forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
input.c
1323 lines (1128 loc) · 34.9 KB
/
input.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
* Copyright (c) 1999-2000 Cisco, Inc.
* Copyright (c) 1999-2001 Motorola, Inc.
* Copyright (c) 2001-2003 International Business Machines, Corp.
* 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
*
* These functions handle all input from the IP layer into SCTP.
*
* Please send any bug reports or fixes you make to the
* email address(es):
* lksctp developers <[email protected]>
*
* Written or modified by:
* La Monte H.P. Yarroll <[email protected]>
* Karl Knutson <[email protected]>
* Xingang Guo <[email protected]>
* Jon Grimm <[email protected]>
* Hui Huang <[email protected]>
* Daisy Chang <[email protected]>
* Sridhar Samudrala <[email protected]>
* Ardelle Fan <[email protected]>
*/
#include <linux/types.h>
#include <linux/list.h> /* For struct list_head */
#include <linux/socket.h>
#include <linux/ip.h>
#include <linux/time.h> /* For struct timeval */
#include <linux/slab.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/snmp.h>
#include <net/sock.h>
#include <net/xfrm.h>
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
#include <net/sctp/checksum.h>
#include <net/net_namespace.h>
#include <linux/rhashtable.h>
#include <net/sock_reuseport.h>
/* Forward declarations for internal helpers. */
static int sctp_rcv_ootb(struct sk_buff *);
static struct sctp_association *__sctp_rcv_lookup(struct net *net,
struct sk_buff *skb,
const union sctp_addr *paddr,
const union sctp_addr *laddr,
struct sctp_transport **transportp);
static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(
struct net *net, struct sk_buff *skb,
const union sctp_addr *laddr,
const union sctp_addr *daddr);
static struct sctp_association *__sctp_lookup_association(
struct net *net,
const union sctp_addr *local,
const union sctp_addr *peer,
struct sctp_transport **pt);
static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb);
/* Calculate the SCTP checksum of an SCTP packet. */
static inline int sctp_rcv_checksum(struct net *net, struct sk_buff *skb)
{
struct sctphdr *sh = sctp_hdr(skb);
__le32 cmp = sh->checksum;
__le32 val = sctp_compute_cksum(skb, 0);
if (val != cmp) {
/* CRC failure, dump it. */
__SCTP_INC_STATS(net, SCTP_MIB_CHECKSUMERRORS);
return -1;
}
return 0;
}
/*
* This is the routine which IP calls when receiving an SCTP packet.
*/
int sctp_rcv(struct sk_buff *skb)
{
struct sock *sk;
struct sctp_association *asoc;
struct sctp_endpoint *ep = NULL;
struct sctp_ep_common *rcvr;
struct sctp_transport *transport = NULL;
struct sctp_chunk *chunk;
union sctp_addr src;
union sctp_addr dest;
int family;
struct sctp_af *af;
struct net *net = dev_net(skb->dev);
bool is_gso = skb_is_gso(skb) && skb_is_gso_sctp(skb);
if (skb->pkt_type != PACKET_HOST)
goto discard_it;
__SCTP_INC_STATS(net, SCTP_MIB_INSCTPPACKS);
/* If packet is too small to contain a single chunk, let's not
* waste time on it anymore.
*/
if (skb->len < sizeof(struct sctphdr) + sizeof(struct sctp_chunkhdr) +
skb_transport_offset(skb))
goto discard_it;
/* If the packet is fragmented and we need to do crc checking,
* it's better to just linearize it otherwise crc computing
* takes longer.
*/
if ((!is_gso && skb_linearize(skb)) ||
!pskb_may_pull(skb, sizeof(struct sctphdr)))
goto discard_it;
/* Pull up the IP header. */
__skb_pull(skb, skb_transport_offset(skb));
skb->csum_valid = 0; /* Previous value not applicable */
if (skb_csum_unnecessary(skb))
__skb_decr_checksum_unnecessary(skb);
else if (!sctp_checksum_disable &&
!is_gso &&
sctp_rcv_checksum(net, skb) < 0)
goto discard_it;
skb->csum_valid = 1;
__skb_pull(skb, sizeof(struct sctphdr));
family = ipver2af(ip_hdr(skb)->version);
af = sctp_get_af_specific(family);
if (unlikely(!af))
goto discard_it;
SCTP_INPUT_CB(skb)->af = af;
/* Initialize local addresses for lookups. */
af->from_skb(&src, skb, 1);
af->from_skb(&dest, skb, 0);
/* If the packet is to or from a non-unicast address,
* silently discard the packet.
*
* This is not clearly defined in the RFC except in section
* 8.4 - OOTB handling. However, based on the book "Stream Control
* Transmission Protocol" 2.1, "It is important to note that the
* IP address of an SCTP transport address must be a routable
* unicast address. In other words, IP multicast addresses and
* IP broadcast addresses cannot be used in an SCTP transport
* address."
*/
if (!af->addr_valid(&src, NULL, skb) ||
!af->addr_valid(&dest, NULL, skb))
goto discard_it;
asoc = __sctp_rcv_lookup(net, skb, &src, &dest, &transport);
if (!asoc)
ep = __sctp_rcv_lookup_endpoint(net, skb, &dest, &src);
/* Retrieve the common input handling substructure. */
rcvr = asoc ? &asoc->base : &ep->base;
sk = rcvr->sk;
/*
* If a frame arrives on an interface and the receiving socket is
* bound to another interface, via SO_BINDTODEVICE, treat it as OOTB
*/
if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb))) {
if (transport) {
sctp_transport_put(transport);
asoc = NULL;
transport = NULL;
} else {
sctp_endpoint_put(ep);
ep = NULL;
}
sk = net->sctp.ctl_sock;
ep = sctp_sk(sk)->ep;
sctp_endpoint_hold(ep);
rcvr = &ep->base;
}
/*
* RFC 2960, 8.4 - Handle "Out of the blue" Packets.
* An SCTP packet is called an "out of the blue" (OOTB)
* packet if it is correctly formed, i.e., passed the
* receiver's checksum check, but the receiver is not
* able to identify the association to which this
* packet belongs.
*/
if (!asoc) {
if (sctp_rcv_ootb(skb)) {
__SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES);
goto discard_release;
}
}
if (!xfrm_policy_check(sk, XFRM_POLICY_IN, skb, family))
goto discard_release;
nf_reset_ct(skb);
if (sk_filter(sk, skb))
goto discard_release;
/* Create an SCTP packet structure. */
chunk = sctp_chunkify(skb, asoc, sk, GFP_ATOMIC);
if (!chunk)
goto discard_release;
SCTP_INPUT_CB(skb)->chunk = chunk;
/* Remember what endpoint is to handle this packet. */
chunk->rcvr = rcvr;
/* Remember the SCTP header. */
chunk->sctp_hdr = sctp_hdr(skb);
/* Set the source and destination addresses of the incoming chunk. */
sctp_init_addrs(chunk, &src, &dest);
/* Remember where we came from. */
chunk->transport = transport;
/* Acquire access to the sock lock. Note: We are safe from other
* bottom halves on this lock, but a user may be in the lock too,
* so check if it is busy.
*/
bh_lock_sock(sk);
if (sk != rcvr->sk) {
/* Our cached sk is different from the rcvr->sk. This is
* because migrate()/accept() may have moved the association
* to a new socket and released all the sockets. So now we
* are holding a lock on the old socket while the user may
* be doing something with the new socket. Switch our veiw
* of the current sk.
*/
bh_unlock_sock(sk);
sk = rcvr->sk;
bh_lock_sock(sk);
}
if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) {
if (sctp_add_backlog(sk, skb)) {
bh_unlock_sock(sk);
sctp_chunk_free(chunk);
skb = NULL; /* sctp_chunk_free already freed the skb */
goto discard_release;
}
__SCTP_INC_STATS(net, SCTP_MIB_IN_PKT_BACKLOG);
} else {
__SCTP_INC_STATS(net, SCTP_MIB_IN_PKT_SOFTIRQ);
sctp_inq_push(&chunk->rcvr->inqueue, chunk);
}
bh_unlock_sock(sk);
/* Release the asoc/ep ref we took in the lookup calls. */
if (transport)
sctp_transport_put(transport);
else
sctp_endpoint_put(ep);
return 0;
discard_it:
__SCTP_INC_STATS(net, SCTP_MIB_IN_PKT_DISCARDS);
kfree_skb(skb);
return 0;
discard_release:
/* Release the asoc/ep ref we took in the lookup calls. */
if (transport)
sctp_transport_put(transport);
else
sctp_endpoint_put(ep);
goto discard_it;
}
/* Process the backlog queue of the socket. Every skb on
* the backlog holds a ref on an association or endpoint.
* We hold this ref throughout the state machine to make
* sure that the structure we need is still around.
*/
int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
struct sctp_inq *inqueue = &chunk->rcvr->inqueue;
struct sctp_transport *t = chunk->transport;
struct sctp_ep_common *rcvr = NULL;
int backloged = 0;
rcvr = chunk->rcvr;
/* If the rcvr is dead then the association or endpoint
* has been deleted and we can safely drop the chunk
* and refs that we are holding.
*/
if (rcvr->dead) {
sctp_chunk_free(chunk);
goto done;
}
if (unlikely(rcvr->sk != sk)) {
/* In this case, the association moved from one socket to
* another. We are currently sitting on the backlog of the
* old socket, so we need to move.
* However, since we are here in the process context we
* need to take make sure that the user doesn't own
* the new socket when we process the packet.
* If the new socket is user-owned, queue the chunk to the
* backlog of the new socket without dropping any refs.
* Otherwise, we can safely push the chunk on the inqueue.
*/
sk = rcvr->sk;
local_bh_disable();
bh_lock_sock(sk);
if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) {
if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))
sctp_chunk_free(chunk);
else
backloged = 1;
} else
sctp_inq_push(inqueue, chunk);
bh_unlock_sock(sk);
local_bh_enable();
/* If the chunk was backloged again, don't drop refs */
if (backloged)
return 0;
} else {
if (!sctp_newsk_ready(sk)) {
if (!sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))
return 0;
sctp_chunk_free(chunk);
} else {
sctp_inq_push(inqueue, chunk);
}
}
done:
/* Release the refs we took in sctp_add_backlog */
if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type)
sctp_transport_put(t);
else if (SCTP_EP_TYPE_SOCKET == rcvr->type)
sctp_endpoint_put(sctp_ep(rcvr));
else
BUG();
return 0;
}
static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
{
struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
struct sctp_transport *t = chunk->transport;
struct sctp_ep_common *rcvr = chunk->rcvr;
int ret;
ret = sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf));
if (!ret) {
/* Hold the assoc/ep while hanging on the backlog queue.
* This way, we know structures we need will not disappear
* from us
*/
if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type)
sctp_transport_hold(t);
else if (SCTP_EP_TYPE_SOCKET == rcvr->type)
sctp_endpoint_hold(sctp_ep(rcvr));
else
BUG();
}
return ret;
}
/* Handle icmp frag needed error. */
void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
struct sctp_transport *t, __u32 pmtu)
{
if (!t || (t->pathmtu <= pmtu))
return;
if (sock_owned_by_user(sk)) {
atomic_set(&t->mtu_info, pmtu);
asoc->pmtu_pending = 1;
t->pmtu_pending = 1;
return;
}
if (!(t->param_flags & SPP_PMTUD_ENABLE))
/* We can't allow retransmitting in such case, as the
* retransmission would be sized just as before, and thus we
* would get another icmp, and retransmit again.
*/
return;
/* Update transports view of the MTU. Return if no update was needed.
* If an update wasn't needed/possible, it also doesn't make sense to
* try to retransmit now.
*/
if (!sctp_transport_update_pmtu(t, pmtu))
return;
/* Update association pmtu. */
sctp_assoc_sync_pmtu(asoc);
/* Retransmit with the new pmtu setting. */
sctp_retransmit(&asoc->outqueue, t, SCTP_RTXR_PMTUD);
}
void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t,
struct sk_buff *skb)
{
struct dst_entry *dst;
if (sock_owned_by_user(sk) || !t)
return;
dst = sctp_transport_dst_check(t);
if (dst)
dst->ops->redirect(dst, sk, skb);
}
/*
* SCTP Implementer's Guide, 2.37 ICMP handling procedures
*
* ICMP8) If the ICMP code is a "Unrecognized next header type encountered"
* or a "Protocol Unreachable" treat this message as an abort
* with the T bit set.
*
* This function sends an event to the state machine, which will abort the
* association.
*
*/
void sctp_icmp_proto_unreachable(struct sock *sk,
struct sctp_association *asoc,
struct sctp_transport *t)
{
if (sock_owned_by_user(sk)) {
if (timer_pending(&t->proto_unreach_timer))
return;
else {
if (!mod_timer(&t->proto_unreach_timer,
jiffies + (HZ/20)))
sctp_transport_hold(t);
}
} else {
struct net *net = sock_net(sk);
pr_debug("%s: unrecognized next header type "
"encountered!\n", __func__);
if (del_timer(&t->proto_unreach_timer))
sctp_transport_put(t);
sctp_do_sm(net, SCTP_EVENT_T_OTHER,
SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH),
asoc->state, asoc->ep, asoc, t,
GFP_ATOMIC);
}
}
/* Common lookup code for icmp/icmpv6 error handler. */
struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb,
struct sctphdr *sctphdr,
struct sctp_association **app,
struct sctp_transport **tpp)
{
struct sctp_init_chunk *chunkhdr, _chunkhdr;
union sctp_addr saddr;
union sctp_addr daddr;
struct sctp_af *af;
struct sock *sk = NULL;
struct sctp_association *asoc;
struct sctp_transport *transport = NULL;
__u32 vtag = ntohl(sctphdr->vtag);
*app = NULL; *tpp = NULL;
af = sctp_get_af_specific(family);
if (unlikely(!af)) {
return NULL;
}
/* Initialize local addresses for lookups. */
af->from_skb(&saddr, skb, 1);
af->from_skb(&daddr, skb, 0);
/* Look for an association that matches the incoming ICMP error
* packet.
*/
asoc = __sctp_lookup_association(net, &saddr, &daddr, &transport);
if (!asoc)
return NULL;
sk = asoc->base.sk;
/* RFC 4960, Appendix C. ICMP Handling
*
* ICMP6) An implementation MUST validate that the Verification Tag
* contained in the ICMP message matches the Verification Tag of
* the peer. If the Verification Tag is not 0 and does NOT
* match, discard the ICMP message. If it is 0 and the ICMP
* message contains enough bytes to verify that the chunk type is
* an INIT chunk and that the Initiate Tag matches the tag of the
* peer, continue with ICMP7. If the ICMP message is too short
* or the chunk type or the Initiate Tag does not match, silently
* discard the packet.
*/
if (vtag == 0) {
/* chunk header + first 4 octects of init header */
chunkhdr = skb_header_pointer(skb, skb_transport_offset(skb) +
sizeof(struct sctphdr),
sizeof(struct sctp_chunkhdr) +
sizeof(__be32), &_chunkhdr);
if (!chunkhdr ||
chunkhdr->chunk_hdr.type != SCTP_CID_INIT ||
ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag)
goto out;
} else if (vtag != asoc->c.peer_vtag) {
goto out;
}
bh_lock_sock(sk);
/* If too many ICMPs get dropped on busy
* servers this needs to be solved differently.
*/
if (sock_owned_by_user(sk))
__NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS);
*app = asoc;
*tpp = transport;
return sk;
out:
sctp_transport_put(transport);
return NULL;
}
/* Common cleanup code for icmp/icmpv6 error handler. */
void sctp_err_finish(struct sock *sk, struct sctp_transport *t)
__releases(&((__sk)->sk_lock.slock))
{
bh_unlock_sock(sk);
sctp_transport_put(t);
}
/*
* This routine is called by the ICMP module when it gets some
* sort of error condition. If err < 0 then the socket should
* be closed and the error returned to the user. If err > 0
* it's just the icmp type << 8 | icmp code. After adjustment
* header points to the first 8 bytes of the sctp header. We need
* to find the appropriate port.
*
* The locking strategy used here is very "optimistic". When
* someone else accesses the socket the ICMP is just dropped
* and for some paths there is no check at all.
* A more general error queue to queue errors for later handling
* is probably better.
*
*/
int sctp_v4_err(struct sk_buff *skb, __u32 info)
{
const struct iphdr *iph = (const struct iphdr *)skb->data;
const int ihlen = iph->ihl * 4;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct sock *sk;
struct sctp_association *asoc = NULL;
struct sctp_transport *transport;
struct inet_sock *inet;
__u16 saveip, savesctp;
int err;
struct net *net = dev_net(skb->dev);
/* Fix up skb to look at the embedded net header. */
saveip = skb->network_header;
savesctp = skb->transport_header;
skb_reset_network_header(skb);
skb_set_transport_header(skb, ihlen);
sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &transport);
/* Put back, the original values. */
skb->network_header = saveip;
skb->transport_header = savesctp;
if (!sk) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
return -ENOENT;
}
/* Warning: The sock lock is held. Remember to call
* sctp_err_finish!
*/
switch (type) {
case ICMP_PARAMETERPROB:
err = EPROTO;
break;
case ICMP_DEST_UNREACH:
if (code > NR_ICMP_UNREACH)
goto out_unlock;
/* PMTU discovery (RFC1191) */
if (ICMP_FRAG_NEEDED == code) {
sctp_icmp_frag_needed(sk, asoc, transport,
SCTP_TRUNC4(info));
goto out_unlock;
} else {
if (ICMP_PROT_UNREACH == code) {
sctp_icmp_proto_unreachable(sk, asoc,
transport);
goto out_unlock;
}
}
err = icmp_err_convert[code].errno;
break;
case ICMP_TIME_EXCEEDED:
/* Ignore any time exceeded errors due to fragment reassembly
* timeouts.
*/
if (ICMP_EXC_FRAGTIME == code)
goto out_unlock;
err = EHOSTUNREACH;
break;
case ICMP_REDIRECT:
sctp_icmp_redirect(sk, transport, skb);
/* Fall through to out_unlock. */
default:
goto out_unlock;
}
inet = inet_sk(sk);
if (!sock_owned_by_user(sk) && inet->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else { /* Only an error on timeout */
sk->sk_err_soft = err;
}
out_unlock:
sctp_err_finish(sk, transport);
return 0;
}
/*
* RFC 2960, 8.4 - Handle "Out of the blue" Packets.
*
* This function scans all the chunks in the OOTB packet to determine if
* the packet should be discarded right away. If a response might be needed
* for this packet, or, if further processing is possible, the packet will
* be queued to a proper inqueue for the next phase of handling.
*
* Output:
* Return 0 - If further processing is needed.
* Return 1 - If the packet can be discarded right away.
*/
static int sctp_rcv_ootb(struct sk_buff *skb)
{
struct sctp_chunkhdr *ch, _ch;
int ch_end, offset = 0;
/* Scan through all the chunks in the packet. */
do {
/* Make sure we have at least the header there */
if (offset + sizeof(_ch) > skb->len)
break;
ch = skb_header_pointer(skb, offset, sizeof(*ch), &_ch);
/* Break out if chunk length is less then minimal. */
if (ntohs(ch->length) < sizeof(_ch))
break;
ch_end = offset + SCTP_PAD4(ntohs(ch->length));
if (ch_end > skb->len)
break;
/* RFC 8.4, 2) If the OOTB packet contains an ABORT chunk, the
* receiver MUST silently discard the OOTB packet and take no
* further action.
*/
if (SCTP_CID_ABORT == ch->type)
goto discard;
/* RFC 8.4, 6) If the packet contains a SHUTDOWN COMPLETE
* chunk, the receiver should silently discard the packet
* and take no further action.
*/
if (SCTP_CID_SHUTDOWN_COMPLETE == ch->type)
goto discard;
/* RFC 4460, 2.11.2
* This will discard packets with INIT chunk bundled as
* subsequent chunks in the packet. When INIT is first,
* the normal INIT processing will discard the chunk.
*/
if (SCTP_CID_INIT == ch->type && (void *)ch != skb->data)
goto discard;
offset = ch_end;
} while (ch_end < skb->len);
return 0;
discard:
return 1;
}
/* Insert endpoint into the hash table. */
static int __sctp_hash_endpoint(struct sctp_endpoint *ep)
{
struct sock *sk = ep->base.sk;
struct net *net = sock_net(sk);
struct sctp_hashbucket *head;
struct sctp_ep_common *epb;
epb = &ep->base;
epb->hashent = sctp_ep_hashfn(net, epb->bind_addr.port);
head = &sctp_ep_hashtable[epb->hashent];
if (sk->sk_reuseport) {
bool any = sctp_is_ep_boundall(sk);
struct sctp_ep_common *epb2;
struct list_head *list;
int cnt = 0, err = 1;
list_for_each(list, &ep->base.bind_addr.address_list)
cnt++;
sctp_for_each_hentry(epb2, &head->chain) {
struct sock *sk2 = epb2->sk;
if (!net_eq(sock_net(sk2), net) || sk2 == sk ||
!uid_eq(sock_i_uid(sk2), sock_i_uid(sk)) ||
!sk2->sk_reuseport)
continue;
err = sctp_bind_addrs_check(sctp_sk(sk2),
sctp_sk(sk), cnt);
if (!err) {
err = reuseport_add_sock(sk, sk2, any);
if (err)
return err;
break;
} else if (err < 0) {
return err;
}
}
if (err) {
err = reuseport_alloc(sk, any);
if (err)
return err;
}
}
write_lock(&head->lock);
hlist_add_head(&epb->node, &head->chain);
write_unlock(&head->lock);
return 0;
}
/* Add an endpoint to the hash. Local BH-safe. */
int sctp_hash_endpoint(struct sctp_endpoint *ep)
{
int err;
local_bh_disable();
err = __sctp_hash_endpoint(ep);
local_bh_enable();
return err;
}
/* Remove endpoint from the hash table. */
static void __sctp_unhash_endpoint(struct sctp_endpoint *ep)
{
struct sock *sk = ep->base.sk;
struct sctp_hashbucket *head;
struct sctp_ep_common *epb;
epb = &ep->base;
epb->hashent = sctp_ep_hashfn(sock_net(sk), epb->bind_addr.port);
head = &sctp_ep_hashtable[epb->hashent];
if (rcu_access_pointer(sk->sk_reuseport_cb))
reuseport_detach_sock(sk);
write_lock(&head->lock);
hlist_del_init(&epb->node);
write_unlock(&head->lock);
}
/* Remove endpoint from the hash. Local BH-safe. */
void sctp_unhash_endpoint(struct sctp_endpoint *ep)
{
local_bh_disable();
__sctp_unhash_endpoint(ep);
local_bh_enable();
}
static inline __u32 sctp_hashfn(const struct net *net, __be16 lport,
const union sctp_addr *paddr, __u32 seed)
{
__u32 addr;
if (paddr->sa.sa_family == AF_INET6)
addr = jhash(&paddr->v6.sin6_addr, 16, seed);
else
addr = (__force __u32)paddr->v4.sin_addr.s_addr;
return jhash_3words(addr, ((__force __u32)paddr->v4.sin_port) << 16 |
(__force __u32)lport, net_hash_mix(net), seed);
}
/* Look up an endpoint. */
static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(
struct net *net, struct sk_buff *skb,
const union sctp_addr *laddr,
const union sctp_addr *paddr)
{
struct sctp_hashbucket *head;
struct sctp_ep_common *epb;
struct sctp_endpoint *ep;
struct sock *sk;
__be16 lport;
int hash;
lport = laddr->v4.sin_port;
hash = sctp_ep_hashfn(net, ntohs(lport));
head = &sctp_ep_hashtable[hash];
read_lock(&head->lock);
sctp_for_each_hentry(epb, &head->chain) {
ep = sctp_ep(epb);
if (sctp_endpoint_is_match(ep, net, laddr))
goto hit;
}
ep = sctp_sk(net->sctp.ctl_sock)->ep;
hit:
sk = ep->base.sk;
if (sk->sk_reuseport) {
__u32 phash = sctp_hashfn(net, lport, paddr, 0);
sk = reuseport_select_sock(sk, phash, skb,
sizeof(struct sctphdr));
if (sk)
ep = sctp_sk(sk)->ep;
}
sctp_endpoint_hold(ep);
read_unlock(&head->lock);
return ep;
}
/* rhashtable for transport */
struct sctp_hash_cmp_arg {
const union sctp_addr *paddr;
const struct net *net;
__be16 lport;
};
static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg,
const void *ptr)
{
struct sctp_transport *t = (struct sctp_transport *)ptr;
const struct sctp_hash_cmp_arg *x = arg->key;
int err = 1;
if (!sctp_cmp_addr_exact(&t->ipaddr, x->paddr))
return err;
if (!sctp_transport_hold(t))
return err;
if (!net_eq(t->asoc->base.net, x->net))
goto out;
if (x->lport != htons(t->asoc->base.bind_addr.port))
goto out;
err = 0;
out:
sctp_transport_put(t);
return err;
}
static inline __u32 sctp_hash_obj(const void *data, u32 len, u32 seed)
{
const struct sctp_transport *t = data;
return sctp_hashfn(t->asoc->base.net,
htons(t->asoc->base.bind_addr.port),
&t->ipaddr, seed);
}
static inline __u32 sctp_hash_key(const void *data, u32 len, u32 seed)
{
const struct sctp_hash_cmp_arg *x = data;
return sctp_hashfn(x->net, x->lport, x->paddr, seed);
}
static const struct rhashtable_params sctp_hash_params = {
.head_offset = offsetof(struct sctp_transport, node),
.hashfn = sctp_hash_key,
.obj_hashfn = sctp_hash_obj,
.obj_cmpfn = sctp_hash_cmp,
.automatic_shrinking = true,
};
int sctp_transport_hashtable_init(void)
{
return rhltable_init(&sctp_transport_hashtable, &sctp_hash_params);
}
void sctp_transport_hashtable_destroy(void)
{
rhltable_destroy(&sctp_transport_hashtable);
}
int sctp_hash_transport(struct sctp_transport *t)
{
struct sctp_transport *transport;
struct rhlist_head *tmp, *list;
struct sctp_hash_cmp_arg arg;
int err;
if (t->asoc->temp)
return 0;
arg.net = t->asoc->base.net;
arg.paddr = &t->ipaddr;
arg.lport = htons(t->asoc->base.bind_addr.port);
rcu_read_lock();
list = rhltable_lookup(&sctp_transport_hashtable, &arg,
sctp_hash_params);
rhl_for_each_entry_rcu(transport, tmp, list, node)
if (transport->asoc->ep == t->asoc->ep) {
rcu_read_unlock();
return -EEXIST;
}
rcu_read_unlock();
err = rhltable_insert_key(&sctp_transport_hashtable, &arg,
&t->node, sctp_hash_params);
if (err)
pr_err_once("insert transport fail, errno %d\n", err);
return err;
}
void sctp_unhash_transport(struct sctp_transport *t)
{
if (t->asoc->temp)
return;
rhltable_remove(&sctp_transport_hashtable, &t->node,
sctp_hash_params);
}
/* return a transport with holding it */
struct sctp_transport *sctp_addrs_lookup_transport(
struct net *net,
const union sctp_addr *laddr,
const union sctp_addr *paddr)
{
struct rhlist_head *tmp, *list;
struct sctp_transport *t;
struct sctp_hash_cmp_arg arg = {
.paddr = paddr,
.net = net,
.lport = laddr->v4.sin_port,
};
list = rhltable_lookup(&sctp_transport_hashtable, &arg,
sctp_hash_params);
rhl_for_each_entry_rcu(t, tmp, list, node) {
if (!sctp_transport_hold(t))
continue;
if (sctp_bind_addr_match(&t->asoc->base.bind_addr,
laddr, sctp_sk(t->asoc->base.sk)))
return t;
sctp_transport_put(t);
}
return NULL;