-
Notifications
You must be signed in to change notification settings - Fork 53.6k
/
af_inet.c
2120 lines (1815 loc) · 52 KB
/
af_inet.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
/*
* 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.
*
* PF_INET protocol family socket handler.
*
* Authors: Ross Biro
* Fred N. van Kempen, <[email protected]>
* Florian La Roche, <[email protected]>
* Alan Cox, <[email protected]>
*
* Changes (see also sock.c)
*
* piggy,
* Karl Knutson : Socket protocol table
* A.N.Kuznetsov : Socket death error in accept().
* John Richardson : Fix non blocking error in connect()
* so sockets that fail to connect
* don't return -EINPROGRESS.
* Alan Cox : Asynchronous I/O support
* Alan Cox : Keep correct socket pointer on sock
* structures
* when accept() ed
* Alan Cox : Semantics of SO_LINGER aren't state
* moved to close when you look carefully.
* With this fixed and the accept bug fixed
* some RPC stuff seems happier.
* Niibe Yutaka : 4.4BSD style write async I/O
* Alan Cox,
* Tony Gale : Fixed reuse semantics.
* Alan Cox : bind() shouldn't abort existing but dead
* sockets. Stops FTP netin:.. I hope.
* Alan Cox : bind() works correctly for RAW sockets.
* Note that FreeBSD at least was broken
* in this respect so be careful with
* compatibility tests...
* Alan Cox : routing cache support
* Alan Cox : memzero the socket structure for
* compactness.
* Matt Day : nonblock connect error handler
* Alan Cox : Allow large numbers of pending sockets
* (eg for big web sites), but only if
* specifically application requested.
* Alan Cox : New buffering throughout IP. Used
* dumbly.
* Alan Cox : New buffering now used smartly.
* Alan Cox : BSD rather than common sense
* interpretation of listen.
* Germano Caronni : Assorted small races.
* Alan Cox : sendmsg/recvmsg basic support.
* Alan Cox : Only sendmsg/recvmsg now supported.
* Alan Cox : Locked down bind (see security list).
* Alan Cox : Loosened bind a little.
* Mike McLagan : ADD/DEL DLCI Ioctls
* Willy Konynenberg : Transparent proxying support.
* David S. Miller : New socket lookup architecture.
* Some other random speedups.
* Cyrus Durgin : Cleaned up file for kmod hacks.
* Andi Kleen : Fix inet_stream_connect TCP race.
*/
#define pr_fmt(fmt) "IPv4: " fmt
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/capability.h>
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/netfilter_ipv4.h>
#include <linux/random.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/inet.h>
#include <linux/igmp.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <net/checksum.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.h>
#include <net/route.h>
#include <net/ip_fib.h>
#include <net/inet_connection_sock.h>
#include <net/gro.h>
#include <net/gso.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/udplite.h>
#include <net/ping.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/raw.h>
#include <net/icmp.h>
#include <net/inet_common.h>
#include <net/ip_tunnels.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/secure_seq.h>
#ifdef CONFIG_IP_MROUTE
#include <linux/mroute.h>
#endif
#include <net/l3mdev.h>
#include <net/compat.h>
#include <net/rps.h>
#include <trace/events/sock.h>
/* The inetsw table contains everything that inet_create needs to
* build a new socket.
*/
static struct list_head inetsw[SOCK_MAX];
static DEFINE_SPINLOCK(inetsw_lock);
/* New destruction routine */
void inet_sock_destruct(struct sock *sk)
{
struct inet_sock *inet = inet_sk(sk);
__skb_queue_purge(&sk->sk_receive_queue);
__skb_queue_purge(&sk->sk_error_queue);
sk_mem_reclaim_final(sk);
if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) {
pr_err("Attempt to release TCP socket in state %d %p\n",
sk->sk_state, sk);
return;
}
if (!sock_flag(sk, SOCK_DEAD)) {
pr_err("Attempt to release alive inet socket %p\n", sk);
return;
}
WARN_ON_ONCE(atomic_read(&sk->sk_rmem_alloc));
WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc));
WARN_ON_ONCE(sk->sk_wmem_queued);
WARN_ON_ONCE(sk_forward_alloc_get(sk));
kfree(rcu_dereference_protected(inet->inet_opt, 1));
dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1));
dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1));
}
EXPORT_SYMBOL(inet_sock_destruct);
/*
* The routines beyond this point handle the behaviour of an AF_INET
* socket object. Mostly it punts to the subprotocols of IP to do
* the work.
*/
/*
* Automatically bind an unbound socket.
*/
static int inet_autobind(struct sock *sk)
{
struct inet_sock *inet;
/* We may need to bind the socket. */
lock_sock(sk);
inet = inet_sk(sk);
if (!inet->inet_num) {
if (sk->sk_prot->get_port(sk, 0)) {
release_sock(sk);
return -EAGAIN;
}
inet->inet_sport = htons(inet->inet_num);
}
release_sock(sk);
return 0;
}
int __inet_listen_sk(struct sock *sk, int backlog)
{
unsigned char old_state = sk->sk_state;
int err, tcp_fastopen;
if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN)))
return -EINVAL;
WRITE_ONCE(sk->sk_max_ack_backlog, backlog);
/* Really, if the socket is already in listen state
* we can only allow the backlog to be adjusted.
*/
if (old_state != TCP_LISTEN) {
/* Enable TFO w/o requiring TCP_FASTOPEN socket option.
* Note that only TCP sockets (SOCK_STREAM) will reach here.
* Also fastopen backlog may already been set via the option
* because the socket was in TCP_LISTEN state previously but
* was shutdown() rather than close().
*/
tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen);
if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
(tcp_fastopen & TFO_SERVER_ENABLE) &&
!inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) {
fastopen_queue_tune(sk, backlog);
tcp_fastopen_init_key_once(sock_net(sk));
}
err = inet_csk_listen_start(sk);
if (err)
return err;
tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL);
}
return 0;
}
/*
* Move a socket into listening state.
*/
int inet_listen(struct socket *sock, int backlog)
{
struct sock *sk = sock->sk;
int err = -EINVAL;
lock_sock(sk);
if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM)
goto out;
err = __inet_listen_sk(sk, backlog);
out:
release_sock(sk);
return err;
}
EXPORT_SYMBOL(inet_listen);
/*
* Create an inet socket.
*/
static int inet_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
struct sock *sk;
struct inet_protosw *answer;
struct inet_sock *inet;
struct proto *answer_prot;
unsigned char answer_flags;
int try_loading_module = 0;
int err;
if (protocol < 0 || protocol >= IPPROTO_MAX)
return -EINVAL;
sock->state = SS_UNCONNECTED;
/* Look for the requested type/protocol pair. */
lookup_protocol:
err = -ESOCKTNOSUPPORT;
rcu_read_lock();
list_for_each_entry_rcu(answer, &inetsw[sock->type], list) {
err = 0;
/* Check the non-wild match. */
if (protocol == answer->protocol) {
if (protocol != IPPROTO_IP)
break;
} else {
/* Check for the two wild cases. */
if (IPPROTO_IP == protocol) {
protocol = answer->protocol;
break;
}
if (IPPROTO_IP == answer->protocol)
break;
}
err = -EPROTONOSUPPORT;
}
if (unlikely(err)) {
if (try_loading_module < 2) {
rcu_read_unlock();
/*
* Be more specific, e.g. net-pf-2-proto-132-type-1
* (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM)
*/
if (++try_loading_module == 1)
request_module("net-pf-%d-proto-%d-type-%d",
PF_INET, protocol, sock->type);
/*
* Fall back to generic, e.g. net-pf-2-proto-132
* (net-pf-PF_INET-proto-IPPROTO_SCTP)
*/
else
request_module("net-pf-%d-proto-%d",
PF_INET, protocol);
goto lookup_protocol;
} else
goto out_rcu_unlock;
}
err = -EPERM;
if (sock->type == SOCK_RAW && !kern &&
!ns_capable(net->user_ns, CAP_NET_RAW))
goto out_rcu_unlock;
sock->ops = answer->ops;
answer_prot = answer->prot;
answer_flags = answer->flags;
rcu_read_unlock();
WARN_ON(!answer_prot->slab);
err = -ENOMEM;
sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, kern);
if (!sk)
goto out;
err = 0;
if (INET_PROTOSW_REUSE & answer_flags)
sk->sk_reuse = SK_CAN_REUSE;
if (INET_PROTOSW_ICSK & answer_flags)
inet_init_csk_locks(sk);
inet = inet_sk(sk);
inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags);
inet_clear_bit(NODEFRAG, sk);
if (SOCK_RAW == sock->type) {
inet->inet_num = protocol;
if (IPPROTO_RAW == protocol)
inet_set_bit(HDRINCL, sk);
}
if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc))
inet->pmtudisc = IP_PMTUDISC_DONT;
else
inet->pmtudisc = IP_PMTUDISC_WANT;
atomic_set(&inet->inet_id, 0);
sock_init_data(sock, sk);
sk->sk_destruct = inet_sock_destruct;
sk->sk_protocol = protocol;
sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash);
inet->uc_ttl = -1;
inet_set_bit(MC_LOOP, sk);
inet->mc_ttl = 1;
inet_set_bit(MC_ALL, sk);
inet->mc_index = 0;
inet->mc_list = NULL;
inet->rcv_tos = 0;
if (inet->inet_num) {
/* It assumes that any protocol which allows
* the user to assign a number at socket
* creation time automatically
* shares.
*/
inet->inet_sport = htons(inet->inet_num);
/* Add to protocol hash chains. */
err = sk->sk_prot->hash(sk);
if (err) {
sk_common_release(sk);
goto out;
}
}
if (sk->sk_prot->init) {
err = sk->sk_prot->init(sk);
if (err) {
sk_common_release(sk);
goto out;
}
}
if (!kern) {
err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk);
if (err) {
sk_common_release(sk);
goto out;
}
}
out:
return err;
out_rcu_unlock:
rcu_read_unlock();
goto out;
}
/*
* The peer socket should always be NULL (or else). When we call this
* function we are destroying the object and from then on nobody
* should refer to it.
*/
int inet_release(struct socket *sock)
{
struct sock *sk = sock->sk;
if (sk) {
long timeout;
if (!sk->sk_kern_sock)
BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk);
/* Applications forget to leave groups before exiting */
ip_mc_drop_socket(sk);
/* If linger is set, we don't return until the close
* is complete. Otherwise we return immediately. The
* actually closing is done the same either way.
*
* If the close is due to the process exiting, we never
* linger..
*/
timeout = 0;
if (sock_flag(sk, SOCK_LINGER) &&
!(current->flags & PF_EXITING))
timeout = sk->sk_lingertime;
sk->sk_prot->close(sk, timeout);
sock->sk = NULL;
}
return 0;
}
EXPORT_SYMBOL(inet_release);
int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
u32 flags = BIND_WITH_LOCK;
int err;
/* If the socket has its own bind function then use it. (RAW) */
if (sk->sk_prot->bind) {
return sk->sk_prot->bind(sk, uaddr, addr_len);
}
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
/* BPF prog is run before any checks are done so that if the prog
* changes context in a wrong way it will be caught.
*/
err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, &addr_len,
CGROUP_INET4_BIND, &flags);
if (err)
return err;
return __inet_bind(sk, uaddr, addr_len, flags);
}
int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
return inet_bind_sk(sock->sk, uaddr, addr_len);
}
EXPORT_SYMBOL(inet_bind);
int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
u32 flags)
{
struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
unsigned short snum;
int chk_addr_ret;
u32 tb_id = RT_TABLE_LOCAL;
int err;
if (addr->sin_family != AF_INET) {
/* Compatibility games : accept AF_UNSPEC (mapped to AF_INET)
* only if s_addr is INADDR_ANY.
*/
err = -EAFNOSUPPORT;
if (addr->sin_family != AF_UNSPEC ||
addr->sin_addr.s_addr != htonl(INADDR_ANY))
goto out;
}
tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id;
chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);
/* Not specified by any standard per-se, however it breaks too
* many applications when removed. It is unfortunate since
* allowing applications to make a non-local bind solves
* several problems with systems using dynamic addressing.
* (ie. your servers still start up even if your ISDN link
* is temporarily down)
*/
err = -EADDRNOTAVAIL;
if (!inet_addr_valid_or_nonlocal(net, inet, addr->sin_addr.s_addr,
chk_addr_ret))
goto out;
snum = ntohs(addr->sin_port);
err = -EACCES;
if (!(flags & BIND_NO_CAP_NET_BIND_SERVICE) &&
snum && inet_port_requires_bind_service(net, snum) &&
!ns_capable(net->user_ns, CAP_NET_BIND_SERVICE))
goto out;
/* We keep a pair of addresses. rcv_saddr is the one
* used by hash lookups, and saddr is used for transmit.
*
* In the BSD API these are the same except where it
* would be illegal to use them (multicast/broadcast) in
* which case the sending device address is used.
*/
if (flags & BIND_WITH_LOCK)
lock_sock(sk);
/* Check these errors (active socket, double bind). */
err = -EINVAL;
if (sk->sk_state != TCP_CLOSE || inet->inet_num)
goto out_release_sock;
inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr;
if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
inet->inet_saddr = 0; /* Use device */
/* Make sure we are allowed to bind here. */
if (snum || !(inet_test_bit(BIND_ADDRESS_NO_PORT, sk) ||
(flags & BIND_FORCE_ADDRESS_NO_PORT))) {
err = sk->sk_prot->get_port(sk, snum);
if (err) {
inet->inet_saddr = inet->inet_rcv_saddr = 0;
goto out_release_sock;
}
if (!(flags & BIND_FROM_BPF)) {
err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk);
if (err) {
inet->inet_saddr = inet->inet_rcv_saddr = 0;
if (sk->sk_prot->put_port)
sk->sk_prot->put_port(sk);
goto out_release_sock;
}
}
}
if (inet->inet_rcv_saddr)
sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
if (snum)
sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
inet->inet_sport = htons(inet->inet_num);
inet->inet_daddr = 0;
inet->inet_dport = 0;
sk_dst_reset(sk);
err = 0;
out_release_sock:
if (flags & BIND_WITH_LOCK)
release_sock(sk);
out:
return err;
}
int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags)
{
struct sock *sk = sock->sk;
const struct proto *prot;
int err;
if (addr_len < sizeof(uaddr->sa_family))
return -EINVAL;
/* IPV6_ADDRFORM can change sk->sk_prot under us. */
prot = READ_ONCE(sk->sk_prot);
if (uaddr->sa_family == AF_UNSPEC)
return prot->disconnect(sk, flags);
if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) {
err = prot->pre_connect(sk, uaddr, addr_len);
if (err)
return err;
}
if (data_race(!inet_sk(sk)->inet_num) && inet_autobind(sk))
return -EAGAIN;
return prot->connect(sk, uaddr, addr_len);
}
EXPORT_SYMBOL(inet_dgram_connect);
static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
add_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending += writebias;
/* Basic assumption: if someone sets sk->sk_err, he _must_
* change state of the socket from TCP_SYN_*.
* Connect() does not allow to get error notifications
* without closing the socket.
*/
while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
release_sock(sk);
timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
lock_sock(sk);
if (signal_pending(current) || !timeo)
break;
}
remove_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending -= writebias;
return timeo;
}
/*
* Connect to a remote host. There is regrettably still a little
* TCP 'magic' in here.
*/
int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags, int is_sendmsg)
{
struct sock *sk = sock->sk;
int err;
long timeo;
/*
* uaddr can be NULL and addr_len can be 0 if:
* sk is a TCP fastopen active socket and
* TCP_FASTOPEN_CONNECT sockopt is set and
* we already have a valid cookie for this socket.
* In this case, user can call write() after connect().
* write() will invoke tcp_sendmsg_fastopen() which calls
* __inet_stream_connect().
*/
if (uaddr) {
if (addr_len < sizeof(uaddr->sa_family))
return -EINVAL;
if (uaddr->sa_family == AF_UNSPEC) {
sk->sk_disconnects++;
err = sk->sk_prot->disconnect(sk, flags);
sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
goto out;
}
}
switch (sock->state) {
default:
err = -EINVAL;
goto out;
case SS_CONNECTED:
err = -EISCONN;
goto out;
case SS_CONNECTING:
if (inet_test_bit(DEFER_CONNECT, sk))
err = is_sendmsg ? -EINPROGRESS : -EISCONN;
else
err = -EALREADY;
/* Fall out of switch with err, set for this state */
break;
case SS_UNCONNECTED:
err = -EISCONN;
if (sk->sk_state != TCP_CLOSE)
goto out;
if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) {
err = sk->sk_prot->pre_connect(sk, uaddr, addr_len);
if (err)
goto out;
}
err = sk->sk_prot->connect(sk, uaddr, addr_len);
if (err < 0)
goto out;
sock->state = SS_CONNECTING;
if (!err && inet_test_bit(DEFER_CONNECT, sk))
goto out;
/* Just entered SS_CONNECTING state; the only
* difference is that return value in non-blocking
* case is EINPROGRESS, rather than EALREADY.
*/
err = -EINPROGRESS;
break;
}
timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
int writebias = (sk->sk_protocol == IPPROTO_TCP) &&
tcp_sk(sk)->fastopen_req &&
tcp_sk(sk)->fastopen_req->data ? 1 : 0;
int dis = sk->sk_disconnects;
/* Error code is set above */
if (!timeo || !inet_wait_for_connect(sk, timeo, writebias))
goto out;
err = sock_intr_errno(timeo);
if (signal_pending(current))
goto out;
if (dis != sk->sk_disconnects) {
err = -EPIPE;
goto out;
}
}
/* Connection was closed by RST, timeout, ICMP error
* or another process disconnected us.
*/
if (sk->sk_state == TCP_CLOSE)
goto sock_error;
/* sk->sk_err may be not zero now, if RECVERR was ordered by user
* and error was received after socket entered established state.
* Hence, it is handled normally after connect() return successfully.
*/
sock->state = SS_CONNECTED;
err = 0;
out:
return err;
sock_error:
err = sock_error(sk) ? : -ECONNABORTED;
sock->state = SS_UNCONNECTED;
sk->sk_disconnects++;
if (sk->sk_prot->disconnect(sk, flags))
sock->state = SS_DISCONNECTING;
goto out;
}
EXPORT_SYMBOL(__inet_stream_connect);
int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags)
{
int err;
lock_sock(sock->sk);
err = __inet_stream_connect(sock, uaddr, addr_len, flags, 0);
release_sock(sock->sk);
return err;
}
EXPORT_SYMBOL(inet_stream_connect);
void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *newsk)
{
sock_rps_record_flow(newsk);
WARN_ON(!((1 << newsk->sk_state) &
(TCPF_ESTABLISHED | TCPF_SYN_RECV |
TCPF_CLOSE_WAIT | TCPF_CLOSE)));
if (test_bit(SOCK_SUPPORT_ZC, &sock->flags))
set_bit(SOCK_SUPPORT_ZC, &newsock->flags);
sock_graft(newsk, newsock);
newsock->state = SS_CONNECTED;
}
/*
* Accept a pending connection. The TCP layer now gives BSD semantics.
*/
int inet_accept(struct socket *sock, struct socket *newsock,
struct proto_accept_arg *arg)
{
struct sock *sk1 = sock->sk, *sk2;
/* IPV6_ADDRFORM can change sk->sk_prot under us. */
arg->err = -EINVAL;
sk2 = READ_ONCE(sk1->sk_prot)->accept(sk1, arg);
if (!sk2)
return arg->err;
lock_sock(sk2);
__inet_accept(sock, newsock, sk2);
release_sock(sk2);
return 0;
}
EXPORT_SYMBOL(inet_accept);
/*
* This does both peername and sockname.
*/
int inet_getname(struct socket *sock, struct sockaddr *uaddr,
int peer)
{
struct sock *sk = sock->sk;
struct inet_sock *inet = inet_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr);
int sin_addr_len = sizeof(*sin);
sin->sin_family = AF_INET;
lock_sock(sk);
if (peer) {
if (!inet->inet_dport ||
(((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) &&
peer == 1)) {
release_sock(sk);
return -ENOTCONN;
}
sin->sin_port = inet->inet_dport;
sin->sin_addr.s_addr = inet->inet_daddr;
BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len,
CGROUP_INET4_GETPEERNAME);
} else {
__be32 addr = inet->inet_rcv_saddr;
if (!addr)
addr = inet->inet_saddr;
sin->sin_port = inet->inet_sport;
sin->sin_addr.s_addr = addr;
BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len,
CGROUP_INET4_GETSOCKNAME);
}
release_sock(sk);
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
return sin_addr_len;
}
EXPORT_SYMBOL(inet_getname);
int inet_send_prepare(struct sock *sk)
{
sock_rps_record_flow(sk);
/* We may need to bind the socket. */
if (data_race(!inet_sk(sk)->inet_num) && !sk->sk_prot->no_autobind &&
inet_autobind(sk))
return -EAGAIN;
return 0;
}
EXPORT_SYMBOL_GPL(inet_send_prepare);
int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
{
struct sock *sk = sock->sk;
if (unlikely(inet_send_prepare(sk)))
return -EAGAIN;
return INDIRECT_CALL_2(sk->sk_prot->sendmsg, tcp_sendmsg, udp_sendmsg,
sk, msg, size);
}
EXPORT_SYMBOL(inet_sendmsg);
void inet_splice_eof(struct socket *sock)
{
const struct proto *prot;
struct sock *sk = sock->sk;
if (unlikely(inet_send_prepare(sk)))
return;
/* IPV6_ADDRFORM can change sk->sk_prot under us. */
prot = READ_ONCE(sk->sk_prot);
if (prot->splice_eof)
prot->splice_eof(sock);
}
EXPORT_SYMBOL_GPL(inet_splice_eof);
INDIRECT_CALLABLE_DECLARE(int udp_recvmsg(struct sock *, struct msghdr *,
size_t, int, int *));
int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags)
{
struct sock *sk = sock->sk;
int addr_len = 0;
int err;
if (likely(!(flags & MSG_ERRQUEUE)))
sock_rps_record_flow(sk);
err = INDIRECT_CALL_2(sk->sk_prot->recvmsg, tcp_recvmsg, udp_recvmsg,
sk, msg, size, flags, &addr_len);
if (err >= 0)
msg->msg_namelen = addr_len;
return err;
}
EXPORT_SYMBOL(inet_recvmsg);
int inet_shutdown(struct socket *sock, int how)
{
struct sock *sk = sock->sk;
int err = 0;
/* This should really check to make sure
* the socket is a TCP socket. (WHY AC...)
*/
how++; /* maps 0->1 has the advantage of making bit 1 rcvs and
1->2 bit 2 snds.
2->3 */
if ((how & ~SHUTDOWN_MASK) || !how) /* MAXINT->0 */
return -EINVAL;
lock_sock(sk);
if (sock->state == SS_CONNECTING) {
if ((1 << sk->sk_state) &
(TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
sock->state = SS_DISCONNECTING;
else
sock->state = SS_CONNECTED;
}
switch (sk->sk_state) {
case TCP_CLOSE:
err = -ENOTCONN;
/* Hack to wake up other listeners, who can poll for
EPOLLHUP, even on eg. unconnected UDP sockets -- RR */
fallthrough;
default:
WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | how);
if (sk->sk_prot->shutdown)
sk->sk_prot->shutdown(sk, how);
break;
/* Remaining two branches are temporary solution for missing
* close() in multithreaded environment. It is _not_ a good idea,
* but we have no choice until close() is repaired at VFS level.
*/
case TCP_LISTEN:
if (!(how & RCV_SHUTDOWN))
break;
fallthrough;
case TCP_SYN_SENT:
err = sk->sk_prot->disconnect(sk, O_NONBLOCK);
sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
break;
}
/* Wake up anyone sleeping in poll. */
sk->sk_state_change(sk);
release_sock(sk);
return err;
}
EXPORT_SYMBOL(inet_shutdown);
/*
* ioctl() calls you can issue on an INET socket. Most of these are
* device configuration and stuff and very rarely used. Some ioctls
* pass on to the socket itself.
*
* NOTE: I like the idea of a module for the config stuff. ie ifconfig
* loads the devconfigure module does its configuring and unloads it.
* There's a good 20K of config code hanging around the kernel.
*/
int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct sock *sk = sock->sk;
int err = 0;
struct net *net = sock_net(sk);
void __user *p = (void __user *)arg;
struct ifreq ifr;
struct rtentry rt;
switch (cmd) {
case SIOCADDRT:
case SIOCDELRT:
if (copy_from_user(&rt, p, sizeof(struct rtentry)))
return -EFAULT;
err = ip_rt_ioctl(net, cmd, &rt);
break;
case SIOCRTMSG:
err = -EINVAL;
break;
case SIOCDARP:
case SIOCGARP:
case SIOCSARP:
err = arp_ioctl(net, cmd, (void __user *)arg);
break;
case SIOCGIFADDR:
case SIOCGIFBRDADDR:
case SIOCGIFNETMASK:
case SIOCGIFDSTADDR:
case SIOCGIFPFLAGS:
if (get_user_ifreq(&ifr, NULL, p))
return -EFAULT;
err = devinet_ioctl(net, cmd, &ifr);
if (!err && put_user_ifreq(&ifr, p))
err = -EFAULT;
break;
case SIOCSIFADDR:
case SIOCSIFBRDADDR:
case SIOCSIFNETMASK:
case SIOCSIFDSTADDR:
case SIOCSIFPFLAGS:
case SIOCSIFFLAGS:
if (get_user_ifreq(&ifr, NULL, p))
return -EFAULT;