1// SPDX-License-Identifier: GPL-2.0-only 2/* 3 * net/core/fib_rules.c Generic Routing Rules 4 * 5 * Authors: Thomas Graf <tgraf@suug.ch> 6 */ 7 8#include <linux/types.h> 9#include <linux/kernel.h> 10#include <linux/slab.h> 11#include <linux/list.h> 12#include <linux/module.h> 13#include <net/net_namespace.h> 14#include <net/sock.h> 15#include <net/fib_rules.h> 16#include <net/ip_tunnels.h> 17#include <linux/indirect_call_wrapper.h> 18 19#if defined(CONFIG_IPV6) && defined(CONFIG_IPV6_MULTIPLE_TABLES) 20#ifdef CONFIG_IP_MULTIPLE_TABLES 21#define INDIRECT_CALL_MT(f, f2, f1, ...) \ 22 INDIRECT_CALL_INET(f, f2, f1, __VA_ARGS__) 23#else 24#define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__) 25#endif 26#elif defined(CONFIG_IP_MULTIPLE_TABLES) 27#define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) 28#else 29#define INDIRECT_CALL_MT(f, f2, f1, ...) f(__VA_ARGS__) 30#endif 31 32static const struct fib_kuid_range fib_kuid_range_unset = { 33 KUIDT_INIT(0), 34 KUIDT_INIT(~0), 35}; 36 37bool fib_rule_matchall(const struct fib_rule *rule) 38{ 39 if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id || 40 rule->flags) 41 return false; 42 if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1) 43 return false; 44 if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) || 45 !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end)) 46 return false; 47 if (fib_rule_port_range_set(&rule->sport_range)) 48 return false; 49 if (fib_rule_port_range_set(&rule->dport_range)) 50 return false; 51 return true; 52} 53EXPORT_SYMBOL_GPL(fib_rule_matchall); 54 55int fib_default_rule_add(struct fib_rules_ops *ops, 56 u32 pref, u32 table, u32 flags) 57{ 58 struct fib_rule *r; 59 60 r = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); 61 if (r == NULL) 62 return -ENOMEM; 63 64 refcount_set(&r->refcnt, 1); 65 r->action = FR_ACT_TO_TBL; 66 r->pref = pref; 67 r->table = table; 68 r->flags = flags; 69 r->proto = RTPROT_KERNEL; 70 r->fr_net = ops->fro_net; 71 r->uid_range = fib_kuid_range_unset; 72 73 r->suppress_prefixlen = -1; 74 r->suppress_ifgroup = -1; 75 76 /* The lock is not required here, the list in unreacheable 77 * at the moment this function is called */ 78 list_add_tail(&r->list, &ops->rules_list); 79 return 0; 80} 81EXPORT_SYMBOL(fib_default_rule_add); 82 83static u32 fib_default_rule_pref(struct fib_rules_ops *ops) 84{ 85 struct list_head *pos; 86 struct fib_rule *rule; 87 88 if (!list_empty(&ops->rules_list)) { 89 pos = ops->rules_list.next; 90 if (pos->next != &ops->rules_list) { 91 rule = list_entry(pos->next, struct fib_rule, list); 92 if (rule->pref) 93 return rule->pref - 1; 94 } 95 } 96 97 return 0; 98} 99 100static void notify_rule_change(int event, struct fib_rule *rule, 101 struct fib_rules_ops *ops, struct nlmsghdr *nlh, 102 u32 pid); 103 104static struct fib_rules_ops *lookup_rules_ops(struct net *net, int family) 105{ 106 struct fib_rules_ops *ops; 107 108 rcu_read_lock(); 109 list_for_each_entry_rcu(ops, &net->rules_ops, list) { 110 if (ops->family == family) { 111 if (!try_module_get(ops->owner)) 112 ops = NULL; 113 rcu_read_unlock(); 114 return ops; 115 } 116 } 117 rcu_read_unlock(); 118 119 return NULL; 120} 121 122static void rules_ops_put(struct fib_rules_ops *ops) 123{ 124 if (ops) 125 module_put(ops->owner); 126} 127 128static void flush_route_cache(struct fib_rules_ops *ops) 129{ 130 if (ops->flush_cache) 131 ops->flush_cache(ops); 132} 133 134static int __fib_rules_register(struct fib_rules_ops *ops) 135{ 136 int err = -EEXIST; 137 struct fib_rules_ops *o; 138 struct net *net; 139 140 net = ops->fro_net; 141 142 if (ops->rule_size < sizeof(struct fib_rule)) 143 return -EINVAL; 144 145 if (ops->match == NULL || ops->configure == NULL || 146 ops->compare == NULL || ops->fill == NULL || 147 ops->action == NULL) 148 return -EINVAL; 149 150 spin_lock(&net->rules_mod_lock); 151 list_for_each_entry(o, &net->rules_ops, list) 152 if (ops->family == o->family) 153 goto errout; 154 155 list_add_tail_rcu(&ops->list, &net->rules_ops); 156 err = 0; 157errout: 158 spin_unlock(&net->rules_mod_lock); 159 160 return err; 161} 162 163struct fib_rules_ops * 164fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net) 165{ 166 struct fib_rules_ops *ops; 167 int err; 168 169 ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL); 170 if (ops == NULL) 171 return ERR_PTR(-ENOMEM); 172 173 INIT_LIST_HEAD(&ops->rules_list); 174 ops->fro_net = net; 175 176 err = __fib_rules_register(ops); 177 if (err) { 178 kfree(ops); 179 ops = ERR_PTR(err); 180 } 181 182 return ops; 183} 184EXPORT_SYMBOL_GPL(fib_rules_register); 185 186static void fib_rules_cleanup_ops(struct fib_rules_ops *ops) 187{ 188 struct fib_rule *rule, *tmp; 189 190 list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) { 191 list_del_rcu(&rule->list); 192 if (ops->delete) 193 ops->delete(rule); 194 fib_rule_put(rule); 195 } 196} 197 198void fib_rules_unregister(struct fib_rules_ops *ops) 199{ 200 struct net *net = ops->fro_net; 201 202 spin_lock(&net->rules_mod_lock); 203 list_del_rcu(&ops->list); 204 spin_unlock(&net->rules_mod_lock); 205 206 fib_rules_cleanup_ops(ops); 207 kfree_rcu(ops, rcu); 208} 209EXPORT_SYMBOL_GPL(fib_rules_unregister); 210 211static int uid_range_set(struct fib_kuid_range *range) 212{ 213 return uid_valid(range->start) && uid_valid(range->end); 214} 215 216static struct fib_kuid_range nla_get_kuid_range(struct nlattr **tb) 217{ 218 struct fib_rule_uid_range *in; 219 struct fib_kuid_range out; 220 221 in = (struct fib_rule_uid_range *)nla_data(tb[FRA_UID_RANGE]); 222 223 out.start = make_kuid(current_user_ns(), in->start); 224 out.end = make_kuid(current_user_ns(), in->end); 225 226 return out; 227} 228 229static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range) 230{ 231 struct fib_rule_uid_range out = { 232 from_kuid_munged(current_user_ns(), range->start), 233 from_kuid_munged(current_user_ns(), range->end) 234 }; 235 236 return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out); 237} 238 239static int nla_get_port_range(struct nlattr *pattr, 240 struct fib_rule_port_range *port_range) 241{ 242 const struct fib_rule_port_range *pr = nla_data(pattr); 243 244 if (!fib_rule_port_range_valid(pr)) 245 return -EINVAL; 246 247 port_range->start = pr->start; 248 port_range->end = pr->end; 249 250 return 0; 251} 252 253static int nla_put_port_range(struct sk_buff *skb, int attrtype, 254 struct fib_rule_port_range *range) 255{ 256 return nla_put(skb, attrtype, sizeof(*range), range); 257} 258 259static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, 260 struct flowi *fl, int flags, 261 struct fib_lookup_arg *arg) 262{ 263 int ret = 0; 264 265 if (rule->iifindex && (rule->iifindex != fl->flowi_iif)) 266 goto out; 267 268 if (rule->oifindex && (rule->oifindex != fl->flowi_oif)) 269 goto out; 270 271 if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask) 272 goto out; 273 274 if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id)) 275 goto out; 276 277 if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg)) 278 goto out; 279 280 if (uid_lt(fl->flowi_uid, rule->uid_range.start) || 281 uid_gt(fl->flowi_uid, rule->uid_range.end)) 282 goto out; 283 284 ret = INDIRECT_CALL_MT(ops->match, 285 fib6_rule_match, 286 fib4_rule_match, 287 rule, fl, flags); 288out: 289 return (rule->flags & FIB_RULE_INVERT) ? !ret : ret; 290} 291 292int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl, 293 int flags, struct fib_lookup_arg *arg) 294{ 295 struct fib_rule *rule; 296 int err; 297 298 rcu_read_lock(); 299 300 list_for_each_entry_rcu(rule, &ops->rules_list, list) { 301jumped: 302 if (!fib_rule_match(rule, ops, fl, flags, arg)) 303 continue; 304 305 if (rule->action == FR_ACT_GOTO) { 306 struct fib_rule *target; 307 308 target = rcu_dereference(rule->ctarget); 309 if (target == NULL) { 310 continue; 311 } else { 312 rule = target; 313 goto jumped; 314 } 315 } else if (rule->action == FR_ACT_NOP) 316 continue; 317 else 318 err = INDIRECT_CALL_MT(ops->action, 319 fib6_rule_action, 320 fib4_rule_action, 321 rule, fl, flags, arg); 322 323 if (!err && ops->suppress && INDIRECT_CALL_MT(ops->suppress, 324 fib6_rule_suppress, 325 fib4_rule_suppress, 326 rule, flags, arg)) 327 continue; 328 329 if (err != -EAGAIN) { 330 if ((arg->flags & FIB_LOOKUP_NOREF) || 331 likely(refcount_inc_not_zero(&rule->refcnt))) { 332 arg->rule = rule; 333 goto out; 334 } 335 break; 336 } 337 } 338 339 err = -ESRCH; 340out: 341 rcu_read_unlock(); 342 343 return err; 344} 345EXPORT_SYMBOL_GPL(fib_rules_lookup); 346 347static int call_fib_rule_notifier(struct notifier_block *nb, 348 enum fib_event_type event_type, 349 struct fib_rule *rule, int family, 350 struct netlink_ext_ack *extack) 351{ 352 struct fib_rule_notifier_info info = { 353 .info.family = family, 354 .info.extack = extack, 355 .rule = rule, 356 }; 357 358 return call_fib_notifier(nb, event_type, &info.info); 359} 360 361static int call_fib_rule_notifiers(struct net *net, 362 enum fib_event_type event_type, 363 struct fib_rule *rule, 364 struct fib_rules_ops *ops, 365 struct netlink_ext_ack *extack) 366{ 367 struct fib_rule_notifier_info info = { 368 .info.family = ops->family, 369 .info.extack = extack, 370 .rule = rule, 371 }; 372 373 ops->fib_rules_seq++; 374 return call_fib_notifiers(net, event_type, &info.info); 375} 376 377/* Called with rcu_read_lock() */ 378int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, 379 struct netlink_ext_ack *extack) 380{ 381 struct fib_rules_ops *ops; 382 struct fib_rule *rule; 383 int err = 0; 384 385 ops = lookup_rules_ops(net, family); 386 if (!ops) 387 return -EAFNOSUPPORT; 388 list_for_each_entry_rcu(rule, &ops->rules_list, list) { 389 err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD, 390 rule, family, extack); 391 if (err) 392 break; 393 } 394 rules_ops_put(ops); 395 396 return err; 397} 398EXPORT_SYMBOL_GPL(fib_rules_dump); 399 400unsigned int fib_rules_seq_read(struct net *net, int family) 401{ 402 unsigned int fib_rules_seq; 403 struct fib_rules_ops *ops; 404 405 ASSERT_RTNL(); 406 407 ops = lookup_rules_ops(net, family); 408 if (!ops) 409 return 0; 410 fib_rules_seq = ops->fib_rules_seq; 411 rules_ops_put(ops); 412 413 return fib_rules_seq; 414} 415EXPORT_SYMBOL_GPL(fib_rules_seq_read); 416 417static struct fib_rule *rule_find(struct fib_rules_ops *ops, 418 struct fib_rule_hdr *frh, 419 struct nlattr **tb, 420 struct fib_rule *rule, 421 bool user_priority) 422{ 423 struct fib_rule *r; 424 425 list_for_each_entry(r, &ops->rules_list, list) { 426 if (rule->action && r->action != rule->action) 427 continue; 428 429 if (rule->table && r->table != rule->table) 430 continue; 431 432 if (user_priority && r->pref != rule->pref) 433 continue; 434 435 if (rule->iifname[0] && 436 memcmp(r->iifname, rule->iifname, IFNAMSIZ)) 437 continue; 438 439 if (rule->oifname[0] && 440 memcmp(r->oifname, rule->oifname, IFNAMSIZ)) 441 continue; 442 443 if (rule->mark && r->mark != rule->mark) 444 continue; 445 446 if (rule->suppress_ifgroup != -1 && 447 r->suppress_ifgroup != rule->suppress_ifgroup) 448 continue; 449 450 if (rule->suppress_prefixlen != -1 && 451 r->suppress_prefixlen != rule->suppress_prefixlen) 452 continue; 453 454 if (rule->mark_mask && r->mark_mask != rule->mark_mask) 455 continue; 456 457 if (rule->tun_id && r->tun_id != rule->tun_id) 458 continue; 459 460 if (r->fr_net != rule->fr_net) 461 continue; 462 463 if (rule->l3mdev && r->l3mdev != rule->l3mdev) 464 continue; 465 466 if (uid_range_set(&rule->uid_range) && 467 (!uid_eq(r->uid_range.start, rule->uid_range.start) || 468 !uid_eq(r->uid_range.end, rule->uid_range.end))) 469 continue; 470 471 if (rule->ip_proto && r->ip_proto != rule->ip_proto) 472 continue; 473 474 if (rule->proto && r->proto != rule->proto) 475 continue; 476 477 if (fib_rule_port_range_set(&rule->sport_range) && 478 !fib_rule_port_range_compare(&r->sport_range, 479 &rule->sport_range)) 480 continue; 481 482 if (fib_rule_port_range_set(&rule->dport_range) && 483 !fib_rule_port_range_compare(&r->dport_range, 484 &rule->dport_range)) 485 continue; 486 487 if (!ops->compare(r, frh, tb)) 488 continue; 489 return r; 490 } 491 492 return NULL; 493} 494 495#ifdef CONFIG_NET_L3_MASTER_DEV 496static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, 497 struct netlink_ext_ack *extack) 498{ 499 nlrule->l3mdev = nla_get_u8(nla); 500 if (nlrule->l3mdev != 1) { 501 NL_SET_ERR_MSG(extack, "Invalid l3mdev attribute"); 502 return -1; 503 } 504 505 return 0; 506} 507#else 508static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, 509 struct netlink_ext_ack *extack) 510{ 511 NL_SET_ERR_MSG(extack, "l3mdev support is not enabled in kernel"); 512 return -1; 513} 514#endif 515 516static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, 517 struct netlink_ext_ack *extack, 518 struct fib_rules_ops *ops, 519 struct nlattr *tb[], 520 struct fib_rule **rule, 521 bool *user_priority) 522{ 523 struct net *net = sock_net(skb->sk); 524 struct fib_rule_hdr *frh = nlmsg_data(nlh); 525 struct fib_rule *nlrule = NULL; 526 int err = -EINVAL; 527 528 if (frh->src_len) 529 if (!tb[FRA_SRC] || 530 frh->src_len > (ops->addr_size * 8) || 531 nla_len(tb[FRA_SRC]) != ops->addr_size) { 532 NL_SET_ERR_MSG(extack, "Invalid source address"); 533 goto errout; 534 } 535 536 if (frh->dst_len) 537 if (!tb[FRA_DST] || 538 frh->dst_len > (ops->addr_size * 8) || 539 nla_len(tb[FRA_DST]) != ops->addr_size) { 540 NL_SET_ERR_MSG(extack, "Invalid dst address"); 541 goto errout; 542 } 543 544 nlrule = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); 545 if (!nlrule) { 546 err = -ENOMEM; 547 goto errout; 548 } 549 refcount_set(&nlrule->refcnt, 1); 550 nlrule->fr_net = net; 551 552 if (tb[FRA_PRIORITY]) { 553 nlrule->pref = nla_get_u32(tb[FRA_PRIORITY]); 554 *user_priority = true; 555 } else { 556 nlrule->pref = fib_default_rule_pref(ops); 557 } 558 559 nlrule->proto = tb[FRA_PROTOCOL] ? 560 nla_get_u8(tb[FRA_PROTOCOL]) : RTPROT_UNSPEC; 561 562 if (tb[FRA_IIFNAME]) { 563 struct net_device *dev; 564 565 nlrule->iifindex = -1; 566 nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); 567 dev = __dev_get_by_name(net, nlrule->iifname); 568 if (dev) 569 nlrule->iifindex = dev->ifindex; 570 } 571 572 if (tb[FRA_OIFNAME]) { 573 struct net_device *dev; 574 575 nlrule->oifindex = -1; 576 nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); 577 dev = __dev_get_by_name(net, nlrule->oifname); 578 if (dev) 579 nlrule->oifindex = dev->ifindex; 580 } 581 582 if (tb[FRA_FWMARK]) { 583 nlrule->mark = nla_get_u32(tb[FRA_FWMARK]); 584 if (nlrule->mark) 585 /* compatibility: if the mark value is non-zero all bits 586 * are compared unless a mask is explicitly specified. 587 */ 588 nlrule->mark_mask = 0xFFFFFFFF; 589 } 590 591 if (tb[FRA_FWMASK]) 592 nlrule->mark_mask = nla_get_u32(tb[FRA_FWMASK]); 593 594 if (tb[FRA_TUN_ID]) 595 nlrule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); 596 597 err = -EINVAL; 598 if (tb[FRA_L3MDEV] && 599 fib_nl2rule_l3mdev(tb[FRA_L3MDEV], nlrule, extack) < 0) 600 goto errout_free; 601 602 nlrule->action = frh->action; 603 nlrule->flags = frh->flags; 604 nlrule->table = frh_get_table(frh, tb); 605 if (tb[FRA_SUPPRESS_PREFIXLEN]) 606 nlrule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); 607 else 608 nlrule->suppress_prefixlen = -1; 609 610 if (tb[FRA_SUPPRESS_IFGROUP]) 611 nlrule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); 612 else 613 nlrule->suppress_ifgroup = -1; 614 615 if (tb[FRA_GOTO]) { 616 if (nlrule->action != FR_ACT_GOTO) { 617 NL_SET_ERR_MSG(extack, "Unexpected goto"); 618 goto errout_free; 619 } 620 621 nlrule->target = nla_get_u32(tb[FRA_GOTO]); 622 /* Backward jumps are prohibited to avoid endless loops */ 623 if (nlrule->target <= nlrule->pref) { 624 NL_SET_ERR_MSG(extack, "Backward goto not supported"); 625 goto errout_free; 626 } 627 } else if (nlrule->action == FR_ACT_GOTO) { 628 NL_SET_ERR_MSG(extack, "Missing goto target for action goto"); 629 goto errout_free; 630 } 631 632 if (nlrule->l3mdev && nlrule->table) { 633 NL_SET_ERR_MSG(extack, "l3mdev and table are mutually exclusive"); 634 goto errout_free; 635 } 636 637 if (tb[FRA_UID_RANGE]) { 638 if (current_user_ns() != net->user_ns) { 639 err = -EPERM; 640 NL_SET_ERR_MSG(extack, "No permission to set uid"); 641 goto errout_free; 642 } 643 644 nlrule->uid_range = nla_get_kuid_range(tb); 645 646 if (!uid_range_set(&nlrule->uid_range) || 647 !uid_lte(nlrule->uid_range.start, nlrule->uid_range.end)) { 648 NL_SET_ERR_MSG(extack, "Invalid uid range"); 649 goto errout_free; 650 } 651 } else { 652 nlrule->uid_range = fib_kuid_range_unset; 653 } 654 655 if (tb[FRA_IP_PROTO]) 656 nlrule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]); 657 658 if (tb[FRA_SPORT_RANGE]) { 659 err = nla_get_port_range(tb[FRA_SPORT_RANGE], 660 &nlrule->sport_range); 661 if (err) { 662 NL_SET_ERR_MSG(extack, "Invalid sport range"); 663 goto errout_free; 664 } 665 } 666 667 if (tb[FRA_DPORT_RANGE]) { 668 err = nla_get_port_range(tb[FRA_DPORT_RANGE], 669 &nlrule->dport_range); 670 if (err) { 671 NL_SET_ERR_MSG(extack, "Invalid dport range"); 672 goto errout_free; 673 } 674 } 675 676 *rule = nlrule; 677 678 return 0; 679 680errout_free: 681 kfree(nlrule); 682errout: 683 return err; 684} 685 686static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, 687 struct nlattr **tb, struct fib_rule *rule) 688{ 689 struct fib_rule *r; 690 691 list_for_each_entry(r, &ops->rules_list, list) { 692 if (r->action != rule->action) 693 continue; 694 695 if (r->table != rule->table) 696 continue; 697 698 if (r->pref != rule->pref) 699 continue; 700 701 if (memcmp(r->iifname, rule->iifname, IFNAMSIZ)) 702 continue; 703 704 if (memcmp(r->oifname, rule->oifname, IFNAMSIZ)) 705 continue; 706 707 if (r->mark != rule->mark) 708 continue; 709 710 if (r->suppress_ifgroup != rule->suppress_ifgroup) 711 continue; 712 713 if (r->suppress_prefixlen != rule->suppress_prefixlen) 714 continue; 715 716 if (r->mark_mask != rule->mark_mask) 717 continue; 718 719 if (r->tun_id != rule->tun_id) 720 continue; 721 722 if (r->fr_net != rule->fr_net) 723 continue; 724 725 if (r->l3mdev != rule->l3mdev) 726 continue; 727 728 if (!uid_eq(r->uid_range.start, rule->uid_range.start) || 729 !uid_eq(r->uid_range.end, rule->uid_range.end)) 730 continue; 731 732 if (r->ip_proto != rule->ip_proto) 733 continue; 734 735 if (r->proto != rule->proto) 736 continue; 737 738 if (!fib_rule_port_range_compare(&r->sport_range, 739 &rule->sport_range)) 740 continue; 741 742 if (!fib_rule_port_range_compare(&r->dport_range, 743 &rule->dport_range)) 744 continue; 745 746 if (!ops->compare(r, frh, tb)) 747 continue; 748 return 1; 749 } 750 return 0; 751} 752 753static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = { 754 [FRA_UNSPEC] = { .strict_start_type = FRA_DPORT_RANGE + 1 }, 755 [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, 756 [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, 757 [FRA_PRIORITY] = { .type = NLA_U32 }, 758 [FRA_FWMARK] = { .type = NLA_U32 }, 759 [FRA_FLOW] = { .type = NLA_U32 }, 760 [FRA_TUN_ID] = { .type = NLA_U64 }, 761 [FRA_FWMASK] = { .type = NLA_U32 }, 762 [FRA_TABLE] = { .type = NLA_U32 }, 763 [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, 764 [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, 765 [FRA_GOTO] = { .type = NLA_U32 }, 766 [FRA_L3MDEV] = { .type = NLA_U8 }, 767 [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) }, 768 [FRA_PROTOCOL] = { .type = NLA_U8 }, 769 [FRA_IP_PROTO] = { .type = NLA_U8 }, 770 [FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, 771 [FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) } 772}; 773 774int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, 775 struct netlink_ext_ack *extack) 776{ 777 struct net *net = sock_net(skb->sk); 778 struct fib_rule_hdr *frh = nlmsg_data(nlh); 779 struct fib_rules_ops *ops = NULL; 780 struct fib_rule *rule = NULL, *r, *last = NULL; 781 struct nlattr *tb[FRA_MAX + 1]; 782 int err = -EINVAL, unresolved = 0; 783 bool user_priority = false; 784 785 if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { 786 NL_SET_ERR_MSG(extack, "Invalid msg length"); 787 goto errout; 788 } 789 790 ops = lookup_rules_ops(net, frh->family); 791 if (!ops) { 792 err = -EAFNOSUPPORT; 793 NL_SET_ERR_MSG(extack, "Rule family not supported"); 794 goto errout; 795 } 796 797 err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, 798 fib_rule_policy, extack); 799 if (err < 0) { 800 NL_SET_ERR_MSG(extack, "Error parsing msg"); 801 goto errout; 802 } 803 804 err = fib_nl2rule(skb, nlh, extack, ops, tb, &rule, &user_priority); 805 if (err) 806 goto errout; 807 808 if ((nlh->nlmsg_flags & NLM_F_EXCL) && 809 rule_exists(ops, frh, tb, rule)) { 810 err = -EEXIST; 811 goto errout_free; 812 } 813 814 err = ops->configure(rule, skb, frh, tb, extack); 815 if (err < 0) 816 goto errout_free; 817 818 err = call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops, 819 extack); 820 if (err < 0) 821 goto errout_free; 822 823 list_for_each_entry(r, &ops->rules_list, list) { 824 if (r->pref == rule->target) { 825 RCU_INIT_POINTER(rule->ctarget, r); 826 break; 827 } 828 } 829 830 if (rcu_dereference_protected(rule->ctarget, 1) == NULL) 831 unresolved = 1; 832 833 list_for_each_entry(r, &ops->rules_list, list) { 834 if (r->pref > rule->pref) 835 break; 836 last = r; 837 } 838 839 if (last) 840 list_add_rcu(&rule->list, &last->list); 841 else 842 list_add_rcu(&rule->list, &ops->rules_list); 843 844 if (ops->unresolved_rules) { 845 /* 846 * There are unresolved goto rules in the list, check if 847 * any of them are pointing to this new rule. 848 */ 849 list_for_each_entry(r, &ops->rules_list, list) { 850 if (r->action == FR_ACT_GOTO && 851 r->target == rule->pref && 852 rtnl_dereference(r->ctarget) == NULL) { 853 rcu_assign_pointer(r->ctarget, rule); 854 if (--ops->unresolved_rules == 0) 855 break; 856 } 857 } 858 } 859 860 if (rule->action == FR_ACT_GOTO) 861 ops->nr_goto_rules++; 862 863 if (unresolved) 864 ops->unresolved_rules++; 865 866 if (rule->tun_id) 867 ip_tunnel_need_metadata(); 868 869 notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); 870 flush_route_cache(ops); 871 rules_ops_put(ops); 872 return 0; 873 874errout_free: 875 kfree(rule); 876errout: 877 rules_ops_put(ops); 878 return err; 879} 880EXPORT_SYMBOL_GPL(fib_nl_newrule); 881 882int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, 883 struct netlink_ext_ack *extack) 884{ 885 struct net *net = sock_net(skb->sk); 886 struct fib_rule_hdr *frh = nlmsg_data(nlh); 887 struct fib_rules_ops *ops = NULL; 888 struct fib_rule *rule = NULL, *r, *nlrule = NULL; 889 struct nlattr *tb[FRA_MAX+1]; 890 int err = -EINVAL; 891 bool user_priority = false; 892 893 if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { 894 NL_SET_ERR_MSG(extack, "Invalid msg length"); 895 goto errout; 896 } 897 898 ops = lookup_rules_ops(net, frh->family); 899 if (ops == NULL) { 900 err = -EAFNOSUPPORT; 901 NL_SET_ERR_MSG(extack, "Rule family not supported"); 902 goto errout; 903 } 904 905 err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, 906 fib_rule_policy, extack); 907 if (err < 0) { 908 NL_SET_ERR_MSG(extack, "Error parsing msg"); 909 goto errout; 910 } 911 912 err = fib_nl2rule(skb, nlh, extack, ops, tb, &nlrule, &user_priority); 913 if (err) 914 goto errout; 915 916 rule = rule_find(ops, frh, tb, nlrule, user_priority); 917 if (!rule) { 918 err = -ENOENT; 919 goto errout; 920 } 921 922 if (rule->flags & FIB_RULE_PERMANENT) { 923 err = -EPERM; 924 goto errout; 925 } 926 927 if (ops->delete) { 928 err = ops->delete(rule); 929 if (err) 930 goto errout; 931 } 932 933 if (rule->tun_id) 934 ip_tunnel_unneed_metadata(); 935 936 list_del_rcu(&rule->list); 937 938 if (rule->action == FR_ACT_GOTO) { 939 ops->nr_goto_rules--; 940 if (rtnl_dereference(rule->ctarget) == NULL) 941 ops->unresolved_rules--; 942 } 943 944 /* 945 * Check if this rule is a target to any of them. If so, 946 * adjust to the next one with the same preference or 947 * disable them. As this operation is eventually very 948 * expensive, it is only performed if goto rules, except 949 * current if it is goto rule, have actually been added. 950 */ 951 if (ops->nr_goto_rules > 0) { 952 struct fib_rule *n; 953 954 n = list_next_entry(rule, list); 955 if (&n->list == &ops->rules_list || n->pref != rule->pref) 956 n = NULL; 957 list_for_each_entry(r, &ops->rules_list, list) { 958 if (rtnl_dereference(r->ctarget) != rule) 959 continue; 960 rcu_assign_pointer(r->ctarget, n); 961 if (!n) 962 ops->unresolved_rules++; 963 } 964 } 965 966 call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, 967 NULL); 968 notify_rule_change(RTM_DELRULE, rule, ops, nlh, 969 NETLINK_CB(skb).portid); 970 fib_rule_put(rule); 971 flush_route_cache(ops); 972 rules_ops_put(ops); 973 kfree(nlrule); 974 return 0; 975 976errout: 977 kfree(nlrule); 978 rules_ops_put(ops); 979 return err; 980} 981EXPORT_SYMBOL_GPL(fib_nl_delrule); 982 983static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, 984 struct fib_rule *rule) 985{ 986 size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)) 987 + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */ 988 + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ 989 + nla_total_size(4) /* FRA_PRIORITY */ 990 + nla_total_size(4) /* FRA_TABLE */ 991 + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */ 992 + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ 993 + nla_total_size(4) /* FRA_FWMARK */ 994 + nla_total_size(4) /* FRA_FWMASK */ 995 + nla_total_size_64bit(8) /* FRA_TUN_ID */ 996 + nla_total_size(sizeof(struct fib_kuid_range)) 997 + nla_total_size(1) /* FRA_PROTOCOL */ 998 + nla_total_size(1) /* FRA_IP_PROTO */ 999 + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_SPORT_RANGE */ 1000 + nla_total_size(sizeof(struct fib_rule_port_range)); /* FRA_DPORT_RANGE */ 1001 1002 if (ops->nlmsg_payload) 1003 payload += ops->nlmsg_payload(rule); 1004 1005 return payload; 1006} 1007 1008static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, 1009 u32 pid, u32 seq, int type, int flags, 1010 struct fib_rules_ops *ops) 1011{ 1012 struct nlmsghdr *nlh; 1013 struct fib_rule_hdr *frh; 1014 1015 nlh = nlmsg_put(skb, pid, seq, type, sizeof(*frh), flags); 1016 if (nlh == NULL) 1017 return -EMSGSIZE; 1018 1019 frh = nlmsg_data(nlh); 1020 frh->family = ops->family; 1021 frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT; 1022 if (nla_put_u32(skb, FRA_TABLE, rule->table)) 1023 goto nla_put_failure; 1024 if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) 1025 goto nla_put_failure; 1026 frh->res1 = 0; 1027 frh->res2 = 0; 1028 frh->action = rule->action; 1029 frh->flags = rule->flags; 1030 1031 if (nla_put_u8(skb, FRA_PROTOCOL, rule->proto)) 1032 goto nla_put_failure; 1033 1034 if (rule->action == FR_ACT_GOTO && 1035 rcu_access_pointer(rule->ctarget) == NULL) 1036 frh->flags |= FIB_RULE_UNRESOLVED; 1037 1038 if (rule->iifname[0]) { 1039 if (nla_put_string(skb, FRA_IIFNAME, rule->iifname)) 1040 goto nla_put_failure; 1041 if (rule->iifindex == -1) 1042 frh->flags |= FIB_RULE_IIF_DETACHED; 1043 } 1044 1045 if (rule->oifname[0]) { 1046 if (nla_put_string(skb, FRA_OIFNAME, rule->oifname)) 1047 goto nla_put_failure; 1048 if (rule->oifindex == -1) 1049 frh->flags |= FIB_RULE_OIF_DETACHED; 1050 } 1051 1052 if ((rule->pref && 1053 nla_put_u32(skb, FRA_PRIORITY, rule->pref)) || 1054 (rule->mark && 1055 nla_put_u32(skb, FRA_FWMARK, rule->mark)) || 1056 ((rule->mark_mask || rule->mark) && 1057 nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) || 1058 (rule->target && 1059 nla_put_u32(skb, FRA_GOTO, rule->target)) || 1060 (rule->tun_id && 1061 nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) || 1062 (rule->l3mdev && 1063 nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) || 1064 (uid_range_set(&rule->uid_range) && 1065 nla_put_uid_range(skb, &rule->uid_range)) || 1066 (fib_rule_port_range_set(&rule->sport_range) && 1067 nla_put_port_range(skb, FRA_SPORT_RANGE, &rule->sport_range)) || 1068 (fib_rule_port_range_set(&rule->dport_range) && 1069 nla_put_port_range(skb, FRA_DPORT_RANGE, &rule->dport_range)) || 1070 (rule->ip_proto && nla_put_u8(skb, FRA_IP_PROTO, rule->ip_proto))) 1071 goto nla_put_failure; 1072 1073 if (rule->suppress_ifgroup != -1) { 1074 if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup)) 1075 goto nla_put_failure; 1076 } 1077 1078 if (ops->fill(rule, skb, frh) < 0) 1079 goto nla_put_failure; 1080 1081 nlmsg_end(skb, nlh); 1082 return 0; 1083 1084nla_put_failure: 1085 nlmsg_cancel(skb, nlh); 1086 return -EMSGSIZE; 1087} 1088 1089static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, 1090 struct fib_rules_ops *ops) 1091{ 1092 int idx = 0; 1093 struct fib_rule *rule; 1094 int err = 0; 1095 1096 rcu_read_lock(); 1097 list_for_each_entry_rcu(rule, &ops->rules_list, list) { 1098 if (idx < cb->args[1]) 1099 goto skip; 1100 1101 err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, 1102 cb->nlh->nlmsg_seq, RTM_NEWRULE, 1103 NLM_F_MULTI, ops); 1104 if (err) 1105 break; 1106skip: 1107 idx++; 1108 } 1109 rcu_read_unlock(); 1110 cb->args[1] = idx; 1111 rules_ops_put(ops); 1112 1113 return err; 1114} 1115 1116static int fib_valid_dumprule_req(const struct nlmsghdr *nlh, 1117 struct netlink_ext_ack *extack) 1118{ 1119 struct fib_rule_hdr *frh; 1120 1121 if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { 1122 NL_SET_ERR_MSG(extack, "Invalid header for fib rule dump request"); 1123 return -EINVAL; 1124 } 1125 1126 frh = nlmsg_data(nlh); 1127 if (frh->dst_len || frh->src_len || frh->tos || frh->table || 1128 frh->res1 || frh->res2 || frh->action || frh->flags) { 1129 NL_SET_ERR_MSG(extack, 1130 "Invalid values in header for fib rule dump request"); 1131 return -EINVAL; 1132 } 1133 1134 if (nlmsg_attrlen(nlh, sizeof(*frh))) { 1135 NL_SET_ERR_MSG(extack, "Invalid data after header in fib rule dump request"); 1136 return -EINVAL; 1137 } 1138 1139 return 0; 1140} 1141 1142static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) 1143{ 1144 const struct nlmsghdr *nlh = cb->nlh; 1145 struct net *net = sock_net(skb->sk); 1146 struct fib_rules_ops *ops; 1147 int idx = 0, family; 1148 1149 if (cb->strict_check) { 1150 int err = fib_valid_dumprule_req(nlh, cb->extack); 1151 1152 if (err < 0) 1153 return err; 1154 } 1155 1156 family = rtnl_msg_family(nlh); 1157 if (family != AF_UNSPEC) { 1158 /* Protocol specific dump request */ 1159 ops = lookup_rules_ops(net, family); 1160 if (ops == NULL) 1161 return -EAFNOSUPPORT; 1162 1163 dump_rules(skb, cb, ops); 1164 1165 return skb->len; 1166 } 1167 1168 rcu_read_lock(); 1169 list_for_each_entry_rcu(ops, &net->rules_ops, list) { 1170 if (idx < cb->args[0] || !try_module_get(ops->owner)) 1171 goto skip; 1172 1173 if (dump_rules(skb, cb, ops) < 0) 1174 break; 1175 1176 cb->args[1] = 0; 1177skip: 1178 idx++; 1179 } 1180 rcu_read_unlock(); 1181 cb->args[0] = idx; 1182 1183 return skb->len; 1184} 1185 1186static void notify_rule_change(int event, struct fib_rule *rule, 1187 struct fib_rules_ops *ops, struct nlmsghdr *nlh, 1188 u32 pid) 1189{ 1190 struct net *net; 1191 struct sk_buff *skb; 1192 int err = -ENOMEM; 1193 1194 net = ops->fro_net; 1195 skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL); 1196 if (skb == NULL) 1197 goto errout; 1198 1199 err = fib_nl_fill_rule(skb, rule, pid, nlh->nlmsg_seq, event, 0, ops); 1200 if (err < 0) { 1201 /* -EMSGSIZE implies BUG in fib_rule_nlmsg_size() */ 1202 WARN_ON(err == -EMSGSIZE); 1203 kfree_skb(skb); 1204 goto errout; 1205 } 1206 1207 rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL); 1208 return; 1209errout: 1210 if (err < 0) 1211 rtnl_set_sk_err(net, ops->nlgroup, err); 1212} 1213 1214static void attach_rules(struct list_head *rules, struct net_device *dev) 1215{ 1216 struct fib_rule *rule; 1217 1218 list_for_each_entry(rule, rules, list) { 1219 if (rule->iifindex == -1 && 1220 strcmp(dev->name, rule->iifname) == 0) 1221 rule->iifindex = dev->ifindex; 1222 if (rule->oifindex == -1 && 1223 strcmp(dev->name, rule->oifname) == 0) 1224 rule->oifindex = dev->ifindex; 1225 } 1226} 1227 1228static void detach_rules(struct list_head *rules, struct net_device *dev) 1229{ 1230 struct fib_rule *rule; 1231 1232 list_for_each_entry(rule, rules, list) { 1233 if (rule->iifindex == dev->ifindex) 1234 rule->iifindex = -1; 1235 if (rule->oifindex == dev->ifindex) 1236 rule->oifindex = -1; 1237 } 1238} 1239 1240 1241static int fib_rules_event(struct notifier_block *this, unsigned long event, 1242 void *ptr) 1243{ 1244 struct net_device *dev = netdev_notifier_info_to_dev(ptr); 1245 struct net *net = dev_net(dev); 1246 struct fib_rules_ops *ops; 1247 1248 ASSERT_RTNL(); 1249 1250 switch (event) { 1251 case NETDEV_REGISTER: 1252 list_for_each_entry(ops, &net->rules_ops, list) 1253 attach_rules(&ops->rules_list, dev); 1254 break; 1255 1256 case NETDEV_CHANGENAME: 1257 list_for_each_entry(ops, &net->rules_ops, list) { 1258 detach_rules(&ops->rules_list, dev); 1259 attach_rules(&ops->rules_list, dev); 1260 } 1261 break; 1262 1263 case NETDEV_UNREGISTER: 1264 list_for_each_entry(ops, &net->rules_ops, list) 1265 detach_rules(&ops->rules_list, dev); 1266 break; 1267 } 1268 1269 return NOTIFY_DONE; 1270} 1271 1272static struct notifier_block fib_rules_notifier = { 1273 .notifier_call = fib_rules_event, 1274}; 1275 1276static int __net_init fib_rules_net_init(struct net *net) 1277{ 1278 INIT_LIST_HEAD(&net->rules_ops); 1279 spin_lock_init(&net->rules_mod_lock); 1280 return 0; 1281} 1282 1283static void __net_exit fib_rules_net_exit(struct net *net) 1284{ 1285 WARN_ON_ONCE(!list_empty(&net->rules_ops)); 1286} 1287 1288static struct pernet_operations fib_rules_net_ops = { 1289 .init = fib_rules_net_init, 1290 .exit = fib_rules_net_exit, 1291}; 1292 1293static int __init fib_rules_init(void) 1294{ 1295 int err; 1296 rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, 0); 1297 rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, 0); 1298 rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, 0); 1299 1300 err = register_pernet_subsys(&fib_rules_net_ops); 1301 if (err < 0) 1302 goto fail; 1303 1304 err = register_netdevice_notifier(&fib_rules_notifier); 1305 if (err < 0) 1306 goto fail_unregister; 1307 1308 return 0; 1309 1310fail_unregister: 1311 unregister_pernet_subsys(&fib_rules_net_ops); 1312fail: 1313 rtnl_unregister(PF_UNSPEC, RTM_NEWRULE); 1314 rtnl_unregister(PF_UNSPEC, RTM_DELRULE); 1315 rtnl_unregister(PF_UNSPEC, RTM_GETRULE); 1316 return err; 1317} 1318 1319subsys_initcall(fib_rules_init); 1320