forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathprotocol.c
1746 lines (1483 loc) · 46.3 KB
/
protocol.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
/* SCTP kernel implementation
* (C) Copyright IBM Corp. 2001, 2004
* Copyright (c) 1999-2000 Cisco, Inc.
* Copyright (c) 1999-2001 Motorola, Inc.
* Copyright (c) 2001 Intel Corp.
* Copyright (c) 2001 Nokia, Inc.
* Copyright (c) 2001 La Monte H.P. Yarroll
*
* This file is part of the SCTP kernel implementation
*
* Initialization/cleanup for SCTP protocol support.
*
* Please send any bug reports or fixes you make to the
* email address(es):
* lksctp developers <linux-sctp@vger.kernel.org>
*
* Written or modified by:
* La Monte H.P. Yarroll <piggy@acm.org>
* Karl Knutson <karl@athena.chicago.il.us>
* Jon Grimm <jgrimm@us.ibm.com>
* Sridhar Samudrala <sri@us.ibm.com>
* Daisy Chang <daisyc@us.ibm.com>
* Ardelle Fan <ardelle.fan@intel.com>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/init.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/seq_file.h>
#include <linux/memblock.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/route.h>
#include <net/sctp/sctp.h>
#include <net/addrconf.h>
#include <net/inet_common.h>
#include <net/inet_ecn.h>
#include <net/udp_tunnel.h>
#include <net/inet_dscp.h>
#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)
/* Global data structures. */
struct sctp_globals sctp_globals __read_mostly;
struct idr sctp_assocs_id;
DEFINE_SPINLOCK(sctp_assocs_id_lock);
static struct sctp_pf *sctp_pf_inet6_specific;
static struct sctp_pf *sctp_pf_inet_specific;
static struct sctp_af *sctp_af_v4_specific;
static struct sctp_af *sctp_af_v6_specific;
struct kmem_cache *sctp_chunk_cachep __read_mostly;
struct kmem_cache *sctp_bucket_cachep __read_mostly;
long sysctl_sctp_mem[3];
int sysctl_sctp_rmem[3];
int sysctl_sctp_wmem[3];
/* Private helper to extract ipv4 address and stash them in
* the protocol structure.
*/
static void sctp_v4_copy_addrlist(struct list_head *addrlist,
struct net_device *dev)
{
struct in_device *in_dev;
struct in_ifaddr *ifa;
struct sctp_sockaddr_entry *addr;
rcu_read_lock();
if ((in_dev = __in_dev_get_rcu(dev)) == NULL) {
rcu_read_unlock();
return;
}
in_dev_for_each_ifa_rcu(ifa, in_dev) {
/* Add the address to the local list. */
addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
if (addr) {
addr->a.v4.sin_family = AF_INET;
addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
addr->valid = 1;
INIT_LIST_HEAD(&addr->list);
list_add_tail(&addr->list, addrlist);
}
}
rcu_read_unlock();
}
/* Extract our IP addresses from the system and stash them in the
* protocol structure.
*/
static void sctp_get_local_addr_list(struct net *net)
{
struct net_device *dev;
struct list_head *pos;
struct sctp_af *af;
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
list_for_each(pos, &sctp_address_families) {
af = list_entry(pos, struct sctp_af, list);
af->copy_addrlist(&net->sctp.local_addr_list, dev);
}
}
rcu_read_unlock();
}
/* Free the existing local addresses. */
static void sctp_free_local_addr_list(struct net *net)
{
struct sctp_sockaddr_entry *addr;
struct list_head *pos, *temp;
list_for_each_safe(pos, temp, &net->sctp.local_addr_list) {
addr = list_entry(pos, struct sctp_sockaddr_entry, list);
list_del(pos);
kfree(addr);
}
}
/* Copy the local addresses which are valid for 'scope' into 'bp'. */
int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
enum sctp_scope scope, gfp_t gfp, int copy_flags)
{
struct sctp_sockaddr_entry *addr;
union sctp_addr laddr;
int error = 0;
rcu_read_lock();
list_for_each_entry_rcu(addr, &net->sctp.local_addr_list, list) {
if (!addr->valid)
continue;
if (!sctp_in_scope(net, &addr->a, scope))
continue;
/* Now that the address is in scope, check to see if
* the address type is really supported by the local
* sock as well as the remote peer.
*/
if (addr->a.sa.sa_family == AF_INET &&
(!(copy_flags & SCTP_ADDR4_ALLOWED) ||
!(copy_flags & SCTP_ADDR4_PEERSUPP)))
continue;
if (addr->a.sa.sa_family == AF_INET6 &&
(!(copy_flags & SCTP_ADDR6_ALLOWED) ||
!(copy_flags & SCTP_ADDR6_PEERSUPP)))
continue;
laddr = addr->a;
/* also works for setting ipv6 address port */
laddr.v4.sin_port = htons(bp->port);
if (sctp_bind_addr_state(bp, &laddr) != -1)
continue;
error = sctp_add_bind_addr(bp, &addr->a, sizeof(addr->a),
SCTP_ADDR_SRC, GFP_ATOMIC);
if (error)
break;
}
rcu_read_unlock();
return error;
}
/* Copy over any ip options */
static void sctp_v4_copy_ip_options(struct sock *sk, struct sock *newsk)
{
struct inet_sock *newinet, *inet = inet_sk(sk);
struct ip_options_rcu *inet_opt, *newopt = NULL;
newinet = inet_sk(newsk);
rcu_read_lock();
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt) {
newopt = sock_kmalloc(newsk, sizeof(*inet_opt) +
inet_opt->opt.optlen, GFP_ATOMIC);
if (newopt)
memcpy(newopt, inet_opt, sizeof(*inet_opt) +
inet_opt->opt.optlen);
else
pr_err("%s: Failed to copy ip options\n", __func__);
}
RCU_INIT_POINTER(newinet->inet_opt, newopt);
rcu_read_unlock();
}
/* Account for the IP options */
static int sctp_v4_ip_options_len(struct sock *sk)
{
struct inet_sock *inet = inet_sk(sk);
struct ip_options_rcu *inet_opt;
int len = 0;
rcu_read_lock();
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt)
len = inet_opt->opt.optlen;
rcu_read_unlock();
return len;
}
/* Initialize a sctp_addr from in incoming skb. */
static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb,
int is_saddr)
{
/* Always called on head skb, so this is safe */
struct sctphdr *sh = sctp_hdr(skb);
struct sockaddr_in *sa = &addr->v4;
addr->v4.sin_family = AF_INET;
if (is_saddr) {
sa->sin_port = sh->source;
sa->sin_addr.s_addr = ip_hdr(skb)->saddr;
} else {
sa->sin_port = sh->dest;
sa->sin_addr.s_addr = ip_hdr(skb)->daddr;
}
memset(sa->sin_zero, 0, sizeof(sa->sin_zero));
}
/* Initialize an sctp_addr from a socket. */
static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk)
{
addr->v4.sin_family = AF_INET;
addr->v4.sin_port = 0;
addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr;
memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
}
/* Initialize sk->sk_rcv_saddr from sctp_addr. */
static void sctp_v4_to_sk_saddr(union sctp_addr *addr, struct sock *sk)
{
inet_sk(sk)->inet_rcv_saddr = addr->v4.sin_addr.s_addr;
}
/* Initialize sk->sk_daddr from sctp_addr. */
static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
{
inet_sk(sk)->inet_daddr = addr->v4.sin_addr.s_addr;
}
/* Initialize a sctp_addr from an address parameter. */
static bool sctp_v4_from_addr_param(union sctp_addr *addr,
union sctp_addr_param *param,
__be16 port, int iif)
{
if (ntohs(param->v4.param_hdr.length) < sizeof(struct sctp_ipv4addr_param))
return false;
addr->v4.sin_family = AF_INET;
addr->v4.sin_port = port;
addr->v4.sin_addr.s_addr = param->v4.addr.s_addr;
memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
return true;
}
/* Initialize an address parameter from a sctp_addr and return the length
* of the address parameter.
*/
static int sctp_v4_to_addr_param(const union sctp_addr *addr,
union sctp_addr_param *param)
{
int length = sizeof(struct sctp_ipv4addr_param);
param->v4.param_hdr.type = SCTP_PARAM_IPV4_ADDRESS;
param->v4.param_hdr.length = htons(length);
param->v4.addr.s_addr = addr->v4.sin_addr.s_addr;
return length;
}
/* Initialize a sctp_addr from a dst_entry. */
static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4,
__be16 port)
{
saddr->v4.sin_family = AF_INET;
saddr->v4.sin_port = port;
saddr->v4.sin_addr.s_addr = fl4->saddr;
memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero));
}
/* Compare two addresses exactly. */
static int sctp_v4_cmp_addr(const union sctp_addr *addr1,
const union sctp_addr *addr2)
{
if (addr1->sa.sa_family != addr2->sa.sa_family)
return 0;
if (addr1->v4.sin_port != addr2->v4.sin_port)
return 0;
if (addr1->v4.sin_addr.s_addr != addr2->v4.sin_addr.s_addr)
return 0;
return 1;
}
/* Initialize addr struct to INADDR_ANY. */
static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port)
{
addr->v4.sin_family = AF_INET;
addr->v4.sin_addr.s_addr = htonl(INADDR_ANY);
addr->v4.sin_port = port;
memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
}
/* Is this a wildcard address? */
static int sctp_v4_is_any(const union sctp_addr *addr)
{
return htonl(INADDR_ANY) == addr->v4.sin_addr.s_addr;
}
/* This function checks if the address is a valid address to be used for
* SCTP binding.
*
* Output:
* Return 0 - If the address is a non-unicast or an illegal address.
* Return 1 - If the address is a unicast.
*/
static int sctp_v4_addr_valid(union sctp_addr *addr,
struct sctp_sock *sp,
const struct sk_buff *skb)
{
/* IPv4 addresses not allowed */
if (sp && ipv6_only_sock(sctp_opt2sk(sp)))
return 0;
/* Is this a non-unicast address or a unusable SCTP address? */
if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr))
return 0;
/* Is this a broadcast address? */
if (skb && skb_rtable(skb)->rt_flags & RTCF_BROADCAST)
return 0;
return 1;
}
/* Should this be available for binding? */
static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
{
struct sock *sk = &sp->inet.sk;
struct net *net = sock_net(sk);
int tb_id = RT_TABLE_LOCAL;
int ret;
tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ?: tb_id;
ret = inet_addr_type_table(net, addr->v4.sin_addr.s_addr, tb_id);
if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) &&
ret != RTN_LOCAL &&
!inet_test_bit(FREEBIND, sk) &&
!READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind))
return 0;
if (ipv6_only_sock(sctp_opt2sk(sp)))
return 0;
return 1;
}
/* Checking the loopback, private and other address scopes as defined in
* RFC 1918. The IPv4 scoping is based on the draft for SCTP IPv4
* scoping <draft-stewart-tsvwg-sctp-ipv4-00.txt>.
*
* Level 0 - unusable SCTP addresses
* Level 1 - loopback address
* Level 2 - link-local addresses
* Level 3 - private addresses.
* Level 4 - global addresses
* For INIT and INIT-ACK address list, let L be the level of
* requested destination address, sender and receiver
* SHOULD include all of its addresses with level greater
* than or equal to L.
*
* IPv4 scoping can be controlled through sysctl option
* net.sctp.addr_scope_policy
*/
static enum sctp_scope sctp_v4_scope(union sctp_addr *addr)
{
enum sctp_scope retval;
/* Check for unusable SCTP addresses. */
if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr)) {
retval = SCTP_SCOPE_UNUSABLE;
} else if (ipv4_is_loopback(addr->v4.sin_addr.s_addr)) {
retval = SCTP_SCOPE_LOOPBACK;
} else if (ipv4_is_linklocal_169(addr->v4.sin_addr.s_addr)) {
retval = SCTP_SCOPE_LINK;
} else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) ||
ipv4_is_private_172(addr->v4.sin_addr.s_addr) ||
ipv4_is_private_192(addr->v4.sin_addr.s_addr) ||
ipv4_is_test_198(addr->v4.sin_addr.s_addr)) {
retval = SCTP_SCOPE_PRIVATE;
} else {
retval = SCTP_SCOPE_GLOBAL;
}
return retval;
}
/* Returns a valid dst cache entry for the given source and destination ip
* addresses. If an association is passed, trys to get a dst entry with a
* source address that matches an address in the bind address list.
*/
static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
struct flowi *fl, struct sock *sk)
{
struct sctp_association *asoc = t->asoc;
struct rtable *rt;
struct flowi _fl;
struct flowi4 *fl4 = &_fl.u.ip4;
struct sctp_bind_addr *bp;
struct sctp_sockaddr_entry *laddr;
struct dst_entry *dst = NULL;
union sctp_addr *daddr = &t->ipaddr;
union sctp_addr dst_saddr;
u8 tos = READ_ONCE(inet_sk(sk)->tos);
if (t->dscp & SCTP_DSCP_SET_MASK)
tos = t->dscp & SCTP_DSCP_VAL_MASK;
memset(&_fl, 0x0, sizeof(_fl));
fl4->daddr = daddr->v4.sin_addr.s_addr;
fl4->fl4_dport = daddr->v4.sin_port;
fl4->flowi4_proto = IPPROTO_SCTP;
if (asoc) {
fl4->flowi4_tos = tos & INET_DSCP_MASK;
fl4->flowi4_scope = ip_sock_rt_scope(asoc->base.sk);
fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if;
fl4->fl4_sport = htons(asoc->base.bind_addr.port);
}
if (saddr) {
fl4->saddr = saddr->v4.sin_addr.s_addr;
if (!fl4->fl4_sport)
fl4->fl4_sport = saddr->v4.sin_port;
}
pr_debug("%s: dst:%pI4, src:%pI4 - ", __func__, &fl4->daddr,
&fl4->saddr);
rt = ip_route_output_key(sock_net(sk), fl4);
if (!IS_ERR(rt)) {
dst = &rt->dst;
t->dst = dst;
memcpy(fl, &_fl, sizeof(_fl));
}
/* If there is no association or if a source address is passed, no
* more validation is required.
*/
if (!asoc || saddr)
goto out;
bp = &asoc->base.bind_addr;
if (dst) {
/* Walk through the bind address list and look for a bind
* address that matches the source address of the returned dst.
*/
sctp_v4_dst_saddr(&dst_saddr, fl4, htons(bp->port));
rcu_read_lock();
list_for_each_entry_rcu(laddr, &bp->address_list, list) {
if (!laddr->valid || (laddr->state == SCTP_ADDR_DEL) ||
(laddr->state != SCTP_ADDR_SRC &&
!asoc->src_out_of_asoc_ok))
continue;
if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a))
goto out_unlock;
}
rcu_read_unlock();
/* None of the bound addresses match the source address of the
* dst. So release it.
*/
dst_release(dst);
dst = NULL;
}
/* Walk through the bind address list and try to get a dst that
* matches a bind address as the source address.
*/
rcu_read_lock();
list_for_each_entry_rcu(laddr, &bp->address_list, list) {
struct net_device *odev;
if (!laddr->valid)
continue;
if (laddr->state != SCTP_ADDR_SRC ||
AF_INET != laddr->a.sa.sa_family)
continue;
fl4->fl4_sport = laddr->a.v4.sin_port;
flowi4_update_output(fl4, asoc->base.sk->sk_bound_dev_if,
daddr->v4.sin_addr.s_addr,
laddr->a.v4.sin_addr.s_addr);
rt = ip_route_output_key(sock_net(sk), fl4);
if (IS_ERR(rt))
continue;
/* Ensure the src address belongs to the output
* interface.
*/
odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr,
false);
if (!odev || odev->ifindex != fl4->flowi4_oif) {
if (!dst) {
dst = &rt->dst;
t->dst = dst;
memcpy(fl, &_fl, sizeof(_fl));
} else {
dst_release(&rt->dst);
}
continue;
}
dst_release(dst);
dst = &rt->dst;
t->dst = dst;
memcpy(fl, &_fl, sizeof(_fl));
break;
}
out_unlock:
rcu_read_unlock();
out:
if (dst) {
pr_debug("rt_dst:%pI4, rt_src:%pI4\n",
&fl->u.ip4.daddr, &fl->u.ip4.saddr);
} else {
t->dst = NULL;
pr_debug("no route\n");
}
}
/* For v4, the source address is cached in the route entry(dst). So no need
* to cache it separately and hence this is an empty routine.
*/
static void sctp_v4_get_saddr(struct sctp_sock *sk,
struct sctp_transport *t,
struct flowi *fl)
{
union sctp_addr *saddr = &t->saddr;
struct rtable *rt = dst_rtable(t->dst);
if (rt) {
saddr->v4.sin_family = AF_INET;
saddr->v4.sin_addr.s_addr = fl->u.ip4.saddr;
}
}
/* What interface did this skb arrive on? */
static int sctp_v4_skb_iif(const struct sk_buff *skb)
{
return inet_iif(skb);
}
static int sctp_v4_skb_sdif(const struct sk_buff *skb)
{
return inet_sdif(skb);
}
/* Was this packet marked by Explicit Congestion Notification? */
static int sctp_v4_is_ce(const struct sk_buff *skb)
{
return INET_ECN_is_ce(ip_hdr(skb)->tos);
}
/* Create and initialize a new sk for the socket returned by accept(). */
static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
struct sctp_association *asoc,
bool kern)
{
struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL,
sk->sk_prot, kern);
struct inet_sock *newinet;
if (!newsk)
goto out;
sock_init_data(NULL, newsk);
sctp_copy_sock(newsk, sk, asoc);
sock_reset_flag(newsk, SOCK_ZAPPED);
sctp_v4_copy_ip_options(sk, newsk);
newinet = inet_sk(newsk);
newinet->inet_daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr;
if (newsk->sk_prot->init(newsk)) {
sk_common_release(newsk);
newsk = NULL;
}
out:
return newsk;
}
static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
{
/* No address mapping for V4 sockets */
memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
return sizeof(struct sockaddr_in);
}
/* Dump the v4 addr to the seq file. */
static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr)
{
seq_printf(seq, "%pI4 ", &addr->v4.sin_addr);
}
static void sctp_v4_ecn_capable(struct sock *sk)
{
INET_ECN_xmit(sk);
}
static void sctp_addr_wq_timeout_handler(struct timer_list *t)
{
struct net *net = from_timer(net, t, sctp.addr_wq_timer);
struct sctp_sockaddr_entry *addrw, *temp;
struct sctp_sock *sp;
spin_lock_bh(&net->sctp.addr_wq_lock);
list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) {
pr_debug("%s: the first ent in wq:%p is addr:%pISc for cmd:%d at "
"entry:%p\n", __func__, &net->sctp.addr_waitq, &addrw->a.sa,
addrw->state, addrw);
#if IS_ENABLED(CONFIG_IPV6)
/* Now we send an ASCONF for each association */
/* Note. we currently don't handle link local IPv6 addressees */
if (addrw->a.sa.sa_family == AF_INET6) {
struct in6_addr *in6;
if (ipv6_addr_type(&addrw->a.v6.sin6_addr) &
IPV6_ADDR_LINKLOCAL)
goto free_next;
in6 = (struct in6_addr *)&addrw->a.v6.sin6_addr;
if (ipv6_chk_addr(net, in6, NULL, 0) == 0 &&
addrw->state == SCTP_ADDR_NEW) {
unsigned long timeo_val;
pr_debug("%s: this is on DAD, trying %d sec "
"later\n", __func__,
SCTP_ADDRESS_TICK_DELAY);
timeo_val = jiffies;
timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
mod_timer(&net->sctp.addr_wq_timer, timeo_val);
break;
}
}
#endif
list_for_each_entry(sp, &net->sctp.auto_asconf_splist, auto_asconf_list) {
struct sock *sk;
sk = sctp_opt2sk(sp);
/* ignore bound-specific endpoints */
if (!sctp_is_ep_boundall(sk))
continue;
bh_lock_sock(sk);
if (sctp_asconf_mgmt(sp, addrw) < 0)
pr_debug("%s: sctp_asconf_mgmt failed\n", __func__);
bh_unlock_sock(sk);
}
#if IS_ENABLED(CONFIG_IPV6)
free_next:
#endif
list_del(&addrw->list);
kfree(addrw);
}
spin_unlock_bh(&net->sctp.addr_wq_lock);
}
static void sctp_free_addr_wq(struct net *net)
{
struct sctp_sockaddr_entry *addrw;
struct sctp_sockaddr_entry *temp;
spin_lock_bh(&net->sctp.addr_wq_lock);
del_timer(&net->sctp.addr_wq_timer);
list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) {
list_del(&addrw->list);
kfree(addrw);
}
spin_unlock_bh(&net->sctp.addr_wq_lock);
}
/* lookup the entry for the same address in the addr_waitq
* sctp_addr_wq MUST be locked
*/
static struct sctp_sockaddr_entry *sctp_addr_wq_lookup(struct net *net,
struct sctp_sockaddr_entry *addr)
{
struct sctp_sockaddr_entry *addrw;
list_for_each_entry(addrw, &net->sctp.addr_waitq, list) {
if (addrw->a.sa.sa_family != addr->a.sa.sa_family)
continue;
if (addrw->a.sa.sa_family == AF_INET) {
if (addrw->a.v4.sin_addr.s_addr ==
addr->a.v4.sin_addr.s_addr)
return addrw;
} else if (addrw->a.sa.sa_family == AF_INET6) {
if (ipv6_addr_equal(&addrw->a.v6.sin6_addr,
&addr->a.v6.sin6_addr))
return addrw;
}
}
return NULL;
}
void sctp_addr_wq_mgmt(struct net *net, struct sctp_sockaddr_entry *addr, int cmd)
{
struct sctp_sockaddr_entry *addrw;
unsigned long timeo_val;
/* first, we check if an opposite message already exist in the queue.
* If we found such message, it is removed.
* This operation is a bit stupid, but the DHCP client attaches the
* new address after a couple of addition and deletion of that address
*/
spin_lock_bh(&net->sctp.addr_wq_lock);
/* Avoid searching the queue or modifying it if there are no consumers,
* as it can lead to performance degradation if addresses are modified
* en-masse.
*
* If the queue already contains some events, update it anyway to avoid
* ugly races between new sessions and new address events.
*/
if (list_empty(&net->sctp.auto_asconf_splist) &&
list_empty(&net->sctp.addr_waitq)) {
spin_unlock_bh(&net->sctp.addr_wq_lock);
return;
}
/* Offsets existing events in addr_wq */
addrw = sctp_addr_wq_lookup(net, addr);
if (addrw) {
if (addrw->state != cmd) {
pr_debug("%s: offsets existing entry for %d, addr:%pISc "
"in wq:%p\n", __func__, addrw->state, &addrw->a.sa,
&net->sctp.addr_waitq);
list_del(&addrw->list);
kfree(addrw);
}
spin_unlock_bh(&net->sctp.addr_wq_lock);
return;
}
/* OK, we have to add the new address to the wait queue */
addrw = kmemdup(addr, sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC);
if (addrw == NULL) {
spin_unlock_bh(&net->sctp.addr_wq_lock);
return;
}
addrw->state = cmd;
list_add_tail(&addrw->list, &net->sctp.addr_waitq);
pr_debug("%s: add new entry for cmd:%d, addr:%pISc in wq:%p\n",
__func__, addrw->state, &addrw->a.sa, &net->sctp.addr_waitq);
if (!timer_pending(&net->sctp.addr_wq_timer)) {
timeo_val = jiffies;
timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
mod_timer(&net->sctp.addr_wq_timer, timeo_val);
}
spin_unlock_bh(&net->sctp.addr_wq_lock);
}
/* Event handler for inet address addition/deletion events.
* The sctp_local_addr_list needs to be protocted by a spin lock since
* multiple notifiers (say IPv4 and IPv6) may be running at the same
* time and thus corrupt the list.
* The reader side is protected with RCU.
*/
static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
void *ptr)
{
struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
struct sctp_sockaddr_entry *addr = NULL;
struct sctp_sockaddr_entry *temp;
struct net *net = dev_net(ifa->ifa_dev->dev);
int found = 0;
switch (ev) {
case NETDEV_UP:
addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
if (addr) {
addr->a.v4.sin_family = AF_INET;
addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
addr->valid = 1;
spin_lock_bh(&net->sctp.local_addr_lock);
list_add_tail_rcu(&addr->list, &net->sctp.local_addr_list);
sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_NEW);
spin_unlock_bh(&net->sctp.local_addr_lock);
}
break;
case NETDEV_DOWN:
spin_lock_bh(&net->sctp.local_addr_lock);
list_for_each_entry_safe(addr, temp,
&net->sctp.local_addr_list, list) {
if (addr->a.sa.sa_family == AF_INET &&
addr->a.v4.sin_addr.s_addr ==
ifa->ifa_local) {
found = 1;
addr->valid = 0;
list_del_rcu(&addr->list);
sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL);
break;
}
}
spin_unlock_bh(&net->sctp.local_addr_lock);
if (found)
kfree_rcu(addr, rcu);
break;
}
return NOTIFY_DONE;
}
/*
* Initialize the control inode/socket with a control endpoint data
* structure. This endpoint is reserved exclusively for the OOTB processing.
*/
static int sctp_ctl_sock_init(struct net *net)
{
int err;
sa_family_t family = PF_INET;
if (sctp_get_pf_specific(PF_INET6))
family = PF_INET6;
err = inet_ctl_sock_create(&net->sctp.ctl_sock, family,
SOCK_SEQPACKET, IPPROTO_SCTP, net);
/* If IPv6 socket could not be created, try the IPv4 socket */
if (err < 0 && family == PF_INET6)
err = inet_ctl_sock_create(&net->sctp.ctl_sock, AF_INET,
SOCK_SEQPACKET, IPPROTO_SCTP,
net);
if (err < 0) {
pr_err("Failed to create the SCTP control socket\n");
return err;
}
return 0;
}
static int sctp_udp_rcv(struct sock *sk, struct sk_buff *skb)
{
SCTP_INPUT_CB(skb)->encap_port = udp_hdr(skb)->source;
skb_set_transport_header(skb, sizeof(struct udphdr));
sctp_rcv(skb);
return 0;
}
int sctp_udp_sock_start(struct net *net)
{
struct udp_tunnel_sock_cfg tuncfg = {NULL};
struct udp_port_cfg udp_conf = {0};
struct socket *sock;
int err;
udp_conf.family = AF_INET;
udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
udp_conf.local_udp_port = htons(net->sctp.udp_port);
err = udp_sock_create(net, &udp_conf, &sock);
if (err) {
pr_err("Failed to create the SCTP UDP tunneling v4 sock\n");
return err;
}
tuncfg.encap_type = 1;
tuncfg.encap_rcv = sctp_udp_rcv;
tuncfg.encap_err_lookup = sctp_udp_v4_err;
setup_udp_tunnel_sock(net, sock, &tuncfg);
net->sctp.udp4_sock = sock->sk;
#if IS_ENABLED(CONFIG_IPV6)
memset(&udp_conf, 0, sizeof(udp_conf));
udp_conf.family = AF_INET6;
udp_conf.local_ip6 = in6addr_any;
udp_conf.local_udp_port = htons(net->sctp.udp_port);
udp_conf.use_udp6_rx_checksums = true;
udp_conf.ipv6_v6only = true;
err = udp_sock_create(net, &udp_conf, &sock);
if (err) {
pr_err("Failed to create the SCTP UDP tunneling v6 sock\n");
udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
net->sctp.udp4_sock = NULL;
return err;
}
tuncfg.encap_type = 1;
tuncfg.encap_rcv = sctp_udp_rcv;
tuncfg.encap_err_lookup = sctp_udp_v6_err;
setup_udp_tunnel_sock(net, sock, &tuncfg);
net->sctp.udp6_sock = sock->sk;
#endif
return 0;
}
void sctp_udp_sock_stop(struct net *net)
{
if (net->sctp.udp4_sock) {
udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
net->sctp.udp4_sock = NULL;
}
if (net->sctp.udp6_sock) {
udp_tunnel_sock_release(net->sctp.udp6_sock->sk_socket);
net->sctp.udp6_sock = NULL;
}
}
/* Register address family specific functions. */
int sctp_register_af(struct sctp_af *af)
{
switch (af->sa_family) {
case AF_INET:
if (sctp_af_v4_specific)
return 0;
sctp_af_v4_specific = af;
break;
case AF_INET6:
if (sctp_af_v6_specific)
return 0;
sctp_af_v6_specific = af;
break;
default:
return 0;
}
INIT_LIST_HEAD(&af->list);
list_add_tail(&af->list, &sctp_address_families);
return 1;
}
/* Get the table of functions for manipulating a particular address
* family.
*/
struct sctp_af *sctp_get_af_specific(sa_family_t family)
{
switch (family) {
case AF_INET:
return sctp_af_v4_specific;
case AF_INET6:
return sctp_af_v6_specific;
default:
return NULL;
}
}
/* Common code to initialize a AF_INET msg_name. */
static void sctp_inet_msgname(char *msgname, int *addr_len)
{
struct sockaddr_in *sin;
sin = (struct sockaddr_in *)msgname;
*addr_len = sizeof(struct sockaddr_in);
sin->sin_family = AF_INET;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
}
/* Copy the primary address of the peer primary address as the msg_name. */
static void sctp_inet_event_msgname(struct sctp_ulpevent *event, char *msgname,
int *addr_len)
{
struct sockaddr_in *sin, *sinfrom;
if (msgname) {
struct sctp_association *asoc;
asoc = event->asoc;
sctp_inet_msgname(msgname, addr_len);
sin = (struct sockaddr_in *)msgname;
sinfrom = &asoc->peer.primary_addr.v4;
sin->sin_port = htons(asoc->peer.port);