forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
af_netlink.c
2873 lines (2408 loc) · 67.1 KB
/
af_netlink.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* NETLINK Kernel-user communication protocol.
*
* Authors: Alan Cox <[email protected]>
* Alexey Kuznetsov <[email protected]>
* Patrick McHardy <[email protected]>
*
* Tue Jun 26 14:36:48 MEST 2001 Herbert "herp" Rosmanith
* added netlink_proto_exit
* Tue Jan 22 18:32:44 BRST 2002 Arnaldo C. de Melo <[email protected]>
* use nlk_sk, as sk->protinfo is on a diet 8)
* Fri Jul 22 19:51:12 MEST 2005 Harald Welte <[email protected]>
* - inc module use count of module that owns
* the kernel socket in case userspace opens
* socket of same protocol
* - remove all module support, since netlink is
* mandatory if CONFIG_NET=y these days
*/
#include <linux/module.h>
#include <linux/capability.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/socket.h>
#include <linux/un.h>
#include <linux/fcntl.h>
#include <linux/termios.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/notifier.h>
#include <linux/security.h>
#include <linux/jhash.h>
#include <linux/jiffies.h>
#include <linux/random.h>
#include <linux/bitops.h>
#include <linux/mm.h>
#include <linux/types.h>
#include <linux/audit.h>
#include <linux/mutex.h>
#include <linux/vmalloc.h>
#include <linux/if_arp.h>
#include <linux/rhashtable.h>
#include <asm/cacheflush.h>
#include <linux/hash.h>
#include <linux/genetlink.h>
#include <linux/net_namespace.h>
#include <linux/nospec.h>
#include <linux/btf_ids.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/sock.h>
#include <net/scm.h>
#include <net/netlink.h>
#include "af_netlink.h"
struct listeners {
struct rcu_head rcu;
unsigned long masks[];
};
/* state bits */
#define NETLINK_S_CONGESTED 0x0
static inline int netlink_is_kernel(struct sock *sk)
{
return nlk_sk(sk)->flags & NETLINK_F_KERNEL_SOCKET;
}
struct netlink_table *nl_table __read_mostly;
EXPORT_SYMBOL_GPL(nl_table);
static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);
static struct lock_class_key nlk_cb_mutex_keys[MAX_LINKS];
static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = {
"nlk_cb_mutex-ROUTE",
"nlk_cb_mutex-1",
"nlk_cb_mutex-USERSOCK",
"nlk_cb_mutex-FIREWALL",
"nlk_cb_mutex-SOCK_DIAG",
"nlk_cb_mutex-NFLOG",
"nlk_cb_mutex-XFRM",
"nlk_cb_mutex-SELINUX",
"nlk_cb_mutex-ISCSI",
"nlk_cb_mutex-AUDIT",
"nlk_cb_mutex-FIB_LOOKUP",
"nlk_cb_mutex-CONNECTOR",
"nlk_cb_mutex-NETFILTER",
"nlk_cb_mutex-IP6_FW",
"nlk_cb_mutex-DNRTMSG",
"nlk_cb_mutex-KOBJECT_UEVENT",
"nlk_cb_mutex-GENERIC",
"nlk_cb_mutex-17",
"nlk_cb_mutex-SCSITRANSPORT",
"nlk_cb_mutex-ECRYPTFS",
"nlk_cb_mutex-RDMA",
"nlk_cb_mutex-CRYPTO",
"nlk_cb_mutex-SMC",
"nlk_cb_mutex-23",
"nlk_cb_mutex-24",
"nlk_cb_mutex-25",
"nlk_cb_mutex-26",
"nlk_cb_mutex-27",
"nlk_cb_mutex-28",
"nlk_cb_mutex-29",
"nlk_cb_mutex-30",
"nlk_cb_mutex-31",
"nlk_cb_mutex-MAX_LINKS"
};
static int netlink_dump(struct sock *sk);
/* nl_table locking explained:
* Lookup and traversal are protected with an RCU read-side lock. Insertion
* and removal are protected with per bucket lock while using RCU list
* modification primitives and may run in parallel to RCU protected lookups.
* Destruction of the Netlink socket may only occur *after* nl_table_lock has
* been acquired * either during or after the socket has been removed from
* the list and after an RCU grace period.
*/
DEFINE_RWLOCK(nl_table_lock);
EXPORT_SYMBOL_GPL(nl_table_lock);
static atomic_t nl_table_users = ATOMIC_INIT(0);
#define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock));
static BLOCKING_NOTIFIER_HEAD(netlink_chain);
static const struct rhashtable_params netlink_rhashtable_params;
static inline u32 netlink_group_mask(u32 group)
{
return group ? 1 << (group - 1) : 0;
}
static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
gfp_t gfp_mask)
{
unsigned int len = skb_end_offset(skb);
struct sk_buff *new;
new = alloc_skb(len, gfp_mask);
if (new == NULL)
return NULL;
NETLINK_CB(new).portid = NETLINK_CB(skb).portid;
NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group;
NETLINK_CB(new).creds = NETLINK_CB(skb).creds;
skb_put_data(new, skb->data, len);
return new;
}
static unsigned int netlink_tap_net_id;
struct netlink_tap_net {
struct list_head netlink_tap_all;
struct mutex netlink_tap_lock;
};
int netlink_add_tap(struct netlink_tap *nt)
{
struct net *net = dev_net(nt->dev);
struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id);
if (unlikely(nt->dev->type != ARPHRD_NETLINK))
return -EINVAL;
mutex_lock(&nn->netlink_tap_lock);
list_add_rcu(&nt->list, &nn->netlink_tap_all);
mutex_unlock(&nn->netlink_tap_lock);
__module_get(nt->module);
return 0;
}
EXPORT_SYMBOL_GPL(netlink_add_tap);
static int __netlink_remove_tap(struct netlink_tap *nt)
{
struct net *net = dev_net(nt->dev);
struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id);
bool found = false;
struct netlink_tap *tmp;
mutex_lock(&nn->netlink_tap_lock);
list_for_each_entry(tmp, &nn->netlink_tap_all, list) {
if (nt == tmp) {
list_del_rcu(&nt->list);
found = true;
goto out;
}
}
pr_warn("__netlink_remove_tap: %p not found\n", nt);
out:
mutex_unlock(&nn->netlink_tap_lock);
if (found)
module_put(nt->module);
return found ? 0 : -ENODEV;
}
int netlink_remove_tap(struct netlink_tap *nt)
{
int ret;
ret = __netlink_remove_tap(nt);
synchronize_net();
return ret;
}
EXPORT_SYMBOL_GPL(netlink_remove_tap);
static __net_init int netlink_tap_init_net(struct net *net)
{
struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id);
INIT_LIST_HEAD(&nn->netlink_tap_all);
mutex_init(&nn->netlink_tap_lock);
return 0;
}
static struct pernet_operations netlink_tap_net_ops = {
.init = netlink_tap_init_net,
.id = &netlink_tap_net_id,
.size = sizeof(struct netlink_tap_net),
};
static bool netlink_filter_tap(const struct sk_buff *skb)
{
struct sock *sk = skb->sk;
/* We take the more conservative approach and
* whitelist socket protocols that may pass.
*/
switch (sk->sk_protocol) {
case NETLINK_ROUTE:
case NETLINK_USERSOCK:
case NETLINK_SOCK_DIAG:
case NETLINK_NFLOG:
case NETLINK_XFRM:
case NETLINK_FIB_LOOKUP:
case NETLINK_NETFILTER:
case NETLINK_GENERIC:
return true;
}
return false;
}
static int __netlink_deliver_tap_skb(struct sk_buff *skb,
struct net_device *dev)
{
struct sk_buff *nskb;
struct sock *sk = skb->sk;
int ret = -ENOMEM;
if (!net_eq(dev_net(dev), sock_net(sk)))
return 0;
dev_hold(dev);
if (is_vmalloc_addr(skb->head))
nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
else
nskb = skb_clone(skb, GFP_ATOMIC);
if (nskb) {
nskb->dev = dev;
nskb->protocol = htons((u16) sk->sk_protocol);
nskb->pkt_type = netlink_is_kernel(sk) ?
PACKET_KERNEL : PACKET_USER;
skb_reset_network_header(nskb);
ret = dev_queue_xmit(nskb);
if (unlikely(ret > 0))
ret = net_xmit_errno(ret);
}
dev_put(dev);
return ret;
}
static void __netlink_deliver_tap(struct sk_buff *skb, struct netlink_tap_net *nn)
{
int ret;
struct netlink_tap *tmp;
if (!netlink_filter_tap(skb))
return;
list_for_each_entry_rcu(tmp, &nn->netlink_tap_all, list) {
ret = __netlink_deliver_tap_skb(skb, tmp->dev);
if (unlikely(ret))
break;
}
}
static void netlink_deliver_tap(struct net *net, struct sk_buff *skb)
{
struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id);
rcu_read_lock();
if (unlikely(!list_empty(&nn->netlink_tap_all)))
__netlink_deliver_tap(skb, nn);
rcu_read_unlock();
}
static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src,
struct sk_buff *skb)
{
if (!(netlink_is_kernel(dst) && netlink_is_kernel(src)))
netlink_deliver_tap(sock_net(dst), skb);
}
static void netlink_overrun(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (!(nlk->flags & NETLINK_F_RECV_NO_ENOBUFS)) {
if (!test_and_set_bit(NETLINK_S_CONGESTED,
&nlk_sk(sk)->state)) {
sk->sk_err = ENOBUFS;
sk->sk_error_report(sk);
}
}
atomic_inc(&sk->sk_drops);
}
static void netlink_rcv_wake(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (skb_queue_empty(&sk->sk_receive_queue))
clear_bit(NETLINK_S_CONGESTED, &nlk->state);
if (!test_bit(NETLINK_S_CONGESTED, &nlk->state))
wake_up_interruptible(&nlk->wait);
}
static void netlink_skb_destructor(struct sk_buff *skb)
{
if (is_vmalloc_addr(skb->head)) {
if (!skb->cloned ||
!atomic_dec_return(&(skb_shinfo(skb)->dataref)))
vfree(skb->head);
skb->head = NULL;
}
if (skb->sk != NULL)
sock_rfree(skb);
}
static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
WARN_ON(skb->sk != NULL);
skb->sk = sk;
skb->destructor = netlink_skb_destructor;
atomic_add(skb->truesize, &sk->sk_rmem_alloc);
sk_mem_charge(sk, skb->truesize);
}
static void netlink_sock_destruct(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (nlk->cb_running) {
if (nlk->cb.done)
nlk->cb.done(&nlk->cb);
module_put(nlk->cb.module);
kfree_skb(nlk->cb.skb);
}
skb_queue_purge(&sk->sk_receive_queue);
if (!sock_flag(sk, SOCK_DEAD)) {
printk(KERN_ERR "Freeing alive netlink socket %p\n", sk);
return;
}
WARN_ON(atomic_read(&sk->sk_rmem_alloc));
WARN_ON(refcount_read(&sk->sk_wmem_alloc));
WARN_ON(nlk_sk(sk)->groups);
}
static void netlink_sock_destruct_work(struct work_struct *work)
{
struct netlink_sock *nlk = container_of(work, struct netlink_sock,
work);
sk_free(&nlk->sk);
}
/* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
* SMP. Look, when several writers sleep and reader wakes them up, all but one
* immediately hit write lock and grab all the cpus. Exclusive sleep solves
* this, _but_ remember, it adds useless work on UP machines.
*/
void netlink_table_grab(void)
__acquires(nl_table_lock)
{
might_sleep();
write_lock_irq(&nl_table_lock);
if (atomic_read(&nl_table_users)) {
DECLARE_WAITQUEUE(wait, current);
add_wait_queue_exclusive(&nl_table_wait, &wait);
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (atomic_read(&nl_table_users) == 0)
break;
write_unlock_irq(&nl_table_lock);
schedule();
write_lock_irq(&nl_table_lock);
}
__set_current_state(TASK_RUNNING);
remove_wait_queue(&nl_table_wait, &wait);
}
}
void netlink_table_ungrab(void)
__releases(nl_table_lock)
{
write_unlock_irq(&nl_table_lock);
wake_up(&nl_table_wait);
}
static inline void
netlink_lock_table(void)
{
/* read_lock() synchronizes us to netlink_table_grab */
read_lock(&nl_table_lock);
atomic_inc(&nl_table_users);
read_unlock(&nl_table_lock);
}
static inline void
netlink_unlock_table(void)
{
if (atomic_dec_and_test(&nl_table_users))
wake_up(&nl_table_wait);
}
struct netlink_compare_arg
{
possible_net_t pnet;
u32 portid;
};
/* Doing sizeof directly may yield 4 extra bytes on 64-bit. */
#define netlink_compare_arg_len \
(offsetof(struct netlink_compare_arg, portid) + sizeof(u32))
static inline int netlink_compare(struct rhashtable_compare_arg *arg,
const void *ptr)
{
const struct netlink_compare_arg *x = arg->key;
const struct netlink_sock *nlk = ptr;
return nlk->portid != x->portid ||
!net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet));
}
static void netlink_compare_arg_init(struct netlink_compare_arg *arg,
struct net *net, u32 portid)
{
memset(arg, 0, sizeof(*arg));
write_pnet(&arg->pnet, net);
arg->portid = portid;
}
static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid,
struct net *net)
{
struct netlink_compare_arg arg;
netlink_compare_arg_init(&arg, net, portid);
return rhashtable_lookup_fast(&table->hash, &arg,
netlink_rhashtable_params);
}
static int __netlink_insert(struct netlink_table *table, struct sock *sk)
{
struct netlink_compare_arg arg;
netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid);
return rhashtable_lookup_insert_key(&table->hash, &arg,
&nlk_sk(sk)->node,
netlink_rhashtable_params);
}
static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid)
{
struct netlink_table *table = &nl_table[protocol];
struct sock *sk;
rcu_read_lock();
sk = __netlink_lookup(table, portid, net);
if (sk)
sock_hold(sk);
rcu_read_unlock();
return sk;
}
static const struct proto_ops netlink_ops;
static void
netlink_update_listeners(struct sock *sk)
{
struct netlink_table *tbl = &nl_table[sk->sk_protocol];
unsigned long mask;
unsigned int i;
struct listeners *listeners;
listeners = nl_deref_protected(tbl->listeners);
if (!listeners)
return;
for (i = 0; i < NLGRPLONGS(tbl->groups); i++) {
mask = 0;
sk_for_each_bound(sk, &tbl->mc_list) {
if (i < NLGRPLONGS(nlk_sk(sk)->ngroups))
mask |= nlk_sk(sk)->groups[i];
}
listeners->masks[i] = mask;
}
/* this function is only called with the netlink table "grabbed", which
* makes sure updates are visible before bind or setsockopt return. */
}
static int netlink_insert(struct sock *sk, u32 portid)
{
struct netlink_table *table = &nl_table[sk->sk_protocol];
int err;
lock_sock(sk);
err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY;
if (nlk_sk(sk)->bound)
goto err;
nlk_sk(sk)->portid = portid;
sock_hold(sk);
err = __netlink_insert(table, sk);
if (err) {
/* In case the hashtable backend returns with -EBUSY
* from here, it must not escape to the caller.
*/
if (unlikely(err == -EBUSY))
err = -EOVERFLOW;
if (err == -EEXIST)
err = -EADDRINUSE;
sock_put(sk);
goto err;
}
/* We need to ensure that the socket is hashed and visible. */
smp_wmb();
nlk_sk(sk)->bound = portid;
err:
release_sock(sk);
return err;
}
static void netlink_remove(struct sock *sk)
{
struct netlink_table *table;
table = &nl_table[sk->sk_protocol];
if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node,
netlink_rhashtable_params)) {
WARN_ON(refcount_read(&sk->sk_refcnt) == 1);
__sock_put(sk);
}
netlink_table_grab();
if (nlk_sk(sk)->subscriptions) {
__sk_del_bind_node(sk);
netlink_update_listeners(sk);
}
if (sk->sk_protocol == NETLINK_GENERIC)
atomic_inc(&genl_sk_destructing_cnt);
netlink_table_ungrab();
}
static struct proto netlink_proto = {
.name = "NETLINK",
.owner = THIS_MODULE,
.obj_size = sizeof(struct netlink_sock),
};
static int __netlink_create(struct net *net, struct socket *sock,
struct mutex *cb_mutex, int protocol,
int kern)
{
struct sock *sk;
struct netlink_sock *nlk;
sock->ops = &netlink_ops;
sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto, kern);
if (!sk)
return -ENOMEM;
sock_init_data(sock, sk);
nlk = nlk_sk(sk);
if (cb_mutex) {
nlk->cb_mutex = cb_mutex;
} else {
nlk->cb_mutex = &nlk->cb_def_mutex;
mutex_init(nlk->cb_mutex);
lockdep_set_class_and_name(nlk->cb_mutex,
nlk_cb_mutex_keys + protocol,
nlk_cb_mutex_key_strings[protocol]);
}
init_waitqueue_head(&nlk->wait);
sk->sk_destruct = netlink_sock_destruct;
sk->sk_protocol = protocol;
return 0;
}
static int netlink_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
struct module *module = NULL;
struct mutex *cb_mutex;
struct netlink_sock *nlk;
int (*bind)(struct net *net, int group);
void (*unbind)(struct net *net, int group);
int err = 0;
sock->state = SS_UNCONNECTED;
if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
return -ESOCKTNOSUPPORT;
if (protocol < 0 || protocol >= MAX_LINKS)
return -EPROTONOSUPPORT;
protocol = array_index_nospec(protocol, MAX_LINKS);
netlink_lock_table();
#ifdef CONFIG_MODULES
if (!nl_table[protocol].registered) {
netlink_unlock_table();
request_module("net-pf-%d-proto-%d", PF_NETLINK, protocol);
netlink_lock_table();
}
#endif
if (nl_table[protocol].registered &&
try_module_get(nl_table[protocol].module))
module = nl_table[protocol].module;
else
err = -EPROTONOSUPPORT;
cb_mutex = nl_table[protocol].cb_mutex;
bind = nl_table[protocol].bind;
unbind = nl_table[protocol].unbind;
netlink_unlock_table();
if (err < 0)
goto out;
err = __netlink_create(net, sock, cb_mutex, protocol, kern);
if (err < 0)
goto out_module;
local_bh_disable();
sock_prot_inuse_add(net, &netlink_proto, 1);
local_bh_enable();
nlk = nlk_sk(sock->sk);
nlk->module = module;
nlk->netlink_bind = bind;
nlk->netlink_unbind = unbind;
out:
return err;
out_module:
module_put(module);
goto out;
}
static void deferred_put_nlk_sk(struct rcu_head *head)
{
struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
struct sock *sk = &nlk->sk;
kfree(nlk->groups);
nlk->groups = NULL;
if (!refcount_dec_and_test(&sk->sk_refcnt))
return;
if (nlk->cb_running && nlk->cb.done) {
INIT_WORK(&nlk->work, netlink_sock_destruct_work);
schedule_work(&nlk->work);
return;
}
sk_free(sk);
}
static int netlink_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct netlink_sock *nlk;
if (!sk)
return 0;
netlink_remove(sk);
sock_orphan(sk);
nlk = nlk_sk(sk);
/*
* OK. Socket is unlinked, any packets that arrive now
* will be purged.
*/
/* must not acquire netlink_table_lock in any way again before unbind
* and notifying genetlink is done as otherwise it might deadlock
*/
if (nlk->netlink_unbind) {
int i;
for (i = 0; i < nlk->ngroups; i++)
if (test_bit(i, nlk->groups))
nlk->netlink_unbind(sock_net(sk), i + 1);
}
if (sk->sk_protocol == NETLINK_GENERIC &&
atomic_dec_return(&genl_sk_destructing_cnt) == 0)
wake_up(&genl_sk_destructing_waitq);
sock->sk = NULL;
wake_up_interruptible_all(&nlk->wait);
skb_queue_purge(&sk->sk_write_queue);
if (nlk->portid && nlk->bound) {
struct netlink_notify n = {
.net = sock_net(sk),
.protocol = sk->sk_protocol,
.portid = nlk->portid,
};
blocking_notifier_call_chain(&netlink_chain,
NETLINK_URELEASE, &n);
}
module_put(nlk->module);
if (netlink_is_kernel(sk)) {
netlink_table_grab();
BUG_ON(nl_table[sk->sk_protocol].registered == 0);
if (--nl_table[sk->sk_protocol].registered == 0) {
struct listeners *old;
old = nl_deref_protected(nl_table[sk->sk_protocol].listeners);
RCU_INIT_POINTER(nl_table[sk->sk_protocol].listeners, NULL);
kfree_rcu(old, rcu);
nl_table[sk->sk_protocol].module = NULL;
nl_table[sk->sk_protocol].bind = NULL;
nl_table[sk->sk_protocol].unbind = NULL;
nl_table[sk->sk_protocol].flags = 0;
nl_table[sk->sk_protocol].registered = 0;
}
netlink_table_ungrab();
}
local_bh_disable();
sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1);
local_bh_enable();
call_rcu(&nlk->rcu, deferred_put_nlk_sk);
return 0;
}
static int netlink_autobind(struct socket *sock)
{
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
struct netlink_table *table = &nl_table[sk->sk_protocol];
s32 portid = task_tgid_vnr(current);
int err;
s32 rover = -4096;
bool ok;
retry:
cond_resched();
rcu_read_lock();
ok = !__netlink_lookup(table, portid, net);
rcu_read_unlock();
if (!ok) {
/* Bind collision, search negative portid values. */
if (rover == -4096)
/* rover will be in range [S32_MIN, -4097] */
rover = S32_MIN + prandom_u32_max(-4096 - S32_MIN);
else if (rover >= -4096)
rover = -4097;
portid = rover--;
goto retry;
}
err = netlink_insert(sk, portid);
if (err == -EADDRINUSE)
goto retry;
/* If 2 threads race to autobind, that is fine. */
if (err == -EBUSY)
err = 0;
return err;
}
/**
* __netlink_ns_capable - General netlink message capability test
* @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace.
* @user_ns: The user namespace of the capability to use
* @cap: The capability to use
*
* Test to see if the opener of the socket we received the message
* from had when the netlink socket was created and the sender of the
* message has has the capability @cap in the user namespace @user_ns.
*/
bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
struct user_namespace *user_ns, int cap)
{
return ((nsp->flags & NETLINK_SKB_DST) ||
file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) &&
ns_capable(user_ns, cap);
}
EXPORT_SYMBOL(__netlink_ns_capable);
/**
* netlink_ns_capable - General netlink message capability test
* @skb: socket buffer holding a netlink command from userspace
* @user_ns: The user namespace of the capability to use
* @cap: The capability to use
*
* Test to see if the opener of the socket we received the message
* from had when the netlink socket was created and the sender of the
* message has has the capability @cap in the user namespace @user_ns.
*/
bool netlink_ns_capable(const struct sk_buff *skb,
struct user_namespace *user_ns, int cap)
{
return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap);
}
EXPORT_SYMBOL(netlink_ns_capable);
/**
* netlink_capable - Netlink global message capability test
* @skb: socket buffer holding a netlink command from userspace
* @cap: The capability to use
*
* Test to see if the opener of the socket we received the message
* from had when the netlink socket was created and the sender of the
* message has has the capability @cap in all user namespaces.
*/
bool netlink_capable(const struct sk_buff *skb, int cap)
{
return netlink_ns_capable(skb, &init_user_ns, cap);
}
EXPORT_SYMBOL(netlink_capable);
/**
* netlink_net_capable - Netlink network namespace message capability test
* @skb: socket buffer holding a netlink command from userspace
* @cap: The capability to use
*
* Test to see if the opener of the socket we received the message
* from had when the netlink socket was created and the sender of the
* message has has the capability @cap over the network namespace of
* the socket we received the message from.
*/
bool netlink_net_capable(const struct sk_buff *skb, int cap)
{
return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap);
}
EXPORT_SYMBOL(netlink_net_capable);
static inline int netlink_allowed(const struct socket *sock, unsigned int flag)
{
return (nl_table[sock->sk->sk_protocol].flags & flag) ||
ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN);
}
static void
netlink_update_subscriptions(struct sock *sk, unsigned int subscriptions)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (nlk->subscriptions && !subscriptions)
__sk_del_bind_node(sk);
else if (!nlk->subscriptions && subscriptions)
sk_add_bind_node(sk, &nl_table[sk->sk_protocol].mc_list);
nlk->subscriptions = subscriptions;
}
static int netlink_realloc_groups(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
unsigned int groups;
unsigned long *new_groups;
int err = 0;
netlink_table_grab();
groups = nl_table[sk->sk_protocol].groups;
if (!nl_table[sk->sk_protocol].registered) {
err = -ENOENT;
goto out_unlock;
}
if (nlk->ngroups >= groups)
goto out_unlock;
new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_ATOMIC);
if (new_groups == NULL) {
err = -ENOMEM;
goto out_unlock;
}
memset((char *)new_groups + NLGRPSZ(nlk->ngroups), 0,
NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups));
nlk->groups = new_groups;
nlk->ngroups = groups;
out_unlock:
netlink_table_ungrab();
return err;
}
static void netlink_undo_bind(int group, long unsigned int groups,
struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
int undo;
if (!nlk->netlink_unbind)
return;
for (undo = 0; undo < group; undo++)
if (test_bit(undo, &groups))
nlk->netlink_unbind(sock_net(sk), undo + 1);
}
static int netlink_bind(struct socket *sock, struct sockaddr *addr,
int addr_len)
{
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
struct netlink_sock *nlk = nlk_sk(sk);
struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
int err = 0;
unsigned long groups;
bool bound;
if (addr_len < sizeof(struct sockaddr_nl))
return -EINVAL;
if (nladdr->nl_family != AF_NETLINK)
return -EINVAL;
groups = nladdr->nl_groups;
/* Only superuser is allowed to listen multicasts */
if (groups) {
if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
return -EPERM;
err = netlink_realloc_groups(sk);
if (err)
return err;
}