1// SPDX-License-Identifier: GPL-2.0-or-later 2/* 3 * NETLINK Kernel-user communication protocol. 4 * 5 * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> 6 * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> 7 * Patrick McHardy <kaber@trash.net> 8 * 9 * Tue Jun 26 14:36:48 MEST 2001 Herbert "herp" Rosmanith 10 * added netlink_proto_exit 11 * Tue Jan 22 18:32:44 BRST 2002 Arnaldo C. de Melo <acme@conectiva.com.br> 12 * use nlk_sk, as sk->protinfo is on a diet 8) 13 * Fri Jul 22 19:51:12 MEST 2005 Harald Welte <laforge@gnumonks.org> 14 * - inc module use count of module that owns 15 * the kernel socket in case userspace opens 16 * socket of same protocol 17 * - remove all module support, since netlink is 18 * mandatory if CONFIG_NET=y these days 19 */ 20 21#include <linux/module.h> 22 23#include <linux/bpf.h> 24#include <linux/capability.h> 25#include <linux/kernel.h> 26#include <linux/filter.h> 27#include <linux/init.h> 28#include <linux/signal.h> 29#include <linux/sched.h> 30#include <linux/errno.h> 31#include <linux/string.h> 32#include <linux/stat.h> 33#include <linux/socket.h> 34#include <linux/un.h> 35#include <linux/fcntl.h> 36#include <linux/termios.h> 37#include <linux/sockios.h> 38#include <linux/net.h> 39#include <linux/fs.h> 40#include <linux/slab.h> 41#include <linux/uaccess.h> 42#include <linux/skbuff.h> 43#include <linux/netdevice.h> 44#include <linux/rtnetlink.h> 45#include <linux/proc_fs.h> 46#include <linux/seq_file.h> 47#include <linux/notifier.h> 48#include <linux/security.h> 49#include <linux/jhash.h> 50#include <linux/jiffies.h> 51#include <linux/random.h> 52#include <linux/bitops.h> 53#include <linux/mm.h> 54#include <linux/types.h> 55#include <linux/audit.h> 56#include <linux/mutex.h> 57#include <linux/vmalloc.h> 58#include <linux/if_arp.h> 59#include <linux/rhashtable.h> 60#include <asm/cacheflush.h> 61#include <linux/hash.h> 62#include <linux/genetlink.h> 63#include <linux/net_namespace.h> 64#include <linux/nospec.h> 65#include <linux/btf_ids.h> 66 67#include <net/net_namespace.h> 68#include <net/netns/generic.h> 69#include <net/sock.h> 70#include <net/scm.h> 71#include <net/netlink.h> 72#define CREATE_TRACE_POINTS 73#include <trace/events/netlink.h> 74 75#include "af_netlink.h" 76 77struct listeners { 78 struct rcu_head rcu; 79 unsigned long masks[]; 80}; 81 82/* state bits */ 83#define NETLINK_S_CONGESTED 0x0 84 85static inline int netlink_is_kernel(struct sock *sk) 86{ 87 return nlk_test_bit(KERNEL_SOCKET, sk); 88} 89 90struct netlink_table *nl_table __read_mostly; 91EXPORT_SYMBOL_GPL(nl_table); 92 93static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait); 94 95static struct lock_class_key nlk_cb_mutex_keys[MAX_LINKS]; 96 97static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = { 98 "nlk_cb_mutex-ROUTE", 99 "nlk_cb_mutex-1", 100 "nlk_cb_mutex-USERSOCK", 101 "nlk_cb_mutex-FIREWALL", 102 "nlk_cb_mutex-SOCK_DIAG", 103 "nlk_cb_mutex-NFLOG", 104 "nlk_cb_mutex-XFRM", 105 "nlk_cb_mutex-SELINUX", 106 "nlk_cb_mutex-ISCSI", 107 "nlk_cb_mutex-AUDIT", 108 "nlk_cb_mutex-FIB_LOOKUP", 109 "nlk_cb_mutex-CONNECTOR", 110 "nlk_cb_mutex-NETFILTER", 111 "nlk_cb_mutex-IP6_FW", 112 "nlk_cb_mutex-DNRTMSG", 113 "nlk_cb_mutex-KOBJECT_UEVENT", 114 "nlk_cb_mutex-GENERIC", 115 "nlk_cb_mutex-17", 116 "nlk_cb_mutex-SCSITRANSPORT", 117 "nlk_cb_mutex-ECRYPTFS", 118 "nlk_cb_mutex-RDMA", 119 "nlk_cb_mutex-CRYPTO", 120 "nlk_cb_mutex-SMC", 121 "nlk_cb_mutex-23", 122 "nlk_cb_mutex-24", 123 "nlk_cb_mutex-25", 124 "nlk_cb_mutex-26", 125 "nlk_cb_mutex-27", 126 "nlk_cb_mutex-28", 127 "nlk_cb_mutex-29", 128 "nlk_cb_mutex-30", 129 "nlk_cb_mutex-31", 130 "nlk_cb_mutex-MAX_LINKS" 131}; 132 133static int netlink_dump(struct sock *sk); 134 135/* nl_table locking explained: 136 * Lookup and traversal are protected with an RCU read-side lock. Insertion 137 * and removal are protected with per bucket lock while using RCU list 138 * modification primitives and may run in parallel to RCU protected lookups. 139 * Destruction of the Netlink socket may only occur *after* nl_table_lock has 140 * been acquired * either during or after the socket has been removed from 141 * the list and after an RCU grace period. 142 */ 143DEFINE_RWLOCK(nl_table_lock); 144EXPORT_SYMBOL_GPL(nl_table_lock); 145static atomic_t nl_table_users = ATOMIC_INIT(0); 146 147#define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock)); 148 149static BLOCKING_NOTIFIER_HEAD(netlink_chain); 150 151 152static const struct rhashtable_params netlink_rhashtable_params; 153 154void do_trace_netlink_extack(const char *msg) 155{ 156 trace_netlink_extack(msg); 157} 158EXPORT_SYMBOL(do_trace_netlink_extack); 159 160static inline u32 netlink_group_mask(u32 group) 161{ 162 if (group > 32) 163 return 0; 164 return group ? 1 << (group - 1) : 0; 165} 166 167static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, 168 gfp_t gfp_mask) 169{ 170 unsigned int len = skb->len; 171 struct sk_buff *new; 172 173 new = alloc_skb(len, gfp_mask); 174 if (new == NULL) 175 return NULL; 176 177 NETLINK_CB(new).portid = NETLINK_CB(skb).portid; 178 NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group; 179 NETLINK_CB(new).creds = NETLINK_CB(skb).creds; 180 181 skb_put_data(new, skb->data, len); 182 return new; 183} 184 185static unsigned int netlink_tap_net_id; 186 187struct netlink_tap_net { 188 struct list_head netlink_tap_all; 189 struct mutex netlink_tap_lock; 190}; 191 192int netlink_add_tap(struct netlink_tap *nt) 193{ 194 struct net *net = dev_net(nt->dev); 195 struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); 196 197 if (unlikely(nt->dev->type != ARPHRD_NETLINK)) 198 return -EINVAL; 199 200 mutex_lock(&nn->netlink_tap_lock); 201 list_add_rcu(&nt->list, &nn->netlink_tap_all); 202 mutex_unlock(&nn->netlink_tap_lock); 203 204 __module_get(nt->module); 205 206 return 0; 207} 208EXPORT_SYMBOL_GPL(netlink_add_tap); 209 210static int __netlink_remove_tap(struct netlink_tap *nt) 211{ 212 struct net *net = dev_net(nt->dev); 213 struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); 214 bool found = false; 215 struct netlink_tap *tmp; 216 217 mutex_lock(&nn->netlink_tap_lock); 218 219 list_for_each_entry(tmp, &nn->netlink_tap_all, list) { 220 if (nt == tmp) { 221 list_del_rcu(&nt->list); 222 found = true; 223 goto out; 224 } 225 } 226 227 pr_warn("__netlink_remove_tap: %p not found\n", nt); 228out: 229 mutex_unlock(&nn->netlink_tap_lock); 230 231 if (found) 232 module_put(nt->module); 233 234 return found ? 0 : -ENODEV; 235} 236 237int netlink_remove_tap(struct netlink_tap *nt) 238{ 239 int ret; 240 241 ret = __netlink_remove_tap(nt); 242 synchronize_net(); 243 244 return ret; 245} 246EXPORT_SYMBOL_GPL(netlink_remove_tap); 247 248static __net_init int netlink_tap_init_net(struct net *net) 249{ 250 struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); 251 252 INIT_LIST_HEAD(&nn->netlink_tap_all); 253 mutex_init(&nn->netlink_tap_lock); 254 return 0; 255} 256 257static struct pernet_operations netlink_tap_net_ops = { 258 .init = netlink_tap_init_net, 259 .id = &netlink_tap_net_id, 260 .size = sizeof(struct netlink_tap_net), 261}; 262 263static bool netlink_filter_tap(const struct sk_buff *skb) 264{ 265 struct sock *sk = skb->sk; 266 267 /* We take the more conservative approach and 268 * whitelist socket protocols that may pass. 269 */ 270 switch (sk->sk_protocol) { 271 case NETLINK_ROUTE: 272 case NETLINK_USERSOCK: 273 case NETLINK_SOCK_DIAG: 274 case NETLINK_NFLOG: 275 case NETLINK_XFRM: 276 case NETLINK_FIB_LOOKUP: 277 case NETLINK_NETFILTER: 278 case NETLINK_GENERIC: 279 return true; 280 } 281 282 return false; 283} 284 285static int __netlink_deliver_tap_skb(struct sk_buff *skb, 286 struct net_device *dev) 287{ 288 struct sk_buff *nskb; 289 struct sock *sk = skb->sk; 290 int ret = -ENOMEM; 291 292 if (!net_eq(dev_net(dev), sock_net(sk))) 293 return 0; 294 295 dev_hold(dev); 296 297 if (is_vmalloc_addr(skb->head)) 298 nskb = netlink_to_full_skb(skb, GFP_ATOMIC); 299 else 300 nskb = skb_clone(skb, GFP_ATOMIC); 301 if (nskb) { 302 nskb->dev = dev; 303 nskb->protocol = htons((u16) sk->sk_protocol); 304 nskb->pkt_type = netlink_is_kernel(sk) ? 305 PACKET_KERNEL : PACKET_USER; 306 skb_reset_network_header(nskb); 307 ret = dev_queue_xmit(nskb); 308 if (unlikely(ret > 0)) 309 ret = net_xmit_errno(ret); 310 } 311 312 dev_put(dev); 313 return ret; 314} 315 316static void __netlink_deliver_tap(struct sk_buff *skb, struct netlink_tap_net *nn) 317{ 318 int ret; 319 struct netlink_tap *tmp; 320 321 if (!netlink_filter_tap(skb)) 322 return; 323 324 list_for_each_entry_rcu(tmp, &nn->netlink_tap_all, list) { 325 ret = __netlink_deliver_tap_skb(skb, tmp->dev); 326 if (unlikely(ret)) 327 break; 328 } 329} 330 331static void netlink_deliver_tap(struct net *net, struct sk_buff *skb) 332{ 333 struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); 334 335 rcu_read_lock(); 336 337 if (unlikely(!list_empty(&nn->netlink_tap_all))) 338 __netlink_deliver_tap(skb, nn); 339 340 rcu_read_unlock(); 341} 342 343static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src, 344 struct sk_buff *skb) 345{ 346 if (!(netlink_is_kernel(dst) && netlink_is_kernel(src))) 347 netlink_deliver_tap(sock_net(dst), skb); 348} 349 350static void netlink_overrun(struct sock *sk) 351{ 352 if (!nlk_test_bit(RECV_NO_ENOBUFS, sk)) { 353 if (!test_and_set_bit(NETLINK_S_CONGESTED, 354 &nlk_sk(sk)->state)) { 355 WRITE_ONCE(sk->sk_err, ENOBUFS); 356 sk_error_report(sk); 357 } 358 } 359 atomic_inc(&sk->sk_drops); 360} 361 362static void netlink_rcv_wake(struct sock *sk) 363{ 364 struct netlink_sock *nlk = nlk_sk(sk); 365 366 if (skb_queue_empty_lockless(&sk->sk_receive_queue)) 367 clear_bit(NETLINK_S_CONGESTED, &nlk->state); 368 if (!test_bit(NETLINK_S_CONGESTED, &nlk->state)) 369 wake_up_interruptible(&nlk->wait); 370} 371 372static void netlink_skb_destructor(struct sk_buff *skb) 373{ 374 if (is_vmalloc_addr(skb->head)) { 375 if (!skb->cloned || 376 !atomic_dec_return(&(skb_shinfo(skb)->dataref))) 377 vfree_atomic(skb->head); 378 379 skb->head = NULL; 380 } 381 if (skb->sk != NULL) 382 sock_rfree(skb); 383} 384 385static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) 386{ 387 WARN_ON(skb->sk != NULL); 388 skb->sk = sk; 389 skb->destructor = netlink_skb_destructor; 390 atomic_add(skb->truesize, &sk->sk_rmem_alloc); 391 sk_mem_charge(sk, skb->truesize); 392} 393 394static void netlink_sock_destruct(struct sock *sk) 395{ 396 struct netlink_sock *nlk = nlk_sk(sk); 397 398 if (nlk->cb_running) { 399 if (nlk->cb.done) 400 nlk->cb.done(&nlk->cb); 401 module_put(nlk->cb.module); 402 kfree_skb(nlk->cb.skb); 403 } 404 405 skb_queue_purge(&sk->sk_receive_queue); 406 407 if (!sock_flag(sk, SOCK_DEAD)) { 408 printk(KERN_ERR "Freeing alive netlink socket %p\n", sk); 409 return; 410 } 411 412 WARN_ON(atomic_read(&sk->sk_rmem_alloc)); 413 WARN_ON(refcount_read(&sk->sk_wmem_alloc)); 414 WARN_ON(nlk_sk(sk)->groups); 415} 416 417static void netlink_sock_destruct_work(struct work_struct *work) 418{ 419 struct netlink_sock *nlk = container_of(work, struct netlink_sock, 420 work); 421 422 sk_free(&nlk->sk); 423} 424 425/* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on 426 * SMP. Look, when several writers sleep and reader wakes them up, all but one 427 * immediately hit write lock and grab all the cpus. Exclusive sleep solves 428 * this, _but_ remember, it adds useless work on UP machines. 429 */ 430 431void netlink_table_grab(void) 432 __acquires(nl_table_lock) 433{ 434 might_sleep(); 435 436 write_lock_irq(&nl_table_lock); 437 438 if (atomic_read(&nl_table_users)) { 439 DECLARE_WAITQUEUE(wait, current); 440 441 add_wait_queue_exclusive(&nl_table_wait, &wait); 442 for (;;) { 443 set_current_state(TASK_UNINTERRUPTIBLE); 444 if (atomic_read(&nl_table_users) == 0) 445 break; 446 write_unlock_irq(&nl_table_lock); 447 schedule(); 448 write_lock_irq(&nl_table_lock); 449 } 450 451 __set_current_state(TASK_RUNNING); 452 remove_wait_queue(&nl_table_wait, &wait); 453 } 454} 455 456void netlink_table_ungrab(void) 457 __releases(nl_table_lock) 458{ 459 write_unlock_irq(&nl_table_lock); 460 wake_up(&nl_table_wait); 461} 462 463static inline void 464netlink_lock_table(void) 465{ 466 unsigned long flags; 467 468 /* read_lock() synchronizes us to netlink_table_grab */ 469 470 read_lock_irqsave(&nl_table_lock, flags); 471 atomic_inc(&nl_table_users); 472 read_unlock_irqrestore(&nl_table_lock, flags); 473} 474 475static inline void 476netlink_unlock_table(void) 477{ 478 if (atomic_dec_and_test(&nl_table_users)) 479 wake_up(&nl_table_wait); 480} 481 482struct netlink_compare_arg 483{ 484 possible_net_t pnet; 485 u32 portid; 486}; 487 488/* Doing sizeof directly may yield 4 extra bytes on 64-bit. */ 489#define netlink_compare_arg_len \ 490 (offsetof(struct netlink_compare_arg, portid) + sizeof(u32)) 491 492static inline int netlink_compare(struct rhashtable_compare_arg *arg, 493 const void *ptr) 494{ 495 const struct netlink_compare_arg *x = arg->key; 496 const struct netlink_sock *nlk = ptr; 497 498 return nlk->portid != x->portid || 499 !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet)); 500} 501 502static void netlink_compare_arg_init(struct netlink_compare_arg *arg, 503 struct net *net, u32 portid) 504{ 505 memset(arg, 0, sizeof(*arg)); 506 write_pnet(&arg->pnet, net); 507 arg->portid = portid; 508} 509 510static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid, 511 struct net *net) 512{ 513 struct netlink_compare_arg arg; 514 515 netlink_compare_arg_init(&arg, net, portid); 516 return rhashtable_lookup_fast(&table->hash, &arg, 517 netlink_rhashtable_params); 518} 519 520static int __netlink_insert(struct netlink_table *table, struct sock *sk) 521{ 522 struct netlink_compare_arg arg; 523 524 netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid); 525 return rhashtable_lookup_insert_key(&table->hash, &arg, 526 &nlk_sk(sk)->node, 527 netlink_rhashtable_params); 528} 529 530static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) 531{ 532 struct netlink_table *table = &nl_table[protocol]; 533 struct sock *sk; 534 535 rcu_read_lock(); 536 sk = __netlink_lookup(table, portid, net); 537 if (sk) 538 sock_hold(sk); 539 rcu_read_unlock(); 540 541 return sk; 542} 543 544static const struct proto_ops netlink_ops; 545 546static void 547netlink_update_listeners(struct sock *sk) 548{ 549 struct netlink_table *tbl = &nl_table[sk->sk_protocol]; 550 unsigned long mask; 551 unsigned int i; 552 struct listeners *listeners; 553 554 listeners = nl_deref_protected(tbl->listeners); 555 if (!listeners) 556 return; 557 558 for (i = 0; i < NLGRPLONGS(tbl->groups); i++) { 559 mask = 0; 560 sk_for_each_bound(sk, &tbl->mc_list) { 561 if (i < NLGRPLONGS(nlk_sk(sk)->ngroups)) 562 mask |= nlk_sk(sk)->groups[i]; 563 } 564 listeners->masks[i] = mask; 565 } 566 /* this function is only called with the netlink table "grabbed", which 567 * makes sure updates are visible before bind or setsockopt return. */ 568} 569 570static int netlink_insert(struct sock *sk, u32 portid) 571{ 572 struct netlink_table *table = &nl_table[sk->sk_protocol]; 573 int err; 574 575 lock_sock(sk); 576 577 err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY; 578 if (nlk_sk(sk)->bound) 579 goto err; 580 581 /* portid can be read locklessly from netlink_getname(). */ 582 WRITE_ONCE(nlk_sk(sk)->portid, portid); 583 584 sock_hold(sk); 585 586 err = __netlink_insert(table, sk); 587 if (err) { 588 /* In case the hashtable backend returns with -EBUSY 589 * from here, it must not escape to the caller. 590 */ 591 if (unlikely(err == -EBUSY)) 592 err = -EOVERFLOW; 593 if (err == -EEXIST) 594 err = -EADDRINUSE; 595 sock_put(sk); 596 goto err; 597 } 598 599 /* We need to ensure that the socket is hashed and visible. */ 600 smp_wmb(); 601 /* Paired with lockless reads from netlink_bind(), 602 * netlink_connect() and netlink_sendmsg(). 603 */ 604 WRITE_ONCE(nlk_sk(sk)->bound, portid); 605 606err: 607 release_sock(sk); 608 return err; 609} 610 611static void netlink_remove(struct sock *sk) 612{ 613 struct netlink_table *table; 614 615 table = &nl_table[sk->sk_protocol]; 616 if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node, 617 netlink_rhashtable_params)) { 618 WARN_ON(refcount_read(&sk->sk_refcnt) == 1); 619 __sock_put(sk); 620 } 621 622 netlink_table_grab(); 623 if (nlk_sk(sk)->subscriptions) { 624 __sk_del_bind_node(sk); 625 netlink_update_listeners(sk); 626 } 627 if (sk->sk_protocol == NETLINK_GENERIC) 628 atomic_inc(&genl_sk_destructing_cnt); 629 netlink_table_ungrab(); 630} 631 632static struct proto netlink_proto = { 633 .name = "NETLINK", 634 .owner = THIS_MODULE, 635 .obj_size = sizeof(struct netlink_sock), 636}; 637 638static int __netlink_create(struct net *net, struct socket *sock, 639 struct mutex *cb_mutex, int protocol, 640 int kern) 641{ 642 struct sock *sk; 643 struct netlink_sock *nlk; 644 645 sock->ops = &netlink_ops; 646 647 sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto, kern); 648 if (!sk) 649 return -ENOMEM; 650 651 sock_init_data(sock, sk); 652 653 nlk = nlk_sk(sk); 654 if (cb_mutex) { 655 nlk->cb_mutex = cb_mutex; 656 } else { 657 nlk->cb_mutex = &nlk->cb_def_mutex; 658 mutex_init(nlk->cb_mutex); 659 lockdep_set_class_and_name(nlk->cb_mutex, 660 nlk_cb_mutex_keys + protocol, 661 nlk_cb_mutex_key_strings[protocol]); 662 } 663 init_waitqueue_head(&nlk->wait); 664 665 sk->sk_destruct = netlink_sock_destruct; 666 sk->sk_protocol = protocol; 667 return 0; 668} 669 670static int netlink_create(struct net *net, struct socket *sock, int protocol, 671 int kern) 672{ 673 struct module *module = NULL; 674 struct mutex *cb_mutex; 675 struct netlink_sock *nlk; 676 int (*bind)(struct net *net, int group); 677 void (*unbind)(struct net *net, int group); 678 void (*release)(struct sock *sock, unsigned long *groups); 679 int err = 0; 680 681 sock->state = SS_UNCONNECTED; 682 683 if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) 684 return -ESOCKTNOSUPPORT; 685 686 if (protocol < 0 || protocol >= MAX_LINKS) 687 return -EPROTONOSUPPORT; 688 protocol = array_index_nospec(protocol, MAX_LINKS); 689 690 netlink_lock_table(); 691#ifdef CONFIG_MODULES 692 if (!nl_table[protocol].registered) { 693 netlink_unlock_table(); 694 request_module("net-pf-%d-proto-%d", PF_NETLINK, protocol); 695 netlink_lock_table(); 696 } 697#endif 698 if (nl_table[protocol].registered && 699 try_module_get(nl_table[protocol].module)) 700 module = nl_table[protocol].module; 701 else 702 err = -EPROTONOSUPPORT; 703 cb_mutex = nl_table[protocol].cb_mutex; 704 bind = nl_table[protocol].bind; 705 unbind = nl_table[protocol].unbind; 706 release = nl_table[protocol].release; 707 netlink_unlock_table(); 708 709 if (err < 0) 710 goto out; 711 712 err = __netlink_create(net, sock, cb_mutex, protocol, kern); 713 if (err < 0) 714 goto out_module; 715 716 sock_prot_inuse_add(net, &netlink_proto, 1); 717 718 nlk = nlk_sk(sock->sk); 719 nlk->module = module; 720 nlk->netlink_bind = bind; 721 nlk->netlink_unbind = unbind; 722 nlk->netlink_release = release; 723out: 724 return err; 725 726out_module: 727 module_put(module); 728 goto out; 729} 730 731static void deferred_put_nlk_sk(struct rcu_head *head) 732{ 733 struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu); 734 struct sock *sk = &nlk->sk; 735 736 kfree(nlk->groups); 737 nlk->groups = NULL; 738 739 if (!refcount_dec_and_test(&sk->sk_refcnt)) 740 return; 741 742 if (nlk->cb_running && nlk->cb.done) { 743 INIT_WORK(&nlk->work, netlink_sock_destruct_work); 744 schedule_work(&nlk->work); 745 return; 746 } 747 748 sk_free(sk); 749} 750 751static int netlink_release(struct socket *sock) 752{ 753 struct sock *sk = sock->sk; 754 struct netlink_sock *nlk; 755 756 if (!sk) 757 return 0; 758 759 netlink_remove(sk); 760 sock_orphan(sk); 761 nlk = nlk_sk(sk); 762 763 /* 764 * OK. Socket is unlinked, any packets that arrive now 765 * will be purged. 766 */ 767 if (nlk->netlink_release) 768 nlk->netlink_release(sk, nlk->groups); 769 770 /* must not acquire netlink_table_lock in any way again before unbind 771 * and notifying genetlink is done as otherwise it might deadlock 772 */ 773 if (nlk->netlink_unbind) { 774 int i; 775 776 for (i = 0; i < nlk->ngroups; i++) 777 if (test_bit(i, nlk->groups)) 778 nlk->netlink_unbind(sock_net(sk), i + 1); 779 } 780 if (sk->sk_protocol == NETLINK_GENERIC && 781 atomic_dec_return(&genl_sk_destructing_cnt) == 0) 782 wake_up(&genl_sk_destructing_waitq); 783 784 sock->sk = NULL; 785 wake_up_interruptible_all(&nlk->wait); 786 787 skb_queue_purge(&sk->sk_write_queue); 788 789 if (nlk->portid && nlk->bound) { 790 struct netlink_notify n = { 791 .net = sock_net(sk), 792 .protocol = sk->sk_protocol, 793 .portid = nlk->portid, 794 }; 795 blocking_notifier_call_chain(&netlink_chain, 796 NETLINK_URELEASE, &n); 797 } 798 799 module_put(nlk->module); 800 801 if (netlink_is_kernel(sk)) { 802 netlink_table_grab(); 803 BUG_ON(nl_table[sk->sk_protocol].registered == 0); 804 if (--nl_table[sk->sk_protocol].registered == 0) { 805 struct listeners *old; 806 807 old = nl_deref_protected(nl_table[sk->sk_protocol].listeners); 808 RCU_INIT_POINTER(nl_table[sk->sk_protocol].listeners, NULL); 809 kfree_rcu(old, rcu); 810 nl_table[sk->sk_protocol].module = NULL; 811 nl_table[sk->sk_protocol].bind = NULL; 812 nl_table[sk->sk_protocol].unbind = NULL; 813 nl_table[sk->sk_protocol].flags = 0; 814 nl_table[sk->sk_protocol].registered = 0; 815 } 816 netlink_table_ungrab(); 817 } 818 819 sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1); 820 821 /* Because struct net might disappear soon, do not keep a pointer. */ 822 if (!sk->sk_net_refcnt && sock_net(sk) != &init_net) { 823 __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false); 824 /* Because of deferred_put_nlk_sk and use of work queue, 825 * it is possible netns will be freed before this socket. 826 */ 827 sock_net_set(sk, &init_net); 828 __netns_tracker_alloc(&init_net, &sk->ns_tracker, 829 false, GFP_KERNEL); 830 } 831 call_rcu(&nlk->rcu, deferred_put_nlk_sk); 832 return 0; 833} 834 835static int netlink_autobind(struct socket *sock) 836{ 837 struct sock *sk = sock->sk; 838 struct net *net = sock_net(sk); 839 struct netlink_table *table = &nl_table[sk->sk_protocol]; 840 s32 portid = task_tgid_vnr(current); 841 int err; 842 s32 rover = -4096; 843 bool ok; 844 845retry: 846 cond_resched(); 847 rcu_read_lock(); 848 ok = !__netlink_lookup(table, portid, net); 849 rcu_read_unlock(); 850 if (!ok) { 851 /* Bind collision, search negative portid values. */ 852 if (rover == -4096) 853 /* rover will be in range [S32_MIN, -4097] */ 854 rover = S32_MIN + get_random_u32_below(-4096 - S32_MIN); 855 else if (rover >= -4096) 856 rover = -4097; 857 portid = rover--; 858 goto retry; 859 } 860 861 err = netlink_insert(sk, portid); 862 if (err == -EADDRINUSE) 863 goto retry; 864 865 /* If 2 threads race to autobind, that is fine. */ 866 if (err == -EBUSY) 867 err = 0; 868 869 return err; 870} 871 872/** 873 * __netlink_ns_capable - General netlink message capability test 874 * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace. 875 * @user_ns: The user namespace of the capability to use 876 * @cap: The capability to use 877 * 878 * Test to see if the opener of the socket we received the message 879 * from had when the netlink socket was created and the sender of the 880 * message has the capability @cap in the user namespace @user_ns. 881 */ 882bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, 883 struct user_namespace *user_ns, int cap) 884{ 885 return ((nsp->flags & NETLINK_SKB_DST) || 886 file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) && 887 ns_capable(user_ns, cap); 888} 889EXPORT_SYMBOL(__netlink_ns_capable); 890 891/** 892 * netlink_ns_capable - General netlink message capability test 893 * @skb: socket buffer holding a netlink command from userspace 894 * @user_ns: The user namespace of the capability to use 895 * @cap: The capability to use 896 * 897 * Test to see if the opener of the socket we received the message 898 * from had when the netlink socket was created and the sender of the 899 * message has the capability @cap in the user namespace @user_ns. 900 */ 901bool netlink_ns_capable(const struct sk_buff *skb, 902 struct user_namespace *user_ns, int cap) 903{ 904 return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap); 905} 906EXPORT_SYMBOL(netlink_ns_capable); 907 908/** 909 * netlink_capable - Netlink global message capability test 910 * @skb: socket buffer holding a netlink command from userspace 911 * @cap: The capability to use 912 * 913 * Test to see if the opener of the socket we received the message 914 * from had when the netlink socket was created and the sender of the 915 * message has the capability @cap in all user namespaces. 916 */ 917bool netlink_capable(const struct sk_buff *skb, int cap) 918{ 919 return netlink_ns_capable(skb, &init_user_ns, cap); 920} 921EXPORT_SYMBOL(netlink_capable); 922 923/** 924 * netlink_net_capable - Netlink network namespace message capability test 925 * @skb: socket buffer holding a netlink command from userspace 926 * @cap: The capability to use 927 * 928 * Test to see if the opener of the socket we received the message 929 * from had when the netlink socket was created and the sender of the 930 * message has the capability @cap over the network namespace of 931 * the socket we received the message from. 932 */ 933bool netlink_net_capable(const struct sk_buff *skb, int cap) 934{ 935 return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap); 936} 937EXPORT_SYMBOL(netlink_net_capable); 938 939static inline int netlink_allowed(const struct socket *sock, unsigned int flag) 940{ 941 return (nl_table[sock->sk->sk_protocol].flags & flag) || 942 ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN); 943} 944 945static void 946netlink_update_subscriptions(struct sock *sk, unsigned int subscriptions) 947{ 948 struct netlink_sock *nlk = nlk_sk(sk); 949 950 if (nlk->subscriptions && !subscriptions) 951 __sk_del_bind_node(sk); 952 else if (!nlk->subscriptions && subscriptions) 953 sk_add_bind_node(sk, &nl_table[sk->sk_protocol].mc_list); 954 nlk->subscriptions = subscriptions; 955} 956 957static int netlink_realloc_groups(struct sock *sk) 958{ 959 struct netlink_sock *nlk = nlk_sk(sk); 960 unsigned int groups; 961 unsigned long *new_groups; 962 int err = 0; 963 964 netlink_table_grab(); 965 966 groups = nl_table[sk->sk_protocol].groups; 967 if (!nl_table[sk->sk_protocol].registered) { 968 err = -ENOENT; 969 goto out_unlock; 970 } 971 972 if (nlk->ngroups >= groups) 973 goto out_unlock; 974 975 new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_ATOMIC); 976 if (new_groups == NULL) { 977 err = -ENOMEM; 978 goto out_unlock; 979 } 980 memset((char *)new_groups + NLGRPSZ(nlk->ngroups), 0, 981 NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups)); 982 983 nlk->groups = new_groups; 984 nlk->ngroups = groups; 985 out_unlock: 986 netlink_table_ungrab(); 987 return err; 988} 989 990static void netlink_undo_bind(int group, long unsigned int groups, 991 struct sock *sk) 992{ 993 struct netlink_sock *nlk = nlk_sk(sk); 994 int undo; 995 996 if (!nlk->netlink_unbind) 997 return; 998 999 for (undo = 0; undo < group; undo++) 1000 if (test_bit(undo, &groups)) 1001 nlk->netlink_unbind(sock_net(sk), undo + 1); 1002} 1003 1004static int netlink_bind(struct socket *sock, struct sockaddr *addr, 1005 int addr_len) 1006{ 1007 struct sock *sk = sock->sk; 1008 struct net *net = sock_net(sk); 1009 struct netlink_sock *nlk = nlk_sk(sk); 1010 struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; 1011 int err = 0; 1012 unsigned long groups; 1013 bool bound; 1014 1015 if (addr_len < sizeof(struct sockaddr_nl)) 1016 return -EINVAL; 1017 1018 if (nladdr->nl_family != AF_NETLINK) 1019 return -EINVAL; 1020 groups = nladdr->nl_groups; 1021 1022 /* Only superuser is allowed to listen multicasts */ 1023 if (groups) { 1024 if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) 1025 return -EPERM; 1026 err = netlink_realloc_groups(sk); 1027 if (err) 1028 return err; 1029 } 1030 1031 if (nlk->ngroups < BITS_PER_LONG) 1032 groups &= (1UL << nlk->ngroups) - 1; 1033 1034 /* Paired with WRITE_ONCE() in netlink_insert() */ 1035 bound = READ_ONCE(nlk->bound); 1036 if (bound) { 1037 /* Ensure nlk->portid is up-to-date. */ 1038 smp_rmb(); 1039 1040 if (nladdr->nl_pid != nlk->portid) 1041 return -EINVAL; 1042 } 1043 1044 if (nlk->netlink_bind && groups) { 1045 int group; 1046 1047 /* nl_groups is a u32, so cap the maximum groups we can bind */ 1048 for (group = 0; group < BITS_PER_TYPE(u32); group++) { 1049 if (!test_bit(group, &groups)) 1050 continue; 1051 err = nlk->netlink_bind(net, group + 1); 1052 if (!err) 1053 continue; 1054 netlink_undo_bind(group, groups, sk); 1055 return err; 1056 } 1057 } 1058 1059 /* No need for barriers here as we return to user-space without 1060 * using any of the bound attributes. 1061 */ 1062 netlink_lock_table(); 1063 if (!bound) { 1064 err = nladdr->nl_pid ? 1065 netlink_insert(sk, nladdr->nl_pid) : 1066 netlink_autobind(sock); 1067 if (err) { 1068 netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk); 1069 goto unlock; 1070 } 1071 } 1072 1073 if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0])) 1074 goto unlock; 1075 netlink_unlock_table(); 1076 1077 netlink_table_grab(); 1078 netlink_update_subscriptions(sk, nlk->subscriptions + 1079 hweight32(groups) - 1080 hweight32(nlk->groups[0])); 1081 nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups; 1082 netlink_update_listeners(sk); 1083 netlink_table_ungrab(); 1084 1085 return 0; 1086 1087unlock: 1088 netlink_unlock_table(); 1089 return err; 1090} 1091 1092static int netlink_connect(struct socket *sock, struct sockaddr *addr, 1093 int alen, int flags) 1094{ 1095 int err = 0; 1096 struct sock *sk = sock->sk; 1097 struct netlink_sock *nlk = nlk_sk(sk); 1098 struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; 1099 1100 if (alen < sizeof(addr->sa_family)) 1101 return -EINVAL; 1102 1103 if (addr->sa_family == AF_UNSPEC) { 1104 /* paired with READ_ONCE() in netlink_getsockbyportid() */ 1105 WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED); 1106 /* dst_portid and dst_group can be read locklessly */ 1107 WRITE_ONCE(nlk->dst_portid, 0); 1108 WRITE_ONCE(nlk->dst_group, 0); 1109 return 0; 1110 } 1111 if (addr->sa_family != AF_NETLINK) 1112 return -EINVAL; 1113 1114 if (alen < sizeof(struct sockaddr_nl)) 1115 return -EINVAL; 1116 1117 if ((nladdr->nl_groups || nladdr->nl_pid) && 1118 !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) 1119 return -EPERM; 1120 1121 /* No need for barriers here as we return to user-space without 1122 * using any of the bound attributes. 1123 * Paired with WRITE_ONCE() in netlink_insert(). 1124 */ 1125 if (!READ_ONCE(nlk->bound)) 1126 err = netlink_autobind(sock); 1127 1128 if (err == 0) { 1129 /* paired with READ_ONCE() in netlink_getsockbyportid() */ 1130 WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED); 1131 /* dst_portid and dst_group can be read locklessly */ 1132 WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid); 1133 WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups)); 1134 } 1135 1136 return err; 1137} 1138 1139static int netlink_getname(struct socket *sock, struct sockaddr *addr, 1140 int peer) 1141{ 1142 struct sock *sk = sock->sk; 1143 struct netlink_sock *nlk = nlk_sk(sk); 1144 DECLARE_SOCKADDR(struct sockaddr_nl *, nladdr, addr); 1145 1146 nladdr->nl_family = AF_NETLINK; 1147 nladdr->nl_pad = 0; 1148 1149 if (peer) { 1150 /* Paired with WRITE_ONCE() in netlink_connect() */ 1151 nladdr->nl_pid = READ_ONCE(nlk->dst_portid); 1152 nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group)); 1153 } else { 1154 /* Paired with WRITE_ONCE() in netlink_insert() */ 1155 nladdr->nl_pid = READ_ONCE(nlk->portid); 1156 netlink_lock_table(); 1157 nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; 1158 netlink_unlock_table(); 1159 } 1160 return sizeof(*nladdr); 1161} 1162 1163static int netlink_ioctl(struct socket *sock, unsigned int cmd, 1164 unsigned long arg) 1165{ 1166 /* try to hand this ioctl down to the NIC drivers. 1167 */ 1168 return -ENOIOCTLCMD; 1169} 1170 1171static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) 1172{ 1173 struct sock *sock; 1174 struct netlink_sock *nlk; 1175 1176 sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, portid); 1177 if (!sock) 1178 return ERR_PTR(-ECONNREFUSED); 1179 1180 /* Don't bother queuing skb if kernel socket has no input function */ 1181 nlk = nlk_sk(sock); 1182 /* dst_portid and sk_state can be changed in netlink_connect() */ 1183 if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED && 1184 READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) { 1185 sock_put(sock); 1186 return ERR_PTR(-ECONNREFUSED); 1187 } 1188 return sock; 1189} 1190 1191struct sock *netlink_getsockbyfilp(struct file *filp) 1192{ 1193 struct inode *inode = file_inode(filp); 1194 struct sock *sock; 1195 1196 if (!S_ISSOCK(inode->i_mode)) 1197 return ERR_PTR(-ENOTSOCK); 1198 1199 sock = SOCKET_I(inode)->sk; 1200 if (sock->sk_family != AF_NETLINK) 1201 return ERR_PTR(-EINVAL); 1202 1203 sock_hold(sock); 1204 return sock; 1205} 1206 1207static struct sk_buff *netlink_alloc_large_skb(unsigned int size, 1208 int broadcast) 1209{ 1210 struct sk_buff *skb; 1211 void *data; 1212 1213 if (size <= NLMSG_GOODSIZE || broadcast) 1214 return alloc_skb(size, GFP_KERNEL); 1215 1216 size = SKB_DATA_ALIGN(size) + 1217 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); 1218 1219 data = vmalloc(size); 1220 if (data == NULL) 1221 return NULL; 1222 1223 skb = __build_skb(data, size); 1224 if (skb == NULL) 1225 vfree(data); 1226 else 1227 skb->destructor = netlink_skb_destructor; 1228 1229 return skb; 1230} 1231 1232/* 1233 * Attach a skb to a netlink socket. 1234 * The caller must hold a reference to the destination socket. On error, the 1235 * reference is dropped. The skb is not send to the destination, just all 1236 * all error checks are performed and memory in the queue is reserved. 1237 * Return values: 1238 * < 0: error. skb freed, reference to sock dropped. 1239 * 0: continue 1240 * 1: repeat lookup - reference dropped while waiting for socket memory. 1241 */ 1242int netlink_attachskb(struct sock *sk, struct sk_buff *skb, 1243 long *timeo, struct sock *ssk) 1244{ 1245 struct netlink_sock *nlk; 1246 1247 nlk = nlk_sk(sk); 1248 1249 if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || 1250 test_bit(NETLINK_S_CONGESTED, &nlk->state))) { 1251 DECLARE_WAITQUEUE(wait, current); 1252 if (!*timeo) { 1253 if (!ssk || netlink_is_kernel(ssk)) 1254 netlink_overrun(sk); 1255 sock_put(sk); 1256 kfree_skb(skb); 1257 return -EAGAIN; 1258 } 1259 1260 __set_current_state(TASK_INTERRUPTIBLE); 1261 add_wait_queue(&nlk->wait, &wait); 1262 1263 if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || 1264 test_bit(NETLINK_S_CONGESTED, &nlk->state)) && 1265 !sock_flag(sk, SOCK_DEAD)) 1266 *timeo = schedule_timeout(*timeo); 1267 1268 __set_current_state(TASK_RUNNING); 1269 remove_wait_queue(&nlk->wait, &wait); 1270 sock_put(sk); 1271 1272 if (signal_pending(current)) { 1273 kfree_skb(skb); 1274 return sock_intr_errno(*timeo); 1275 } 1276 return 1; 1277 } 1278 netlink_skb_set_owner_r(skb, sk); 1279 return 0; 1280} 1281 1282static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) 1283{ 1284 int len = skb->len; 1285 1286 netlink_deliver_tap(sock_net(sk), skb); 1287 1288 skb_queue_tail(&sk->sk_receive_queue, skb); 1289 sk->sk_data_ready(sk); 1290 return len; 1291} 1292 1293int netlink_sendskb(struct sock *sk, struct sk_buff *skb) 1294{ 1295 int len = __netlink_sendskb(sk, skb); 1296 1297 sock_put(sk); 1298 return len; 1299} 1300 1301void netlink_detachskb(struct sock *sk, struct sk_buff *skb) 1302{ 1303 kfree_skb(skb); 1304 sock_put(sk); 1305} 1306 1307static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation) 1308{ 1309 int delta; 1310 1311 WARN_ON(skb->sk != NULL); 1312 delta = skb->end - skb->tail; 1313 if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize) 1314 return skb; 1315 1316 if (skb_shared(skb)) { 1317 struct sk_buff *nskb = skb_clone(skb, allocation); 1318 if (!nskb) 1319 return skb; 1320 consume_skb(skb); 1321 skb = nskb; 1322 } 1323 1324 pskb_expand_head(skb, 0, -delta, 1325 (allocation & ~__GFP_DIRECT_RECLAIM) | 1326 __GFP_NOWARN | __GFP_NORETRY); 1327 return skb; 1328} 1329 1330static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb, 1331 struct sock *ssk) 1332{ 1333 int ret; 1334 struct netlink_sock *nlk = nlk_sk(sk); 1335 1336 ret = -ECONNREFUSED; 1337 if (nlk->netlink_rcv != NULL) { 1338 ret = skb->len; 1339 netlink_skb_set_owner_r(skb, sk); 1340 NETLINK_CB(skb).sk = ssk; 1341 netlink_deliver_tap_kernel(sk, ssk, skb); 1342 nlk->netlink_rcv(skb); 1343 consume_skb(skb); 1344 } else { 1345 kfree_skb(skb); 1346 } 1347 sock_put(sk); 1348 return ret; 1349} 1350 1351int netlink_unicast(struct sock *ssk, struct sk_buff *skb, 1352 u32 portid, int nonblock) 1353{ 1354 struct sock *sk; 1355 int err; 1356 long timeo; 1357 1358 skb = netlink_trim(skb, gfp_any()); 1359 1360 timeo = sock_sndtimeo(ssk, nonblock); 1361retry: 1362 sk = netlink_getsockbyportid(ssk, portid); 1363 if (IS_ERR(sk)) { 1364 kfree_skb(skb); 1365 return PTR_ERR(sk); 1366 } 1367 if (netlink_is_kernel(sk)) 1368 return netlink_unicast_kernel(sk, skb, ssk); 1369 1370 if (sk_filter(sk, skb)) { 1371 err = skb->len; 1372 kfree_skb(skb); 1373 sock_put(sk); 1374 return err; 1375 } 1376 1377 err = netlink_attachskb(sk, skb, &timeo, ssk); 1378 if (err == 1) 1379 goto retry; 1380 if (err) 1381 return err; 1382 1383 return netlink_sendskb(sk, skb); 1384} 1385EXPORT_SYMBOL(netlink_unicast); 1386 1387int netlink_has_listeners(struct sock *sk, unsigned int group) 1388{ 1389 int res = 0; 1390 struct listeners *listeners; 1391 1392 BUG_ON(!netlink_is_kernel(sk)); 1393 1394 rcu_read_lock(); 1395 listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners); 1396 1397 if (listeners && group - 1 < nl_table[sk->sk_protocol].groups) 1398 res = test_bit(group - 1, listeners->masks); 1399 1400 rcu_read_unlock(); 1401 1402 return res; 1403} 1404EXPORT_SYMBOL_GPL(netlink_has_listeners); 1405 1406bool netlink_strict_get_check(struct sk_buff *skb) 1407{ 1408 return nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); 1409} 1410EXPORT_SYMBOL_GPL(netlink_strict_get_check); 1411 1412static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) 1413{ 1414 struct netlink_sock *nlk = nlk_sk(sk); 1415 1416 if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && 1417 !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { 1418 netlink_skb_set_owner_r(skb, sk); 1419 __netlink_sendskb(sk, skb); 1420 return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1); 1421 } 1422 return -1; 1423} 1424 1425struct netlink_broadcast_data { 1426 struct sock *exclude_sk; 1427 struct net *net; 1428 u32 portid; 1429 u32 group; 1430 int failure; 1431 int delivery_failure; 1432 int congested; 1433 int delivered; 1434 gfp_t allocation; 1435 struct sk_buff *skb, *skb2; 1436 int (*tx_filter)(struct sock *dsk, struct sk_buff *skb, void *data); 1437 void *tx_data; 1438}; 1439 1440static void do_one_broadcast(struct sock *sk, 1441 struct netlink_broadcast_data *p) 1442{ 1443 struct netlink_sock *nlk = nlk_sk(sk); 1444 int val; 1445 1446 if (p->exclude_sk == sk) 1447 return; 1448 1449 if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || 1450 !test_bit(p->group - 1, nlk->groups)) 1451 return; 1452 1453 if (!net_eq(sock_net(sk), p->net)) { 1454 if (!nlk_test_bit(LISTEN_ALL_NSID, sk)) 1455 return; 1456 1457 if (!peernet_has_id(sock_net(sk), p->net)) 1458 return; 1459 1460 if (!file_ns_capable(sk->sk_socket->file, p->net->user_ns, 1461 CAP_NET_BROADCAST)) 1462 return; 1463 } 1464 1465 if (p->failure) { 1466 netlink_overrun(sk); 1467 return; 1468 } 1469 1470 sock_hold(sk); 1471 if (p->skb2 == NULL) { 1472 if (skb_shared(p->skb)) { 1473 p->skb2 = skb_clone(p->skb, p->allocation); 1474 } else { 1475 p->skb2 = skb_get(p->skb); 1476 /* 1477 * skb ownership may have been set when 1478 * delivered to a previous socket. 1479 */ 1480 skb_orphan(p->skb2); 1481 } 1482 } 1483 if (p->skb2 == NULL) { 1484 netlink_overrun(sk); 1485 /* Clone failed. Notify ALL listeners. */ 1486 p->failure = 1; 1487 if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) 1488 p->delivery_failure = 1; 1489 goto out; 1490 } 1491 1492 if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) { 1493 kfree_skb(p->skb2); 1494 p->skb2 = NULL; 1495 goto out; 1496 } 1497 1498 if (sk_filter(sk, p->skb2)) { 1499 kfree_skb(p->skb2); 1500 p->skb2 = NULL; 1501 goto out; 1502 } 1503 NETLINK_CB(p->skb2).nsid = peernet2id(sock_net(sk), p->net); 1504 if (NETLINK_CB(p->skb2).nsid != NETNSA_NSID_NOT_ASSIGNED) 1505 NETLINK_CB(p->skb2).nsid_is_set = true; 1506 val = netlink_broadcast_deliver(sk, p->skb2); 1507 if (val < 0) { 1508 netlink_overrun(sk); 1509 if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) 1510 p->delivery_failure = 1; 1511 } else { 1512 p->congested |= val; 1513 p->delivered = 1; 1514 p->skb2 = NULL; 1515 } 1516out: 1517 sock_put(sk); 1518} 1519 1520int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, 1521 u32 portid, 1522 u32 group, gfp_t allocation, 1523 int (*filter)(struct sock *dsk, 1524 struct sk_buff *skb, void *data), 1525 void *filter_data) 1526{ 1527 struct net *net = sock_net(ssk); 1528 struct netlink_broadcast_data info; 1529 struct sock *sk; 1530 1531 skb = netlink_trim(skb, allocation); 1532 1533 info.exclude_sk = ssk; 1534 info.net = net; 1535 info.portid = portid; 1536 info.group = group; 1537 info.failure = 0; 1538 info.delivery_failure = 0; 1539 info.congested = 0; 1540 info.delivered = 0; 1541 info.allocation = allocation; 1542 info.skb = skb; 1543 info.skb2 = NULL; 1544 info.tx_filter = filter; 1545 info.tx_data = filter_data; 1546 1547 /* While we sleep in clone, do not allow to change socket list */ 1548 1549 netlink_lock_table(); 1550 1551 sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) 1552 do_one_broadcast(sk, &info); 1553 1554 consume_skb(skb); 1555 1556 netlink_unlock_table(); 1557 1558 if (info.delivery_failure) { 1559 kfree_skb(info.skb2); 1560 return -ENOBUFS; 1561 } 1562 consume_skb(info.skb2); 1563 1564 if (info.delivered) { 1565 if (info.congested && gfpflags_allow_blocking(allocation)) 1566 yield(); 1567 return 0; 1568 } 1569 return -ESRCH; 1570} 1571EXPORT_SYMBOL(netlink_broadcast_filtered); 1572 1573int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, 1574 u32 group, gfp_t allocation) 1575{ 1576 return netlink_broadcast_filtered(ssk, skb, portid, group, allocation, 1577 NULL, NULL); 1578} 1579EXPORT_SYMBOL(netlink_broadcast); 1580 1581struct netlink_set_err_data { 1582 struct sock *exclude_sk; 1583 u32 portid; 1584 u32 group; 1585 int code; 1586}; 1587 1588static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) 1589{ 1590 struct netlink_sock *nlk = nlk_sk(sk); 1591 int ret = 0; 1592 1593 if (sk == p->exclude_sk) 1594 goto out; 1595 1596 if (!net_eq(sock_net(sk), sock_net(p->exclude_sk))) 1597 goto out; 1598 1599 if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || 1600 !test_bit(p->group - 1, nlk->groups)) 1601 goto out; 1602 1603 if (p->code == ENOBUFS && nlk_test_bit(RECV_NO_ENOBUFS, sk)) { 1604 ret = 1; 1605 goto out; 1606 } 1607 1608 WRITE_ONCE(sk->sk_err, p->code); 1609 sk_error_report(sk); 1610out: 1611 return ret; 1612} 1613 1614/** 1615 * netlink_set_err - report error to broadcast listeners 1616 * @ssk: the kernel netlink socket, as returned by netlink_kernel_create() 1617 * @portid: the PORTID of a process that we want to skip (if any) 1618 * @group: the broadcast group that will notice the error 1619 * @code: error code, must be negative (as usual in kernelspace) 1620 * 1621 * This function returns the number of broadcast listeners that have set the 1622 * NETLINK_NO_ENOBUFS socket option. 1623 */ 1624int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) 1625{ 1626 struct netlink_set_err_data info; 1627 unsigned long flags; 1628 struct sock *sk; 1629 int ret = 0; 1630 1631 info.exclude_sk = ssk; 1632 info.portid = portid; 1633 info.group = group; 1634 /* sk->sk_err wants a positive error value */ 1635 info.code = -code; 1636 1637 read_lock_irqsave(&nl_table_lock, flags); 1638 1639 sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) 1640 ret += do_one_set_err(sk, &info); 1641 1642 read_unlock_irqrestore(&nl_table_lock, flags); 1643 return ret; 1644} 1645EXPORT_SYMBOL(netlink_set_err); 1646 1647/* must be called with netlink table grabbed */ 1648static void netlink_update_socket_mc(struct netlink_sock *nlk, 1649 unsigned int group, 1650 int is_new) 1651{ 1652 int old, new = !!is_new, subscriptions; 1653 1654 old = test_bit(group - 1, nlk->groups); 1655 subscriptions = nlk->subscriptions - old + new; 1656 __assign_bit(group - 1, nlk->groups, new); 1657 netlink_update_subscriptions(&nlk->sk, subscriptions); 1658 netlink_update_listeners(&nlk->sk); 1659} 1660 1661static int netlink_setsockopt(struct socket *sock, int level, int optname, 1662 sockptr_t optval, unsigned int optlen) 1663{ 1664 struct sock *sk = sock->sk; 1665 struct netlink_sock *nlk = nlk_sk(sk); 1666 unsigned int val = 0; 1667 int nr = -1; 1668 1669 if (level != SOL_NETLINK) 1670 return -ENOPROTOOPT; 1671 1672 if (optlen >= sizeof(int) && 1673 copy_from_sockptr(&val, optval, sizeof(val))) 1674 return -EFAULT; 1675 1676 switch (optname) { 1677 case NETLINK_PKTINFO: 1678 nr = NETLINK_F_RECV_PKTINFO; 1679 break; 1680 case NETLINK_ADD_MEMBERSHIP: 1681 case NETLINK_DROP_MEMBERSHIP: { 1682 int err; 1683 1684 if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) 1685 return -EPERM; 1686 err = netlink_realloc_groups(sk); 1687 if (err) 1688 return err; 1689 if (!val || val - 1 >= nlk->ngroups) 1690 return -EINVAL; 1691 if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) { 1692 err = nlk->netlink_bind(sock_net(sk), val); 1693 if (err) 1694 return err; 1695 } 1696 netlink_table_grab(); 1697 netlink_update_socket_mc(nlk, val, 1698 optname == NETLINK_ADD_MEMBERSHIP); 1699 netlink_table_ungrab(); 1700 if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind) 1701 nlk->netlink_unbind(sock_net(sk), val); 1702 1703 break; 1704 } 1705 case NETLINK_BROADCAST_ERROR: 1706 nr = NETLINK_F_BROADCAST_SEND_ERROR; 1707 break; 1708 case NETLINK_NO_ENOBUFS: 1709 assign_bit(NETLINK_F_RECV_NO_ENOBUFS, &nlk->flags, val); 1710 if (val) { 1711 clear_bit(NETLINK_S_CONGESTED, &nlk->state); 1712 wake_up_interruptible(&nlk->wait); 1713 } 1714 break; 1715 case NETLINK_LISTEN_ALL_NSID: 1716 if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST)) 1717 return -EPERM; 1718 nr = NETLINK_F_LISTEN_ALL_NSID; 1719 break; 1720 case NETLINK_CAP_ACK: 1721 nr = NETLINK_F_CAP_ACK; 1722 break; 1723 case NETLINK_EXT_ACK: 1724 nr = NETLINK_F_EXT_ACK; 1725 break; 1726 case NETLINK_GET_STRICT_CHK: 1727 nr = NETLINK_F_STRICT_CHK; 1728 break; 1729 default: 1730 return -ENOPROTOOPT; 1731 } 1732 if (nr >= 0) 1733 assign_bit(nr, &nlk->flags, val); 1734 return 0; 1735} 1736 1737static int netlink_getsockopt(struct socket *sock, int level, int optname, 1738 char __user *optval, int __user *optlen) 1739{ 1740 struct sock *sk = sock->sk; 1741 struct netlink_sock *nlk = nlk_sk(sk); 1742 unsigned int flag; 1743 int len, val; 1744 1745 if (level != SOL_NETLINK) 1746 return -ENOPROTOOPT; 1747 1748 if (get_user(len, optlen)) 1749 return -EFAULT; 1750 if (len < 0) 1751 return -EINVAL; 1752 1753 switch (optname) { 1754 case NETLINK_PKTINFO: 1755 flag = NETLINK_F_RECV_PKTINFO; 1756 break; 1757 case NETLINK_BROADCAST_ERROR: 1758 flag = NETLINK_F_BROADCAST_SEND_ERROR; 1759 break; 1760 case NETLINK_NO_ENOBUFS: 1761 flag = NETLINK_F_RECV_NO_ENOBUFS; 1762 break; 1763 case NETLINK_LIST_MEMBERSHIPS: { 1764 int pos, idx, shift, err = 0; 1765 1766 netlink_lock_table(); 1767 for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) { 1768 if (len - pos < sizeof(u32)) 1769 break; 1770 1771 idx = pos / sizeof(unsigned long); 1772 shift = (pos % sizeof(unsigned long)) * 8; 1773 if (put_user((u32)(nlk->groups[idx] >> shift), 1774 (u32 __user *)(optval + pos))) { 1775 err = -EFAULT; 1776 break; 1777 } 1778 } 1779 if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen)) 1780 err = -EFAULT; 1781 netlink_unlock_table(); 1782 return err; 1783 } 1784 case NETLINK_CAP_ACK: 1785 flag = NETLINK_F_CAP_ACK; 1786 break; 1787 case NETLINK_EXT_ACK: 1788 flag = NETLINK_F_EXT_ACK; 1789 break; 1790 case NETLINK_GET_STRICT_CHK: 1791 flag = NETLINK_F_STRICT_CHK; 1792 break; 1793 default: 1794 return -ENOPROTOOPT; 1795 } 1796 1797 if (len < sizeof(int)) 1798 return -EINVAL; 1799 1800 len = sizeof(int); 1801 val = test_bit(flag, &nlk->flags); 1802 1803 if (put_user(len, optlen) || 1804 copy_to_user(optval, &val, len)) 1805 return -EFAULT; 1806 1807 return 0; 1808} 1809 1810static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) 1811{ 1812 struct nl_pktinfo info; 1813 1814 info.group = NETLINK_CB(skb).dst_group; 1815 put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info); 1816} 1817 1818static void netlink_cmsg_listen_all_nsid(struct sock *sk, struct msghdr *msg, 1819 struct sk_buff *skb) 1820{ 1821 if (!NETLINK_CB(skb).nsid_is_set) 1822 return; 1823 1824 put_cmsg(msg, SOL_NETLINK, NETLINK_LISTEN_ALL_NSID, sizeof(int), 1825 &NETLINK_CB(skb).nsid); 1826} 1827 1828static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) 1829{ 1830 struct sock *sk = sock->sk; 1831 struct netlink_sock *nlk = nlk_sk(sk); 1832 DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); 1833 u32 dst_portid; 1834 u32 dst_group; 1835 struct sk_buff *skb; 1836 int err; 1837 struct scm_cookie scm; 1838 u32 netlink_skb_flags = 0; 1839 1840 if (msg->msg_flags & MSG_OOB) 1841 return -EOPNOTSUPP; 1842 1843 if (len == 0) { 1844 pr_warn_once("Zero length message leads to an empty skb\n"); 1845 return -ENODATA; 1846 } 1847 1848 err = scm_send(sock, msg, &scm, true); 1849 if (err < 0) 1850 return err; 1851 1852 if (msg->msg_namelen) { 1853 err = -EINVAL; 1854 if (msg->msg_namelen < sizeof(struct sockaddr_nl)) 1855 goto out; 1856 if (addr->nl_family != AF_NETLINK) 1857 goto out; 1858 dst_portid = addr->nl_pid; 1859 dst_group = ffs(addr->nl_groups); 1860 err = -EPERM; 1861 if ((dst_group || dst_portid) && 1862 !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) 1863 goto out; 1864 netlink_skb_flags |= NETLINK_SKB_DST; 1865 } else { 1866 /* Paired with WRITE_ONCE() in netlink_connect() */ 1867 dst_portid = READ_ONCE(nlk->dst_portid); 1868 dst_group = READ_ONCE(nlk->dst_group); 1869 } 1870 1871 /* Paired with WRITE_ONCE() in netlink_insert() */ 1872 if (!READ_ONCE(nlk->bound)) { 1873 err = netlink_autobind(sock); 1874 if (err) 1875 goto out; 1876 } else { 1877 /* Ensure nlk is hashed and visible. */ 1878 smp_rmb(); 1879 } 1880 1881 err = -EMSGSIZE; 1882 if (len > sk->sk_sndbuf - 32) 1883 goto out; 1884 err = -ENOBUFS; 1885 skb = netlink_alloc_large_skb(len, dst_group); 1886 if (skb == NULL) 1887 goto out; 1888 1889 NETLINK_CB(skb).portid = nlk->portid; 1890 NETLINK_CB(skb).dst_group = dst_group; 1891 NETLINK_CB(skb).creds = scm.creds; 1892 NETLINK_CB(skb).flags = netlink_skb_flags; 1893 1894 err = -EFAULT; 1895 if (memcpy_from_msg(skb_put(skb, len), msg, len)) { 1896 kfree_skb(skb); 1897 goto out; 1898 } 1899 1900 err = security_netlink_send(sk, skb); 1901 if (err) { 1902 kfree_skb(skb); 1903 goto out; 1904 } 1905 1906 if (dst_group) { 1907 refcount_inc(&skb->users); 1908 netlink_broadcast(sk, skb, dst_portid, dst_group, GFP_KERNEL); 1909 } 1910 err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags & MSG_DONTWAIT); 1911 1912out: 1913 scm_destroy(&scm); 1914 return err; 1915} 1916 1917static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, 1918 int flags) 1919{ 1920 struct scm_cookie scm; 1921 struct sock *sk = sock->sk; 1922 struct netlink_sock *nlk = nlk_sk(sk); 1923 size_t copied, max_recvmsg_len; 1924 struct sk_buff *skb, *data_skb; 1925 int err, ret; 1926 1927 if (flags & MSG_OOB) 1928 return -EOPNOTSUPP; 1929 1930 copied = 0; 1931 1932 skb = skb_recv_datagram(sk, flags, &err); 1933 if (skb == NULL) 1934 goto out; 1935 1936 data_skb = skb; 1937 1938#ifdef CONFIG_COMPAT_NETLINK_MESSAGES 1939 if (unlikely(skb_shinfo(skb)->frag_list)) { 1940 /* 1941 * If this skb has a frag_list, then here that means that we 1942 * will have to use the frag_list skb's data for compat tasks 1943 * and the regular skb's data for normal (non-compat) tasks. 1944 * 1945 * If we need to send the compat skb, assign it to the 1946 * 'data_skb' variable so that it will be used below for data 1947 * copying. We keep 'skb' for everything else, including 1948 * freeing both later. 1949 */ 1950 if (flags & MSG_CMSG_COMPAT) 1951 data_skb = skb_shinfo(skb)->frag_list; 1952 } 1953#endif 1954 1955 /* Record the max length of recvmsg() calls for future allocations */ 1956 max_recvmsg_len = max(READ_ONCE(nlk->max_recvmsg_len), len); 1957 max_recvmsg_len = min_t(size_t, max_recvmsg_len, 1958 SKB_WITH_OVERHEAD(32768)); 1959 WRITE_ONCE(nlk->max_recvmsg_len, max_recvmsg_len); 1960 1961 copied = data_skb->len; 1962 if (len < copied) { 1963 msg->msg_flags |= MSG_TRUNC; 1964 copied = len; 1965 } 1966 1967 err = skb_copy_datagram_msg(data_skb, 0, msg, copied); 1968 1969 if (msg->msg_name) { 1970 DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); 1971 addr->nl_family = AF_NETLINK; 1972 addr->nl_pad = 0; 1973 addr->nl_pid = NETLINK_CB(skb).portid; 1974 addr->nl_groups = netlink_group_mask(NETLINK_CB(skb).dst_group); 1975 msg->msg_namelen = sizeof(*addr); 1976 } 1977 1978 if (nlk_test_bit(RECV_PKTINFO, sk)) 1979 netlink_cmsg_recv_pktinfo(msg, skb); 1980 if (nlk_test_bit(LISTEN_ALL_NSID, sk)) 1981 netlink_cmsg_listen_all_nsid(sk, msg, skb); 1982 1983 memset(&scm, 0, sizeof(scm)); 1984 scm.creds = *NETLINK_CREDS(skb); 1985 if (flags & MSG_TRUNC) 1986 copied = data_skb->len; 1987 1988 skb_free_datagram(sk, skb); 1989 1990 if (READ_ONCE(nlk->cb_running) && 1991 atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { 1992 ret = netlink_dump(sk); 1993 if (ret) { 1994 WRITE_ONCE(sk->sk_err, -ret); 1995 sk_error_report(sk); 1996 } 1997 } 1998 1999 scm_recv(sock, msg, &scm, flags); 2000out: 2001 netlink_rcv_wake(sk); 2002 return err ? : copied; 2003} 2004 2005static void netlink_data_ready(struct sock *sk) 2006{ 2007 BUG(); 2008} 2009 2010/* 2011 * We export these functions to other modules. They provide a 2012 * complete set of kernel non-blocking support for message 2013 * queueing. 2014 */ 2015 2016struct sock * 2017__netlink_kernel_create(struct net *net, int unit, struct module *module, 2018 struct netlink_kernel_cfg *cfg) 2019{ 2020 struct socket *sock; 2021 struct sock *sk; 2022 struct netlink_sock *nlk; 2023 struct listeners *listeners = NULL; 2024 struct mutex *cb_mutex = cfg ? cfg->cb_mutex : NULL; 2025 unsigned int groups; 2026 2027 BUG_ON(!nl_table); 2028 2029 if (unit < 0 || unit >= MAX_LINKS) 2030 return NULL; 2031 2032 if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock)) 2033 return NULL; 2034 2035 if (__netlink_create(net, sock, cb_mutex, unit, 1) < 0) 2036 goto out_sock_release_nosk; 2037 2038 sk = sock->sk; 2039 2040 if (!cfg || cfg->groups < 32) 2041 groups = 32; 2042 else 2043 groups = cfg->groups; 2044 2045 listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); 2046 if (!listeners) 2047 goto out_sock_release; 2048 2049 sk->sk_data_ready = netlink_data_ready; 2050 if (cfg && cfg->input) 2051 nlk_sk(sk)->netlink_rcv = cfg->input; 2052 2053 if (netlink_insert(sk, 0)) 2054 goto out_sock_release; 2055 2056 nlk = nlk_sk(sk); 2057 set_bit(NETLINK_F_KERNEL_SOCKET, &nlk->flags); 2058 2059 netlink_table_grab(); 2060 if (!nl_table[unit].registered) { 2061 nl_table[unit].groups = groups; 2062 rcu_assign_pointer(nl_table[unit].listeners, listeners); 2063 nl_table[unit].cb_mutex = cb_mutex; 2064 nl_table[unit].module = module; 2065 if (cfg) { 2066 nl_table[unit].bind = cfg->bind; 2067 nl_table[unit].unbind = cfg->unbind; 2068 nl_table[unit].release = cfg->release; 2069 nl_table[unit].flags = cfg->flags; 2070 } 2071 nl_table[unit].registered = 1; 2072 } else { 2073 kfree(listeners); 2074 nl_table[unit].registered++; 2075 } 2076 netlink_table_ungrab(); 2077 return sk; 2078 2079out_sock_release: 2080 kfree(listeners); 2081 netlink_kernel_release(sk); 2082 return NULL; 2083 2084out_sock_release_nosk: 2085 sock_release(sock); 2086 return NULL; 2087} 2088EXPORT_SYMBOL(__netlink_kernel_create); 2089 2090void 2091netlink_kernel_release(struct sock *sk) 2092{ 2093 if (sk == NULL || sk->sk_socket == NULL) 2094 return; 2095 2096 sock_release(sk->sk_socket); 2097} 2098EXPORT_SYMBOL(netlink_kernel_release); 2099 2100int __netlink_change_ngroups(struct sock *sk, unsigned int groups) 2101{ 2102 struct listeners *new, *old; 2103 struct netlink_table *tbl = &nl_table[sk->sk_protocol]; 2104 2105 if (groups < 32) 2106 groups = 32; 2107 2108 if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) { 2109 new = kzalloc(sizeof(*new) + NLGRPSZ(groups), GFP_ATOMIC); 2110 if (!new) 2111 return -ENOMEM; 2112 old = nl_deref_protected(tbl->listeners); 2113 memcpy(new->masks, old->masks, NLGRPSZ(tbl->groups)); 2114 rcu_assign_pointer(tbl->listeners, new); 2115 2116 kfree_rcu(old, rcu); 2117 } 2118 tbl->groups = groups; 2119 2120 return 0; 2121} 2122 2123/** 2124 * netlink_change_ngroups - change number of multicast groups 2125 * 2126 * This changes the number of multicast groups that are available 2127 * on a certain netlink family. Note that it is not possible to 2128 * change the number of groups to below 32. Also note that it does 2129 * not implicitly call netlink_clear_multicast_users() when the 2130 * number of groups is reduced. 2131 * 2132 * @sk: The kernel netlink socket, as returned by netlink_kernel_create(). 2133 * @groups: The new number of groups. 2134 */ 2135int netlink_change_ngroups(struct sock *sk, unsigned int groups) 2136{ 2137 int err; 2138 2139 netlink_table_grab(); 2140 err = __netlink_change_ngroups(sk, groups); 2141 netlink_table_ungrab(); 2142 2143 return err; 2144} 2145 2146void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group) 2147{ 2148 struct sock *sk; 2149 struct netlink_table *tbl = &nl_table[ksk->sk_protocol]; 2150 2151 sk_for_each_bound(sk, &tbl->mc_list) 2152 netlink_update_socket_mc(nlk_sk(sk), group, 0); 2153} 2154 2155struct nlmsghdr * 2156__nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags) 2157{ 2158 struct nlmsghdr *nlh; 2159 int size = nlmsg_msg_size(len); 2160 2161 nlh = skb_put(skb, NLMSG_ALIGN(size)); 2162 nlh->nlmsg_type = type; 2163 nlh->nlmsg_len = size; 2164 nlh->nlmsg_flags = flags; 2165 nlh->nlmsg_pid = portid; 2166 nlh->nlmsg_seq = seq; 2167 if (!__builtin_constant_p(size) || NLMSG_ALIGN(size) - size != 0) 2168 memset(nlmsg_data(nlh) + len, 0, NLMSG_ALIGN(size) - size); 2169 return nlh; 2170} 2171EXPORT_SYMBOL(__nlmsg_put); 2172 2173/* 2174 * It looks a bit ugly. 2175 * It would be better to create kernel thread. 2176 */ 2177 2178static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb, 2179 struct netlink_callback *cb, 2180 struct netlink_ext_ack *extack) 2181{ 2182 struct nlmsghdr *nlh; 2183 2184 nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(nlk->dump_done_errno), 2185 NLM_F_MULTI | cb->answer_flags); 2186 if (WARN_ON(!nlh)) 2187 return -ENOBUFS; 2188 2189 nl_dump_check_consistent(cb, nlh); 2190 memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno)); 2191 2192 if (extack->_msg && test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) { 2193 nlh->nlmsg_flags |= NLM_F_ACK_TLVS; 2194 if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)) 2195 nlmsg_end(skb, nlh); 2196 } 2197 2198 return 0; 2199} 2200 2201static int netlink_dump(struct sock *sk) 2202{ 2203 struct netlink_sock *nlk = nlk_sk(sk); 2204 struct netlink_ext_ack extack = {}; 2205 struct netlink_callback *cb; 2206 struct sk_buff *skb = NULL; 2207 size_t max_recvmsg_len; 2208 struct module *module; 2209 int err = -ENOBUFS; 2210 int alloc_min_size; 2211 int alloc_size; 2212 2213 mutex_lock(nlk->cb_mutex); 2214 if (!nlk->cb_running) { 2215 err = -EINVAL; 2216 goto errout_skb; 2217 } 2218 2219 if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) 2220 goto errout_skb; 2221 2222 /* NLMSG_GOODSIZE is small to avoid high order allocations being 2223 * required, but it makes sense to _attempt_ a 16K bytes allocation 2224 * to reduce number of system calls on dump operations, if user 2225 * ever provided a big enough buffer. 2226 */ 2227 cb = &nlk->cb; 2228 alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); 2229 2230 max_recvmsg_len = READ_ONCE(nlk->max_recvmsg_len); 2231 if (alloc_min_size < max_recvmsg_len) { 2232 alloc_size = max_recvmsg_len; 2233 skb = alloc_skb(alloc_size, 2234 (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) | 2235 __GFP_NOWARN | __GFP_NORETRY); 2236 } 2237 if (!skb) { 2238 alloc_size = alloc_min_size; 2239 skb = alloc_skb(alloc_size, GFP_KERNEL); 2240 } 2241 if (!skb) 2242 goto errout_skb; 2243 2244 /* Trim skb to allocated size. User is expected to provide buffer as 2245 * large as max(min_dump_alloc, 16KiB (mac_recvmsg_len capped at 2246 * netlink_recvmsg())). dump will pack as many smaller messages as 2247 * could fit within the allocated skb. skb is typically allocated 2248 * with larger space than required (could be as much as near 2x the 2249 * requested size with align to next power of 2 approach). Allowing 2250 * dump to use the excess space makes it difficult for a user to have a 2251 * reasonable static buffer based on the expected largest dump of a 2252 * single netdev. The outcome is MSG_TRUNC error. 2253 */ 2254 skb_reserve(skb, skb_tailroom(skb) - alloc_size); 2255 2256 /* Make sure malicious BPF programs can not read unitialized memory 2257 * from skb->head -> skb->data 2258 */ 2259 skb_reset_network_header(skb); 2260 skb_reset_mac_header(skb); 2261 2262 netlink_skb_set_owner_r(skb, sk); 2263 2264 if (nlk->dump_done_errno > 0) { 2265 cb->extack = &extack; 2266 nlk->dump_done_errno = cb->dump(skb, cb); 2267 cb->extack = NULL; 2268 } 2269 2270 if (nlk->dump_done_errno > 0 || 2271 skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) { 2272 mutex_unlock(nlk->cb_mutex); 2273 2274 if (sk_filter(sk, skb)) 2275 kfree_skb(skb); 2276 else 2277 __netlink_sendskb(sk, skb); 2278 return 0; 2279 } 2280 2281 if (netlink_dump_done(nlk, skb, cb, &extack)) 2282 goto errout_skb; 2283 2284#ifdef CONFIG_COMPAT_NETLINK_MESSAGES 2285 /* frag_list skb's data is used for compat tasks 2286 * and the regular skb's data for normal (non-compat) tasks. 2287 * See netlink_recvmsg(). 2288 */ 2289 if (unlikely(skb_shinfo(skb)->frag_list)) { 2290 if (netlink_dump_done(nlk, skb_shinfo(skb)->frag_list, cb, &extack)) 2291 goto errout_skb; 2292 } 2293#endif 2294 2295 if (sk_filter(sk, skb)) 2296 kfree_skb(skb); 2297 else 2298 __netlink_sendskb(sk, skb); 2299 2300 if (cb->done) 2301 cb->done(cb); 2302 2303 WRITE_ONCE(nlk->cb_running, false); 2304 module = cb->module; 2305 skb = cb->skb; 2306 mutex_unlock(nlk->cb_mutex); 2307 module_put(module); 2308 consume_skb(skb); 2309 return 0; 2310 2311errout_skb: 2312 mutex_unlock(nlk->cb_mutex); 2313 kfree_skb(skb); 2314 return err; 2315} 2316 2317int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, 2318 const struct nlmsghdr *nlh, 2319 struct netlink_dump_control *control) 2320{ 2321 struct netlink_callback *cb; 2322 struct netlink_sock *nlk; 2323 struct sock *sk; 2324 int ret; 2325 2326 refcount_inc(&skb->users); 2327 2328 sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid); 2329 if (sk == NULL) { 2330 ret = -ECONNREFUSED; 2331 goto error_free; 2332 } 2333 2334 nlk = nlk_sk(sk); 2335 mutex_lock(nlk->cb_mutex); 2336 /* A dump is in progress... */ 2337 if (nlk->cb_running) { 2338 ret = -EBUSY; 2339 goto error_unlock; 2340 } 2341 /* add reference of module which cb->dump belongs to */ 2342 if (!try_module_get(control->module)) { 2343 ret = -EPROTONOSUPPORT; 2344 goto error_unlock; 2345 } 2346 2347 cb = &nlk->cb; 2348 memset(cb, 0, sizeof(*cb)); 2349 cb->dump = control->dump; 2350 cb->done = control->done; 2351 cb->nlh = nlh; 2352 cb->data = control->data; 2353 cb->module = control->module; 2354 cb->min_dump_alloc = control->min_dump_alloc; 2355 cb->skb = skb; 2356 2357 cb->strict_check = nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); 2358 2359 if (control->start) { 2360 cb->extack = control->extack; 2361 ret = control->start(cb); 2362 cb->extack = NULL; 2363 if (ret) 2364 goto error_put; 2365 } 2366 2367 WRITE_ONCE(nlk->cb_running, true); 2368 nlk->dump_done_errno = INT_MAX; 2369 2370 mutex_unlock(nlk->cb_mutex); 2371 2372 ret = netlink_dump(sk); 2373 2374 sock_put(sk); 2375 2376 if (ret) 2377 return ret; 2378 2379 /* We successfully started a dump, by returning -EINTR we 2380 * signal not to send ACK even if it was requested. 2381 */ 2382 return -EINTR; 2383 2384error_put: 2385 module_put(control->module); 2386error_unlock: 2387 sock_put(sk); 2388 mutex_unlock(nlk->cb_mutex); 2389error_free: 2390 kfree_skb(skb); 2391 return ret; 2392} 2393EXPORT_SYMBOL(__netlink_dump_start); 2394 2395static size_t 2396netlink_ack_tlv_len(struct netlink_sock *nlk, int err, 2397 const struct netlink_ext_ack *extack) 2398{ 2399 size_t tlvlen; 2400 2401 if (!extack || !test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) 2402 return 0; 2403 2404 tlvlen = 0; 2405 if (extack->_msg) 2406 tlvlen += nla_total_size(strlen(extack->_msg) + 1); 2407 if (extack->cookie_len) 2408 tlvlen += nla_total_size(extack->cookie_len); 2409 2410 /* Following attributes are only reported as error (not warning) */ 2411 if (!err) 2412 return tlvlen; 2413 2414 if (extack->bad_attr) 2415 tlvlen += nla_total_size(sizeof(u32)); 2416 if (extack->policy) 2417 tlvlen += netlink_policy_dump_attr_size_estimate(extack->policy); 2418 if (extack->miss_type) 2419 tlvlen += nla_total_size(sizeof(u32)); 2420 if (extack->miss_nest) 2421 tlvlen += nla_total_size(sizeof(u32)); 2422 2423 return tlvlen; 2424} 2425 2426static void 2427netlink_ack_tlv_fill(struct sk_buff *in_skb, struct sk_buff *skb, 2428 struct nlmsghdr *nlh, int err, 2429 const struct netlink_ext_ack *extack) 2430{ 2431 if (extack->_msg) 2432 WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)); 2433 if (extack->cookie_len) 2434 WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, 2435 extack->cookie_len, extack->cookie)); 2436 2437 if (!err) 2438 return; 2439 2440 if (extack->bad_attr && 2441 !WARN_ON((u8 *)extack->bad_attr < in_skb->data || 2442 (u8 *)extack->bad_attr >= in_skb->data + in_skb->len)) 2443 WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS, 2444 (u8 *)extack->bad_attr - (u8 *)nlh)); 2445 if (extack->policy) 2446 netlink_policy_dump_write_attr(skb, extack->policy, 2447 NLMSGERR_ATTR_POLICY); 2448 if (extack->miss_type) 2449 WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_TYPE, 2450 extack->miss_type)); 2451 if (extack->miss_nest && 2452 !WARN_ON((u8 *)extack->miss_nest < in_skb->data || 2453 (u8 *)extack->miss_nest > in_skb->data + in_skb->len)) 2454 WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_NEST, 2455 (u8 *)extack->miss_nest - (u8 *)nlh)); 2456} 2457 2458void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, 2459 const struct netlink_ext_ack *extack) 2460{ 2461 struct sk_buff *skb; 2462 struct nlmsghdr *rep; 2463 struct nlmsgerr *errmsg; 2464 size_t payload = sizeof(*errmsg); 2465 struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk); 2466 unsigned int flags = 0; 2467 size_t tlvlen; 2468 2469 /* Error messages get the original request appened, unless the user 2470 * requests to cap the error message, and get extra error data if 2471 * requested. 2472 */ 2473 if (err && !test_bit(NETLINK_F_CAP_ACK, &nlk->flags)) 2474 payload += nlmsg_len(nlh); 2475 else 2476 flags |= NLM_F_CAPPED; 2477 2478 tlvlen = netlink_ack_tlv_len(nlk, err, extack); 2479 if (tlvlen) 2480 flags |= NLM_F_ACK_TLVS; 2481 2482 skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); 2483 if (!skb) 2484 goto err_skb; 2485 2486 rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 2487 NLMSG_ERROR, sizeof(*errmsg), flags); 2488 if (!rep) 2489 goto err_bad_put; 2490 errmsg = nlmsg_data(rep); 2491 errmsg->error = err; 2492 errmsg->msg = *nlh; 2493 2494 if (!(flags & NLM_F_CAPPED)) { 2495 if (!nlmsg_append(skb, nlmsg_len(nlh))) 2496 goto err_bad_put; 2497 2498 memcpy(nlmsg_data(&errmsg->msg), nlmsg_data(nlh), 2499 nlmsg_len(nlh)); 2500 } 2501 2502 if (tlvlen) 2503 netlink_ack_tlv_fill(in_skb, skb, nlh, err, extack); 2504 2505 nlmsg_end(skb, rep); 2506 2507 nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid); 2508 2509 return; 2510 2511err_bad_put: 2512 nlmsg_free(skb); 2513err_skb: 2514 WRITE_ONCE(NETLINK_CB(in_skb).sk->sk_err, ENOBUFS); 2515 sk_error_report(NETLINK_CB(in_skb).sk); 2516} 2517EXPORT_SYMBOL(netlink_ack); 2518 2519int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, 2520 struct nlmsghdr *, 2521 struct netlink_ext_ack *)) 2522{ 2523 struct netlink_ext_ack extack; 2524 struct nlmsghdr *nlh; 2525 int err; 2526 2527 while (skb->len >= nlmsg_total_size(0)) { 2528 int msglen; 2529 2530 memset(&extack, 0, sizeof(extack)); 2531 nlh = nlmsg_hdr(skb); 2532 err = 0; 2533 2534 if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) 2535 return 0; 2536 2537 /* Only requests are handled by the kernel */ 2538 if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) 2539 goto ack; 2540 2541 /* Skip control messages */ 2542 if (nlh->nlmsg_type < NLMSG_MIN_TYPE) 2543 goto ack; 2544 2545 err = cb(skb, nlh, &extack); 2546 if (err == -EINTR) 2547 goto skip; 2548 2549ack: 2550 if (nlh->nlmsg_flags & NLM_F_ACK || err) 2551 netlink_ack(skb, nlh, err, &extack); 2552 2553skip: 2554 msglen = NLMSG_ALIGN(nlh->nlmsg_len); 2555 if (msglen > skb->len) 2556 msglen = skb->len; 2557 skb_pull(skb, msglen); 2558 } 2559 2560 return 0; 2561} 2562EXPORT_SYMBOL(netlink_rcv_skb); 2563 2564/** 2565 * nlmsg_notify - send a notification netlink message 2566 * @sk: netlink socket to use 2567 * @skb: notification message 2568 * @portid: destination netlink portid for reports or 0 2569 * @group: destination multicast group or 0 2570 * @report: 1 to report back, 0 to disable 2571 * @flags: allocation flags 2572 */ 2573int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, 2574 unsigned int group, int report, gfp_t flags) 2575{ 2576 int err = 0; 2577 2578 if (group) { 2579 int exclude_portid = 0; 2580 2581 if (report) { 2582 refcount_inc(&skb->users); 2583 exclude_portid = portid; 2584 } 2585 2586 /* errors reported via destination sk->sk_err, but propagate 2587 * delivery errors if NETLINK_BROADCAST_ERROR flag is set */ 2588 err = nlmsg_multicast(sk, skb, exclude_portid, group, flags); 2589 if (err == -ESRCH) 2590 err = 0; 2591 } 2592 2593 if (report) { 2594 int err2; 2595 2596 err2 = nlmsg_unicast(sk, skb, portid); 2597 if (!err) 2598 err = err2; 2599 } 2600 2601 return err; 2602} 2603EXPORT_SYMBOL(nlmsg_notify); 2604 2605#ifdef CONFIG_PROC_FS 2606struct nl_seq_iter { 2607 struct seq_net_private p; 2608 struct rhashtable_iter hti; 2609 int link; 2610}; 2611 2612static void netlink_walk_start(struct nl_seq_iter *iter) 2613{ 2614 rhashtable_walk_enter(&nl_table[iter->link].hash, &iter->hti); 2615 rhashtable_walk_start(&iter->hti); 2616} 2617 2618static void netlink_walk_stop(struct nl_seq_iter *iter) 2619{ 2620 rhashtable_walk_stop(&iter->hti); 2621 rhashtable_walk_exit(&iter->hti); 2622} 2623 2624static void *__netlink_seq_next(struct seq_file *seq) 2625{ 2626 struct nl_seq_iter *iter = seq->private; 2627 struct netlink_sock *nlk; 2628 2629 do { 2630 for (;;) { 2631 nlk = rhashtable_walk_next(&iter->hti); 2632 2633 if (IS_ERR(nlk)) { 2634 if (PTR_ERR(nlk) == -EAGAIN) 2635 continue; 2636 2637 return nlk; 2638 } 2639 2640 if (nlk) 2641 break; 2642 2643 netlink_walk_stop(iter); 2644 if (++iter->link >= MAX_LINKS) 2645 return NULL; 2646 2647 netlink_walk_start(iter); 2648 } 2649 } while (sock_net(&nlk->sk) != seq_file_net(seq)); 2650 2651 return nlk; 2652} 2653 2654static void *netlink_seq_start(struct seq_file *seq, loff_t *posp) 2655 __acquires(RCU) 2656{ 2657 struct nl_seq_iter *iter = seq->private; 2658 void *obj = SEQ_START_TOKEN; 2659 loff_t pos; 2660 2661 iter->link = 0; 2662 2663 netlink_walk_start(iter); 2664 2665 for (pos = *posp; pos && obj && !IS_ERR(obj); pos--) 2666 obj = __netlink_seq_next(seq); 2667 2668 return obj; 2669} 2670 2671static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) 2672{ 2673 ++*pos; 2674 return __netlink_seq_next(seq); 2675} 2676 2677static void netlink_native_seq_stop(struct seq_file *seq, void *v) 2678{ 2679 struct nl_seq_iter *iter = seq->private; 2680 2681 if (iter->link >= MAX_LINKS) 2682 return; 2683 2684 netlink_walk_stop(iter); 2685} 2686 2687 2688static int netlink_native_seq_show(struct seq_file *seq, void *v) 2689{ 2690 if (v == SEQ_START_TOKEN) { 2691 seq_puts(seq, 2692 "sk Eth Pid Groups " 2693 "Rmem Wmem Dump Locks Drops Inode\n"); 2694 } else { 2695 struct sock *s = v; 2696 struct netlink_sock *nlk = nlk_sk(s); 2697 2698 seq_printf(seq, "%pK %-3d %-10u %08x %-8d %-8d %-5d %-8d %-8u %-8lu\n", 2699 s, 2700 s->sk_protocol, 2701 nlk->portid, 2702 nlk->groups ? (u32)nlk->groups[0] : 0, 2703 sk_rmem_alloc_get(s), 2704 sk_wmem_alloc_get(s), 2705 READ_ONCE(nlk->cb_running), 2706 refcount_read(&s->sk_refcnt), 2707 atomic_read(&s->sk_drops), 2708 sock_i_ino(s) 2709 ); 2710 2711 } 2712 return 0; 2713} 2714 2715#ifdef CONFIG_BPF_SYSCALL 2716struct bpf_iter__netlink { 2717 __bpf_md_ptr(struct bpf_iter_meta *, meta); 2718 __bpf_md_ptr(struct netlink_sock *, sk); 2719}; 2720 2721DEFINE_BPF_ITER_FUNC(netlink, struct bpf_iter_meta *meta, struct netlink_sock *sk) 2722 2723static int netlink_prog_seq_show(struct bpf_prog *prog, 2724 struct bpf_iter_meta *meta, 2725 void *v) 2726{ 2727 struct bpf_iter__netlink ctx; 2728 2729 meta->seq_num--; /* skip SEQ_START_TOKEN */ 2730 ctx.meta = meta; 2731 ctx.sk = nlk_sk((struct sock *)v); 2732 return bpf_iter_run_prog(prog, &ctx); 2733} 2734 2735static int netlink_seq_show(struct seq_file *seq, void *v) 2736{ 2737 struct bpf_iter_meta meta; 2738 struct bpf_prog *prog; 2739 2740 meta.seq = seq; 2741 prog = bpf_iter_get_info(&meta, false); 2742 if (!prog) 2743 return netlink_native_seq_show(seq, v); 2744 2745 if (v != SEQ_START_TOKEN) 2746 return netlink_prog_seq_show(prog, &meta, v); 2747 2748 return 0; 2749} 2750 2751static void netlink_seq_stop(struct seq_file *seq, void *v) 2752{ 2753 struct bpf_iter_meta meta; 2754 struct bpf_prog *prog; 2755 2756 if (!v) { 2757 meta.seq = seq; 2758 prog = bpf_iter_get_info(&meta, true); 2759 if (prog) 2760 (void)netlink_prog_seq_show(prog, &meta, v); 2761 } 2762 2763 netlink_native_seq_stop(seq, v); 2764} 2765#else 2766static int netlink_seq_show(struct seq_file *seq, void *v) 2767{ 2768 return netlink_native_seq_show(seq, v); 2769} 2770 2771static void netlink_seq_stop(struct seq_file *seq, void *v) 2772{ 2773 netlink_native_seq_stop(seq, v); 2774} 2775#endif 2776 2777static const struct seq_operations netlink_seq_ops = { 2778 .start = netlink_seq_start, 2779 .next = netlink_seq_next, 2780 .stop = netlink_seq_stop, 2781 .show = netlink_seq_show, 2782}; 2783#endif 2784 2785int netlink_register_notifier(struct notifier_block *nb) 2786{ 2787 return blocking_notifier_chain_register(&netlink_chain, nb); 2788} 2789EXPORT_SYMBOL(netlink_register_notifier); 2790 2791int netlink_unregister_notifier(struct notifier_block *nb) 2792{ 2793 return blocking_notifier_chain_unregister(&netlink_chain, nb); 2794} 2795EXPORT_SYMBOL(netlink_unregister_notifier); 2796 2797static const struct proto_ops netlink_ops = { 2798 .family = PF_NETLINK, 2799 .owner = THIS_MODULE, 2800 .release = netlink_release, 2801 .bind = netlink_bind, 2802 .connect = netlink_connect, 2803 .socketpair = sock_no_socketpair, 2804 .accept = sock_no_accept, 2805 .getname = netlink_getname, 2806 .poll = datagram_poll, 2807 .ioctl = netlink_ioctl, 2808 .listen = sock_no_listen, 2809 .shutdown = sock_no_shutdown, 2810 .setsockopt = netlink_setsockopt, 2811 .getsockopt = netlink_getsockopt, 2812 .sendmsg = netlink_sendmsg, 2813 .recvmsg = netlink_recvmsg, 2814 .mmap = sock_no_mmap, 2815}; 2816 2817static const struct net_proto_family netlink_family_ops = { 2818 .family = PF_NETLINK, 2819 .create = netlink_create, 2820 .owner = THIS_MODULE, /* for consistency 8) */ 2821}; 2822 2823static int __net_init netlink_net_init(struct net *net) 2824{ 2825#ifdef CONFIG_PROC_FS 2826 if (!proc_create_net("netlink", 0, net->proc_net, &netlink_seq_ops, 2827 sizeof(struct nl_seq_iter))) 2828 return -ENOMEM; 2829#endif 2830 return 0; 2831} 2832 2833static void __net_exit netlink_net_exit(struct net *net) 2834{ 2835#ifdef CONFIG_PROC_FS 2836 remove_proc_entry("netlink", net->proc_net); 2837#endif 2838} 2839 2840static void __init netlink_add_usersock_entry(void) 2841{ 2842 struct listeners *listeners; 2843 int groups = 32; 2844 2845 listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); 2846 if (!listeners) 2847 panic("netlink_add_usersock_entry: Cannot allocate listeners\n"); 2848 2849 netlink_table_grab(); 2850 2851 nl_table[NETLINK_USERSOCK].groups = groups; 2852 rcu_assign_pointer(nl_table[NETLINK_USERSOCK].listeners, listeners); 2853 nl_table[NETLINK_USERSOCK].module = THIS_MODULE; 2854 nl_table[NETLINK_USERSOCK].registered = 1; 2855 nl_table[NETLINK_USERSOCK].flags = NL_CFG_F_NONROOT_SEND; 2856 2857 netlink_table_ungrab(); 2858} 2859 2860static struct pernet_operations __net_initdata netlink_net_ops = { 2861 .init = netlink_net_init, 2862 .exit = netlink_net_exit, 2863}; 2864 2865static inline u32 netlink_hash(const void *data, u32 len, u32 seed) 2866{ 2867 const struct netlink_sock *nlk = data; 2868 struct netlink_compare_arg arg; 2869 2870 netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid); 2871 return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed); 2872} 2873 2874static const struct rhashtable_params netlink_rhashtable_params = { 2875 .head_offset = offsetof(struct netlink_sock, node), 2876 .key_len = netlink_compare_arg_len, 2877 .obj_hashfn = netlink_hash, 2878 .obj_cmpfn = netlink_compare, 2879 .automatic_shrinking = true, 2880}; 2881 2882#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) 2883BTF_ID_LIST(btf_netlink_sock_id) 2884BTF_ID(struct, netlink_sock) 2885 2886static const struct bpf_iter_seq_info netlink_seq_info = { 2887 .seq_ops = &netlink_seq_ops, 2888 .init_seq_private = bpf_iter_init_seq_net, 2889 .fini_seq_private = bpf_iter_fini_seq_net, 2890 .seq_priv_size = sizeof(struct nl_seq_iter), 2891}; 2892 2893static struct bpf_iter_reg netlink_reg_info = { 2894 .target = "netlink", 2895 .ctx_arg_info_size = 1, 2896 .ctx_arg_info = { 2897 { offsetof(struct bpf_iter__netlink, sk), 2898 PTR_TO_BTF_ID_OR_NULL }, 2899 }, 2900 .seq_info = &netlink_seq_info, 2901}; 2902 2903static int __init bpf_iter_register(void) 2904{ 2905 netlink_reg_info.ctx_arg_info[0].btf_id = *btf_netlink_sock_id; 2906 return bpf_iter_reg_target(&netlink_reg_info); 2907} 2908#endif 2909 2910static int __init netlink_proto_init(void) 2911{ 2912 int i; 2913 int err = proto_register(&netlink_proto, 0); 2914 2915 if (err != 0) 2916 goto out; 2917 2918#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) 2919 err = bpf_iter_register(); 2920 if (err) 2921 goto out; 2922#endif 2923 2924 BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof_field(struct sk_buff, cb)); 2925 2926 nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL); 2927 if (!nl_table) 2928 goto panic; 2929 2930 for (i = 0; i < MAX_LINKS; i++) { 2931 if (rhashtable_init(&nl_table[i].hash, 2932 &netlink_rhashtable_params) < 0) { 2933 while (--i > 0) 2934 rhashtable_destroy(&nl_table[i].hash); 2935 kfree(nl_table); 2936 goto panic; 2937 } 2938 } 2939 2940 netlink_add_usersock_entry(); 2941 2942 sock_register(&netlink_family_ops); 2943 register_pernet_subsys(&netlink_net_ops); 2944 register_pernet_subsys(&netlink_tap_net_ops); 2945 /* The netlink device handler may be needed early. */ 2946 rtnetlink_init(); 2947out: 2948 return err; 2949panic: 2950 panic("netlink_init: Cannot allocate nl_table\n"); 2951} 2952 2953core_initcall(netlink_proto_init); 2954