1// SPDX-License-Identifier: GPL-2.0-only 2#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt 3 4#include <linux/workqueue.h> 5#include <linux/rtnetlink.h> 6#include <linux/cache.h> 7#include <linux/slab.h> 8#include <linux/list.h> 9#include <linux/delay.h> 10#include <linux/sched.h> 11#include <linux/idr.h> 12#include <linux/rculist.h> 13#include <linux/nsproxy.h> 14#include <linux/fs.h> 15#include <linux/proc_ns.h> 16#include <linux/file.h> 17#include <linux/export.h> 18#include <linux/user_namespace.h> 19#include <linux/net_namespace.h> 20#include <linux/sched/task.h> 21#include <linux/uidgid.h> 22#include <linux/cookie.h> 23#include <linux/proc_fs.h> 24 25#include <net/sock.h> 26#include <net/netlink.h> 27#include <net/net_namespace.h> 28#include <net/netns/generic.h> 29 30/* 31 * Our network namespace constructor/destructor lists 32 */ 33 34static LIST_HEAD(pernet_list); 35static struct list_head *first_device = &pernet_list; 36 37LIST_HEAD(net_namespace_list); 38EXPORT_SYMBOL_GPL(net_namespace_list); 39 40/* Protects net_namespace_list. Nests iside rtnl_lock() */ 41DECLARE_RWSEM(net_rwsem); 42EXPORT_SYMBOL_GPL(net_rwsem); 43 44#ifdef CONFIG_KEYS 45static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) }; 46#endif 47 48struct net init_net; 49EXPORT_SYMBOL(init_net); 50 51static bool init_net_initialized; 52/* 53 * pernet_ops_rwsem: protects: pernet_list, net_generic_ids, 54 * init_net_initialized and first_device pointer. 55 * This is internal net namespace object. Please, don't use it 56 * outside. 57 */ 58DECLARE_RWSEM(pernet_ops_rwsem); 59EXPORT_SYMBOL_GPL(pernet_ops_rwsem); 60 61#define MIN_PERNET_OPS_ID \ 62 ((sizeof(struct net_generic) + sizeof(void *) - 1) / sizeof(void *)) 63 64#define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ 65 66static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; 67 68DEFINE_COOKIE(net_cookie); 69 70static struct net_generic *net_alloc_generic(void) 71{ 72 struct net_generic *ng; 73 unsigned int generic_size = offsetof(struct net_generic, ptr[max_gen_ptrs]); 74 75 ng = kzalloc(generic_size, GFP_KERNEL); 76 if (ng) 77 ng->s.len = max_gen_ptrs; 78 79 return ng; 80} 81 82static int net_assign_generic(struct net *net, unsigned int id, void *data) 83{ 84 struct net_generic *ng, *old_ng; 85 86 BUG_ON(id < MIN_PERNET_OPS_ID); 87 88 old_ng = rcu_dereference_protected(net->gen, 89 lockdep_is_held(&pernet_ops_rwsem)); 90 if (old_ng->s.len > id) { 91 old_ng->ptr[id] = data; 92 return 0; 93 } 94 95 ng = net_alloc_generic(); 96 if (!ng) 97 return -ENOMEM; 98 99 /* 100 * Some synchronisation notes: 101 * 102 * The net_generic explores the net->gen array inside rcu 103 * read section. Besides once set the net->gen->ptr[x] 104 * pointer never changes (see rules in netns/generic.h). 105 * 106 * That said, we simply duplicate this array and schedule 107 * the old copy for kfree after a grace period. 108 */ 109 110 memcpy(&ng->ptr[MIN_PERNET_OPS_ID], &old_ng->ptr[MIN_PERNET_OPS_ID], 111 (old_ng->s.len - MIN_PERNET_OPS_ID) * sizeof(void *)); 112 ng->ptr[id] = data; 113 114 rcu_assign_pointer(net->gen, ng); 115 kfree_rcu(old_ng, s.rcu); 116 return 0; 117} 118 119static int ops_init(const struct pernet_operations *ops, struct net *net) 120{ 121 struct net_generic *ng; 122 int err = -ENOMEM; 123 void *data = NULL; 124 125 if (ops->id && ops->size) { 126 data = kzalloc(ops->size, GFP_KERNEL); 127 if (!data) 128 goto out; 129 130 err = net_assign_generic(net, *ops->id, data); 131 if (err) 132 goto cleanup; 133 } 134 err = 0; 135 if (ops->init) 136 err = ops->init(net); 137 if (!err) 138 return 0; 139 140 if (ops->id && ops->size) { 141 ng = rcu_dereference_protected(net->gen, 142 lockdep_is_held(&pernet_ops_rwsem)); 143 ng->ptr[*ops->id] = NULL; 144 } 145 146cleanup: 147 kfree(data); 148 149out: 150 return err; 151} 152 153static void ops_pre_exit_list(const struct pernet_operations *ops, 154 struct list_head *net_exit_list) 155{ 156 struct net *net; 157 158 if (ops->pre_exit) { 159 list_for_each_entry(net, net_exit_list, exit_list) 160 ops->pre_exit(net); 161 } 162} 163 164static void ops_exit_list(const struct pernet_operations *ops, 165 struct list_head *net_exit_list) 166{ 167 struct net *net; 168 if (ops->exit) { 169 list_for_each_entry(net, net_exit_list, exit_list) { 170 ops->exit(net); 171 cond_resched(); 172 } 173 } 174 if (ops->exit_batch) 175 ops->exit_batch(net_exit_list); 176} 177 178static void ops_free_list(const struct pernet_operations *ops, 179 struct list_head *net_exit_list) 180{ 181 struct net *net; 182 if (ops->size && ops->id) { 183 list_for_each_entry(net, net_exit_list, exit_list) 184 kfree(net_generic(net, *ops->id)); 185 } 186} 187 188/* should be called with nsid_lock held */ 189static int alloc_netid(struct net *net, struct net *peer, int reqid) 190{ 191 int min = 0, max = 0; 192 193 if (reqid >= 0) { 194 min = reqid; 195 max = reqid + 1; 196 } 197 198 return idr_alloc(&net->netns_ids, peer, min, max, GFP_ATOMIC); 199} 200 201/* This function is used by idr_for_each(). If net is equal to peer, the 202 * function returns the id so that idr_for_each() stops. Because we cannot 203 * returns the id 0 (idr_for_each() will not stop), we return the magic value 204 * NET_ID_ZERO (-1) for it. 205 */ 206#define NET_ID_ZERO -1 207static int net_eq_idr(int id, void *net, void *peer) 208{ 209 if (net_eq(net, peer)) 210 return id ? : NET_ID_ZERO; 211 return 0; 212} 213 214/* Must be called from RCU-critical section or with nsid_lock held */ 215static int __peernet2id(const struct net *net, struct net *peer) 216{ 217 int id = idr_for_each(&net->netns_ids, net_eq_idr, peer); 218 219 /* Magic value for id 0. */ 220 if (id == NET_ID_ZERO) 221 return 0; 222 if (id > 0) 223 return id; 224 225 return NETNSA_NSID_NOT_ASSIGNED; 226} 227 228static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, 229 struct nlmsghdr *nlh, gfp_t gfp); 230/* This function returns the id of a peer netns. If no id is assigned, one will 231 * be allocated and returned. 232 */ 233int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) 234{ 235 int id; 236 237 if (refcount_read(&net->ns.count) == 0) 238 return NETNSA_NSID_NOT_ASSIGNED; 239 240 spin_lock_bh(&net->nsid_lock); 241 id = __peernet2id(net, peer); 242 if (id >= 0) { 243 spin_unlock_bh(&net->nsid_lock); 244 return id; 245 } 246 247 /* When peer is obtained from RCU lists, we may race with 248 * its cleanup. Check whether it's alive, and this guarantees 249 * we never hash a peer back to net->netns_ids, after it has 250 * just been idr_remove()'d from there in cleanup_net(). 251 */ 252 if (!maybe_get_net(peer)) { 253 spin_unlock_bh(&net->nsid_lock); 254 return NETNSA_NSID_NOT_ASSIGNED; 255 } 256 257 id = alloc_netid(net, peer, -1); 258 spin_unlock_bh(&net->nsid_lock); 259 260 put_net(peer); 261 if (id < 0) 262 return NETNSA_NSID_NOT_ASSIGNED; 263 264 rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp); 265 266 return id; 267} 268EXPORT_SYMBOL_GPL(peernet2id_alloc); 269 270/* This function returns, if assigned, the id of a peer netns. */ 271int peernet2id(const struct net *net, struct net *peer) 272{ 273 int id; 274 275 rcu_read_lock(); 276 id = __peernet2id(net, peer); 277 rcu_read_unlock(); 278 279 return id; 280} 281EXPORT_SYMBOL(peernet2id); 282 283/* This function returns true is the peer netns has an id assigned into the 284 * current netns. 285 */ 286bool peernet_has_id(const struct net *net, struct net *peer) 287{ 288 return peernet2id(net, peer) >= 0; 289} 290 291struct net *get_net_ns_by_id(const struct net *net, int id) 292{ 293 struct net *peer; 294 295 if (id < 0) 296 return NULL; 297 298 rcu_read_lock(); 299 peer = idr_find(&net->netns_ids, id); 300 if (peer) 301 peer = maybe_get_net(peer); 302 rcu_read_unlock(); 303 304 return peer; 305} 306EXPORT_SYMBOL_GPL(get_net_ns_by_id); 307 308/* init code that must occur even if setup_net() is not called. */ 309static __net_init void preinit_net(struct net *net) 310{ 311 ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net notrefcnt"); 312} 313 314/* 315 * setup_net runs the initializers for the network namespace object. 316 */ 317static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) 318{ 319 /* Must be called with pernet_ops_rwsem held */ 320 const struct pernet_operations *ops, *saved_ops; 321 int error = 0; 322 LIST_HEAD(net_exit_list); 323 324 refcount_set(&net->ns.count, 1); 325 ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt"); 326 327 refcount_set(&net->passive, 1); 328 get_random_bytes(&net->hash_mix, sizeof(u32)); 329 preempt_disable(); 330 net->net_cookie = gen_cookie_next(&net_cookie); 331 preempt_enable(); 332 net->dev_base_seq = 1; 333 net->user_ns = user_ns; 334 idr_init(&net->netns_ids); 335 spin_lock_init(&net->nsid_lock); 336 mutex_init(&net->ipv4.ra_mutex); 337 338 list_for_each_entry(ops, &pernet_list, list) { 339 error = ops_init(ops, net); 340 if (error < 0) 341 goto out_undo; 342 } 343 down_write(&net_rwsem); 344 list_add_tail_rcu(&net->list, &net_namespace_list); 345 up_write(&net_rwsem); 346out: 347 return error; 348 349out_undo: 350 /* Walk through the list backwards calling the exit functions 351 * for the pernet modules whose init functions did not fail. 352 */ 353 list_add(&net->exit_list, &net_exit_list); 354 saved_ops = ops; 355 list_for_each_entry_continue_reverse(ops, &pernet_list, list) 356 ops_pre_exit_list(ops, &net_exit_list); 357 358 synchronize_rcu(); 359 360 ops = saved_ops; 361 list_for_each_entry_continue_reverse(ops, &pernet_list, list) 362 ops_exit_list(ops, &net_exit_list); 363 364 ops = saved_ops; 365 list_for_each_entry_continue_reverse(ops, &pernet_list, list) 366 ops_free_list(ops, &net_exit_list); 367 368 rcu_barrier(); 369 goto out; 370} 371 372static int __net_init net_defaults_init_net(struct net *net) 373{ 374 net->core.sysctl_somaxconn = SOMAXCONN; 375 net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; 376 377 return 0; 378} 379 380static struct pernet_operations net_defaults_ops = { 381 .init = net_defaults_init_net, 382}; 383 384static __init int net_defaults_init(void) 385{ 386 if (register_pernet_subsys(&net_defaults_ops)) 387 panic("Cannot initialize net default settings"); 388 389 return 0; 390} 391 392core_initcall(net_defaults_init); 393 394#ifdef CONFIG_NET_NS 395static struct ucounts *inc_net_namespaces(struct user_namespace *ns) 396{ 397 return inc_ucount(ns, current_euid(), UCOUNT_NET_NAMESPACES); 398} 399 400static void dec_net_namespaces(struct ucounts *ucounts) 401{ 402 dec_ucount(ucounts, UCOUNT_NET_NAMESPACES); 403} 404 405static struct kmem_cache *net_cachep __ro_after_init; 406static struct workqueue_struct *netns_wq; 407 408static struct net *net_alloc(void) 409{ 410 struct net *net = NULL; 411 struct net_generic *ng; 412 413 ng = net_alloc_generic(); 414 if (!ng) 415 goto out; 416 417 net = kmem_cache_zalloc(net_cachep, GFP_KERNEL); 418 if (!net) 419 goto out_free; 420 421#ifdef CONFIG_KEYS 422 net->key_domain = kzalloc(sizeof(struct key_tag), GFP_KERNEL); 423 if (!net->key_domain) 424 goto out_free_2; 425 refcount_set(&net->key_domain->usage, 1); 426#endif 427 428 rcu_assign_pointer(net->gen, ng); 429out: 430 return net; 431 432#ifdef CONFIG_KEYS 433out_free_2: 434 kmem_cache_free(net_cachep, net); 435 net = NULL; 436#endif 437out_free: 438 kfree(ng); 439 goto out; 440} 441 442static void net_free(struct net *net) 443{ 444 if (refcount_dec_and_test(&net->passive)) { 445 kfree(rcu_access_pointer(net->gen)); 446 447 /* There should not be any trackers left there. */ 448 ref_tracker_dir_exit(&net->notrefcnt_tracker); 449 450 kmem_cache_free(net_cachep, net); 451 } 452} 453 454void net_drop_ns(void *p) 455{ 456 struct net *net = (struct net *)p; 457 458 if (net) 459 net_free(net); 460} 461 462struct net *copy_net_ns(unsigned long flags, 463 struct user_namespace *user_ns, struct net *old_net) 464{ 465 struct ucounts *ucounts; 466 struct net *net; 467 int rv; 468 469 if (!(flags & CLONE_NEWNET)) 470 return get_net(old_net); 471 472 ucounts = inc_net_namespaces(user_ns); 473 if (!ucounts) 474 return ERR_PTR(-ENOSPC); 475 476 net = net_alloc(); 477 if (!net) { 478 rv = -ENOMEM; 479 goto dec_ucounts; 480 } 481 482 preinit_net(net); 483 refcount_set(&net->passive, 1); 484 net->ucounts = ucounts; 485 get_user_ns(user_ns); 486 487 rv = down_read_killable(&pernet_ops_rwsem); 488 if (rv < 0) 489 goto put_userns; 490 491 rv = setup_net(net, user_ns); 492 493 up_read(&pernet_ops_rwsem); 494 495 if (rv < 0) { 496put_userns: 497#ifdef CONFIG_KEYS 498 key_remove_domain(net->key_domain); 499#endif 500 put_user_ns(user_ns); 501 net_free(net); 502dec_ucounts: 503 dec_net_namespaces(ucounts); 504 return ERR_PTR(rv); 505 } 506 return net; 507} 508 509/** 510 * net_ns_get_ownership - get sysfs ownership data for @net 511 * @net: network namespace in question (can be NULL) 512 * @uid: kernel user ID for sysfs objects 513 * @gid: kernel group ID for sysfs objects 514 * 515 * Returns the uid/gid pair of root in the user namespace associated with the 516 * given network namespace. 517 */ 518void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid) 519{ 520 if (net) { 521 kuid_t ns_root_uid = make_kuid(net->user_ns, 0); 522 kgid_t ns_root_gid = make_kgid(net->user_ns, 0); 523 524 if (uid_valid(ns_root_uid)) 525 *uid = ns_root_uid; 526 527 if (gid_valid(ns_root_gid)) 528 *gid = ns_root_gid; 529 } else { 530 *uid = GLOBAL_ROOT_UID; 531 *gid = GLOBAL_ROOT_GID; 532 } 533} 534EXPORT_SYMBOL_GPL(net_ns_get_ownership); 535 536static void unhash_nsid(struct net *net, struct net *last) 537{ 538 struct net *tmp; 539 /* This function is only called from cleanup_net() work, 540 * and this work is the only process, that may delete 541 * a net from net_namespace_list. So, when the below 542 * is executing, the list may only grow. Thus, we do not 543 * use for_each_net_rcu() or net_rwsem. 544 */ 545 for_each_net(tmp) { 546 int id; 547 548 spin_lock_bh(&tmp->nsid_lock); 549 id = __peernet2id(tmp, net); 550 if (id >= 0) 551 idr_remove(&tmp->netns_ids, id); 552 spin_unlock_bh(&tmp->nsid_lock); 553 if (id >= 0) 554 rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL, 555 GFP_KERNEL); 556 if (tmp == last) 557 break; 558 } 559 spin_lock_bh(&net->nsid_lock); 560 idr_destroy(&net->netns_ids); 561 spin_unlock_bh(&net->nsid_lock); 562} 563 564static LLIST_HEAD(cleanup_list); 565 566static void cleanup_net(struct work_struct *work) 567{ 568 const struct pernet_operations *ops; 569 struct net *net, *tmp, *last; 570 struct llist_node *net_kill_list; 571 LIST_HEAD(net_exit_list); 572 573 /* Atomically snapshot the list of namespaces to cleanup */ 574 net_kill_list = llist_del_all(&cleanup_list); 575 576 down_read(&pernet_ops_rwsem); 577 578 /* Don't let anyone else find us. */ 579 down_write(&net_rwsem); 580 llist_for_each_entry(net, net_kill_list, cleanup_list) 581 list_del_rcu(&net->list); 582 /* Cache last net. After we unlock rtnl, no one new net 583 * added to net_namespace_list can assign nsid pointer 584 * to a net from net_kill_list (see peernet2id_alloc()). 585 * So, we skip them in unhash_nsid(). 586 * 587 * Note, that unhash_nsid() does not delete nsid links 588 * between net_kill_list's nets, as they've already 589 * deleted from net_namespace_list. But, this would be 590 * useless anyway, as netns_ids are destroyed there. 591 */ 592 last = list_last_entry(&net_namespace_list, struct net, list); 593 up_write(&net_rwsem); 594 595 llist_for_each_entry(net, net_kill_list, cleanup_list) { 596 unhash_nsid(net, last); 597 list_add_tail(&net->exit_list, &net_exit_list); 598 } 599 600 /* Run all of the network namespace pre_exit methods */ 601 list_for_each_entry_reverse(ops, &pernet_list, list) 602 ops_pre_exit_list(ops, &net_exit_list); 603 604 /* 605 * Another CPU might be rcu-iterating the list, wait for it. 606 * This needs to be before calling the exit() notifiers, so 607 * the rcu_barrier() below isn't sufficient alone. 608 * Also the pre_exit() and exit() methods need this barrier. 609 */ 610 synchronize_rcu(); 611 612 /* Run all of the network namespace exit methods */ 613 list_for_each_entry_reverse(ops, &pernet_list, list) 614 ops_exit_list(ops, &net_exit_list); 615 616 /* Free the net generic variables */ 617 list_for_each_entry_reverse(ops, &pernet_list, list) 618 ops_free_list(ops, &net_exit_list); 619 620 up_read(&pernet_ops_rwsem); 621 622 /* Ensure there are no outstanding rcu callbacks using this 623 * network namespace. 624 */ 625 rcu_barrier(); 626 627 /* Finally it is safe to free my network namespace structure */ 628 list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { 629 list_del_init(&net->exit_list); 630 dec_net_namespaces(net->ucounts); 631#ifdef CONFIG_KEYS 632 key_remove_domain(net->key_domain); 633#endif 634 put_user_ns(net->user_ns); 635 net_free(net); 636 } 637} 638 639/** 640 * net_ns_barrier - wait until concurrent net_cleanup_work is done 641 * 642 * cleanup_net runs from work queue and will first remove namespaces 643 * from the global list, then run net exit functions. 644 * 645 * Call this in module exit path to make sure that all netns 646 * ->exit ops have been invoked before the function is removed. 647 */ 648void net_ns_barrier(void) 649{ 650 down_write(&pernet_ops_rwsem); 651 up_write(&pernet_ops_rwsem); 652} 653EXPORT_SYMBOL(net_ns_barrier); 654 655static DECLARE_WORK(net_cleanup_work, cleanup_net); 656 657void __put_net(struct net *net) 658{ 659 ref_tracker_dir_exit(&net->refcnt_tracker); 660 /* Cleanup the network namespace in process context */ 661 if (llist_add(&net->cleanup_list, &cleanup_list)) 662 queue_work(netns_wq, &net_cleanup_work); 663} 664EXPORT_SYMBOL_GPL(__put_net); 665 666/** 667 * get_net_ns - increment the refcount of the network namespace 668 * @ns: common namespace (net) 669 * 670 * Returns the net's common namespace. 671 */ 672struct ns_common *get_net_ns(struct ns_common *ns) 673{ 674 return &get_net(container_of(ns, struct net, ns))->ns; 675} 676EXPORT_SYMBOL_GPL(get_net_ns); 677 678struct net *get_net_ns_by_fd(int fd) 679{ 680 struct fd f = fdget(fd); 681 struct net *net = ERR_PTR(-EINVAL); 682 683 if (!f.file) 684 return ERR_PTR(-EBADF); 685 686 if (proc_ns_file(f.file)) { 687 struct ns_common *ns = get_proc_ns(file_inode(f.file)); 688 if (ns->ops == &netns_operations) 689 net = get_net(container_of(ns, struct net, ns)); 690 } 691 fdput(f); 692 693 return net; 694} 695EXPORT_SYMBOL_GPL(get_net_ns_by_fd); 696#endif 697 698struct net *get_net_ns_by_pid(pid_t pid) 699{ 700 struct task_struct *tsk; 701 struct net *net; 702 703 /* Lookup the network namespace */ 704 net = ERR_PTR(-ESRCH); 705 rcu_read_lock(); 706 tsk = find_task_by_vpid(pid); 707 if (tsk) { 708 struct nsproxy *nsproxy; 709 task_lock(tsk); 710 nsproxy = tsk->nsproxy; 711 if (nsproxy) 712 net = get_net(nsproxy->net_ns); 713 task_unlock(tsk); 714 } 715 rcu_read_unlock(); 716 return net; 717} 718EXPORT_SYMBOL_GPL(get_net_ns_by_pid); 719 720static __net_init int net_ns_net_init(struct net *net) 721{ 722#ifdef CONFIG_NET_NS 723 net->ns.ops = &netns_operations; 724#endif 725 return ns_alloc_inum(&net->ns); 726} 727 728static __net_exit void net_ns_net_exit(struct net *net) 729{ 730 ns_free_inum(&net->ns); 731} 732 733static struct pernet_operations __net_initdata net_ns_ops = { 734 .init = net_ns_net_init, 735 .exit = net_ns_net_exit, 736}; 737 738static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = { 739 [NETNSA_NONE] = { .type = NLA_UNSPEC }, 740 [NETNSA_NSID] = { .type = NLA_S32 }, 741 [NETNSA_PID] = { .type = NLA_U32 }, 742 [NETNSA_FD] = { .type = NLA_U32 }, 743 [NETNSA_TARGET_NSID] = { .type = NLA_S32 }, 744}; 745 746static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, 747 struct netlink_ext_ack *extack) 748{ 749 struct net *net = sock_net(skb->sk); 750 struct nlattr *tb[NETNSA_MAX + 1]; 751 struct nlattr *nla; 752 struct net *peer; 753 int nsid, err; 754 755 err = nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg), tb, 756 NETNSA_MAX, rtnl_net_policy, extack); 757 if (err < 0) 758 return err; 759 if (!tb[NETNSA_NSID]) { 760 NL_SET_ERR_MSG(extack, "nsid is missing"); 761 return -EINVAL; 762 } 763 nsid = nla_get_s32(tb[NETNSA_NSID]); 764 765 if (tb[NETNSA_PID]) { 766 peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID])); 767 nla = tb[NETNSA_PID]; 768 } else if (tb[NETNSA_FD]) { 769 peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD])); 770 nla = tb[NETNSA_FD]; 771 } else { 772 NL_SET_ERR_MSG(extack, "Peer netns reference is missing"); 773 return -EINVAL; 774 } 775 if (IS_ERR(peer)) { 776 NL_SET_BAD_ATTR(extack, nla); 777 NL_SET_ERR_MSG(extack, "Peer netns reference is invalid"); 778 return PTR_ERR(peer); 779 } 780 781 spin_lock_bh(&net->nsid_lock); 782 if (__peernet2id(net, peer) >= 0) { 783 spin_unlock_bh(&net->nsid_lock); 784 err = -EEXIST; 785 NL_SET_BAD_ATTR(extack, nla); 786 NL_SET_ERR_MSG(extack, 787 "Peer netns already has a nsid assigned"); 788 goto out; 789 } 790 791 err = alloc_netid(net, peer, nsid); 792 spin_unlock_bh(&net->nsid_lock); 793 if (err >= 0) { 794 rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, 795 nlh, GFP_KERNEL); 796 err = 0; 797 } else if (err == -ENOSPC && nsid >= 0) { 798 err = -EEXIST; 799 NL_SET_BAD_ATTR(extack, tb[NETNSA_NSID]); 800 NL_SET_ERR_MSG(extack, "The specified nsid is already used"); 801 } 802out: 803 put_net(peer); 804 return err; 805} 806 807static int rtnl_net_get_size(void) 808{ 809 return NLMSG_ALIGN(sizeof(struct rtgenmsg)) 810 + nla_total_size(sizeof(s32)) /* NETNSA_NSID */ 811 + nla_total_size(sizeof(s32)) /* NETNSA_CURRENT_NSID */ 812 ; 813} 814 815struct net_fill_args { 816 u32 portid; 817 u32 seq; 818 int flags; 819 int cmd; 820 int nsid; 821 bool add_ref; 822 int ref_nsid; 823}; 824 825static int rtnl_net_fill(struct sk_buff *skb, struct net_fill_args *args) 826{ 827 struct nlmsghdr *nlh; 828 struct rtgenmsg *rth; 829 830 nlh = nlmsg_put(skb, args->portid, args->seq, args->cmd, sizeof(*rth), 831 args->flags); 832 if (!nlh) 833 return -EMSGSIZE; 834 835 rth = nlmsg_data(nlh); 836 rth->rtgen_family = AF_UNSPEC; 837 838 if (nla_put_s32(skb, NETNSA_NSID, args->nsid)) 839 goto nla_put_failure; 840 841 if (args->add_ref && 842 nla_put_s32(skb, NETNSA_CURRENT_NSID, args->ref_nsid)) 843 goto nla_put_failure; 844 845 nlmsg_end(skb, nlh); 846 return 0; 847 848nla_put_failure: 849 nlmsg_cancel(skb, nlh); 850 return -EMSGSIZE; 851} 852 853static int rtnl_net_valid_getid_req(struct sk_buff *skb, 854 const struct nlmsghdr *nlh, 855 struct nlattr **tb, 856 struct netlink_ext_ack *extack) 857{ 858 int i, err; 859 860 if (!netlink_strict_get_check(skb)) 861 return nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg), 862 tb, NETNSA_MAX, rtnl_net_policy, 863 extack); 864 865 err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb, 866 NETNSA_MAX, rtnl_net_policy, 867 extack); 868 if (err) 869 return err; 870 871 for (i = 0; i <= NETNSA_MAX; i++) { 872 if (!tb[i]) 873 continue; 874 875 switch (i) { 876 case NETNSA_PID: 877 case NETNSA_FD: 878 case NETNSA_NSID: 879 case NETNSA_TARGET_NSID: 880 break; 881 default: 882 NL_SET_ERR_MSG(extack, "Unsupported attribute in peer netns getid request"); 883 return -EINVAL; 884 } 885 } 886 887 return 0; 888} 889 890static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh, 891 struct netlink_ext_ack *extack) 892{ 893 struct net *net = sock_net(skb->sk); 894 struct nlattr *tb[NETNSA_MAX + 1]; 895 struct net_fill_args fillargs = { 896 .portid = NETLINK_CB(skb).portid, 897 .seq = nlh->nlmsg_seq, 898 .cmd = RTM_NEWNSID, 899 }; 900 struct net *peer, *target = net; 901 struct nlattr *nla; 902 struct sk_buff *msg; 903 int err; 904 905 err = rtnl_net_valid_getid_req(skb, nlh, tb, extack); 906 if (err < 0) 907 return err; 908 if (tb[NETNSA_PID]) { 909 peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID])); 910 nla = tb[NETNSA_PID]; 911 } else if (tb[NETNSA_FD]) { 912 peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD])); 913 nla = tb[NETNSA_FD]; 914 } else if (tb[NETNSA_NSID]) { 915 peer = get_net_ns_by_id(net, nla_get_s32(tb[NETNSA_NSID])); 916 if (!peer) 917 peer = ERR_PTR(-ENOENT); 918 nla = tb[NETNSA_NSID]; 919 } else { 920 NL_SET_ERR_MSG(extack, "Peer netns reference is missing"); 921 return -EINVAL; 922 } 923 924 if (IS_ERR(peer)) { 925 NL_SET_BAD_ATTR(extack, nla); 926 NL_SET_ERR_MSG(extack, "Peer netns reference is invalid"); 927 return PTR_ERR(peer); 928 } 929 930 if (tb[NETNSA_TARGET_NSID]) { 931 int id = nla_get_s32(tb[NETNSA_TARGET_NSID]); 932 933 target = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, id); 934 if (IS_ERR(target)) { 935 NL_SET_BAD_ATTR(extack, tb[NETNSA_TARGET_NSID]); 936 NL_SET_ERR_MSG(extack, 937 "Target netns reference is invalid"); 938 err = PTR_ERR(target); 939 goto out; 940 } 941 fillargs.add_ref = true; 942 fillargs.ref_nsid = peernet2id(net, peer); 943 } 944 945 msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL); 946 if (!msg) { 947 err = -ENOMEM; 948 goto out; 949 } 950 951 fillargs.nsid = peernet2id(target, peer); 952 err = rtnl_net_fill(msg, &fillargs); 953 if (err < 0) 954 goto err_out; 955 956 err = rtnl_unicast(msg, net, NETLINK_CB(skb).portid); 957 goto out; 958 959err_out: 960 nlmsg_free(msg); 961out: 962 if (fillargs.add_ref) 963 put_net(target); 964 put_net(peer); 965 return err; 966} 967 968struct rtnl_net_dump_cb { 969 struct net *tgt_net; 970 struct net *ref_net; 971 struct sk_buff *skb; 972 struct net_fill_args fillargs; 973 int idx; 974 int s_idx; 975}; 976 977/* Runs in RCU-critical section. */ 978static int rtnl_net_dumpid_one(int id, void *peer, void *data) 979{ 980 struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data; 981 int ret; 982 983 if (net_cb->idx < net_cb->s_idx) 984 goto cont; 985 986 net_cb->fillargs.nsid = id; 987 if (net_cb->fillargs.add_ref) 988 net_cb->fillargs.ref_nsid = __peernet2id(net_cb->ref_net, peer); 989 ret = rtnl_net_fill(net_cb->skb, &net_cb->fillargs); 990 if (ret < 0) 991 return ret; 992 993cont: 994 net_cb->idx++; 995 return 0; 996} 997 998static int rtnl_valid_dump_net_req(const struct nlmsghdr *nlh, struct sock *sk, 999 struct rtnl_net_dump_cb *net_cb, 1000 struct netlink_callback *cb) 1001{ 1002 struct netlink_ext_ack *extack = cb->extack; 1003 struct nlattr *tb[NETNSA_MAX + 1]; 1004 int err, i; 1005 1006 err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb, 1007 NETNSA_MAX, rtnl_net_policy, 1008 extack); 1009 if (err < 0) 1010 return err; 1011 1012 for (i = 0; i <= NETNSA_MAX; i++) { 1013 if (!tb[i]) 1014 continue; 1015 1016 if (i == NETNSA_TARGET_NSID) { 1017 struct net *net; 1018 1019 net = rtnl_get_net_ns_capable(sk, nla_get_s32(tb[i])); 1020 if (IS_ERR(net)) { 1021 NL_SET_BAD_ATTR(extack, tb[i]); 1022 NL_SET_ERR_MSG(extack, 1023 "Invalid target network namespace id"); 1024 return PTR_ERR(net); 1025 } 1026 net_cb->fillargs.add_ref = true; 1027 net_cb->ref_net = net_cb->tgt_net; 1028 net_cb->tgt_net = net; 1029 } else { 1030 NL_SET_BAD_ATTR(extack, tb[i]); 1031 NL_SET_ERR_MSG(extack, 1032 "Unsupported attribute in dump request"); 1033 return -EINVAL; 1034 } 1035 } 1036 1037 return 0; 1038} 1039 1040static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb) 1041{ 1042 struct rtnl_net_dump_cb net_cb = { 1043 .tgt_net = sock_net(skb->sk), 1044 .skb = skb, 1045 .fillargs = { 1046 .portid = NETLINK_CB(cb->skb).portid, 1047 .seq = cb->nlh->nlmsg_seq, 1048 .flags = NLM_F_MULTI, 1049 .cmd = RTM_NEWNSID, 1050 }, 1051 .idx = 0, 1052 .s_idx = cb->args[0], 1053 }; 1054 int err = 0; 1055 1056 if (cb->strict_check) { 1057 err = rtnl_valid_dump_net_req(cb->nlh, skb->sk, &net_cb, cb); 1058 if (err < 0) 1059 goto end; 1060 } 1061 1062 rcu_read_lock(); 1063 idr_for_each(&net_cb.tgt_net->netns_ids, rtnl_net_dumpid_one, &net_cb); 1064 rcu_read_unlock(); 1065 1066 cb->args[0] = net_cb.idx; 1067end: 1068 if (net_cb.fillargs.add_ref) 1069 put_net(net_cb.tgt_net); 1070 return err < 0 ? err : skb->len; 1071} 1072 1073static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, 1074 struct nlmsghdr *nlh, gfp_t gfp) 1075{ 1076 struct net_fill_args fillargs = { 1077 .portid = portid, 1078 .seq = nlh ? nlh->nlmsg_seq : 0, 1079 .cmd = cmd, 1080 .nsid = id, 1081 }; 1082 struct sk_buff *msg; 1083 int err = -ENOMEM; 1084 1085 msg = nlmsg_new(rtnl_net_get_size(), gfp); 1086 if (!msg) 1087 goto out; 1088 1089 err = rtnl_net_fill(msg, &fillargs); 1090 if (err < 0) 1091 goto err_out; 1092 1093 rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, gfp); 1094 return; 1095 1096err_out: 1097 nlmsg_free(msg); 1098out: 1099 rtnl_set_sk_err(net, RTNLGRP_NSID, err); 1100} 1101 1102void __init net_ns_init(void) 1103{ 1104 struct net_generic *ng; 1105 1106#ifdef CONFIG_NET_NS 1107 net_cachep = kmem_cache_create("net_namespace", sizeof(struct net), 1108 SMP_CACHE_BYTES, 1109 SLAB_PANIC|SLAB_ACCOUNT, NULL); 1110 1111 /* Create workqueue for cleanup */ 1112 netns_wq = create_singlethread_workqueue("netns"); 1113 if (!netns_wq) 1114 panic("Could not create netns workq"); 1115#endif 1116 1117 ng = net_alloc_generic(); 1118 if (!ng) 1119 panic("Could not allocate generic netns"); 1120 1121 rcu_assign_pointer(init_net.gen, ng); 1122 1123#ifdef CONFIG_KEYS 1124 init_net.key_domain = &init_net_key_domain; 1125#endif 1126 down_write(&pernet_ops_rwsem); 1127 preinit_net(&init_net); 1128 if (setup_net(&init_net, &init_user_ns)) 1129 panic("Could not setup the initial network namespace"); 1130 1131 init_net_initialized = true; 1132 up_write(&pernet_ops_rwsem); 1133 1134 if (register_pernet_subsys(&net_ns_ops)) 1135 panic("Could not register network namespace subsystems"); 1136 1137 rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL, 1138 RTNL_FLAG_DOIT_UNLOCKED); 1139 rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid, 1140 RTNL_FLAG_DOIT_UNLOCKED); 1141} 1142 1143static void free_exit_list(struct pernet_operations *ops, struct list_head *net_exit_list) 1144{ 1145 ops_pre_exit_list(ops, net_exit_list); 1146 synchronize_rcu(); 1147 ops_exit_list(ops, net_exit_list); 1148 ops_free_list(ops, net_exit_list); 1149} 1150 1151#ifdef CONFIG_NET_NS 1152static int __register_pernet_operations(struct list_head *list, 1153 struct pernet_operations *ops) 1154{ 1155 struct net *net; 1156 int error; 1157 LIST_HEAD(net_exit_list); 1158 1159 list_add_tail(&ops->list, list); 1160 if (ops->init || (ops->id && ops->size)) { 1161 /* We held write locked pernet_ops_rwsem, and parallel 1162 * setup_net() and cleanup_net() are not possible. 1163 */ 1164 for_each_net(net) { 1165 error = ops_init(ops, net); 1166 if (error) 1167 goto out_undo; 1168 list_add_tail(&net->exit_list, &net_exit_list); 1169 } 1170 } 1171 return 0; 1172 1173out_undo: 1174 /* If I have an error cleanup all namespaces I initialized */ 1175 list_del(&ops->list); 1176 free_exit_list(ops, &net_exit_list); 1177 return error; 1178} 1179 1180static void __unregister_pernet_operations(struct pernet_operations *ops) 1181{ 1182 struct net *net; 1183 LIST_HEAD(net_exit_list); 1184 1185 list_del(&ops->list); 1186 /* See comment in __register_pernet_operations() */ 1187 for_each_net(net) 1188 list_add_tail(&net->exit_list, &net_exit_list); 1189 1190 free_exit_list(ops, &net_exit_list); 1191} 1192 1193#else 1194 1195static int __register_pernet_operations(struct list_head *list, 1196 struct pernet_operations *ops) 1197{ 1198 if (!init_net_initialized) { 1199 list_add_tail(&ops->list, list); 1200 return 0; 1201 } 1202 1203 return ops_init(ops, &init_net); 1204} 1205 1206static void __unregister_pernet_operations(struct pernet_operations *ops) 1207{ 1208 if (!init_net_initialized) { 1209 list_del(&ops->list); 1210 } else { 1211 LIST_HEAD(net_exit_list); 1212 list_add(&init_net.exit_list, &net_exit_list); 1213 free_exit_list(ops, &net_exit_list); 1214 } 1215} 1216 1217#endif /* CONFIG_NET_NS */ 1218 1219static DEFINE_IDA(net_generic_ids); 1220 1221static int register_pernet_operations(struct list_head *list, 1222 struct pernet_operations *ops) 1223{ 1224 int error; 1225 1226 if (ops->id) { 1227 error = ida_alloc_min(&net_generic_ids, MIN_PERNET_OPS_ID, 1228 GFP_KERNEL); 1229 if (error < 0) 1230 return error; 1231 *ops->id = error; 1232 max_gen_ptrs = max(max_gen_ptrs, *ops->id + 1); 1233 } 1234 error = __register_pernet_operations(list, ops); 1235 if (error) { 1236 rcu_barrier(); 1237 if (ops->id) 1238 ida_free(&net_generic_ids, *ops->id); 1239 } 1240 1241 return error; 1242} 1243 1244static void unregister_pernet_operations(struct pernet_operations *ops) 1245{ 1246 __unregister_pernet_operations(ops); 1247 rcu_barrier(); 1248 if (ops->id) 1249 ida_free(&net_generic_ids, *ops->id); 1250} 1251 1252/** 1253 * register_pernet_subsys - register a network namespace subsystem 1254 * @ops: pernet operations structure for the subsystem 1255 * 1256 * Register a subsystem which has init and exit functions 1257 * that are called when network namespaces are created and 1258 * destroyed respectively. 1259 * 1260 * When registered all network namespace init functions are 1261 * called for every existing network namespace. Allowing kernel 1262 * modules to have a race free view of the set of network namespaces. 1263 * 1264 * When a new network namespace is created all of the init 1265 * methods are called in the order in which they were registered. 1266 * 1267 * When a network namespace is destroyed all of the exit methods 1268 * are called in the reverse of the order with which they were 1269 * registered. 1270 */ 1271int register_pernet_subsys(struct pernet_operations *ops) 1272{ 1273 int error; 1274 down_write(&pernet_ops_rwsem); 1275 error = register_pernet_operations(first_device, ops); 1276 up_write(&pernet_ops_rwsem); 1277 return error; 1278} 1279EXPORT_SYMBOL_GPL(register_pernet_subsys); 1280 1281/** 1282 * unregister_pernet_subsys - unregister a network namespace subsystem 1283 * @ops: pernet operations structure to manipulate 1284 * 1285 * Remove the pernet operations structure from the list to be 1286 * used when network namespaces are created or destroyed. In 1287 * addition run the exit method for all existing network 1288 * namespaces. 1289 */ 1290void unregister_pernet_subsys(struct pernet_operations *ops) 1291{ 1292 down_write(&pernet_ops_rwsem); 1293 unregister_pernet_operations(ops); 1294 up_write(&pernet_ops_rwsem); 1295} 1296EXPORT_SYMBOL_GPL(unregister_pernet_subsys); 1297 1298/** 1299 * register_pernet_device - register a network namespace device 1300 * @ops: pernet operations structure for the subsystem 1301 * 1302 * Register a device which has init and exit functions 1303 * that are called when network namespaces are created and 1304 * destroyed respectively. 1305 * 1306 * When registered all network namespace init functions are 1307 * called for every existing network namespace. Allowing kernel 1308 * modules to have a race free view of the set of network namespaces. 1309 * 1310 * When a new network namespace is created all of the init 1311 * methods are called in the order in which they were registered. 1312 * 1313 * When a network namespace is destroyed all of the exit methods 1314 * are called in the reverse of the order with which they were 1315 * registered. 1316 */ 1317int register_pernet_device(struct pernet_operations *ops) 1318{ 1319 int error; 1320 down_write(&pernet_ops_rwsem); 1321 error = register_pernet_operations(&pernet_list, ops); 1322 if (!error && (first_device == &pernet_list)) 1323 first_device = &ops->list; 1324 up_write(&pernet_ops_rwsem); 1325 return error; 1326} 1327EXPORT_SYMBOL_GPL(register_pernet_device); 1328 1329/** 1330 * unregister_pernet_device - unregister a network namespace netdevice 1331 * @ops: pernet operations structure to manipulate 1332 * 1333 * Remove the pernet operations structure from the list to be 1334 * used when network namespaces are created or destroyed. In 1335 * addition run the exit method for all existing network 1336 * namespaces. 1337 */ 1338void unregister_pernet_device(struct pernet_operations *ops) 1339{ 1340 down_write(&pernet_ops_rwsem); 1341 if (&ops->list == first_device) 1342 first_device = first_device->next; 1343 unregister_pernet_operations(ops); 1344 up_write(&pernet_ops_rwsem); 1345} 1346EXPORT_SYMBOL_GPL(unregister_pernet_device); 1347 1348#ifdef CONFIG_NET_NS 1349static struct ns_common *netns_get(struct task_struct *task) 1350{ 1351 struct net *net = NULL; 1352 struct nsproxy *nsproxy; 1353 1354 task_lock(task); 1355 nsproxy = task->nsproxy; 1356 if (nsproxy) 1357 net = get_net(nsproxy->net_ns); 1358 task_unlock(task); 1359 1360 return net ? &net->ns : NULL; 1361} 1362 1363static inline struct net *to_net_ns(struct ns_common *ns) 1364{ 1365 return container_of(ns, struct net, ns); 1366} 1367 1368static void netns_put(struct ns_common *ns) 1369{ 1370 put_net(to_net_ns(ns)); 1371} 1372 1373static int netns_install(struct nsset *nsset, struct ns_common *ns) 1374{ 1375 struct nsproxy *nsproxy = nsset->nsproxy; 1376 struct net *net = to_net_ns(ns); 1377 1378 if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) || 1379 !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) 1380 return -EPERM; 1381 1382 put_net(nsproxy->net_ns); 1383 nsproxy->net_ns = get_net(net); 1384 return 0; 1385} 1386 1387static struct user_namespace *netns_owner(struct ns_common *ns) 1388{ 1389 return to_net_ns(ns)->user_ns; 1390} 1391 1392const struct proc_ns_operations netns_operations = { 1393 .name = "net", 1394 .type = CLONE_NEWNET, 1395 .get = netns_get, 1396 .put = netns_put, 1397 .install = netns_install, 1398 .owner = netns_owner, 1399}; 1400#endif 1401