1// SPDX-License-Identifier: GPL-2.0-or-later 2/* 3 * Linux INET6 implementation 4 * Forwarding Information Database 5 * 6 * Authors: 7 * Pedro Roque <roque@di.fc.ul.pt> 8 * 9 * Changes: 10 * Yuji SEKIYA @USAGI: Support default route on router node; 11 * remove ip6_null_entry from the top of 12 * routing table. 13 * Ville Nuorvala: Fixed routing subtrees. 14 */ 15 16#define pr_fmt(fmt) "IPv6: " fmt 17 18#include <linux/errno.h> 19#include <linux/types.h> 20#include <linux/net.h> 21#include <linux/route.h> 22#include <linux/netdevice.h> 23#include <linux/in6.h> 24#include <linux/init.h> 25#include <linux/list.h> 26#include <linux/slab.h> 27 28#include <net/ip.h> 29#include <net/ipv6.h> 30#include <net/ndisc.h> 31#include <net/addrconf.h> 32#include <net/lwtunnel.h> 33#include <net/fib_notifier.h> 34 35#include <net/ip6_fib.h> 36#include <net/ip6_route.h> 37 38static struct kmem_cache *fib6_node_kmem __read_mostly; 39 40struct fib6_cleaner { 41 struct fib6_walker w; 42 struct net *net; 43 int (*func)(struct fib6_info *, void *arg); 44 int sernum; 45 void *arg; 46 bool skip_notify; 47}; 48 49#ifdef CONFIG_IPV6_SUBTREES 50#define FWS_INIT FWS_S 51#else 52#define FWS_INIT FWS_L 53#endif 54 55static struct fib6_info *fib6_find_prefix(struct net *net, 56 struct fib6_table *table, 57 struct fib6_node *fn); 58static struct fib6_node *fib6_repair_tree(struct net *net, 59 struct fib6_table *table, 60 struct fib6_node *fn); 61static int fib6_walk(struct net *net, struct fib6_walker *w); 62static int fib6_walk_continue(struct fib6_walker *w); 63 64/* 65 * A routing update causes an increase of the serial number on the 66 * affected subtree. This allows for cached routes to be asynchronously 67 * tested when modifications are made to the destination cache as a 68 * result of redirects, path MTU changes, etc. 69 */ 70 71static void fib6_gc_timer_cb(struct timer_list *t); 72 73#define FOR_WALKERS(net, w) \ 74 list_for_each_entry(w, &(net)->ipv6.fib6_walkers, lh) 75 76static void fib6_walker_link(struct net *net, struct fib6_walker *w) 77{ 78 write_lock_bh(&net->ipv6.fib6_walker_lock); 79 list_add(&w->lh, &net->ipv6.fib6_walkers); 80 write_unlock_bh(&net->ipv6.fib6_walker_lock); 81} 82 83static void fib6_walker_unlink(struct net *net, struct fib6_walker *w) 84{ 85 write_lock_bh(&net->ipv6.fib6_walker_lock); 86 list_del(&w->lh); 87 write_unlock_bh(&net->ipv6.fib6_walker_lock); 88} 89 90static int fib6_new_sernum(struct net *net) 91{ 92 int new, old; 93 94 do { 95 old = atomic_read(&net->ipv6.fib6_sernum); 96 new = old < INT_MAX ? old + 1 : 1; 97 } while (atomic_cmpxchg(&net->ipv6.fib6_sernum, 98 old, new) != old); 99 return new; 100} 101 102enum { 103 FIB6_NO_SERNUM_CHANGE = 0, 104}; 105 106void fib6_update_sernum(struct net *net, struct fib6_info *f6i) 107{ 108 struct fib6_node *fn; 109 110 fn = rcu_dereference_protected(f6i->fib6_node, 111 lockdep_is_held(&f6i->fib6_table->tb6_lock)); 112 if (fn) 113 WRITE_ONCE(fn->fn_sernum, fib6_new_sernum(net)); 114} 115 116/* 117 * Auxiliary address test functions for the radix tree. 118 * 119 * These assume a 32bit processor (although it will work on 120 * 64bit processors) 121 */ 122 123/* 124 * test bit 125 */ 126#if defined(__LITTLE_ENDIAN) 127# define BITOP_BE32_SWIZZLE (0x1F & ~7) 128#else 129# define BITOP_BE32_SWIZZLE 0 130#endif 131 132static __be32 addr_bit_set(const void *token, int fn_bit) 133{ 134 const __be32 *addr = token; 135 /* 136 * Here, 137 * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) 138 * is optimized version of 139 * htonl(1 << ((~fn_bit)&0x1F)) 140 * See include/asm-generic/bitops/le.h. 141 */ 142 return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) & 143 addr[fn_bit >> 5]; 144} 145 146struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh) 147{ 148 struct fib6_info *f6i; 149 size_t sz = sizeof(*f6i); 150 151 if (with_fib6_nh) 152 sz += sizeof(struct fib6_nh); 153 154 f6i = kzalloc(sz, gfp_flags); 155 if (!f6i) 156 return NULL; 157 158 /* fib6_siblings is a union with nh_list, so this initializes both */ 159 INIT_LIST_HEAD(&f6i->fib6_siblings); 160 refcount_set(&f6i->fib6_ref, 1); 161 162 return f6i; 163} 164 165void fib6_info_destroy_rcu(struct rcu_head *head) 166{ 167 struct fib6_info *f6i = container_of(head, struct fib6_info, rcu); 168 169 WARN_ON(f6i->fib6_node); 170 171 if (f6i->nh) 172 nexthop_put(f6i->nh); 173 else 174 fib6_nh_release(f6i->fib6_nh); 175 176 ip_fib_metrics_put(f6i->fib6_metrics); 177 kfree(f6i); 178} 179EXPORT_SYMBOL_GPL(fib6_info_destroy_rcu); 180 181static struct fib6_node *node_alloc(struct net *net) 182{ 183 struct fib6_node *fn; 184 185 fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC); 186 if (fn) 187 net->ipv6.rt6_stats->fib_nodes++; 188 189 return fn; 190} 191 192static void node_free_immediate(struct net *net, struct fib6_node *fn) 193{ 194 kmem_cache_free(fib6_node_kmem, fn); 195 net->ipv6.rt6_stats->fib_nodes--; 196} 197 198static void node_free_rcu(struct rcu_head *head) 199{ 200 struct fib6_node *fn = container_of(head, struct fib6_node, rcu); 201 202 kmem_cache_free(fib6_node_kmem, fn); 203} 204 205static void node_free(struct net *net, struct fib6_node *fn) 206{ 207 call_rcu(&fn->rcu, node_free_rcu); 208 net->ipv6.rt6_stats->fib_nodes--; 209} 210 211static void fib6_free_table(struct fib6_table *table) 212{ 213 inetpeer_invalidate_tree(&table->tb6_peers); 214 kfree(table); 215} 216 217static void fib6_link_table(struct net *net, struct fib6_table *tb) 218{ 219 unsigned int h; 220 221 /* 222 * Initialize table lock at a single place to give lockdep a key, 223 * tables aren't visible prior to being linked to the list. 224 */ 225 spin_lock_init(&tb->tb6_lock); 226 h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1); 227 228 /* 229 * No protection necessary, this is the only list mutatation 230 * operation, tables never disappear once they exist. 231 */ 232 hlist_add_head_rcu(&tb->tb6_hlist, &net->ipv6.fib_table_hash[h]); 233} 234 235#ifdef CONFIG_IPV6_MULTIPLE_TABLES 236 237static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) 238{ 239 struct fib6_table *table; 240 241 table = kzalloc(sizeof(*table), GFP_ATOMIC); 242 if (table) { 243 table->tb6_id = id; 244 rcu_assign_pointer(table->tb6_root.leaf, 245 net->ipv6.fib6_null_entry); 246 table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; 247 inet_peer_base_init(&table->tb6_peers); 248 } 249 250 return table; 251} 252 253struct fib6_table *fib6_new_table(struct net *net, u32 id) 254{ 255 struct fib6_table *tb; 256 257 if (id == 0) 258 id = RT6_TABLE_MAIN; 259 tb = fib6_get_table(net, id); 260 if (tb) 261 return tb; 262 263 tb = fib6_alloc_table(net, id); 264 if (tb) 265 fib6_link_table(net, tb); 266 267 return tb; 268} 269EXPORT_SYMBOL_GPL(fib6_new_table); 270 271struct fib6_table *fib6_get_table(struct net *net, u32 id) 272{ 273 struct fib6_table *tb; 274 struct hlist_head *head; 275 unsigned int h; 276 277 if (id == 0) 278 id = RT6_TABLE_MAIN; 279 h = id & (FIB6_TABLE_HASHSZ - 1); 280 rcu_read_lock(); 281 head = &net->ipv6.fib_table_hash[h]; 282 hlist_for_each_entry_rcu(tb, head, tb6_hlist) { 283 if (tb->tb6_id == id) { 284 rcu_read_unlock(); 285 return tb; 286 } 287 } 288 rcu_read_unlock(); 289 290 return NULL; 291} 292EXPORT_SYMBOL_GPL(fib6_get_table); 293 294static void __net_init fib6_tables_init(struct net *net) 295{ 296 fib6_link_table(net, net->ipv6.fib6_main_tbl); 297 fib6_link_table(net, net->ipv6.fib6_local_tbl); 298} 299#else 300 301struct fib6_table *fib6_new_table(struct net *net, u32 id) 302{ 303 return fib6_get_table(net, id); 304} 305 306struct fib6_table *fib6_get_table(struct net *net, u32 id) 307{ 308 return net->ipv6.fib6_main_tbl; 309} 310 311struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, 312 const struct sk_buff *skb, 313 int flags, pol_lookup_t lookup) 314{ 315 struct rt6_info *rt; 316 317 rt = pol_lookup_func(lookup, 318 net, net->ipv6.fib6_main_tbl, fl6, skb, flags); 319 if (rt->dst.error == -EAGAIN) { 320 ip6_rt_put_flags(rt, flags); 321 rt = net->ipv6.ip6_null_entry; 322 if (!(flags & RT6_LOOKUP_F_DST_NOREF)) 323 dst_hold(&rt->dst); 324 } 325 326 return &rt->dst; 327} 328 329/* called with rcu lock held; no reference taken on fib6_info */ 330int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, 331 struct fib6_result *res, int flags) 332{ 333 return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, 334 res, flags); 335} 336 337static void __net_init fib6_tables_init(struct net *net) 338{ 339 fib6_link_table(net, net->ipv6.fib6_main_tbl); 340} 341 342#endif 343 344unsigned int fib6_tables_seq_read(struct net *net) 345{ 346 unsigned int h, fib_seq = 0; 347 348 rcu_read_lock(); 349 for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { 350 struct hlist_head *head = &net->ipv6.fib_table_hash[h]; 351 struct fib6_table *tb; 352 353 hlist_for_each_entry_rcu(tb, head, tb6_hlist) 354 fib_seq += tb->fib_seq; 355 } 356 rcu_read_unlock(); 357 358 return fib_seq; 359} 360 361static int call_fib6_entry_notifier(struct notifier_block *nb, 362 enum fib_event_type event_type, 363 struct fib6_info *rt, 364 struct netlink_ext_ack *extack) 365{ 366 struct fib6_entry_notifier_info info = { 367 .info.extack = extack, 368 .rt = rt, 369 }; 370 371 return call_fib6_notifier(nb, event_type, &info.info); 372} 373 374static int call_fib6_multipath_entry_notifier(struct notifier_block *nb, 375 enum fib_event_type event_type, 376 struct fib6_info *rt, 377 unsigned int nsiblings, 378 struct netlink_ext_ack *extack) 379{ 380 struct fib6_entry_notifier_info info = { 381 .info.extack = extack, 382 .rt = rt, 383 .nsiblings = nsiblings, 384 }; 385 386 return call_fib6_notifier(nb, event_type, &info.info); 387} 388 389int call_fib6_entry_notifiers(struct net *net, 390 enum fib_event_type event_type, 391 struct fib6_info *rt, 392 struct netlink_ext_ack *extack) 393{ 394 struct fib6_entry_notifier_info info = { 395 .info.extack = extack, 396 .rt = rt, 397 }; 398 399 rt->fib6_table->fib_seq++; 400 return call_fib6_notifiers(net, event_type, &info.info); 401} 402 403int call_fib6_multipath_entry_notifiers(struct net *net, 404 enum fib_event_type event_type, 405 struct fib6_info *rt, 406 unsigned int nsiblings, 407 struct netlink_ext_ack *extack) 408{ 409 struct fib6_entry_notifier_info info = { 410 .info.extack = extack, 411 .rt = rt, 412 .nsiblings = nsiblings, 413 }; 414 415 rt->fib6_table->fib_seq++; 416 return call_fib6_notifiers(net, event_type, &info.info); 417} 418 419int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt) 420{ 421 struct fib6_entry_notifier_info info = { 422 .rt = rt, 423 .nsiblings = rt->fib6_nsiblings, 424 }; 425 426 rt->fib6_table->fib_seq++; 427 return call_fib6_notifiers(net, FIB_EVENT_ENTRY_REPLACE, &info.info); 428} 429 430struct fib6_dump_arg { 431 struct net *net; 432 struct notifier_block *nb; 433 struct netlink_ext_ack *extack; 434}; 435 436static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) 437{ 438 enum fib_event_type fib_event = FIB_EVENT_ENTRY_REPLACE; 439 int err; 440 441 if (!rt || rt == arg->net->ipv6.fib6_null_entry) 442 return 0; 443 444 if (rt->fib6_nsiblings) 445 err = call_fib6_multipath_entry_notifier(arg->nb, fib_event, 446 rt, 447 rt->fib6_nsiblings, 448 arg->extack); 449 else 450 err = call_fib6_entry_notifier(arg->nb, fib_event, rt, 451 arg->extack); 452 453 return err; 454} 455 456static int fib6_node_dump(struct fib6_walker *w) 457{ 458 int err; 459 460 err = fib6_rt_dump(w->leaf, w->args); 461 w->leaf = NULL; 462 return err; 463} 464 465static int fib6_table_dump(struct net *net, struct fib6_table *tb, 466 struct fib6_walker *w) 467{ 468 int err; 469 470 w->root = &tb->tb6_root; 471 spin_lock_bh(&tb->tb6_lock); 472 err = fib6_walk(net, w); 473 spin_unlock_bh(&tb->tb6_lock); 474 return err; 475} 476 477/* Called with rcu_read_lock() */ 478int fib6_tables_dump(struct net *net, struct notifier_block *nb, 479 struct netlink_ext_ack *extack) 480{ 481 struct fib6_dump_arg arg; 482 struct fib6_walker *w; 483 unsigned int h; 484 int err = 0; 485 486 w = kzalloc(sizeof(*w), GFP_ATOMIC); 487 if (!w) 488 return -ENOMEM; 489 490 w->func = fib6_node_dump; 491 arg.net = net; 492 arg.nb = nb; 493 arg.extack = extack; 494 w->args = &arg; 495 496 for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { 497 struct hlist_head *head = &net->ipv6.fib_table_hash[h]; 498 struct fib6_table *tb; 499 500 hlist_for_each_entry_rcu(tb, head, tb6_hlist) { 501 err = fib6_table_dump(net, tb, w); 502 if (err) 503 goto out; 504 } 505 } 506 507out: 508 kfree(w); 509 510 /* The tree traversal function should never return a positive value. */ 511 return err > 0 ? -EINVAL : err; 512} 513 514static int fib6_dump_node(struct fib6_walker *w) 515{ 516 int res; 517 struct fib6_info *rt; 518 519 for_each_fib6_walker_rt(w) { 520 res = rt6_dump_route(rt, w->args, w->skip_in_node); 521 if (res >= 0) { 522 /* Frame is full, suspend walking */ 523 w->leaf = rt; 524 525 /* We'll restart from this node, so if some routes were 526 * already dumped, skip them next time. 527 */ 528 w->skip_in_node += res; 529 530 return 1; 531 } 532 w->skip_in_node = 0; 533 534 /* Multipath routes are dumped in one route with the 535 * RTA_MULTIPATH attribute. Jump 'rt' to point to the 536 * last sibling of this route (no need to dump the 537 * sibling routes again) 538 */ 539 if (rt->fib6_nsiblings) 540 rt = list_last_entry(&rt->fib6_siblings, 541 struct fib6_info, 542 fib6_siblings); 543 } 544 w->leaf = NULL; 545 return 0; 546} 547 548static void fib6_dump_end(struct netlink_callback *cb) 549{ 550 struct net *net = sock_net(cb->skb->sk); 551 struct fib6_walker *w = (void *)cb->args[2]; 552 553 if (w) { 554 if (cb->args[4]) { 555 cb->args[4] = 0; 556 fib6_walker_unlink(net, w); 557 } 558 cb->args[2] = 0; 559 kfree(w); 560 } 561 cb->done = (void *)cb->args[3]; 562 cb->args[1] = 3; 563} 564 565static int fib6_dump_done(struct netlink_callback *cb) 566{ 567 fib6_dump_end(cb); 568 return cb->done ? cb->done(cb) : 0; 569} 570 571static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, 572 struct netlink_callback *cb) 573{ 574 struct net *net = sock_net(skb->sk); 575 struct fib6_walker *w; 576 int res; 577 578 w = (void *)cb->args[2]; 579 w->root = &table->tb6_root; 580 581 if (cb->args[4] == 0) { 582 w->count = 0; 583 w->skip = 0; 584 w->skip_in_node = 0; 585 586 spin_lock_bh(&table->tb6_lock); 587 res = fib6_walk(net, w); 588 spin_unlock_bh(&table->tb6_lock); 589 if (res > 0) { 590 cb->args[4] = 1; 591 cb->args[5] = READ_ONCE(w->root->fn_sernum); 592 } 593 } else { 594 int sernum = READ_ONCE(w->root->fn_sernum); 595 if (cb->args[5] != sernum) { 596 /* Begin at the root if the tree changed */ 597 cb->args[5] = sernum; 598 w->state = FWS_INIT; 599 w->node = w->root; 600 w->skip = w->count; 601 w->skip_in_node = 0; 602 } else 603 w->skip = 0; 604 605 spin_lock_bh(&table->tb6_lock); 606 res = fib6_walk_continue(w); 607 spin_unlock_bh(&table->tb6_lock); 608 if (res <= 0) { 609 fib6_walker_unlink(net, w); 610 cb->args[4] = 0; 611 } 612 } 613 614 return res; 615} 616 617static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) 618{ 619 struct rt6_rtnl_dump_arg arg = { .filter.dump_exceptions = true, 620 .filter.dump_routes = true }; 621 const struct nlmsghdr *nlh = cb->nlh; 622 struct net *net = sock_net(skb->sk); 623 unsigned int h, s_h; 624 unsigned int e = 0, s_e; 625 struct fib6_walker *w; 626 struct fib6_table *tb; 627 struct hlist_head *head; 628 int res = 0; 629 630 if (cb->strict_check) { 631 int err; 632 633 err = ip_valid_fib_dump_req(net, nlh, &arg.filter, cb); 634 if (err < 0) 635 return err; 636 } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { 637 struct rtmsg *rtm = nlmsg_data(nlh); 638 639 if (rtm->rtm_flags & RTM_F_PREFIX) 640 arg.filter.flags = RTM_F_PREFIX; 641 } 642 643 w = (void *)cb->args[2]; 644 if (!w) { 645 /* New dump: 646 * 647 * 1. allocate and initialize walker. 648 */ 649 w = kzalloc(sizeof(*w), GFP_ATOMIC); 650 if (!w) 651 return -ENOMEM; 652 w->func = fib6_dump_node; 653 cb->args[2] = (long)w; 654 655 /* 2. hook callback destructor. 656 */ 657 cb->args[3] = (long)cb->done; 658 cb->done = fib6_dump_done; 659 660 } 661 662 arg.skb = skb; 663 arg.cb = cb; 664 arg.net = net; 665 w->args = &arg; 666 667 if (arg.filter.table_id) { 668 tb = fib6_get_table(net, arg.filter.table_id); 669 if (!tb) { 670 if (rtnl_msg_family(cb->nlh) != PF_INET6) 671 goto out; 672 673 NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); 674 return -ENOENT; 675 } 676 677 if (!cb->args[0]) { 678 res = fib6_dump_table(tb, skb, cb); 679 if (!res) 680 cb->args[0] = 1; 681 } 682 goto out; 683 } 684 685 s_h = cb->args[0]; 686 s_e = cb->args[1]; 687 688 rcu_read_lock(); 689 for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) { 690 e = 0; 691 head = &net->ipv6.fib_table_hash[h]; 692 hlist_for_each_entry_rcu(tb, head, tb6_hlist) { 693 if (e < s_e) 694 goto next; 695 res = fib6_dump_table(tb, skb, cb); 696 if (res != 0) 697 goto out_unlock; 698next: 699 e++; 700 } 701 } 702out_unlock: 703 rcu_read_unlock(); 704 cb->args[1] = e; 705 cb->args[0] = h; 706out: 707 res = res < 0 ? res : skb->len; 708 if (res <= 0) 709 fib6_dump_end(cb); 710 return res; 711} 712 713void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val) 714{ 715 if (!f6i) 716 return; 717 718 if (f6i->fib6_metrics == &dst_default_metrics) { 719 struct dst_metrics *p = kzalloc(sizeof(*p), GFP_ATOMIC); 720 721 if (!p) 722 return; 723 724 refcount_set(&p->refcnt, 1); 725 f6i->fib6_metrics = p; 726 } 727 728 f6i->fib6_metrics->metrics[metric - 1] = val; 729} 730 731/* 732 * Routing Table 733 * 734 * return the appropriate node for a routing tree "add" operation 735 * by either creating and inserting or by returning an existing 736 * node. 737 */ 738 739static struct fib6_node *fib6_add_1(struct net *net, 740 struct fib6_table *table, 741 struct fib6_node *root, 742 struct in6_addr *addr, int plen, 743 int offset, int allow_create, 744 int replace_required, 745 struct netlink_ext_ack *extack) 746{ 747 struct fib6_node *fn, *in, *ln; 748 struct fib6_node *pn = NULL; 749 struct rt6key *key; 750 int bit; 751 __be32 dir = 0; 752 753 RT6_TRACE("fib6_add_1\n"); 754 755 /* insert node in tree */ 756 757 fn = root; 758 759 do { 760 struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, 761 lockdep_is_held(&table->tb6_lock)); 762 key = (struct rt6key *)((u8 *)leaf + offset); 763 764 /* 765 * Prefix match 766 */ 767 if (plen < fn->fn_bit || 768 !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) { 769 if (!allow_create) { 770 if (replace_required) { 771 NL_SET_ERR_MSG(extack, 772 "Can not replace route - no match found"); 773 pr_warn("Can't replace route, no match found\n"); 774 return ERR_PTR(-ENOENT); 775 } 776 pr_warn("NLM_F_CREATE should be set when creating new route\n"); 777 } 778 goto insert_above; 779 } 780 781 /* 782 * Exact match ? 783 */ 784 785 if (plen == fn->fn_bit) { 786 /* clean up an intermediate node */ 787 if (!(fn->fn_flags & RTN_RTINFO)) { 788 RCU_INIT_POINTER(fn->leaf, NULL); 789 fib6_info_release(leaf); 790 /* remove null_entry in the root node */ 791 } else if (fn->fn_flags & RTN_TL_ROOT && 792 rcu_access_pointer(fn->leaf) == 793 net->ipv6.fib6_null_entry) { 794 RCU_INIT_POINTER(fn->leaf, NULL); 795 } 796 797 return fn; 798 } 799 800 /* 801 * We have more bits to go 802 */ 803 804 /* Try to walk down on tree. */ 805 dir = addr_bit_set(addr, fn->fn_bit); 806 pn = fn; 807 fn = dir ? 808 rcu_dereference_protected(fn->right, 809 lockdep_is_held(&table->tb6_lock)) : 810 rcu_dereference_protected(fn->left, 811 lockdep_is_held(&table->tb6_lock)); 812 } while (fn); 813 814 if (!allow_create) { 815 /* We should not create new node because 816 * NLM_F_REPLACE was specified without NLM_F_CREATE 817 * I assume it is safe to require NLM_F_CREATE when 818 * REPLACE flag is used! Later we may want to remove the 819 * check for replace_required, because according 820 * to netlink specification, NLM_F_CREATE 821 * MUST be specified if new route is created. 822 * That would keep IPv6 consistent with IPv4 823 */ 824 if (replace_required) { 825 NL_SET_ERR_MSG(extack, 826 "Can not replace route - no match found"); 827 pr_warn("Can't replace route, no match found\n"); 828 return ERR_PTR(-ENOENT); 829 } 830 pr_warn("NLM_F_CREATE should be set when creating new route\n"); 831 } 832 /* 833 * We walked to the bottom of tree. 834 * Create new leaf node without children. 835 */ 836 837 ln = node_alloc(net); 838 839 if (!ln) 840 return ERR_PTR(-ENOMEM); 841 ln->fn_bit = plen; 842 RCU_INIT_POINTER(ln->parent, pn); 843 844 if (dir) 845 rcu_assign_pointer(pn->right, ln); 846 else 847 rcu_assign_pointer(pn->left, ln); 848 849 return ln; 850 851 852insert_above: 853 /* 854 * split since we don't have a common prefix anymore or 855 * we have a less significant route. 856 * we've to insert an intermediate node on the list 857 * this new node will point to the one we need to create 858 * and the current 859 */ 860 861 pn = rcu_dereference_protected(fn->parent, 862 lockdep_is_held(&table->tb6_lock)); 863 864 /* find 1st bit in difference between the 2 addrs. 865 866 See comment in __ipv6_addr_diff: bit may be an invalid value, 867 but if it is >= plen, the value is ignored in any case. 868 */ 869 870 bit = __ipv6_addr_diff(addr, &key->addr, sizeof(*addr)); 871 872 /* 873 * (intermediate)[in] 874 * / \ 875 * (new leaf node)[ln] (old node)[fn] 876 */ 877 if (plen > bit) { 878 in = node_alloc(net); 879 ln = node_alloc(net); 880 881 if (!in || !ln) { 882 if (in) 883 node_free_immediate(net, in); 884 if (ln) 885 node_free_immediate(net, ln); 886 return ERR_PTR(-ENOMEM); 887 } 888 889 /* 890 * new intermediate node. 891 * RTN_RTINFO will 892 * be off since that an address that chooses one of 893 * the branches would not match less specific routes 894 * in the other branch 895 */ 896 897 in->fn_bit = bit; 898 899 RCU_INIT_POINTER(in->parent, pn); 900 in->leaf = fn->leaf; 901 fib6_info_hold(rcu_dereference_protected(in->leaf, 902 lockdep_is_held(&table->tb6_lock))); 903 904 /* update parent pointer */ 905 if (dir) 906 rcu_assign_pointer(pn->right, in); 907 else 908 rcu_assign_pointer(pn->left, in); 909 910 ln->fn_bit = plen; 911 912 RCU_INIT_POINTER(ln->parent, in); 913 rcu_assign_pointer(fn->parent, in); 914 915 if (addr_bit_set(addr, bit)) { 916 rcu_assign_pointer(in->right, ln); 917 rcu_assign_pointer(in->left, fn); 918 } else { 919 rcu_assign_pointer(in->left, ln); 920 rcu_assign_pointer(in->right, fn); 921 } 922 } else { /* plen <= bit */ 923 924 /* 925 * (new leaf node)[ln] 926 * / \ 927 * (old node)[fn] NULL 928 */ 929 930 ln = node_alloc(net); 931 932 if (!ln) 933 return ERR_PTR(-ENOMEM); 934 935 ln->fn_bit = plen; 936 937 RCU_INIT_POINTER(ln->parent, pn); 938 939 if (addr_bit_set(&key->addr, plen)) 940 RCU_INIT_POINTER(ln->right, fn); 941 else 942 RCU_INIT_POINTER(ln->left, fn); 943 944 rcu_assign_pointer(fn->parent, ln); 945 946 if (dir) 947 rcu_assign_pointer(pn->right, ln); 948 else 949 rcu_assign_pointer(pn->left, ln); 950 } 951 return ln; 952} 953 954static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, 955 const struct fib6_info *match, 956 const struct fib6_table *table) 957{ 958 int cpu; 959 960 if (!fib6_nh->rt6i_pcpu) 961 return; 962 963 rcu_read_lock(); 964 /* release the reference to this fib entry from 965 * all of its cached pcpu routes 966 */ 967 for_each_possible_cpu(cpu) { 968 struct rt6_info **ppcpu_rt; 969 struct rt6_info *pcpu_rt; 970 971 ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); 972 973 /* Paired with xchg() in rt6_get_pcpu_route() */ 974 pcpu_rt = READ_ONCE(*ppcpu_rt); 975 976 /* only dropping the 'from' reference if the cached route 977 * is using 'match'. The cached pcpu_rt->from only changes 978 * from a fib6_info to NULL (ip6_dst_destroy); it can never 979 * change from one fib6_info reference to another 980 */ 981 if (pcpu_rt && rcu_access_pointer(pcpu_rt->from) == match) { 982 struct fib6_info *from; 983 984 from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL); 985 fib6_info_release(from); 986 } 987 } 988 rcu_read_unlock(); 989} 990 991struct fib6_nh_pcpu_arg { 992 struct fib6_info *from; 993 const struct fib6_table *table; 994}; 995 996static int fib6_nh_drop_pcpu_from(struct fib6_nh *nh, void *_arg) 997{ 998 struct fib6_nh_pcpu_arg *arg = _arg; 999 1000 __fib6_drop_pcpu_from(nh, arg->from, arg->table); 1001 return 0; 1002} 1003 1004static void fib6_drop_pcpu_from(struct fib6_info *f6i, 1005 const struct fib6_table *table) 1006{ 1007 /* Make sure rt6_make_pcpu_route() wont add other percpu routes 1008 * while we are cleaning them here. 1009 */ 1010 f6i->fib6_destroying = 1; 1011 mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */ 1012 1013 if (f6i->nh) { 1014 struct fib6_nh_pcpu_arg arg = { 1015 .from = f6i, 1016 .table = table 1017 }; 1018 1019 nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from, 1020 &arg); 1021 } else { 1022 struct fib6_nh *fib6_nh; 1023 1024 fib6_nh = f6i->fib6_nh; 1025 __fib6_drop_pcpu_from(fib6_nh, f6i, table); 1026 } 1027} 1028 1029static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, 1030 struct net *net) 1031{ 1032 struct fib6_table *table = rt->fib6_table; 1033 1034 /* Flush all cached dst in exception table */ 1035 rt6_flush_exceptions(rt); 1036 fib6_drop_pcpu_from(rt, table); 1037 1038 if (rt->nh && !list_empty(&rt->nh_list)) 1039 list_del_init(&rt->nh_list); 1040 1041 if (refcount_read(&rt->fib6_ref) != 1) { 1042 /* This route is used as dummy address holder in some split 1043 * nodes. It is not leaked, but it still holds other resources, 1044 * which must be released in time. So, scan ascendant nodes 1045 * and replace dummy references to this route with references 1046 * to still alive ones. 1047 */ 1048 while (fn) { 1049 struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, 1050 lockdep_is_held(&table->tb6_lock)); 1051 struct fib6_info *new_leaf; 1052 if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) { 1053 new_leaf = fib6_find_prefix(net, table, fn); 1054 fib6_info_hold(new_leaf); 1055 1056 rcu_assign_pointer(fn->leaf, new_leaf); 1057 fib6_info_release(rt); 1058 } 1059 fn = rcu_dereference_protected(fn->parent, 1060 lockdep_is_held(&table->tb6_lock)); 1061 } 1062 } 1063} 1064 1065/* 1066 * Insert routing information in a node. 1067 */ 1068 1069static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, 1070 struct nl_info *info, 1071 struct netlink_ext_ack *extack) 1072{ 1073 struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, 1074 lockdep_is_held(&rt->fib6_table->tb6_lock)); 1075 struct fib6_info *iter = NULL; 1076 struct fib6_info __rcu **ins; 1077 struct fib6_info __rcu **fallback_ins = NULL; 1078 int replace = (info->nlh && 1079 (info->nlh->nlmsg_flags & NLM_F_REPLACE)); 1080 int add = (!info->nlh || 1081 (info->nlh->nlmsg_flags & NLM_F_CREATE)); 1082 int found = 0; 1083 bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); 1084 bool notify_sibling_rt = false; 1085 u16 nlflags = NLM_F_EXCL; 1086 int err; 1087 1088 if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND)) 1089 nlflags |= NLM_F_APPEND; 1090 1091 ins = &fn->leaf; 1092 1093 for (iter = leaf; iter; 1094 iter = rcu_dereference_protected(iter->fib6_next, 1095 lockdep_is_held(&rt->fib6_table->tb6_lock))) { 1096 /* 1097 * Search for duplicates 1098 */ 1099 1100 if (iter->fib6_metric == rt->fib6_metric) { 1101 /* 1102 * Same priority level 1103 */ 1104 if (info->nlh && 1105 (info->nlh->nlmsg_flags & NLM_F_EXCL)) 1106 return -EEXIST; 1107 1108 nlflags &= ~NLM_F_EXCL; 1109 if (replace) { 1110 if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { 1111 found++; 1112 break; 1113 } 1114 fallback_ins = fallback_ins ?: ins; 1115 goto next_iter; 1116 } 1117 1118 if (rt6_duplicate_nexthop(iter, rt)) { 1119 if (rt->fib6_nsiblings) 1120 rt->fib6_nsiblings = 0; 1121 if (!(iter->fib6_flags & RTF_EXPIRES)) 1122 return -EEXIST; 1123 if (!(rt->fib6_flags & RTF_EXPIRES)) 1124 fib6_clean_expires(iter); 1125 else 1126 fib6_set_expires(iter, rt->expires); 1127 1128 if (rt->fib6_pmtu) 1129 fib6_metric_set(iter, RTAX_MTU, 1130 rt->fib6_pmtu); 1131 return -EEXIST; 1132 } 1133 /* If we have the same destination and the same metric, 1134 * but not the same gateway, then the route we try to 1135 * add is sibling to this route, increment our counter 1136 * of siblings, and later we will add our route to the 1137 * list. 1138 * Only static routes (which don't have flag 1139 * RTF_EXPIRES) are used for ECMPv6. 1140 * 1141 * To avoid long list, we only had siblings if the 1142 * route have a gateway. 1143 */ 1144 if (rt_can_ecmp && 1145 rt6_qualify_for_ecmp(iter)) 1146 rt->fib6_nsiblings++; 1147 } 1148 1149 if (iter->fib6_metric > rt->fib6_metric) 1150 break; 1151 1152next_iter: 1153 ins = &iter->fib6_next; 1154 } 1155 1156 if (fallback_ins && !found) { 1157 /* No matching route with same ecmp-able-ness found, replace 1158 * first matching route 1159 */ 1160 ins = fallback_ins; 1161 iter = rcu_dereference_protected(*ins, 1162 lockdep_is_held(&rt->fib6_table->tb6_lock)); 1163 found++; 1164 } 1165 1166 /* Reset round-robin state, if necessary */ 1167 if (ins == &fn->leaf) 1168 fn->rr_ptr = NULL; 1169 1170 /* Link this route to others same route. */ 1171 if (rt->fib6_nsiblings) { 1172 unsigned int fib6_nsiblings; 1173 struct fib6_info *sibling, *temp_sibling; 1174 1175 /* Find the first route that have the same metric */ 1176 sibling = leaf; 1177 notify_sibling_rt = true; 1178 while (sibling) { 1179 if (sibling->fib6_metric == rt->fib6_metric && 1180 rt6_qualify_for_ecmp(sibling)) { 1181 list_add_tail(&rt->fib6_siblings, 1182 &sibling->fib6_siblings); 1183 break; 1184 } 1185 sibling = rcu_dereference_protected(sibling->fib6_next, 1186 lockdep_is_held(&rt->fib6_table->tb6_lock)); 1187 notify_sibling_rt = false; 1188 } 1189 /* For each sibling in the list, increment the counter of 1190 * siblings. BUG() if counters does not match, list of siblings 1191 * is broken! 1192 */ 1193 fib6_nsiblings = 0; 1194 list_for_each_entry_safe(sibling, temp_sibling, 1195 &rt->fib6_siblings, fib6_siblings) { 1196 sibling->fib6_nsiblings++; 1197 BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings); 1198 fib6_nsiblings++; 1199 } 1200 BUG_ON(fib6_nsiblings != rt->fib6_nsiblings); 1201 rt6_multipath_rebalance(temp_sibling); 1202 } 1203 1204 /* 1205 * insert node 1206 */ 1207 if (!replace) { 1208 if (!add) 1209 pr_warn("NLM_F_CREATE should be set when creating new route\n"); 1210 1211add: 1212 nlflags |= NLM_F_CREATE; 1213 1214 /* The route should only be notified if it is the first 1215 * route in the node or if it is added as a sibling 1216 * route to the first route in the node. 1217 */ 1218 if (!info->skip_notify_kernel && 1219 (notify_sibling_rt || ins == &fn->leaf)) { 1220 enum fib_event_type fib_event; 1221 1222 if (notify_sibling_rt) 1223 fib_event = FIB_EVENT_ENTRY_APPEND; 1224 else 1225 fib_event = FIB_EVENT_ENTRY_REPLACE; 1226 err = call_fib6_entry_notifiers(info->nl_net, 1227 fib_event, rt, 1228 extack); 1229 if (err) { 1230 struct fib6_info *sibling, *next_sibling; 1231 1232 /* If the route has siblings, then it first 1233 * needs to be unlinked from them. 1234 */ 1235 if (!rt->fib6_nsiblings) 1236 return err; 1237 1238 list_for_each_entry_safe(sibling, next_sibling, 1239 &rt->fib6_siblings, 1240 fib6_siblings) 1241 sibling->fib6_nsiblings--; 1242 rt->fib6_nsiblings = 0; 1243 list_del_init(&rt->fib6_siblings); 1244 rt6_multipath_rebalance(next_sibling); 1245 return err; 1246 } 1247 } 1248 1249 rcu_assign_pointer(rt->fib6_next, iter); 1250 fib6_info_hold(rt); 1251 rcu_assign_pointer(rt->fib6_node, fn); 1252 rcu_assign_pointer(*ins, rt); 1253 if (!info->skip_notify) 1254 inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); 1255 info->nl_net->ipv6.rt6_stats->fib_rt_entries++; 1256 1257 if (!(fn->fn_flags & RTN_RTINFO)) { 1258 info->nl_net->ipv6.rt6_stats->fib_route_nodes++; 1259 fn->fn_flags |= RTN_RTINFO; 1260 } 1261 1262 } else { 1263 int nsiblings; 1264 1265 if (!found) { 1266 if (add) 1267 goto add; 1268 pr_warn("NLM_F_REPLACE set, but no existing node found!\n"); 1269 return -ENOENT; 1270 } 1271 1272 if (!info->skip_notify_kernel && ins == &fn->leaf) { 1273 err = call_fib6_entry_notifiers(info->nl_net, 1274 FIB_EVENT_ENTRY_REPLACE, 1275 rt, extack); 1276 if (err) 1277 return err; 1278 } 1279 1280 fib6_info_hold(rt); 1281 rcu_assign_pointer(rt->fib6_node, fn); 1282 rt->fib6_next = iter->fib6_next; 1283 rcu_assign_pointer(*ins, rt); 1284 if (!info->skip_notify) 1285 inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); 1286 if (!(fn->fn_flags & RTN_RTINFO)) { 1287 info->nl_net->ipv6.rt6_stats->fib_route_nodes++; 1288 fn->fn_flags |= RTN_RTINFO; 1289 } 1290 nsiblings = iter->fib6_nsiblings; 1291 iter->fib6_node = NULL; 1292 fib6_purge_rt(iter, fn, info->nl_net); 1293 if (rcu_access_pointer(fn->rr_ptr) == iter) 1294 fn->rr_ptr = NULL; 1295 fib6_info_release(iter); 1296 1297 if (nsiblings) { 1298 /* Replacing an ECMP route, remove all siblings */ 1299 ins = &rt->fib6_next; 1300 iter = rcu_dereference_protected(*ins, 1301 lockdep_is_held(&rt->fib6_table->tb6_lock)); 1302 while (iter) { 1303 if (iter->fib6_metric > rt->fib6_metric) 1304 break; 1305 if (rt6_qualify_for_ecmp(iter)) { 1306 *ins = iter->fib6_next; 1307 iter->fib6_node = NULL; 1308 fib6_purge_rt(iter, fn, info->nl_net); 1309 if (rcu_access_pointer(fn->rr_ptr) == iter) 1310 fn->rr_ptr = NULL; 1311 fib6_info_release(iter); 1312 nsiblings--; 1313 info->nl_net->ipv6.rt6_stats->fib_rt_entries--; 1314 } else { 1315 ins = &iter->fib6_next; 1316 } 1317 iter = rcu_dereference_protected(*ins, 1318 lockdep_is_held(&rt->fib6_table->tb6_lock)); 1319 } 1320 WARN_ON(nsiblings != 0); 1321 } 1322 } 1323 1324 return 0; 1325} 1326 1327static void fib6_start_gc(struct net *net, struct fib6_info *rt) 1328{ 1329 if (!timer_pending(&net->ipv6.ip6_fib_timer) && 1330 (rt->fib6_flags & RTF_EXPIRES)) 1331 mod_timer(&net->ipv6.ip6_fib_timer, 1332 jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); 1333} 1334 1335void fib6_force_start_gc(struct net *net) 1336{ 1337 if (!timer_pending(&net->ipv6.ip6_fib_timer)) 1338 mod_timer(&net->ipv6.ip6_fib_timer, 1339 jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); 1340} 1341 1342static void __fib6_update_sernum_upto_root(struct fib6_info *rt, 1343 int sernum) 1344{ 1345 struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, 1346 lockdep_is_held(&rt->fib6_table->tb6_lock)); 1347 1348 /* paired with smp_rmb() in rt6_get_cookie_safe() */ 1349 smp_wmb(); 1350 while (fn) { 1351 WRITE_ONCE(fn->fn_sernum, sernum); 1352 fn = rcu_dereference_protected(fn->parent, 1353 lockdep_is_held(&rt->fib6_table->tb6_lock)); 1354 } 1355} 1356 1357void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt) 1358{ 1359 __fib6_update_sernum_upto_root(rt, fib6_new_sernum(net)); 1360} 1361 1362/* allow ipv4 to update sernum via ipv6_stub */ 1363void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i) 1364{ 1365 spin_lock_bh(&f6i->fib6_table->tb6_lock); 1366 fib6_update_sernum_upto_root(net, f6i); 1367 spin_unlock_bh(&f6i->fib6_table->tb6_lock); 1368} 1369 1370/* 1371 * Add routing information to the routing tree. 1372 * <destination addr>/<source addr> 1373 * with source addr info in sub-trees 1374 * Need to own table->tb6_lock 1375 */ 1376 1377int fib6_add(struct fib6_node *root, struct fib6_info *rt, 1378 struct nl_info *info, struct netlink_ext_ack *extack) 1379{ 1380 struct fib6_table *table = rt->fib6_table; 1381 struct fib6_node *fn, *pn = NULL; 1382 int err = -ENOMEM; 1383 int allow_create = 1; 1384 int replace_required = 0; 1385 1386 if (info->nlh) { 1387 if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) 1388 allow_create = 0; 1389 if (info->nlh->nlmsg_flags & NLM_F_REPLACE) 1390 replace_required = 1; 1391 } 1392 if (!allow_create && !replace_required) 1393 pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); 1394 1395 fn = fib6_add_1(info->nl_net, table, root, 1396 &rt->fib6_dst.addr, rt->fib6_dst.plen, 1397 offsetof(struct fib6_info, fib6_dst), allow_create, 1398 replace_required, extack); 1399 if (IS_ERR(fn)) { 1400 err = PTR_ERR(fn); 1401 fn = NULL; 1402 goto out; 1403 } 1404 1405 pn = fn; 1406 1407#ifdef CONFIG_IPV6_SUBTREES 1408 if (rt->fib6_src.plen) { 1409 struct fib6_node *sn; 1410 1411 if (!rcu_access_pointer(fn->subtree)) { 1412 struct fib6_node *sfn; 1413 1414 /* 1415 * Create subtree. 1416 * 1417 * fn[main tree] 1418 * | 1419 * sfn[subtree root] 1420 * \ 1421 * sn[new leaf node] 1422 */ 1423 1424 /* Create subtree root node */ 1425 sfn = node_alloc(info->nl_net); 1426 if (!sfn) 1427 goto failure; 1428 1429 fib6_info_hold(info->nl_net->ipv6.fib6_null_entry); 1430 rcu_assign_pointer(sfn->leaf, 1431 info->nl_net->ipv6.fib6_null_entry); 1432 sfn->fn_flags = RTN_ROOT; 1433 1434 /* Now add the first leaf node to new subtree */ 1435 1436 sn = fib6_add_1(info->nl_net, table, sfn, 1437 &rt->fib6_src.addr, rt->fib6_src.plen, 1438 offsetof(struct fib6_info, fib6_src), 1439 allow_create, replace_required, extack); 1440 1441 if (IS_ERR(sn)) { 1442 /* If it is failed, discard just allocated 1443 root, and then (in failure) stale node 1444 in main tree. 1445 */ 1446 node_free_immediate(info->nl_net, sfn); 1447 err = PTR_ERR(sn); 1448 goto failure; 1449 } 1450 1451 /* Now link new subtree to main tree */ 1452 rcu_assign_pointer(sfn->parent, fn); 1453 rcu_assign_pointer(fn->subtree, sfn); 1454 } else { 1455 sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn), 1456 &rt->fib6_src.addr, rt->fib6_src.plen, 1457 offsetof(struct fib6_info, fib6_src), 1458 allow_create, replace_required, extack); 1459 1460 if (IS_ERR(sn)) { 1461 err = PTR_ERR(sn); 1462 goto failure; 1463 } 1464 } 1465 1466 if (!rcu_access_pointer(fn->leaf)) { 1467 if (fn->fn_flags & RTN_TL_ROOT) { 1468 /* put back null_entry for root node */ 1469 rcu_assign_pointer(fn->leaf, 1470 info->nl_net->ipv6.fib6_null_entry); 1471 } else { 1472 fib6_info_hold(rt); 1473 rcu_assign_pointer(fn->leaf, rt); 1474 } 1475 } 1476 fn = sn; 1477 } 1478#endif 1479 1480 err = fib6_add_rt2node(fn, rt, info, extack); 1481 if (!err) { 1482 if (rt->nh) 1483 list_add(&rt->nh_list, &rt->nh->f6i_list); 1484 __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); 1485 fib6_start_gc(info->nl_net, rt); 1486 } 1487 1488out: 1489 if (err) { 1490#ifdef CONFIG_IPV6_SUBTREES 1491 /* 1492 * If fib6_add_1 has cleared the old leaf pointer in the 1493 * super-tree leaf node we have to find a new one for it. 1494 */ 1495 if (pn != fn) { 1496 struct fib6_info *pn_leaf = 1497 rcu_dereference_protected(pn->leaf, 1498 lockdep_is_held(&table->tb6_lock)); 1499 if (pn_leaf == rt) { 1500 pn_leaf = NULL; 1501 RCU_INIT_POINTER(pn->leaf, NULL); 1502 fib6_info_release(rt); 1503 } 1504 if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { 1505 pn_leaf = fib6_find_prefix(info->nl_net, table, 1506 pn); 1507 if (!pn_leaf) 1508 pn_leaf = 1509 info->nl_net->ipv6.fib6_null_entry; 1510 fib6_info_hold(pn_leaf); 1511 rcu_assign_pointer(pn->leaf, pn_leaf); 1512 } 1513 } 1514#endif 1515 goto failure; 1516 } else if (fib6_requires_src(rt)) { 1517 fib6_routes_require_src_inc(info->nl_net); 1518 } 1519 return err; 1520 1521failure: 1522 /* fn->leaf could be NULL and fib6_repair_tree() needs to be called if: 1523 * 1. fn is an intermediate node and we failed to add the new 1524 * route to it in both subtree creation failure and fib6_add_rt2node() 1525 * failure case. 1526 * 2. fn is the root node in the table and we fail to add the first 1527 * default route to it. 1528 */ 1529 if (fn && 1530 (!(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)) || 1531 (fn->fn_flags & RTN_TL_ROOT && 1532 !rcu_access_pointer(fn->leaf)))) 1533 fib6_repair_tree(info->nl_net, table, fn); 1534 return err; 1535} 1536 1537/* 1538 * Routing tree lookup 1539 * 1540 */ 1541 1542struct lookup_args { 1543 int offset; /* key offset on fib6_info */ 1544 const struct in6_addr *addr; /* search key */ 1545}; 1546 1547static struct fib6_node *fib6_node_lookup_1(struct fib6_node *root, 1548 struct lookup_args *args) 1549{ 1550 struct fib6_node *fn; 1551 __be32 dir; 1552 1553 if (unlikely(args->offset == 0)) 1554 return NULL; 1555 1556 /* 1557 * Descend on a tree 1558 */ 1559 1560 fn = root; 1561 1562 for (;;) { 1563 struct fib6_node *next; 1564 1565 dir = addr_bit_set(args->addr, fn->fn_bit); 1566 1567 next = dir ? rcu_dereference(fn->right) : 1568 rcu_dereference(fn->left); 1569 1570 if (next) { 1571 fn = next; 1572 continue; 1573 } 1574 break; 1575 } 1576 1577 while (fn) { 1578 struct fib6_node *subtree = FIB6_SUBTREE(fn); 1579 1580 if (subtree || fn->fn_flags & RTN_RTINFO) { 1581 struct fib6_info *leaf = rcu_dereference(fn->leaf); 1582 struct rt6key *key; 1583 1584 if (!leaf) 1585 goto backtrack; 1586 1587 key = (struct rt6key *) ((u8 *)leaf + args->offset); 1588 1589 if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { 1590#ifdef CONFIG_IPV6_SUBTREES 1591 if (subtree) { 1592 struct fib6_node *sfn; 1593 sfn = fib6_node_lookup_1(subtree, 1594 args + 1); 1595 if (!sfn) 1596 goto backtrack; 1597 fn = sfn; 1598 } 1599#endif 1600 if (fn->fn_flags & RTN_RTINFO) 1601 return fn; 1602 } 1603 } 1604backtrack: 1605 if (fn->fn_flags & RTN_ROOT) 1606 break; 1607 1608 fn = rcu_dereference(fn->parent); 1609 } 1610 1611 return NULL; 1612} 1613 1614/* called with rcu_read_lock() held 1615 */ 1616struct fib6_node *fib6_node_lookup(struct fib6_node *root, 1617 const struct in6_addr *daddr, 1618 const struct in6_addr *saddr) 1619{ 1620 struct fib6_node *fn; 1621 struct lookup_args args[] = { 1622 { 1623 .offset = offsetof(struct fib6_info, fib6_dst), 1624 .addr = daddr, 1625 }, 1626#ifdef CONFIG_IPV6_SUBTREES 1627 { 1628 .offset = offsetof(struct fib6_info, fib6_src), 1629 .addr = saddr, 1630 }, 1631#endif 1632 { 1633 .offset = 0, /* sentinel */ 1634 } 1635 }; 1636 1637 fn = fib6_node_lookup_1(root, daddr ? args : args + 1); 1638 if (!fn || fn->fn_flags & RTN_TL_ROOT) 1639 fn = root; 1640 1641 return fn; 1642} 1643 1644/* 1645 * Get node with specified destination prefix (and source prefix, 1646 * if subtrees are used) 1647 * exact_match == true means we try to find fn with exact match of 1648 * the passed in prefix addr 1649 * exact_match == false means we try to find fn with longest prefix 1650 * match of the passed in prefix addr. This is useful for finding fn 1651 * for cached route as it will be stored in the exception table under 1652 * the node with longest prefix length. 1653 */ 1654 1655 1656static struct fib6_node *fib6_locate_1(struct fib6_node *root, 1657 const struct in6_addr *addr, 1658 int plen, int offset, 1659 bool exact_match) 1660{ 1661 struct fib6_node *fn, *prev = NULL; 1662 1663 for (fn = root; fn ; ) { 1664 struct fib6_info *leaf = rcu_dereference(fn->leaf); 1665 struct rt6key *key; 1666 1667 /* This node is being deleted */ 1668 if (!leaf) { 1669 if (plen <= fn->fn_bit) 1670 goto out; 1671 else 1672 goto next; 1673 } 1674 1675 key = (struct rt6key *)((u8 *)leaf + offset); 1676 1677 /* 1678 * Prefix match 1679 */ 1680 if (plen < fn->fn_bit || 1681 !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) 1682 goto out; 1683 1684 if (plen == fn->fn_bit) 1685 return fn; 1686 1687 if (fn->fn_flags & RTN_RTINFO) 1688 prev = fn; 1689 1690next: 1691 /* 1692 * We have more bits to go 1693 */ 1694 if (addr_bit_set(addr, fn->fn_bit)) 1695 fn = rcu_dereference(fn->right); 1696 else 1697 fn = rcu_dereference(fn->left); 1698 } 1699out: 1700 if (exact_match) 1701 return NULL; 1702 else 1703 return prev; 1704} 1705 1706struct fib6_node *fib6_locate(struct fib6_node *root, 1707 const struct in6_addr *daddr, int dst_len, 1708 const struct in6_addr *saddr, int src_len, 1709 bool exact_match) 1710{ 1711 struct fib6_node *fn; 1712 1713 fn = fib6_locate_1(root, daddr, dst_len, 1714 offsetof(struct fib6_info, fib6_dst), 1715 exact_match); 1716 1717#ifdef CONFIG_IPV6_SUBTREES 1718 if (src_len) { 1719 WARN_ON(saddr == NULL); 1720 if (fn) { 1721 struct fib6_node *subtree = FIB6_SUBTREE(fn); 1722 1723 if (subtree) { 1724 fn = fib6_locate_1(subtree, saddr, src_len, 1725 offsetof(struct fib6_info, fib6_src), 1726 exact_match); 1727 } 1728 } 1729 } 1730#endif 1731 1732 if (fn && fn->fn_flags & RTN_RTINFO) 1733 return fn; 1734 1735 return NULL; 1736} 1737 1738 1739/* 1740 * Deletion 1741 * 1742 */ 1743 1744static struct fib6_info *fib6_find_prefix(struct net *net, 1745 struct fib6_table *table, 1746 struct fib6_node *fn) 1747{ 1748 struct fib6_node *child_left, *child_right; 1749 1750 if (fn->fn_flags & RTN_ROOT) 1751 return net->ipv6.fib6_null_entry; 1752 1753 while (fn) { 1754 child_left = rcu_dereference_protected(fn->left, 1755 lockdep_is_held(&table->tb6_lock)); 1756 child_right = rcu_dereference_protected(fn->right, 1757 lockdep_is_held(&table->tb6_lock)); 1758 if (child_left) 1759 return rcu_dereference_protected(child_left->leaf, 1760 lockdep_is_held(&table->tb6_lock)); 1761 if (child_right) 1762 return rcu_dereference_protected(child_right->leaf, 1763 lockdep_is_held(&table->tb6_lock)); 1764 1765 fn = FIB6_SUBTREE(fn); 1766 } 1767 return NULL; 1768} 1769 1770/* 1771 * Called to trim the tree of intermediate nodes when possible. "fn" 1772 * is the node we want to try and remove. 1773 * Need to own table->tb6_lock 1774 */ 1775 1776static struct fib6_node *fib6_repair_tree(struct net *net, 1777 struct fib6_table *table, 1778 struct fib6_node *fn) 1779{ 1780 int children; 1781 int nstate; 1782 struct fib6_node *child; 1783 struct fib6_walker *w; 1784 int iter = 0; 1785 1786 /* Set fn->leaf to null_entry for root node. */ 1787 if (fn->fn_flags & RTN_TL_ROOT) { 1788 rcu_assign_pointer(fn->leaf, net->ipv6.fib6_null_entry); 1789 return fn; 1790 } 1791 1792 for (;;) { 1793 struct fib6_node *fn_r = rcu_dereference_protected(fn->right, 1794 lockdep_is_held(&table->tb6_lock)); 1795 struct fib6_node *fn_l = rcu_dereference_protected(fn->left, 1796 lockdep_is_held(&table->tb6_lock)); 1797 struct fib6_node *pn = rcu_dereference_protected(fn->parent, 1798 lockdep_is_held(&table->tb6_lock)); 1799 struct fib6_node *pn_r = rcu_dereference_protected(pn->right, 1800 lockdep_is_held(&table->tb6_lock)); 1801 struct fib6_node *pn_l = rcu_dereference_protected(pn->left, 1802 lockdep_is_held(&table->tb6_lock)); 1803 struct fib6_info *fn_leaf = rcu_dereference_protected(fn->leaf, 1804 lockdep_is_held(&table->tb6_lock)); 1805 struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, 1806 lockdep_is_held(&table->tb6_lock)); 1807 struct fib6_info *new_fn_leaf; 1808 1809 RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); 1810 iter++; 1811 1812 WARN_ON(fn->fn_flags & RTN_RTINFO); 1813 WARN_ON(fn->fn_flags & RTN_TL_ROOT); 1814 WARN_ON(fn_leaf); 1815 1816 children = 0; 1817 child = NULL; 1818 if (fn_r) { 1819 child = fn_r; 1820 children |= 1; 1821 } 1822 if (fn_l) { 1823 child = fn_l; 1824 children |= 2; 1825 } 1826 1827 if (children == 3 || FIB6_SUBTREE(fn) 1828#ifdef CONFIG_IPV6_SUBTREES 1829 /* Subtree root (i.e. fn) may have one child */ 1830 || (children && fn->fn_flags & RTN_ROOT) 1831#endif 1832 ) { 1833 new_fn_leaf = fib6_find_prefix(net, table, fn); 1834#if RT6_DEBUG >= 2 1835 if (!new_fn_leaf) { 1836 WARN_ON(!new_fn_leaf); 1837 new_fn_leaf = net->ipv6.fib6_null_entry; 1838 } 1839#endif 1840 fib6_info_hold(new_fn_leaf); 1841 rcu_assign_pointer(fn->leaf, new_fn_leaf); 1842 return pn; 1843 } 1844 1845#ifdef CONFIG_IPV6_SUBTREES 1846 if (FIB6_SUBTREE(pn) == fn) { 1847 WARN_ON(!(fn->fn_flags & RTN_ROOT)); 1848 RCU_INIT_POINTER(pn->subtree, NULL); 1849 nstate = FWS_L; 1850 } else { 1851 WARN_ON(fn->fn_flags & RTN_ROOT); 1852#endif 1853 if (pn_r == fn) 1854 rcu_assign_pointer(pn->right, child); 1855 else if (pn_l == fn) 1856 rcu_assign_pointer(pn->left, child); 1857#if RT6_DEBUG >= 2 1858 else 1859 WARN_ON(1); 1860#endif 1861 if (child) 1862 rcu_assign_pointer(child->parent, pn); 1863 nstate = FWS_R; 1864#ifdef CONFIG_IPV6_SUBTREES 1865 } 1866#endif 1867 1868 read_lock(&net->ipv6.fib6_walker_lock); 1869 FOR_WALKERS(net, w) { 1870 if (!child) { 1871 if (w->node == fn) { 1872 RT6_TRACE("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate); 1873 w->node = pn; 1874 w->state = nstate; 1875 } 1876 } else { 1877 if (w->node == fn) { 1878 w->node = child; 1879 if (children&2) { 1880 RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); 1881 w->state = w->state >= FWS_R ? FWS_U : FWS_INIT; 1882 } else { 1883 RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); 1884 w->state = w->state >= FWS_C ? FWS_U : FWS_INIT; 1885 } 1886 } 1887 } 1888 } 1889 read_unlock(&net->ipv6.fib6_walker_lock); 1890 1891 node_free(net, fn); 1892 if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) 1893 return pn; 1894 1895 RCU_INIT_POINTER(pn->leaf, NULL); 1896 fib6_info_release(pn_leaf); 1897 fn = pn; 1898 } 1899} 1900 1901static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, 1902 struct fib6_info __rcu **rtp, struct nl_info *info) 1903{ 1904 struct fib6_info *leaf, *replace_rt = NULL; 1905 struct fib6_walker *w; 1906 struct fib6_info *rt = rcu_dereference_protected(*rtp, 1907 lockdep_is_held(&table->tb6_lock)); 1908 struct net *net = info->nl_net; 1909 bool notify_del = false; 1910 1911 RT6_TRACE("fib6_del_route\n"); 1912 1913 /* If the deleted route is the first in the node and it is not part of 1914 * a multipath route, then we need to replace it with the next route 1915 * in the node, if exists. 1916 */ 1917 leaf = rcu_dereference_protected(fn->leaf, 1918 lockdep_is_held(&table->tb6_lock)); 1919 if (leaf == rt && !rt->fib6_nsiblings) { 1920 if (rcu_access_pointer(rt->fib6_next)) 1921 replace_rt = rcu_dereference_protected(rt->fib6_next, 1922 lockdep_is_held(&table->tb6_lock)); 1923 else 1924 notify_del = true; 1925 } 1926 1927 /* Unlink it */ 1928 *rtp = rt->fib6_next; 1929 rt->fib6_node = NULL; 1930 net->ipv6.rt6_stats->fib_rt_entries--; 1931 net->ipv6.rt6_stats->fib_discarded_routes++; 1932 1933 /* Reset round-robin state, if necessary */ 1934 if (rcu_access_pointer(fn->rr_ptr) == rt) 1935 fn->rr_ptr = NULL; 1936 1937 /* Remove this entry from other siblings */ 1938 if (rt->fib6_nsiblings) { 1939 struct fib6_info *sibling, *next_sibling; 1940 1941 /* The route is deleted from a multipath route. If this 1942 * multipath route is the first route in the node, then we need 1943 * to emit a delete notification. Otherwise, we need to skip 1944 * the notification. 1945 */ 1946 if (rt->fib6_metric == leaf->fib6_metric && 1947 rt6_qualify_for_ecmp(leaf)) 1948 notify_del = true; 1949 list_for_each_entry_safe(sibling, next_sibling, 1950 &rt->fib6_siblings, fib6_siblings) 1951 sibling->fib6_nsiblings--; 1952 rt->fib6_nsiblings = 0; 1953 list_del_init(&rt->fib6_siblings); 1954 rt6_multipath_rebalance(next_sibling); 1955 } 1956 1957 /* Adjust walkers */ 1958 read_lock(&net->ipv6.fib6_walker_lock); 1959 FOR_WALKERS(net, w) { 1960 if (w->state == FWS_C && w->leaf == rt) { 1961 RT6_TRACE("walker %p adjusted by delroute\n", w); 1962 w->leaf = rcu_dereference_protected(rt->fib6_next, 1963 lockdep_is_held(&table->tb6_lock)); 1964 if (!w->leaf) 1965 w->state = FWS_U; 1966 } 1967 } 1968 read_unlock(&net->ipv6.fib6_walker_lock); 1969 1970 /* If it was last route, call fib6_repair_tree() to: 1971 * 1. For root node, put back null_entry as how the table was created. 1972 * 2. For other nodes, expunge its radix tree node. 1973 */ 1974 if (!rcu_access_pointer(fn->leaf)) { 1975 if (!(fn->fn_flags & RTN_TL_ROOT)) { 1976 fn->fn_flags &= ~RTN_RTINFO; 1977 net->ipv6.rt6_stats->fib_route_nodes--; 1978 } 1979 fn = fib6_repair_tree(net, table, fn); 1980 } 1981 1982 fib6_purge_rt(rt, fn, net); 1983 1984 if (!info->skip_notify_kernel) { 1985 if (notify_del) 1986 call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, 1987 rt, NULL); 1988 else if (replace_rt) 1989 call_fib6_entry_notifiers_replace(net, replace_rt); 1990 } 1991 if (!info->skip_notify) 1992 inet6_rt_notify(RTM_DELROUTE, rt, info, 0); 1993 1994 fib6_info_release(rt); 1995} 1996 1997/* Need to own table->tb6_lock */ 1998int fib6_del(struct fib6_info *rt, struct nl_info *info) 1999{ 2000 struct net *net = info->nl_net; 2001 struct fib6_info __rcu **rtp; 2002 struct fib6_info __rcu **rtp_next; 2003 struct fib6_table *table; 2004 struct fib6_node *fn; 2005 2006 if (rt == net->ipv6.fib6_null_entry) 2007 return -ENOENT; 2008 2009 table = rt->fib6_table; 2010 fn = rcu_dereference_protected(rt->fib6_node, 2011 lockdep_is_held(&table->tb6_lock)); 2012 if (!fn) 2013 return -ENOENT; 2014 2015 WARN_ON(!(fn->fn_flags & RTN_RTINFO)); 2016 2017 /* 2018 * Walk the leaf entries looking for ourself 2019 */ 2020 2021 for (rtp = &fn->leaf; *rtp; rtp = rtp_next) { 2022 struct fib6_info *cur = rcu_dereference_protected(*rtp, 2023 lockdep_is_held(&table->tb6_lock)); 2024 if (rt == cur) { 2025 if (fib6_requires_src(cur)) 2026 fib6_routes_require_src_dec(info->nl_net); 2027 fib6_del_route(table, fn, rtp, info); 2028 return 0; 2029 } 2030 rtp_next = &cur->fib6_next; 2031 } 2032 return -ENOENT; 2033} 2034 2035/* 2036 * Tree traversal function. 2037 * 2038 * Certainly, it is not interrupt safe. 2039 * However, it is internally reenterable wrt itself and fib6_add/fib6_del. 2040 * It means, that we can modify tree during walking 2041 * and use this function for garbage collection, clone pruning, 2042 * cleaning tree when a device goes down etc. etc. 2043 * 2044 * It guarantees that every node will be traversed, 2045 * and that it will be traversed only once. 2046 * 2047 * Callback function w->func may return: 2048 * 0 -> continue walking. 2049 * positive value -> walking is suspended (used by tree dumps, 2050 * and probably by gc, if it will be split to several slices) 2051 * negative value -> terminate walking. 2052 * 2053 * The function itself returns: 2054 * 0 -> walk is complete. 2055 * >0 -> walk is incomplete (i.e. suspended) 2056 * <0 -> walk is terminated by an error. 2057 * 2058 * This function is called with tb6_lock held. 2059 */ 2060 2061static int fib6_walk_continue(struct fib6_walker *w) 2062{ 2063 struct fib6_node *fn, *pn, *left, *right; 2064 2065 /* w->root should always be table->tb6_root */ 2066 WARN_ON_ONCE(!(w->root->fn_flags & RTN_TL_ROOT)); 2067 2068 for (;;) { 2069 fn = w->node; 2070 if (!fn) 2071 return 0; 2072 2073 switch (w->state) { 2074#ifdef CONFIG_IPV6_SUBTREES 2075 case FWS_S: 2076 if (FIB6_SUBTREE(fn)) { 2077 w->node = FIB6_SUBTREE(fn); 2078 continue; 2079 } 2080 w->state = FWS_L; 2081 fallthrough; 2082#endif 2083 case FWS_L: 2084 left = rcu_dereference_protected(fn->left, 1); 2085 if (left) { 2086 w->node = left; 2087 w->state = FWS_INIT; 2088 continue; 2089 } 2090 w->state = FWS_R; 2091 fallthrough; 2092 case FWS_R: 2093 right = rcu_dereference_protected(fn->right, 1); 2094 if (right) { 2095 w->node = right; 2096 w->state = FWS_INIT; 2097 continue; 2098 } 2099 w->state = FWS_C; 2100 w->leaf = rcu_dereference_protected(fn->leaf, 1); 2101 fallthrough; 2102 case FWS_C: 2103 if (w->leaf && fn->fn_flags & RTN_RTINFO) { 2104 int err; 2105 2106 if (w->skip) { 2107 w->skip--; 2108 goto skip; 2109 } 2110 2111 err = w->func(w); 2112 if (err) 2113 return err; 2114 2115 w->count++; 2116 continue; 2117 } 2118skip: 2119 w->state = FWS_U; 2120 fallthrough; 2121 case FWS_U: 2122 if (fn == w->root) 2123 return 0; 2124 pn = rcu_dereference_protected(fn->parent, 1); 2125 left = rcu_dereference_protected(pn->left, 1); 2126 right = rcu_dereference_protected(pn->right, 1); 2127 w->node = pn; 2128#ifdef CONFIG_IPV6_SUBTREES 2129 if (FIB6_SUBTREE(pn) == fn) { 2130 WARN_ON(!(fn->fn_flags & RTN_ROOT)); 2131 w->state = FWS_L; 2132 continue; 2133 } 2134#endif 2135 if (left == fn) { 2136 w->state = FWS_R; 2137 continue; 2138 } 2139 if (right == fn) { 2140 w->state = FWS_C; 2141 w->leaf = rcu_dereference_protected(w->node->leaf, 1); 2142 continue; 2143 } 2144#if RT6_DEBUG >= 2 2145 WARN_ON(1); 2146#endif 2147 } 2148 } 2149} 2150 2151static int fib6_walk(struct net *net, struct fib6_walker *w) 2152{ 2153 int res; 2154 2155 w->state = FWS_INIT; 2156 w->node = w->root; 2157 2158 fib6_walker_link(net, w); 2159 res = fib6_walk_continue(w); 2160 if (res <= 0) 2161 fib6_walker_unlink(net, w); 2162 return res; 2163} 2164 2165static int fib6_clean_node(struct fib6_walker *w) 2166{ 2167 int res; 2168 struct fib6_info *rt; 2169 struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w); 2170 struct nl_info info = { 2171 .nl_net = c->net, 2172 .skip_notify = c->skip_notify, 2173 }; 2174 2175 if (c->sernum != FIB6_NO_SERNUM_CHANGE && 2176 READ_ONCE(w->node->fn_sernum) != c->sernum) 2177 WRITE_ONCE(w->node->fn_sernum, c->sernum); 2178 2179 if (!c->func) { 2180 WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE); 2181 w->leaf = NULL; 2182 return 0; 2183 } 2184 2185 for_each_fib6_walker_rt(w) { 2186 res = c->func(rt, c->arg); 2187 if (res == -1) { 2188 w->leaf = rt; 2189 res = fib6_del(rt, &info); 2190 if (res) { 2191#if RT6_DEBUG >= 2 2192 pr_debug("%s: del failed: rt=%p@%p err=%d\n", 2193 __func__, rt, 2194 rcu_access_pointer(rt->fib6_node), 2195 res); 2196#endif 2197 continue; 2198 } 2199 return 0; 2200 } else if (res == -2) { 2201 if (WARN_ON(!rt->fib6_nsiblings)) 2202 continue; 2203 rt = list_last_entry(&rt->fib6_siblings, 2204 struct fib6_info, fib6_siblings); 2205 continue; 2206 } 2207 WARN_ON(res != 0); 2208 } 2209 w->leaf = rt; 2210 return 0; 2211} 2212 2213/* 2214 * Convenient frontend to tree walker. 2215 * 2216 * func is called on each route. 2217 * It may return -2 -> skip multipath route. 2218 * -1 -> delete this route. 2219 * 0 -> continue walking 2220 */ 2221 2222static void fib6_clean_tree(struct net *net, struct fib6_node *root, 2223 int (*func)(struct fib6_info *, void *arg), 2224 int sernum, void *arg, bool skip_notify) 2225{ 2226 struct fib6_cleaner c; 2227 2228 c.w.root = root; 2229 c.w.func = fib6_clean_node; 2230 c.w.count = 0; 2231 c.w.skip = 0; 2232 c.w.skip_in_node = 0; 2233 c.func = func; 2234 c.sernum = sernum; 2235 c.arg = arg; 2236 c.net = net; 2237 c.skip_notify = skip_notify; 2238 2239 fib6_walk(net, &c.w); 2240} 2241 2242static void __fib6_clean_all(struct net *net, 2243 int (*func)(struct fib6_info *, void *), 2244 int sernum, void *arg, bool skip_notify) 2245{ 2246 struct fib6_table *table; 2247 struct hlist_head *head; 2248 unsigned int h; 2249 2250 rcu_read_lock(); 2251 for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { 2252 head = &net->ipv6.fib_table_hash[h]; 2253 hlist_for_each_entry_rcu(table, head, tb6_hlist) { 2254 spin_lock_bh(&table->tb6_lock); 2255 fib6_clean_tree(net, &table->tb6_root, 2256 func, sernum, arg, skip_notify); 2257 spin_unlock_bh(&table->tb6_lock); 2258 } 2259 } 2260 rcu_read_unlock(); 2261} 2262 2263void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *), 2264 void *arg) 2265{ 2266 __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, false); 2267} 2268 2269void fib6_clean_all_skip_notify(struct net *net, 2270 int (*func)(struct fib6_info *, void *), 2271 void *arg) 2272{ 2273 __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, true); 2274} 2275 2276static void fib6_flush_trees(struct net *net) 2277{ 2278 int new_sernum = fib6_new_sernum(net); 2279 2280 __fib6_clean_all(net, NULL, new_sernum, NULL, false); 2281} 2282 2283/* 2284 * Garbage collection 2285 */ 2286 2287static int fib6_age(struct fib6_info *rt, void *arg) 2288{ 2289 struct fib6_gc_args *gc_args = arg; 2290 unsigned long now = jiffies; 2291 2292 /* 2293 * check addrconf expiration here. 2294 * Routes are expired even if they are in use. 2295 */ 2296 2297 if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { 2298 if (time_after(now, rt->expires)) { 2299 RT6_TRACE("expiring %p\n", rt); 2300 return -1; 2301 } 2302 gc_args->more++; 2303 } 2304 2305 /* Also age clones in the exception table. 2306 * Note, that clones are aged out 2307 * only if they are not in use now. 2308 */ 2309 rt6_age_exceptions(rt, gc_args, now); 2310 2311 return 0; 2312} 2313 2314void fib6_run_gc(unsigned long expires, struct net *net, bool force) 2315{ 2316 struct fib6_gc_args gc_args; 2317 unsigned long now; 2318 2319 if (force) { 2320 spin_lock_bh(&net->ipv6.fib6_gc_lock); 2321 } else if (!spin_trylock_bh(&net->ipv6.fib6_gc_lock)) { 2322 mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); 2323 return; 2324 } 2325 gc_args.timeout = expires ? (int)expires : 2326 net->ipv6.sysctl.ip6_rt_gc_interval; 2327 gc_args.more = 0; 2328 2329 fib6_clean_all(net, fib6_age, &gc_args); 2330 now = jiffies; 2331 net->ipv6.ip6_rt_last_gc = now; 2332 2333 if (gc_args.more) 2334 mod_timer(&net->ipv6.ip6_fib_timer, 2335 round_jiffies(now 2336 + net->ipv6.sysctl.ip6_rt_gc_interval)); 2337 else 2338 del_timer(&net->ipv6.ip6_fib_timer); 2339 spin_unlock_bh(&net->ipv6.fib6_gc_lock); 2340} 2341 2342static void fib6_gc_timer_cb(struct timer_list *t) 2343{ 2344 struct net *arg = from_timer(arg, t, ipv6.ip6_fib_timer); 2345 2346 fib6_run_gc(0, arg, true); 2347} 2348 2349static int __net_init fib6_net_init(struct net *net) 2350{ 2351 size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ; 2352 int err; 2353 2354 err = fib6_notifier_init(net); 2355 if (err) 2356 return err; 2357 2358 spin_lock_init(&net->ipv6.fib6_gc_lock); 2359 rwlock_init(&net->ipv6.fib6_walker_lock); 2360 INIT_LIST_HEAD(&net->ipv6.fib6_walkers); 2361 timer_setup(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, 0); 2362 2363 net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); 2364 if (!net->ipv6.rt6_stats) 2365 goto out_timer; 2366 2367 /* Avoid false sharing : Use at least a full cache line */ 2368 size = max_t(size_t, size, L1_CACHE_BYTES); 2369 2370 net->ipv6.fib_table_hash = kzalloc(size, GFP_KERNEL); 2371 if (!net->ipv6.fib_table_hash) 2372 goto out_rt6_stats; 2373 2374 net->ipv6.fib6_main_tbl = kzalloc(sizeof(*net->ipv6.fib6_main_tbl), 2375 GFP_KERNEL); 2376 if (!net->ipv6.fib6_main_tbl) 2377 goto out_fib_table_hash; 2378 2379 net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN; 2380 rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf, 2381 net->ipv6.fib6_null_entry); 2382 net->ipv6.fib6_main_tbl->tb6_root.fn_flags = 2383 RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; 2384 inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); 2385 2386#ifdef CONFIG_IPV6_MULTIPLE_TABLES 2387 net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl), 2388 GFP_KERNEL); 2389 if (!net->ipv6.fib6_local_tbl) 2390 goto out_fib6_main_tbl; 2391 net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL; 2392 rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf, 2393 net->ipv6.fib6_null_entry); 2394 net->ipv6.fib6_local_tbl->tb6_root.fn_flags = 2395 RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; 2396 inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); 2397#endif 2398 fib6_tables_init(net); 2399 2400 return 0; 2401 2402#ifdef CONFIG_IPV6_MULTIPLE_TABLES 2403out_fib6_main_tbl: 2404 kfree(net->ipv6.fib6_main_tbl); 2405#endif 2406out_fib_table_hash: 2407 kfree(net->ipv6.fib_table_hash); 2408out_rt6_stats: 2409 kfree(net->ipv6.rt6_stats); 2410out_timer: 2411 fib6_notifier_exit(net); 2412 return -ENOMEM; 2413} 2414 2415static void fib6_net_exit(struct net *net) 2416{ 2417 unsigned int i; 2418 2419 del_timer_sync(&net->ipv6.ip6_fib_timer); 2420 2421 for (i = 0; i < FIB6_TABLE_HASHSZ; i++) { 2422 struct hlist_head *head = &net->ipv6.fib_table_hash[i]; 2423 struct hlist_node *tmp; 2424 struct fib6_table *tb; 2425 2426 hlist_for_each_entry_safe(tb, tmp, head, tb6_hlist) { 2427 hlist_del(&tb->tb6_hlist); 2428 fib6_free_table(tb); 2429 } 2430 } 2431 2432 kfree(net->ipv6.fib_table_hash); 2433 kfree(net->ipv6.rt6_stats); 2434 fib6_notifier_exit(net); 2435} 2436 2437static struct pernet_operations fib6_net_ops = { 2438 .init = fib6_net_init, 2439 .exit = fib6_net_exit, 2440}; 2441 2442int __init fib6_init(void) 2443{ 2444 int ret = -ENOMEM; 2445 2446 fib6_node_kmem = kmem_cache_create("fib6_nodes", 2447 sizeof(struct fib6_node), 2448 0, SLAB_HWCACHE_ALIGN, 2449 NULL); 2450 if (!fib6_node_kmem) 2451 goto out; 2452 2453 ret = register_pernet_subsys(&fib6_net_ops); 2454 if (ret) 2455 goto out_kmem_cache_create; 2456 2457 ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE, NULL, 2458 inet6_dump_fib, 0); 2459 if (ret) 2460 goto out_unregister_subsys; 2461 2462 __fib6_flush_trees = fib6_flush_trees; 2463out: 2464 return ret; 2465 2466out_unregister_subsys: 2467 unregister_pernet_subsys(&fib6_net_ops); 2468out_kmem_cache_create: 2469 kmem_cache_destroy(fib6_node_kmem); 2470 goto out; 2471} 2472 2473void fib6_gc_cleanup(void) 2474{ 2475 unregister_pernet_subsys(&fib6_net_ops); 2476 kmem_cache_destroy(fib6_node_kmem); 2477} 2478 2479#ifdef CONFIG_PROC_FS 2480static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) 2481{ 2482 struct fib6_info *rt = v; 2483 struct ipv6_route_iter *iter = seq->private; 2484 struct fib6_nh *fib6_nh = rt->fib6_nh; 2485 unsigned int flags = rt->fib6_flags; 2486 const struct net_device *dev; 2487 2488 if (rt->nh) 2489 fib6_nh = nexthop_fib6_nh_bh(rt->nh); 2490 2491 seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); 2492 2493#ifdef CONFIG_IPV6_SUBTREES 2494 seq_printf(seq, "%pi6 %02x ", &rt->fib6_src.addr, rt->fib6_src.plen); 2495#else 2496 seq_puts(seq, "00000000000000000000000000000000 00 "); 2497#endif 2498 if (fib6_nh->fib_nh_gw_family) { 2499 flags |= RTF_GATEWAY; 2500 seq_printf(seq, "%pi6", &fib6_nh->fib_nh_gw6); 2501 } else { 2502 seq_puts(seq, "00000000000000000000000000000000"); 2503 } 2504 2505 dev = fib6_nh->fib_nh_dev; 2506 seq_printf(seq, " %08x %08x %08x %08x %8s\n", 2507 rt->fib6_metric, refcount_read(&rt->fib6_ref), 0, 2508 flags, dev ? dev->name : ""); 2509 iter->w.leaf = NULL; 2510 return 0; 2511} 2512 2513static int ipv6_route_yield(struct fib6_walker *w) 2514{ 2515 struct ipv6_route_iter *iter = w->args; 2516 2517 if (!iter->skip) 2518 return 1; 2519 2520 do { 2521 iter->w.leaf = rcu_dereference_protected( 2522 iter->w.leaf->fib6_next, 2523 lockdep_is_held(&iter->tbl->tb6_lock)); 2524 iter->skip--; 2525 if (!iter->skip && iter->w.leaf) 2526 return 1; 2527 } while (iter->w.leaf); 2528 2529 return 0; 2530} 2531 2532static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter, 2533 struct net *net) 2534{ 2535 memset(&iter->w, 0, sizeof(iter->w)); 2536 iter->w.func = ipv6_route_yield; 2537 iter->w.root = &iter->tbl->tb6_root; 2538 iter->w.state = FWS_INIT; 2539 iter->w.node = iter->w.root; 2540 iter->w.args = iter; 2541 iter->sernum = READ_ONCE(iter->w.root->fn_sernum); 2542 INIT_LIST_HEAD(&iter->w.lh); 2543 fib6_walker_link(net, &iter->w); 2544} 2545 2546static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, 2547 struct net *net) 2548{ 2549 unsigned int h; 2550 struct hlist_node *node; 2551 2552 if (tbl) { 2553 h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; 2554 node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist)); 2555 } else { 2556 h = 0; 2557 node = NULL; 2558 } 2559 2560 while (!node && h < FIB6_TABLE_HASHSZ) { 2561 node = rcu_dereference_bh( 2562 hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); 2563 } 2564 return hlist_entry_safe(node, struct fib6_table, tb6_hlist); 2565} 2566 2567static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) 2568{ 2569 int sernum = READ_ONCE(iter->w.root->fn_sernum); 2570 2571 if (iter->sernum != sernum) { 2572 iter->sernum = sernum; 2573 iter->w.state = FWS_INIT; 2574 iter->w.node = iter->w.root; 2575 WARN_ON(iter->w.skip); 2576 iter->w.skip = iter->w.count; 2577 } 2578} 2579 2580static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) 2581{ 2582 int r; 2583 struct fib6_info *n; 2584 struct net *net = seq_file_net(seq); 2585 struct ipv6_route_iter *iter = seq->private; 2586 2587 ++(*pos); 2588 if (!v) 2589 goto iter_table; 2590 2591 n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); 2592 if (n) 2593 return n; 2594 2595iter_table: 2596 ipv6_route_check_sernum(iter); 2597 spin_lock_bh(&iter->tbl->tb6_lock); 2598 r = fib6_walk_continue(&iter->w); 2599 spin_unlock_bh(&iter->tbl->tb6_lock); 2600 if (r > 0) { 2601 return iter->w.leaf; 2602 } else if (r < 0) { 2603 fib6_walker_unlink(net, &iter->w); 2604 return NULL; 2605 } 2606 fib6_walker_unlink(net, &iter->w); 2607 2608 iter->tbl = ipv6_route_seq_next_table(iter->tbl, net); 2609 if (!iter->tbl) 2610 return NULL; 2611 2612 ipv6_route_seq_setup_walk(iter, net); 2613 goto iter_table; 2614} 2615 2616static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) 2617 __acquires(RCU_BH) 2618{ 2619 struct net *net = seq_file_net(seq); 2620 struct ipv6_route_iter *iter = seq->private; 2621 2622 rcu_read_lock_bh(); 2623 iter->tbl = ipv6_route_seq_next_table(NULL, net); 2624 iter->skip = *pos; 2625 2626 if (iter->tbl) { 2627 loff_t p = 0; 2628 2629 ipv6_route_seq_setup_walk(iter, net); 2630 return ipv6_route_seq_next(seq, NULL, &p); 2631 } else { 2632 return NULL; 2633 } 2634} 2635 2636static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) 2637{ 2638 struct fib6_walker *w = &iter->w; 2639 return w->node && !(w->state == FWS_U && w->node == w->root); 2640} 2641 2642static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) 2643 __releases(RCU_BH) 2644{ 2645 struct net *net = seq_file_net(seq); 2646 struct ipv6_route_iter *iter = seq->private; 2647 2648 if (ipv6_route_iter_active(iter)) 2649 fib6_walker_unlink(net, &iter->w); 2650 2651 rcu_read_unlock_bh(); 2652} 2653 2654#if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) 2655static int ipv6_route_prog_seq_show(struct bpf_prog *prog, 2656 struct bpf_iter_meta *meta, 2657 void *v) 2658{ 2659 struct bpf_iter__ipv6_route ctx; 2660 2661 ctx.meta = meta; 2662 ctx.rt = v; 2663 return bpf_iter_run_prog(prog, &ctx); 2664} 2665 2666static int ipv6_route_seq_show(struct seq_file *seq, void *v) 2667{ 2668 struct ipv6_route_iter *iter = seq->private; 2669 struct bpf_iter_meta meta; 2670 struct bpf_prog *prog; 2671 int ret; 2672 2673 meta.seq = seq; 2674 prog = bpf_iter_get_info(&meta, false); 2675 if (!prog) 2676 return ipv6_route_native_seq_show(seq, v); 2677 2678 ret = ipv6_route_prog_seq_show(prog, &meta, v); 2679 iter->w.leaf = NULL; 2680 2681 return ret; 2682} 2683 2684static void ipv6_route_seq_stop(struct seq_file *seq, void *v) 2685{ 2686 struct bpf_iter_meta meta; 2687 struct bpf_prog *prog; 2688 2689 if (!v) { 2690 meta.seq = seq; 2691 prog = bpf_iter_get_info(&meta, true); 2692 if (prog) 2693 (void)ipv6_route_prog_seq_show(prog, &meta, v); 2694 } 2695 2696 ipv6_route_native_seq_stop(seq, v); 2697} 2698#else 2699static int ipv6_route_seq_show(struct seq_file *seq, void *v) 2700{ 2701 return ipv6_route_native_seq_show(seq, v); 2702} 2703 2704static void ipv6_route_seq_stop(struct seq_file *seq, void *v) 2705{ 2706 ipv6_route_native_seq_stop(seq, v); 2707} 2708#endif 2709 2710const struct seq_operations ipv6_route_seq_ops = { 2711 .start = ipv6_route_seq_start, 2712 .next = ipv6_route_seq_next, 2713 .stop = ipv6_route_seq_stop, 2714 .show = ipv6_route_seq_show 2715}; 2716#endif /* CONFIG_PROC_FS */ 2717