (!(state->flags & NEIGH_SEQ_SKIP_NOARP)) break; if (n->nud_state & ~NUD_NOARP) break; next: n = rcu_dereference_bh(n->next); } if (n) break; if (++state->bucket >= (1 << nht->hash_shift)) break; n = rcu_dereference_bh(nht->hash_buckets[state->bucket]); } if (n && pos) --(*pos); return n; } static struct neighbour *neigh_get_idx(struct seq_file *seq, loff_t *pos) { struct neighbour *n = neigh_get_first(seq); if (n) { --(*pos); while (*pos) { n = neigh_get_next(seq, n, pos); if (!n) break; } } return *pos ? NULL : n; } static struct pneigh_entry *pneigh_get_first(struct seq_file *seq) { struct neigh_seq_state *state = seq->private; struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; struct pneigh_entry *pn = NULL; int bucket; state->flags |= NEIGH_SEQ_IS_PNEIGH; for (bucket = 0; bucket <= PNEIGH_HASHMASK; bucket++) { pn = tbl->phash_buckets[bucket]; while (pn && !net_eq(pneigh_net(pn), net)) pn = pn->next; if (pn) break; } state->bucket = bucket; return pn; } static struct pneigh_entry *pneigh_get_next(struct seq_file *seq, struct pneigh_entry *pn, loff_t *pos) { struct neigh_seq_state *state = seq->private; struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; do { pn = pn->next; } while (pn && !net_eq(pneigh_net(pn), net)); while (!pn) { if (++state->bucket > PNEIGH_HASHMASK) break; pn = tbl->phash_buckets[state->bucket]; while (pn && !net_eq(pneigh_net(pn), net)) pn = pn->next; if (pn) break; } if (pn && pos) --(*pos); return pn; } static struct pneigh_entry *pneigh_get_idx(struct seq_file *seq, loff_t *pos) { struct pneigh_entry *pn = pneigh_get_first(seq); if (pn) { --(*pos); while (*pos) { pn = pneigh_get_next(seq, pn, pos); if (!pn) break; } } return *pos ? NULL : pn; } static void *neigh_get_idx_any(struct seq_file *seq, loff_t *pos) { struct neigh_seq_state *state = seq->private; void *rc; loff_t idxpos = *pos; rc = neigh_get_idx(seq, &idxpos); if (!rc && !(state->flags & NEIGH_SEQ_NEIGH_ONLY)) rc = pneigh_get_idx(seq, &idxpos); return rc; } void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl, unsigned int neigh_seq_flags) __acquires(tbl->lock) __acquires(rcu_bh) { struct neigh_seq_state *state = seq->private; state->tbl = tbl; state->bucket = 0; state->flags = (neigh_seq_flags & ~NEIGH_SEQ_IS_PNEIGH); rcu_read_lock_bh(); state->nht = rcu_dereference_bh(tbl->nht); read_lock(&tbl->lock); return *pos ? neigh_get_idx_any(seq, pos) : SEQ_START_TOKEN; } EXPORT_SYMBOL(neigh_seq_start); void *neigh_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct neigh_seq_state *state; void *rc; if (v == SEQ_START_TOKEN) { rc = neigh_get_first(seq); goto out; } state = seq->private; if (!(state->flags & NEIGH_SEQ_IS_PNEIGH)) { rc = neigh_get_next(seq, v, NULL); if (rc) goto out; if (!(state->flags & NEIGH_SEQ_NEIGH_ONLY)) rc = pneigh_get_first(seq); } else { BUG_ON(state->flags & NEIGH_SEQ_NEIGH_ONLY); rc = pneigh_get_next(seq, v, NULL); } out: ++(*pos); return rc; } EXPORT_SYMBOL(neigh_seq_next); void neigh_seq_stop(struct seq_file *seq, void *v) __releases(tbl->lock) __releases(rcu_bh) { struct neigh_seq_state *state = seq->private; struct neigh_table *tbl = state->tbl; read_unlock(&tbl->lock); rcu_read_unlock_bh(); } EXPORT_SYMBOL(neigh_seq_stop); /* statistics via seq_file */ static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos) { struct neigh_table *tbl = PDE_DATA(file_inode(seq->file)); int cpu; if (*pos == 0) return SEQ_START_TOKEN; for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return per_cpu_ptr(tbl->stats, cpu); } return NULL; } static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct neigh_table *tbl = PDE_DATA(file_inode(seq->file)); int cpu; for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return per_cpu_ptr(tbl->stats, cpu); } (*pos)++; return NULL; } static void neigh_stat_seq_stop(struct seq_file *seq, void *v) { } static int neigh_stat_seq_show(struct seq_file *seq, void *v) { struct neigh_table *tbl = PDE_DATA(file_inode(seq->file)); struct neigh_statistics *st = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards table_fulls\n"); return 0; } seq_printf(seq, "%08x %08lx %08lx %08lx %08lx %08lx %08lx " "%08lx %08lx %08lx " "%08lx %08lx %08lx\n", atomic_read(&tbl->entries), st->allocs, st->destroys, st->hash_grows, st->lookups, st->hits, st->res_failed, st->rcv_probes_mcast, st->rcv_probes_ucast, st->periodic_gc_runs, st->forced_gc_runs, st->unres_discards, st->table_fulls ); return 0; } static const struct seq_operations neigh_stat_seq_ops = { .start = neigh_stat_seq_start, .next = neigh_stat_seq_next, .stop = neigh_stat_seq_stop, .show = neigh_stat_seq_show, }; #endif /* CONFIG_PROC_FS */ static void __neigh_notify(struct neighbour *n, int type, int flags, u32 pid) { struct sk_buff *skb; int err = -ENOBUFS; struct net *net; rcu_read_lock(); net = dev_net_rcu(n->dev); skb = nlmsg_new(neigh_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) goto errout; err = neigh_fill_info(skb, n, pid, 0, type, flags); if (err < 0) { /* -EMSGSIZE implies BUG in neigh_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); goto out; errout: rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); out: rcu_read_unlock(); } void neigh_app_ns(struct neighbour *n) { __neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST, 0); } EXPORT_SYMBOL(neigh_app_ns); #ifdef CONFIG_SYSCTL static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN); static int proc_unres_qlen(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int size, ret; struct ctl_table tmp = *ctl; tmp.extra1 = SYSCTL_ZERO; tmp.extra2 = &unres_qlen_max; tmp.data = &size; size = *(int *)ctl->data / SKB_TRUESIZE(ETH_FRAME_LEN); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret) *(int *)ctl->data = size * SKB_TRUESIZE(ETH_FRAME_LEN); return ret; } static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, int family) { switch (family) { case AF_INET: return __in_dev_arp_parms_get_rcu(dev); case AF_INET6: return __in6_dev_nd_parms_get_rcu(dev); } return NULL; } static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, int index) { struct net_device *dev; int family = neigh_parms_family(p); rcu_read_lock(); for_each_netdev_rcu(net, dev) { struct neigh_parms *dst_p = neigh_get_dev_parms_rcu(dev, family); if (dst_p && !test_bit(index, dst_p->data_state)) dst_p->data[index] = p->data[index]; } rcu_read_unlock(); } static void neigh_proc_update(struct ctl_table *ctl, int write) { struct net_device *dev = ctl->extra1; struct neigh_parms *p = ctl->extra2; struct net *net = neigh_parms_net(p); int index = (int *) ctl->data - p->data; if (!write) return; set_bit(index, p->data_state); if (index == NEIGH_VAR_DELAY_PROBE_TIME) call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p); if (!dev) /* NULL dev means this is default value */ neigh_copy_dflt_parms(net, p, index); } static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tmp = *ctl; int ret; tmp.extra1 = SYSCTL_ZERO; tmp.extra2 = SYSCTL_INT_MAX; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); neigh_proc_update(ctl, write); return ret; } int neigh_proc_dointvec(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); neigh_proc_update(ctl, write); return ret; } EXPORT_SYMBOL(neigh_proc_dointvec); int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); neigh_proc_update(ctl, write); return ret; } EXPORT_SYMBOL(neigh_proc_dointvec_jiffies); static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec_userhz_jiffies(ctl, write, buffer, lenp, ppos); neigh_proc_update(ctl, write); return ret; } int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); neigh_proc_update(ctl, write); return ret; } EXPORT_SYMBOL(neigh_proc_dointvec_ms_jiffies); static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_unres_qlen(ctl, write, buffer, lenp, ppos); neigh_proc_update(ctl, write); return ret; } static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct neigh_parms *p = ctl->extra2; int ret; if (strcmp(ctl->procname, "base_reachable_time") == 0) ret = neigh_proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); else if (strcmp(ctl->procname, "base_reachable_time_ms") == 0) ret = neigh_proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); else ret = -1; if (write && ret == 0) { /* update reachable_time as well, otherwise, the change will * only be effective after the next time neigh_periodic_work * decides to recompute it */ p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } return ret; } #define NEIGH_PARMS_DATA_OFFSET(index) \ (&((struct neigh_parms *) 0)->data[index]) #define NEIGH_SYSCTL_ENTRY(attr, data_attr, name, mval, proc) \ [NEIGH_VAR_ ## attr] = { \ .procname = name, \ .data = NEIGH_PARMS_DATA_OFFSET(NEIGH_VAR_ ## data_attr), \ .maxlen = sizeof(int), \ .mode = mval, \ .proc_handler = proc, \ } #define NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(attr, name) \ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_zero_intmax) #define NEIGH_SYSCTL_JIFFIES_ENTRY(attr, name) \ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_jiffies) #define NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(attr, name) \ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_userhz_jiffies) #define NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(attr, data_attr, name) \ NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_ms_jiffies) #define NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(attr, data_attr, name) \ NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_unres_qlen) static struct neigh_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1]; } neigh_sysctl_template __read_mostly = { .neigh_vars = { NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(UCAST_PROBES, "ucast_solicit"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(APP_PROBES, "app_solicit"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_REPROBES, "mcast_resolicit"), NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"), NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"), NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"), NEIGH_SYSCTL_JIFFIES_ENTRY(GC_STALETIME, "gc_stale_time"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(QUEUE_LEN_BYTES, "unres_qlen_bytes"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(PROXY_QLEN, "proxy_qlen"), NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(ANYCAST_DELAY, "anycast_delay"), NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(PROXY_DELAY, "proxy_delay"), NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(LOCKTIME, "locktime"), NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(QUEUE_LEN, QUEUE_LEN_BYTES, "unres_qlen"), NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(RETRANS_TIME_MS, RETRANS_TIME, "retrans_time_ms"), NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(BASE_REACHABLE_TIME_MS, BASE_REACHABLE_TIME, "base_reachable_time_ms"), [NEIGH_VAR_GC_INTERVAL] = { .procname = "gc_interval", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NEIGH_VAR_GC_THRESH1] = { .procname = "gc_thresh1", .maxlen = sizeof(int), .mode = 0644, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_GC_THRESH2] = { .procname = "gc_thresh2", .maxlen = sizeof(int), .mode = 0644, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_GC_THRESH3] = { .procname = "gc_thresh3", .maxlen = sizeof(int), .mode = 0644, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, .proc_handler = proc_dointvec_minmax, }, {}, }, }; int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, proc_handler *handler) { int i; struct neigh_sysctl_table *t; const char *dev_name_source; char neigh_path[ sizeof("net//neigh/") + IFNAMSIZ + IFNAMSIZ ]; char *p_name; t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL); if (!t) goto err; for (i = 0; i < NEIGH_VAR_GC_INTERVAL; i++) { t->neigh_vars[i].data += (long) p; t->neigh_vars[i].extra1 = dev; t->neigh_vars[i].extra2 = p; } if (dev) { dev_name_source = dev->name; /* Terminate the table early */ memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0, sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL])); } else { struct neigh_table *tbl = p->tbl; dev_name_source = "default"; t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = &tbl->gc_interval; t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = &tbl->gc_thresh1; t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = &tbl->gc_thresh2; t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = &tbl->gc_thresh3; } if (handler) { /* RetransTime */ t->neigh_vars[NEIGH_VAR_RETRANS_TIME].proc_handler = handler; /* ReachableTime */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = handler; /* RetransTime (in milliseconds)*/ t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler; /* ReachableTime (in milliseconds) */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler; } else { /* Those handlers will update p->reachable_time after * base_reachable_time(_ms) is set to ensure the new timer starts being * applied after the next neighbour update instead of waiting for * neigh_periodic_work to update its value (can be multiple minutes) * So any handler that replaces them should do this as well */ /* ReachableTime */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = neigh_proc_base_reachable_time; /* ReachableTime (in milliseconds) */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = neigh_proc_base_reachable_time; } /* Don't export sysctls to unprivileged users */ if (neigh_parms_net(p)->user_ns != &init_user_ns) t->neigh_vars[0].procname = NULL; switch (neigh_parms_family(p)) { case AF_INET: p_name = "ipv4"; break; case AF_INET6: p_name = "ipv6"; break; default: BUG(); } snprintf(neigh_path, sizeof(neigh_path), "net/%s/neigh/%s", p_name, dev_name_source); t->sysctl_header = register_net_sysctl(neigh_parms_net(p), neigh_path, t->neigh_vars); if (!t->sysctl_header) goto free; p->sysctl_table = t; return 0; free: kfree(t); err: return -ENOBUFS; } EXPORT_SYMBOL(neigh_sysctl_register); void neigh_sysctl_unregister(struct neigh_parms *p) { if (p->sysctl_table) { struct neigh_sysctl_table *t = p->sysctl_table; p->sysctl_table = NULL; unregister_net_sysctl_table(t->sysctl_header); kfree(t); } } EXPORT_SYMBOL(neigh_sysctl_unregister); #endif /* CONFIG_SYSCTL */ static int __init neigh_init(void) { rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETNEIGH, neigh_get, neigh_dump_info, 0); rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info, 0); rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL, 0); return 0; } subsys_initcall(neigh_init); |
| 13 13 2 13 14 13 1 2 13 21 28 20 1 7 9 5 8 5 2 1 2 2 3 2 2 2 2 35 35 36 36 35 1 1 34 19 26 34 4 4 20 23 27 1 38 38 1 36 759 750 4 753 6 8 42 42 6 6 21 7 4 28 14 7 7 1 2 1 1 49 4 28 14 5 55 54 1 3 2 761 759 759 759 743 897 897 897 747 747 743 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 over IPv4 tunnel device - Simple Internet Transition (SIT) * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * * Changes: * Roger Venning <r.venning@telstra.com>: 6to4 support * Nate Thompson <nate@thebog.net>: 6to4 support * Fred Templin <fred.l.templin@boeing.com>: isatap support */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmp.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/ip.h> #include <net/udp.h> #include <net/icmp.h> #include <net/ip_tunnels.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/dsfield.h> #include <net/net_namespace.h> #include <net/netns/generic.h> /* This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c For comments look at net/ipv4/ip_gre.c --ANK */ #define IP6_SIT_HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static int ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); static void ipip6_dev_free(struct net_device *dev); static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, __be32 *v4dst); static struct rtnl_link_ops sit_link_ops __read_mostly; static unsigned int sit_net_id __read_mostly; struct sit_net { struct ip_tunnel __rcu *tunnels_r_l[IP6_SIT_HASH_SIZE]; struct ip_tunnel __rcu *tunnels_r[IP6_SIT_HASH_SIZE]; struct ip_tunnel __rcu *tunnels_l[IP6_SIT_HASH_SIZE]; struct ip_tunnel __rcu *tunnels_wc[1]; struct ip_tunnel __rcu **tunnels[4]; struct net_device *fb_tunnel_dev; }; static inline struct sit_net *dev_to_sit_net(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); return net_generic(t->net, sit_net_id); } /* * Must be invoked with rcu_read_lock */ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, struct net_device *dev, __be32 remote, __be32 local, int sifindex) { unsigned int h0 = HASH(remote); unsigned int h1 = HASH(local); struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); int ifindex = dev ? dev->ifindex : 0; for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (!dev || !t->parms.link || ifindex == t->parms.link || sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && (!dev || !t->parms.link || ifindex == t->parms.link || sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && (!dev || !t->parms.link || ifindex == t->parms.link || sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } t = rcu_dereference(sitn->tunnels_wc[0]); if (t && (t->dev->flags & IFF_UP)) return t; return NULL; } static struct ip_tunnel __rcu **__ipip6_bucket(struct sit_net *sitn, struct ip_tunnel_parm *parms) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; unsigned int h = 0; int prio = 0; if (remote) { prio |= 2; h ^= HASH(remote); } if (local) { prio |= 1; h ^= HASH(local); } return &sitn->tunnels[prio][h]; } static inline struct ip_tunnel __rcu **ipip6_bucket(struct sit_net *sitn, struct ip_tunnel *t) { return __ipip6_bucket(sitn, &t->parms); } static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t) { struct ip_tunnel __rcu **tp; struct ip_tunnel *iter; for (tp = ipip6_bucket(sitn, t); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { rcu_assign_pointer(*tp, t->next); break; } } } static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t) { struct ip_tunnel __rcu **tp = ipip6_bucket(sitn, t); rcu_assign_pointer(t->next, rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) { #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel *t = netdev_priv(dev); if (dev == sitn->fb_tunnel_dev || !sitn->fb_tunnel_dev) { ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0); t->ip6rd.relay_prefix = 0; t->ip6rd.prefixlen = 16; t->ip6rd.relay_prefixlen = 0; } else { struct ip_tunnel *t0 = netdev_priv(sitn->fb_tunnel_dev); memcpy(&t->ip6rd, &t0->ip6rd, sizeof(t->ip6rd)); } #endif } static int ipip6_tunnel_create(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); int err; memcpy(dev->dev_addr, &t->parms.iph.saddr, 4); memcpy(dev->broadcast, &t->parms.iph.daddr, 4); if ((__force u16)t->parms.i_flags & SIT_ISATAP) dev->priv_flags |= IFF_ISATAP; dev->rtnl_link_ops = &sit_link_ops; err = register_netdevice(dev); if (err < 0) goto out; ipip6_tunnel_clone_6rd(dev, sitn); ipip6_tunnel_link(sitn, t); return 0; out: return err; } static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, struct ip_tunnel_parm *parms, int create) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; struct ip_tunnel *t, *nt; struct ip_tunnel __rcu **tp; struct net_device *dev; char name[IFNAMSIZ]; struct sit_net *sitn = net_generic(net, sit_net_id); for (tp = __ipip6_bucket(sitn, parms); (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && parms->link == t->parms.link) { if (create) return NULL; else return t; } } if (!create) goto failed; if (parms->name[0]) { if (!dev_valid_name(parms->name)) goto failed; strlcpy(name, parms->name, IFNAMSIZ); } else { strcpy(name, "sit%d"); } dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ipip6_tunnel_setup); if (!dev) return NULL; dev_net_set(dev, net); nt = netdev_priv(dev); nt->parms = *parms; if (ipip6_tunnel_create(dev) < 0) goto failed_free; if (!parms->name[0]) strcpy(parms->name, dev->name); return nt; failed_free: free_netdev(dev); failed: return NULL; } #define for_each_prl_rcu(start) \ for (prl = rcu_dereference(start); \ prl; \ prl = rcu_dereference(prl->next)) static struct ip_tunnel_prl_entry * __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) { struct ip_tunnel_prl_entry *prl; for_each_prl_rcu(t->prl) if (prl->addr == addr) break; return prl; } static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __user *a) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_prl kprl, *kp; struct ip_tunnel_prl_entry *prl; unsigned int cmax, c = 0, ca, len; int ret = 0; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) return -EINVAL; if (copy_from_user(&kprl, a, sizeof(kprl))) return -EFAULT; cmax = kprl.datalen / sizeof(kprl); if (cmax > 1 && kprl.addr != htonl(INADDR_ANY)) cmax = 1; /* For simple GET or for root users, * we try harder to allocate. */ kp = (cmax <= 1 || capable(CAP_NET_ADMIN)) ? kcalloc(cmax, sizeof(*kp), GFP_KERNEL_ACCOUNT | __GFP_NOWARN) : NULL; ca = min(t->prl_count, cmax); if (!kp) { /* We don't try hard to allocate much memory for * non-root users. * For root users, retry allocating enough memory for * the answer. */ kp = kcalloc(ca, sizeof(*kp), GFP_ATOMIC | __GFP_ACCOUNT | __GFP_NOWARN); if (!kp) { ret = -ENOMEM; goto out; } } rcu_read_lock(); for_each_prl_rcu(t->prl) { if (c >= cmax) break; if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr) continue; kp[c].addr = prl->addr; kp[c].flags = prl->flags; c++; if (kprl.addr != htonl(INADDR_ANY)) break; } rcu_read_unlock(); len = sizeof(*kp) * c; ret = 0; if ((len && copy_to_user(a + 1, kp, len)) || put_user(len, &a->datalen)) ret = -EFAULT; kfree(kp); out: return ret; } static int ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) { struct ip_tunnel_prl_entry *p; int err = 0; if (a->addr == htonl(INADDR_ANY)) return -EINVAL; ASSERT_RTNL(); for (p = rtnl_dereference(t->prl); p; p = rtnl_dereference(p->next)) { if (p->addr == a->addr) { if (chg) { p->flags = a->flags; goto out; } err = -EEXIST; goto out; } } if (chg) { err = -ENXIO; goto out; } p = kzalloc(sizeof(struct ip_tunnel_prl_entry), GFP_KERNEL); if (!p) { err = -ENOBUFS; goto out; } p->next = t->prl; p->addr = a->addr; p->flags = a->flags; t->prl_count++; rcu_assign_pointer(t->prl, p); out: return err; } static void prl_list_destroy_rcu(struct rcu_head *head) { struct ip_tunnel_prl_entry *p, *n; p = container_of(head, struct ip_tunnel_prl_entry, rcu_head); do { n = rcu_dereference_protected(p->next, 1); kfree(p); p = n; } while (p); } static int ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) { struct ip_tunnel_prl_entry *x; struct ip_tunnel_prl_entry __rcu **p; int err = 0; ASSERT_RTNL(); if (a && a->addr != htonl(INADDR_ANY)) { for (p = &t->prl; (x = rtnl_dereference(*p)) != NULL; p = &x->next) { if (x->addr == a->addr) { *p = x->next; kfree_rcu(x, rcu_head); t->prl_count--; goto out; } } err = -ENXIO; } else { x = rtnl_dereference(t->prl); if (x) { t->prl_count = 0; call_rcu(&x->rcu_head, prl_list_destroy_rcu); t->prl = NULL; } } out: return err; } static int ipip6_tunnel_prl_ctl(struct net_device *dev, struct ip_tunnel_prl __user *data, int cmd) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_prl prl; int err; if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) return -EINVAL; if (copy_from_user(&prl, data, sizeof(prl))) return -EFAULT; switch (cmd) { case SIOCDELPRL: err = ipip6_tunnel_del_prl(t, &prl); break; case SIOCADDPRL: case SIOCCHGPRL: err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL); break; } dst_cache_reset(&t->dst_cache); netdev_state_change(dev); return err; } static int isatap_chksrc(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *t) { struct ip_tunnel_prl_entry *p; int ok = 1; rcu_read_lock(); p = __ipip6_tunnel_locate_prl(t, iph->saddr); if (p) { if (p->flags & PRL_DEFAULT) skb->ndisc_nodetype = NDISC_NODETYPE_DEFAULT; else skb->ndisc_nodetype = NDISC_NODETYPE_NODEFAULT; } else { const struct in6_addr *addr6 = &ipv6_hdr(skb)->saddr; if (ipv6_addr_is_isatap(addr6) && (addr6->s6_addr32[3] == iph->saddr) && ipv6_chk_prefix(addr6, t->dev)) skb->ndisc_nodetype = NDISC_NODETYPE_HOST; else ok = 0; } rcu_read_unlock(); return ok; } static void ipip6_tunnel_uninit(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct sit_net *sitn = net_generic(tunnel->net, sit_net_id); if (dev == sitn->fb_tunnel_dev) { RCU_INIT_POINTER(sitn->tunnels_wc[0], NULL); } else { ipip6_tunnel_unlink(sitn, tunnel); ipip6_tunnel_del_prl(tunnel, NULL); } dst_cache_reset(&tunnel->dst_cache); dev_put(dev); } static int ipip6_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; unsigned int data_len = 0; struct ip_tunnel *t; int sifindex; int err; switch (type) { default: case ICMP_PARAMETERPROB: return 0; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: /* Impossible event. */ return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, I believe they are just ether pollution. --ANK */ break; } break; case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) return 0; data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ break; case ICMP_REDIRECT: break; } err = -ENOENT; sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->daddr, iph->saddr, sifindex); if (!t) goto out; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, t->parms.link, iph->protocol); err = 0; goto out; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, iph->protocol); err = 0; goto out; } err = 0; if (__in6_dev_get(skb->dev) && !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) goto out; if (t->parms.iph.daddr == 0) goto out; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) goto out; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; out: return err; } static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr, const struct in6_addr *v6addr) { __be32 v4embed = 0; if (check_6rd(tunnel, v6addr, &v4embed) && v4addr != v4embed) return true; return false; } /* Checks if an address matches an address on the tunnel interface. * Used to detect the NAT of proto 41 packets and let them pass spoofing test. * Long story: * This function is called after we considered the packet as spoofed * in is_spoofed_6rd. * We may have a router that is doing NAT for proto 41 packets * for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb * will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd * function will return true, dropping the packet. * But, we can still check if is spoofed against the IP * addresses associated with the interface. */ static bool only_dnatted(const struct ip_tunnel *tunnel, const struct in6_addr *v6dst) { int prefix_len; #ifdef CONFIG_IPV6_SIT_6RD prefix_len = tunnel->ip6rd.prefixlen + 32 - tunnel->ip6rd.relay_prefixlen; #else prefix_len = 48; #endif return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev); } /* Returns true if a packet is spoofed */ static bool packet_is_spoofed(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *tunnel) { const struct ipv6hdr *ipv6h; if (tunnel->dev->priv_flags & IFF_ISATAP) { if (!isatap_chksrc(skb, iph, tunnel)) return true; return false; } if (tunnel->dev->flags & IFF_POINTOPOINT) return false; ipv6h = ipv6_hdr(skb); if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) { net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n", &iph->saddr, &ipv6h->saddr, &iph->daddr, &ipv6h->daddr); return true; } if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr))) return false; if (only_dnatted(tunnel, &ipv6h->daddr)) return false; net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n", &iph->saddr, &ipv6h->saddr, &iph->daddr, &ipv6h->daddr); return true; } static int ipip6_rcv(struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); struct ip_tunnel *tunnel; int sifindex; int err; sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr, sifindex); if (tunnel) { struct pcpu_sw_netstats *tstats; if (tunnel->parms.iph.protocol != IPPROTO_IPV6 && tunnel->parms.iph.protocol != 0) goto out; skb->mac_header = skb->network_header; skb_reset_network_header(skb); IPCB(skb)->flags = 0; skb->dev = tunnel->dev; if (packet_is_spoofed(skb, iph, tunnel)) { tunnel->dev->stats.rx_errors++; goto out; } if (iptunnel_pull_header(skb, 0, htons(ETH_P_IPV6), !net_eq(tunnel->net, dev_net(tunnel->dev)))) goto out; /* skb can be uncloned in iptunnel_pull_header, so * old iph is no longer valid */ iph = (const struct iphdr *)skb_mac_header(skb); skb_reset_mac_header(skb); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &iph->saddr, iph->tos); if (err > 1) { ++tunnel->dev->stats.rx_frame_errors; ++tunnel->dev->stats.rx_errors; goto out; } } tstats = this_cpu_ptr(tunnel->dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); netif_rx(skb); return 0; } /* no tunnel matched, let upstream know, ipsec may handle it */ return 1; out: kfree_skb(skb); return 0; } static const struct tnl_ptk_info ipip_tpi = { /* no tunnel info required for ipip. */ .proto = htons(ETH_P_IP), }; #if IS_ENABLED(CONFIG_MPLS) static const struct tnl_ptk_info mplsip_tpi = { /* no tunnel info required for mplsip. */ .proto = htons(ETH_P_MPLS_UC), }; #endif static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { const struct iphdr *iph; struct ip_tunnel *tunnel; int sifindex; sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; iph = ip_hdr(skb); tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr, sifindex); if (tunnel) { const struct tnl_ptk_info *tpi; if (tunnel->parms.iph.protocol != ipproto && tunnel->parms.iph.protocol != 0) goto drop; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; #if IS_ENABLED(CONFIG_MPLS) if (ipproto == IPPROTO_MPLS) tpi = &mplsip_tpi; else #endif tpi = &ipip_tpi; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; skb_reset_mac_header(skb); return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error); } return 1; drop: kfree_skb(skb); return 0; } static int ipip_rcv(struct sk_buff *skb) { return sit_tunnel_rcv(skb, IPPROTO_IPIP); } #if IS_ENABLED(CONFIG_MPLS) static int mplsip_rcv(struct sk_buff *skb) { return sit_tunnel_rcv(skb, IPPROTO_MPLS); } #endif /* * If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function * stores the embedded IPv4 address in v4dst and returns true. */ static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, __be32 *v4dst) { #ifdef CONFIG_IPV6_SIT_6RD if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix, tunnel->ip6rd.prefixlen)) { unsigned int pbw0, pbi0; int pbi1; u32 d; pbw0 = tunnel->ip6rd.prefixlen >> 5; pbi0 = tunnel->ip6rd.prefixlen & 0x1f; d = tunnel->ip6rd.relay_prefixlen < 32 ? (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >> tunnel->ip6rd.relay_prefixlen : 0; pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen; if (pbi1 > 0) d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >> (32 - pbi1); *v4dst = tunnel->ip6rd.relay_prefix | htonl(d); return true; } #else if (v6dst->s6_addr16[0] == htons(0x2002)) { /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */ memcpy(v4dst, &v6dst->s6_addr16[1], 4); return true; } #endif return false; } static inline __be32 try_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst) { __be32 dst = 0; check_6rd(tunnel, v6dst, &dst); return dst; } /* * This function assumes it is being called from dev_queue_xmit() * and that skb is filled properly by that function. */ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; const struct ipv6hdr *iph6 = ipv6_hdr(skb); u8 tos = tunnel->parms.iph.tos; __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ struct net_device *tdev; /* Device to other host */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst = tiph->daddr; struct flowi4 fl4; int mtu; const struct in6_addr *addr6; int addr_type; u8 ttl; u8 protocol = IPPROTO_IPV6; int t_hlen = tunnel->hlen + sizeof(struct iphdr); if (tos == 1) tos = ipv6_get_dsfield(iph6); /* ISATAP (RFC4214) - must come before 6to4 */ if (dev->priv_flags & IFF_ISATAP) { struct neighbour *neigh = NULL; bool do_tx_error = false; if (skb_dst(skb)) neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (!neigh) { net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if ((addr_type & IPV6_ADDR_UNICAST) && ipv6_addr_is_isatap(addr6)) dst = addr6->s6_addr32[3]; else do_tx_error = true; neigh_release(neigh); if (do_tx_error) goto tx_error; } if (!dst) dst = try_6rd(tunnel, &iph6->daddr); if (!dst) { struct neighbour *neigh = NULL; bool do_tx_error = false; if (skb_dst(skb)) neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (!neigh) { net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { addr6 = &ipv6_hdr(skb)->daddr; addr_type = ipv6_addr_type(addr6); } if ((addr_type & IPV6_ADDR_COMPATv4) != 0) dst = addr6->s6_addr32[3]; else do_tx_error = true; neigh_release(neigh); if (do_tx_error) goto tx_error; } flowi4_init_output(&fl4, tunnel->parms.link, tunnel->fwmark, RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPV6, 0, dst, tiph->saddr, 0, 0, sock_net_uid(tunnel->net, NULL)); rt = dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr); if (!rt) { rt = ip_route_output_flow(tunnel->net, &fl4, NULL); if (IS_ERR(rt)) { dev->stats.tx_carrier_errors++; goto tx_error_icmp; } dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr); } if (rt->rt_type != RTN_UNICAST) { ip_rt_put(rt); dev->stats.tx_carrier_errors++; goto tx_error_icmp; } tdev = rt->dst.dev; if (tdev == dev) { ip_rt_put(rt); dev->stats.collisions++; goto tx_error; } if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) { ip_rt_put(rt); goto tx_error; } if (df) { mtu = dst_mtu(&rt->dst) - t_hlen; if (mtu < IPV4_MIN_MTU) { dev->stats.collisions++; ip_rt_put(rt); goto tx_error; } if (mtu < IPV6_MIN_MTU) { mtu = IPV6_MIN_MTU; df = 0; } if (tunnel->parms.iph.daddr) skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len > mtu && !skb_is_gso(skb)) { icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ip_rt_put(rt); goto tx_error; } } if (tunnel->err_count > 0) { if (time_before(jiffies, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; dst_link_failure(skb); } else tunnel->err_count = 0; } /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom = LL_RESERVED_SPACE(tdev) + t_hlen; if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); dev->stats.tx_dropped++; kfree_skb(skb); return NETDEV_TX_OK; } if (skb->sk) skb_set_owner_w(new_skb, skb->sk); dev_kfree_skb(skb); skb = new_skb; iph6 = ipv6_hdr(skb); } ttl = tiph->ttl; if (ttl == 0) ttl = iph6->hop_limit; tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) { ip_rt_put(rt); goto tx_error; } skb_set_inner_ipproto(skb, IPPROTO_IPV6); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: kfree_skb(skb); dev->stats.tx_errors++; return NETDEV_TX_OK; } static netdev_tx_t sit_tunnel_xmit__(struct sk_buff *skb, struct net_device *dev, u8 ipproto) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) goto tx_error; skb_set_inner_ipproto(skb, ipproto); ip_tunnel_xmit(skb, dev, tiph, ipproto); return NETDEV_TX_OK; tx_error: kfree_skb(skb); dev->stats.tx_errors++; return NETDEV_TX_OK; } static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { if (!pskb_inet_may_pull(skb)) goto tx_err; switch (skb->protocol) { case htons(ETH_P_IP): sit_tunnel_xmit__(skb, dev, IPPROTO_IPIP); break; case htons(ETH_P_IPV6): ipip6_tunnel_xmit(skb, dev); break; #if IS_ENABLED(CONFIG_MPLS) case htons(ETH_P_MPLS_UC): sit_tunnel_xmit__(skb, dev, IPPROTO_MPLS); break; #endif default: goto tx_err; } return NETDEV_TX_OK; tx_err: dev->stats.tx_errors++; kfree_skb(skb); return NETDEV_TX_OK; } static void ipip6_tunnel_bind_dev(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); struct net_device *tdev = NULL; int hlen = LL_MAX_HEADER; const struct iphdr *iph; struct flowi4 fl4; iph = &tunnel->parms.iph; if (iph->daddr) { struct rtable *rt = ip_route_output_ports(tunnel->net, &fl4, NULL, iph->daddr, iph->saddr, 0, 0, IPPROTO_IPV6, RT_TOS(iph->tos), tunnel->parms.link); if (!IS_ERR(rt)) { tdev = rt->dst.dev; ip_rt_put(rt); } dev->flags |= IFF_POINTOPOINT; } if (!tdev && tunnel->parms.link) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); if (tdev && !netif_is_l3_master(tdev)) { int mtu; mtu = tdev->mtu - t_hlen; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; WRITE_ONCE(dev->mtu, mtu); hlen = tdev->hard_header_len + tdev->needed_headroom; } dev->needed_headroom = t_hlen + hlen; } static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p, __u32 fwmark) { struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); ipip6_tunnel_unlink(sitn, t); synchronize_net(); t->parms.iph.saddr = p->iph.saddr; t->parms.iph.daddr = p->iph.daddr; memcpy(t->dev->dev_addr, &p->iph.saddr, 4); memcpy(t->dev->broadcast, &p->iph.daddr, 4); ipip6_tunnel_link(sitn, t); t->parms.iph.ttl = p->iph.ttl; t->parms.iph.tos = p->iph.tos; t->parms.iph.frag_off = p->iph.frag_off; if (t->parms.link != p->link || t->fwmark != fwmark) { t->parms.link = p->link; t->fwmark = fwmark; ipip6_tunnel_bind_dev(t->dev); } dst_cache_reset(&t->dst_cache); netdev_state_change(t->dev); } #ifdef CONFIG_IPV6_SIT_6RD static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, struct ip_tunnel_6rd *ip6rd) { struct in6_addr prefix; __be32 relay_prefix; if (ip6rd->relay_prefixlen > 32 || ip6rd->prefixlen + (32 - ip6rd->relay_prefixlen) > 64) return -EINVAL; ipv6_addr_prefix(&prefix, &ip6rd->prefix, ip6rd->prefixlen); if (!ipv6_addr_equal(&prefix, &ip6rd->prefix)) return -EINVAL; if (ip6rd->relay_prefixlen) relay_prefix = ip6rd->relay_prefix & htonl(0xffffffffUL << (32 - ip6rd->relay_prefixlen)); else relay_prefix = 0; if (relay_prefix != ip6rd->relay_prefix) return -EINVAL; t->ip6rd.prefix = prefix; t->ip6rd.relay_prefix = relay_prefix; t->ip6rd.prefixlen = ip6rd->prefixlen; t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen; dst_cache_reset(&t->dst_cache); netdev_state_change(t->dev); return 0; } static int ipip6_tunnel_get6rd(struct net_device *dev, struct ip_tunnel_parm __user *data) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_6rd ip6rd; struct ip_tunnel_parm p; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { if (copy_from_user(&p, data, sizeof(p))) return -EFAULT; t = ipip6_tunnel_locate(t->net, &p, 0); } if (!t) t = netdev_priv(dev); ip6rd.prefix = t->ip6rd.prefix; ip6rd.relay_prefix = t->ip6rd.relay_prefix; ip6rd.prefixlen = t->ip6rd.prefixlen; ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen; if (copy_to_user(data, &ip6rd, sizeof(ip6rd))) return -EFAULT; return 0; } static int ipip6_tunnel_6rdctl(struct net_device *dev, struct ip_tunnel_6rd __user *data, int cmd) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_6rd ip6rd; int err; if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ip6rd, data, sizeof(ip6rd))) return -EFAULT; if (cmd != SIOCDEL6RD) { err = ipip6_tunnel_update_6rd(t, &ip6rd); if (err < 0) return err; } else ipip6_tunnel_clone_6rd(dev, dev_to_sit_net(dev)); return 0; } #endif /* CONFIG_IPV6_SIT_6RD */ static bool ipip6_valid_ip_proto(u8 ipproto) { return ipproto == IPPROTO_IPV6 || ipproto == IPPROTO_IPIP || #if IS_ENABLED(CONFIG_MPLS) ipproto == IPPROTO_MPLS || #endif ipproto == 0; } static int __ipip6_tunnel_ioctl_validate(struct net *net, struct ip_tunnel_parm *p) { if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (!ipip6_valid_ip_proto(p->iph.protocol)) return -EINVAL; if (p->iph.version != 4 || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF))) return -EINVAL; if (p->iph.ttl) p->iph.frag_off |= htons(IP_DF); return 0; } static int ipip6_tunnel_get(struct net_device *dev, struct ip_tunnel_parm *p) { struct ip_tunnel *t = netdev_priv(dev); if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) t = ipip6_tunnel_locate(t->net, p, 0); if (!t) t = netdev_priv(dev); memcpy(p, &t->parms, sizeof(*p)); return 0; } static int ipip6_tunnel_add(struct net_device *dev, struct ip_tunnel_parm *p) { struct ip_tunnel *t = netdev_priv(dev); int err; err = __ipip6_tunnel_ioctl_validate(t->net, p); if (err) return err; t = ipip6_tunnel_locate(t->net, p, 1); if (!t) return -ENOBUFS; return 0; } static int ipip6_tunnel_change(struct net_device *dev, struct ip_tunnel_parm *p) { struct ip_tunnel *t = netdev_priv(dev); int err; err = __ipip6_tunnel_ioctl_validate(t->net, p); if (err) return err; t = ipip6_tunnel_locate(t->net, p, 0); if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { if (!t) return -ENOENT; } else { if (t) { if (t->dev != dev) return -EEXIST; } else { if (((dev->flags & IFF_POINTOPOINT) && !p->iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p->iph.daddr)) return -EINVAL; t = netdev_priv(dev); } ipip6_tunnel_update(t, p, t->fwmark); } return 0; } static int ipip6_tunnel_del(struct net_device *dev, struct ip_tunnel_parm *p) { struct ip_tunnel *t = netdev_priv(dev); if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { t = ipip6_tunnel_locate(t->net, p, 0); if (!t) return -ENOENT; if (t == netdev_priv(dev_to_sit_net(dev)->fb_tunnel_dev)) return -EPERM; dev = t->dev; } unregister_netdevice(dev); return 0; } static int ipip6_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) { switch (cmd) { case SIOCGETTUNNEL: return ipip6_tunnel_get(dev, p); case SIOCADDTUNNEL: return ipip6_tunnel_add(dev, p); case SIOCCHGTUNNEL: return ipip6_tunnel_change(dev, p); case SIOCDELTUNNEL: return ipip6_tunnel_del(dev, p); default: return -EINVAL; } } static int ipip6_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { switch (cmd) { case SIOCGETTUNNEL: case SIOCADDTUNNEL: case SIOCCHGTUNNEL: case SIOCDELTUNNEL: return ip_tunnel_siocdevprivate(dev, ifr, data, cmd); case SIOCGETPRL: return ipip6_tunnel_get_prl(dev, data); case SIOCADDPRL: case SIOCDELPRL: case SIOCCHGPRL: return ipip6_tunnel_prl_ctl(dev, data, cmd); #ifdef CONFIG_IPV6_SIT_6RD case SIOCGET6RD: return ipip6_tunnel_get6rd(dev, data); case SIOCADD6RD: case SIOCCHG6RD: case SIOCDEL6RD: return ipip6_tunnel_6rdctl(dev, data, cmd); #endif default: return -EINVAL; } } static const struct net_device_ops ipip6_netdev_ops = { .ndo_init = ipip6_tunnel_init, .ndo_uninit = ipip6_tunnel_uninit, .ndo_start_xmit = sit_tunnel_xmit, .ndo_siocdevprivate = ipip6_tunnel_siocdevprivate, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipip6_tunnel_ctl, }; static void ipip6_dev_free(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); dst_cache_destroy(&tunnel->dst_cache); free_percpu(dev->tstats); } #define SIT_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_GSO_SOFTWARE | \ NETIF_F_HW_CSUM) static void ipip6_tunnel_setup(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->netdev_ops = &ipip6_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = ipip6_dev_free; dev->type = ARPHRD_SIT; dev->mtu = ETH_DATA_LEN - t_hlen; dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - t_hlen; dev->flags = IFF_NOARP; netif_keep_dst(dev); dev->addr_len = 4; dev->features |= NETIF_F_LLTX; dev->features |= SIT_FEATURES; dev->hw_features |= SIT_FEATURES; } static int ipip6_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); int err; tunnel->dev = dev; tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); ipip6_tunnel_bind_dev(dev); dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (err) { free_percpu(dev->tstats); dev->tstats = NULL; return err; } dev_hold(dev); return 0; } static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); iph->version = 4; iph->protocol = IPPROTO_IPV6; iph->ihl = 5; iph->ttl = 64; rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); } static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { u8 proto; if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (!ipip6_valid_ip_proto(proto)) return -EINVAL; return 0; } static void ipip6_netlink_parms(struct nlattr *data[], struct ip_tunnel_parm *parms, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); parms->iph.version = 4; parms->iph.protocol = IPPROTO_IPV6; parms->iph.ihl = 5; parms->iph.ttl = 64; if (!data) return; if (data[IFLA_IPTUN_LINK]) parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); if (data[IFLA_IPTUN_LOCAL]) parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]); if (data[IFLA_IPTUN_REMOTE]) parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]); if (data[IFLA_IPTUN_TTL]) { parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]); if (parms->iph.ttl) parms->iph.frag_off = htons(IP_DF); } if (data[IFLA_IPTUN_TOS]) parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]); if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) parms->iph.frag_off = htons(IP_DF); if (data[IFLA_IPTUN_FLAGS]) parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); if (data[IFLA_IPTUN_PROTO]) parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (data[IFLA_IPTUN_FWMARK]) *fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } /* This function returns true when ENCAP attributes are present in the nl msg */ static bool ipip6_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *ipencap) { bool ret = false; memset(ipencap, 0, sizeof(*ipencap)); if (!data) return ret; if (data[IFLA_IPTUN_ENCAP_TYPE]) { ret = true; ipencap->type = nla_get_u16(data[IFLA_IPTUN_ENCAP_TYPE]); } if (data[IFLA_IPTUN_ENCAP_FLAGS]) { ret = true; ipencap->flags = nla_get_u16(data[IFLA_IPTUN_ENCAP_FLAGS]); } if (data[IFLA_IPTUN_ENCAP_SPORT]) { ret = true; ipencap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]); } if (data[IFLA_IPTUN_ENCAP_DPORT]) { ret = true; ipencap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]); } return ret; } #ifdef CONFIG_IPV6_SIT_6RD /* This function returns true when 6RD attributes are present in the nl msg */ static bool ipip6_netlink_6rd_parms(struct nlattr *data[], struct ip_tunnel_6rd *ip6rd) { bool ret = false; memset(ip6rd, 0, sizeof(*ip6rd)); if (!data) return ret; if (data[IFLA_IPTUN_6RD_PREFIX]) { ret = true; ip6rd->prefix = nla_get_in6_addr(data[IFLA_IPTUN_6RD_PREFIX]); } if (data[IFLA_IPTUN_6RD_RELAY_PREFIX]) { ret = true; ip6rd->relay_prefix = nla_get_be32(data[IFLA_IPTUN_6RD_RELAY_PREFIX]); } if (data[IFLA_IPTUN_6RD_PREFIXLEN]) { ret = true; ip6rd->prefixlen = nla_get_u16(data[IFLA_IPTUN_6RD_PREFIXLEN]); } if (data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]) { ret = true; ip6rd->relay_prefixlen = nla_get_u16(data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]); } return ret; } #endif static int ipip6_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip_tunnel *nt; struct ip_tunnel_encap ipencap; #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; #endif int err; nt = netdev_priv(dev); if (ipip6_netlink_encap_parms(data, &ipencap)) { err = ip_tunnel_encap_setup(nt, &ipencap); if (err < 0) return err; } ipip6_netlink_parms(data, &nt->parms, &nt->fwmark); if (ipip6_tunnel_locate(net, &nt->parms, 0)) return -EEXIST; err = ipip6_tunnel_create(dev); if (err < 0) return err; if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); if (mtu >= IPV6_MIN_MTU && mtu <= IP6_MAX_MTU - dev->hard_header_len) dev->mtu = mtu; } #ifdef CONFIG_IPV6_SIT_6RD if (ipip6_netlink_6rd_parms(data, &ip6rd)) { err = ipip6_tunnel_update_6rd(nt, &ip6rd); if (err < 0) unregister_netdevice_queue(dev, NULL); } #endif return err; } static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; #endif __u32 fwmark = t->fwmark; int err; if (dev == sitn->fb_tunnel_dev) return -EINVAL; if (ipip6_netlink_encap_parms(data, &ipencap)) { err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } ipip6_netlink_parms(data, &p, &fwmark); if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) return -EINVAL; t = ipip6_tunnel_locate(net, &p, 0); if (t) { if (t->dev != dev) return -EEXIST; } else t = netdev_priv(dev); ipip6_tunnel_update(t, &p, fwmark); #ifdef CONFIG_IPV6_SIT_6RD if (ipip6_netlink_6rd_parms(data, &ip6rd)) return ipip6_tunnel_update_6rd(t, &ip6rd); #endif return 0; } static size_t ipip6_get_size(const struct net_device *dev) { return /* IFLA_IPTUN_LINK */ nla_total_size(4) + /* IFLA_IPTUN_LOCAL */ nla_total_size(4) + /* IFLA_IPTUN_REMOTE */ nla_total_size(4) + /* IFLA_IPTUN_TTL */ nla_total_size(1) + /* IFLA_IPTUN_TOS */ nla_total_size(1) + /* IFLA_IPTUN_PMTUDISC */ nla_total_size(1) + /* IFLA_IPTUN_FLAGS */ nla_total_size(2) + /* IFLA_IPTUN_PROTO */ nla_total_size(1) + #ifdef CONFIG_IPV6_SIT_6RD /* IFLA_IPTUN_6RD_PREFIX */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_IPTUN_6RD_RELAY_PREFIX */ nla_total_size(4) + /* IFLA_IPTUN_6RD_PREFIXLEN */ nla_total_size(2) + /* IFLA_IPTUN_6RD_RELAY_PREFIXLEN */ nla_total_size(2) + #endif /* IFLA_IPTUN_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_IPTUN_FWMARK */ nla_total_size(4) + 0; } static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_parm *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, !!(parm->iph.frag_off & htons(IP_DF))) || nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) || nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags) || nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark)) goto nla_put_failure; #ifdef CONFIG_IPV6_SIT_6RD if (nla_put_in6_addr(skb, IFLA_IPTUN_6RD_PREFIX, &tunnel->ip6rd.prefix) || nla_put_in_addr(skb, IFLA_IPTUN_6RD_RELAY_PREFIX, tunnel->ip6rd.relay_prefix) || nla_put_u16(skb, IFLA_IPTUN_6RD_PREFIXLEN, tunnel->ip6rd.prefixlen) || nla_put_u16(skb, IFLA_IPTUN_6RD_RELAY_PREFIXLEN, tunnel->ip6rd.relay_prefixlen)) goto nla_put_failure; #endif if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, tunnel->encap.type) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, tunnel->encap.sport) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, tunnel->encap.dport) || nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, tunnel->encap.flags)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, [IFLA_IPTUN_LOCAL] = { .type = NLA_U32 }, [IFLA_IPTUN_REMOTE] = { .type = NLA_U32 }, [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, [IFLA_IPTUN_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, #ifdef CONFIG_IPV6_SIT_6RD [IFLA_IPTUN_6RD_PREFIX] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_6RD_RELAY_PREFIX] = { .type = NLA_U32 }, [IFLA_IPTUN_6RD_PREFIXLEN] = { .type = NLA_U16 }, [IFLA_IPTUN_6RD_RELAY_PREFIXLEN] = { .type = NLA_U16 }, #endif [IFLA_IPTUN_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_FWMARK] = { .type = NLA_U32 }, }; static void ipip6_dellink(struct net_device *dev, struct list_head *head) { struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); if (dev != sitn->fb_tunnel_dev) unregister_netdevice_queue(dev, head); } static struct rtnl_link_ops sit_link_ops __read_mostly = { .kind = "sit", .maxtype = IFLA_IPTUN_MAX, .policy = ipip6_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipip6_tunnel_setup, .validate = ipip6_validate, .newlink = ipip6_newlink, .changelink = ipip6_changelink, .get_size = ipip6_get_size, .fill_info = ipip6_fill_info, .dellink = ipip6_dellink, .get_link_net = ip_tunnel_get_link_net, }; static struct xfrm_tunnel sit_handler __read_mostly = { .handler = ipip6_rcv, .err_handler = ipip6_err, .priority = 1, }; static struct xfrm_tunnel ipip_handler __read_mostly = { .handler = ipip_rcv, .err_handler = ipip6_err, .priority = 2, }; #if IS_ENABLED(CONFIG_MPLS) static struct xfrm_tunnel mplsip_handler __read_mostly = { .handler = mplsip_rcv, .err_handler = ipip6_err, .priority = 2, }; #endif static void __net_exit sit_destroy_tunnels(struct net *net, struct list_head *head) { struct sit_net *sitn = net_generic(net, sit_net_id); struct net_device *dev, *aux; int prio; for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &sit_link_ops) unregister_netdevice_queue(dev, head); for (prio = 0; prio < 4; prio++) { int h; for (h = 0; h < (prio ? IP6_SIT_HASH_SIZE : 1); h++) { struct ip_tunnel *t; t = rtnl_dereference(sitn->tunnels[prio][h]); while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, head); t = rtnl_dereference(t->next); } } } } static int __net_init sit_init_net(struct net *net) { struct sit_net *sitn = net_generic(net, sit_net_id); struct ip_tunnel *t; int err; sitn->tunnels[0] = sitn->tunnels_wc; sitn->tunnels[1] = sitn->tunnels_l; sitn->tunnels[2] = sitn->tunnels_r; sitn->tunnels[3] = sitn->tunnels_r_l; if (!net_has_fallback_tunnels(net)) return 0; sitn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0", NET_NAME_UNKNOWN, ipip6_tunnel_setup); if (!sitn->fb_tunnel_dev) { err = -ENOMEM; goto err_alloc_dev; } dev_net_set(sitn->fb_tunnel_dev, net); sitn->fb_tunnel_dev->rtnl_link_ops = &sit_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; err = register_netdev(sitn->fb_tunnel_dev); if (err) goto err_reg_dev; ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn); ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); t = netdev_priv(sitn->fb_tunnel_dev); strcpy(t->parms.name, sitn->fb_tunnel_dev->name); return 0; err_reg_dev: free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: return err; } static void __net_exit sit_exit_batch_net(struct list_head *net_list) { LIST_HEAD(list); struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) sit_destroy_tunnels(net, &list); unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations sit_net_ops = { .init = sit_init_net, .exit_batch = sit_exit_batch_net, .id = &sit_net_id, .size = sizeof(struct sit_net), }; static void __exit sit_cleanup(void) { rtnl_link_unregister(&sit_link_ops); xfrm4_tunnel_deregister(&sit_handler, AF_INET6); xfrm4_tunnel_deregister(&ipip_handler, AF_INET); #if IS_ENABLED(CONFIG_MPLS) xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); #endif unregister_pernet_device(&sit_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ } static int __init sit_init(void) { int err; pr_info("IPv6, IPv4 and MPLS over IPv4 tunneling driver\n"); err = register_pernet_device(&sit_net_ops); if (err < 0) return err; err = xfrm4_tunnel_register(&sit_handler, AF_INET6); if (err < 0) { pr_info("%s: can't register ip6ip4\n", __func__); goto xfrm_tunnel_failed; } err = xfrm4_tunnel_register(&ipip_handler, AF_INET); if (err < 0) { pr_info("%s: can't register ip4ip4\n", __func__); goto xfrm_tunnel4_failed; } #if IS_ENABLED(CONFIG_MPLS) err = xfrm4_tunnel_register(&mplsip_handler, AF_MPLS); if (err < 0) { pr_info("%s: can't register mplsip\n", __func__); goto xfrm_tunnel_mpls_failed; } #endif err = rtnl_link_register(&sit_link_ops); if (err < 0) goto rtnl_link_failed; out: return err; rtnl_link_failed: #if IS_ENABLED(CONFIG_MPLS) xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); xfrm_tunnel_mpls_failed: #endif xfrm4_tunnel_deregister(&ipip_handler, AF_INET); xfrm_tunnel4_failed: xfrm4_tunnel_deregister(&sit_handler, AF_INET6); xfrm_tunnel_failed: unregister_pernet_device(&sit_net_ops); goto out; } module_init(sit_init); module_exit(sit_cleanup); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("sit"); MODULE_ALIAS_NETDEV("sit0"); |
| 5945 5951 5953 5957 5948 209 4287 208 4293 4289 4290 5 111 111 1 1 5477 5485 5480 4122 2 1 2125 5479 85 14 85 90 517 147 517 562 808 811 423 811 811 337 90 562 601 1 769 270 600 602 601 263 264 1824 12 1825 1824 1823 4188 1 229 4165 18880 4239 4239 4239 4213 13 56 57 57 1772 4191 4188 4188 4190 1772 57 19845 19812 10 10 10 1 1 19819 19859 38 38 50 4313 4344 4292 4287 4291 4292 4292 4289 5 5425 19 49 1 17 2 4284 1807 49 4283 200 4117 4119 4118 4285 126 98 31 140 122 22 10 12 9 9 4 4 4 3 4 1 3 17 11 5 4 4 2 13 11 2 2 2 2 12 10 6 2 1 4 4073 4066 242 10 5599 5600 1928 1927 3 220 219 2537 2537 2537 28 110 4200 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux Socket Filter - Kernel level socket filtering * * Based on the design of the Berkeley Packet Filter. The new * internal format has been designed by PLUMgrid: * * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com * * Authors: * * Jay Schulist <jschlst@samba.org> * Alexei Starovoitov <ast@plumgrid.com> * Daniel Borkmann <dborkman@redhat.com> * * Andi Kleen - Fix a few bad bugs and races. * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <uapi/linux/btf.h> #include <linux/filter.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/random.h> #include <linux/moduleloader.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/objtool.h> #include <linux/rbtree_latch.h> #include <linux/kallsyms.h> #include <linux/rcupdate.h> #include <linux/perf_event.h> #include <linux/extable.h> #include <linux/log2.h> #include <linux/nospec.h> #include <asm/barrier.h> #include <asm/unaligned.h> /* Registers */ #define BPF_R0 regs[BPF_REG_0] #define BPF_R1 regs[BPF_REG_1] #define BPF_R2 regs[BPF_REG_2] #define BPF_R3 regs[BPF_REG_3] #define BPF_R4 regs[BPF_REG_4] #define BPF_R5 regs[BPF_REG_5] #define BPF_R6 regs[BPF_REG_6] #define BPF_R7 regs[BPF_REG_7] #define BPF_R8 regs[BPF_REG_8] #define BPF_R9 regs[BPF_REG_9] #define BPF_R10 regs[BPF_REG_10] /* Named registers */ #define DST regs[insn->dst_reg] #define SRC regs[insn->src_reg] #define FP regs[BPF_REG_FP] #define AX regs[BPF_REG_AX] #define ARG1 regs[BPF_REG_ARG1] #define CTX regs[BPF_REG_CTX] #define IMM insn->imm /* No hurry in this branch * * Exported for the bpf jit load helper. */ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size) { u8 *ptr = NULL; if (k >= SKF_NET_OFF) { ptr = skb_network_header(skb) + k - SKF_NET_OFF; } else if (k >= SKF_LL_OFF) { if (unlikely(!skb_mac_header_was_set(skb))) return NULL; ptr = skb_mac_header(skb) + k - SKF_LL_OFF; } if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; return NULL; } struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; struct bpf_prog_aux *aux; struct bpf_prog *fp; size = round_up(size, PAGE_SIZE); fp = __vmalloc(size, gfp_flags); if (fp == NULL) return NULL; aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT | gfp_extra_flags); if (aux == NULL) { vfree(fp); return NULL; } fp->active = alloc_percpu_gfp(int, GFP_KERNEL_ACCOUNT | gfp_extra_flags); if (!fp->active) { vfree(fp); kfree(aux); return NULL; } fp->pages = size / PAGE_SIZE; fp->aux = aux; fp->aux->prog = fp; fp->jit_requested = ebpf_jit_enabled(); INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode); mutex_init(&fp->aux->used_maps_mutex); mutex_init(&fp->aux->dst_mutex); return fp; } struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *prog; int cpu; prog = bpf_prog_alloc_no_stats(size, gfp_extra_flags); if (!prog) return NULL; prog->stats = alloc_percpu_gfp(struct bpf_prog_stats, gfp_flags); if (!prog->stats) { free_percpu(prog->active); kfree(prog->aux); vfree(prog); return NULL; } for_each_possible_cpu(cpu) { struct bpf_prog_stats *pstats; pstats = per_cpu_ptr(prog->stats, cpu); u64_stats_init(&pstats->syncp); } return prog; } EXPORT_SYMBOL_GPL(bpf_prog_alloc); int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog) { if (!prog->aux->nr_linfo || !prog->jit_requested) return 0; prog->aux->jited_linfo = kvcalloc(prog->aux->nr_linfo, sizeof(*prog->aux->jited_linfo), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!prog->aux->jited_linfo) return -ENOMEM; return 0; } void bpf_prog_jit_attempt_done(struct bpf_prog *prog) { if (prog->aux->jited_linfo && (!prog->jited || !prog->aux->jited_linfo[0])) { kvfree(prog->aux->jited_linfo); prog->aux->jited_linfo = NULL; } kfree(prog->aux->kfunc_tab); prog->aux->kfunc_tab = NULL; } /* The jit engine is responsible to provide an array * for insn_off to the jited_off mapping (insn_to_jit_off). * * The idx to this array is the insn_off. Hence, the insn_off * here is relative to the prog itself instead of the main prog. * This array has one entry for each xlated bpf insn. * * jited_off is the byte off to the last byte of the jited insn. * * Hence, with * insn_start: * The first bpf insn off of the prog. The insn off * here is relative to the main prog. * e.g. if prog is a subprog, insn_start > 0 * linfo_idx: * The prog's idx to prog->aux->linfo and jited_linfo * * jited_linfo[linfo_idx] = prog->bpf_func * * For i > linfo_idx, * * jited_linfo[i] = prog->bpf_func + * insn_to_jit_off[linfo[i].insn_off - insn_start - 1] */ void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const u32 *insn_to_jit_off) { u32 linfo_idx, insn_start, insn_end, nr_linfo, i; const struct bpf_line_info *linfo; void **jited_linfo; if (!prog->aux->jited_linfo) /* Userspace did not provide linfo */ return; linfo_idx = prog->aux->linfo_idx; linfo = &prog->aux->linfo[linfo_idx]; insn_start = linfo[0].insn_off; insn_end = insn_start + prog->len; jited_linfo = &prog->aux->jited_linfo[linfo_idx]; jited_linfo[0] = prog->bpf_func; nr_linfo = prog->aux->nr_linfo - linfo_idx; for (i = 1; i < nr_linfo && linfo[i].insn_off < insn_end; i++) /* The verifier ensures that linfo[i].insn_off is * strictly increasing */ jited_linfo[i] = prog->bpf_func + insn_to_jit_off[linfo[i].insn_off - insn_start - 1]; } struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; u32 pages; size = round_up(size, PAGE_SIZE); pages = size / PAGE_SIZE; if (pages <= fp_old->pages) return fp_old; fp = __vmalloc(size, gfp_flags); if (fp) { memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); fp->pages = pages; fp->aux->prog = fp; /* We keep fp->aux from fp_old around in the new * reallocated structure. */ fp_old->aux = NULL; fp_old->stats = NULL; fp_old->active = NULL; __bpf_prog_free(fp_old); } return fp; } void __bpf_prog_free(struct bpf_prog *fp) { if (fp->aux) { mutex_destroy(&fp->aux->used_maps_mutex); mutex_destroy(&fp->aux->dst_mutex); kfree(fp->aux->poke_tab); kfree(fp->aux); } free_percpu(fp->stats); free_percpu(fp->active); vfree(fp); } int bpf_prog_calc_tag(struct bpf_prog *fp) { const u32 bits_offset = SHA1_BLOCK_SIZE - sizeof(__be64); u32 raw_size = bpf_prog_tag_scratch_size(fp); u32 digest[SHA1_DIGEST_WORDS]; u32 ws[SHA1_WORKSPACE_WORDS]; u32 i, bsize, psize, blocks; struct bpf_insn *dst; bool was_ld_map; u8 *raw, *todo; __be32 *result; __be64 *bits; raw = vmalloc(raw_size); if (!raw) return -ENOMEM; sha1_init(digest); memset(ws, 0, sizeof(ws)); /* We need to take out the map fd for the digest calculation * since they are unstable from user space side. */ dst = (void *)raw; for (i = 0, was_ld_map = false; i < fp->len; i++) { dst[i] = fp->insnsi[i]; if (!was_ld_map && dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) && (dst[i].src_reg == BPF_PSEUDO_MAP_FD || dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) { was_ld_map = true; dst[i].imm = 0; } else if (was_ld_map && dst[i].code == 0 && dst[i].dst_reg == 0 && dst[i].src_reg == 0 && dst[i].off == 0) { was_ld_map = false; dst[i].imm = 0; } else { was_ld_map = false; } } psize = bpf_prog_insn_size(fp); memset(&raw[psize], 0, raw_size - psize); raw[psize++] = 0x80; bsize = round_up(psize, SHA1_BLOCK_SIZE); blocks = bsize / SHA1_BLOCK_SIZE; todo = raw; if (bsize - psize >= sizeof(__be64)) { bits = (__be64 *)(todo + bsize - sizeof(__be64)); } else { bits = (__be64 *)(todo + bsize + bits_offset); blocks++; } *bits = cpu_to_be64((psize - 1) << 3); while (blocks--) { sha1_transform(digest, todo, ws); todo += SHA1_BLOCK_SIZE; } result = (__force __be32 *)digest; for (i = 0; i < SHA1_DIGEST_WORDS; i++) result[i] = cpu_to_be32(digest[i]); memcpy(fp->tag, result, sizeof(fp->tag)); vfree(raw); return 0; } static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { const s64 imm_min = S32_MIN, imm_max = S32_MAX; s32 delta = end_new - end_old; s64 imm = insn->imm; if (curr < pos && curr + imm + 1 >= end_old) imm += delta; else if (curr >= end_new && curr + imm + 1 < end_new) imm -= delta; if (imm < imm_min || imm > imm_max) return -ERANGE; if (!probe_pass) insn->imm = imm; return 0; } static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { const s32 off_min = S16_MIN, off_max = S16_MAX; s32 delta = end_new - end_old; s32 off = insn->off; if (curr < pos && curr + off + 1 >= end_old) off += delta; else if (curr >= end_new && curr + off + 1 < end_new) off -= delta; if (off < off_min || off > off_max) return -ERANGE; if (!probe_pass) insn->off = off; return 0; } static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old, s32 end_new, const bool probe_pass) { u32 i, insn_cnt = prog->len + (probe_pass ? end_new - end_old : 0); struct bpf_insn *insn = prog->insnsi; int ret = 0; for (i = 0; i < insn_cnt; i++, insn++) { u8 code; /* In the probing pass we still operate on the original, * unpatched image in order to check overflows before we * do any other adjustments. Therefore skip the patchlet. */ if (probe_pass && i == pos) { i = end_new; insn = prog->insnsi + end_old; } if (bpf_pseudo_func(insn)) { ret = bpf_adj_delta_to_imm(insn, pos, end_old, end_new, i, probe_pass); if (ret) return ret; continue; } code = insn->code; if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) || BPF_OP(code) == BPF_EXIT) continue; /* Adjust offset of jmps if we cross patch boundaries. */ if (BPF_OP(code) == BPF_CALL) { if (insn->src_reg != BPF_PSEUDO_CALL) continue; ret = bpf_adj_delta_to_imm(insn, pos, end_old, end_new, i, probe_pass); } else { ret = bpf_adj_delta_to_off(insn, pos, end_old, end_new, i, probe_pass); } if (ret) break; } return ret; } static void bpf_adj_linfo(struct bpf_prog *prog, u32 off, u32 delta) { struct bpf_line_info *linfo; u32 i, nr_linfo; nr_linfo = prog->aux->nr_linfo; if (!nr_linfo || !delta) return; linfo = prog->aux->linfo; for (i = 0; i < nr_linfo; i++) if (off < linfo[i].insn_off) break; /* Push all off < linfo[i].insn_off by delta */ for (; i < nr_linfo; i++) linfo[i].insn_off += delta; } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len) { u32 insn_adj_cnt, insn_rest, insn_delta = len - 1; const u32 cnt_max = S16_MAX; struct bpf_prog *prog_adj; int err; /* Since our patchlet doesn't expand the image, we're done. */ if (insn_delta == 0) { memcpy(prog->insnsi + off, patch, sizeof(*patch)); return prog; } insn_adj_cnt = prog->len + insn_delta; /* Reject anything that would potentially let the insn->off * target overflow when we have excessive program expansions. * We need to probe here before we do any reallocation where * we afterwards may not fail anymore. */ if (insn_adj_cnt > cnt_max && (err = bpf_adj_branches(prog, off, off + 1, off + len, true))) return ERR_PTR(err); /* Several new instructions need to be inserted. Make room * for them. Likely, there's no need for a new allocation as * last page could have large enough tailroom. */ prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt), GFP_USER); if (!prog_adj) return ERR_PTR(-ENOMEM); prog_adj->len = insn_adj_cnt; /* Patching happens in 3 steps: * * 1) Move over tail of insnsi from next instruction onwards, * so we can patch the single target insn with one or more * new ones (patching is always from 1 to n insns, n > 0). * 2) Inject new instructions at the target location. * 3) Adjust branch offsets if necessary. */ insn_rest = insn_adj_cnt - off - len; memmove(prog_adj->insnsi + off + len, prog_adj->insnsi + off + 1, sizeof(*patch) * insn_rest); memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len); /* We are guaranteed to not fail at this point, otherwise * the ship has sailed to reverse to the original state. An * overflow cannot happen at this point. */ BUG_ON(bpf_adj_branches(prog_adj, off, off + 1, off + len, false)); bpf_adj_linfo(prog_adj, off, insn_delta); return prog_adj; } int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) { int err; /* Branch offsets can't overflow when program is shrinking, no need * to call bpf_adj_branches(..., true) here */ memmove(prog->insnsi + off, prog->insnsi + off + cnt, sizeof(struct bpf_insn) * (prog->len - off - cnt)); prog->len -= cnt; err = bpf_adj_branches(prog, off, off + cnt, off, false); WARN_ON_ONCE(err); return err; } static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) { int i; for (i = 0; i < fp->aux->func_cnt; i++) bpf_prog_kallsyms_del(fp->aux->func[i]); } void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) { bpf_prog_kallsyms_del_subprogs(fp); bpf_prog_kallsyms_del(fp); } #ifdef CONFIG_BPF_JIT /* All BPF JIT sysctl knobs here. */ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_harden __read_mostly; long bpf_jit_limit __read_mostly; long bpf_jit_limit_max __read_mostly; static void bpf_prog_ksym_set_addr(struct bpf_prog *prog) { const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(prog); unsigned long addr = (unsigned long)hdr; WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog)); prog->aux->ksym.start = (unsigned long) prog->bpf_func; prog->aux->ksym.end = addr + hdr->pages * PAGE_SIZE; } static void bpf_prog_ksym_set_name(struct bpf_prog *prog) { char *sym = prog->aux->ksym.name; const char *end = sym + KSYM_NAME_LEN; const struct btf_type *type; const char *func_name; BUILD_BUG_ON(sizeof("bpf_prog_") + sizeof(prog->tag) * 2 + /* name has been null terminated. * We should need +1 for the '_' preceding * the name. However, the null character * is double counted between the name and the * sizeof("bpf_prog_") above, so we omit * the +1 here. */ sizeof(prog->aux->name) > KSYM_NAME_LEN); sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_"); sym = bin2hex(sym, prog->tag, sizeof(prog->tag)); /* prog->aux->name will be ignored if full btf name is available */ if (prog->aux->func_info_cnt) { type = btf_type_by_id(prog->aux->btf, prog->aux->func_info[prog->aux->func_idx].type_id); func_name = btf_name_by_offset(prog->aux->btf, type->name_off); snprintf(sym, (size_t)(end - sym), "_%s", func_name); return; } if (prog->aux->name[0]) snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name); else *sym = 0; } static unsigned long bpf_get_ksym_start(struct latch_tree_node *n) { return container_of(n, struct bpf_ksym, tnode)->start; } static __always_inline bool bpf_tree_less(struct latch_tree_node *a, struct latch_tree_node *b) { return bpf_get_ksym_start(a) < bpf_get_ksym_start(b); } static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n) { unsigned long val = (unsigned long)key; const struct bpf_ksym *ksym; ksym = container_of(n, struct bpf_ksym, tnode); if (val < ksym->start) return -1; /* Ensure that we detect return addresses as part of the program, when * the final instruction is a call for a program part of the stack * trace. Therefore, do val > ksym->end instead of val >= ksym->end. */ if (val > ksym->end) return 1; return 0; } static const struct latch_tree_ops bpf_tree_ops = { .less = bpf_tree_less, .comp = bpf_tree_comp, }; static DEFINE_SPINLOCK(bpf_lock); static LIST_HEAD(bpf_kallsyms); static struct latch_tree_root bpf_tree __cacheline_aligned; void bpf_ksym_add(struct bpf_ksym *ksym) { spin_lock_bh(&bpf_lock); WARN_ON_ONCE(!list_empty(&ksym->lnode)); list_add_tail_rcu(&ksym->lnode, &bpf_kallsyms); latch_tree_insert(&ksym->tnode, &bpf_tree, &bpf_tree_ops); spin_unlock_bh(&bpf_lock); } static void __bpf_ksym_del(struct bpf_ksym *ksym) { if (list_empty(&ksym->lnode)) return; latch_tree_erase(&ksym->tnode, &bpf_tree, &bpf_tree_ops); list_del_rcu(&ksym->lnode); } void bpf_ksym_del(struct bpf_ksym *ksym) { spin_lock_bh(&bpf_lock); __bpf_ksym_del(ksym); spin_unlock_bh(&bpf_lock); } static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) { return fp->jited && !bpf_prog_was_classic(fp); } static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) { return list_empty(&fp->aux->ksym.lnode) || fp->aux->ksym.lnode.prev == LIST_POISON2; } void bpf_prog_kallsyms_add(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp) || !bpf_capable()) return; bpf_prog_ksym_set_addr(fp); bpf_prog_ksym_set_name(fp); fp->aux->ksym.prog = true; bpf_ksym_add(&fp->aux->ksym); } void bpf_prog_kallsyms_del(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp)) return; bpf_ksym_del(&fp->aux->ksym); } static struct bpf_ksym *bpf_ksym_find(unsigned long addr) { struct latch_tree_node *n; n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops); return n ? container_of(n, struct bpf_ksym, tnode) : NULL; } const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { struct bpf_ksym *ksym; char *ret = NULL; rcu_read_lock(); ksym = bpf_ksym_find(addr); if (ksym) { unsigned long symbol_start = ksym->start; unsigned long symbol_end = ksym->end; strncpy(sym, ksym->name, KSYM_NAME_LEN); ret = sym; if (size) *size = symbol_end - symbol_start; if (off) *off = addr - symbol_start; } rcu_read_unlock(); return ret; } bool is_bpf_text_address(unsigned long addr) { bool ret; rcu_read_lock(); ret = bpf_ksym_find(addr) != NULL; rcu_read_unlock(); return ret; } static struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) { struct bpf_ksym *ksym = bpf_ksym_find(addr); return ksym && ksym->prog ? container_of(ksym, struct bpf_prog_aux, ksym)->prog : NULL; } const struct exception_table_entry *search_bpf_extables(unsigned long addr) { const struct exception_table_entry *e = NULL; struct bpf_prog *prog; rcu_read_lock(); prog = bpf_prog_ksym_find(addr); if (!prog) goto out; if (!prog->aux->num_exentries) goto out; e = search_extable(prog->aux->extable, prog->aux->num_exentries, addr); out: rcu_read_unlock(); return e; } int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { struct bpf_ksym *ksym; unsigned int it = 0; int ret = -ERANGE; if (!bpf_jit_kallsyms_enabled()) return ret; rcu_read_lock(); list_for_each_entry_rcu(ksym, &bpf_kallsyms, lnode) { if (it++ != symnum) continue; strncpy(sym, ksym->name, KSYM_NAME_LEN); *value = ksym->start; *type = BPF_SYM_ELF_TYPE; ret = 0; break; } rcu_read_unlock(); return ret; } int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke) { struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab; static const u32 poke_tab_max = 1024; u32 slot = prog->aux->size_poke_tab; u32 size = slot + 1; if (size > poke_tab_max) return -ENOSPC; if (poke->tailcall_target || poke->tailcall_target_stable || poke->tailcall_bypass || poke->adj_off || poke->bypass_addr) return -EINVAL; switch (poke->reason) { case BPF_POKE_REASON_TAIL_CALL: if (!poke->tail_call.map) return -EINVAL; break; default: return -EINVAL; } tab = krealloc(tab, size * sizeof(*poke), GFP_KERNEL); if (!tab) return -ENOMEM; memcpy(&tab[slot], poke, sizeof(*poke)); prog->aux->size_poke_tab = size; prog->aux->poke_tab = tab; return slot; } static atomic_long_t bpf_jit_current; /* Can be overridden by an arch's JIT compiler if it has a custom, * dedicated BPF backend memory area, or if neither of the two * below apply. */ u64 __weak bpf_jit_alloc_exec_limit(void) { #if defined(MODULES_VADDR) return MODULES_END - MODULES_VADDR; #else return VMALLOC_END - VMALLOC_START; #endif } static int __init bpf_jit_charge_init(void) { /* Only used as heuristic here to derive limit. */ bpf_jit_limit_max = bpf_jit_alloc_exec_limit(); bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 1, PAGE_SIZE), LONG_MAX); return 0; } pure_initcall(bpf_jit_charge_init); int bpf_jit_charge_modmem(u32 pages) { if (atomic_long_add_return(pages, &bpf_jit_current) > (bpf_jit_limit >> PAGE_SHIFT)) { if (!bpf_capable()) { atomic_long_sub(pages, &bpf_jit_current); return -EPERM; } } return 0; } void bpf_jit_uncharge_modmem(u32 pages) { atomic_long_sub(pages, &bpf_jit_current); } void *__weak bpf_jit_alloc_exec(unsigned long size) { return module_alloc(size); } void __weak bpf_jit_free_exec(void *addr) { module_memfree(addr); } struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_binary_header *hdr; u32 size, hole, start, pages; WARN_ON_ONCE(!is_power_of_2(alignment) || alignment > BPF_IMAGE_ALIGNMENT); /* Most of BPF filters are really small, but if some of them * fill a page, allow at least 128 extra bytes to insert a * random section of illegal instructions. */ size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE); pages = size / PAGE_SIZE; if (bpf_jit_charge_modmem(pages)) return NULL; hdr = bpf_jit_alloc_exec(size); if (!hdr) { bpf_jit_uncharge_modmem(pages); return NULL; } /* Fill space with illegal/arch-dep instructions. */ bpf_fill_ill_insns(hdr, size); hdr->pages = pages; hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); start = (get_random_int() % hole) & ~(alignment - 1); /* Leave a random number of instructions before BPF code. */ *image_ptr = &hdr->image[start]; return hdr; } void bpf_jit_binary_free(struct bpf_binary_header *hdr) { u32 pages = hdr->pages; bpf_jit_free_exec(hdr); bpf_jit_uncharge_modmem(pages); } /* This symbol is only overridden by archs that have different * requirements than the usual eBPF JITs, f.e. when they only * implement cBPF JIT, do not set images read-only, etc. */ void __weak bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) { struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp); bpf_jit_binary_free(hdr); WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp)); } bpf_prog_unlock_free(fp); } int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed) { s16 off = insn->off; s32 imm = insn->imm; u8 *addr; *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL; if (!*func_addr_fixed) { /* Place-holder address till the last pass has collected * all addresses for JITed subprograms in which case we * can pick them up from prog->aux. */ if (!extra_pass) addr = NULL; else if (prog->aux->func && off >= 0 && off < prog->aux->func_cnt) addr = (u8 *)prog->aux->func[off]->bpf_func; else return -EINVAL; } else { /* Address of a BPF helper call. Since part of the core * kernel, it's always at a fixed location. __bpf_call_base * and the helper with imm relative to it are both in core * kernel. */ addr = (u8 *)__bpf_call_base + imm; } *func_addr = (unsigned long)addr; return 0; } static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff, bool emit_zext) { struct bpf_insn *to = to_buff; u32 imm_rnd = get_random_int(); s16 off; BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG); BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG); /* Constraints on AX register: * * AX register is inaccessible from user space. It is mapped in * all JITs, and used here for constant blinding rewrites. It is * typically "stateless" meaning its contents are only valid within * the executed instruction, but not across several instructions. * There are a few exceptions however which are further detailed * below. * * Constant blinding is only used by JITs, not in the interpreter. * The interpreter uses AX in some occasions as a local temporary * register e.g. in DIV or MOD instructions. * * In restricted circumstances, the verifier can also use the AX * register for rewrites as long as they do not interfere with * the above cases! */ if (from->dst_reg == BPF_REG_AX || from->src_reg == BPF_REG_AX) goto out; if (from->imm == 0 && (from->code == (BPF_ALU | BPF_MOV | BPF_K) || from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) { *to++ = BPF_ALU64_REG(BPF_XOR, from->dst_reg, from->dst_reg); goto out; } switch (from->code) { case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_MOV | BPF_K: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_K: *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX); break; case BPF_ALU64 | BPF_ADD | BPF_K: case BPF_ALU64 | BPF_SUB | BPF_K: case BPF_ALU64 | BPF_AND | BPF_K: case BPF_ALU64 | BPF_OR | BPF_K: case BPF_ALU64 | BPF_XOR | BPF_K: case BPF_ALU64 | BPF_MUL | BPF_K: case BPF_ALU64 | BPF_MOV | BPF_K: case BPF_ALU64 | BPF_DIV | BPF_K: case BPF_ALU64 | BPF_MOD | BPF_K: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX); break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JLE | BPF_K: case BPF_JMP | BPF_JSGT | BPF_K: case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: case BPF_JMP | BPF_JSLE | BPF_K: case BPF_JMP | BPF_JSET | BPF_K: /* Accommodate for extra offset in case of a backjump. */ off = from->off; if (off < 0) off -= 2; *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; case BPF_JMP32 | BPF_JEQ | BPF_K: case BPF_JMP32 | BPF_JNE | BPF_K: case BPF_JMP32 | BPF_JGT | BPF_K: case BPF_JMP32 | BPF_JLT | BPF_K: case BPF_JMP32 | BPF_JGE | BPF_K: case BPF_JMP32 | BPF_JLE | BPF_K: case BPF_JMP32 | BPF_JSGT | BPF_K: case BPF_JMP32 | BPF_JSLT | BPF_K: case BPF_JMP32 | BPF_JSGE | BPF_K: case BPF_JMP32 | BPF_JSLE | BPF_K: case BPF_JMP32 | BPF_JSET | BPF_K: /* Accommodate for extra offset in case of a backjump. */ off = from->off; if (off < 0) off -= 2; *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_JMP32_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; case BPF_LD | BPF_IMM | BPF_DW: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32); *to++ = BPF_ALU64_REG(BPF_MOV, aux[0].dst_reg, BPF_REG_AX); break; case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */ *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); if (emit_zext) *to++ = BPF_ZEXT_REG(BPF_REG_AX); *to++ = BPF_ALU64_REG(BPF_OR, aux[0].dst_reg, BPF_REG_AX); break; case BPF_ST | BPF_MEM | BPF_DW: case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_B: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off); break; } out: return to - to_buff; } static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other, gfp_t gfp_extra_flags) { gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags); if (fp != NULL) { /* aux->prog still points to the fp_other one, so * when promoting the clone to the real program, * this still needs to be adapted. */ memcpy(fp, fp_other, fp_other->pages * PAGE_SIZE); } return fp; } static void bpf_prog_clone_free(struct bpf_prog *fp) { /* aux was stolen by the other clone, so we cannot free * it from this path! It will be freed eventually by the * other program on release. * * At this point, we don't need a deferred release since * clone is guaranteed to not be locked. */ fp->aux = NULL; fp->stats = NULL; fp->active = NULL; __bpf_prog_free(fp); } void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other) { /* We have to repoint aux->prog to self, as we don't * know whether fp here is the clone or the original. */ fp->aux->prog = fp; bpf_prog_clone_free(fp_other); } struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) { struct bpf_insn insn_buff[16], aux[2]; struct bpf_prog *clone, *tmp; int insn_delta, insn_cnt; struct bpf_insn *insn; int i, rewritten; if (!bpf_jit_blinding_enabled(prog) || prog->blinded) return prog; clone = bpf_prog_clone_create(prog, GFP_USER); if (!clone) return ERR_PTR(-ENOMEM); insn_cnt = clone->len; insn = clone->insnsi; for (i = 0; i < insn_cnt; i++, insn++) { /* We temporarily need to hold the original ld64 insn * so that we can still access the first part in the * second blinding run. */ if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW) && insn[1].code == 0) memcpy(aux, insn, sizeof(aux)); rewritten = bpf_jit_blind_insn(insn, aux, insn_buff, clone->aux->verifier_zext); if (!rewritten) continue; tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten); if (IS_ERR(tmp)) { /* Patching may have repointed aux->prog during * realloc from the original one, so we need to * fix it up here on error. */ bpf_jit_prog_release_other(prog, clone); return tmp; } clone = tmp; insn_delta = rewritten - 1; /* Walk new program and skip insns we just inserted. */ insn = clone->insnsi + i + insn_delta; insn_cnt += insn_delta; i += insn_delta; } clone->blinded = 1; return clone; } #endif /* CONFIG_BPF_JIT */ /* Base function for offset calculation. Needs to go into .text section, * therefore keeping it non-static as well; will also be used by JITs * anyway later on, so do not let the compiler omit it. This also needs * to go into kallsyms for correlation from e.g. bpftool, so naming * must not change. */ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { return 0; } EXPORT_SYMBOL_GPL(__bpf_call_base); /* All UAPI available opcodes. */ #define BPF_INSN_MAP(INSN_2, INSN_3) \ /* 32 bit ALU operations. */ \ /* Register based. */ \ INSN_3(ALU, ADD, X), \ INSN_3(ALU, SUB, X), \ INSN_3(ALU, AND, X), \ INSN_3(ALU, OR, X), \ INSN_3(ALU, LSH, X), \ INSN_3(ALU, RSH, X), \ INSN_3(ALU, XOR, X), \ INSN_3(ALU, MUL, X), \ INSN_3(ALU, MOV, X), \ INSN_3(ALU, ARSH, X), \ INSN_3(ALU, DIV, X), \ INSN_3(ALU, MOD, X), \ INSN_2(ALU, NEG), \ INSN_3(ALU, END, TO_BE), \ INSN_3(ALU, END, TO_LE), \ /* Immediate based. */ \ INSN_3(ALU, ADD, K), \ INSN_3(ALU, SUB, K), \ INSN_3(ALU, AND, K), \ INSN_3(ALU, OR, K), \ INSN_3(ALU, LSH, K), \ INSN_3(ALU, RSH, K), \ INSN_3(ALU, XOR, K), \ INSN_3(ALU, MUL, K), \ INSN_3(ALU, MOV, K), \ INSN_3(ALU, ARSH, K), \ INSN_3(ALU, DIV, K), \ INSN_3(ALU, MOD, K), \ /* 64 bit ALU operations. */ \ /* Register based. */ \ INSN_3(ALU64, ADD, X), \ INSN_3(ALU64, SUB, X), \ INSN_3(ALU64, AND, X), \ INSN_3(ALU64, OR, X), \ INSN_3(ALU64, LSH, X), \ INSN_3(ALU64, RSH, X), \ INSN_3(ALU64, XOR, X), \ INSN_3(ALU64, MUL, X), \ INSN_3(ALU64, MOV, X), \ INSN_3(ALU64, ARSH, X), \ INSN_3(ALU64, DIV, X), \ INSN_3(ALU64, MOD, X), \ INSN_2(ALU64, NEG), \ /* Immediate based. */ \ INSN_3(ALU64, ADD, K), \ INSN_3(ALU64, SUB, K), \ INSN_3(ALU64, AND, K), \ INSN_3(ALU64, OR, K), \ INSN_3(ALU64, LSH, K), \ INSN_3(ALU64, RSH, K), \ INSN_3(ALU64, XOR, K), \ INSN_3(ALU64, MUL, K), \ INSN_3(ALU64, MOV, K), \ INSN_3(ALU64, ARSH, K), \ INSN_3(ALU64, DIV, K), \ INSN_3(ALU64, MOD, K), \ /* Call instruction. */ \ INSN_2(JMP, CALL), \ /* Exit instruction. */ \ INSN_2(JMP, EXIT), \ /* 32-bit Jump instructions. */ \ /* Register based. */ \ INSN_3(JMP32, JEQ, X), \ INSN_3(JMP32, JNE, X), \ INSN_3(JMP32, JGT, X), \ INSN_3(JMP32, JLT, X), \ INSN_3(JMP32, JGE, X), \ INSN_3(JMP32, JLE, X), \ INSN_3(JMP32, JSGT, X), \ INSN_3(JMP32, JSLT, X), \ INSN_3(JMP32, JSGE, X), \ INSN_3(JMP32, JSLE, X), \ INSN_3(JMP32, JSET, X), \ /* Immediate based. */ \ INSN_3(JMP32, JEQ, K), \ INSN_3(JMP32, JNE, K), \ INSN_3(JMP32, JGT, K), \ INSN_3(JMP32, JLT, K), \ INSN_3(JMP32, JGE, K), \ INSN_3(JMP32, JLE, K), \ INSN_3(JMP32, JSGT, K), \ INSN_3(JMP32, JSLT, K), \ INSN_3(JMP32, JSGE, K), \ INSN_3(JMP32, JSLE, K), \ INSN_3(JMP32, JSET, K), \ /* Jump instructions. */ \ /* Register based. */ \ INSN_3(JMP, JEQ, X), \ INSN_3(JMP, JNE, X), \ INSN_3(JMP, JGT, X), \ INSN_3(JMP, JLT, X), \ INSN_3(JMP, JGE, X), \ INSN_3(JMP, JLE, X), \ INSN_3(JMP, JSGT, X), \ INSN_3(JMP, JSLT, X), \ INSN_3(JMP, JSGE, X), \ INSN_3(JMP, JSLE, X), \ INSN_3(JMP, JSET, X), \ /* Immediate based. */ \ INSN_3(JMP, JEQ, K), \ INSN_3(JMP, JNE, K), \ INSN_3(JMP, JGT, K), \ INSN_3(JMP, JLT, K), \ INSN_3(JMP, JGE, K), \ INSN_3(JMP, JLE, K), \ INSN_3(JMP, JSGT, K), \ INSN_3(JMP, JSLT, K), \ INSN_3(JMP, JSGE, K), \ INSN_3(JMP, JSLE, K), \ INSN_3(JMP, JSET, K), \ INSN_2(JMP, JA), \ /* Store instructions. */ \ /* Register based. */ \ INSN_3(STX, MEM, B), \ INSN_3(STX, MEM, H), \ INSN_3(STX, MEM, W), \ INSN_3(STX, MEM, DW), \ INSN_3(STX, ATOMIC, W), \ INSN_3(STX, ATOMIC, DW), \ /* Immediate based. */ \ INSN_3(ST, MEM, B), \ INSN_3(ST, MEM, H), \ INSN_3(ST, MEM, W), \ INSN_3(ST, MEM, DW), \ /* Load instructions. */ \ /* Register based. */ \ INSN_3(LDX, MEM, B), \ INSN_3(LDX, MEM, H), \ INSN_3(LDX, MEM, W), \ INSN_3(LDX, MEM, DW), \ /* Immediate based. */ \ INSN_3(LD, IMM, DW) bool bpf_opcode_in_insntable(u8 code) { #define BPF_INSN_2_TBL(x, y) [BPF_##x | BPF_##y] = true #define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true static const bool public_insntable[256] = { [0 ... 255] = false, /* Now overwrite non-defaults ... */ BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL), /* UAPI exposed, but rewritten opcodes. cBPF carry-over. */ [BPF_LD | BPF_ABS | BPF_B] = true, [BPF_LD | BPF_ABS | BPF_H] = true, [BPF_LD | BPF_ABS | BPF_W] = true, [BPF_LD | BPF_IND | BPF_B] = true, [BPF_LD | BPF_IND | BPF_H] = true, [BPF_LD | BPF_IND | BPF_W] = true, }; #undef BPF_INSN_3_TBL #undef BPF_INSN_2_TBL return public_insntable[code]; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) { memset(dst, 0, size); return -EFAULT; } /** * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers * @insn: is the array of eBPF instructions * * Decode and execute eBPF instructions. * * Return: whatever value is in %BPF_R0 at program exit */ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) { #define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z static const void * const jumptable[256] __annotate_jump_table = { [0 ... 255] = &&default_label, /* Now overwrite non-defaults ... */ BPF_INSN_MAP(BPF_INSN_2_LBL, BPF_INSN_3_LBL), /* Non-UAPI available opcodes. */ [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS, [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC, [BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B, [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, [BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW, }; #undef BPF_INSN_3_LBL #undef BPF_INSN_2_LBL u32 tail_call_cnt = 0; #define CONT ({ insn++; goto select_insn; }) #define CONT_JMP ({ insn++; goto select_insn; }) select_insn: goto *jumptable[insn->code]; /* Explicitly mask the register-based shift amounts with 63 or 31 * to avoid undefined behavior. Normally this won't affect the * generated code, for example, in case of native 64 bit archs such * as x86-64 or arm64, the compiler is optimizing the AND away for * the interpreter. In case of JITs, each of the JIT backends compiles * the BPF shift operations to machine instructions which produce * implementation-defined results in such a case; the resulting * contents of the register may be arbitrary, but program behaviour * as a whole remains defined. In other words, in case of JIT backends, * the AND must /not/ be added to the emitted LSH/RSH/ARSH translation. */ /* ALU (shifts) */ #define SHT(OPCODE, OP) \ ALU64_##OPCODE##_X: \ DST = DST OP (SRC & 63); \ CONT; \ ALU_##OPCODE##_X: \ DST = (u32) DST OP ((u32) SRC & 31); \ CONT; \ ALU64_##OPCODE##_K: \ DST = DST OP IMM; \ CONT; \ ALU_##OPCODE##_K: \ DST = (u32) DST OP (u32) IMM; \ CONT; /* ALU (rest) */ #define ALU(OPCODE, OP) \ ALU64_##OPCODE##_X: \ DST = DST OP SRC; \ CONT; \ ALU_##OPCODE##_X: \ DST = (u32) DST OP (u32) SRC; \ CONT; \ ALU64_##OPCODE##_K: \ DST = DST OP IMM; \ CONT; \ ALU_##OPCODE##_K: \ DST = (u32) DST OP (u32) IMM; \ CONT; ALU(ADD, +) ALU(SUB, -) ALU(AND, &) ALU(OR, |) ALU(XOR, ^) ALU(MUL, *) SHT(LSH, <<) SHT(RSH, >>) #undef SHT #undef ALU ALU_NEG: DST = (u32) -DST; CONT; ALU64_NEG: DST = -DST; CONT; ALU_MOV_X: DST = (u32) SRC; CONT; ALU_MOV_K: DST = (u32) IMM; CONT; ALU64_MOV_X: DST = SRC; CONT; ALU64_MOV_K: DST = IMM; CONT; LD_IMM_DW: DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32; insn++; CONT; ALU_ARSH_X: DST = (u64) (u32) (((s32) DST) >> (SRC & 31)); CONT; ALU_ARSH_K: DST = (u64) (u32) (((s32) DST) >> IMM); CONT; ALU64_ARSH_X: (*(s64 *) &DST) >>= (SRC & 63); CONT; ALU64_ARSH_K: (*(s64 *) &DST) >>= IMM; CONT; ALU64_MOD_X: div64_u64_rem(DST, SRC, &AX); DST = AX; CONT; ALU_MOD_X: AX = (u32) DST; DST = do_div(AX, (u32) SRC); CONT; ALU64_MOD_K: div64_u64_rem(DST, IMM, &AX); DST = AX; CONT; ALU_MOD_K: AX = (u32) DST; DST = do_div(AX, (u32) IMM); CONT; ALU64_DIV_X: DST = div64_u64(DST, SRC); CONT; ALU_DIV_X: AX = (u32) DST; do_div(AX, (u32) SRC); DST = (u32) AX; CONT; ALU64_DIV_K: DST = div64_u64(DST, IMM); CONT; ALU_DIV_K: AX = (u32) DST; do_div(AX, (u32) IMM); DST = (u32) AX; CONT; ALU_END_TO_BE: switch (IMM) { case 16: DST = (__force u16) cpu_to_be16(DST); break; case 32: DST = (__force u32) cpu_to_be32(DST); break; case 64: DST = (__force u64) cpu_to_be64(DST); break; } CONT; ALU_END_TO_LE: switch (IMM) { case 16: DST = (__force u16) cpu_to_le16(DST); break; case 32: DST = (__force u32) cpu_to_le32(DST); break; case 64: DST = (__force u64) cpu_to_le64(DST); break; } CONT; /* CALL */ JMP_CALL: /* Function call scratches BPF_R1-BPF_R5 registers, * preserves BPF_R6-BPF_R9, and stores return value * into BPF_R0. */ BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3, BPF_R4, BPF_R5); CONT; JMP_CALL_ARGS: BPF_R0 = (__bpf_call_base_args + insn->imm)(BPF_R1, BPF_R2, BPF_R3, BPF_R4, BPF_R5, insn + insn->off + 1); CONT; JMP_TAIL_CALL: { struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog; u32 index = BPF_R3; if (unlikely(index >= array->map.max_entries)) goto out; if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT)) goto out; tail_call_cnt++; prog = READ_ONCE(array->ptrs[index]); if (!prog) goto out; /* ARG1 at this point is guaranteed to point to CTX from * the verifier side due to the fact that the tail call is * handled like a helper, that is, bpf_tail_call_proto, * where arg1_type is ARG_PTR_TO_CTX. */ insn = prog->insnsi; goto select_insn; out: CONT; } JMP_JA: insn += insn->off; CONT; JMP_EXIT: return BPF_R0; /* JMP */ #define COND_JMP(SIGN, OPCODE, CMP_OP) \ JMP_##OPCODE##_X: \ if ((SIGN##64) DST CMP_OP (SIGN##64) SRC) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; \ JMP32_##OPCODE##_X: \ if ((SIGN##32) DST CMP_OP (SIGN##32) SRC) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; \ JMP_##OPCODE##_K: \ if ((SIGN##64) DST CMP_OP (SIGN##64) IMM) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; \ JMP32_##OPCODE##_K: \ if ((SIGN##32) DST CMP_OP (SIGN##32) IMM) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; COND_JMP(u, JEQ, ==) COND_JMP(u, JNE, !=) COND_JMP(u, JGT, >) COND_JMP(u, JLT, <) COND_JMP(u, JGE, >=) COND_JMP(u, JLE, <=) COND_JMP(u, JSET, &) COND_JMP(s, JSGT, >) COND_JMP(s, JSLT, <) COND_JMP(s, JSGE, >=) COND_JMP(s, JSLE, <=) #undef COND_JMP /* ST, STX and LDX*/ ST_NOSPEC: /* Speculation barrier for mitigating Speculative Store Bypass. * In case of arm64, we rely on the firmware mitigation as * controlled via the ssbd kernel parameter. Whenever the * mitigation is enabled, it works for all of the kernel code * with no need to provide any additional instructions here. * In case of x86, we use 'lfence' insn for mitigation. We * reuse preexisting logic from Spectre v1 mitigation that * happens to produce the required code on x86 for v4 as well. */ barrier_nospec(); CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ CONT; \ ST_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (DST + insn->off) = IMM; \ CONT; \ LDX_MEM_##SIZEOP: \ DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ CONT; \ LDX_PROBE_MEM_##SIZEOP: \ bpf_probe_read_kernel(&DST, sizeof(SIZE), \ (const void *)(long) (SRC + insn->off)); \ DST = *((SIZE *)&DST); \ CONT; LDST(B, u8) LDST(H, u16) LDST(W, u32) LDST(DW, u64) #undef LDST #define ATOMIC_ALU_OP(BOP, KOP) \ case BOP: \ if (BPF_SIZE(insn->code) == BPF_W) \ atomic_##KOP((u32) SRC, (atomic_t *)(unsigned long) \ (DST + insn->off)); \ else \ atomic64_##KOP((u64) SRC, (atomic64_t *)(unsigned long) \ (DST + insn->off)); \ break; \ case BOP | BPF_FETCH: \ if (BPF_SIZE(insn->code) == BPF_W) \ SRC = (u32) atomic_fetch_##KOP( \ (u32) SRC, \ (atomic_t *)(unsigned long) (DST + insn->off)); \ else \ SRC = (u64) atomic64_fetch_##KOP( \ (u64) SRC, \ (atomic64_t *)(unsigned long) (DST + insn->off)); \ break; STX_ATOMIC_DW: STX_ATOMIC_W: switch (IMM) { ATOMIC_ALU_OP(BPF_ADD, add) ATOMIC_ALU_OP(BPF_AND, and) ATOMIC_ALU_OP(BPF_OR, or) ATOMIC_ALU_OP(BPF_XOR, xor) #undef ATOMIC_ALU_OP case BPF_XCHG: if (BPF_SIZE(insn->code) == BPF_W) SRC = (u32) atomic_xchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) SRC); else SRC = (u64) atomic64_xchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) SRC); break; case BPF_CMPXCHG: if (BPF_SIZE(insn->code) == BPF_W) BPF_R0 = (u32) atomic_cmpxchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) BPF_R0, (u32) SRC); else BPF_R0 = (u64) atomic64_cmpxchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) BPF_R0, (u64) SRC); break; default: goto default_label; } CONT; default_label: /* If we ever reach this, we have a bug somewhere. Die hard here * instead of just returning 0; we could be somewhere in a subprog, * so execution could continue otherwise which we do /not/ want. * * Note, verifier whitelists all opcodes in bpf_opcode_in_insntable(). */ pr_warn("BPF interpreter: unknown opcode %02x (imm: 0x%x)\n", insn->code, insn->imm); BUG_ON(1); return 0; } #define PROG_NAME(stack_size) __bpf_prog_run##stack_size #define DEFINE_BPF_PROG_RUN(stack_size) \ static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \ { \ u64 stack[stack_size / sizeof(u64)]; \ u64 regs[MAX_BPF_EXT_REG]; \ \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ ARG1 = (u64) (unsigned long) ctx; \ return ___bpf_prog_run(regs, insn); \ } #define PROG_NAME_ARGS(stack_size) __bpf_prog_run_args##stack_size #define DEFINE_BPF_PROG_RUN_ARGS(stack_size) \ static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \ const struct bpf_insn *insn) \ { \ u64 stack[stack_size / sizeof(u64)]; \ u64 regs[MAX_BPF_EXT_REG]; \ \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ BPF_R1 = r1; \ BPF_R2 = r2; \ BPF_R3 = r3; \ BPF_R4 = r4; \ BPF_R5 = r5; \ return ___bpf_prog_run(regs, insn); \ } #define EVAL1(FN, X) FN(X) #define EVAL2(FN, X, Y...) FN(X) EVAL1(FN, Y) #define EVAL3(FN, X, Y...) FN(X) EVAL2(FN, Y) #define EVAL4(FN, X, Y...) FN(X) EVAL3(FN, Y) #define EVAL5(FN, X, Y...) FN(X) EVAL4(FN, Y) #define EVAL6(FN, X, Y...) FN(X) EVAL5(FN, Y) EVAL6(DEFINE_BPF_PROG_RUN, 32, 64, 96, 128, 160, 192); EVAL6(DEFINE_BPF_PROG_RUN, 224, 256, 288, 320, 352, 384); EVAL4(DEFINE_BPF_PROG_RUN, 416, 448, 480, 512); EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 32, 64, 96, 128, 160, 192); EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 224, 256, 288, 320, 352, 384); EVAL4(DEFINE_BPF_PROG_RUN_ARGS, 416, 448, 480, 512); #define PROG_NAME_LIST(stack_size) PROG_NAME(stack_size), static unsigned int (*interpreters[])(const void *ctx, const struct bpf_insn *insn) = { EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) }; #undef PROG_NAME_LIST #define PROG_NAME_LIST(stack_size) PROG_NAME_ARGS(stack_size), static u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, const struct bpf_insn *insn) = { EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) }; #undef PROG_NAME_LIST void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) { stack_depth = max_t(u32, stack_depth, 1); insn->off = (s16) insn->imm; insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] - __bpf_call_base_args; insn->code = BPF_JMP | BPF_CALL_ARGS; } #else static unsigned int __bpf_prog_ret0_warn(const void *ctx, const struct bpf_insn *insn) { /* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON * is not working properly, so warn about it! */ WARN_ON_ONCE(1); return 0; } #endif bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) { bool ret; if (fp->kprobe_override) return false; spin_lock(&array->aux->owner.lock); if (!array->aux->owner.type) { /* There's no owner yet where we could check for * compatibility. */ array->aux->owner.type = fp->type; array->aux->owner.jited = fp->jited; ret = true; } else { ret = array->aux->owner.type == fp->type && array->aux->owner.jited == fp->jited; } spin_unlock(&array->aux->owner.lock); return ret; } static int bpf_check_tail_call(const struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; int i, ret = 0; mutex_lock(&aux->used_maps_mutex); for (i = 0; i < aux->used_map_cnt; i++) { struct bpf_map *map = aux->used_maps[i]; struct bpf_array *array; if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) continue; array = container_of(map, struct bpf_array, map); if (!bpf_prog_array_compatible(array, fp)) { ret = -EINVAL; goto out; } } out: mutex_unlock(&aux->used_maps_mutex); return ret; } static void bpf_prog_select_func(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; #else fp->bpf_func = __bpf_prog_ret0_warn; #endif } /** * bpf_prog_select_runtime - select exec runtime for BPF program * @fp: bpf_prog populated with internal BPF program * @err: pointer to error variable * * Try to JIT eBPF program, if JIT is not available, use interpreter. * The BPF program will be executed via bpf_prog_run() function. * * Return: the &fp argument along with &err set to 0 for success or * a negative errno code on failure */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { /* In case of BPF to BPF calls, verifier did all the prep * work with regards to JITing, etc. */ bool jit_needed = false; if (fp->bpf_func) goto finalize; if (IS_ENABLED(CONFIG_BPF_JIT_ALWAYS_ON) || bpf_prog_has_kfunc_call(fp)) jit_needed = true; bpf_prog_select_func(fp); /* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during * blinding, bpf_int_jit_compile() must always return a * valid program, which in this case would simply not * be JITed, but falls back to the interpreter. */ if (!bpf_prog_is_dev_bound(fp->aux)) { *err = bpf_prog_alloc_jited_linfo(fp); if (*err) return fp; fp = bpf_int_jit_compile(fp); bpf_prog_jit_attempt_done(fp); if (!fp->jited && jit_needed) { *err = -ENOTSUPP; return fp; } } else { *err = bpf_prog_offload_compile(fp); if (*err) return fp; } finalize: *err = bpf_prog_lock_ro(fp); if (*err) return fp; /* The tail call compatibility check can only be done at * this late stage as we need to determine, if we deal * with JITed or non JITed program concatenations and not * all eBPF JITs might immediately support all features. */ *err = bpf_check_tail_call(fp); return fp; } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); static unsigned int __bpf_prog_ret1(const void *ctx, const struct bpf_insn *insn) { return 1; } static struct bpf_prog_dummy { struct bpf_prog prog; } dummy_bpf_prog = { .prog = { .bpf_func = __bpf_prog_ret1, }, }; /* to avoid allocating empty bpf_prog_array for cgroups that * don't have bpf program attached use one global 'empty_prog_array' * It will not be modified the caller of bpf_prog_array_alloc() * (since caller requested prog_cnt == 0) * that pointer should be 'freed' by bpf_prog_array_free() */ static struct { struct bpf_prog_array hdr; struct bpf_prog *null_prog; } empty_prog_array = { .null_prog = NULL, }; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) { if (prog_cnt) return kzalloc(sizeof(struct bpf_prog_array) + sizeof(struct bpf_prog_array_item) * (prog_cnt + 1), flags); return &empty_prog_array.hdr; } void bpf_prog_array_free(struct bpf_prog_array *progs) { if (!progs || progs == &empty_prog_array.hdr) return; kfree_rcu(progs, rcu); } int bpf_prog_array_length(struct bpf_prog_array *array) { struct bpf_prog_array_item *item; u32 cnt = 0; for (item = array->items; item->prog; item++) if (item->prog != &dummy_bpf_prog.prog) cnt++; return cnt; } bool bpf_prog_array_is_empty(struct bpf_prog_array *array) { struct bpf_prog_array_item *item; for (item = array->items; item->prog; item++) if (item->prog != &dummy_bpf_prog.prog) return false; return true; } static bool bpf_prog_array_copy_core(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt) { struct bpf_prog_array_item *item; int i = 0; for (item = array->items; item->prog; item++) { if (item->prog == &dummy_bpf_prog.prog) continue; prog_ids[i] = item->prog->aux->id; if (++i == request_cnt) { item++; break; } } return !!(item->prog); } int bpf_prog_array_copy_to_user(struct bpf_prog_array *array, __u32 __user *prog_ids, u32 cnt) { unsigned long err = 0; bool nospc; u32 *ids; /* users of this function are doing: * cnt = bpf_prog_array_length(); * if (cnt > 0) * bpf_prog_array_copy_to_user(..., cnt); * so below kcalloc doesn't need extra cnt > 0 check. */ ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN); if (!ids) return -ENOMEM; nospc = bpf_prog_array_copy_core(array, ids, cnt); err = copy_to_user(prog_ids, ids, cnt * sizeof(u32)); kfree(ids); if (err) return -EFAULT; if (nospc) return -ENOSPC; return 0; } void bpf_prog_array_delete_safe(struct bpf_prog_array *array, struct bpf_prog *old_prog) { struct bpf_prog_array_item *item; for (item = array->items; item->prog; item++) if (item->prog == old_prog) { WRITE_ONCE(item->prog, &dummy_bpf_prog.prog); break; } } /** * bpf_prog_array_delete_safe_at() - Replaces the program at the given * index into the program array with * a dummy no-op program. * @array: a bpf_prog_array * @index: the index of the program to replace * * Skips over dummy programs, by not counting them, when calculating * the position of the program to replace. * * Return: * * 0 - Success * * -EINVAL - Invalid index value. Must be a non-negative integer. * * -ENOENT - Index out of range */ int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index) { return bpf_prog_array_update_at(array, index, &dummy_bpf_prog.prog); } /** * bpf_prog_array_update_at() - Updates the program at the given index * into the program array. * @array: a bpf_prog_array * @index: the index of the program to update * @prog: the program to insert into the array * * Skips over dummy programs, by not counting them, when calculating * the position of the program to update. * * Return: * * 0 - Success * * -EINVAL - Invalid index value. Must be a non-negative integer. * * -ENOENT - Index out of range */ int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, struct bpf_prog *prog) { struct bpf_prog_array_item *item; if (unlikely(index < 0)) return -EINVAL; for (item = array->items; item->prog; item++) { if (item->prog == &dummy_bpf_prog.prog) continue; if (!index) { WRITE_ONCE(item->prog, prog); return 0; } index--; } return -ENOENT; } int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, u64 bpf_cookie, struct bpf_prog_array **new_array) { int new_prog_cnt, carry_prog_cnt = 0; struct bpf_prog_array_item *existing, *new; struct bpf_prog_array *array; bool found_exclude = false; /* Figure out how many existing progs we need to carry over to * the new array. */ if (old_array) { existing = old_array->items; for (; existing->prog; existing++) { if (existing->prog == exclude_prog) { found_exclude = true; continue; } if (existing->prog != &dummy_bpf_prog.prog) carry_prog_cnt++; if (existing->prog == include_prog) return -EEXIST; } } if (exclude_prog && !found_exclude) return -ENOENT; /* How many progs (not NULL) will be in the new array? */ new_prog_cnt = carry_prog_cnt; if (include_prog) new_prog_cnt += 1; /* Do we have any prog (not NULL) in the new array? */ if (!new_prog_cnt) { *new_array = NULL; return 0; } /* +1 as the end of prog_array is marked with NULL */ array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL); if (!array) return -ENOMEM; new = array->items; /* Fill in the new prog array */ if (carry_prog_cnt) { existing = old_array->items; for (; existing->prog; existing++) { if (existing->prog == exclude_prog || existing->prog == &dummy_bpf_prog.prog) continue; new->prog = existing->prog; new->bpf_cookie = existing->bpf_cookie; new++; } } if (include_prog) { new->prog = include_prog; new->bpf_cookie = bpf_cookie; new++; } new->prog = NULL; *new_array = array; return 0; } int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt) { u32 cnt = 0; if (array) cnt = bpf_prog_array_length(array); *prog_cnt = cnt; /* return early if user requested only program count or nothing to copy */ if (!request_cnt || !cnt) return 0; /* this function is called under trace/bpf_trace.c: bpf_event_mutex */ return bpf_prog_array_copy_core(array, prog_ids, request_cnt) ? -ENOSPC : 0; } void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len) { struct bpf_map *map; u32 i; for (i = 0; i < len; i++) { map = used_maps[i]; if (map->ops->map_poke_untrack) map->ops->map_poke_untrack(map, aux); bpf_map_put(map); } } static void bpf_free_used_maps(struct bpf_prog_aux *aux) { __bpf_free_used_maps(aux, aux->used_maps, aux->used_map_cnt); kfree(aux->used_maps); } void __bpf_free_used_btfs(struct bpf_prog_aux *aux, struct btf_mod_pair *used_btfs, u32 len) { #ifdef CONFIG_BPF_SYSCALL struct btf_mod_pair *btf_mod; u32 i; for (i = 0; i < len; i++) { btf_mod = &used_btfs[i]; if (btf_mod->module) module_put(btf_mod->module); btf_put(btf_mod->btf); } #endif } static void bpf_free_used_btfs(struct bpf_prog_aux *aux) { __bpf_free_used_btfs(aux, aux->used_btfs, aux->used_btf_cnt); kfree(aux->used_btfs); } static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; int i; aux = container_of(work, struct bpf_prog_aux, work); bpf_free_used_maps(aux); bpf_free_used_btfs(aux); if (bpf_prog_is_dev_bound(aux)) bpf_prog_offload_destroy(aux->prog); #ifdef CONFIG_PERF_EVENTS if (aux->prog->has_callchain_buf) put_callchain_buffers(); #endif if (aux->dst_trampoline) bpf_trampoline_put(aux->dst_trampoline); for (i = 0; i < aux->func_cnt; i++) { /* We can just unlink the subprog poke descriptor table as * it was originally linked to the main program and is also * released along with it. */ aux->func[i]->aux->poke_tab = NULL; bpf_jit_free(aux->func[i]); } if (aux->func_cnt) { kfree(aux->func); bpf_prog_unlock_free(aux->prog); } else { bpf_jit_free(aux->prog); } } /* Free internal BPF program */ void bpf_prog_free(struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; if (aux->dst_prog) bpf_prog_put(aux->dst_prog); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } EXPORT_SYMBOL_GPL(bpf_prog_free); /* RNG for unpriviledged user space with separated state from prandom_u32(). */ static DEFINE_PER_CPU(struct rnd_state, bpf_user_rnd_state); void bpf_user_rnd_init_once(void) { prandom_init_once(&bpf_user_rnd_state); } BPF_CALL_0(bpf_user_rnd_u32) { /* Should someone ever have the rather unwise idea to use some * of the registers passed into this function, then note that * this function is called from native eBPF and classic-to-eBPF * transformations. Register assignments from both sides are * different, f.e. classic always sets fn(ctx, A, X) here. */ struct rnd_state *state; u32 res; state = &get_cpu_var(bpf_user_rnd_state); res = prandom_u32_state(state); put_cpu_var(bpf_user_rnd_state); return res; } BPF_CALL_0(bpf_get_raw_cpu_id) { return raw_smp_processor_id(); } /* Weak definitions of helper functions in case we don't have bpf syscall. */ const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; const struct bpf_func_proto bpf_map_update_elem_proto __weak; const struct bpf_func_proto bpf_map_delete_elem_proto __weak; const struct bpf_func_proto bpf_map_push_elem_proto __weak; const struct bpf_func_proto bpf_map_pop_elem_proto __weak; const struct bpf_func_proto bpf_map_peek_elem_proto __weak; const struct bpf_func_proto bpf_spin_lock_proto __weak; const struct bpf_func_proto bpf_spin_unlock_proto __weak; const struct bpf_func_proto bpf_jiffies64_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; const struct bpf_func_proto bpf_get_numa_node_id_proto __weak; const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_local_storage_proto __weak; const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_snprintf_btf_proto __weak; const struct bpf_func_proto bpf_seq_printf_btf_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { return NULL; } u64 __weak bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { return -ENOTSUPP; } EXPORT_SYMBOL_GPL(bpf_event_output); /* Always built-in helper functions. */ const struct bpf_func_proto bpf_tail_call_proto = { .func = NULL, .gpl_only = false, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; /* Stub for JITs that only support cBPF. eBPF programs are interpreted. * It is encouraged to implement bpf_int_jit_compile() instead, so that * eBPF and implicitly also cBPF can get JITed! */ struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_prog *prog) { return prog; } /* Stub for JITs that support eBPF. All cBPF code gets transformed into * eBPF by the kernel and is later compiled by bpf_int_jit_compile(). */ void __weak bpf_jit_compile(struct bpf_prog *prog) { } bool __weak bpf_helper_changes_pkt_data(void *func) { return false; } /* Return TRUE if the JIT backend wants verifier to enable sub-register usage * analysis code and wants explicit zero extension inserted by verifier. * Otherwise, return FALSE. * * The verifier inserts an explicit zero extension after BPF_CMPXCHGs even if * you don't override this. JITs that don't want these extra insns can detect * them using insn_is_zext. */ bool __weak bpf_jit_needs_zext(void) { return false; } bool __weak bpf_jit_supports_kfunc_call(void) { return false; } /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { return -EFAULT; } int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2) { return -ENOTSUPP; } DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(bpf_stats_enabled_key); /* All definitions of tracepoints related to BPF. */ #define CREATE_TRACE_POINTS #include <linux/bpf_trace.h> EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx); |
| 323 44 37 53 2 2 48 106 106 106 527 527 527 527 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 | // SPDX-License-Identifier: GPL-2.0-only /* * common LSM auditing functions * * Based on code written for SELinux by : * Stephen Smalley, <sds@tycho.nsa.gov> * James Morris <jmorris@redhat.com> * Author : Etienne Basset, <etienne.basset@ensta.org> */ #include <linux/types.h> #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/gfp.h> #include <linux/fs.h> #include <linux/init.h> #include <net/sock.h> #include <linux/un.h> #include <net/af_unix.h> #include <linux/audit.h> #include <linux/ipv6.h> #include <linux/ip.h> #include <net/ip.h> #include <net/ipv6.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/dccp.h> #include <linux/sctp.h> #include <linux/lsm_audit.h> #include <linux/security.h> /** * ipv4_skb_to_auditdata : fill auditdata from skb * @skb : the skb * @ad : the audit data to fill * @proto : the layer 4 protocol * * return 0 on success */ int ipv4_skb_to_auditdata(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int ret = 0; struct iphdr *ih; ih = ip_hdr(skb); if (ih == NULL) return -EINVAL; ad->u.net->v4info.saddr = ih->saddr; ad->u.net->v4info.daddr = ih->daddr; if (proto) *proto = ih->protocol; /* non initial fragment */ if (ntohs(ih->frag_off) & IP_OFFSET) return 0; switch (ih->protocol) { case IPPROTO_TCP: { struct tcphdr *th = tcp_hdr(skb); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr *uh = udp_hdr(skb); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr *dh = dccp_hdr(skb); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } case IPPROTO_SCTP: { struct sctphdr *sh = sctp_hdr(skb); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } default: ret = -EINVAL; } return ret; } #if IS_ENABLED(CONFIG_IPV6) /** * ipv6_skb_to_auditdata : fill auditdata from skb * @skb : the skb * @ad : the audit data to fill * @proto : the layer 4 protocol * * return 0 on success */ int ipv6_skb_to_auditdata(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int offset, ret = 0; struct ipv6hdr *ip6; u8 nexthdr; __be16 frag_off; ip6 = ipv6_hdr(skb); if (ip6 == NULL) return -EINVAL; ad->u.net->v6info.saddr = ip6->saddr; ad->u.net->v6info.daddr = ip6->daddr; /* IPv6 can have several extension header before the Transport header * skip them */ offset = skb_network_offset(skb); offset += sizeof(*ip6); nexthdr = ip6->nexthdr; offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); if (offset < 0) return 0; if (proto) *proto = nexthdr; switch (nexthdr) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } default: ret = -EINVAL; } return ret; } #endif static inline void print_ipv6_addr(struct audit_buffer *ab, const struct in6_addr *addr, __be16 port, char *name1, char *name2) { if (!ipv6_addr_any(addr)) audit_log_format(ab, " %s=%pI6c", name1, addr); if (port) audit_log_format(ab, " %s=%d", name2, ntohs(port)); } static inline void print_ipv4_addr(struct audit_buffer *ab, __be32 addr, __be16 port, char *name1, char *name2) { if (addr) audit_log_format(ab, " %s=%pI4", name1, &addr); if (port) audit_log_format(ab, " %s=%d", name2, ntohs(port)); } /** * dump_common_audit_data - helper to dump common audit data * @a : common audit data * */ static void dump_common_audit_data(struct audit_buffer *ab, struct common_audit_data *a) { char comm[sizeof(current->comm)]; /* * To keep stack sizes in check force programers to notice if they * start making this union too large! See struct lsm_network_audit * as an example of how to deal with large data. */ BUILD_BUG_ON(sizeof(a->u) > sizeof(void *)*2); audit_log_format(ab, " pid=%d comm=", task_tgid_nr(current)); audit_log_untrustedstring(ab, memcpy(comm, current->comm, sizeof(comm))); switch (a->type) { case LSM_AUDIT_DATA_NONE: return; case LSM_AUDIT_DATA_IPC: audit_log_format(ab, " key=%d ", a->u.ipc_id); break; case LSM_AUDIT_DATA_CAP: audit_log_format(ab, " capability=%d ", a->u.cap); break; case LSM_AUDIT_DATA_PATH: { struct inode *inode; audit_log_d_path(ab, " path=", &a->u.path); inode = d_backing_inode(a->u.path.dentry); if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } break; } case LSM_AUDIT_DATA_FILE: { struct inode *inode; audit_log_d_path(ab, " path=", &a->u.file->f_path); inode = file_inode(a->u.file); if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } break; } case LSM_AUDIT_DATA_IOCTL_OP: { struct inode *inode; audit_log_d_path(ab, " path=", &a->u.op->path); inode = a->u.op->path.dentry->d_inode; if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } audit_log_format(ab, " ioctlcmd=0x%hx", a->u.op->cmd); break; } case LSM_AUDIT_DATA_DENTRY: { struct inode *inode; audit_log_format(ab, " name="); spin_lock(&a->u.dentry->d_lock); audit_log_untrustedstring(ab, a->u.dentry->d_name.name); spin_unlock(&a->u.dentry->d_lock); inode = d_backing_inode(a->u.dentry); if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } break; } case LSM_AUDIT_DATA_INODE: { struct dentry *dentry; struct inode *inode; rcu_read_lock(); inode = a->u.inode; dentry = d_find_alias_rcu(inode); if (dentry) { audit_log_format(ab, " name="); spin_lock(&dentry->d_lock); audit_log_untrustedstring(ab, dentry->d_name.name); spin_unlock(&dentry->d_lock); } audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); rcu_read_unlock(); break; } case LSM_AUDIT_DATA_TASK: { struct task_struct *tsk = a->u.tsk; if (tsk) { pid_t pid = task_tgid_nr(tsk); if (pid) { char comm[sizeof(tsk->comm)]; audit_log_format(ab, " opid=%d ocomm=", pid); audit_log_untrustedstring(ab, memcpy(comm, tsk->comm, sizeof(comm))); } } break; } case LSM_AUDIT_DATA_NET: if (a->u.net->sk) { const struct sock *sk = a->u.net->sk; struct unix_sock *u; struct unix_address *addr; int len = 0; char *p = NULL; switch (sk->sk_family) { case AF_INET: { struct inet_sock *inet = inet_sk(sk); print_ipv4_addr(ab, inet->inet_rcv_saddr, inet->inet_sport, "laddr", "lport"); print_ipv4_addr(ab, inet->inet_daddr, inet->inet_dport, "faddr", "fport"); break; } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct inet_sock *inet = inet_sk(sk); print_ipv6_addr(ab, &sk->sk_v6_rcv_saddr, inet->inet_sport, "laddr", "lport"); print_ipv6_addr(ab, &sk->sk_v6_daddr, inet->inet_dport, "faddr", "fport"); break; } #endif case AF_UNIX: u = unix_sk(sk); addr = smp_load_acquire(&u->addr); if (!addr) break; if (u->path.dentry) { audit_log_d_path(ab, " path=", &u->path); break; } len = addr->len-sizeof(short); p = &addr->name->sun_path[0]; audit_log_format(ab, " path="); if (*p) audit_log_untrustedstring(ab, p); else audit_log_n_hex(ab, p, len); break; } } switch (a->u.net->family) { case AF_INET: print_ipv4_addr(ab, a->u.net->v4info.saddr, a->u.net->sport, "saddr", "src"); print_ipv4_addr(ab, a->u.net->v4info.daddr, a->u.net->dport, "daddr", "dest"); break; case AF_INET6: print_ipv6_addr(ab, &a->u.net->v6info.saddr, a->u.net->sport, "saddr", "src"); print_ipv6_addr(ab, &a->u.net->v6info.daddr, a->u.net->dport, "daddr", "dest"); break; } if (a->u.net->netif > 0) { struct net_device *dev; /* NOTE: we always use init's namespace */ dev = dev_get_by_index(&init_net, a->u.net->netif); if (dev) { audit_log_format(ab, " netif=%s", dev->name); dev_put(dev); } } break; #ifdef CONFIG_KEYS case LSM_AUDIT_DATA_KEY: audit_log_format(ab, " key_serial=%u", a->u.key_struct.key); if (a->u.key_struct.key_desc) { audit_log_format(ab, " key_desc="); audit_log_untrustedstring(ab, a->u.key_struct.key_desc); } break; #endif case LSM_AUDIT_DATA_KMOD: audit_log_format(ab, " kmod="); audit_log_untrustedstring(ab, a->u.kmod_name); break; case LSM_AUDIT_DATA_IBPKEY: { struct in6_addr sbn_pfx; memset(&sbn_pfx.s6_addr, 0, sizeof(sbn_pfx.s6_addr)); memcpy(&sbn_pfx.s6_addr, &a->u.ibpkey->subnet_prefix, sizeof(a->u.ibpkey->subnet_prefix)); audit_log_format(ab, " pkey=0x%x subnet_prefix=%pI6c", a->u.ibpkey->pkey, &sbn_pfx); break; } case LSM_AUDIT_DATA_IBENDPORT: audit_log_format(ab, " device=%s port_num=%u", a->u.ibendport->dev_name, a->u.ibendport->port); break; case LSM_AUDIT_DATA_LOCKDOWN: audit_log_format(ab, " lockdown_reason=\"%s\"", lockdown_reasons[a->u.reason]); break; } /* switch (a->type) */ } /** * common_lsm_audit - generic LSM auditing function * @a: auxiliary audit data * @pre_audit: lsm-specific pre-audit callback * @post_audit: lsm-specific post-audit callback * * setup the audit buffer for common security information * uses callback to print LSM specific information */ void common_lsm_audit(struct common_audit_data *a, void (*pre_audit)(struct audit_buffer *, void *), void (*post_audit)(struct audit_buffer *, void *)) { struct audit_buffer *ab; if (a == NULL) return; /* we use GFP_ATOMIC so we won't sleep */ ab = audit_log_start(audit_context(), GFP_ATOMIC | __GFP_NOWARN, AUDIT_AVC); if (ab == NULL) return; if (pre_audit) pre_audit(ab, a); dump_common_audit_data(ab, a); if (post_audit) post_audit(ab, a); audit_log_end(ab); } |
| 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 | /* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* Copyright (c) 2002-2007 Volkswagen Group Electronic Research * Copyright (c) 2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de> * * 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 name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * 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. * */ #ifndef CAN_ML_H #define CAN_ML_H #include <linux/can.h> #include <linux/list.h> #include <linux/netdevice.h> #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS) #define CAN_EFF_RCV_HASH_BITS 10 #define CAN_EFF_RCV_ARRAY_SZ (1 << CAN_EFF_RCV_HASH_BITS) enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_MAX }; struct can_dev_rcv_lists { struct hlist_head rx[RX_MAX]; struct hlist_head rx_sff[CAN_SFF_RCV_ARRAY_SZ]; struct hlist_head rx_eff[CAN_EFF_RCV_ARRAY_SZ]; int entries; }; struct can_ml_priv { struct can_dev_rcv_lists dev_rcv_lists; #ifdef CAN_J1939 struct j1939_priv *j1939_priv; #endif }; static inline struct can_ml_priv *can_get_ml_priv(struct net_device *dev) { return netdev_get_ml_priv(dev, ML_PRIV_CAN); } static inline void can_set_ml_priv(struct net_device *dev, struct can_ml_priv *ml_priv) { netdev_set_ml_priv(dev, ml_priv, ML_PRIV_CAN); } #endif /* CAN_ML_H */ |
| 4 67 69 70 70 66 4 69 66 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/ethtool_netlink.h> #include <linux/bitmap.h> #include "netlink.h" #include "bitset.h" /* Some bitmaps are internally represented as an array of unsigned long, some * as an array of u32 (some even as single u32 for now). To avoid the need of * wrappers on caller side, we provide two set of functions: those with "32" * suffix in their names expect u32 based bitmaps, those without it expect * unsigned long bitmaps. */ static u32 ethnl_lower_bits(unsigned int n) { return ~(u32)0 >> (32 - n % 32); } static u32 ethnl_upper_bits(unsigned int n) { return ~(u32)0 << (n % 32); } /** * ethnl_bitmap32_clear() - Clear u32 based bitmap * @dst: bitmap to clear * @start: beginning of the interval * @end: end of the interval * @mod: set if bitmap was modified * * Clear @nbits bits of a bitmap with indices @start <= i < @end */ static void ethnl_bitmap32_clear(u32 *dst, unsigned int start, unsigned int end, bool *mod) { unsigned int start_word = start / 32; unsigned int end_word = end / 32; unsigned int i; u32 mask; if (end <= start) return; if (start % 32) { mask = ethnl_upper_bits(start); if (end_word == start_word) { mask &= ethnl_lower_bits(end); if (dst[start_word] & mask) { dst[start_word] &= ~mask; *mod = true; } return; } if (dst[start_word] & mask) { dst[start_word] &= ~mask; *mod = true; } start_word++; } for (i = start_word; i < end_word; i++) { if (dst[i]) { dst[i] = 0; *mod = true; } } if (end % 32) { mask = ethnl_lower_bits(end); if (dst[end_word] & mask) { dst[end_word] &= ~mask; *mod = true; } } } /** * ethnl_bitmap32_not_zero() - Check if any bit is set in an interval * @map: bitmap to test * @start: beginning of the interval * @end: end of the interval * * Return: true if there is non-zero bit with index @start <= i < @end, * false if the whole interval is zero */ static bool ethnl_bitmap32_not_zero(const u32 *map, unsigned int start, unsigned int end) { unsigned int start_word = start / 32; unsigned int end_word = end / 32; u32 mask; if (end <= start) return true; if (start % 32) { mask = ethnl_upper_bits(start); if (end_word == start_word) { mask &= ethnl_lower_bits(end); return map[start_word] & mask; } if (map[start_word] & mask) return true; start_word++; } if (!memchr_inv(map + start_word, '\0', (end_word - start_word) * sizeof(u32))) return true; if (end % 32 == 0) return true; return map[end_word] & ethnl_lower_bits(end); } /** * ethnl_bitmap32_update() - Modify u32 based bitmap according to value/mask * pair * @dst: bitmap to update * @nbits: bit size of the bitmap * @value: values to set * @mask: mask of bits to set * @mod: set to true if bitmap is modified, preserve if not * * Set bits in @dst bitmap which are set in @mask to values from @value, leave * the rest untouched. If destination bitmap was modified, set @mod to true, * leave as it is if not. */ static void ethnl_bitmap32_update(u32 *dst, unsigned int nbits, const u32 *value, const u32 *mask, bool *mod) { while (nbits > 0) { u32 real_mask = mask ? *mask : ~(u32)0; u32 new_value; if (nbits < 32) real_mask &= ethnl_lower_bits(nbits); new_value = (*dst & ~real_mask) | (*value & real_mask); if (new_value != *dst) { *dst = new_value; *mod = true; } if (nbits <= 32) break; dst++; nbits -= 32; value++; if (mask) mask++; } } static bool ethnl_bitmap32_test_bit(const u32 *map, unsigned int index) { return map[index / 32] & (1U << (index % 32)); } /** * ethnl_bitset32_size() - Calculate size of bitset nested attribute * @val: value bitmap (u32 based) * @mask: mask bitmap (u32 based, optional) * @nbits: bit length of the bitset * @names: array of bit names (optional) * @compact: assume compact format for output * * Estimate length of netlink attribute composed by a later call to * ethnl_put_bitset32() call with the same arguments. * * Return: negative error code or attribute length estimate */ int ethnl_bitset32_size(const u32 *val, const u32 *mask, unsigned int nbits, ethnl_string_array_t names, bool compact) { unsigned int len = 0; /* list flag */ if (!mask) len += nla_total_size(sizeof(u32)); /* size */ len += nla_total_size(sizeof(u32)); if (compact) { unsigned int nwords = DIV_ROUND_UP(nbits, 32); /* value, mask */ len += (mask ? 2 : 1) * nla_total_size(nwords * sizeof(u32)); } else { unsigned int bits_len = 0; unsigned int bit_len, i; for (i = 0; i < nbits; i++) { const char *name = names ? names[i] : NULL; if (!ethnl_bitmap32_test_bit(mask ?: val, i)) continue; /* index */ bit_len = nla_total_size(sizeof(u32)); /* name */ if (name) bit_len += ethnl_strz_size(name); /* value */ if (mask && ethnl_bitmap32_test_bit(val, i)) bit_len += nla_total_size(0); /* bit nest */ bits_len += nla_total_size(bit_len); } /* bits nest */ len += nla_total_size(bits_len); } /* outermost nest */ return nla_total_size(len); } /** * ethnl_put_bitset32() - Put a bitset nest into a message * @skb: skb with the message * @attrtype: attribute type for the bitset nest * @val: value bitmap (u32 based) * @mask: mask bitmap (u32 based, optional) * @nbits: bit length of the bitset * @names: array of bit names (optional) * @compact: use compact format for the output * * Compose a nested attribute representing a bitset. If @mask is null, simple * bitmap (bit list) is created, if @mask is provided, represent a value/mask * pair. Bit names are only used in verbose mode and when provided by calller. * * Return: 0 on success, negative error value on error */ int ethnl_put_bitset32(struct sk_buff *skb, int attrtype, const u32 *val, const u32 *mask, unsigned int nbits, ethnl_string_array_t names, bool compact) { struct nlattr *nest; struct nlattr *attr; nest = nla_nest_start(skb, attrtype); if (!nest) return -EMSGSIZE; if (!mask && nla_put_flag(skb, ETHTOOL_A_BITSET_NOMASK)) goto nla_put_failure; if (nla_put_u32(skb, ETHTOOL_A_BITSET_SIZE, nbits)) goto nla_put_failure; if (compact) { unsigned int nwords = DIV_ROUND_UP(nbits, 32); unsigned int nbytes = nwords * sizeof(u32); u32 *dst; attr = nla_reserve(skb, ETHTOOL_A_BITSET_VALUE, nbytes); if (!attr) goto nla_put_failure; dst = nla_data(attr); memcpy(dst, val, nbytes); if (nbits % 32) dst[nwords - 1] &= ethnl_lower_bits(nbits); if (mask) { attr = nla_reserve(skb, ETHTOOL_A_BITSET_MASK, nbytes); if (!attr) goto nla_put_failure; dst = nla_data(attr); memcpy(dst, mask, nbytes); if (nbits % 32) dst[nwords - 1] &= ethnl_lower_bits(nbits); } } else { struct nlattr *bits; unsigned int i; bits = nla_nest_start(skb, ETHTOOL_A_BITSET_BITS); if (!bits) goto nla_put_failure; for (i = 0; i < nbits; i++) { const char *name = names ? names[i] : NULL; if (!ethnl_bitmap32_test_bit(mask ?: val, i)) continue; attr = nla_nest_start(skb, ETHTOOL_A_BITSET_BITS_BIT); if (!attr) goto nla_put_failure; if (nla_put_u32(skb, ETHTOOL_A_BITSET_BIT_INDEX, i)) goto nla_put_failure; if (name && ethnl_put_strz(skb, ETHTOOL_A_BITSET_BIT_NAME, name)) goto nla_put_failure; if (mask && ethnl_bitmap32_test_bit(val, i) && nla_put_flag(skb, ETHTOOL_A_BITSET_BIT_VALUE)) goto nla_put_failure; nla_nest_end(skb, attr); } nla_nest_end(skb, bits); } nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static const struct nla_policy bitset_policy[] = { [ETHTOOL_A_BITSET_NOMASK] = { .type = NLA_FLAG }, [ETHTOOL_A_BITSET_SIZE] = NLA_POLICY_MAX(NLA_U32, ETHNL_MAX_BITSET_SIZE), [ETHTOOL_A_BITSET_BITS] = { .type = NLA_NESTED }, [ETHTOOL_A_BITSET_VALUE] = { .type = NLA_BINARY }, [ETHTOOL_A_BITSET_MASK] = { .type = NLA_BINARY }, }; static const struct nla_policy bit_policy[] = { [ETHTOOL_A_BITSET_BIT_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_BITSET_BIT_NAME] = { .type = NLA_NUL_STRING }, [ETHTOOL_A_BITSET_BIT_VALUE] = { .type = NLA_FLAG }, }; /** * ethnl_bitset_is_compact() - check if bitset attribute represents a compact * bitset * @bitset: nested attribute representing a bitset * @compact: pointer for return value * * Return: 0 on success, negative error code on failure */ int ethnl_bitset_is_compact(const struct nlattr *bitset, bool *compact) { struct nlattr *tb[ARRAY_SIZE(bitset_policy)]; int ret; ret = nla_parse_nested(tb, ARRAY_SIZE(bitset_policy) - 1, bitset, bitset_policy, NULL); if (ret < 0) return ret; if (tb[ETHTOOL_A_BITSET_BITS]) { if (tb[ETHTOOL_A_BITSET_VALUE] || tb[ETHTOOL_A_BITSET_MASK]) return -EINVAL; *compact = false; return 0; } if (!tb[ETHTOOL_A_BITSET_SIZE] || !tb[ETHTOOL_A_BITSET_VALUE]) return -EINVAL; *compact = true; return 0; } /** * ethnl_name_to_idx() - look up string index for a name * @names: array of ETH_GSTRING_LEN sized strings * @n_names: number of strings in the array * @name: name to look up * * Return: index of the string if found, -ENOENT if not found */ static int ethnl_name_to_idx(ethnl_string_array_t names, unsigned int n_names, const char *name) { unsigned int i; if (!names) return -ENOENT; for (i = 0; i < n_names; i++) { /* names[i] may not be null terminated */ if (!strncmp(names[i], name, ETH_GSTRING_LEN) && strlen(name) <= ETH_GSTRING_LEN) return i; } return -ENOENT; } static int ethnl_parse_bit(unsigned int *index, bool *val, unsigned int nbits, const struct nlattr *bit_attr, bool no_mask, ethnl_string_array_t names, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(bit_policy)]; int ret, idx; ret = nla_parse_nested(tb, ARRAY_SIZE(bit_policy) - 1, bit_attr, bit_policy, extack); if (ret < 0) return ret; if (tb[ETHTOOL_A_BITSET_BIT_INDEX]) { const char *name; idx = nla_get_u32(tb[ETHTOOL_A_BITSET_BIT_INDEX]); if (idx >= nbits) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_BIT_INDEX], "bit index too high"); return -EOPNOTSUPP; } name = names ? names[idx] : NULL; if (tb[ETHTOOL_A_BITSET_BIT_NAME] && name && strncmp(nla_data(tb[ETHTOOL_A_BITSET_BIT_NAME]), name, nla_len(tb[ETHTOOL_A_BITSET_BIT_NAME]))) { NL_SET_ERR_MSG_ATTR(extack, bit_attr, "bit index and name mismatch"); return -EINVAL; } } else if (tb[ETHTOOL_A_BITSET_BIT_NAME]) { idx = ethnl_name_to_idx(names, nbits, nla_data(tb[ETHTOOL_A_BITSET_BIT_NAME])); if (idx < 0) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_BIT_NAME], "bit name not found"); return -EOPNOTSUPP; } } else { NL_SET_ERR_MSG_ATTR(extack, bit_attr, "neither bit index nor name specified"); return -EINVAL; } *index = idx; *val = no_mask || tb[ETHTOOL_A_BITSET_BIT_VALUE]; return 0; } /** * ethnl_bitmap32_equal() - Compare two bitmaps * @map1: first bitmap * @map2: second bitmap * @nbits: bit size to compare * * Return: true if first @nbits are equal, false if not */ static bool ethnl_bitmap32_equal(const u32 *map1, const u32 *map2, unsigned int nbits) { if (memcmp(map1, map2, nbits / 32 * sizeof(u32))) return false; if (nbits % 32 == 0) return true; return !((map1[nbits / 32] ^ map2[nbits / 32]) & ethnl_lower_bits(nbits % 32)); } static int ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, const struct nlattr *attr, struct nlattr **tb, ethnl_string_array_t names, struct netlink_ext_ack *extack, bool *mod) { u32 *saved_bitmap = NULL; struct nlattr *bit_attr; bool no_mask; int rem; int ret; if (tb[ETHTOOL_A_BITSET_VALUE]) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_VALUE], "value only allowed in compact bitset"); return -EINVAL; } if (tb[ETHTOOL_A_BITSET_MASK]) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_MASK], "mask only allowed in compact bitset"); return -EINVAL; } no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; if (no_mask) { unsigned int nwords = DIV_ROUND_UP(nbits, 32); unsigned int nbytes = nwords * sizeof(u32); bool dummy; /* The bitmap size is only the size of the map part without * its mask part. */ saved_bitmap = kcalloc(nwords, sizeof(u32), GFP_KERNEL); if (!saved_bitmap) return -ENOMEM; memcpy(saved_bitmap, bitmap, nbytes); ethnl_bitmap32_clear(bitmap, 0, nbits, &dummy); } nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) { bool old_val, new_val; unsigned int idx; if (nla_type(bit_attr) != ETHTOOL_A_BITSET_BITS_BIT) { NL_SET_ERR_MSG_ATTR(extack, bit_attr, "only ETHTOOL_A_BITSET_BITS_BIT allowed in ETHTOOL_A_BITSET_BITS"); kfree(saved_bitmap); return -EINVAL; } ret = ethnl_parse_bit(&idx, &new_val, nbits, bit_attr, no_mask, names, extack); if (ret < 0) { kfree(saved_bitmap); return ret; } old_val = bitmap[idx / 32] & ((u32)1 << (idx % 32)); if (new_val != old_val) { if (new_val) bitmap[idx / 32] |= ((u32)1 << (idx % 32)); else bitmap[idx / 32] &= ~((u32)1 << (idx % 32)); if (!no_mask) *mod = true; } } if (no_mask && !ethnl_bitmap32_equal(saved_bitmap, bitmap, nbits)) *mod = true; kfree(saved_bitmap); return 0; } static int ethnl_compact_sanity_checks(unsigned int nbits, const struct nlattr *nest, struct nlattr **tb, struct netlink_ext_ack *extack) { bool no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; unsigned int attr_nbits, attr_nwords; const struct nlattr *test_attr; if (no_mask && tb[ETHTOOL_A_BITSET_MASK]) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_MASK], "mask not allowed in list bitset"); return -EINVAL; } if (!tb[ETHTOOL_A_BITSET_SIZE]) { NL_SET_ERR_MSG_ATTR(extack, nest, "missing size in compact bitset"); return -EINVAL; } if (!tb[ETHTOOL_A_BITSET_VALUE]) { NL_SET_ERR_MSG_ATTR(extack, nest, "missing value in compact bitset"); return -EINVAL; } if (!no_mask && !tb[ETHTOOL_A_BITSET_MASK]) { NL_SET_ERR_MSG_ATTR(extack, nest, "missing mask in compact nonlist bitset"); return -EINVAL; } attr_nbits = nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]); attr_nwords = DIV_ROUND_UP(attr_nbits, 32); if (nla_len(tb[ETHTOOL_A_BITSET_VALUE]) != attr_nwords * sizeof(u32)) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_VALUE], "bitset value length does not match size"); return -EINVAL; } if (tb[ETHTOOL_A_BITSET_MASK] && nla_len(tb[ETHTOOL_A_BITSET_MASK]) != attr_nwords * sizeof(u32)) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_MASK], "bitset mask length does not match size"); return -EINVAL; } if (attr_nbits <= nbits) return 0; test_attr = no_mask ? tb[ETHTOOL_A_BITSET_VALUE] : tb[ETHTOOL_A_BITSET_MASK]; if (ethnl_bitmap32_not_zero(nla_data(test_attr), nbits, attr_nbits)) { NL_SET_ERR_MSG_ATTR(extack, test_attr, "cannot modify bits past kernel bitset size"); return -EINVAL; } return 0; } /** * ethnl_update_bitset32() - Apply a bitset nest to a u32 based bitmap * @bitmap: bitmap to update * @nbits: size of the updated bitmap in bits * @attr: nest attribute to parse and apply * @names: array of bit names; may be null for compact format * @extack: extack for error reporting * @mod: set this to true if bitmap is modified, leave as it is if not * * Apply bitset netsted attribute to a bitmap. If the attribute represents * a bit list, @bitmap is set to its contents; otherwise, bits in mask are * set to values from value. Bitmaps in the attribute may be longer than * @nbits but the message must not request modifying any bits past @nbits. * * Return: negative error code on failure, 0 on success */ int ethnl_update_bitset32(u32 *bitmap, unsigned int nbits, const struct nlattr *attr, ethnl_string_array_t names, struct netlink_ext_ack *extack, bool *mod) { struct nlattr *tb[ARRAY_SIZE(bitset_policy)]; unsigned int change_bits; bool no_mask; int ret; if (!attr) return 0; ret = nla_parse_nested(tb, ARRAY_SIZE(bitset_policy) - 1, attr, bitset_policy, extack); if (ret < 0) return ret; if (tb[ETHTOOL_A_BITSET_BITS]) return ethnl_update_bitset32_verbose(bitmap, nbits, attr, tb, names, extack, mod); ret = ethnl_compact_sanity_checks(nbits, attr, tb, extack); if (ret < 0) return ret; no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; change_bits = min_t(unsigned int, nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]), nbits); ethnl_bitmap32_update(bitmap, change_bits, nla_data(tb[ETHTOOL_A_BITSET_VALUE]), no_mask ? NULL : nla_data(tb[ETHTOOL_A_BITSET_MASK]), mod); if (no_mask && change_bits < nbits) ethnl_bitmap32_clear(bitmap, change_bits, nbits, mod); return 0; } /** * ethnl_parse_bitset() - Compute effective value and mask from bitset nest * @val: unsigned long based bitmap to put value into * @mask: unsigned long based bitmap to put mask into * @nbits: size of @val and @mask bitmaps * @attr: nest attribute to parse and apply * @names: array of bit names; may be null for compact format * @extack: extack for error reporting * * Provide @nbits size long bitmaps for value and mask so that * x = (val & mask) | (x & ~mask) would modify any @nbits sized bitmap x * the same way ethnl_update_bitset() with the same bitset attribute would. * * Return: negative error code on failure, 0 on success */ int ethnl_parse_bitset(unsigned long *val, unsigned long *mask, unsigned int nbits, const struct nlattr *attr, ethnl_string_array_t names, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(bitset_policy)]; const struct nlattr *bit_attr; bool no_mask; int rem; int ret; if (!attr) return 0; ret = nla_parse_nested(tb, ARRAY_SIZE(bitset_policy) - 1, attr, bitset_policy, extack); if (ret < 0) return ret; no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; if (!tb[ETHTOOL_A_BITSET_BITS]) { unsigned int change_bits; ret = ethnl_compact_sanity_checks(nbits, attr, tb, extack); if (ret < 0) return ret; change_bits = nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]); if (change_bits > nbits) change_bits = nbits; bitmap_from_arr32(val, nla_data(tb[ETHTOOL_A_BITSET_VALUE]), change_bits); if (change_bits < nbits) bitmap_clear(val, change_bits, nbits - change_bits); if (no_mask) { bitmap_fill(mask, nbits); } else { bitmap_from_arr32(mask, nla_data(tb[ETHTOOL_A_BITSET_MASK]), change_bits); if (change_bits < nbits) bitmap_clear(mask, change_bits, nbits - change_bits); } return 0; } if (tb[ETHTOOL_A_BITSET_VALUE]) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_VALUE], "value only allowed in compact bitset"); return -EINVAL; } if (tb[ETHTOOL_A_BITSET_MASK]) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_MASK], "mask only allowed in compact bitset"); return -EINVAL; } bitmap_zero(val, nbits); if (no_mask) bitmap_fill(mask, nbits); else bitmap_zero(mask, nbits); nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) { unsigned int idx; bool bit_val; ret = ethnl_parse_bit(&idx, &bit_val, nbits, bit_attr, no_mask, names, extack); if (ret < 0) return ret; if (bit_val) __set_bit(idx, val); if (!no_mask) __set_bit(idx, mask); } return 0; } #if BITS_PER_LONG == 64 && defined(__BIG_ENDIAN) /* 64-bit big endian architectures are the only case when u32 based bitmaps * and unsigned long based bitmaps have different memory layout so that we * cannot simply cast the latter to the former and need actual wrappers * converting the latter to the former. * * To reduce the number of slab allocations, the wrappers use fixed size local * variables for bitmaps up to ETHNL_SMALL_BITMAP_BITS bits which is the * majority of bitmaps used by ethtool. */ #define ETHNL_SMALL_BITMAP_BITS 128 #define ETHNL_SMALL_BITMAP_WORDS DIV_ROUND_UP(ETHNL_SMALL_BITMAP_BITS, 32) int ethnl_bitset_size(const unsigned long *val, const unsigned long *mask, unsigned int nbits, ethnl_string_array_t names, bool compact) { u32 small_mask32[ETHNL_SMALL_BITMAP_WORDS]; u32 small_val32[ETHNL_SMALL_BITMAP_WORDS]; u32 *mask32; u32 *val32; int ret; if (nbits > ETHNL_SMALL_BITMAP_BITS) { unsigned int nwords = DIV_ROUND_UP(nbits, 32); val32 = kmalloc_array(2 * nwords, sizeof(u32), GFP_KERNEL); if (!val32) return -ENOMEM; mask32 = val32 + nwords; } else { val32 = small_val32; mask32 = small_mask32; } bitmap_to_arr32(val32, val, nbits); if (mask) bitmap_to_arr32(mask32, mask, nbits); else mask32 = NULL; ret = ethnl_bitset32_size(val32, mask32, nbits, names, compact); if (nbits > ETHNL_SMALL_BITMAP_BITS) kfree(val32); return ret; } int ethnl_put_bitset(struct sk_buff *skb, int attrtype, const unsigned long *val, const unsigned long *mask, unsigned int nbits, ethnl_string_array_t names, bool compact) { u32 small_mask32[ETHNL_SMALL_BITMAP_WORDS]; u32 small_val32[ETHNL_SMALL_BITMAP_WORDS]; u32 *mask32; u32 *val32; int ret; if (nbits > ETHNL_SMALL_BITMAP_BITS) { unsigned int nwords = DIV_ROUND_UP(nbits, 32); val32 = kmalloc_array(2 * nwords, sizeof(u32), GFP_KERNEL); if (!val32) return -ENOMEM; mask32 = val32 + nwords; } else { val32 = small_val32; mask32 = small_mask32; } bitmap_to_arr32(val32, val, nbits); if (mask) bitmap_to_arr32(mask32, mask, nbits); else mask32 = NULL; ret = ethnl_put_bitset32(skb, attrtype, val32, mask32, nbits, names, compact); if (nbits > ETHNL_SMALL_BITMAP_BITS) kfree(val32); return ret; } int ethnl_update_bitset(unsigned long *bitmap, unsigned int nbits, const struct nlattr *attr, ethnl_string_array_t names, struct netlink_ext_ack *extack, bool *mod) { u32 small_bitmap32[ETHNL_SMALL_BITMAP_WORDS]; u32 *bitmap32 = small_bitmap32; bool u32_mod = false; int ret; if (nbits > ETHNL_SMALL_BITMAP_BITS) { unsigned int dst_words = DIV_ROUND_UP(nbits, 32); bitmap32 = kmalloc_array(dst_words, sizeof(u32), GFP_KERNEL); if (!bitmap32) return -ENOMEM; } bitmap_to_arr32(bitmap32, bitmap, nbits); ret = ethnl_update_bitset32(bitmap32, nbits, attr, names, extack, &u32_mod); if (u32_mod) { bitmap_from_arr32(bitmap, bitmap32, nbits); *mod = true; } if (nbits > ETHNL_SMALL_BITMAP_BITS) kfree(bitmap32); return ret; } #else /* On little endian 64-bit and all 32-bit architectures, an unsigned long * based bitmap can be interpreted as u32 based one using a simple cast. */ int ethnl_bitset_size(const unsigned long *val, const unsigned long *mask, unsigned int nbits, ethnl_string_array_t names, bool compact) { return ethnl_bitset32_size((const u32 *)val, (const u32 *)mask, nbits, names, compact); } int ethnl_put_bitset(struct sk_buff *skb, int attrtype, const unsigned long *val, const unsigned long *mask, unsigned int nbits, ethnl_string_array_t names, bool compact) { return ethnl_put_bitset32(skb, attrtype, (const u32 *)val, (const u32 *)mask, nbits, names, compact); } int ethnl_update_bitset(unsigned long *bitmap, unsigned int nbits, const struct nlattr *attr, ethnl_string_array_t names, struct netlink_ext_ack *extack, bool *mod) { return ethnl_update_bitset32((u32 *)bitmap, nbits, attr, names, extack, mod); } #endif /* BITS_PER_LONG == 64 && defined(__BIG_ENDIAN) */ |
| 415 218 393 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the Forwarding Information Base. * * Authors: A.N.Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #ifndef _NET_IP_FIB_H #define _NET_IP_FIB_H #include <net/flow.h> #include <linux/seq_file.h> #include <linux/rcupdate.h> #include <net/fib_notifier.h> #include <net/fib_rules.h> #include <net/inetpeer.h> #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/refcount.h> struct fib_config { u8 fc_dst_len; u8 fc_tos; u8 fc_protocol; u8 fc_scope; u8 fc_type; u8 fc_gw_family; /* 2 bytes unused */ u32 fc_table; __be32 fc_dst; union { __be32 fc_gw4; struct in6_addr fc_gw6; }; int fc_oif; u32 fc_flags; u32 fc_priority; __be32 fc_prefsrc; u32 fc_nh_id; struct nlattr *fc_mx; struct rtnexthop *fc_mp; int fc_mx_len; int fc_mp_len; u32 fc_flow; u32 fc_nlflags; struct nl_info fc_nlinfo; struct nlattr *fc_encap; u16 fc_encap_type; }; struct fib_info; struct rtable; struct fib_nh_exception { struct fib_nh_exception __rcu *fnhe_next; int fnhe_genid; __be32 fnhe_daddr; u32 fnhe_pmtu; bool fnhe_mtu_locked; __be32 fnhe_gw; unsigned long fnhe_expires; struct rtable __rcu *fnhe_rth_input; struct rtable __rcu *fnhe_rth_output; unsigned long fnhe_stamp; struct rcu_head rcu; }; struct fnhe_hash_bucket { struct fib_nh_exception __rcu *chain; }; #define FNHE_HASH_SHIFT 11 #define FNHE_HASH_SIZE (1 << FNHE_HASH_SHIFT) #define FNHE_RECLAIM_DEPTH 5 struct fib_nh_common { struct net_device *nhc_dev; int nhc_oif; unsigned char nhc_scope; u8 nhc_family; u8 nhc_gw_family; unsigned char nhc_flags; struct lwtunnel_state *nhc_lwtstate; union { __be32 ipv4; struct in6_addr ipv6; } nhc_gw; int nhc_weight; atomic_t nhc_upper_bound; /* v4 specific, but allows fib6_nh with v4 routes */ struct rtable __rcu * __percpu *nhc_pcpu_rth_output; struct rtable __rcu *nhc_rth_input; struct fnhe_hash_bucket __rcu *nhc_exceptions; }; struct fib_nh { struct fib_nh_common nh_common; struct hlist_node nh_hash; struct fib_info *nh_parent; #ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; #endif __be32 nh_saddr; int nh_saddr_genid; #define fib_nh_family nh_common.nhc_family #define fib_nh_dev nh_common.nhc_dev #define fib_nh_oif nh_common.nhc_oif #define fib_nh_flags nh_common.nhc_flags #define fib_nh_lws nh_common.nhc_lwtstate #define fib_nh_scope nh_common.nhc_scope #define fib_nh_gw_family nh_common.nhc_gw_family #define fib_nh_gw4 nh_common.nhc_gw.ipv4 #define fib_nh_gw6 nh_common.nhc_gw.ipv6 #define fib_nh_weight nh_common.nhc_weight #define fib_nh_upper_bound nh_common.nhc_upper_bound }; /* * This structure contains data shared by many of routes. */ struct nexthop; struct fib_info { struct hlist_node fib_hash; struct hlist_node fib_lhash; struct list_head nh_list; struct net *fib_net; refcount_t fib_treeref; refcount_t fib_clntref; unsigned int fib_flags; unsigned char fib_dead; unsigned char fib_protocol; unsigned char fib_scope; unsigned char fib_type; __be32 fib_prefsrc; u32 fib_tb_id; u32 fib_priority; struct dst_metrics *fib_metrics; #define fib_mtu fib_metrics->metrics[RTAX_MTU-1] #define fib_window fib_metrics->metrics[RTAX_WINDOW-1] #define fib_rtt fib_metrics->metrics[RTAX_RTT-1] #define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1] int fib_nhs; bool fib_nh_is_v6; bool nh_updated; struct nexthop *nh; struct rcu_head rcu; struct fib_nh fib_nh[]; }; #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rule; #endif struct fib_table; struct fib_result { __be32 prefix; unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; u32 tclassid; struct fib_nh_common *nhc; struct fib_info *fi; struct fib_table *table; struct hlist_head *fa_head; }; struct fib_result_nl { __be32 fl_addr; /* To be looked up*/ u32 fl_mark; unsigned char fl_tos; unsigned char fl_scope; unsigned char tb_id_in; unsigned char tb_id; /* Results */ unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; int err; }; #ifdef CONFIG_IP_MULTIPLE_TABLES #define FIB_TABLE_HASHSZ 256 #else #define FIB_TABLE_HASHSZ 2 #endif __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, unsigned char scope); __be32 fib_result_prefsrc(struct net *net, struct fib_result *res); #define FIB_RES_NHC(res) ((res).nhc) #define FIB_RES_DEV(res) (FIB_RES_NHC(res)->nhc_dev) #define FIB_RES_OIF(res) (FIB_RES_NHC(res)->nhc_oif) struct fib_rt_info { struct fib_info *fi; u32 tb_id; __be32 dst; int dst_len; u8 tos; u8 type; u8 offload:1, trap:1, offload_failed:1, unused:5; }; struct fib_entry_notifier_info { struct fib_notifier_info info; /* must be first */ u32 dst; int dst_len; struct fib_info *fi; u8 tos; u8 type; u32 tb_id; }; struct fib_nh_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib_nh *fib_nh; }; int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); int __net_init fib4_notifier_init(struct net *net); void __net_exit fib4_notifier_exit(struct net *net); void fib_info_notify_update(struct net *net, struct nl_info *info); int fib_notify(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); struct fib_table { struct hlist_node tb_hlist; u32 tb_id; int tb_num_default; struct rcu_head rcu; unsigned long *tb_data; unsigned long __data[]; }; struct fib_dump_filter { u32 table_id; /* filter_set is an optimization that an entry is set */ bool filter_set; bool dump_routes; bool dump_exceptions; unsigned char protocol; unsigned char rt_type; unsigned int flags; struct net_device *dev; }; int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags); int fib_table_insert(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_delete(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter); int fib_table_flush(struct net *net, struct fib_table *table, bool flush_all); struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); #ifndef CONFIG_IP_MULTIPLE_TABLES #define TABLE_LOCAL_INDEX (RT_TABLE_LOCAL & (FIB_TABLE_HASHSZ - 1)) #define TABLE_MAIN_INDEX (RT_TABLE_MAIN & (FIB_TABLE_HASHSZ - 1)) static inline struct fib_table *fib_get_table(struct net *net, u32 id) { struct hlist_node *tb_hlist; struct hlist_head *ptr; ptr = id == RT_TABLE_LOCAL ? &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX] : &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]; tb_hlist = rcu_dereference_rtnl(hlist_first_rcu(ptr)); return hlist_entry(tb_hlist, struct fib_table, tb_hlist); } static inline struct fib_table *fib_new_table(struct net *net, u32 id) { return fib_get_table(net, id); } static inline int fib_lookup(struct net *net, const struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; int err = -ENETUNREACH; rcu_read_lock(); tb = fib_get_table(net, RT_TABLE_MAIN); if (tb) err = fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF); if (err == -EAGAIN) err = -ENETUNREACH; rcu_read_unlock(); return err; } static inline bool fib4_has_custom_rules(const struct net *net) { return false; } static inline bool fib4_rule_default(const struct fib_rule *rule) { return true; } static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static inline unsigned int fib4_rules_seq_read(struct net *net) { return 0; } static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi4 *fl4, struct flow_keys *flkeys) { return false; } #else /* CONFIG_IP_MULTIPLE_TABLES */ int __net_init fib4_rules_init(struct net *net); void __net_exit fib4_rules_exit(struct net *net); struct fib_table *fib_new_table(struct net *net, u32 id); struct fib_table *fib_get_table(struct net *net, u32 id); int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags); static inline int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; int err = -ENETUNREACH; flags |= FIB_LOOKUP_NOREF; if (net->ipv4.fib_has_custom_rules) return __fib_lookup(net, flp, res, flags); rcu_read_lock(); res->tclassid = 0; tb = rcu_dereference_rtnl(net->ipv4.fib_main); if (tb) err = fib_table_lookup(tb, flp, res, flags); if (!err) goto out; tb = rcu_dereference_rtnl(net->ipv4.fib_default); if (tb) err = fib_table_lookup(tb, flp, res, flags); out: if (err == -EAGAIN) err = -ENETUNREACH; rcu_read_unlock(); return err; } static inline bool fib4_has_custom_rules(const struct net *net) { return net->ipv4.fib_has_custom_rules; } bool fib4_rule_default(const struct fib_rule *rule); int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); unsigned int fib4_rules_seq_read(struct net *net); static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi4 *fl4, struct flow_keys *flkeys) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; if (!net->ipv4.fib_rules_require_fldissect) return false; memset(flkeys, 0, sizeof(*flkeys)); __skb_flow_dissect(net, skb, &flow_keys_dissector, flkeys, NULL, 0, 0, 0, flag); fl4->fl4_sport = flkeys->ports.src; fl4->fl4_dport = flkeys->ports.dst; fl4->flowi4_proto = flkeys->basic.ip_proto; return true; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ /* Exported by fib_frontend.c */ extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, struct netlink_ext_ack *extack); __be32 fib_compute_spec_dst(struct sk_buff *skb); bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev); int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, struct in_device *idev, u32 *itag); #ifdef CONFIG_IP_ROUTE_CLASSID static inline int fib_num_tclassid_users(struct net *net) { return atomic_read(&net->ipv4.fib_num_tclassid_users); } #else static inline int fib_num_tclassid_users(struct net *net) { return 0; } #endif int fib_unmerge(struct net *net); static inline bool nhc_l3mdev_matches_dev(const struct fib_nh_common *nhc, const struct net_device *dev) { if (nhc->nhc_dev == dev || l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex) return true; return false; } /* Exported by fib_semantics.c */ int ip_fib_check_default(__be32 gw, struct net_device *dev); int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); int fib_sync_down_addr(struct net_device *dev, __be32 local); int fib_sync_up(struct net_device *dev, unsigned char nh_flags); void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig); /* Fields used for sysctl_fib_multipath_hash_fields. * Common to IPv4 and IPv6. * * Add new fields at the end. This is user API. */ #define FIB_MULTIPATH_HASH_FIELD_SRC_IP BIT(0) #define FIB_MULTIPATH_HASH_FIELD_DST_IP BIT(1) #define FIB_MULTIPATH_HASH_FIELD_IP_PROTO BIT(2) #define FIB_MULTIPATH_HASH_FIELD_FLOWLABEL BIT(3) #define FIB_MULTIPATH_HASH_FIELD_SRC_PORT BIT(4) #define FIB_MULTIPATH_HASH_FIELD_DST_PORT BIT(5) #define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP BIT(6) #define FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP BIT(7) #define FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO BIT(8) #define FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL BIT(9) #define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT BIT(10) #define FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT BIT(11) #define FIB_MULTIPATH_HASH_FIELD_OUTER_MASK \ (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_IP_PROTO | \ FIB_MULTIPATH_HASH_FIELD_FLOWLABEL | \ FIB_MULTIPATH_HASH_FIELD_SRC_PORT | \ FIB_MULTIPATH_HASH_FIELD_DST_PORT) #define FIB_MULTIPATH_HASH_FIELD_INNER_MASK \ (FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO | \ FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL | \ FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT | \ FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) #define FIB_MULTIPATH_HASH_FIELD_ALL_MASK \ (FIB_MULTIPATH_HASH_FIELD_OUTER_MASK | \ FIB_MULTIPATH_HASH_FIELD_INNER_MASK) #define FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK \ (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_IP_PROTO) #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys); #endif int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, struct netlink_ext_ack *extack); void fib_select_multipath(struct fib_result *res, int hash); void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb); int fib_nh_init(struct net *net, struct fib_nh *fib_nh, struct fib_config *cfg, int nh_weight, struct netlink_ext_ack *extack); void fib_nh_release(struct net *net, struct fib_nh *fib_nh); int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc, struct nlattr *fc_encap, u16 fc_encap_type, void *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib_nh_common_release(struct fib_nh_common *nhc); /* Exported by fib_trie.c */ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri); void fib_trie_init(void); struct fib_table *fib_trie_table(u32 id, struct fib_table *alias); bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags, const struct flowi4 *flp); static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { #ifdef CONFIG_IP_ROUTE_CLASSID struct fib_nh_common *nhc = res->nhc; #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); *itag = nh->nh_tclassid << 16; } else { *itag = 0; } #ifdef CONFIG_IP_MULTIPLE_TABLES rtag = res->tclassid; if (*itag == 0) *itag = (rtag<<16); *itag |= (rtag>>16); #endif #endif } void fib_flush(struct net *net); void free_fib_info(struct fib_info *fi); static inline void fib_info_hold(struct fib_info *fi) { refcount_inc(&fi->fib_clntref); } static inline void fib_info_put(struct fib_info *fi) { if (refcount_dec_and_test(&fi->fib_clntref)) free_fib_info(fi); } #ifdef CONFIG_PROC_FS int __net_init fib_proc_init(struct net *net); void __net_exit fib_proc_exit(struct net *net); #else static inline int fib_proc_init(struct net *net) { return 0; } static inline void fib_proc_exit(struct net *net) { } #endif u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr); int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb); int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh, u8 rt_family, unsigned char *flags, bool skip_oif); int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh, int nh_weight, u8 rt_family, u32 nh_tclassid); #endif /* _NET_FIB_H */ |
| 414 423 413 292 414 1 413 413 413 295 293 414 416 416 413 327 291 416 421 422 423 49 423 423 292 423 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2019 Intel Corporation. */ #include <linux/hash.h> #include <linux/bpf.h> #include <linux/filter.h> /* The BPF dispatcher is a multiway branch code generator. The * dispatcher is a mechanism to avoid the performance penalty of an * indirect call, which is expensive when retpolines are enabled. A * dispatch client registers a BPF program into the dispatcher, and if * there is available room in the dispatcher a direct call to the BPF * program will be generated. All calls to the BPF programs called via * the dispatcher will then be a direct call, instead of an * indirect. The dispatcher hijacks a trampoline function it via the * __fentry__ of the trampoline. The trampoline function has the * following signature: * * unsigned int trampoline(const void *ctx, const struct bpf_insn *insnsi, * unsigned int (*bpf_func)(const void *, * const struct bpf_insn *)); */ static struct bpf_dispatcher_prog *bpf_dispatcher_find_prog( struct bpf_dispatcher *d, struct bpf_prog *prog) { int i; for (i = 0; i < BPF_DISPATCHER_MAX; i++) { if (prog == d->progs[i].prog) return &d->progs[i]; } return NULL; } static struct bpf_dispatcher_prog *bpf_dispatcher_find_free( struct bpf_dispatcher *d) { return bpf_dispatcher_find_prog(d, NULL); } static bool bpf_dispatcher_add_prog(struct bpf_dispatcher *d, struct bpf_prog *prog) { struct bpf_dispatcher_prog *entry; if (!prog) return false; entry = bpf_dispatcher_find_prog(d, prog); if (entry) { refcount_inc(&entry->users); return false; } entry = bpf_dispatcher_find_free(d); if (!entry) return false; bpf_prog_inc(prog); entry->prog = prog; refcount_set(&entry->users, 1); d->num_progs++; return true; } static bool bpf_dispatcher_remove_prog(struct bpf_dispatcher *d, struct bpf_prog *prog) { struct bpf_dispatcher_prog *entry; if (!prog) return false; entry = bpf_dispatcher_find_prog(d, prog); if (!entry) return false; if (refcount_dec_and_test(&entry->users)) { entry->prog = NULL; bpf_prog_put(prog); d->num_progs--; return true; } return false; } int __weak arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs) { return -ENOTSUPP; } static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image) { s64 ips[BPF_DISPATCHER_MAX] = {}, *ipsp = &ips[0]; int i; for (i = 0; i < BPF_DISPATCHER_MAX; i++) { if (d->progs[i].prog) *ipsp++ = (s64)(uintptr_t)d->progs[i].prog->bpf_func; } return arch_prepare_bpf_dispatcher(image, &ips[0], d->num_progs); } static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs) { void *old, *new; u32 noff; int err; if (!prev_num_progs) { old = NULL; noff = 0; } else { old = d->image + d->image_off; noff = d->image_off ^ (PAGE_SIZE / 2); } new = d->num_progs ? d->image + noff : NULL; if (new) { if (bpf_dispatcher_prepare(d, new)) return; } err = bpf_arch_text_poke(d->func, BPF_MOD_JUMP, old, new); if (err || !new) return; d->image_off = noff; } void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to) { bool changed = false; int prev_num_progs; if (from == to) return; mutex_lock(&d->mutex); if (!d->image) { d->image = bpf_jit_alloc_exec_page(); if (!d->image) goto out; bpf_image_ksym_add(d->image, &d->ksym); } prev_num_progs = d->num_progs; changed |= bpf_dispatcher_remove_prog(d, from); changed |= bpf_dispatcher_add_prog(d, to); if (!changed) goto out; bpf_dispatcher_update(d, prev_num_progs); out: mutex_unlock(&d->mutex); } |
| 2 1 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * inet6 interface/address list definitions * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #ifndef _NET_IF_INET6_H #define _NET_IF_INET6_H #include <net/snmp.h> #include <linux/ipv6.h> #include <linux/refcount.h> /* inet6_dev.if_flags */ #define IF_RA_OTHERCONF 0x80 #define IF_RA_MANAGED 0x40 #define IF_RA_RCVD 0x20 #define IF_RS_SENT 0x10 #define IF_READY 0x80000000 enum { INET6_IFADDR_STATE_PREDAD, INET6_IFADDR_STATE_DAD, INET6_IFADDR_STATE_POSTDAD, INET6_IFADDR_STATE_ERRDAD, INET6_IFADDR_STATE_DEAD, }; struct inet6_ifaddr { struct in6_addr addr; __u32 prefix_len; __u32 rt_priority; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 valid_lft; __u32 prefered_lft; refcount_t refcnt; spinlock_t lock; int state; __u32 flags; __u8 dad_probes; __u8 stable_privacy_retry; __u16 scope; __u64 dad_nonce; unsigned long cstamp; /* created timestamp */ unsigned long tstamp; /* updated timestamp */ struct delayed_work dad_work; struct inet6_dev *idev; struct fib6_info *rt; struct hlist_node addr_lst; struct list_head if_list; /* * Used to safely traverse idev->addr_list in process context * if the idev->lock needed to protect idev->addr_list cannot be held. * In that case, add the items to this list temporarily and iterate * without holding idev->lock. * See addrconf_ifdown and dev_forward_change. */ struct list_head if_list_aux; struct list_head tmp_list; struct inet6_ifaddr *ifpub; int regen_count; bool tokenized; struct rcu_head rcu; struct in6_addr peer_addr; }; struct ip6_sf_socklist { unsigned int sl_max; unsigned int sl_count; struct rcu_head rcu; struct in6_addr sl_addr[]; }; #define IP6_SFBLOCK 10 /* allocate this many at once */ struct ipv6_mc_socklist { struct in6_addr addr; int ifindex; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ struct ipv6_mc_socklist __rcu *next; struct ip6_sf_socklist __rcu *sflist; struct rcu_head rcu; }; struct ip6_sf_list { struct ip6_sf_list __rcu *sf_next; struct in6_addr sf_addr; unsigned long sf_count[2]; /* include/exclude counts */ unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ struct rcu_head rcu; }; #define MAF_TIMER_RUNNING 0x01 #define MAF_LAST_REPORTER 0x02 #define MAF_LOADED 0x04 #define MAF_NOREPORT 0x08 #define MAF_GSQUERY 0x10 struct ifmcaddr6 { struct in6_addr mca_addr; struct inet6_dev *idev; struct ifmcaddr6 __rcu *next; struct ip6_sf_list __rcu *mca_sources; struct ip6_sf_list __rcu *mca_tomb; unsigned int mca_sfmode; unsigned char mca_crcount; unsigned long mca_sfcount[2]; struct delayed_work mca_work; unsigned int mca_flags; int mca_users; refcount_t mca_refcnt; unsigned long mca_cstamp; unsigned long mca_tstamp; struct rcu_head rcu; }; /* Anycast stuff */ struct ipv6_ac_socklist { struct in6_addr acl_addr; int acl_ifindex; struct ipv6_ac_socklist *acl_next; }; struct ifacaddr6 { struct in6_addr aca_addr; struct fib6_info *aca_rt; struct ifacaddr6 *aca_next; struct hlist_node aca_addr_lst; int aca_users; refcount_t aca_refcnt; unsigned long aca_cstamp; unsigned long aca_tstamp; struct rcu_head rcu; }; #define IFA_HOST IPV6_ADDR_LOOPBACK #define IFA_LINK IPV6_ADDR_LINKLOCAL #define IFA_SITE IPV6_ADDR_SITELOCAL struct ipv6_devstat { struct proc_dir_entry *proc_dir_entry; DEFINE_SNMP_STAT(struct ipstats_mib, ipv6); DEFINE_SNMP_STAT_ATOMIC(struct icmpv6_mib_device, icmpv6dev); DEFINE_SNMP_STAT_ATOMIC(struct icmpv6msg_mib_device, icmpv6msgdev); }; struct inet6_dev { struct net_device *dev; struct list_head addr_list; struct ifmcaddr6 __rcu *mc_list; struct ifmcaddr6 __rcu *mc_tomb; unsigned char mc_qrv; /* Query Robustness Variable */ unsigned char mc_gq_running; unsigned char mc_ifc_count; unsigned char mc_dad_count; unsigned long mc_v1_seen; /* Max time we stay in MLDv1 mode */ unsigned long mc_qi; /* Query Interval */ unsigned long mc_qri; /* Query Response Interval */ unsigned long mc_maxdelay; struct delayed_work mc_gq_work; /* general query work */ struct delayed_work mc_ifc_work; /* interface change work */ struct delayed_work mc_dad_work; /* dad complete mc work */ struct delayed_work mc_query_work; /* mld query work */ struct delayed_work mc_report_work; /* mld report work */ struct sk_buff_head mc_query_queue; /* mld query queue */ struct sk_buff_head mc_report_queue; /* mld report queue */ spinlock_t mc_query_lock; /* mld query queue lock */ spinlock_t mc_report_lock; /* mld query report lock */ struct mutex mc_lock; /* mld global lock */ struct ifacaddr6 *ac_list; rwlock_t lock; refcount_t refcnt; __u32 if_flags; int dead; u32 desync_factor; struct list_head tempaddr_list; struct in6_addr token; struct neigh_parms *nd_parms; struct ipv6_devconf cnf; struct ipv6_devstat stats; struct timer_list rs_timer; __s32 rs_interval; /* in jiffies */ __u8 rs_probes; unsigned long tstamp; /* ipv6InterfaceTable update timestamp */ struct rcu_head rcu; unsigned int ra_mtu; }; static inline void ipv6_eth_mc_map(const struct in6_addr *addr, char *buf) { /* * +-------+-------+-------+-------+-------+-------+ * | 33 | 33 | DST13 | DST14 | DST15 | DST16 | * +-------+-------+-------+-------+-------+-------+ */ buf[0]= 0x33; buf[1]= 0x33; memcpy(buf + 2, &addr->s6_addr32[3], sizeof(__u32)); } static inline void ipv6_arcnet_mc_map(const struct in6_addr *addr, char *buf) { buf[0] = 0x00; } static inline void ipv6_ib_mc_map(const struct in6_addr *addr, const unsigned char *broadcast, char *buf) { unsigned char scope = broadcast[5] & 0xF; buf[0] = 0; /* Reserved */ buf[1] = 0xff; /* Multicast QPN */ buf[2] = 0xff; buf[3] = 0xff; buf[4] = 0xff; buf[5] = 0x10 | scope; /* scope from broadcast address */ buf[6] = 0x60; /* IPv6 signature */ buf[7] = 0x1b; buf[8] = broadcast[8]; /* P_Key */ buf[9] = broadcast[9]; memcpy(buf + 10, addr->s6_addr + 6, 10); } static inline int ipv6_ipgre_mc_map(const struct in6_addr *addr, const unsigned char *broadcast, char *buf) { if ((broadcast[0] | broadcast[1] | broadcast[2] | broadcast[3]) != 0) { memcpy(buf, broadcast, 4); } else { /* v4mapped? */ if ((addr->s6_addr32[0] | addr->s6_addr32[1] | (addr->s6_addr32[2] ^ htonl(0x0000ffff))) != 0) return -EINVAL; memcpy(buf, &addr->s6_addr32[3], 4); } return 0; } #endif |
| 2661 2663 1851 1039 1041 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/spinlock.h> #include <linux/atomic.h> /* * This is an implementation of the notion of "decrement a * reference count, and return locked if it decremented to zero". * * NOTE NOTE NOTE! This is _not_ equivalent to * * if (atomic_dec_and_test(&atomic)) { * spin_lock(&lock); * return 1; * } * return 0; * * because the spin-lock and the decrement must be * "atomic". */ int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock(lock); if (atomic_dec_and_test(atomic)) return 1; spin_unlock(lock); return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock); int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock_irqsave(lock, *flags); if (atomic_dec_and_test(atomic)) return 1; spin_unlock_irqrestore(lock, *flags); return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave); |
| 8 8 7 5 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV4 GSO/GRO offload support * Linux INET implementation * * TCPv4 GSO/GRO support */ #include <linux/indirect_call_wrapper.h> #include <linux/skbuff.h> #include <net/tcp.h> #include <net/protocol.h> static void tcp_gso_tstamp(struct sk_buff *skb, struct sk_buff *gso_skb, unsigned int seq, unsigned int mss) { u32 flags = skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP; u32 ts_seq = skb_shinfo(gso_skb)->tskey; while (skb) { if (before(ts_seq, seq + mss)) { skb_shinfo(skb)->tx_flags |= flags; skb_shinfo(skb)->tskey = ts_seq; return; } skb = skb->next; seq += mss; } } static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb, netdev_features_t features) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)) return ERR_PTR(-EINVAL); if (!pskb_may_pull(skb, sizeof(struct tcphdr))) return ERR_PTR(-EINVAL); if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { const struct iphdr *iph = ip_hdr(skb); struct tcphdr *th = tcp_hdr(skb); /* Set up checksum pseudo header, usually expect stack to * have done this already. */ th->check = 0; skb->ip_summed = CHECKSUM_PARTIAL; __tcp_v4_send_check(skb, iph->saddr, iph->daddr); } return tcp_gso_segment(skb, features); } struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int sum_truesize = 0; struct tcphdr *th; unsigned int thlen; unsigned int seq; __be32 delta; unsigned int oldlen; unsigned int mss; struct sk_buff *gso_skb = skb; __sum16 newcheck; bool ooo_okay, copy_destructor; th = tcp_hdr(skb); thlen = th->doff * 4; if (thlen < sizeof(*th)) goto out; if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb))) goto out; if (!pskb_may_pull(skb, thlen)) goto out; oldlen = (u16)~skb->len; __skb_pull(skb, thlen); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); segs = NULL; goto out; } copy_destructor = gso_skb->destructor == tcp_wfree; ooo_okay = gso_skb->ooo_okay; /* All segments but the first should have ooo_okay cleared */ skb->ooo_okay = 0; segs = skb_segment(skb, features); if (IS_ERR(segs)) goto out; /* Only first segment might have ooo_okay set */ segs->ooo_okay = ooo_okay; /* GSO partial and frag_list segmentation only requires splitting * the frame into an MSS multiple and possibly a remainder, both * cases return a GSO skb. So update the mss now. */ if (skb_is_gso(segs)) mss *= skb_shinfo(segs)->gso_segs; delta = htonl(oldlen + (thlen + mss)); skb = segs; th = tcp_hdr(skb); seq = ntohl(th->seq); if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP)) tcp_gso_tstamp(segs, gso_skb, seq, mss); newcheck = ~csum_fold((__force __wsum)((__force u32)th->check + (__force u32)delta)); while (skb->next) { th->fin = th->psh = 0; th->check = newcheck; if (skb->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(skb, ~th->check); else th->check = gso_make_checksum(skb, ~th->check); seq += mss; if (copy_destructor) { skb->destructor = gso_skb->destructor; skb->sk = gso_skb->sk; sum_truesize += skb->truesize; } skb = skb->next; th = tcp_hdr(skb); th->seq = htonl(seq); th->cwr = 0; } /* Following permits TCP Small Queues to work well with GSO : * The callback to TCP stack will be called at the time last frag * is freed at TX completion, and not right now when gso_skb * is freed by GSO engine */ if (copy_destructor) { int delta; swap(gso_skb->sk, skb->sk); swap(gso_skb->destructor, skb->destructor); sum_truesize += skb->truesize; delta = sum_truesize - gso_skb->truesize; /* In some pathological cases, delta can be negative. * We need to either use refcount_add() or refcount_sub_and_test() */ if (likely(delta >= 0)) refcount_add(delta, &skb->sk->sk_wmem_alloc); else WARN_ON_ONCE(refcount_sub_and_test(-delta, &skb->sk->sk_wmem_alloc)); } delta = htonl(oldlen + (skb_tail_pointer(skb) - skb_transport_header(skb)) + skb->data_len); th->check = ~csum_fold((__force __wsum)((__force u32)th->check + (__force u32)delta)); if (skb->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(skb, ~th->check); else th->check = gso_make_checksum(skb, ~th->check); out: return segs; } struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb) { struct sk_buff *pp = NULL; struct sk_buff *p; struct tcphdr *th; struct tcphdr *th2; unsigned int len; unsigned int thlen; __be32 flags; unsigned int mss = 1; unsigned int hlen; unsigned int off; int flush = 1; int i; off = skb_gro_offset(skb); hlen = off + sizeof(*th); th = skb_gro_header_fast(skb, off); if (skb_gro_header_hard(skb, hlen)) { th = skb_gro_header_slow(skb, hlen, off); if (unlikely(!th)) goto out; } thlen = th->doff * 4; if (thlen < sizeof(*th)) goto out; hlen = off + thlen; if (skb_gro_header_hard(skb, hlen)) { th = skb_gro_header_slow(skb, hlen, off); if (unlikely(!th)) goto out; } skb_gro_pull(skb, thlen); len = skb_gro_len(skb); flags = tcp_flag_word(th); list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; th2 = tcp_hdr(p); if (*(u32 *)&th->source ^ *(u32 *)&th2->source) { NAPI_GRO_CB(p)->same_flow = 0; continue; } goto found; } p = NULL; goto out_check_final; found: /* Include the IP ID check below from the inner most IP hdr */ flush = NAPI_GRO_CB(p)->flush; flush |= (__force int)(flags & TCP_FLAG_CWR); flush |= (__force int)((flags ^ tcp_flag_word(th2)) & ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH)); flush |= (__force int)(th->ack_seq ^ th2->ack_seq); for (i = sizeof(*th); i < thlen; i += 4) flush |= *(u32 *)((u8 *)th + i) ^ *(u32 *)((u8 *)th2 + i); /* When we receive our second frame we can made a decision on if we * continue this flow as an atomic flow with a fixed ID or if we use * an incrementing ID. */ if (NAPI_GRO_CB(p)->flush_id != 1 || NAPI_GRO_CB(p)->count != 1 || !NAPI_GRO_CB(p)->is_atomic) flush |= NAPI_GRO_CB(p)->flush_id; else NAPI_GRO_CB(p)->is_atomic = false; mss = skb_shinfo(p)->gso_size; flush |= (len - 1) >= mss; flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq); #ifdef CONFIG_TLS_DEVICE flush |= p->decrypted ^ skb->decrypted; #endif if (flush || skb_gro_receive(p, skb)) { mss = 1; goto out_check_final; } tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH); out_check_final: flush = len < mss; flush |= (__force int)(flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST | TCP_FLAG_SYN | TCP_FLAG_FIN)); if (p && (!NAPI_GRO_CB(skb)->same_flow || flush)) pp = p; out: NAPI_GRO_CB(skb)->flush |= (flush != 0); return pp; } int tcp_gro_complete(struct sk_buff *skb) { struct tcphdr *th = tcp_hdr(skb); skb->csum_start = (unsigned char *)th - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; if (th->cwr) skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; if (skb->encapsulation) skb->inner_transport_header = skb->transport_header; return 0; } EXPORT_SYMBOL(tcp_gro_complete); INDIRECT_CALLABLE_SCOPE struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) { /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && skb_gro_checksum_validate(skb, IPPROTO_TCP, inet_gro_compute_pseudo)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } return tcp_gro_receive(head, skb); } INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff) { const struct iphdr *iph = ip_hdr(skb); struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, iph->daddr, 0); skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; if (NAPI_GRO_CB(skb)->is_atomic) skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID; return tcp_gro_complete(skb); } static const struct net_offload tcpv4_offload = { .callbacks = { .gso_segment = tcp4_gso_segment, .gro_receive = tcp4_gro_receive, .gro_complete = tcp4_gro_complete, }, }; int __init tcpv4_offload_init(void) { return inet_add_offload(&tcpv4_offload, IPPROTO_TCP); } |
| 12722 9510 12728 12729 9637 9774 9651 1317 1 1320 2220 913 2221 8169 1570 8112 69 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 | // SPDX-License-Identifier: GPL-2.0-or-later /* bit search implementation * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * Copyright (C) 2008 IBM Corporation * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au> * (Inspired by David Howell's find_next_bit implementation) * * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease * size and improve performance, 2015. */ #include <linux/bitops.h> #include <linux/bitmap.h> #include <linux/export.h> #include <linux/math.h> #include <linux/minmax.h> #include <linux/swab.h> #if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) || \ !defined(find_next_and_bit) /* * This is a common helper function for find_next_bit, find_next_zero_bit, and * find_next_and_bit. The differences are: * - The "invert" argument, which is XORed with each fetched word before * searching it for one bits. * - The optional "addr2", which is anded with "addr1" if present. */ unsigned long _find_next_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start, unsigned long invert, unsigned long le) { unsigned long tmp, mask; if (unlikely(start >= nbits)) return nbits; tmp = addr1[start / BITS_PER_LONG]; if (addr2) tmp &= addr2[start / BITS_PER_LONG]; tmp ^= invert; /* Handle 1st word. */ mask = BITMAP_FIRST_WORD_MASK(start); if (le) mask = swab(mask); tmp &= mask; start = round_down(start, BITS_PER_LONG); while (!tmp) { start += BITS_PER_LONG; if (start >= nbits) return nbits; tmp = addr1[start / BITS_PER_LONG]; if (addr2) tmp &= addr2[start / BITS_PER_LONG]; tmp ^= invert; } if (le) tmp = swab(tmp); return min(start + __ffs(tmp), nbits); } EXPORT_SYMBOL(_find_next_bit); #endif #ifndef find_first_bit /* * Find the first set bit in a memory region. */ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; for (idx = 0; idx * BITS_PER_LONG < size; idx++) { if (addr[idx]) return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size); } return size; } EXPORT_SYMBOL(_find_first_bit); #endif #ifndef find_first_zero_bit /* * Find the first cleared bit in a memory region. */ unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; for (idx = 0; idx * BITS_PER_LONG < size; idx++) { if (addr[idx] != ~0UL) return min(idx * BITS_PER_LONG + ffz(addr[idx]), size); } return size; } EXPORT_SYMBOL(_find_first_zero_bit); #endif #ifndef find_last_bit unsigned long _find_last_bit(const unsigned long *addr, unsigned long size) { if (size) { unsigned long val = BITMAP_LAST_WORD_MASK(size); unsigned long idx = (size-1) / BITS_PER_LONG; do { val &= addr[idx]; if (val) return idx * BITS_PER_LONG + __fls(val); val = ~0ul; } while (idx--); } return size; } EXPORT_SYMBOL(_find_last_bit); #endif unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, unsigned long size, unsigned long offset) { offset = find_next_bit(addr, size, offset); if (offset == size) return size; offset = round_down(offset, 8); *clump = bitmap_get_value8(addr, offset); return offset; } EXPORT_SYMBOL(find_next_clump8); |
| 26 316 316 1019 80 918 316 55 47 26 1983 1981 1982 1982 1983 904 1208 29 1208 8 917 896 35 1982 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 | // SPDX-License-Identifier: GPL-2.0 /* * Performance events callchain code, extracted from core.c: * * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> */ #include <linux/perf_event.h> #include <linux/slab.h> #include <linux/sched/task_stack.h> #include "internal.h" struct callchain_cpus_entries { struct rcu_head rcu_head; struct perf_callchain_entry *cpu_entries[]; }; int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH; int sysctl_perf_event_max_contexts_per_stack __read_mostly = PERF_MAX_CONTEXTS_PER_STACK; static inline size_t perf_callchain_entry__sizeof(void) { return (sizeof(struct perf_callchain_entry) + sizeof(__u64) * (sysctl_perf_event_max_stack + sysctl_perf_event_max_contexts_per_stack)); } static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]); static atomic_t nr_callchain_events; static DEFINE_MUTEX(callchain_mutex); static struct callchain_cpus_entries *callchain_cpus_entries; __weak void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { } __weak void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { } static void release_callchain_buffers_rcu(struct rcu_head *head) { struct callchain_cpus_entries *entries; int cpu; entries = container_of(head, struct callchain_cpus_entries, rcu_head); for_each_possible_cpu(cpu) kfree(entries->cpu_entries[cpu]); kfree(entries); } static void release_callchain_buffers(void) { struct callchain_cpus_entries *entries; entries = callchain_cpus_entries; RCU_INIT_POINTER(callchain_cpus_entries, NULL); call_rcu(&entries->rcu_head, release_callchain_buffers_rcu); } static int alloc_callchain_buffers(void) { int cpu; int size; struct callchain_cpus_entries *entries; /* * We can't use the percpu allocation API for data that can be * accessed from NMI. Use a temporary manual per cpu allocation * until that gets sorted out. */ size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]); entries = kzalloc(size, GFP_KERNEL); if (!entries) return -ENOMEM; size = perf_callchain_entry__sizeof() * PERF_NR_CONTEXTS; for_each_possible_cpu(cpu) { entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); if (!entries->cpu_entries[cpu]) goto fail; } rcu_assign_pointer(callchain_cpus_entries, entries); return 0; fail: for_each_possible_cpu(cpu) kfree(entries->cpu_entries[cpu]); kfree(entries); return -ENOMEM; } int get_callchain_buffers(int event_max_stack) { int err = 0; int count; mutex_lock(&callchain_mutex); count = atomic_inc_return(&nr_callchain_events); if (WARN_ON_ONCE(count < 1)) { err = -EINVAL; goto exit; } /* * If requesting per event more than the global cap, * return a different error to help userspace figure * this out. * * And also do it here so that we have &callchain_mutex held. */ if (event_max_stack > sysctl_perf_event_max_stack) { err = -EOVERFLOW; goto exit; } if (count == 1) err = alloc_callchain_buffers(); exit: if (err) atomic_dec(&nr_callchain_events); mutex_unlock(&callchain_mutex); return err; } void put_callchain_buffers(void) { if (atomic_dec_and_mutex_lock(&nr_callchain_events, &callchain_mutex)) { release_callchain_buffers(); mutex_unlock(&callchain_mutex); } } struct perf_callchain_entry *get_callchain_entry(int *rctx) { int cpu; struct callchain_cpus_entries *entries; *rctx = get_recursion_context(this_cpu_ptr(callchain_recursion)); if (*rctx == -1) return NULL; entries = rcu_dereference(callchain_cpus_entries); if (!entries) { put_recursion_context(this_cpu_ptr(callchain_recursion), *rctx); return NULL; } cpu = smp_processor_id(); return (((void *)entries->cpu_entries[cpu]) + (*rctx * perf_callchain_entry__sizeof())); } void put_callchain_entry(int rctx) { put_recursion_context(this_cpu_ptr(callchain_recursion), rctx); } struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark) { struct perf_callchain_entry *entry; struct perf_callchain_entry_ctx ctx; int rctx; entry = get_callchain_entry(&rctx); if (!entry) return NULL; ctx.entry = entry; ctx.max_stack = max_stack; ctx.nr = entry->nr = init_nr; ctx.contexts = 0; ctx.contexts_maxed = false; if (kernel && !user_mode(regs)) { if (add_mark) perf_callchain_store_context(&ctx, PERF_CONTEXT_KERNEL); perf_callchain_kernel(&ctx, regs); } if (user) { if (!user_mode(regs)) { if (current->mm) regs = task_pt_regs(current); else regs = NULL; } if (regs) { mm_segment_t fs; if (crosstask) goto exit_put; if (add_mark) perf_callchain_store_context(&ctx, PERF_CONTEXT_USER); fs = force_uaccess_begin(); perf_callchain_user(&ctx, regs); force_uaccess_end(fs); } } exit_put: put_callchain_entry(rctx); return entry; } /* * Used for sysctl_perf_event_max_stack and * sysctl_perf_event_max_contexts_per_stack. */ int perf_event_max_stack_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *value = table->data; int new_value = *value, ret; struct ctl_table new_table = *table; new_table.data = &new_value; ret = proc_dointvec_minmax(&new_table, write, buffer, lenp, ppos); if (ret || !write) return ret; mutex_lock(&callchain_mutex); if (atomic_read(&nr_callchain_events)) ret = -EBUSY; else *value = new_value; mutex_unlock(&callchain_mutex); return ret; } |
| 750 750 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_gact.c Generic actions * * copyright Jamal Hadi Salim (2002-4) */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_gact.h> #include <net/tc_act/tc_gact.h> static unsigned int gact_net_id; static struct tc_action_ops act_gact_ops; #ifdef CONFIG_GACT_PROB static int gact_net_rand(struct tcf_gact *gact) { smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */ if (prandom_u32() % gact->tcfg_pval) return gact->tcf_action; return gact->tcfg_paction; } static int gact_determ(struct tcf_gact *gact) { u32 pack = atomic_inc_return(&gact->packets); smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */ if (pack % gact->tcfg_pval) return gact->tcf_action; return gact->tcfg_paction; } typedef int (*g_rand)(struct tcf_gact *gact); static g_rand gact_rand[MAX_RAND] = { NULL, gact_net_rand, gact_determ }; #endif /* CONFIG_GACT_PROB */ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = { [TCA_GACT_PARMS] = { .len = sizeof(struct tc_gact) }, [TCA_GACT_PROB] = { .len = sizeof(struct tc_gact_p) }, }; static int tcf_gact_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, gact_net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_GACT_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_gact *parm; struct tcf_gact *gact; int ret = 0; u32 index; int err; #ifdef CONFIG_GACT_PROB struct tc_gact_p *p_parm = NULL; #endif if (nla == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_GACT_MAX, nla, gact_policy, NULL); if (err < 0) return err; if (tb[TCA_GACT_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_GACT_PARMS]); index = parm->index; #ifndef CONFIG_GACT_PROB if (tb[TCA_GACT_PROB] != NULL) return -EOPNOTSUPP; #else if (tb[TCA_GACT_PROB]) { p_parm = nla_data(tb[TCA_GACT_PROB]); if (p_parm->ptype >= MAX_RAND) return -EINVAL; if (TC_ACT_EXT_CMP(p_parm->paction, TC_ACT_GOTO_CHAIN)) { NL_SET_ERR_MSG(extack, "goto chain not allowed on fallback"); return -EINVAL; } } #endif err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { ret = tcf_idr_create_from_flags(tn, index, est, a, &act_gact_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (err > 0) { if (bind)/* dont override defaults */ return 0; if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } } else { return err; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; gact = to_gact(*a); spin_lock_bh(&gact->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); #ifdef CONFIG_GACT_PROB if (p_parm) { gact->tcfg_paction = p_parm->paction; gact->tcfg_pval = max_t(u16, 1, p_parm->pval); /* Make sure tcfg_pval is written before tcfg_ptype * coupled with smp_rmb() in gact_net_rand() & gact_determ() */ smp_wmb(); gact->tcfg_ptype = p_parm->ptype; } #endif spin_unlock_bh(&gact->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); return ret; release_idr: tcf_idr_release(*a, bind); return err; } static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_gact *gact = to_gact(a); int action = READ_ONCE(gact->tcf_action); #ifdef CONFIG_GACT_PROB { u32 ptype = READ_ONCE(gact->tcfg_ptype); if (ptype) action = gact_rand[ptype](gact); } #endif tcf_action_update_bstats(&gact->common, skb); if (action == TC_ACT_SHOT) tcf_action_inc_drop_qstats(&gact->common); tcf_lastuse_update(&gact->tcf_tm); return action; } static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_gact *gact = to_gact(a); int action = READ_ONCE(gact->tcf_action); struct tcf_t *tm = &gact->tcf_tm; tcf_action_update_stats(a, bytes, packets, action == TC_ACT_SHOT ? packets : drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_gact *gact = to_gact(a); struct tc_gact opt = { .index = gact->tcf_index, .refcnt = refcount_read(&gact->tcf_refcnt) - ref, .bindcnt = atomic_read(&gact->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&gact->tcf_lock); opt.action = gact->tcf_action; if (nla_put(skb, TCA_GACT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; #ifdef CONFIG_GACT_PROB if (gact->tcfg_ptype) { struct tc_gact_p p_opt = { .paction = gact->tcfg_paction, .pval = gact->tcfg_pval, .ptype = gact->tcfg_ptype, }; if (nla_put(skb, TCA_GACT_PROB, sizeof(p_opt), &p_opt)) goto nla_put_failure; } #endif tcf_tm_dump(&t, &gact->tcf_tm); if (nla_put_64bit(skb, TCA_GACT_TM, sizeof(t), &t, TCA_GACT_PAD)) goto nla_put_failure; spin_unlock_bh(&gact->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&gact->tcf_lock); nlmsg_trim(skb, b); return -1; } static int tcf_gact_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, const struct tc_action_ops *ops, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, gact_net_id); return tcf_generic_walker(tn, skb, cb, type, ops, extack); } static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, gact_net_id); return tcf_idr_search(tn, a, index); } static size_t tcf_gact_get_fill_size(const struct tc_action *act) { size_t sz = nla_total_size(sizeof(struct tc_gact)); /* TCA_GACT_PARMS */ #ifdef CONFIG_GACT_PROB if (to_gact(act)->tcfg_ptype) /* TCA_GACT_PROB */ sz += nla_total_size(sizeof(struct tc_gact_p)); #endif return sz; } static struct tc_action_ops act_gact_ops = { .kind = "gact", .id = TCA_ID_GACT, .owner = THIS_MODULE, .act = tcf_gact_act, .stats_update = tcf_gact_stats_update, .dump = tcf_gact_dump, .init = tcf_gact_init, .walk = tcf_gact_walker, .lookup = tcf_gact_search, .get_fill_size = tcf_gact_get_fill_size, .size = sizeof(struct tcf_gact), }; static __net_init int gact_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, gact_net_id); return tc_action_net_init(net, tn, &act_gact_ops); } static void __net_exit gact_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, gact_net_id); } static struct pernet_operations gact_net_ops = { .init = gact_init_net, .exit_batch = gact_exit_net, .id = &gact_net_id, .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); MODULE_DESCRIPTION("Generic Classifier actions"); MODULE_LICENSE("GPL"); static int __init gact_init_module(void) { #ifdef CONFIG_GACT_PROB pr_info("GACT probability on\n"); #else pr_info("GACT probability NOT on\n"); #endif return tcf_register_action(&act_gact_ops, &gact_net_ops); } static void __exit gact_cleanup_module(void) { tcf_unregister_action(&act_gact_ops, &gact_net_ops); } module_init(gact_init_module); module_exit(gact_cleanup_module); |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Authentication token and access key management * * Copyright (C) 2004, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * See Documentation/security/keys/core.rst for information on keys/keyrings. */ #ifndef _LINUX_KEY_H #define _LINUX_KEY_H #include <linux/types.h> #include <linux/list.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> #include <linux/sysctl.h> #include <linux/rwsem.h> #include <linux/atomic.h> #include <linux/assoc_array.h> #include <linux/refcount.h> #include <linux/time64.h> #ifdef __KERNEL__ #include <linux/uidgid.h> /* key handle serial number */ typedef int32_t key_serial_t; /* key handle permissions mask */ typedef uint32_t key_perm_t; struct key; struct net; #ifdef CONFIG_KEYS #undef KEY_DEBUGGING #define KEY_POS_VIEW 0x01000000 /* possessor can view a key's attributes */ #define KEY_POS_READ 0x02000000 /* possessor can read key payload / view keyring */ #define KEY_POS_WRITE 0x04000000 /* possessor can update key payload / add link to keyring */ #define KEY_POS_SEARCH 0x08000000 /* possessor can find a key in search / search a keyring */ #define KEY_POS_LINK 0x10000000 /* possessor can create a link to a key/keyring */ #define KEY_POS_SETATTR 0x20000000 /* possessor can set key attributes */ #define KEY_POS_ALL 0x3f000000 #define KEY_USR_VIEW 0x00010000 /* user permissions... */ #define KEY_USR_READ 0x00020000 #define KEY_USR_WRITE 0x00040000 #define KEY_USR_SEARCH 0x00080000 #define KEY_USR_LINK 0x00100000 #define KEY_USR_SETATTR 0x00200000 #define KEY_USR_ALL 0x003f0000 #define KEY_GRP_VIEW 0x00000100 /* group permissions... */ #define KEY_GRP_READ 0x00000200 #define KEY_GRP_WRITE 0x00000400 #define KEY_GRP_SEARCH 0x00000800 #define KEY_GRP_LINK 0x00001000 #define KEY_GRP_SETATTR 0x00002000 #define KEY_GRP_ALL 0x00003f00 #define KEY_OTH_VIEW 0x00000001 /* third party permissions... */ #define KEY_OTH_READ 0x00000002 #define KEY_OTH_WRITE 0x00000004 #define KEY_OTH_SEARCH 0x00000008 #define KEY_OTH_LINK 0x00000010 #define KEY_OTH_SETATTR 0x00000020 #define KEY_OTH_ALL 0x0000003f #define KEY_PERM_UNDEF 0xffffffff /* * The permissions required on a key that we're looking up. */ enum key_need_perm { KEY_NEED_UNSPECIFIED, /* Needed permission unspecified */ KEY_NEED_VIEW, /* Require permission to view attributes */ KEY_NEED_READ, /* Require permission to read content */ KEY_NEED_WRITE, /* Require permission to update / modify */ KEY_NEED_SEARCH, /* Require permission to search (keyring) or find (key) */ KEY_NEED_LINK, /* Require permission to link */ KEY_NEED_SETATTR, /* Require permission to change attributes */ KEY_NEED_UNLINK, /* Require permission to unlink key */ KEY_SYSADMIN_OVERRIDE, /* Special: override by CAP_SYS_ADMIN */ KEY_AUTHTOKEN_OVERRIDE, /* Special: override by possession of auth token */ KEY_DEFER_PERM_CHECK, /* Special: permission check is deferred */ }; struct seq_file; struct user_struct; struct signal_struct; struct cred; struct key_type; struct key_owner; struct key_tag; struct keyring_list; struct keyring_name; struct key_tag { struct rcu_head rcu; refcount_t usage; bool removed; /* T when subject removed */ }; struct keyring_index_key { /* [!] If this structure is altered, the union in struct key must change too! */ unsigned long hash; /* Hash value */ union { struct { #ifdef __LITTLE_ENDIAN /* Put desc_len at the LSB of x */ u16 desc_len; char desc[sizeof(long) - 2]; /* First few chars of description */ #else char desc[sizeof(long) - 2]; /* First few chars of description */ u16 desc_len; #endif }; unsigned long x; }; struct key_type *type; struct key_tag *domain_tag; /* Domain of operation */ const char *description; }; union key_payload { void __rcu *rcu_data0; void *data[4]; }; /*****************************************************************************/ /* * key reference with possession attribute handling * * NOTE! key_ref_t is a typedef'd pointer to a type that is not actually * defined. This is because we abuse the bottom bit of the reference to carry a * flag to indicate whether the calling process possesses that key in one of * its keyrings. * * the key_ref_t has been made a separate type so that the compiler can reject * attempts to dereference it without proper conversion. * * the three functions are used to assemble and disassemble references */ typedef struct __key_reference_with_attributes *key_ref_t; static inline key_ref_t make_key_ref(const struct key *key, bool possession) { return (key_ref_t) ((unsigned long) key | possession); } static inline struct key *key_ref_to_ptr(const key_ref_t key_ref) { return (struct key *) ((unsigned long) key_ref & ~1UL); } static inline bool is_key_possessed(const key_ref_t key_ref) { return (unsigned long) key_ref & 1UL; } typedef int (*key_restrict_link_func_t)(struct key *dest_keyring, const struct key_type *type, const union key_payload *payload, struct key *restriction_key); struct key_restriction { key_restrict_link_func_t check; struct key *key; struct key_type *keytype; }; enum key_state { KEY_IS_UNINSTANTIATED, KEY_IS_POSITIVE, /* Positively instantiated */ }; /*****************************************************************************/ /* * authentication token / access credential / keyring * - types of key include: * - keyrings * - disk encryption IDs * - Kerberos TGTs and tickets */ struct key { refcount_t usage; /* number of references */ key_serial_t serial; /* key serial number */ union { struct list_head graveyard_link; struct rb_node serial_node; }; #ifdef CONFIG_KEY_NOTIFICATIONS struct watch_list *watchers; /* Entities watching this key for changes */ #endif struct rw_semaphore sem; /* change vs change sem */ struct key_user *user; /* owner of this key */ void *security; /* security data for this key */ union { time64_t expiry; /* time at which key expires (or 0) */ time64_t revoked_at; /* time at which key was revoked */ }; time64_t last_used_at; /* last time used for LRU keyring discard */ kuid_t uid; kgid_t gid; key_perm_t perm; /* access permissions */ unsigned short quotalen; /* length added to quota */ unsigned short datalen; /* payload data length * - may not match RCU dereferenced payload * - payload should contain own length */ short state; /* Key state (+) or rejection error (-) */ #ifdef KEY_DEBUGGING unsigned magic; #define KEY_DEBUG_MAGIC 0x18273645u #endif unsigned long flags; /* status flags (change with bitops) */ #define KEY_FLAG_DEAD 0 /* set if key type has been deleted */ #define KEY_FLAG_REVOKED 1 /* set if key had been revoked */ #define KEY_FLAG_IN_QUOTA 2 /* set if key consumes quota */ #define KEY_FLAG_USER_CONSTRUCT 3 /* set if key is being constructed in userspace */ #define KEY_FLAG_ROOT_CAN_CLEAR 4 /* set if key can be cleared by root without permission */ #define KEY_FLAG_INVALIDATED 5 /* set if key has been invalidated */ #define KEY_FLAG_BUILTIN 6 /* set if key is built in to the kernel */ #define KEY_FLAG_ROOT_CAN_INVAL 7 /* set if key can be invalidated by root without permission */ #define KEY_FLAG_KEEP 8 /* set if key should not be removed */ #define KEY_FLAG_UID_KEYRING 9 /* set if key is a user or user session keyring */ /* the key type and key description string * - the desc is used to match a key against search criteria * - it should be a printable string * - eg: for krb5 AFS, this might be "afs@REDHAT.COM" */ union { struct keyring_index_key index_key; struct { unsigned long hash; unsigned long len_desc; struct key_type *type; /* type of key */ struct key_tag *domain_tag; /* Domain of operation */ char *description; }; }; /* key data * - this is used to hold the data actually used in cryptography or * whatever */ union { union key_payload payload; struct { /* Keyring bits */ struct list_head name_link; struct assoc_array keys; }; }; /* This is set on a keyring to restrict the addition of a link to a key * to it. If this structure isn't provided then it is assumed that the * keyring is open to any addition. It is ignored for non-keyring * keys. Only set this value using keyring_restrict(), keyring_alloc(), * or key_alloc(). * * This is intended for use with rings of trusted keys whereby addition * to the keyring needs to be controlled. KEY_ALLOC_BYPASS_RESTRICTION * overrides this, allowing the kernel to add extra keys without * restriction. */ struct key_restriction *restrict_link; }; extern struct key *key_alloc(struct key_type *type, const char *desc, kuid_t uid, kgid_t gid, const struct cred *cred, key_perm_t perm, unsigned long flags, struct key_restriction *restrict_link); #define KEY_ALLOC_IN_QUOTA 0x0000 /* add to quota, reject if would overrun */ #define KEY_ALLOC_QUOTA_OVERRUN 0x0001 /* add to quota, permit even if overrun */ #define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */ #define KEY_ALLOC_BUILT_IN 0x0004 /* Key is built into kernel */ #define KEY_ALLOC_BYPASS_RESTRICTION 0x0008 /* Override the check on restricted keyrings */ #define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */ #define KEY_ALLOC_SET_KEEP 0x0020 /* Set the KEEP flag on the key/keyring */ extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); extern void key_put(struct key *key); extern bool key_put_tag(struct key_tag *tag); extern void key_remove_domain(struct key_tag *domain_tag); static inline struct key *__key_get(struct key *key) { refcount_inc(&key->usage); return key; } static inline struct key *key_get(struct key *key) { return key ? __key_get(key) : key; } static inline void key_ref_put(key_ref_t key_ref) { key_put(key_ref_to_ptr(key_ref)); } extern struct key *request_key_tag(struct key_type *type, const char *description, struct key_tag *domain_tag, const char *callout_info); extern struct key *request_key_rcu(struct key_type *type, const char *description, struct key_tag *domain_tag); extern struct key *request_key_with_auxdata(struct key_type *type, const char *description, struct key_tag *domain_tag, const void *callout_info, size_t callout_len, void *aux); /** * request_key - Request a key and wait for construction * @type: Type of key. * @description: The searchable description of the key. * @callout_info: The data to pass to the instantiation upcall (or NULL). * * As for request_key_tag(), but with the default global domain tag. */ static inline struct key *request_key(struct key_type *type, const char *description, const char *callout_info) { return request_key_tag(type, description, NULL, callout_info); } #ifdef CONFIG_NET /** * request_key_net - Request a key for a net namespace and wait for construction * @type: Type of key. * @description: The searchable description of the key. * @net: The network namespace that is the key's domain of operation. * @callout_info: The data to pass to the instantiation upcall (or NULL). * * As for request_key() except that it does not add the returned key to a * keyring if found, new keys are always allocated in the user's quota, the * callout_info must be a NUL-terminated string and no auxiliary data can be * passed. Only keys that operate the specified network namespace are used. * * Furthermore, it then works as wait_for_key_construction() to wait for the * completion of keys undergoing construction with a non-interruptible wait. */ #define request_key_net(type, description, net, callout_info) \ request_key_tag(type, description, net->key_domain, callout_info) /** * request_key_net_rcu - Request a key for a net namespace under RCU conditions * @type: Type of key. * @description: The searchable description of the key. * @net: The network namespace that is the key's domain of operation. * * As for request_key_rcu() except that only keys that operate the specified * network namespace are used. */ #define request_key_net_rcu(type, description, net) \ request_key_rcu(type, description, net->key_domain) #endif /* CONFIG_NET */ extern int wait_for_key_construction(struct key *key, bool intr); extern int key_validate(const struct key *key); extern key_ref_t key_create_or_update(key_ref_t keyring, const char *type, const char *description, const void *payload, size_t plen, key_perm_t perm, unsigned long flags); extern int key_update(key_ref_t key, const void *payload, size_t plen); extern int key_link(struct key *keyring, struct key *key); extern int key_move(struct key *key, struct key *from_keyring, struct key *to_keyring, unsigned int flags); extern int key_unlink(struct key *keyring, struct key *key); extern struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid, const struct cred *cred, key_perm_t perm, unsigned long flags, struct key_restriction *restrict_link, struct key *dest); extern int restrict_link_reject(struct key *keyring, const struct key_type *type, const union key_payload *payload, struct key *restriction_key); extern int keyring_clear(struct key *keyring); extern key_ref_t keyring_search(key_ref_t keyring, struct key_type *type, const char *description, bool recurse); extern int keyring_add_key(struct key *keyring, struct key *key); extern int keyring_restrict(key_ref_t keyring, const char *type, const char *restriction); extern struct key *key_lookup(key_serial_t id); static inline key_serial_t key_serial(const struct key *key) { return key ? key->serial : 0; } extern void key_set_timeout(struct key *, unsigned); extern key_ref_t lookup_user_key(key_serial_t id, unsigned long flags, enum key_need_perm need_perm); extern void key_free_user_ns(struct user_namespace *); static inline short key_read_state(const struct key *key) { /* Barrier versus mark_key_instantiated(). */ return smp_load_acquire(&key->state); } /** * key_is_positive - Determine if a key has been positively instantiated * @key: The key to check. * * Return true if the specified key has been positively instantiated, false * otherwise. */ static inline bool key_is_positive(const struct key *key) { return key_read_state(key) == KEY_IS_POSITIVE; } static inline bool key_is_negative(const struct key *key) { return key_read_state(key) < 0; } #define dereference_key_rcu(KEY) \ (rcu_dereference((KEY)->payload.rcu_data0)) #define dereference_key_locked(KEY) \ (rcu_dereference_protected((KEY)->payload.rcu_data0, \ rwsem_is_locked(&((struct key *)(KEY))->sem))) #define rcu_assign_keypointer(KEY, PAYLOAD) \ do { \ rcu_assign_pointer((KEY)->payload.rcu_data0, (PAYLOAD)); \ } while (0) #ifdef CONFIG_SYSCTL extern struct ctl_table key_sysctls[]; #endif /* * the userspace interface */ extern int install_thread_keyring_to_cred(struct cred *cred); extern void key_fsuid_changed(struct cred *new_cred); extern void key_fsgid_changed(struct cred *new_cred); extern void key_init(void); #else /* CONFIG_KEYS */ #define key_validate(k) 0 #define key_serial(k) 0 #define key_get(k) ({ NULL; }) #define key_revoke(k) do { } while(0) #define key_invalidate(k) do { } while(0) #define key_put(k) do { } while(0) #define key_ref_put(k) do { } while(0) #define make_key_ref(k, p) NULL #define key_ref_to_ptr(k) NULL #define is_key_possessed(k) 0 #define key_fsuid_changed(c) do { } while(0) #define key_fsgid_changed(c) do { } while(0) #define key_init() do { } while(0) #define key_free_user_ns(ns) do { } while(0) #define key_remove_domain(d) do { } while(0) #endif /* CONFIG_KEYS */ #endif /* __KERNEL__ */ #endif /* _LINUX_KEY_H */ |
| 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux NET3: Internet Group Management Protocol [IGMP] * * Authors: * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Extended to talk the BSD extended IGMP protocol of mrouted 3.6 */ #ifndef _LINUX_IGMP_H #define _LINUX_IGMP_H #include <linux/skbuff.h> #include <linux/timer.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/refcount.h> #include <uapi/linux/igmp.h> static inline struct igmphdr *igmp_hdr(const struct sk_buff *skb) { return (struct igmphdr *)skb_transport_header(skb); } static inline struct igmpv3_report * igmpv3_report_hdr(const struct sk_buff *skb) { return (struct igmpv3_report *)skb_transport_header(skb); } static inline struct igmpv3_query * igmpv3_query_hdr(const struct sk_buff *skb) { return (struct igmpv3_query *)skb_transport_header(skb); } struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; struct rcu_head rcu; __be32 sl_addr[]; }; #define IP_SFBLOCK 10 /* allocate this many at once */ /* ip_mc_socklist is real list now. Speed is not argument; this list never used in fast path code */ struct ip_mc_socklist { struct ip_mc_socklist __rcu *next_rcu; struct ip_mreqn multi; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ struct ip_sf_socklist __rcu *sflist; struct rcu_head rcu; }; struct ip_sf_list { struct ip_sf_list *sf_next; unsigned long sf_count[2]; /* include/exclude counts */ __be32 sf_inaddr; unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ }; struct ip_mc_list { struct in_device *interface; __be32 multiaddr; unsigned int sfmode; struct ip_sf_list *sources; struct ip_sf_list *tomb; unsigned long sfcount[2]; union { struct ip_mc_list *next; struct ip_mc_list __rcu *next_rcu; }; struct ip_mc_list __rcu *next_hash; struct timer_list timer; int users; refcount_t refcnt; spinlock_t lock; char tm_running; char reporter; char unsolicit_count; char loaded; unsigned char gsquery; /* check source marks? */ unsigned char crcount; struct rcu_head rcu; }; /* V3 exponential field decoding */ #define IGMPV3_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value)) #define IGMPV3_EXP(thresh, nbmant, nbexp, value) \ ((value) < (thresh) ? (value) : \ ((IGMPV3_MASK(value, nbmant) | (1<<(nbmant))) << \ (IGMPV3_MASK((value) >> (nbmant), nbexp) + (nbexp)))) #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value) static inline int ip_mc_may_pull(struct sk_buff *skb, unsigned int len) { if (skb_transport_offset(skb) + ip_transport_len(skb) < len) return 0; return pskb_may_pull(skb, len); } extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, unsigned int mode); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern void ip_mc_drop_socket(struct sock *sk); extern int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex); extern int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf,int ifindex); extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, sockptr_t optval, sockptr_t optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t offset); extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); extern void ip_mc_up(struct in_device *); extern void ip_mc_down(struct in_device *); extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); extern void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp); static inline void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) { return __ip_mc_dec_group(in_dev, addr, GFP_KERNEL); } extern void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); int ip_mc_check_igmp(struct sk_buff *skb); #endif |
| 190 190 190 1 188 2301 14 2296 5132 3794 4835 4272 3360 2803 865 909 910 909 909 5132 5084 890 89 5364 4882 210 477 3958 5329 202 4078 1070 1073 5134 2291 5356 2 1142 5364 1 583 5328 2 202 2 202 3 5364 7 958 5360 5372 2280 5359 5365 2 1 964 4941 4934 964 4893 4939 1214 4892 4924 4933 4 2 2 2 3 3 1 1 12 5 2 7 3 12 6 6 6 6 6 6 6 6 6 6 2 2 2 2 2 6 4 2 6 6 6 2 2 8 6 2 113 135 20 6 113 1 1 2 6723 6 6728 6512 3 575 201 2290 2291 5802 5806 7 6 5814 1660 3670 5308 1551 4922 136 168 1121 1 3670 1659 2 54 5268 6 5770 5783 3167 5545 6 1549 1551 1 1549 4893 129 129 1 166 3670 1656 2 53 3959 4549 2323 5774 1311 2372 3100 3942 778 779 3420 2794 2794 2 14 1628 1 1 1 50 6 2 5 3 16 2 2 2 3 841 2222 5 969 219 969 6 961 206 6 206 4 3 6 6 199 202 3 202 202 188 2 188 2 188 969 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/lib/vsprintf.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* vsprintf.c -- Lars Wirzenius & Linus Torvalds. */ /* * Wirzenius wrote this portably, Torvalds fucked it up :-) */ /* * Fri Jul 13 2001 Crutcher Dunnavant <crutcher+kernel@datastacks.com> * - changed to provide snprintf and vsnprintf functions * So Feb 1 16:51:32 CET 2004 Juergen Quade <quade@hsnr.de> * - scnprintf and vscnprintf */ #include <linux/stdarg.h> #include <linux/build_bug.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/errname.h> #include <linux/module.h> /* for KSYM_SYMBOL_LEN */ #include <linux/types.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/kernel.h> #include <linux/kallsyms.h> #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/ioport.h> #include <linux/dcache.h> #include <linux/cred.h> #include <linux/rtc.h> #include <linux/time.h> #include <linux/uuid.h> #include <linux/of.h> #include <net/addrconf.h> #include <linux/siphash.h> #include <linux/compiler.h> #include <linux/property.h> #ifdef CONFIG_BLOCK #include <linux/blkdev.h> #endif #include "../mm/internal.h" /* For the trace_print_flags arrays */ #include <asm/page.h> /* for PAGE_SIZE */ #include <asm/byteorder.h> /* cpu_to_le16 */ #include <asm/unaligned.h> #include <linux/string_helpers.h> #include "kstrtox.h" /* Disable pointer hashing if requested */ bool no_hash_pointers __ro_after_init; EXPORT_SYMBOL_GPL(no_hash_pointers); static noinline unsigned long long simple_strntoull(const char *startp, size_t max_chars, char **endp, unsigned int base) { const char *cp; unsigned long long result = 0ULL; size_t prefix_chars; unsigned int rv; cp = _parse_integer_fixup_radix(startp, &base); prefix_chars = cp - startp; if (prefix_chars < max_chars) { rv = _parse_integer_limit(cp, base, &result, max_chars - prefix_chars); /* FIXME */ cp += (rv & ~KSTRTOX_OVERFLOW); } else { /* Field too short for prefix + digit, skip over without converting */ cp = startp + max_chars; } if (endp) *endp = (char *)cp; return result; } /** * simple_strtoull - convert a string to an unsigned long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoull instead. */ noinline unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) { return simple_strntoull(cp, INT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoull); /** * simple_strtoul - convert a string to an unsigned long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoul instead. */ unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base) { return simple_strtoull(cp, endp, base); } EXPORT_SYMBOL(simple_strtoul); /** * simple_strtol - convert a string to a signed long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtol instead. */ long simple_strtol(const char *cp, char **endp, unsigned int base) { if (*cp == '-') return -simple_strtoul(cp + 1, endp, base); return simple_strtoul(cp, endp, base); } EXPORT_SYMBOL(simple_strtol); static long long simple_strntoll(const char *cp, size_t max_chars, char **endp, unsigned int base) { /* * simple_strntoull() safely handles receiving max_chars==0 in the * case cp[0] == '-' && max_chars == 1. * If max_chars == 0 we can drop through and pass it to simple_strntoull() * and the content of *cp is irrelevant. */ if (*cp == '-' && max_chars > 0) return -simple_strntoull(cp + 1, max_chars - 1, endp, base); return simple_strntoull(cp, max_chars, endp, base); } /** * simple_strtoll - convert a string to a signed long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoll instead. */ long long simple_strtoll(const char *cp, char **endp, unsigned int base) { return simple_strntoll(cp, INT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoll); static noinline_for_stack int skip_atoi(const char **s) { int i = 0; do { i = i*10 + *((*s)++) - '0'; } while (isdigit(**s)); return i; } /* * Decimal conversion is by far the most typical, and is used for * /proc and /sys data. This directly impacts e.g. top performance * with many processes running. We optimize it for speed by emitting * two characters at a time, using a 200 byte lookup table. This * roughly halves the number of multiplications compared to computing * the digits one at a time. Implementation strongly inspired by the * previous version, which in turn used ideas described at * <http://www.cs.uiowa.edu/~jones/bcd/divide.html> (with permission * from the author, Douglas W. Jones). * * It turns out there is precisely one 26 bit fixed-point * approximation a of 64/100 for which x/100 == (x * (u64)a) >> 32 * holds for all x in [0, 10^8-1], namely a = 0x28f5c29. The actual * range happens to be somewhat larger (x <= 1073741898), but that's * irrelevant for our purpose. * * For dividing a number in the range [10^4, 10^6-1] by 100, we still * need a 32x32->64 bit multiply, so we simply use the same constant. * * For dividing a number in the range [100, 10^4-1] by 100, there are * several options. The simplest is (x * 0x147b) >> 19, which is valid * for all x <= 43698. */ static const u16 decpair[100] = { #define _(x) (__force u16) cpu_to_le16(((x % 10) | ((x / 10) << 8)) + 0x3030) _( 0), _( 1), _( 2), _( 3), _( 4), _( 5), _( 6), _( 7), _( 8), _( 9), _(10), _(11), _(12), _(13), _(14), _(15), _(16), _(17), _(18), _(19), _(20), _(21), _(22), _(23), _(24), _(25), _(26), _(27), _(28), _(29), _(30), _(31), _(32), _(33), _(34), _(35), _(36), _(37), _(38), _(39), _(40), _(41), _(42), _(43), _(44), _(45), _(46), _(47), _(48), _(49), _(50), _(51), _(52), _(53), _(54), _(55), _(56), _(57), _(58), _(59), _(60), _(61), _(62), _(63), _(64), _(65), _(66), _(67), _(68), _(69), _(70), _(71), _(72), _(73), _(74), _(75), _(76), _(77), _(78), _(79), _(80), _(81), _(82), _(83), _(84), _(85), _(86), _(87), _(88), _(89), _(90), _(91), _(92), _(93), _(94), _(95), _(96), _(97), _(98), _(99), #undef _ }; /* * This will print a single '0' even if r == 0, since we would * immediately jump to out_r where two 0s would be written but only * one of them accounted for in buf. This is needed by ip4_string * below. All other callers pass a non-zero value of r. */ static noinline_for_stack char *put_dec_trunc8(char *buf, unsigned r) { unsigned q; /* 1 <= r < 10^8 */ if (r < 100) goto out_r; /* 100 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 1 <= q < 10^6 */ if (q < 100) goto out_q; /* 100 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 1 <= r < 10^4 */ if (r < 100) goto out_r; /* 100 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; out_q: /* 1 <= q < 100 */ r = q; out_r: /* 1 <= r < 100 */ *((u16 *)buf) = decpair[r]; buf += r < 10 ? 1 : 2; return buf; } #if BITS_PER_LONG == 64 && BITS_PER_LONG_LONG == 64 static noinline_for_stack char *put_dec_full8(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; buf += 2; return buf; } static noinline_for_stack char *put_dec(char *buf, unsigned long long n) { if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n <= 1.6e11 */ if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n < 1e8 */ return put_dec_trunc8(buf, n); } #elif BITS_PER_LONG == 32 && BITS_PER_LONG_LONG == 64 static void put_dec_full4(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; } /* * Call put_dec_full4 on x % 10000, return x / 10000. * The approximation x/10000 == (x * 0x346DC5D7) >> 43 * holds for all x < 1,128,869,999. The largest value this * helper will ever be asked to convert is 1,125,520,955. * (second call in the put_dec code, assuming n is all-ones). */ static noinline_for_stack unsigned put_dec_helper4(char *buf, unsigned x) { uint32_t q = (x * (uint64_t)0x346DC5D7) >> 43; put_dec_full4(buf, x - q * 10000); return q; } /* Based on code by Douglas W. Jones found at * <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour> * (with permission from the author). * Performs no 64-bit division and hence should be fast on 32-bit machines. */ static char *put_dec(char *buf, unsigned long long n) { uint32_t d3, d2, d1, q, h; if (n < 100*1000*1000) return put_dec_trunc8(buf, n); d1 = ((uint32_t)n >> 16); /* implicit "& 0xffff" */ h = (n >> 32); d2 = (h ) & 0xffff; d3 = (h >> 16); /* implicit "& 0xffff" */ /* n = 2^48 d3 + 2^32 d2 + 2^16 d1 + d0 = 281_4749_7671_0656 d3 + 42_9496_7296 d2 + 6_5536 d1 + d0 */ q = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff); q = put_dec_helper4(buf, q); q += 7671 * d3 + 9496 * d2 + 6 * d1; q = put_dec_helper4(buf+4, q); q += 4749 * d3 + 42 * d2; q = put_dec_helper4(buf+8, q); q += 281 * d3; buf += 12; if (q) buf = put_dec_trunc8(buf, q); else while (buf[-1] == '0') --buf; return buf; } #endif /* * Convert passed number to decimal string. * Returns the length of string. On buffer overflow, returns 0. * * If speed is not important, use snprintf(). It's easy to read the code. */ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[sizeof(num) * 3] __aligned(2); int idx, len; /* put_dec() may work incorrectly for num = 0 (generate "", not "0") */ if (num <= 9) { tmp[0] = '0' + num; len = 1; } else { len = put_dec(tmp, num) - tmp; } if (len > size || width > size) return 0; if (width > len) { width = width - len; for (idx = 0; idx < width; idx++) buf[idx] = ' '; } else { width = 0; } for (idx = 0; idx < len; ++idx) buf[idx + width] = tmp[len - idx - 1]; return len + width; } #define SIGN 1 /* unsigned/signed, must be 1 */ #define LEFT 2 /* left justified */ #define PLUS 4 /* show plus */ #define SPACE 8 /* space if plus */ #define ZEROPAD 16 /* pad with zero, must be 16 == '0' - ' ' */ #define SMALL 32 /* use lowercase in hex (must be 32 == 0x20) */ #define SPECIAL 64 /* prefix hex with "0x", octal with "0" */ static_assert(ZEROPAD == ('0' - ' ')); static_assert(SMALL == ' '); enum format_type { FORMAT_TYPE_NONE, /* Just a string part */ FORMAT_TYPE_WIDTH, FORMAT_TYPE_PRECISION, FORMAT_TYPE_CHAR, FORMAT_TYPE_STR, FORMAT_TYPE_PTR, FORMAT_TYPE_PERCENT_CHAR, FORMAT_TYPE_INVALID, FORMAT_TYPE_LONG_LONG, FORMAT_TYPE_ULONG, FORMAT_TYPE_LONG, FORMAT_TYPE_UBYTE, FORMAT_TYPE_BYTE, FORMAT_TYPE_USHORT, FORMAT_TYPE_SHORT, FORMAT_TYPE_UINT, FORMAT_TYPE_INT, FORMAT_TYPE_SIZE_T, FORMAT_TYPE_PTRDIFF }; struct printf_spec { unsigned int type:8; /* format_type enum */ signed int field_width:24; /* width of output field */ unsigned int flags:8; /* flags to number() */ unsigned int base:8; /* number base, 8, 10 or 16 only */ signed int precision:16; /* # of digits/chars */ } __packed; static_assert(sizeof(struct printf_spec) == 8); #define FIELD_WIDTH_MAX ((1 << 23) - 1) #define PRECISION_MAX ((1 << 15) - 1) static noinline_for_stack char *number(char *buf, char *end, unsigned long long num, struct printf_spec spec) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[3 * sizeof(num)] __aligned(2); char sign; char locase; int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10); int i; bool is_zero = num == 0LL; int field_width = spec.field_width; int precision = spec.precision; /* locase = 0 or 0x20. ORing digits or letters with 'locase' * produces same digits or (maybe lowercased) letters */ locase = (spec.flags & SMALL); if (spec.flags & LEFT) spec.flags &= ~ZEROPAD; sign = 0; if (spec.flags & SIGN) { if ((signed long long)num < 0) { sign = '-'; num = -(signed long long)num; field_width--; } else if (spec.flags & PLUS) { sign = '+'; field_width--; } else if (spec.flags & SPACE) { sign = ' '; field_width--; } } if (need_pfx) { if (spec.base == 16) field_width -= 2; else if (!is_zero) field_width--; } /* generate full string in tmp[], in reverse order */ i = 0; if (num < spec.base) tmp[i++] = hex_asc_upper[num] | locase; else if (spec.base != 10) { /* 8 or 16 */ int mask = spec.base - 1; int shift = 3; if (spec.base == 16) shift = 4; do { tmp[i++] = (hex_asc_upper[((unsigned char)num) & mask] | locase); num >>= shift; } while (num); } else { /* base 10 */ i = put_dec(tmp, num) - tmp; } /* printing 100 using %2d gives "100", not "00" */ if (i > precision) precision = i; /* leading space padding */ field_width -= precision; if (!(spec.flags & (ZEROPAD | LEFT))) { while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } } /* sign */ if (sign) { if (buf < end) *buf = sign; ++buf; } /* "0x" / "0" prefix */ if (need_pfx) { if (spec.base == 16 || !is_zero) { if (buf < end) *buf = '0'; ++buf; } if (spec.base == 16) { if (buf < end) *buf = ('X' | locase); ++buf; } } /* zero or space padding */ if (!(spec.flags & LEFT)) { char c = ' ' + (spec.flags & ZEROPAD); while (--field_width >= 0) { if (buf < end) *buf = c; ++buf; } } /* hmm even more zero padding? */ while (i <= --precision) { if (buf < end) *buf = '0'; ++buf; } /* actual digits of result */ while (--i >= 0) { if (buf < end) *buf = tmp[i]; ++buf; } /* trailing space padding */ while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } return buf; } static noinline_for_stack char *special_hex_number(char *buf, char *end, unsigned long long num, int size) { struct printf_spec spec; spec.type = FORMAT_TYPE_PTR; spec.field_width = 2 + 2 * size; /* 0x + hex */ spec.flags = SPECIAL | SMALL | ZEROPAD; spec.base = 16; spec.precision = -1; return number(buf, end, num, spec); } static void move_right(char *buf, char *end, unsigned len, unsigned spaces) { size_t size; if (buf >= end) /* nowhere to put anything */ return; size = end - buf; if (size <= spaces) { memset(buf, ' ', size); return; } if (len) { if (len > size - spaces) len = size - spaces; memmove(buf + spaces, buf, len); } memset(buf, ' ', spaces); } /* * Handle field width padding for a string. * @buf: current buffer position * @n: length of string * @end: end of output buffer * @spec: for field width and flags * Returns: new buffer position after padding. */ static noinline_for_stack char *widen_string(char *buf, int n, char *end, struct printf_spec spec) { unsigned spaces; if (likely(n >= spec.field_width)) return buf; /* we want to pad the sucker */ spaces = spec.field_width - n; if (!(spec.flags & LEFT)) { move_right(buf - n, end, n, spaces); return buf + spaces; } while (spaces--) { if (buf < end) *buf = ' '; ++buf; } return buf; } /* Handle string from a well known address. */ static char *string_nocheck(char *buf, char *end, const char *s, struct printf_spec spec) { int len = 0; int lim = spec.precision; while (lim--) { char c = *s++; if (!c) break; if (buf < end) *buf = c; ++buf; ++len; } return widen_string(buf, len, end, spec); } static char *err_ptr(char *buf, char *end, void *ptr, struct printf_spec spec) { int err = PTR_ERR(ptr); const char *sym = errname(err); if (sym) return string_nocheck(buf, end, sym, spec); /* * Somebody passed ERR_PTR(-1234) or some other non-existing * Efoo - or perhaps CONFIG_SYMBOLIC_ERRNAME=n. Fall back to * printing it as its decimal representation. */ spec.flags |= SIGN; spec.base = 10; return number(buf, end, err, spec); } /* Be careful: error messages must fit into the given buffer. */ static char *error_string(char *buf, char *end, const char *s, struct printf_spec spec) { /* * Hard limit to avoid a completely insane messages. It actually * works pretty well because most error messages are in * the many pointer format modifiers. */ if (spec.precision == -1) spec.precision = 2 * sizeof(void *); return string_nocheck(buf, end, s, spec); } /* * Do not call any complex external code here. Nested printk()/vsprintf() * might cause infinite loops. Failures might break printk() and would * be hard to debug. */ static const char *check_pointer_msg(const void *ptr) { if (!ptr) return "(null)"; if ((unsigned long)ptr < PAGE_SIZE || IS_ERR_VALUE(ptr)) return "(efault)"; return NULL; } static int check_pointer(char **buf, char *end, const void *ptr, struct printf_spec spec) { const char *err_msg; err_msg = check_pointer_msg(ptr); if (err_msg) { *buf = error_string(*buf, end, err_msg, spec); return -EFAULT; } return 0; } static noinline_for_stack char *string(char *buf, char *end, const char *s, struct printf_spec spec) { if (check_pointer(&buf, end, s, spec)) return buf; return string_nocheck(buf, end, s, spec); } static char *pointer_string(char *buf, char *end, const void *ptr, struct printf_spec spec) { spec.base = 16; spec.flags |= SMALL; if (spec.field_width == -1) { spec.field_width = 2 * sizeof(ptr); spec.flags |= ZEROPAD; } return number(buf, end, (unsigned long int)ptr, spec); } /* Make pointers available for printing early in the boot sequence. */ static int debug_boot_weak_hash __ro_after_init; static int __init debug_boot_weak_hash_enable(char *str) { debug_boot_weak_hash = 1; pr_info("debug_boot_weak_hash enabled\n"); return 0; } early_param("debug_boot_weak_hash", debug_boot_weak_hash_enable); static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key); static siphash_key_t ptr_key __read_mostly; static void enable_ptr_key_workfn(struct work_struct *work) { get_random_bytes(&ptr_key, sizeof(ptr_key)); /* Needs to run from preemptible context */ static_branch_disable(¬_filled_random_ptr_key); } static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn); static int fill_random_ptr_key(struct notifier_block *nb, unsigned long action, void *data) { /* This may be in an interrupt handler. */ queue_work(system_unbound_wq, &enable_ptr_key_work); return 0; } static struct notifier_block random_ready = { .notifier_call = fill_random_ptr_key }; static int __init initialize_ptr_random(void) { int key_size = sizeof(ptr_key); int ret; /* Use hw RNG if available. */ if (get_random_bytes_arch(&ptr_key, key_size) == key_size) { static_branch_disable(¬_filled_random_ptr_key); return 0; } ret = register_random_ready_notifier(&random_ready); if (!ret) { return 0; } else if (ret == -EALREADY) { /* This is in preemptible context */ enable_ptr_key_workfn(&enable_ptr_key_work); return 0; } return ret; } early_initcall(initialize_ptr_random); /* Maps a pointer to a 32 bit unique identifier. */ static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { unsigned long hashval; if (static_branch_unlikely(¬_filled_random_ptr_key)) return -EAGAIN; #ifdef CONFIG_64BIT hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key); /* * Mask off the first 32 bits, this makes explicit that we have * modified the address (and 32 bits is plenty for a unique ID). */ hashval = hashval & 0xffffffff; #else hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key); #endif *hashval_out = hashval; return 0; } int ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { return __ptr_to_hashval(ptr, hashval_out); } static char *ptr_to_id(char *buf, char *end, const void *ptr, struct printf_spec spec) { const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)"; unsigned long hashval; int ret; /* * Print the real pointer value for NULL and error pointers, * as they are not actual addresses. */ if (IS_ERR_OR_NULL(ptr)) return pointer_string(buf, end, ptr, spec); /* When debugging early boot use non-cryptographically secure hash. */ if (unlikely(debug_boot_weak_hash)) { hashval = hash_long((unsigned long)ptr, 32); return pointer_string(buf, end, (const void *)hashval, spec); } ret = __ptr_to_hashval(ptr, &hashval); if (ret) { spec.field_width = 2 * sizeof(ptr); /* string length must be less than default_width */ return error_string(buf, end, str, spec); } return pointer_string(buf, end, (const void *)hashval, spec); } static char *default_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { /* * default is to _not_ leak addresses, so hash before printing, * unless no_hash_pointers is specified on the command line. */ if (unlikely(no_hash_pointers)) return pointer_string(buf, end, ptr, spec); return ptr_to_id(buf, end, ptr, spec); } int kptr_restrict __read_mostly; static noinline_for_stack char *restricted_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { switch (kptr_restrict) { case 0: /* Handle as %p, hash and do _not_ leak addresses. */ return default_pointer(buf, end, ptr, spec); case 1: { const struct cred *cred; /* * kptr_restrict==1 cannot be used in IRQ context * because its test for CAP_SYSLOG would be meaningless. */ if (in_irq() || in_serving_softirq() || in_nmi()) { if (spec.field_width == -1) spec.field_width = 2 * sizeof(ptr); return error_string(buf, end, "pK-error", spec); } /* * Only print the real pointer value if the current * process has CAP_SYSLOG and is running with the * same credentials it started with. This is because * access to files is checked at open() time, but %pK * checks permission at read() time. We don't want to * leak pointer values if a binary opens a file using * %pK and then elevates privileges before reading it. */ cred = current_cred(); if (!has_capability_noaudit(current, CAP_SYSLOG) || !uid_eq(cred->euid, cred->uid) || !gid_eq(cred->egid, cred->gid)) ptr = NULL; break; } case 2: default: /* Always print 0's for %pK */ ptr = NULL; break; } return pointer_string(buf, end, ptr, spec); } static noinline_for_stack char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_spec spec, const char *fmt) { const char *array[4], *s; const struct dentry *p; int depth; int i, n; switch (fmt[1]) { case '2': case '3': case '4': depth = fmt[1] - '0'; break; default: depth = 1; } rcu_read_lock(); for (i = 0; i < depth; i++, d = p) { if (check_pointer(&buf, end, d, spec)) { rcu_read_unlock(); return buf; } p = READ_ONCE(d->d_parent); array[i] = READ_ONCE(d->d_name.name); if (p == d) { if (i) array[i] = ""; i++; break; } } s = array[--i]; for (n = 0; n != spec.precision; n++, buf++) { char c = *s++; if (!c) { if (!i) break; c = '/'; s = array[--i]; } if (buf < end) *buf = c; } rcu_read_unlock(); return widen_string(buf, n, end, spec); } static noinline_for_stack char *file_dentry_name(char *buf, char *end, const struct file *f, struct printf_spec spec, const char *fmt) { if (check_pointer(&buf, end, f, spec)) return buf; return dentry_name(buf, end, f->f_path.dentry, spec, fmt); } #ifdef CONFIG_BLOCK static noinline_for_stack char *bdev_name(char *buf, char *end, struct block_device *bdev, struct printf_spec spec, const char *fmt) { struct gendisk *hd; if (check_pointer(&buf, end, bdev, spec)) return buf; hd = bdev->bd_disk; buf = string(buf, end, hd->disk_name, spec); if (bdev->bd_partno) { if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) { if (buf < end) *buf = 'p'; buf++; } buf = number(buf, end, bdev->bd_partno, spec); } return buf; } #endif static noinline_for_stack char *symbol_string(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { unsigned long value; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; #endif if (fmt[1] == 'R') ptr = __builtin_extract_return_addr(ptr); value = (unsigned long)ptr; #ifdef CONFIG_KALLSYMS if (*fmt == 'B' && fmt[1] == 'b') sprint_backtrace_build_id(sym, value); else if (*fmt == 'B') sprint_backtrace(sym, value); else if (*fmt == 'S' && (fmt[1] == 'b' || (fmt[1] == 'R' && fmt[2] == 'b'))) sprint_symbol_build_id(sym, value); else if (*fmt != 's') sprint_symbol(sym, value); else sprint_symbol_no_offset(sym, value); return string_nocheck(buf, end, sym, spec); #else return special_hex_number(buf, end, value, sizeof(void *)); #endif } static const struct printf_spec default_str_spec = { .field_width = -1, .precision = -1, }; static const struct printf_spec default_flag_spec = { .base = 16, .precision = -1, .flags = SPECIAL | SMALL, }; static const struct printf_spec default_dec_spec = { .base = 10, .precision = -1, }; static const struct printf_spec default_dec02_spec = { .base = 10, .field_width = 2, .precision = -1, .flags = ZEROPAD, }; static const struct printf_spec default_dec04_spec = { .base = 10, .field_width = 4, .precision = -1, .flags = ZEROPAD, }; static noinline_for_stack char *resource_string(char *buf, char *end, struct resource *res, struct printf_spec spec, const char *fmt) { #ifndef IO_RSRC_PRINTK_SIZE #define IO_RSRC_PRINTK_SIZE 6 #endif #ifndef MEM_RSRC_PRINTK_SIZE #define MEM_RSRC_PRINTK_SIZE 10 #endif static const struct printf_spec io_spec = { .base = 16, .field_width = IO_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec mem_spec = { .base = 16, .field_width = MEM_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec bus_spec = { .base = 16, .field_width = 2, .precision = -1, .flags = SMALL | ZEROPAD, }; static const struct printf_spec str_spec = { .field_width = -1, .precision = 10, .flags = LEFT, }; /* 32-bit res (sizeof==4): 10 chars in dec, 10 in hex ("0x" + 8) * 64-bit res (sizeof==8): 20 chars in dec, 18 in hex ("0x" + 16) */ #define RSRC_BUF_SIZE ((2 * sizeof(resource_size_t)) + 4) #define FLAG_BUF_SIZE (2 * sizeof(res->flags)) #define DECODED_BUF_SIZE sizeof("[mem - 64bit pref window disabled]") #define RAW_BUF_SIZE sizeof("[mem - flags 0x]") char sym[max(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE, 2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)]; char *p = sym, *pend = sym + sizeof(sym); int decode = (fmt[0] == 'R') ? 1 : 0; const struct printf_spec *specp; if (check_pointer(&buf, end, res, spec)) return buf; *p++ = '['; if (res->flags & IORESOURCE_IO) { p = string_nocheck(p, pend, "io ", str_spec); specp = &io_spec; } else if (res->flags & IORESOURCE_MEM) { p = string_nocheck(p, pend, "mem ", str_spec); specp = &mem_spec; } else if (res->flags & IORESOURCE_IRQ) { p = string_nocheck(p, pend, "irq ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_DMA) { p = string_nocheck(p, pend, "dma ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_BUS) { p = string_nocheck(p, pend, "bus ", str_spec); specp = &bus_spec; } else { p = string_nocheck(p, pend, "??? ", str_spec); specp = &mem_spec; decode = 0; } if (decode && res->flags & IORESOURCE_UNSET) { p = string_nocheck(p, pend, "size ", str_spec); p = number(p, pend, resource_size(res), *specp); } else { p = number(p, pend, res->start, *specp); if (res->start != res->end) { *p++ = '-'; p = number(p, pend, res->end, *specp); } } if (decode) { if (res->flags & IORESOURCE_MEM_64) p = string_nocheck(p, pend, " 64bit", str_spec); if (res->flags & IORESOURCE_PREFETCH) p = string_nocheck(p, pend, " pref", str_spec); if (res->flags & IORESOURCE_WINDOW) p = string_nocheck(p, pend, " window", str_spec); if (res->flags & IORESOURCE_DISABLED) p = string_nocheck(p, pend, " disabled", str_spec); } else { p = string_nocheck(p, pend, " flags ", str_spec); p = number(p, pend, res->flags, default_flag_spec); } *p++ = ']'; *p = '\0'; return string_nocheck(buf, end, sym, spec); } static noinline_for_stack char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { int i, len = 1; /* if we pass '%ph[CDN]', field width remains negative value, fallback to the default */ char separator; if (spec.field_width == 0) /* nothing to print */ return buf; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'C': separator = ':'; break; case 'D': separator = '-'; break; case 'N': separator = 0; break; default: separator = ' '; break; } if (spec.field_width > 0) len = min_t(int, spec.field_width, 64); for (i = 0; i < len; ++i) { if (buf < end) *buf = hex_asc_hi(addr[i]); ++buf; if (buf < end) *buf = hex_asc_lo(addr[i]); ++buf; if (separator && i != len - 1) { if (buf < end) *buf = separator; ++buf; } } return buf; } static noinline_for_stack char *bitmap_string(char *buf, char *end, unsigned long *bitmap, struct printf_spec spec, const char *fmt) { const int CHUNKSZ = 32; int nr_bits = max_t(int, spec.field_width, 0); int i, chunksz; bool first = true; if (check_pointer(&buf, end, bitmap, spec)) return buf; /* reused to print numbers */ spec = (struct printf_spec){ .flags = SMALL | ZEROPAD, .base = 16 }; chunksz = nr_bits & (CHUNKSZ - 1); if (chunksz == 0) chunksz = CHUNKSZ; i = ALIGN(nr_bits, CHUNKSZ) - CHUNKSZ; for (; i >= 0; i -= CHUNKSZ) { u32 chunkmask, val; int word, bit; chunkmask = ((1ULL << chunksz) - 1); word = i / BITS_PER_LONG; bit = i % BITS_PER_LONG; val = (bitmap[word] >> bit) & chunkmask; if (!first) { if (buf < end) *buf = ','; buf++; } first = false; spec.field_width = DIV_ROUND_UP(chunksz, 4); buf = number(buf, end, val, spec); chunksz = CHUNKSZ; } return buf; } static noinline_for_stack char *bitmap_list_string(char *buf, char *end, unsigned long *bitmap, struct printf_spec spec, const char *fmt) { int nr_bits = max_t(int, spec.field_width, 0); /* current bit is 'cur', most recently seen range is [rbot, rtop] */ int cur, rbot, rtop; bool first = true; if (check_pointer(&buf, end, bitmap, spec)) return buf; rbot = cur = find_first_bit(bitmap, nr_bits); while (cur < nr_bits) { rtop = cur; cur = find_next_bit(bitmap, nr_bits, cur + 1); if (cur < nr_bits && cur <= rtop + 1) continue; if (!first) { if (buf < end) *buf = ','; buf++; } first = false; buf = number(buf, end, rbot, default_dec_spec); if (rbot < rtop) { if (buf < end) *buf = '-'; buf++; buf = number(buf, end, rtop, default_dec_spec); } rbot = cur; } return buf; } static noinline_for_stack char *mac_address_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { char mac_addr[sizeof("xx:xx:xx:xx:xx:xx")]; char *p = mac_addr; int i; char separator; bool reversed = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': separator = '-'; break; case 'R': reversed = true; fallthrough; default: separator = ':'; break; } for (i = 0; i < 6; i++) { if (reversed) p = hex_byte_pack(p, addr[5 - i]); else p = hex_byte_pack(p, addr[i]); if (fmt[0] == 'M' && i != 5) *p++ = separator; } *p = '\0'; return string_nocheck(buf, end, mac_addr, spec); } static noinline_for_stack char *ip4_string(char *p, const u8 *addr, const char *fmt) { int i; bool leading_zeros = (fmt[0] == 'i'); int index; int step; switch (fmt[2]) { case 'h': #ifdef __BIG_ENDIAN index = 0; step = 1; #else index = 3; step = -1; #endif break; case 'l': index = 3; step = -1; break; case 'n': case 'b': default: index = 0; step = 1; break; } for (i = 0; i < 4; i++) { char temp[4] __aligned(2); /* hold each IP quad in reverse order */ int digits = put_dec_trunc8(temp, addr[index]) - temp; if (leading_zeros) { if (digits < 3) *p++ = '0'; if (digits < 2) *p++ = '0'; } /* reverse the digits in the quad */ while (digits--) *p++ = temp[digits]; if (i < 3) *p++ = '.'; index += step; } *p = '\0'; return p; } static noinline_for_stack char *ip6_compressed_string(char *p, const char *addr) { int i, j, range; unsigned char zerolength[8]; int longest = 1; int colonpos = -1; u16 word; u8 hi, lo; bool needcolon = false; bool useIPv4; struct in6_addr in6; memcpy(&in6, addr, sizeof(struct in6_addr)); useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6); memset(zerolength, 0, sizeof(zerolength)); if (useIPv4) range = 6; else range = 8; /* find position of longest 0 run */ for (i = 0; i < range; i++) { for (j = i; j < range; j++) { if (in6.s6_addr16[j] != 0) break; zerolength[i]++; } } for (i = 0; i < range; i++) { if (zerolength[i] > longest) { longest = zerolength[i]; colonpos = i; } } if (longest == 1) /* don't compress a single 0 */ colonpos = -1; /* emit address */ for (i = 0; i < range; i++) { if (i == colonpos) { if (needcolon || i == 0) *p++ = ':'; *p++ = ':'; needcolon = false; i += longest - 1; continue; } if (needcolon) { *p++ = ':'; needcolon = false; } /* hex u16 without leading 0s */ word = ntohs(in6.s6_addr16[i]); hi = word >> 8; lo = word & 0xff; if (hi) { if (hi > 0x0f) p = hex_byte_pack(p, hi); else *p++ = hex_asc_lo(hi); p = hex_byte_pack(p, lo); } else if (lo > 0x0f) p = hex_byte_pack(p, lo); else *p++ = hex_asc_lo(lo); needcolon = true; } if (useIPv4) { if (needcolon) *p++ = ':'; p = ip4_string(p, &in6.s6_addr[12], "I4"); } *p = '\0'; return p; } static noinline_for_stack char *ip6_string(char *p, const char *addr, const char *fmt) { int i; for (i = 0; i < 8; i++) { p = hex_byte_pack(p, *addr++); p = hex_byte_pack(p, *addr++); if (fmt[0] == 'I' && i != 7) *p++ = ':'; } *p = '\0'; return p; } static noinline_for_stack char *ip6_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip6_addr[sizeof("xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255")]; if (fmt[0] == 'I' && fmt[2] == 'c') ip6_compressed_string(ip6_addr, addr); else ip6_string(ip6_addr, addr, fmt); return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip4_addr[sizeof("255.255.255.255")]; ip4_string(ip4_addr, addr, fmt); return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip6_addr_string_sa(char *buf, char *end, const struct sockaddr_in6 *sa, struct printf_spec spec, const char *fmt) { bool have_p = false, have_s = false, have_f = false, have_c = false; char ip6_addr[sizeof("[xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255]") + sizeof(":12345") + sizeof("/123456789") + sizeof("%1234567890")]; char *p = ip6_addr, *pend = ip6_addr + sizeof(ip6_addr); const u8 *addr = (const u8 *) &sa->sin6_addr; char fmt6[2] = { fmt[0], '6' }; u8 off = 0; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'f': have_f = true; break; case 's': have_s = true; break; case 'c': have_c = true; break; } } if (have_p || have_s || have_f) { *p = '['; off = 1; } if (fmt6[0] == 'I' && have_c) p = ip6_compressed_string(ip6_addr + off, addr); else p = ip6_string(ip6_addr + off, addr, fmt6); if (have_p || have_s || have_f) *p++ = ']'; if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin6_port), spec); } if (have_f) { *p++ = '/'; p = number(p, pend, ntohl(sa->sin6_flowinfo & IPV6_FLOWINFO_MASK), spec); } if (have_s) { *p++ = '%'; p = number(p, pend, sa->sin6_scope_id, spec); } *p = '\0'; return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string_sa(char *buf, char *end, const struct sockaddr_in *sa, struct printf_spec spec, const char *fmt) { bool have_p = false; char *p, ip4_addr[sizeof("255.255.255.255") + sizeof(":12345")]; char *pend = ip4_addr + sizeof(ip4_addr); const u8 *addr = (const u8 *) &sa->sin_addr.s_addr; char fmt4[3] = { fmt[0], '4', 0 }; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'h': case 'l': case 'n': case 'b': fmt4[2] = *fmt; break; } } p = ip4_string(ip4_addr, addr, fmt4); if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin_port), spec); } *p = '\0'; return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip_addr_string(char *buf, char *end, const void *ptr, struct printf_spec spec, const char *fmt) { char *err_fmt_msg; if (check_pointer(&buf, end, ptr, spec)) return buf; switch (fmt[1]) { case '6': return ip6_addr_string(buf, end, ptr, spec, fmt); case '4': return ip4_addr_string(buf, end, ptr, spec, fmt); case 'S': { const union { struct sockaddr raw; struct sockaddr_in v4; struct sockaddr_in6 v6; } *sa = ptr; switch (sa->raw.sa_family) { case AF_INET: return ip4_addr_string_sa(buf, end, &sa->v4, spec, fmt); case AF_INET6: return ip6_addr_string_sa(buf, end, &sa->v6, spec, fmt); default: return error_string(buf, end, "(einval)", spec); }} } err_fmt_msg = fmt[0] == 'i' ? "(%pi?)" : "(%pI?)"; return error_string(buf, end, err_fmt_msg, spec); } static noinline_for_stack char *escaped_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { bool found = true; int count = 1; unsigned int flags = 0; int len; if (spec.field_width == 0) return buf; /* nothing to print */ if (check_pointer(&buf, end, addr, spec)) return buf; do { switch (fmt[count++]) { case 'a': flags |= ESCAPE_ANY; break; case 'c': flags |= ESCAPE_SPECIAL; break; case 'h': flags |= ESCAPE_HEX; break; case 'n': flags |= ESCAPE_NULL; break; case 'o': flags |= ESCAPE_OCTAL; break; case 'p': flags |= ESCAPE_NP; break; case 's': flags |= ESCAPE_SPACE; break; default: found = false; break; } } while (found); if (!flags) flags = ESCAPE_ANY_NP; len = spec.field_width < 0 ? 1 : spec.field_width; /* * string_escape_mem() writes as many characters as it can to * the given buffer, and returns the total size of the output * had the buffer been big enough. */ buf += string_escape_mem(addr, len, buf, buf < end ? end - buf : 0, flags, NULL); return buf; } static char *va_format(char *buf, char *end, struct va_format *va_fmt, struct printf_spec spec, const char *fmt) { va_list va; if (check_pointer(&buf, end, va_fmt, spec)) return buf; va_copy(va, *va_fmt->va); buf += vsnprintf(buf, end > buf ? end - buf : 0, va_fmt->fmt, va); va_end(va); return buf; } static noinline_for_stack char *uuid_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char uuid[UUID_STRING_LEN + 1]; char *p = uuid; int i; const u8 *index = uuid_index; bool uc = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (*(++fmt)) { case 'L': uc = true; fallthrough; case 'l': index = guid_index; break; case 'B': uc = true; break; } for (i = 0; i < 16; i++) { if (uc) p = hex_byte_pack_upper(p, addr[index[i]]); else p = hex_byte_pack(p, addr[index[i]]); switch (i) { case 3: case 5: case 7: case 9: *p++ = '-'; break; } } *p = 0; return string_nocheck(buf, end, uuid, spec); } static noinline_for_stack char *netdev_bits(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': num = *(const netdev_features_t *)addr; size = sizeof(netdev_features_t); break; default: return error_string(buf, end, "(%pN?)", spec); } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *fourcc_string(char *buf, char *end, const u32 *fourcc, struct printf_spec spec, const char *fmt) { char output[sizeof("0123 little-endian (0x01234567)")]; char *p = output; unsigned int i; u32 orig, val; if (fmt[1] != 'c' || fmt[2] != 'c') return error_string(buf, end, "(%p4?)", spec); if (check_pointer(&buf, end, fourcc, spec)) return buf; orig = get_unaligned(fourcc); val = orig & ~BIT(31); for (i = 0; i < sizeof(u32); i++) { unsigned char c = val >> (i * 8); /* Print non-control ASCII characters as-is, dot otherwise */ *p++ = isascii(c) && isprint(c) ? c : '.'; } strcpy(p, orig & BIT(31) ? " big-endian" : " little-endian"); p += strlen(p); *p++ = ' '; *p++ = '('; p = special_hex_number(p, output + sizeof(output) - 2, orig, sizeof(u32)); *p++ = ')'; *p = '\0'; return string(buf, end, output, spec); } static noinline_for_stack char *address_val(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'd': num = *(const dma_addr_t *)addr; size = sizeof(dma_addr_t); break; case 'p': default: num = *(const phys_addr_t *)addr; size = sizeof(phys_addr_t); break; } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *date_str(char *buf, char *end, const struct rtc_time *tm, bool r) { int year = tm->tm_year + (r ? 0 : 1900); int mon = tm->tm_mon + (r ? 0 : 1); buf = number(buf, end, year, default_dec04_spec); if (buf < end) *buf = '-'; buf++; buf = number(buf, end, mon, default_dec02_spec); if (buf < end) *buf = '-'; buf++; return number(buf, end, tm->tm_mday, default_dec02_spec); } static noinline_for_stack char *time_str(char *buf, char *end, const struct rtc_time *tm, bool r) { buf = number(buf, end, tm->tm_hour, default_dec02_spec); if (buf < end) *buf = ':'; buf++; buf = number(buf, end, tm->tm_min, default_dec02_spec); if (buf < end) *buf = ':'; buf++; return number(buf, end, tm->tm_sec, default_dec02_spec); } static noinline_for_stack char *rtc_str(char *buf, char *end, const struct rtc_time *tm, struct printf_spec spec, const char *fmt) { bool have_t = true, have_d = true; bool raw = false, iso8601_separator = true; bool found = true; int count = 2; if (check_pointer(&buf, end, tm, spec)) return buf; switch (fmt[count]) { case 'd': have_t = false; count++; break; case 't': have_d = false; count++; break; } do { switch (fmt[count++]) { case 'r': raw = true; break; case 's': iso8601_separator = false; break; default: found = false; break; } } while (found); if (have_d) buf = date_str(buf, end, tm, raw); if (have_d && have_t) { if (buf < end) *buf = iso8601_separator ? 'T' : ' '; buf++; } if (have_t) buf = time_str(buf, end, tm, raw); return buf; } static noinline_for_stack char *time64_str(char *buf, char *end, const time64_t time, struct printf_spec spec, const char *fmt) { struct rtc_time rtc_time; struct tm tm; time64_to_tm(time, 0, &tm); rtc_time.tm_sec = tm.tm_sec; rtc_time.tm_min = tm.tm_min; rtc_time.tm_hour = tm.tm_hour; rtc_time.tm_mday = tm.tm_mday; rtc_time.tm_mon = tm.tm_mon; rtc_time.tm_year = tm.tm_year; rtc_time.tm_wday = tm.tm_wday; rtc_time.tm_yday = tm.tm_yday; rtc_time.tm_isdst = 0; return rtc_str(buf, end, &rtc_time, spec, fmt); } static noinline_for_stack char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { switch (fmt[1]) { case 'R': return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt); case 'T': return time64_str(buf, end, *(const time64_t *)ptr, spec, fmt); default: return error_string(buf, end, "(%pt?)", spec); } } static noinline_for_stack char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec, const char *fmt) { if (!IS_ENABLED(CONFIG_HAVE_CLK)) return error_string(buf, end, "(%pC?)", spec); if (check_pointer(&buf, end, clk, spec)) return buf; switch (fmt[1]) { case 'n': default: #ifdef CONFIG_COMMON_CLK return string(buf, end, __clk_get_name(clk), spec); #else return ptr_to_id(buf, end, clk, spec); #endif } } static char *format_flags(char *buf, char *end, unsigned long flags, const struct trace_print_flags *names) { unsigned long mask; for ( ; flags && names->name; names++) { mask = names->mask; if ((flags & mask) != mask) continue; buf = string(buf, end, names->name, default_str_spec); flags &= ~mask; if (flags) { if (buf < end) *buf = '|'; buf++; } } if (flags) buf = number(buf, end, flags, default_flag_spec); return buf; } struct page_flags_fields { int width; int shift; int mask; const struct printf_spec *spec; const char *name; }; static const struct page_flags_fields pff[] = { {SECTIONS_WIDTH, SECTIONS_PGSHIFT, SECTIONS_MASK, &default_dec_spec, "section"}, {NODES_WIDTH, NODES_PGSHIFT, NODES_MASK, &default_dec_spec, "node"}, {ZONES_WIDTH, ZONES_PGSHIFT, ZONES_MASK, &default_dec_spec, "zone"}, {LAST_CPUPID_WIDTH, LAST_CPUPID_PGSHIFT, LAST_CPUPID_MASK, &default_flag_spec, "lastcpupid"}, {KASAN_TAG_WIDTH, KASAN_TAG_PGSHIFT, KASAN_TAG_MASK, &default_flag_spec, "kasantag"}, }; static char *format_page_flags(char *buf, char *end, unsigned long flags) { unsigned long main_flags = flags & PAGEFLAGS_MASK; bool append = false; int i; /* Page flags from the main area. */ if (main_flags) { buf = format_flags(buf, end, main_flags, pageflag_names); append = true; } /* Page flags from the fields area */ for (i = 0; i < ARRAY_SIZE(pff); i++) { /* Skip undefined fields. */ if (!pff[i].width) continue; /* Format: Flag Name + '=' (equals sign) + Number + '|' (separator) */ if (append) { if (buf < end) *buf = '|'; buf++; } buf = string(buf, end, pff[i].name, default_str_spec); if (buf < end) *buf = '='; buf++; buf = number(buf, end, (flags >> pff[i].shift) & pff[i].mask, *pff[i].spec); append = true; } return buf; } static noinline_for_stack char *flags_string(char *buf, char *end, void *flags_ptr, struct printf_spec spec, const char *fmt) { unsigned long flags; const struct trace_print_flags *names; if (check_pointer(&buf, end, flags_ptr, spec)) return buf; switch (fmt[1]) { case 'p': return format_page_flags(buf, end, *(unsigned long *)flags_ptr); case 'v': flags = *(unsigned long *)flags_ptr; names = vmaflag_names; break; case 'g': flags = (__force unsigned long)(*(gfp_t *)flags_ptr); names = gfpflag_names; break; default: return error_string(buf, end, "(%pG?)", spec); } return format_flags(buf, end, flags, names); } static noinline_for_stack char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf, char *end) { int depth; /* Loop starting from the root node to the current node. */ for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) { /* * Only get a reference for other nodes (i.e. parent nodes). * fwnode refcount may be 0 here. */ struct fwnode_handle *__fwnode = depth ? fwnode_get_nth_parent(fwnode, depth) : fwnode; buf = string(buf, end, fwnode_get_name_prefix(__fwnode), default_str_spec); buf = string(buf, end, fwnode_get_name(__fwnode), default_str_spec); if (depth) fwnode_handle_put(__fwnode); } return buf; } static noinline_for_stack char *device_node_string(char *buf, char *end, struct device_node *dn, struct printf_spec spec, const char *fmt) { char tbuf[sizeof("xxxx") + 1]; const char *p; int ret; char *buf_start = buf; struct property *prop; bool has_mult, pass; struct printf_spec str_spec = spec; str_spec.field_width = -1; if (fmt[0] != 'F') return error_string(buf, end, "(%pO?)", spec); if (!IS_ENABLED(CONFIG_OF)) return error_string(buf, end, "(%pOF?)", spec); if (check_pointer(&buf, end, dn, spec)) return buf; /* simple case without anything any more format specifiers */ fmt++; if (fmt[0] == '\0' || strcspn(fmt,"fnpPFcC") > 0) fmt = "f"; for (pass = false; strspn(fmt,"fnpPFcC"); fmt++, pass = true) { int precision; if (pass) { if (buf < end) *buf = ':'; buf++; } switch (*fmt) { case 'f': /* full_name */ buf = fwnode_full_name_string(of_fwnode_handle(dn), buf, end); break; case 'n': /* name */ p = fwnode_get_name(of_fwnode_handle(dn)); precision = str_spec.precision; str_spec.precision = strchrnul(p, '@') - p; buf = string(buf, end, p, str_spec); str_spec.precision = precision; break; case 'p': /* phandle */ buf = number(buf, end, (unsigned int)dn->phandle, default_dec_spec); break; case 'P': /* path-spec */ p = fwnode_get_name(of_fwnode_handle(dn)); if (!p[1]) p = "/"; buf = string(buf, end, p, str_spec); break; case 'F': /* flags */ tbuf[0] = of_node_check_flag(dn, OF_DYNAMIC) ? 'D' : '-'; tbuf[1] = of_node_check_flag(dn, OF_DETACHED) ? 'd' : '-'; tbuf[2] = of_node_check_flag(dn, OF_POPULATED) ? 'P' : '-'; tbuf[3] = of_node_check_flag(dn, OF_POPULATED_BUS) ? 'B' : '-'; tbuf[4] = 0; buf = string_nocheck(buf, end, tbuf, str_spec); break; case 'c': /* major compatible string */ ret = of_property_read_string(dn, "compatible", &p); if (!ret) buf = string(buf, end, p, str_spec); break; case 'C': /* full compatible string */ has_mult = false; of_property_for_each_string(dn, "compatible", prop, p) { if (has_mult) buf = string_nocheck(buf, end, ",", str_spec); buf = string_nocheck(buf, end, "\"", str_spec); buf = string(buf, end, p, str_spec); buf = string_nocheck(buf, end, "\"", str_spec); has_mult = true; } break; default: break; } } return widen_string(buf, buf - buf_start, end, spec); } static noinline_for_stack char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, struct printf_spec spec, const char *fmt) { struct printf_spec str_spec = spec; char *buf_start = buf; str_spec.field_width = -1; if (*fmt != 'w') return error_string(buf, end, "(%pf?)", spec); if (check_pointer(&buf, end, fwnode, spec)) return buf; fmt++; switch (*fmt) { case 'P': /* name */ buf = string(buf, end, fwnode_get_name(fwnode), str_spec); break; case 'f': /* full_name */ default: buf = fwnode_full_name_string(fwnode, buf, end); break; } return widen_string(buf, buf - buf_start, end, spec); } int __init no_hash_pointers_enable(char *str) { if (no_hash_pointers) return 0; no_hash_pointers = true; pr_warn("**********************************************************\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("** **\n"); pr_warn("** This system shows unhashed kernel memory addresses **\n"); pr_warn("** via the console, logs, and other interfaces. This **\n"); pr_warn("** might reduce the security of your system. **\n"); pr_warn("** **\n"); pr_warn("** If you see this message and you are not debugging **\n"); pr_warn("** the kernel, report this immediately to your system **\n"); pr_warn("** administrator! **\n"); pr_warn("** **\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("**********************************************************\n"); return 0; } early_param("no_hash_pointers", no_hash_pointers_enable); /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format * specifiers. * * Please update scripts/checkpatch.pl when adding/removing conversion * characters. (Search for "check for vsprintf extension"). * * Right now we handle: * * - 'S' For symbolic direct pointers (or function descriptors) with offset * - 's' For symbolic direct pointers (or function descriptors) without offset * - '[Ss]R' as above with __builtin_extract_return_addr() translation * - 'S[R]b' as above with module build ID (for use in backtraces) * - '[Ff]' %pf and %pF were obsoleted and later removed in favor of * %ps and %pS. Be careful when re-using these specifiers. * - 'B' For backtraced symbolic direct pointers with offset * - 'Bb' as above with module build ID (for use in backtraces) * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref] * - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201] * - 'b[l]' For a bitmap, the number of bits is determined by the field * width which must be explicitly specified either as part of the * format string '%32b[l]' or through '%*b[l]', [l] selects * range-list format instead of hex format * - 'M' For a 6-byte MAC address, it prints the address in the * usual colon-separated hex notation * - 'm' For a 6-byte MAC address, it prints the hex address without colons * - 'MF' For a 6-byte MAC FDDI address, it prints the address * with a dash-separated hex notation * - '[mM]R' For a 6-byte MAC address, Reverse order (Bluetooth) * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way * IPv4 uses dot-separated decimal without leading 0's (1.2.3.4) * IPv6 uses colon separated network-order 16 bit hex with leading 0's * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - 'i' [46] for 'raw' IPv4/IPv6 addresses * IPv6 omits the colons (01020304...0f) * IPv4 uses dot-separated decimal with leading 0's (010.123.045.006) * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order * - 'I[6S]c' for IPv6 addresses printed as specified by * https://tools.ietf.org/html/rfc5952 * - 'E[achnops]' For an escaped buffer, where rules are defined by combination * of the following flags (see string_escape_mem() for the * details): * a - ESCAPE_ANY * c - ESCAPE_SPECIAL * h - ESCAPE_HEX * n - ESCAPE_NULL * o - ESCAPE_OCTAL * p - ESCAPE_NP * s - ESCAPE_SPACE * By default ESCAPE_ANY_NP is used. * - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form * "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" * Options for %pU are: * b big endian lower case hex (default) * B big endian UPPER case hex * l little endian lower case hex * L little endian UPPER case hex * big endian output byte order is: * [0][1][2][3]-[4][5]-[6][7]-[8][9]-[10][11][12][13][14][15] * little endian output byte order is: * [3][2][1][0]-[5][4]-[7][6]-[8][9]-[10][11][12][13][14][15] * - 'V' For a struct va_format which contains a format string * and va_list *, * call vsnprintf(->format, *->va_list). * Implements a "recursive vsnprintf". * Do not use this feature without some mechanism to verify the * correctness of the format string and va_list arguments. * - 'K' For a kernel pointer that should be hidden from unprivileged users. * Use only for procfs, sysfs and similar files, not printk(); please * read the documentation (path below) first. * - 'NF' For a netdev_features_t * - '4cc' V4L2 or DRM FourCC code, with endianness and raw numerical value. * - 'h[CDN]' For a variable-length buffer, it prints it as a hex string with * a certain separator (' ' by default): * C colon * D dash * N no separator * The maximum supported length is 64 bytes of the input. Consider * to use print_hex_dump() for the larger input. * - 'a[pd]' For address types [p] phys_addr_t, [d] dma_addr_t and derivatives * (default assumed to be phys_addr_t, passed by reference) * - 'd[234]' For a dentry name (optionally 2-4 last components) * - 'D[234]' Same as 'd' but for a struct file * - 'g' For block_device name (gendisk + partition number) * - 't[RT][dt][r][s]' For time and date as represented by: * R struct rtc_time * T time64_t * - 'C' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'Cn' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'G' For flags to be printed as a collection of symbolic strings that would * construct the specific value. Supported flags given by option: * p page flags (see struct page) given as pointer to unsigned long * g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t * v vma flags (VM_*) given as pointer to unsigned long * - 'OF[fnpPcCF]' For a device tree object * Without any optional arguments prints the full_name * f device node full_name * n device node name * p device node phandle * P device node path spec (name + @unit) * F device node flags * c major compatible string * C full compatible string * - 'fw[fP]' For a firmware node (struct fwnode_handle) pointer * Without an option prints the full name of the node * f full name * P node name, including a possible unit address * - 'x' For printing the address unmodified. Equivalent to "%lx". * Please read the documentation (path below) before using! * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of * bpf_trace_printk() where [ku] prefix specifies either kernel (k) * or user (u) memory to probe, and: * s a string, equivalent to "%s" on direct vsnprintf() use * * ** When making changes please also update: * Documentation/core-api/printk-formats.rst * * Note: The default behaviour (unadorned %p) is to hash the address, * rendering it useful as a unique identifier. */ static noinline_for_stack char *pointer(const char *fmt, char *buf, char *end, void *ptr, struct printf_spec spec) { switch (*fmt) { case 'S': case 's': ptr = dereference_symbol_descriptor(ptr); fallthrough; case 'B': return symbol_string(buf, end, ptr, spec, fmt); case 'R': case 'r': return resource_string(buf, end, ptr, spec, fmt); case 'h': return hex_string(buf, end, ptr, spec, fmt); case 'b': switch (fmt[1]) { case 'l': return bitmap_list_string(buf, end, ptr, spec, fmt); default: return bitmap_string(buf, end, ptr, spec, fmt); } case 'M': /* Colon separated: 00:01:02:03:04:05 */ case 'm': /* Contiguous: 000102030405 */ /* [mM]F (FDDI) */ /* [mM]R (Reverse order; Bluetooth) */ return mac_address_string(buf, end, ptr, spec, fmt); case 'I': /* Formatted IP supported * 4: 1.2.3.4 * 6: 0001:0203:...:0708 * 6c: 1::708 or 1::1.2.3.4 */ case 'i': /* Contiguous: * 4: 001.002.003.004 * 6: 000102...0f */ return ip_addr_string(buf, end, ptr, spec, fmt); case 'E': return escaped_string(buf, end, ptr, spec, fmt); case 'U': return uuid_string(buf, end, ptr, spec, fmt); case 'V': return va_format(buf, end, ptr, spec, fmt); case 'K': return restricted_pointer(buf, end, ptr, spec); case 'N': return netdev_bits(buf, end, ptr, spec, fmt); case '4': return fourcc_string(buf, end, ptr, spec, fmt); case 'a': return address_val(buf, end, ptr, spec, fmt); case 'd': return dentry_name(buf, end, ptr, spec, fmt); case 't': return time_and_date(buf, end, ptr, spec, fmt); case 'C': return clock(buf, end, ptr, spec, fmt); case 'D': return file_dentry_name(buf, end, ptr, spec, fmt); #ifdef CONFIG_BLOCK case 'g': return bdev_name(buf, end, ptr, spec, fmt); #endif case 'G': return flags_string(buf, end, ptr, spec, fmt); case 'O': return device_node_string(buf, end, ptr, spec, fmt + 1); case 'f': return fwnode_string(buf, end, ptr, spec, fmt + 1); case 'x': return pointer_string(buf, end, ptr, spec); case 'e': /* %pe with a non-ERR_PTR gets treated as plain %p */ if (!IS_ERR(ptr)) return default_pointer(buf, end, ptr, spec); return err_ptr(buf, end, ptr, spec); case 'u': case 'k': switch (fmt[1]) { case 's': return string(buf, end, ptr, spec); default: return error_string(buf, end, "(einval)", spec); } default: return default_pointer(buf, end, ptr, spec); } } /* * Helper function to decode printf style format. * Each call decode a token from the format and return the * number of characters read (or likely the delta where it wants * to go on the next call). * The decoded token is returned through the parameters * * 'h', 'l', or 'L' for integer fields * 'z' support added 23/7/1999 S.H. * 'z' changed to 'Z' --davidm 1/25/99 * 'Z' changed to 'z' --adobriyan 2017-01-25 * 't' added for ptrdiff_t * * @fmt: the format string * @type of the token returned * @flags: various flags such as +, -, # tokens.. * @field_width: overwritten width * @base: base of the number (octal, hex, ...) * @precision: precision of a number * @qualifier: qualifier of a number (long, size_t, ...) */ static noinline_for_stack int format_decode(const char *fmt, struct printf_spec *spec) { const char *start = fmt; char qualifier; /* we finished early by reading the field width */ if (spec->type == FORMAT_TYPE_WIDTH) { if (spec->field_width < 0) { spec->field_width = -spec->field_width; spec->flags |= LEFT; } spec->type = FORMAT_TYPE_NONE; goto precision; } /* we finished early by reading the precision */ if (spec->type == FORMAT_TYPE_PRECISION) { if (spec->precision < 0) spec->precision = 0; spec->type = FORMAT_TYPE_NONE; goto qualifier; } /* By default */ spec->type = FORMAT_TYPE_NONE; for (; *fmt ; ++fmt) { if (*fmt == '%') break; } /* Return the current non-format string */ if (fmt != start || !*fmt) return fmt - start; /* Process flags */ spec->flags = 0; while (1) { /* this also skips first '%' */ bool found = true; ++fmt; switch (*fmt) { case '-': spec->flags |= LEFT; break; case '+': spec->flags |= PLUS; break; case ' ': spec->flags |= SPACE; break; case '#': spec->flags |= SPECIAL; break; case '0': spec->flags |= ZEROPAD; break; default: found = false; } if (!found) break; } /* get field width */ spec->field_width = -1; if (isdigit(*fmt)) spec->field_width = skip_atoi(&fmt); else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_WIDTH; return ++fmt - start; } precision: /* get the precision */ spec->precision = -1; if (*fmt == '.') { ++fmt; if (isdigit(*fmt)) { spec->precision = skip_atoi(&fmt); if (spec->precision < 0) spec->precision = 0; } else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_PRECISION; return ++fmt - start; } } qualifier: /* get the conversion qualifier */ qualifier = 0; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z' || *fmt == 't') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'l') { qualifier = 'L'; ++fmt; } else if (qualifier == 'h') { qualifier = 'H'; ++fmt; } } } /* default base */ spec->base = 10; switch (*fmt) { case 'c': spec->type = FORMAT_TYPE_CHAR; return ++fmt - start; case 's': spec->type = FORMAT_TYPE_STR; return ++fmt - start; case 'p': spec->type = FORMAT_TYPE_PTR; return ++fmt - start; case '%': spec->type = FORMAT_TYPE_PERCENT_CHAR; return ++fmt - start; /* integer number formats - set up the flags and "break" */ case 'o': spec->base = 8; break; case 'x': spec->flags |= SMALL; fallthrough; case 'X': spec->base = 16; break; case 'd': case 'i': spec->flags |= SIGN; break; case 'u': break; case 'n': /* * Since %n poses a greater security risk than * utility, treat it as any other invalid or * unsupported format specifier. */ fallthrough; default: WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt); spec->type = FORMAT_TYPE_INVALID; return fmt - start; } if (qualifier == 'L') spec->type = FORMAT_TYPE_LONG_LONG; else if (qualifier == 'l') { BUILD_BUG_ON(FORMAT_TYPE_ULONG + SIGN != FORMAT_TYPE_LONG); spec->type = FORMAT_TYPE_ULONG + (spec->flags & SIGN); } else if (qualifier == 'z') { spec->type = FORMAT_TYPE_SIZE_T; } else if (qualifier == 't') { spec->type = FORMAT_TYPE_PTRDIFF; } else if (qualifier == 'H') { BUILD_BUG_ON(FORMAT_TYPE_UBYTE + SIGN != FORMAT_TYPE_BYTE); spec->type = FORMAT_TYPE_UBYTE + (spec->flags & SIGN); } else if (qualifier == 'h') { BUILD_BUG_ON(FORMAT_TYPE_USHORT + SIGN != FORMAT_TYPE_SHORT); spec->type = FORMAT_TYPE_USHORT + (spec->flags & SIGN); } else { BUILD_BUG_ON(FORMAT_TYPE_UINT + SIGN != FORMAT_TYPE_INT); spec->type = FORMAT_TYPE_UINT + (spec->flags & SIGN); } return ++fmt - start; } static void set_field_width(struct printf_spec *spec, int width) { spec->field_width = width; if (WARN_ONCE(spec->field_width != width, "field width %d too large", width)) { spec->field_width = clamp(width, -FIELD_WIDTH_MAX, FIELD_WIDTH_MAX); } } static void set_precision(struct printf_spec *spec, int prec) { spec->precision = prec; if (WARN_ONCE(spec->precision != prec, "precision %d too large", prec)) { spec->precision = clamp(prec, 0, PRECISION_MAX); } } /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * This function generally follows C99 vsnprintf, but has some * extensions and a few limitations: * * - ``%n`` is unsupported * - ``%p*`` is handled by pointer() * * See pointer() or Documentation/core-api/printk-formats.rst for more * extensive description. * * **Please update the documentation in both places when making changes** * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. * * If you're not already dealing with a va_list consider using snprintf(). */ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) { unsigned long long num; char *str, *end; struct printf_spec spec = {0}; /* Reject out-of-range values early. Large positive sizes are used for unknown buffer sizes. */ if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, va_arg(args, int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, va_arg(args, int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) va_arg(args, int); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: str = string(str, end, va_arg(args, char *), spec); break; case FORMAT_TYPE_PTR: str = pointer(fmt, str, end, va_arg(args, void *), spec); while (isalnum(*fmt)) fmt++; break; case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: /* * Presumably the arguments passed gcc's type * checking, but there is no safe or sane way * for us to continue parsing the format and * fetching from the va_list; the remaining * specifiers and arguments would be out of * sync. */ goto out; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = va_arg(args, long long); break; case FORMAT_TYPE_ULONG: num = va_arg(args, unsigned long); break; case FORMAT_TYPE_LONG: num = va_arg(args, long); break; case FORMAT_TYPE_SIZE_T: if (spec.flags & SIGN) num = va_arg(args, ssize_t); else num = va_arg(args, size_t); break; case FORMAT_TYPE_PTRDIFF: num = va_arg(args, ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = (unsigned char) va_arg(args, int); break; case FORMAT_TYPE_BYTE: num = (signed char) va_arg(args, int); break; case FORMAT_TYPE_USHORT: num = (unsigned short) va_arg(args, int); break; case FORMAT_TYPE_SHORT: num = (short) va_arg(args, int); break; case FORMAT_TYPE_INT: num = (int) va_arg(args, int); break; default: num = va_arg(args, unsigned int); } str = number(str, end, num, spec); } } out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } /* the trailing null byte doesn't count towards the total */ return str-buf; } EXPORT_SYMBOL(vsnprintf); /** * vscnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * The return value is the number of characters which have been written into * the @buf not including the trailing '\0'. If @size is == 0 the function * returns 0. * * If you're not already dealing with a va_list consider using scnprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) { int i; i = vsnprintf(buf, size, fmt, args); if (likely(i < size)) return i; if (size != 0) return size - 1; return 0; } EXPORT_SYMBOL(vscnprintf); /** * snprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters which would be * generated for the given input, excluding the trailing null, * as per ISO C99. If the return is greater than or equal to * @size, the resulting string is truncated. * * See the vsnprintf() documentation for format string extensions over C99. */ int snprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(snprintf); /** * scnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters written into @buf not including * the trailing '\0'. If @size is == 0 the function returns 0. */ int scnprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vscnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(scnprintf); /** * vsprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @args: Arguments for the format string * * The function returns the number of characters written * into @buf. Use vsnprintf() or vscnprintf() in order to avoid * buffer overflows. * * If you're not already dealing with a va_list consider using sprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vsprintf(char *buf, const char *fmt, va_list args) { return vsnprintf(buf, INT_MAX, fmt, args); } EXPORT_SYMBOL(vsprintf); /** * sprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of characters written * into @buf. Use snprintf() or scnprintf() in order to avoid * buffer overflows. * * See the vsnprintf() documentation for format string extensions over C99. */ int sprintf(char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, INT_MAX, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sprintf); #ifdef CONFIG_BINARY_PRINTF /* * bprintf service: * vbin_printf() - VA arguments to binary data * bstr_printf() - Binary data to text string */ /** * vbin_printf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt: The format string to use * @args: Arguments for the format string * * The format follows C99 vsnprintf, except %n is ignored, and its argument * is skipped. * * The return value is the number of words(32bits) which would be generated for * the given input. * * NOTE: * If the return value is greater than @size, the resulting bin_buf is NOT * valid for bstr_printf(). */ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) { struct printf_spec spec = {0}; char *str, *end; int width; str = (char *)bin_buf; end = (char *)(bin_buf + size); #define save_arg(type) \ ({ \ unsigned long long value; \ if (sizeof(type) == 8) { \ unsigned long long val8; \ str = PTR_ALIGN(str, sizeof(u32)); \ val8 = va_arg(args, unsigned long long); \ if (str + sizeof(type) <= end) { \ *(u32 *)str = *(u32 *)&val8; \ *(u32 *)(str + 4) = *((u32 *)&val8 + 1); \ } \ value = val8; \ } else { \ unsigned int val4; \ str = PTR_ALIGN(str, sizeof(type)); \ val4 = va_arg(args, int); \ if (str + sizeof(type) <= end) \ *(typeof(type) *)str = (type)(long)val4; \ value = (unsigned long long)val4; \ } \ str += sizeof(type); \ value; \ }) while (*fmt) { int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: case FORMAT_TYPE_PERCENT_CHAR: break; case FORMAT_TYPE_INVALID: goto out; case FORMAT_TYPE_WIDTH: case FORMAT_TYPE_PRECISION: width = (int)save_arg(int); /* Pointers may require the width */ if (*fmt == 'p') set_field_width(&spec, width); break; case FORMAT_TYPE_CHAR: save_arg(char); break; case FORMAT_TYPE_STR: { const char *save_str = va_arg(args, char *); const char *err_msg; size_t len; err_msg = check_pointer_msg(save_str); if (err_msg) save_str = err_msg; len = strlen(save_str) + 1; if (str + len < end) memcpy(str, save_str, len); str += len; break; } case FORMAT_TYPE_PTR: /* Dereferenced pointers must be done now */ switch (*fmt) { /* Dereference of functions is still OK */ case 'S': case 's': case 'x': case 'K': case 'e': save_arg(void *); break; default: if (!isalnum(*fmt)) { save_arg(void *); break; } str = pointer(fmt, str, end, va_arg(args, void *), spec); if (str + 1 < end) *str++ = '\0'; else end[-1] = '\0'; /* Must be nul terminated */ } /* skip all alphanumeric pointer suffixes */ while (isalnum(*fmt)) fmt++; break; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: save_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: save_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: save_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: save_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: case FORMAT_TYPE_BYTE: save_arg(char); break; case FORMAT_TYPE_USHORT: case FORMAT_TYPE_SHORT: save_arg(short); break; default: save_arg(int); } } } out: return (u32 *)(PTR_ALIGN(str, sizeof(u32))) - bin_buf; #undef save_arg } EXPORT_SYMBOL_GPL(vbin_printf); /** * bstr_printf - Format a string from binary arguments and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @bin_buf: Binary arguments for the format string * * This function like C99 vsnprintf, but the difference is that vsnprintf gets * arguments from stack, and bstr_printf gets arguments from @bin_buf which is * a binary buffer that generated by vbin_printf. * * The format follows C99 vsnprintf, but has some extensions: * see vsnprintf comment for details. * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. */ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) { struct printf_spec spec = {0}; char *str, *end; const char *args = (const char *)bin_buf; if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; #define get_arg(type) \ ({ \ typeof(type) value; \ if (sizeof(type) == 8) { \ args = PTR_ALIGN(args, sizeof(u32)); \ *(u32 *)&value = *(u32 *)args; \ *((u32 *)&value + 1) = *(u32 *)(args + 4); \ } else { \ args = PTR_ALIGN(args, sizeof(type)); \ value = *(typeof(type) *)args; \ } \ args += sizeof(type); \ value; \ }) /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, get_arg(int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, get_arg(int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) get_arg(char); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: { const char *str_arg = args; args += strlen(str_arg) + 1; str = string(str, end, (char *)str_arg, spec); break; } case FORMAT_TYPE_PTR: { bool process = false; int copy, len; /* Non function dereferences were already done */ switch (*fmt) { case 'S': case 's': case 'x': case 'K': case 'e': process = true; break; default: if (!isalnum(*fmt)) { process = true; break; } /* Pointer dereference was already processed */ if (str < end) { len = copy = strlen(args); if (copy > end - str) copy = end - str; memcpy(str, args, copy); str += len; args += len + 1; } } if (process) str = pointer(fmt, str, end, get_arg(void *), spec); while (isalnum(*fmt)) fmt++; break; } case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: goto out; default: { unsigned long long num; switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = get_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: num = get_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: num = get_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: num = get_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = get_arg(unsigned char); break; case FORMAT_TYPE_BYTE: num = get_arg(signed char); break; case FORMAT_TYPE_USHORT: num = get_arg(unsigned short); break; case FORMAT_TYPE_SHORT: num = get_arg(short); break; case FORMAT_TYPE_UINT: num = get_arg(unsigned int); break; default: num = get_arg(int); } str = number(str, end, num, spec); } /* default: */ } /* switch(spec.type) */ } /* while(*fmt) */ out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } #undef get_arg /* the trailing null byte doesn't count towards the total */ return str - buf; } EXPORT_SYMBOL_GPL(bstr_printf); /** * bprintf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of words(u32) written * into @bin_buf. */ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); ret = vbin_printf(bin_buf, size, fmt, args); va_end(args); return ret; } EXPORT_SYMBOL_GPL(bprintf); #endif /* CONFIG_BINARY_PRINTF */ /** * vsscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: format of buffer * @args: arguments */ int vsscanf(const char *buf, const char *fmt, va_list args) { const char *str = buf; char *next; char digit; int num = 0; u8 qualifier; unsigned int base; union { long long s; unsigned long long u; } val; s16 field_width; bool is_sign; while (*fmt) { /* skip any white space in format */ /* white space in format matches any amount of * white space, including none, in the input. */ if (isspace(*fmt)) { fmt = skip_spaces(++fmt); str = skip_spaces(str); } /* anything that is not a conversion must match exactly */ if (*fmt != '%' && *fmt) { if (*fmt++ != *str++) break; continue; } if (!*fmt) break; ++fmt; /* skip this conversion. * advance both strings to next white space */ if (*fmt == '*') { if (!*str) break; while (!isspace(*fmt) && *fmt != '%' && *fmt) { /* '%*[' not yet supported, invalid format */ if (*fmt == '[') return num; fmt++; } while (!isspace(*str) && *str) str++; continue; } /* get field width */ field_width = -1; if (isdigit(*fmt)) { field_width = skip_atoi(&fmt); if (field_width <= 0) break; } /* get conversion qualifier */ qualifier = -1; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'h') { qualifier = 'H'; fmt++; } else if (qualifier == 'l') { qualifier = 'L'; fmt++; } } } if (!*fmt) break; if (*fmt == 'n') { /* return number of characters read so far */ *va_arg(args, int *) = str - buf; ++fmt; continue; } if (!*str) break; base = 10; is_sign = false; switch (*fmt++) { case 'c': { char *s = (char *)va_arg(args, char*); if (field_width == -1) field_width = 1; do { *s++ = *str++; } while (--field_width > 0 && *str); num++; } continue; case 's': { char *s = (char *)va_arg(args, char *); if (field_width == -1) field_width = SHRT_MAX; /* first, skip leading white space in buffer */ str = skip_spaces(str); /* now copy until next white space */ while (*str && !isspace(*str) && field_width--) *s++ = *str++; *s = '\0'; num++; } continue; /* * Warning: This implementation of the '[' conversion specifier * deviates from its glibc counterpart in the following ways: * (1) It does NOT support ranges i.e. '-' is NOT a special * character * (2) It cannot match the closing bracket ']' itself * (3) A field width is required * (4) '%*[' (discard matching input) is currently not supported * * Example usage: * ret = sscanf("00:0a:95","%2[^:]:%2[^:]:%2[^:]", * buf1, buf2, buf3); * if (ret < 3) * // etc.. */ case '[': { char *s = (char *)va_arg(args, char *); DECLARE_BITMAP(set, 256) = {0}; unsigned int len = 0; bool negate = (*fmt == '^'); /* field width is required */ if (field_width == -1) return num; if (negate) ++fmt; for ( ; *fmt && *fmt != ']'; ++fmt, ++len) set_bit((u8)*fmt, set); /* no ']' or no character set found */ if (!*fmt || !len) return num; ++fmt; if (negate) { bitmap_complement(set, set, 256); /* exclude null '\0' byte */ clear_bit(0, set); } /* match must be non-empty */ if (!test_bit((u8)*str, set)) return num; while (test_bit((u8)*str, set) && field_width--) *s++ = *str++; *s = '\0'; ++num; } continue; case 'o': base = 8; break; case 'x': case 'X': base = 16; break; case 'i': base = 0; fallthrough; case 'd': is_sign = true; fallthrough; case 'u': break; case '%': /* looking for '%' in str */ if (*str++ != '%') return num; continue; default: /* invalid format; stop here */ return num; } /* have some sort of integer conversion. * first, skip white space in buffer. */ str = skip_spaces(str); digit = *str; if (is_sign && digit == '-') { if (field_width == 1) break; digit = *(str + 1); } if (!digit || (base == 16 && !isxdigit(digit)) || (base == 10 && !isdigit(digit)) || (base == 8 && (!isdigit(digit) || digit > '7')) || (base == 0 && !isdigit(digit))) break; if (is_sign) val.s = simple_strntoll(str, field_width >= 0 ? field_width : INT_MAX, &next, base); else val.u = simple_strntoull(str, field_width >= 0 ? field_width : INT_MAX, &next, base); switch (qualifier) { case 'H': /* that's 'hh' in format */ if (is_sign) *va_arg(args, signed char *) = val.s; else *va_arg(args, unsigned char *) = val.u; break; case 'h': if (is_sign) *va_arg(args, short *) = val.s; else *va_arg(args, unsigned short *) = val.u; break; case 'l': if (is_sign) *va_arg(args, long *) = val.s; else *va_arg(args, unsigned long *) = val.u; break; case 'L': if (is_sign) *va_arg(args, long long *) = val.s; else *va_arg(args, unsigned long long *) = val.u; break; case 'z': *va_arg(args, size_t *) = val.u; break; default: if (is_sign) *va_arg(args, int *) = val.s; else *va_arg(args, unsigned int *) = val.u; break; } num++; if (!next) break; str = next; } return num; } EXPORT_SYMBOL(vsscanf); /** * sscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: formatting of buffer * @...: resulting arguments */ int sscanf(const char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsscanf(buf, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sscanf); |
| 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux I2C core * * Copyright (C) 1995-99 Simon G. Vogl * With some changes from Kyösti Mälkki <kmalkki@cc.hut.fi> * Mux support by Rodolfo Giometti <giometti@enneenne.com> and * Michael Lawnick <michael.lawnick.ext@nsn.com> * * Copyright (C) 2013-2017 Wolfram Sang <wsa@kernel.org> */ #define pr_fmt(fmt) "i2c-core: " fmt #include <dt-bindings/i2c/i2c.h> #include <linux/acpi.h> #include <linux/clk/clk-conf.h> #include <linux/completion.h> #include <linux/delay.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/gpio/consumer.h> #include <linux/i2c.h> #include <linux/i2c-smbus.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/irqflags.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/of_device.h> #include <linux/of.h> #include <linux/of_irq.h> #include <linux/pinctrl/consumer.h> #include <linux/pm_domain.h> #include <linux/pm_runtime.h> #include <linux/pm_wakeirq.h> #include <linux/property.h> #include <linux/rwsem.h> #include <linux/slab.h> #include "i2c-core.h" #define CREATE_TRACE_POINTS #include <trace/events/i2c.h> #define I2C_ADDR_OFFSET_TEN_BIT 0xa000 #define I2C_ADDR_OFFSET_SLAVE 0x1000 #define I2C_ADDR_7BITS_MAX 0x77 #define I2C_ADDR_7BITS_COUNT (I2C_ADDR_7BITS_MAX + 1) #define I2C_ADDR_DEVICE_ID 0x7c /* * core_lock protects i2c_adapter_idr, and guarantees that device detection, * deletion of detected devices are serialized */ static DEFINE_MUTEX(core_lock); static DEFINE_IDR(i2c_adapter_idr); static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver); static DEFINE_STATIC_KEY_FALSE(i2c_trace_msg_key); static bool is_registered; int i2c_transfer_trace_reg(void) { static_branch_inc(&i2c_trace_msg_key); return 0; } void i2c_transfer_trace_unreg(void) { static_branch_dec(&i2c_trace_msg_key); } const char *i2c_freq_mode_string(u32 bus_freq_hz) { switch (bus_freq_hz) { case I2C_MAX_STANDARD_MODE_FREQ: return "Standard Mode (100 kHz)"; case I2C_MAX_FAST_MODE_FREQ: return "Fast Mode (400 kHz)"; case I2C_MAX_FAST_MODE_PLUS_FREQ: return "Fast Mode Plus (1.0 MHz)"; case I2C_MAX_TURBO_MODE_FREQ: return "Turbo Mode (1.4 MHz)"; case I2C_MAX_HIGH_SPEED_MODE_FREQ: return "High Speed Mode (3.4 MHz)"; case I2C_MAX_ULTRA_FAST_MODE_FREQ: return "Ultra Fast Mode (5.0 MHz)"; default: return "Unknown Mode"; } } EXPORT_SYMBOL_GPL(i2c_freq_mode_string); const struct i2c_device_id *i2c_match_id(const struct i2c_device_id *id, const struct i2c_client *client) { if (!(id && client)) return NULL; while (id->name[0]) { if (strcmp(client->name, id->name) == 0) return id; id++; } return NULL; } EXPORT_SYMBOL_GPL(i2c_match_id); static int i2c_device_match(struct device *dev, struct device_driver *drv) { struct i2c_client *client = i2c_verify_client(dev); struct i2c_driver *driver; /* Attempt an OF style match */ if (i2c_of_match_device(drv->of_match_table, client)) return 1; /* Then ACPI style match */ if (acpi_driver_match_device(dev, drv)) return 1; driver = to_i2c_driver(drv); /* Finally an I2C match */ if (i2c_match_id(driver->id_table, client)) return 1; return 0; } static int i2c_device_uevent(struct device *dev, struct kobj_uevent_env *env) { struct i2c_client *client = to_i2c_client(dev); int rc; rc = of_device_uevent_modalias(dev, env); if (rc != -ENODEV) return rc; rc = acpi_device_uevent_modalias(dev, env); if (rc != -ENODEV) return rc; return add_uevent_var(env, "MODALIAS=%s%s", I2C_MODULE_PREFIX, client->name); } /* i2c bus recovery routines */ static int get_scl_gpio_value(struct i2c_adapter *adap) { return gpiod_get_value_cansleep(adap->bus_recovery_info->scl_gpiod); } static void set_scl_gpio_value(struct i2c_adapter *adap, int val) { gpiod_set_value_cansleep(adap->bus_recovery_info->scl_gpiod, val); } static int get_sda_gpio_value(struct i2c_adapter *adap) { return gpiod_get_value_cansleep(adap->bus_recovery_info->sda_gpiod); } static void set_sda_gpio_value(struct i2c_adapter *adap, int val) { gpiod_set_value_cansleep(adap->bus_recovery_info->sda_gpiod, val); } static int i2c_generic_bus_free(struct i2c_adapter *adap) { struct i2c_bus_recovery_info *bri = adap->bus_recovery_info; int ret = -EOPNOTSUPP; if (bri->get_bus_free) ret = bri->get_bus_free(adap); else if (bri->get_sda) ret = bri->get_sda(adap); if (ret < 0) return ret; return ret ? 0 : -EBUSY; } /* * We are generating clock pulses. ndelay() determines durating of clk pulses. * We will generate clock with rate 100 KHz and so duration of both clock levels * is: delay in ns = (10^6 / 100) / 2 */ #define RECOVERY_NDELAY 5000 #define RECOVERY_CLK_CNT 9 int i2c_generic_scl_recovery(struct i2c_adapter *adap) { struct i2c_bus_recovery_info *bri = adap->bus_recovery_info; int i = 0, scl = 1, ret = 0; if (bri->prepare_recovery) bri->prepare_recovery(adap); if (bri->pinctrl) pinctrl_select_state(bri->pinctrl, bri->pins_gpio); /* * If we can set SDA, we will always create a STOP to ensure additional * pulses will do no harm. This is achieved by letting SDA follow SCL * half a cycle later. Check the 'incomplete_write_byte' fault injector * for details. Note that we must honour tsu:sto, 4us, but lets use 5us * here for simplicity. */ bri->set_scl(adap, scl); ndelay(RECOVERY_NDELAY); if (bri->set_sda) bri->set_sda(adap, scl); ndelay(RECOVERY_NDELAY / 2); /* * By this time SCL is high, as we need to give 9 falling-rising edges */ while (i++ < RECOVERY_CLK_CNT * 2) { if (scl) { /* SCL shouldn't be low here */ if (!bri->get_scl(adap)) { dev_err(&adap->dev, "SCL is stuck low, exit recovery\n"); ret = -EBUSY; break; } } scl = !scl; bri->set_scl(adap, scl); /* Creating STOP again, see above */ if (scl) { /* Honour minimum tsu:sto */ ndelay(RECOVERY_NDELAY); } else { /* Honour minimum tf and thd:dat */ ndelay(RECOVERY_NDELAY / 2); } if (bri->set_sda) bri->set_sda(adap, scl); ndelay(RECOVERY_NDELAY / 2); if (scl) { ret = i2c_generic_bus_free(adap); if (ret == 0) break; } } /* If we can't check bus status, assume recovery worked */ if (ret == -EOPNOTSUPP) ret = 0; if (bri->unprepare_recovery) bri->unprepare_recovery(adap); if (bri->pinctrl) pinctrl_select_state(bri->pinctrl, bri->pins_default); return ret; } EXPORT_SYMBOL_GPL(i2c_generic_scl_recovery); int i2c_recover_bus(struct i2c_adapter *adap) { if (!adap->bus_recovery_info) return -EBUSY; dev_dbg(&adap->dev, "Trying i2c bus recovery\n"); return adap->bus_recovery_info->recover_bus(adap); } EXPORT_SYMBOL_GPL(i2c_recover_bus); static void i2c_gpio_init_pinctrl_recovery(struct i2c_adapter *adap) { struct i2c_bus_recovery_info *bri = adap->bus_recovery_info; struct device *dev = &adap->dev; struct pinctrl *p = bri->pinctrl; /* * we can't change states without pinctrl, so remove the states if * populated */ if (!p) { bri->pins_default = NULL; bri->pins_gpio = NULL; return; } if (!bri->pins_default) { bri->pins_default = pinctrl_lookup_state(p, PINCTRL_STATE_DEFAULT); if (IS_ERR(bri->pins_default)) { dev_dbg(dev, PINCTRL_STATE_DEFAULT " state not found for GPIO recovery\n"); bri->pins_default = NULL; } } if (!bri->pins_gpio) { bri->pins_gpio = pinctrl_lookup_state(p, "gpio"); if (IS_ERR(bri->pins_gpio)) bri->pins_gpio = pinctrl_lookup_state(p, "recovery"); if (IS_ERR(bri->pins_gpio)) { dev_dbg(dev, "no gpio or recovery state found for GPIO recovery\n"); bri->pins_gpio = NULL; } } /* for pinctrl state changes, we need all the information */ if (bri->pins_default && bri->pins_gpio) { dev_info(dev, "using pinctrl states for GPIO recovery"); } else { bri->pinctrl = NULL; bri->pins_default = NULL; bri->pins_gpio = NULL; } } static int i2c_gpio_init_generic_recovery(struct i2c_adapter *adap) { struct i2c_bus_recovery_info *bri = adap->bus_recovery_info; struct device *dev = &adap->dev; struct gpio_desc *gpiod; int ret = 0; /* * don't touch the recovery information if the driver is not using * generic SCL recovery */ if (bri->recover_bus && bri->recover_bus != i2c_generic_scl_recovery) return 0; /* * pins might be taken as GPIO, so we should inform pinctrl about * this and move the state to GPIO */ if (bri->pinctrl) pinctrl_select_state(bri->pinctrl, bri->pins_gpio); /* * if there is incomplete or no recovery information, see if generic * GPIO recovery is available */ if (!bri->scl_gpiod) { gpiod = devm_gpiod_get(dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN); if (PTR_ERR(gpiod) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; goto cleanup_pinctrl_state; } if (!IS |