forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
sock.c
2966 lines (2530 loc) · 73.1 KB
/
sock.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
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Generic socket support routines. Memory allocators, socket lock/release
* handler for protocols to use and generic option handler.
*
*
* Authors: Ross Biro
* Fred N. van Kempen, <[email protected]>
* Florian La Roche, <[email protected]>
* Alan Cox, <[email protected]>
*
* Fixes:
* Alan Cox : Numerous verify_area() problems
* Alan Cox : Connecting on a connecting socket
* now returns an error for tcp.
* Alan Cox : sock->protocol is set correctly.
* and is not sometimes left as 0.
* Alan Cox : connect handles icmp errors on a
* connect properly. Unfortunately there
* is a restart syscall nasty there. I
* can't match BSD without hacking the C
* library. Ideas urgently sought!
* Alan Cox : Disallow bind() to addresses that are
* not ours - especially broadcast ones!!
* Alan Cox : Socket 1024 _IS_ ok for users. (fencepost)
* Alan Cox : sock_wfree/sock_rfree don't destroy sockets,
* instead they leave that for the DESTROY timer.
* Alan Cox : Clean up error flag in accept
* Alan Cox : TCP ack handling is buggy, the DESTROY timer
* was buggy. Put a remove_sock() in the handler
* for memory when we hit 0. Also altered the timer
* code. The ACK stuff can wait and needs major
* TCP layer surgery.
* Alan Cox : Fixed TCP ack bug, removed remove sock
* and fixed timer/inet_bh race.
* Alan Cox : Added zapped flag for TCP
* Alan Cox : Move kfree_skb into skbuff.c and tidied up surplus code
* Alan Cox : for new sk_buff allocations wmalloc/rmalloc now call alloc_skb
* Alan Cox : kfree_s calls now are kfree_skbmem so we can track skb resources
* Alan Cox : Supports socket option broadcast now as does udp. Packet and raw need fixing.
* Alan Cox : Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so...
* Rick Sladkey : Relaxed UDP rules for matching packets.
* C.E.Hawkins : IFF_PROMISC/SIOCGHWADDR support
* Pauline Middelink : identd support
* Alan Cox : Fixed connect() taking signals I think.
* Alan Cox : SO_LINGER supported
* Alan Cox : Error reporting fixes
* Anonymous : inet_create tidied up (sk->reuse setting)
* Alan Cox : inet sockets don't set sk->type!
* Alan Cox : Split socket option code
* Alan Cox : Callbacks
* Alan Cox : Nagle flag for Charles & Johannes stuff
* Alex : Removed restriction on inet fioctl
* Alan Cox : Splitting INET from NET core
* Alan Cox : Fixed bogus SO_TYPE handling in getsockopt()
* Adam Caldwell : Missing return in SO_DONTROUTE/SO_DEBUG code
* Alan Cox : Split IP from generic code
* Alan Cox : New kfree_skbmem()
* Alan Cox : Make SO_DEBUG superuser only.
* Alan Cox : Allow anyone to clear SO_DEBUG
* (compatibility fix)
* Alan Cox : Added optimistic memory grabbing for AF_UNIX throughput.
* Alan Cox : Allocator for a socket is settable.
* Alan Cox : SO_ERROR includes soft errors.
* Alan Cox : Allow NULL arguments on some SO_ opts
* Alan Cox : Generic socket allocation to make hooks
* easier (suggested by Craig Metz).
* Michael Pall : SO_ERROR returns positive errno again
* Steve Whitehouse: Added default destructor to free
* protocol private data.
* Steve Whitehouse: Added various other default routines
* common to several socket families.
* Chris Evans : Call suser() check last on F_SETOWN
* Jay Schulist : Added SO_ATTACH_FILTER and SO_DETACH_FILTER.
* Andi Kleen : Add sock_kmalloc()/sock_kfree_s()
* Andi Kleen : Fix write_space callback
* Chris Evans : Security fixes - signedness again
* Arnaldo C. Melo : cleanups, use skb_queue_purge
*
* To Fix:
*
*
* 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.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/errqueue.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/poll.h>
#include <linux/tcp.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/user_namespace.h>
#include <linux/static_key.h>
#include <linux/memcontrol.h>
#include <linux/prefetch.h>
#include <asm/uaccess.h>
#include <linux/netdevice.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/net_namespace.h>
#include <net/request_sock.h>
#include <net/sock.h>
#include <linux/net_tstamp.h>
#include <net/xfrm.h>
#include <linux/ipsec.h>
#include <net/cls_cgroup.h>
#include <net/netprio_cgroup.h>
#include <linux/filter.h>
#include <trace/events/sock.h>
#ifdef CONFIG_INET
#include <net/tcp.h>
#endif
#include <net/busy_poll.h>
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
#ifdef CONFIG_MEMCG_KMEM
int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
struct proto *proto;
int ret = 0;
mutex_lock(&proto_list_mutex);
list_for_each_entry(proto, &proto_list, node) {
if (proto->init_cgroup) {
ret = proto->init_cgroup(memcg, ss);
if (ret)
goto out;
}
}
mutex_unlock(&proto_list_mutex);
return ret;
out:
list_for_each_entry_continue_reverse(proto, &proto_list, node)
if (proto->destroy_cgroup)
proto->destroy_cgroup(memcg);
mutex_unlock(&proto_list_mutex);
return ret;
}
void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg)
{
struct proto *proto;
mutex_lock(&proto_list_mutex);
list_for_each_entry_reverse(proto, &proto_list, node)
if (proto->destroy_cgroup)
proto->destroy_cgroup(memcg);
mutex_unlock(&proto_list_mutex);
}
#endif
/*
* Each address family might have different locking rules, so we have
* one slock key per address family:
*/
static struct lock_class_key af_family_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];
#if defined(CONFIG_MEMCG_KMEM)
struct static_key memcg_socket_limit_enabled;
EXPORT_SYMBOL(memcg_socket_limit_enabled);
#endif
/*
* Make lock validator output more readable. (we pre-construct these
* strings build-time, so that runtime initialization of socket
* locks is fast):
*/
static const char *const af_family_key_strings[AF_MAX+1] = {
"sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX" , "sk_lock-AF_INET" ,
"sk_lock-AF_AX25" , "sk_lock-AF_IPX" , "sk_lock-AF_APPLETALK",
"sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE" , "sk_lock-AF_ATMPVC" ,
"sk_lock-AF_X25" , "sk_lock-AF_INET6" , "sk_lock-AF_ROSE" ,
"sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI" , "sk_lock-AF_SECURITY" ,
"sk_lock-AF_KEY" , "sk_lock-AF_NETLINK" , "sk_lock-AF_PACKET" ,
"sk_lock-AF_ASH" , "sk_lock-AF_ECONET" , "sk_lock-AF_ATMSVC" ,
"sk_lock-AF_RDS" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" ,
"sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" ,
"sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" ,
"sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" ,
"sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" ,
"sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" ,
"sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_MAX"
};
static const char *const af_family_slock_key_strings[AF_MAX+1] = {
"slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" ,
"slock-AF_AX25" , "slock-AF_IPX" , "slock-AF_APPLETALK",
"slock-AF_NETROM", "slock-AF_BRIDGE" , "slock-AF_ATMPVC" ,
"slock-AF_X25" , "slock-AF_INET6" , "slock-AF_ROSE" ,
"slock-AF_DECnet", "slock-AF_NETBEUI" , "slock-AF_SECURITY" ,
"slock-AF_KEY" , "slock-AF_NETLINK" , "slock-AF_PACKET" ,
"slock-AF_ASH" , "slock-AF_ECONET" , "slock-AF_ATMSVC" ,
"slock-AF_RDS" , "slock-AF_SNA" , "slock-AF_IRDA" ,
"slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" ,
"slock-27" , "slock-28" , "slock-AF_CAN" ,
"slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" ,
"slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" ,
"slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" ,
"slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_MAX"
};
static const char *const af_family_clock_key_strings[AF_MAX+1] = {
"clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" ,
"clock-AF_AX25" , "clock-AF_IPX" , "clock-AF_APPLETALK",
"clock-AF_NETROM", "clock-AF_BRIDGE" , "clock-AF_ATMPVC" ,
"clock-AF_X25" , "clock-AF_INET6" , "clock-AF_ROSE" ,
"clock-AF_DECnet", "clock-AF_NETBEUI" , "clock-AF_SECURITY" ,
"clock-AF_KEY" , "clock-AF_NETLINK" , "clock-AF_PACKET" ,
"clock-AF_ASH" , "clock-AF_ECONET" , "clock-AF_ATMSVC" ,
"clock-AF_RDS" , "clock-AF_SNA" , "clock-AF_IRDA" ,
"clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" ,
"clock-27" , "clock-28" , "clock-AF_CAN" ,
"clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" ,
"clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" ,
"clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" ,
"clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_MAX"
};
/*
* sk_callback_lock locking rules are per-address-family,
* so split the lock classes by using a per-AF key:
*/
static struct lock_class_key af_callback_keys[AF_MAX];
/* Take into consideration the size of the struct sk_buff overhead in the
* determination of these values, since that is non-constant across
* platforms. This makes socket queueing behavior and performance
* not depend upon such differences.
*/
#define _SK_MEM_PACKETS 256
#define _SK_MEM_OVERHEAD SKB_TRUESIZE(256)
#define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
#define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
/* Run time adjustable parameters. */
__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
EXPORT_SYMBOL(sysctl_wmem_max);
__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
EXPORT_SYMBOL(sysctl_rmem_max);
__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
/* Maximal space eaten by iovec or ancillary data plus some space */
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
EXPORT_SYMBOL(sysctl_optmem_max);
struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE;
EXPORT_SYMBOL_GPL(memalloc_socks);
/**
* sk_set_memalloc - sets %SOCK_MEMALLOC
* @sk: socket to set it on
*
* Set %SOCK_MEMALLOC on a socket for access to emergency reserves.
* It's the responsibility of the admin to adjust min_free_kbytes
* to meet the requirements
*/
void sk_set_memalloc(struct sock *sk)
{
sock_set_flag(sk, SOCK_MEMALLOC);
sk->sk_allocation |= __GFP_MEMALLOC;
static_key_slow_inc(&memalloc_socks);
}
EXPORT_SYMBOL_GPL(sk_set_memalloc);
void sk_clear_memalloc(struct sock *sk)
{
sock_reset_flag(sk, SOCK_MEMALLOC);
sk->sk_allocation &= ~__GFP_MEMALLOC;
static_key_slow_dec(&memalloc_socks);
/*
* SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
* progress of swapping. However, if SOCK_MEMALLOC is cleared while
* it has rmem allocations there is a risk that the user of the
* socket cannot make forward progress due to exceeding the rmem
* limits. By rights, sk_clear_memalloc() should only be called
* on sockets being torn down but warn and reset the accounting if
* that assumption breaks.
*/
if (WARN_ON(sk->sk_forward_alloc))
sk_mem_reclaim(sk);
}
EXPORT_SYMBOL_GPL(sk_clear_memalloc);
int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
int ret;
unsigned long pflags = current->flags;
/* these should have been dropped before queueing */
BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));
current->flags |= PF_MEMALLOC;
ret = sk->sk_backlog_rcv(sk, skb);
tsk_restore_flags(current, pflags, PF_MEMALLOC);
return ret;
}
EXPORT_SYMBOL(__sk_backlog_rcv);
static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
{
struct timeval tv;
if (optlen < sizeof(tv))
return -EINVAL;
if (copy_from_user(&tv, optval, sizeof(tv)))
return -EFAULT;
if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC)
return -EDOM;
if (tv.tv_sec < 0) {
static int warned __read_mostly;
*timeo_p = 0;
if (warned < 10 && net_ratelimit()) {
warned++;
pr_info("%s: `%s' (pid %d) tries to set negative timeout\n",
__func__, current->comm, task_pid_nr(current));
}
return 0;
}
*timeo_p = MAX_SCHEDULE_TIMEOUT;
if (tv.tv_sec == 0 && tv.tv_usec == 0)
return 0;
if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT/HZ - 1))
*timeo_p = tv.tv_sec*HZ + (tv.tv_usec+(1000000/HZ-1))/(1000000/HZ);
return 0;
}
static void sock_warn_obsolete_bsdism(const char *name)
{
static int warned;
static char warncomm[TASK_COMM_LEN];
if (strcmp(warncomm, current->comm) && warned < 5) {
strcpy(warncomm, current->comm);
pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n",
warncomm, name);
warned++;
}
}
#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
{
if (sk->sk_flags & flags) {
sk->sk_flags &= ~flags;
if (!(sk->sk_flags & SK_FLAGS_TIMESTAMP))
net_disable_timestamp();
}
}
int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int err;
int skb_len;
unsigned long flags;
struct sk_buff_head *list = &sk->sk_receive_queue;
if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) {
atomic_inc(&sk->sk_drops);
trace_sock_rcvqueue_full(sk, skb);
return -ENOMEM;
}
err = sk_filter(sk, skb);
if (err)
return err;
if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
atomic_inc(&sk->sk_drops);
return -ENOBUFS;
}
skb->dev = NULL;
skb_set_owner_r(skb, sk);
/* Cache the SKB length before we tack it onto the receive
* queue. Once it is added it no longer belongs to us and
* may be freed by other threads of control pulling packets
* from the queue.
*/
skb_len = skb->len;
/* we escape from rcu protected region, make sure we dont leak
* a norefcounted dst
*/
skb_dst_force(skb);
spin_lock_irqsave(&list->lock, flags);
skb->dropcount = atomic_read(&sk->sk_drops);
__skb_queue_tail(list, skb);
spin_unlock_irqrestore(&list->lock, flags);
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_data_ready(sk, skb_len);
return 0;
}
EXPORT_SYMBOL(sock_queue_rcv_skb);
int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
{
int rc = NET_RX_SUCCESS;
if (sk_filter(sk, skb))
goto discard_and_relse;
skb->dev = NULL;
if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) {
atomic_inc(&sk->sk_drops);
goto discard_and_relse;
}
if (nested)
bh_lock_sock_nested(sk);
else
bh_lock_sock(sk);
if (!sock_owned_by_user(sk)) {
/*
* trylock + unlock semantics:
*/
mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_);
rc = sk_backlog_rcv(sk, skb);
mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
} else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) {
bh_unlock_sock(sk);
atomic_inc(&sk->sk_drops);
goto discard_and_relse;
}
bh_unlock_sock(sk);
out:
sock_put(sk);
return rc;
discard_and_relse:
kfree_skb(skb);
goto out;
}
EXPORT_SYMBOL(sk_receive_skb);
struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
{
struct dst_entry *dst = __sk_dst_get(sk);
if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
sk_tx_queue_clear(sk);
RCU_INIT_POINTER(sk->sk_dst_cache, NULL);
dst_release(dst);
return NULL;
}
return dst;
}
EXPORT_SYMBOL(__sk_dst_check);
struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie)
{
struct dst_entry *dst = sk_dst_get(sk);
if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
sk_dst_reset(sk);
dst_release(dst);
return NULL;
}
return dst;
}
EXPORT_SYMBOL(sk_dst_check);
static int sock_setbindtodevice(struct sock *sk, char __user *optval,
int optlen)
{
int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
struct net *net = sock_net(sk);
char devname[IFNAMSIZ];
int index;
/* Sorry... */
ret = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_RAW))
goto out;
ret = -EINVAL;
if (optlen < 0)
goto out;
/* Bind this socket to a particular device like "eth0",
* as specified in the passed interface name. If the
* name is "" or the option length is zero the socket
* is not bound.
*/
if (optlen > IFNAMSIZ - 1)
optlen = IFNAMSIZ - 1;
memset(devname, 0, sizeof(devname));
ret = -EFAULT;
if (copy_from_user(devname, optval, optlen))
goto out;
index = 0;
if (devname[0] != '\0') {
struct net_device *dev;
rcu_read_lock();
dev = dev_get_by_name_rcu(net, devname);
if (dev)
index = dev->ifindex;
rcu_read_unlock();
ret = -ENODEV;
if (!dev)
goto out;
}
lock_sock(sk);
sk->sk_bound_dev_if = index;
sk_dst_reset(sk);
release_sock(sk);
ret = 0;
out:
#endif
return ret;
}
static int sock_getbindtodevice(struct sock *sk, char __user *optval,
int __user *optlen, int len)
{
int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
struct net *net = sock_net(sk);
char devname[IFNAMSIZ];
if (sk->sk_bound_dev_if == 0) {
len = 0;
goto zero;
}
ret = -EINVAL;
if (len < IFNAMSIZ)
goto out;
ret = netdev_get_name(net, devname, sk->sk_bound_dev_if);
if (ret)
goto out;
len = strlen(devname) + 1;
ret = -EFAULT;
if (copy_to_user(optval, devname, len))
goto out;
zero:
ret = -EFAULT;
if (put_user(len, optlen))
goto out;
ret = 0;
out:
#endif
return ret;
}
static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
{
if (valbool)
sock_set_flag(sk, bit);
else
sock_reset_flag(sk, bit);
}
/*
* This is meant for all protocols to use and covers goings on
* at the socket level. Everything here is generic.
*/
int sock_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
int val;
int valbool;
struct linger ling;
int ret = 0;
/*
* Options without arguments
*/
if (optname == SO_BINDTODEVICE)
return sock_setbindtodevice(sk, optval, optlen);
if (optlen < sizeof(int))
return -EINVAL;
if (get_user(val, (int __user *)optval))
return -EFAULT;
valbool = val ? 1 : 0;
lock_sock(sk);
switch (optname) {
case SO_DEBUG:
if (val && !capable(CAP_NET_ADMIN))
ret = -EACCES;
else
sock_valbool_flag(sk, SOCK_DBG, valbool);
break;
case SO_REUSEADDR:
sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE);
break;
case SO_REUSEPORT:
sk->sk_reuseport = valbool;
break;
case SO_TYPE:
case SO_PROTOCOL:
case SO_DOMAIN:
case SO_ERROR:
ret = -ENOPROTOOPT;
break;
case SO_DONTROUTE:
sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool);
break;
case SO_BROADCAST:
sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
break;
case SO_SNDBUF:
/* Don't error on this BSD doesn't and if you think
* about it this is right. Otherwise apps have to
* play 'guess the biggest size' games. RCVBUF/SNDBUF
* are treated in BSD as hints
*/
val = min_t(u32, val, sysctl_wmem_max);
set_sndbuf:
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF);
/* Wake up sending tasks if we upped the value. */
sk->sk_write_space(sk);
break;
case SO_SNDBUFFORCE:
if (!capable(CAP_NET_ADMIN)) {
ret = -EPERM;
break;
}
goto set_sndbuf;
case SO_RCVBUF:
/* Don't error on this BSD doesn't and if you think
* about it this is right. Otherwise apps have to
* play 'guess the biggest size' games. RCVBUF/SNDBUF
* are treated in BSD as hints
*/
val = min_t(u32, val, sysctl_rmem_max);
set_rcvbuf:
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
/*
* We double it on the way in to account for
* "struct sk_buff" etc. overhead. Applications
* assume that the SO_RCVBUF setting they make will
* allow that much actual data to be received on that
* socket.
*
* Applications are unaware that "struct sk_buff" and
* other overheads allocate from the receive buffer
* during socket buffer allocation.
*
* And after considering the possible alternatives,
* returning the value we actually used in getsockopt
* is the most desirable behavior.
*/
sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF);
break;
case SO_RCVBUFFORCE:
if (!capable(CAP_NET_ADMIN)) {
ret = -EPERM;
break;
}
goto set_rcvbuf;
case SO_KEEPALIVE:
#ifdef CONFIG_INET
if (sk->sk_protocol == IPPROTO_TCP &&
sk->sk_type == SOCK_STREAM)
tcp_set_keepalive(sk, valbool);
#endif
sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
break;
case SO_OOBINLINE:
sock_valbool_flag(sk, SOCK_URGINLINE, valbool);
break;
case SO_NO_CHECK:
sk->sk_no_check = valbool;
break;
case SO_PRIORITY:
if ((val >= 0 && val <= 6) ||
ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
sk->sk_priority = val;
else
ret = -EPERM;
break;
case SO_LINGER:
if (optlen < sizeof(ling)) {
ret = -EINVAL; /* 1003.1g */
break;
}
if (copy_from_user(&ling, optval, sizeof(ling))) {
ret = -EFAULT;
break;
}
if (!ling.l_onoff)
sock_reset_flag(sk, SOCK_LINGER);
else {
#if (BITS_PER_LONG == 32)
if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
else
#endif
sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
sock_set_flag(sk, SOCK_LINGER);
}
break;
case SO_BSDCOMPAT:
sock_warn_obsolete_bsdism("setsockopt");
break;
case SO_PASSCRED:
if (valbool)
set_bit(SOCK_PASSCRED, &sock->flags);
else
clear_bit(SOCK_PASSCRED, &sock->flags);
break;
case SO_TIMESTAMP:
case SO_TIMESTAMPNS:
if (valbool) {
if (optname == SO_TIMESTAMP)
sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
else
sock_set_flag(sk, SOCK_RCVTSTAMPNS);
sock_set_flag(sk, SOCK_RCVTSTAMP);
sock_enable_timestamp(sk, SOCK_TIMESTAMP);
} else {
sock_reset_flag(sk, SOCK_RCVTSTAMP);
sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
}
break;
case SO_TIMESTAMPING:
if (val & ~SOF_TIMESTAMPING_MASK) {
ret = -EINVAL;
break;
}
sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE,
val & SOF_TIMESTAMPING_TX_HARDWARE);
sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE,
val & SOF_TIMESTAMPING_TX_SOFTWARE);
sock_valbool_flag(sk, SOCK_TIMESTAMPING_RX_HARDWARE,
val & SOF_TIMESTAMPING_RX_HARDWARE);
if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
sock_enable_timestamp(sk,
SOCK_TIMESTAMPING_RX_SOFTWARE);
else
sock_disable_timestamp(sk,
(1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
sock_valbool_flag(sk, SOCK_TIMESTAMPING_SOFTWARE,
val & SOF_TIMESTAMPING_SOFTWARE);
sock_valbool_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE,
val & SOF_TIMESTAMPING_SYS_HARDWARE);
sock_valbool_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE,
val & SOF_TIMESTAMPING_RAW_HARDWARE);
break;
case SO_RCVLOWAT:
if (val < 0)
val = INT_MAX;
sk->sk_rcvlowat = val ? : 1;
break;
case SO_RCVTIMEO:
ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen);
break;
case SO_SNDTIMEO:
ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen);
break;
case SO_ATTACH_FILTER:
ret = -EINVAL;
if (optlen == sizeof(struct sock_fprog)) {
struct sock_fprog fprog;
ret = -EFAULT;
if (copy_from_user(&fprog, optval, sizeof(fprog)))
break;
ret = sk_attach_filter(&fprog, sk);
}
break;
case SO_DETACH_FILTER:
ret = sk_detach_filter(sk);
break;
case SO_LOCK_FILTER:
if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool)
ret = -EPERM;
else
sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool);
break;
case SO_PASSSEC:
if (valbool)
set_bit(SOCK_PASSSEC, &sock->flags);
else
clear_bit(SOCK_PASSSEC, &sock->flags);
break;
case SO_MARK:
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
ret = -EPERM;
else
sk->sk_mark = val;
break;
/* We implement the SO_SNDLOWAT etc to
not be settable (1003.1g 5.3) */
case SO_RXQ_OVFL:
sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool);
break;
case SO_WIFI_STATUS:
sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool);
break;
case SO_PEEK_OFF:
if (sock->ops->set_peek_off)
ret = sock->ops->set_peek_off(sk, val);
else
ret = -EOPNOTSUPP;
break;
case SO_NOFCS:
sock_valbool_flag(sk, SOCK_NOFCS, valbool);
break;
case SO_SELECT_ERR_QUEUE:
sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool);
break;
#ifdef CONFIG_NET_RX_BUSY_POLL
case SO_BUSY_POLL:
/* allow unprivileged users to decrease the value */
if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN))
ret = -EPERM;
else {
if (val < 0)
ret = -EINVAL;
else
sk->sk_ll_usec = val;
}
break;
#endif
case SO_MAX_PACING_RATE:
sk->sk_max_pacing_rate = val;
sk->sk_pacing_rate = min(sk->sk_pacing_rate,
sk->sk_max_pacing_rate);
break;
default:
ret = -ENOPROTOOPT;
break;
}
release_sock(sk);
return ret;
}
EXPORT_SYMBOL(sock_setsockopt);
void cred_to_ucred(struct pid *pid, const struct cred *cred,
struct ucred *ucred)
{
ucred->pid = pid_vnr(pid);
ucred->uid = ucred->gid = -1;
if (cred) {
struct user_namespace *current_ns = current_user_ns();
ucred->uid = from_kuid_munged(current_ns, cred->euid);
ucred->gid = from_kgid_munged(current_ns, cred->egid);
}
}
EXPORT_SYMBOL_GPL(cred_to_ucred);
int sock_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
union {
int val;
struct linger ling;
struct timeval tm;
} v;
int lv = sizeof(int);
int len;
if (get_user(len, optlen))
return -EFAULT;
if (len < 0)
return -EINVAL;
memset(&v, 0, sizeof(v));
switch (optname) {
case SO_DEBUG:
v.val = sock_flag(sk, SOCK_DBG);
break;
case SO_DONTROUTE:
v.val = sock_flag(sk, SOCK_LOCALROUTE);
break;
case SO_BROADCAST:
v.val = sock_flag(sk, SOCK_BROADCAST);
break;
case SO_SNDBUF:
v.val = sk->sk_sndbuf;
break;
case SO_RCVBUF:
v.val = sk->sk_rcvbuf;
break;
case SO_REUSEADDR:
v.val = sk->sk_reuse;
break;
case SO_REUSEPORT:
v.val = sk->sk_reuseport;
break;
case SO_KEEPALIVE:
v.val = sock_flag(sk, SOCK_KEEPOPEN);
break;
case SO_TYPE:
v.val = sk->sk_type;
break;
case SO_PROTOCOL: