forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
af_unix.c
2316 lines (1956 loc) · 52.8 KB
/
af_unix.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
/*
* NET4: Implementation of BSD Unix domain sockets.
*
* Authors: Alan Cox, <[email protected]>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Fixes:
* Linus Torvalds : Assorted bug cures.
* Niibe Yutaka : async I/O support.
* Carsten Paeth : PF_UNIX check, address fixes.
* Alan Cox : Limit size of allocated blocks.
* Alan Cox : Fixed the stupid socketpair bug.
* Alan Cox : BSD compatibility fine tuning.
* Alan Cox : Fixed a bug in connect when interrupted.
* Alan Cox : Sorted out a proper draft version of
* file descriptor passing hacked up from
* Mike Shaver's work.
* Marty Leisner : Fixes to fd passing
* Nick Nevin : recvmsg bugfix.
* Alan Cox : Started proper garbage collector
* Heiko EiBfeldt : Missing verify_area check
* Alan Cox : Started POSIXisms
* Andreas Schwab : Replace inode by dentry for proper
* reference counting
* Kirk Petersen : Made this a module
* Christoph Rohland : Elegant non-blocking accept/connect algorithm.
* Lots of bug fixes.
* Alexey Kuznetosv : Repaired (I hope) bugs introduces
* by above two patches.
* Andrea Arcangeli : If possible we block in connect(2)
* if the max backlog of the listen socket
* is been reached. This won't break
* old apps and it will avoid huge amount
* of socks hashed (this for unix_gc()
* performances reasons).
* Security fix that limits the max
* number of socks to 2*max_files and
* the number of skb queueable in the
* dgram receiver.
* Artur Skawina : Hash function optimizations
* Alexey Kuznetsov : Full scale SMP. Lot of bugs are introduced 8)
* Malcolm Beattie : Set peercred for socketpair
* Michal Ostrowski : Module initialization cleanup.
* Arnaldo C. Melo : Remove MOD_{INC,DEC}_USE_COUNT,
* the core infrastructure is doing that
* for all net proto families now (2.5.69+)
*
*
* Known differences from reference BSD that was tested:
*
* [TO FIX]
* ECONNREFUSED is not returned from one end of a connected() socket to the
* other the moment one end closes.
* fstat() doesn't return st_dev=0, and give the blksize as high water mark
* and a fake inode identifier (nor the BSD first socket fstat twice bug).
* [NOT TO FIX]
* accept() returns a path name even if the connecting socket has closed
* in the meantime (BSD loses the path and gives up).
* accept() returns 0 length path for an unbound connector. BSD returns 16
* and a null first byte in the path (but not for gethost/peername - BSD bug ??)
* socketpair(...SOCK_RAW..) doesn't panic the kernel.
* BSD af_unix apparently has connect forgetting to block properly.
* (need to check this with the POSIX spec in detail)
*
* Differences from 2.0.0-11-... (ANK)
* Bug fixes and improvements.
* - client shutdown killed server socket.
* - removed all useless cli/sti pairs.
*
* Semantic changes/extensions.
* - generic control message passing.
* - SCM_CREDENTIALS control message.
* - "Abstract" (not FS based) socket bindings.
* Abstract names are sequences of bytes (not zero terminated)
* started by 0, so that this name space does not intersect
* with BSD names.
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/dcache.h>
#include <linux/namei.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/in.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <net/af_unix.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <net/scm.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/rtnetlink.h>
#include <linux/mount.h>
#include <net/checksum.h>
#include <linux/security.h>
static struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
static DEFINE_SPINLOCK(unix_table_lock);
static atomic_t unix_nr_socks = ATOMIC_INIT(0);
#define unix_sockets_unbound (&unix_socket_table[UNIX_HASH_SIZE])
#define UNIX_ABSTRACT(sk) (unix_sk(sk)->addr->hash != UNIX_HASH_SIZE)
#ifdef CONFIG_SECURITY_NETWORK
static void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb)
{
memcpy(UNIXSID(skb), &scm->secid, sizeof(u32));
}
static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
{
scm->secid = *UNIXSID(skb);
}
#else
static inline void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb)
{ }
static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
{ }
#endif /* CONFIG_SECURITY_NETWORK */
/*
* SMP locking strategy:
* hash table is protected with spinlock unix_table_lock
* each socket state is protected by separate spin lock.
*/
static inline unsigned unix_hash_fold(__wsum n)
{
unsigned hash = (__force unsigned)n;
hash ^= hash>>16;
hash ^= hash>>8;
return hash&(UNIX_HASH_SIZE-1);
}
#define unix_peer(sk) (unix_sk(sk)->peer)
static inline int unix_our_peer(struct sock *sk, struct sock *osk)
{
return unix_peer(osk) == sk;
}
static inline int unix_may_send(struct sock *sk, struct sock *osk)
{
return unix_peer(osk) == NULL || unix_our_peer(sk, osk);
}
static inline int unix_recvq_full(struct sock const *sk)
{
return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog;
}
static struct sock *unix_peer_get(struct sock *s)
{
struct sock *peer;
unix_state_lock(s);
peer = unix_peer(s);
if (peer)
sock_hold(peer);
unix_state_unlock(s);
return peer;
}
static inline void unix_release_addr(struct unix_address *addr)
{
if (atomic_dec_and_test(&addr->refcnt))
kfree(addr);
}
/*
* Check unix socket name:
* - should be not zero length.
* - if started by not zero, should be NULL terminated (FS object)
* - if started by zero, it is abstract name.
*/
static int unix_mkname(struct sockaddr_un *sunaddr, int len, unsigned *hashp)
{
if (len <= sizeof(short) || len > sizeof(*sunaddr))
return -EINVAL;
if (!sunaddr || sunaddr->sun_family != AF_UNIX)
return -EINVAL;
if (sunaddr->sun_path[0]) {
/*
* This may look like an off by one error but it is a bit more
* subtle. 108 is the longest valid AF_UNIX path for a binding.
* sun_path[108] doesnt as such exist. However in kernel space
* we are guaranteed that it is a valid memory location in our
* kernel address buffer.
*/
((char *)sunaddr)[len] = 0;
len = strlen(sunaddr->sun_path)+1+sizeof(short);
return len;
}
*hashp = unix_hash_fold(csum_partial(sunaddr, len, 0));
return len;
}
static void __unix_remove_socket(struct sock *sk)
{
sk_del_node_init(sk);
}
static void __unix_insert_socket(struct hlist_head *list, struct sock *sk)
{
WARN_ON(!sk_unhashed(sk));
sk_add_node(sk, list);
}
static inline void unix_remove_socket(struct sock *sk)
{
spin_lock(&unix_table_lock);
__unix_remove_socket(sk);
spin_unlock(&unix_table_lock);
}
static inline void unix_insert_socket(struct hlist_head *list, struct sock *sk)
{
spin_lock(&unix_table_lock);
__unix_insert_socket(list, sk);
spin_unlock(&unix_table_lock);
}
static struct sock *__unix_find_socket_byname(struct net *net,
struct sockaddr_un *sunname,
int len, int type, unsigned hash)
{
struct sock *s;
struct hlist_node *node;
sk_for_each(s, node, &unix_socket_table[hash ^ type]) {
struct unix_sock *u = unix_sk(s);
if (!net_eq(sock_net(s), net))
continue;
if (u->addr->len == len &&
!memcmp(u->addr->name, sunname, len))
goto found;
}
s = NULL;
found:
return s;
}
static inline struct sock *unix_find_socket_byname(struct net *net,
struct sockaddr_un *sunname,
int len, int type,
unsigned hash)
{
struct sock *s;
spin_lock(&unix_table_lock);
s = __unix_find_socket_byname(net, sunname, len, type, hash);
if (s)
sock_hold(s);
spin_unlock(&unix_table_lock);
return s;
}
static struct sock *unix_find_socket_byinode(struct inode *i)
{
struct sock *s;
struct hlist_node *node;
spin_lock(&unix_table_lock);
sk_for_each(s, node,
&unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) {
struct dentry *dentry = unix_sk(s)->dentry;
if (dentry && dentry->d_inode == i) {
sock_hold(s);
goto found;
}
}
s = NULL;
found:
spin_unlock(&unix_table_lock);
return s;
}
static inline int unix_writable(struct sock *sk)
{
return (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
}
static void unix_write_space(struct sock *sk)
{
struct socket_wq *wq;
rcu_read_lock();
if (unix_writable(sk)) {
wq = rcu_dereference(sk->sk_wq);
if (wq_has_sleeper(wq))
wake_up_interruptible_sync(&wq->wait);
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
}
rcu_read_unlock();
}
/* When dgram socket disconnects (or changes its peer), we clear its receive
* queue of packets arrived from previous peer. First, it allows to do
* flow control based only on wmem_alloc; second, sk connected to peer
* may receive messages only from that peer. */
static void unix_dgram_disconnected(struct sock *sk, struct sock *other)
{
if (!skb_queue_empty(&sk->sk_receive_queue)) {
skb_queue_purge(&sk->sk_receive_queue);
wake_up_interruptible_all(&unix_sk(sk)->peer_wait);
/* If one link of bidirectional dgram pipe is disconnected,
* we signal error. Messages are lost. Do not make this,
* when peer was not connected to us.
*/
if (!sock_flag(other, SOCK_DEAD) && unix_peer(other) == sk) {
other->sk_err = ECONNRESET;
other->sk_error_report(other);
}
}
}
static void unix_sock_destructor(struct sock *sk)
{
struct unix_sock *u = unix_sk(sk);
skb_queue_purge(&sk->sk_receive_queue);
WARN_ON(atomic_read(&sk->sk_wmem_alloc));
WARN_ON(!sk_unhashed(sk));
WARN_ON(sk->sk_socket);
if (!sock_flag(sk, SOCK_DEAD)) {
printk(KERN_INFO "Attempt to release alive unix socket: %p\n", sk);
return;
}
if (u->addr)
unix_release_addr(u->addr);
atomic_dec(&unix_nr_socks);
local_bh_disable();
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
local_bh_enable();
#ifdef UNIX_REFCNT_DEBUG
printk(KERN_DEBUG "UNIX %p is destroyed, %d are still alive.\n", sk,
atomic_read(&unix_nr_socks));
#endif
}
static int unix_release_sock(struct sock *sk, int embrion)
{
struct unix_sock *u = unix_sk(sk);
struct dentry *dentry;
struct vfsmount *mnt;
struct sock *skpair;
struct sk_buff *skb;
int state;
unix_remove_socket(sk);
/* Clear state */
unix_state_lock(sk);
sock_orphan(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
dentry = u->dentry;
u->dentry = NULL;
mnt = u->mnt;
u->mnt = NULL;
state = sk->sk_state;
sk->sk_state = TCP_CLOSE;
unix_state_unlock(sk);
wake_up_interruptible_all(&u->peer_wait);
skpair = unix_peer(sk);
if (skpair != NULL) {
if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) {
unix_state_lock(skpair);
/* No more writes */
skpair->sk_shutdown = SHUTDOWN_MASK;
if (!skb_queue_empty(&sk->sk_receive_queue) || embrion)
skpair->sk_err = ECONNRESET;
unix_state_unlock(skpair);
skpair->sk_state_change(skpair);
sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
}
sock_put(skpair); /* It may now die */
unix_peer(sk) = NULL;
}
/* Try to flush out this socket. Throw out buffers at least */
while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) {
if (state == TCP_LISTEN)
unix_release_sock(skb->sk, 1);
/* passed fds are erased in the kfree_skb hook */
kfree_skb(skb);
}
if (dentry) {
dput(dentry);
mntput(mnt);
}
sock_put(sk);
/* ---- Socket is dead now and most probably destroyed ---- */
/*
* Fixme: BSD difference: In BSD all sockets connected to use get
* ECONNRESET and we die on the spot. In Linux we behave
* like files and pipes do and wait for the last
* dereference.
*
* Can't we simply set sock->err?
*
* What the above comment does talk about? --ANK(980817)
*/
if (unix_tot_inflight)
unix_gc(); /* Garbage collect fds */
return 0;
}
static void init_peercred(struct sock *sk)
{
put_pid(sk->sk_peer_pid);
if (sk->sk_peer_cred)
put_cred(sk->sk_peer_cred);
sk->sk_peer_pid = get_pid(task_tgid(current));
sk->sk_peer_cred = get_current_cred();
}
static void copy_peercred(struct sock *sk, struct sock *peersk)
{
put_pid(sk->sk_peer_pid);
if (sk->sk_peer_cred)
put_cred(sk->sk_peer_cred);
sk->sk_peer_pid = get_pid(peersk->sk_peer_pid);
sk->sk_peer_cred = get_cred(peersk->sk_peer_cred);
}
static int unix_listen(struct socket *sock, int backlog)
{
int err;
struct sock *sk = sock->sk;
struct unix_sock *u = unix_sk(sk);
struct pid *old_pid = NULL;
const struct cred *old_cred = NULL;
err = -EOPNOTSUPP;
if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET)
goto out; /* Only stream/seqpacket sockets accept */
err = -EINVAL;
if (!u->addr)
goto out; /* No listens on an unbound socket */
unix_state_lock(sk);
if (sk->sk_state != TCP_CLOSE && sk->sk_state != TCP_LISTEN)
goto out_unlock;
if (backlog > sk->sk_max_ack_backlog)
wake_up_interruptible_all(&u->peer_wait);
sk->sk_max_ack_backlog = backlog;
sk->sk_state = TCP_LISTEN;
/* set credentials so connect can copy them */
init_peercred(sk);
err = 0;
out_unlock:
unix_state_unlock(sk);
put_pid(old_pid);
if (old_cred)
put_cred(old_cred);
out:
return err;
}
static int unix_release(struct socket *);
static int unix_bind(struct socket *, struct sockaddr *, int);
static int unix_stream_connect(struct socket *, struct sockaddr *,
int addr_len, int flags);
static int unix_socketpair(struct socket *, struct socket *);
static int unix_accept(struct socket *, struct socket *, int);
static int unix_getname(struct socket *, struct sockaddr *, int *, int);
static unsigned int unix_poll(struct file *, struct socket *, poll_table *);
static unsigned int unix_dgram_poll(struct file *, struct socket *,
poll_table *);
static int unix_ioctl(struct socket *, unsigned int, unsigned long);
static int unix_shutdown(struct socket *, int);
static int unix_stream_sendmsg(struct kiocb *, struct socket *,
struct msghdr *, size_t);
static int unix_stream_recvmsg(struct kiocb *, struct socket *,
struct msghdr *, size_t, int);
static int unix_dgram_sendmsg(struct kiocb *, struct socket *,
struct msghdr *, size_t);
static int unix_dgram_recvmsg(struct kiocb *, struct socket *,
struct msghdr *, size_t, int);
static int unix_dgram_connect(struct socket *, struct sockaddr *,
int, int);
static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *,
struct msghdr *, size_t);
static const struct proto_ops unix_stream_ops = {
.family = PF_UNIX,
.owner = THIS_MODULE,
.release = unix_release,
.bind = unix_bind,
.connect = unix_stream_connect,
.socketpair = unix_socketpair,
.accept = unix_accept,
.getname = unix_getname,
.poll = unix_poll,
.ioctl = unix_ioctl,
.listen = unix_listen,
.shutdown = unix_shutdown,
.setsockopt = sock_no_setsockopt,
.getsockopt = sock_no_getsockopt,
.sendmsg = unix_stream_sendmsg,
.recvmsg = unix_stream_recvmsg,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
};
static const struct proto_ops unix_dgram_ops = {
.family = PF_UNIX,
.owner = THIS_MODULE,
.release = unix_release,
.bind = unix_bind,
.connect = unix_dgram_connect,
.socketpair = unix_socketpair,
.accept = sock_no_accept,
.getname = unix_getname,
.poll = unix_dgram_poll,
.ioctl = unix_ioctl,
.listen = sock_no_listen,
.shutdown = unix_shutdown,
.setsockopt = sock_no_setsockopt,
.getsockopt = sock_no_getsockopt,
.sendmsg = unix_dgram_sendmsg,
.recvmsg = unix_dgram_recvmsg,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
};
static const struct proto_ops unix_seqpacket_ops = {
.family = PF_UNIX,
.owner = THIS_MODULE,
.release = unix_release,
.bind = unix_bind,
.connect = unix_stream_connect,
.socketpair = unix_socketpair,
.accept = unix_accept,
.getname = unix_getname,
.poll = unix_dgram_poll,
.ioctl = unix_ioctl,
.listen = unix_listen,
.shutdown = unix_shutdown,
.setsockopt = sock_no_setsockopt,
.getsockopt = sock_no_getsockopt,
.sendmsg = unix_seqpacket_sendmsg,
.recvmsg = unix_dgram_recvmsg,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
};
static struct proto unix_proto = {
.name = "UNIX",
.owner = THIS_MODULE,
.obj_size = sizeof(struct unix_sock),
};
/*
* AF_UNIX sockets do not interact with hardware, hence they
* dont trigger interrupts - so it's safe for them to have
* bh-unsafe locking for their sk_receive_queue.lock. Split off
* this special lock-class by reinitializing the spinlock key:
*/
static struct lock_class_key af_unix_sk_receive_queue_lock_key;
static struct sock *unix_create1(struct net *net, struct socket *sock)
{
struct sock *sk = NULL;
struct unix_sock *u;
atomic_inc(&unix_nr_socks);
if (atomic_read(&unix_nr_socks) > 2 * get_max_files())
goto out;
sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto);
if (!sk)
goto out;
sock_init_data(sock, sk);
lockdep_set_class(&sk->sk_receive_queue.lock,
&af_unix_sk_receive_queue_lock_key);
sk->sk_write_space = unix_write_space;
sk->sk_max_ack_backlog = net->unx.sysctl_max_dgram_qlen;
sk->sk_destruct = unix_sock_destructor;
u = unix_sk(sk);
u->dentry = NULL;
u->mnt = NULL;
spin_lock_init(&u->lock);
atomic_long_set(&u->inflight, 0);
INIT_LIST_HEAD(&u->link);
mutex_init(&u->readlock); /* single task reading lock */
init_waitqueue_head(&u->peer_wait);
unix_insert_socket(unix_sockets_unbound, sk);
out:
if (sk == NULL)
atomic_dec(&unix_nr_socks);
else {
local_bh_disable();
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
local_bh_enable();
}
return sk;
}
static int unix_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
if (protocol && protocol != PF_UNIX)
return -EPROTONOSUPPORT;
sock->state = SS_UNCONNECTED;
switch (sock->type) {
case SOCK_STREAM:
sock->ops = &unix_stream_ops;
break;
/*
* Believe it or not BSD has AF_UNIX, SOCK_RAW though
* nothing uses it.
*/
case SOCK_RAW:
sock->type = SOCK_DGRAM;
case SOCK_DGRAM:
sock->ops = &unix_dgram_ops;
break;
case SOCK_SEQPACKET:
sock->ops = &unix_seqpacket_ops;
break;
default:
return -ESOCKTNOSUPPORT;
}
return unix_create1(net, sock) ? 0 : -ENOMEM;
}
static int unix_release(struct socket *sock)
{
struct sock *sk = sock->sk;
if (!sk)
return 0;
sock->sk = NULL;
return unix_release_sock(sk, 0);
}
static int unix_autobind(struct socket *sock)
{
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
struct unix_sock *u = unix_sk(sk);
static u32 ordernum = 1;
struct unix_address *addr;
int err;
mutex_lock(&u->readlock);
err = 0;
if (u->addr)
goto out;
err = -ENOMEM;
addr = kzalloc(sizeof(*addr) + sizeof(short) + 16, GFP_KERNEL);
if (!addr)
goto out;
addr->name->sun_family = AF_UNIX;
atomic_set(&addr->refcnt, 1);
retry:
addr->len = sprintf(addr->name->sun_path+1, "%05x", ordernum) + 1 + sizeof(short);
addr->hash = unix_hash_fold(csum_partial(addr->name, addr->len, 0));
spin_lock(&unix_table_lock);
ordernum = (ordernum+1)&0xFFFFF;
if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type,
addr->hash)) {
spin_unlock(&unix_table_lock);
/* Sanity yield. It is unusual case, but yet... */
if (!(ordernum&0xFF))
yield();
goto retry;
}
addr->hash ^= sk->sk_type;
__unix_remove_socket(sk);
u->addr = addr;
__unix_insert_socket(&unix_socket_table[addr->hash], sk);
spin_unlock(&unix_table_lock);
err = 0;
out: mutex_unlock(&u->readlock);
return err;
}
static struct sock *unix_find_other(struct net *net,
struct sockaddr_un *sunname, int len,
int type, unsigned hash, int *error)
{
struct sock *u;
struct path path;
int err = 0;
if (sunname->sun_path[0]) {
struct inode *inode;
err = kern_path(sunname->sun_path, LOOKUP_FOLLOW, &path);
if (err)
goto fail;
inode = path.dentry->d_inode;
err = inode_permission(inode, MAY_WRITE);
if (err)
goto put_fail;
err = -ECONNREFUSED;
if (!S_ISSOCK(inode->i_mode))
goto put_fail;
u = unix_find_socket_byinode(inode);
if (!u)
goto put_fail;
if (u->sk_type == type)
touch_atime(path.mnt, path.dentry);
path_put(&path);
err = -EPROTOTYPE;
if (u->sk_type != type) {
sock_put(u);
goto fail;
}
} else {
err = -ECONNREFUSED;
u = unix_find_socket_byname(net, sunname, len, type, hash);
if (u) {
struct dentry *dentry;
dentry = unix_sk(u)->dentry;
if (dentry)
touch_atime(unix_sk(u)->mnt, dentry);
} else
goto fail;
}
return u;
put_fail:
path_put(&path);
fail:
*error = err;
return NULL;
}
static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
struct unix_sock *u = unix_sk(sk);
struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
struct dentry *dentry = NULL;
struct nameidata nd;
int err;
unsigned hash;
struct unix_address *addr;
struct hlist_head *list;
err = -EINVAL;
if (sunaddr->sun_family != AF_UNIX)
goto out;
if (addr_len == sizeof(short)) {
err = unix_autobind(sock);
goto out;
}
err = unix_mkname(sunaddr, addr_len, &hash);
if (err < 0)
goto out;
addr_len = err;
mutex_lock(&u->readlock);
err = -EINVAL;
if (u->addr)
goto out_up;
err = -ENOMEM;
addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
if (!addr)
goto out_up;
memcpy(addr->name, sunaddr, addr_len);
addr->len = addr_len;
addr->hash = hash ^ sk->sk_type;
atomic_set(&addr->refcnt, 1);
if (sunaddr->sun_path[0]) {
unsigned int mode;
err = 0;
/*
* Get the parent directory, calculate the hash for last
* component.
*/
err = path_lookup(sunaddr->sun_path, LOOKUP_PARENT, &nd);
if (err)
goto out_mknod_parent;
dentry = lookup_create(&nd, 0);
err = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto out_mknod_unlock;
/*
* All right, let's create it.
*/
mode = S_IFSOCK |
(SOCK_INODE(sock)->i_mode & ~current_umask());
err = mnt_want_write(nd.path.mnt);
if (err)
goto out_mknod_dput;
err = security_path_mknod(&nd.path, dentry, mode, 0);
if (err)
goto out_mknod_drop_write;
err = vfs_mknod(nd.path.dentry->d_inode, dentry, mode, 0);
out_mknod_drop_write:
mnt_drop_write(nd.path.mnt);
if (err)
goto out_mknod_dput;
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
dput(nd.path.dentry);
nd.path.dentry = dentry;
addr->hash = UNIX_HASH_SIZE;
}
spin_lock(&unix_table_lock);
if (!sunaddr->sun_path[0]) {
err = -EADDRINUSE;
if (__unix_find_socket_byname(net, sunaddr, addr_len,
sk->sk_type, hash)) {
unix_release_addr(addr);
goto out_unlock;
}
list = &unix_socket_table[addr->hash];
} else {
list = &unix_socket_table[dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1)];
u->dentry = nd.path.dentry;
u->mnt = nd.path.mnt;
}
err = 0;
__unix_remove_socket(sk);
u->addr = addr;
__unix_insert_socket(list, sk);
out_unlock:
spin_unlock(&unix_table_lock);
out_up:
mutex_unlock(&u->readlock);
out:
return err;
out_mknod_dput:
dput(dentry);
out_mknod_unlock:
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
path_put(&nd.path);
out_mknod_parent:
if (err == -EEXIST)
err = -EADDRINUSE;
unix_release_addr(addr);
goto out_up;
}
static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
{
if (unlikely(sk1 == sk2) || !sk2) {
unix_state_lock(sk1);
return;
}
if (sk1 < sk2) {
unix_state_lock(sk1);
unix_state_lock_nested(sk2);
} else {
unix_state_lock(sk2);
unix_state_lock_nested(sk1);
}
}
static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2)
{
if (unlikely(sk1 == sk2) || !sk2) {
unix_state_unlock(sk1);
return;
}
unix_state_unlock(sk1);
unix_state_unlock(sk2);
}
static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
int alen, int flags)
{
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
struct sockaddr_un *sunaddr = (struct sockaddr_un *)addr;
struct sock *other;
unsigned hash;
int err;
if (addr->sa_family != AF_UNSPEC) {
err = unix_mkname(sunaddr, alen, &hash);
if (err < 0)
goto out;
alen = err;
if (test_bit(SOCK_PASSCRED, &sock->flags) &&
!unix_sk(sk)->addr && (err = unix_autobind(sock)) != 0)
goto out;
restart:
other = unix_find_other(net, sunaddr, alen, sock->type, hash, &err);
if (!other)
goto out;
unix_state_double_lock(sk, other);
/* Apparently VFS overslept socket death. Retry. */
if (sock_flag(other, SOCK_DEAD)) {
unix_state_double_unlock(sk, other);
sock_put(other);
goto restart;
}
err = -EPERM;
if (!unix_may_send(sk, other))
goto out_unlock;
err = security_unix_may_send(sk->sk_socket, other->sk_socket);
if (err)
goto out_unlock;
} else {
/*
* 1003.1g breaking connected state with AF_UNSPEC
*/
other = NULL;
unix_state_double_lock(sk, other);
}
/*
* If it was connected, reconnect.
*/
if (unix_peer(sk)) {
struct sock *old_peer = unix_peer(sk);
unix_peer(sk) = other;
unix_state_double_unlock(sk, other);
if (other != old_peer)
unix_dgram_disconnected(sk, old_peer);