forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
associola.c
1728 lines (1440 loc) · 49 KB
/
associola.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 La Monte H.P. Yarroll
*
* This file is part of the SCTP kernel implementation
*
* This module provides the abstraction for an SCTP association.
*
* 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]>
* Jon Grimm <[email protected]>
* Xingang Guo <[email protected]>
* Hui Huang <[email protected]>
* Sridhar Samudrala <[email protected]>
* Daisy Chang <[email protected]>
* Ryan Layer <[email protected]>
* Kevin Gao <[email protected]>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/in.h>
#include <net/ipv6.h>
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
/* Forward declarations for internal functions. */
static void sctp_select_active_and_retran_path(struct sctp_association *asoc);
static void sctp_assoc_bh_rcv(struct work_struct *work);
static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc);
static void sctp_assoc_free_asconf_queue(struct sctp_association *asoc);
/* 1st Level Abstractions. */
/* Initialize a new association from provided memory. */
static struct sctp_association *sctp_association_init(
struct sctp_association *asoc,
const struct sctp_endpoint *ep,
const struct sock *sk,
enum sctp_scope scope, gfp_t gfp)
{
struct sctp_sock *sp;
struct sctp_paramhdr *p;
int i;
/* Retrieve the SCTP per socket area. */
sp = sctp_sk((struct sock *)sk);
/* Discarding const is appropriate here. */
asoc->ep = (struct sctp_endpoint *)ep;
asoc->base.sk = (struct sock *)sk;
asoc->base.net = sock_net(sk);
sctp_endpoint_hold(asoc->ep);
sock_hold(asoc->base.sk);
/* Initialize the common base substructure. */
asoc->base.type = SCTP_EP_TYPE_ASSOCIATION;
/* Initialize the object handling fields. */
refcount_set(&asoc->base.refcnt, 1);
/* Initialize the bind addr area. */
sctp_bind_addr_init(&asoc->base.bind_addr, ep->base.bind_addr.port);
asoc->state = SCTP_STATE_CLOSED;
asoc->cookie_life = ms_to_ktime(sp->assocparams.sasoc_cookie_life);
asoc->user_frag = sp->user_frag;
/* Set the association max_retrans and RTO values from the
* socket values.
*/
asoc->max_retrans = sp->assocparams.sasoc_asocmaxrxt;
asoc->pf_retrans = sp->pf_retrans;
asoc->ps_retrans = sp->ps_retrans;
asoc->pf_expose = sp->pf_expose;
asoc->rto_initial = msecs_to_jiffies(sp->rtoinfo.srto_initial);
asoc->rto_max = msecs_to_jiffies(sp->rtoinfo.srto_max);
asoc->rto_min = msecs_to_jiffies(sp->rtoinfo.srto_min);
/* Initialize the association's heartbeat interval based on the
* sock configured value.
*/
asoc->hbinterval = msecs_to_jiffies(sp->hbinterval);
asoc->probe_interval = msecs_to_jiffies(sp->probe_interval);
asoc->encap_port = sp->encap_port;
/* Initialize path max retrans value. */
asoc->pathmaxrxt = sp->pathmaxrxt;
asoc->flowlabel = sp->flowlabel;
asoc->dscp = sp->dscp;
/* Set association default SACK delay */
asoc->sackdelay = msecs_to_jiffies(sp->sackdelay);
asoc->sackfreq = sp->sackfreq;
/* Set the association default flags controlling
* Heartbeat, SACK delay, and Path MTU Discovery.
*/
asoc->param_flags = sp->param_flags;
/* Initialize the maximum number of new data packets that can be sent
* in a burst.
*/
asoc->max_burst = sp->max_burst;
asoc->subscribe = sp->subscribe;
/* initialize association timers */
asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_COOKIE] = asoc->rto_initial;
asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_INIT] = asoc->rto_initial;
asoc->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] = asoc->rto_initial;
/* sctpimpguide Section 2.12.2
* If the 'T5-shutdown-guard' timer is used, it SHOULD be set to the
* recommended value of 5 times 'RTO.Max'.
*/
asoc->timeouts[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD]
= 5 * asoc->rto_max;
asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay;
asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ;
/* Initializes the timers */
for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i)
timer_setup(&asoc->timers[i], sctp_timer_events[i], 0);
/* Pull default initialization values from the sock options.
* Note: This assumes that the values have already been
* validated in the sock.
*/
asoc->c.sinit_max_instreams = sp->initmsg.sinit_max_instreams;
asoc->c.sinit_num_ostreams = sp->initmsg.sinit_num_ostreams;
asoc->max_init_attempts = sp->initmsg.sinit_max_attempts;
asoc->max_init_timeo =
msecs_to_jiffies(sp->initmsg.sinit_max_init_timeo);
/* Set the local window size for receive.
* This is also the rcvbuf space per association.
* RFC 6 - A SCTP receiver MUST be able to receive a minimum of
* 1500 bytes in one SCTP packet.
*/
if ((sk->sk_rcvbuf/2) < SCTP_DEFAULT_MINWINDOW)
asoc->rwnd = SCTP_DEFAULT_MINWINDOW;
else
asoc->rwnd = sk->sk_rcvbuf/2;
asoc->a_rwnd = asoc->rwnd;
/* Use my own max window until I learn something better. */
asoc->peer.rwnd = SCTP_DEFAULT_MAXWINDOW;
/* Initialize the receive memory counter */
atomic_set(&asoc->rmem_alloc, 0);
init_waitqueue_head(&asoc->wait);
asoc->c.my_vtag = sctp_generate_tag(ep);
asoc->c.my_port = ep->base.bind_addr.port;
asoc->c.initial_tsn = sctp_generate_tsn(ep);
asoc->next_tsn = asoc->c.initial_tsn;
asoc->ctsn_ack_point = asoc->next_tsn - 1;
asoc->adv_peer_ack_point = asoc->ctsn_ack_point;
asoc->highest_sacked = asoc->ctsn_ack_point;
asoc->last_cwr_tsn = asoc->ctsn_ack_point;
/* ADDIP Section 4.1 Asconf Chunk Procedures
*
* When an endpoint has an ASCONF signaled change to be sent to the
* remote endpoint it should do the following:
* ...
* A2) a serial number should be assigned to the chunk. The serial
* number SHOULD be a monotonically increasing number. The serial
* numbers SHOULD be initialized at the start of the
* association to the same value as the initial TSN.
*/
asoc->addip_serial = asoc->c.initial_tsn;
asoc->strreset_outseq = asoc->c.initial_tsn;
INIT_LIST_HEAD(&asoc->addip_chunk_list);
INIT_LIST_HEAD(&asoc->asconf_ack_list);
/* Make an empty list of remote transport addresses. */
INIT_LIST_HEAD(&asoc->peer.transport_addr_list);
/* RFC 2960 5.1 Normal Establishment of an Association
*
* After the reception of the first data chunk in an
* association the endpoint must immediately respond with a
* sack to acknowledge the data chunk. Subsequent
* acknowledgements should be done as described in Section
* 6.2.
*
* [We implement this by telling a new association that it
* already received one packet.]
*/
asoc->peer.sack_needed = 1;
asoc->peer.sack_generation = 1;
/* Create an input queue. */
sctp_inq_init(&asoc->base.inqueue);
sctp_inq_set_th_handler(&asoc->base.inqueue, sctp_assoc_bh_rcv);
/* Create an output queue. */
sctp_outq_init(asoc, &asoc->outqueue);
sctp_ulpq_init(&asoc->ulpq, asoc);
if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, 0, gfp))
goto stream_free;
/* Initialize default path MTU. */
asoc->pathmtu = sp->pathmtu;
sctp_assoc_update_frag_point(asoc);
/* Assume that peer would support both address types unless we are
* told otherwise.
*/
asoc->peer.ipv4_address = 1;
if (asoc->base.sk->sk_family == PF_INET6)
asoc->peer.ipv6_address = 1;
INIT_LIST_HEAD(&asoc->asocs);
asoc->default_stream = sp->default_stream;
asoc->default_ppid = sp->default_ppid;
asoc->default_flags = sp->default_flags;
asoc->default_context = sp->default_context;
asoc->default_timetolive = sp->default_timetolive;
asoc->default_rcv_context = sp->default_rcv_context;
/* AUTH related initializations */
INIT_LIST_HEAD(&asoc->endpoint_shared_keys);
if (sctp_auth_asoc_copy_shkeys(ep, asoc, gfp))
goto stream_free;
asoc->active_key_id = ep->active_key_id;
asoc->strreset_enable = ep->strreset_enable;
/* Save the hmacs and chunks list into this association */
if (ep->auth_hmacs_list)
memcpy(asoc->c.auth_hmacs, ep->auth_hmacs_list,
ntohs(ep->auth_hmacs_list->param_hdr.length));
if (ep->auth_chunk_list)
memcpy(asoc->c.auth_chunks, ep->auth_chunk_list,
ntohs(ep->auth_chunk_list->param_hdr.length));
/* Get the AUTH random number for this association */
p = (struct sctp_paramhdr *)asoc->c.auth_random;
p->type = SCTP_PARAM_RANDOM;
p->length = htons(sizeof(*p) + SCTP_AUTH_RANDOM_LENGTH);
get_random_bytes(p+1, SCTP_AUTH_RANDOM_LENGTH);
return asoc;
stream_free:
sctp_stream_free(&asoc->stream);
sock_put(asoc->base.sk);
sctp_endpoint_put(asoc->ep);
return NULL;
}
/* Allocate and initialize a new association */
struct sctp_association *sctp_association_new(const struct sctp_endpoint *ep,
const struct sock *sk,
enum sctp_scope scope, gfp_t gfp)
{
struct sctp_association *asoc;
asoc = kzalloc(sizeof(*asoc), gfp);
if (!asoc)
goto fail;
if (!sctp_association_init(asoc, ep, sk, scope, gfp))
goto fail_init;
SCTP_DBG_OBJCNT_INC(assoc);
pr_debug("Created asoc %p\n", asoc);
return asoc;
fail_init:
kfree(asoc);
fail:
return NULL;
}
/* Free this association if possible. There may still be users, so
* the actual deallocation may be delayed.
*/
void sctp_association_free(struct sctp_association *asoc)
{
struct sock *sk = asoc->base.sk;
struct sctp_transport *transport;
struct list_head *pos, *temp;
int i;
/* Only real associations count against the endpoint, so
* don't bother for if this is a temporary association.
*/
if (!list_empty(&asoc->asocs)) {
list_del(&asoc->asocs);
/* Decrement the backlog value for a TCP-style listening
* socket.
*/
if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))
sk_acceptq_removed(sk);
}
/* Mark as dead, so other users can know this structure is
* going away.
*/
asoc->base.dead = true;
/* Dispose of any data lying around in the outqueue. */
sctp_outq_free(&asoc->outqueue);
/* Dispose of any pending messages for the upper layer. */
sctp_ulpq_free(&asoc->ulpq);
/* Dispose of any pending chunks on the inqueue. */
sctp_inq_free(&asoc->base.inqueue);
sctp_tsnmap_free(&asoc->peer.tsn_map);
/* Free stream information. */
sctp_stream_free(&asoc->stream);
if (asoc->strreset_chunk)
sctp_chunk_free(asoc->strreset_chunk);
/* Clean up the bound address list. */
sctp_bind_addr_free(&asoc->base.bind_addr);
/* Do we need to go through all of our timers and
* delete them? To be safe we will try to delete all, but we
* should be able to go through and make a guess based
* on our state.
*/
for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) {
if (del_timer(&asoc->timers[i]))
sctp_association_put(asoc);
}
/* Free peer's cached cookie. */
kfree(asoc->peer.cookie);
kfree(asoc->peer.peer_random);
kfree(asoc->peer.peer_chunks);
kfree(asoc->peer.peer_hmacs);
/* Release the transport structures. */
list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) {
transport = list_entry(pos, struct sctp_transport, transports);
list_del_rcu(pos);
sctp_unhash_transport(transport);
sctp_transport_free(transport);
}
asoc->peer.transport_count = 0;
sctp_asconf_queue_teardown(asoc);
/* Free pending address space being deleted */
kfree(asoc->asconf_addr_del_pending);
/* AUTH - Free the endpoint shared keys */
sctp_auth_destroy_keys(&asoc->endpoint_shared_keys);
/* AUTH - Free the association shared key */
sctp_auth_key_put(asoc->asoc_shared_key);
sctp_association_put(asoc);
}
/* Cleanup and free up an association. */
static void sctp_association_destroy(struct sctp_association *asoc)
{
if (unlikely(!asoc->base.dead)) {
WARN(1, "Attempt to destroy undead association %p!\n", asoc);
return;
}
sctp_endpoint_put(asoc->ep);
sock_put(asoc->base.sk);
if (asoc->assoc_id != 0) {
spin_lock_bh(&sctp_assocs_id_lock);
idr_remove(&sctp_assocs_id, asoc->assoc_id);
spin_unlock_bh(&sctp_assocs_id_lock);
}
WARN_ON(atomic_read(&asoc->rmem_alloc));
kfree_rcu(asoc, rcu);
SCTP_DBG_OBJCNT_DEC(assoc);
}
/* Change the primary destination address for the peer. */
void sctp_assoc_set_primary(struct sctp_association *asoc,
struct sctp_transport *transport)
{
int changeover = 0;
/* it's a changeover only if we already have a primary path
* that we are changing
*/
if (asoc->peer.primary_path != NULL &&
asoc->peer.primary_path != transport)
changeover = 1 ;
asoc->peer.primary_path = transport;
sctp_ulpevent_notify_peer_addr_change(transport,
SCTP_ADDR_MADE_PRIM, 0);
/* Set a default msg_name for events. */
memcpy(&asoc->peer.primary_addr, &transport->ipaddr,
sizeof(union sctp_addr));
/* If the primary path is changing, assume that the
* user wants to use this new path.
*/
if ((transport->state == SCTP_ACTIVE) ||
(transport->state == SCTP_UNKNOWN))
asoc->peer.active_path = transport;
/*
* SFR-CACC algorithm:
* Upon the receipt of a request to change the primary
* destination address, on the data structure for the new
* primary destination, the sender MUST do the following:
*
* 1) If CHANGEOVER_ACTIVE is set, then there was a switch
* to this destination address earlier. The sender MUST set
* CYCLING_CHANGEOVER to indicate that this switch is a
* double switch to the same destination address.
*
* Really, only bother is we have data queued or outstanding on
* the association.
*/
if (!asoc->outqueue.outstanding_bytes && !asoc->outqueue.out_qlen)
return;
if (transport->cacc.changeover_active)
transport->cacc.cycling_changeover = changeover;
/* 2) The sender MUST set CHANGEOVER_ACTIVE to indicate that
* a changeover has occurred.
*/
transport->cacc.changeover_active = changeover;
/* 3) The sender MUST store the next TSN to be sent in
* next_tsn_at_change.
*/
transport->cacc.next_tsn_at_change = asoc->next_tsn;
}
/* Remove a transport from an association. */
void sctp_assoc_rm_peer(struct sctp_association *asoc,
struct sctp_transport *peer)
{
struct sctp_transport *transport;
struct list_head *pos;
struct sctp_chunk *ch;
pr_debug("%s: association:%p addr:%pISpc\n",
__func__, asoc, &peer->ipaddr.sa);
/* If we are to remove the current retran_path, update it
* to the next peer before removing this peer from the list.
*/
if (asoc->peer.retran_path == peer)
sctp_assoc_update_retran_path(asoc);
/* Remove this peer from the list. */
list_del_rcu(&peer->transports);
/* Remove this peer from the transport hashtable */
sctp_unhash_transport(peer);
/* Get the first transport of asoc. */
pos = asoc->peer.transport_addr_list.next;
transport = list_entry(pos, struct sctp_transport, transports);
/* Update any entries that match the peer to be deleted. */
if (asoc->peer.primary_path == peer)
sctp_assoc_set_primary(asoc, transport);
if (asoc->peer.active_path == peer)
asoc->peer.active_path = transport;
if (asoc->peer.retran_path == peer)
asoc->peer.retran_path = transport;
if (asoc->peer.last_data_from == peer)
asoc->peer.last_data_from = transport;
if (asoc->strreset_chunk &&
asoc->strreset_chunk->transport == peer) {
asoc->strreset_chunk->transport = transport;
sctp_transport_reset_reconf_timer(transport);
}
/* If we remove the transport an INIT was last sent to, set it to
* NULL. Combined with the update of the retran path above, this
* will cause the next INIT to be sent to the next available
* transport, maintaining the cycle.
*/
if (asoc->init_last_sent_to == peer)
asoc->init_last_sent_to = NULL;
/* If we remove the transport an SHUTDOWN was last sent to, set it
* to NULL. Combined with the update of the retran path above, this
* will cause the next SHUTDOWN to be sent to the next available
* transport, maintaining the cycle.
*/
if (asoc->shutdown_last_sent_to == peer)
asoc->shutdown_last_sent_to = NULL;
/* If we remove the transport an ASCONF was last sent to, set it to
* NULL.
*/
if (asoc->addip_last_asconf &&
asoc->addip_last_asconf->transport == peer)
asoc->addip_last_asconf->transport = NULL;
/* If we have something on the transmitted list, we have to
* save it off. The best place is the active path.
*/
if (!list_empty(&peer->transmitted)) {
struct sctp_transport *active = asoc->peer.active_path;
/* Reset the transport of each chunk on this list */
list_for_each_entry(ch, &peer->transmitted,
transmitted_list) {
ch->transport = NULL;
ch->rtt_in_progress = 0;
}
list_splice_tail_init(&peer->transmitted,
&active->transmitted);
/* Start a T3 timer here in case it wasn't running so
* that these migrated packets have a chance to get
* retransmitted.
*/
if (!timer_pending(&active->T3_rtx_timer))
if (!mod_timer(&active->T3_rtx_timer,
jiffies + active->rto))
sctp_transport_hold(active);
}
list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list)
if (ch->transport == peer)
ch->transport = NULL;
asoc->peer.transport_count--;
sctp_ulpevent_notify_peer_addr_change(peer, SCTP_ADDR_REMOVED, 0);
sctp_transport_free(peer);
}
/* Add a transport address to an association. */
struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
const union sctp_addr *addr,
const gfp_t gfp,
const int peer_state)
{
struct sctp_transport *peer;
struct sctp_sock *sp;
unsigned short port;
sp = sctp_sk(asoc->base.sk);
/* AF_INET and AF_INET6 share common port field. */
port = ntohs(addr->v4.sin_port);
pr_debug("%s: association:%p addr:%pISpc state:%d\n", __func__,
asoc, &addr->sa, peer_state);
/* Set the port if it has not been set yet. */
if (0 == asoc->peer.port)
asoc->peer.port = port;
/* Check to see if this is a duplicate. */
peer = sctp_assoc_lookup_paddr(asoc, addr);
if (peer) {
/* An UNKNOWN state is only set on transports added by
* user in sctp_connectx() call. Such transports should be
* considered CONFIRMED per RFC 4960, Section 5.4.
*/
if (peer->state == SCTP_UNKNOWN) {
peer->state = SCTP_ACTIVE;
}
return peer;
}
peer = sctp_transport_new(asoc->base.net, addr, gfp);
if (!peer)
return NULL;
sctp_transport_set_owner(peer, asoc);
/* Initialize the peer's heartbeat interval based on the
* association configured value.
*/
peer->hbinterval = asoc->hbinterval;
peer->probe_interval = asoc->probe_interval;
peer->encap_port = asoc->encap_port;
/* Set the path max_retrans. */
peer->pathmaxrxt = asoc->pathmaxrxt;
/* And the partial failure retrans threshold */
peer->pf_retrans = asoc->pf_retrans;
/* And the primary path switchover retrans threshold */
peer->ps_retrans = asoc->ps_retrans;
/* Initialize the peer's SACK delay timeout based on the
* association configured value.
*/
peer->sackdelay = asoc->sackdelay;
peer->sackfreq = asoc->sackfreq;
if (addr->sa.sa_family == AF_INET6) {
__be32 info = addr->v6.sin6_flowinfo;
if (info) {
peer->flowlabel = ntohl(info & IPV6_FLOWLABEL_MASK);
peer->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
} else {
peer->flowlabel = asoc->flowlabel;
}
}
peer->dscp = asoc->dscp;
/* Enable/disable heartbeat, SACK delay, and path MTU discovery
* based on association setting.
*/
peer->param_flags = asoc->param_flags;
/* Initialize the pmtu of the transport. */
sctp_transport_route(peer, NULL, sp);
/* If this is the first transport addr on this association,
* initialize the association PMTU to the peer's PMTU.
* If not and the current association PMTU is higher than the new
* peer's PMTU, reset the association PMTU to the new peer's PMTU.
*/
sctp_assoc_set_pmtu(asoc, asoc->pathmtu ?
min_t(int, peer->pathmtu, asoc->pathmtu) :
peer->pathmtu);
peer->pmtu_pending = 0;
/* The asoc->peer.port might not be meaningful yet, but
* initialize the packet structure anyway.
*/
sctp_packet_init(&peer->packet, peer, asoc->base.bind_addr.port,
asoc->peer.port);
/* 7.2.1 Slow-Start
*
* o The initial cwnd before DATA transmission or after a sufficiently
* long idle period MUST be set to
* min(4*MTU, max(2*MTU, 4380 bytes))
*
* o The initial value of ssthresh MAY be arbitrarily high
* (for example, implementations MAY use the size of the
* receiver advertised window).
*/
peer->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380));
/* At this point, we may not have the receiver's advertised window,
* so initialize ssthresh to the default value and it will be set
* later when we process the INIT.
*/
peer->ssthresh = SCTP_DEFAULT_MAXWINDOW;
peer->partial_bytes_acked = 0;
peer->flight_size = 0;
peer->burst_limited = 0;
/* Set the transport's RTO.initial value */
peer->rto = asoc->rto_initial;
sctp_max_rto(asoc, peer);
/* Set the peer's active state. */
peer->state = peer_state;
/* Add this peer into the transport hashtable */
if (sctp_hash_transport(peer)) {
sctp_transport_free(peer);
return NULL;
}
sctp_transport_pl_reset(peer);
/* Attach the remote transport to our asoc. */
list_add_tail_rcu(&peer->transports, &asoc->peer.transport_addr_list);
asoc->peer.transport_count++;
sctp_ulpevent_notify_peer_addr_change(peer, SCTP_ADDR_ADDED, 0);
/* If we do not yet have a primary path, set one. */
if (!asoc->peer.primary_path) {
sctp_assoc_set_primary(asoc, peer);
asoc->peer.retran_path = peer;
}
if (asoc->peer.active_path == asoc->peer.retran_path &&
peer->state != SCTP_UNCONFIRMED) {
asoc->peer.retran_path = peer;
}
return peer;
}
/* Delete a transport address from an association. */
void sctp_assoc_del_peer(struct sctp_association *asoc,
const union sctp_addr *addr)
{
struct list_head *pos;
struct list_head *temp;
struct sctp_transport *transport;
list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) {
transport = list_entry(pos, struct sctp_transport, transports);
if (sctp_cmp_addr_exact(addr, &transport->ipaddr)) {
/* Do book keeping for removing the peer and free it. */
sctp_assoc_rm_peer(asoc, transport);
break;
}
}
}
/* Lookup a transport by address. */
struct sctp_transport *sctp_assoc_lookup_paddr(
const struct sctp_association *asoc,
const union sctp_addr *address)
{
struct sctp_transport *t;
/* Cycle through all transports searching for a peer address. */
list_for_each_entry(t, &asoc->peer.transport_addr_list,
transports) {
if (sctp_cmp_addr_exact(address, &t->ipaddr))
return t;
}
return NULL;
}
/* Remove all transports except a give one */
void sctp_assoc_del_nonprimary_peers(struct sctp_association *asoc,
struct sctp_transport *primary)
{
struct sctp_transport *temp;
struct sctp_transport *t;
list_for_each_entry_safe(t, temp, &asoc->peer.transport_addr_list,
transports) {
/* if the current transport is not the primary one, delete it */
if (t != primary)
sctp_assoc_rm_peer(asoc, t);
}
}
/* Engage in transport control operations.
* Mark the transport up or down and send a notification to the user.
* Select and update the new active and retran paths.
*/
void sctp_assoc_control_transport(struct sctp_association *asoc,
struct sctp_transport *transport,
enum sctp_transport_cmd command,
sctp_sn_error_t error)
{
int spc_state = SCTP_ADDR_AVAILABLE;
bool ulp_notify = true;
/* Record the transition on the transport. */
switch (command) {
case SCTP_TRANSPORT_UP:
/* If we are moving from UNCONFIRMED state due
* to heartbeat success, report the SCTP_ADDR_CONFIRMED
* state to the user, otherwise report SCTP_ADDR_AVAILABLE.
*/
if (transport->state == SCTP_PF &&
asoc->pf_expose != SCTP_PF_EXPOSE_ENABLE)
ulp_notify = false;
else if (transport->state == SCTP_UNCONFIRMED &&
error == SCTP_HEARTBEAT_SUCCESS)
spc_state = SCTP_ADDR_CONFIRMED;
transport->state = SCTP_ACTIVE;
sctp_transport_pl_reset(transport);
break;
case SCTP_TRANSPORT_DOWN:
/* If the transport was never confirmed, do not transition it
* to inactive state. Also, release the cached route since
* there may be a better route next time.
*/
if (transport->state != SCTP_UNCONFIRMED) {
transport->state = SCTP_INACTIVE;
sctp_transport_pl_reset(transport);
spc_state = SCTP_ADDR_UNREACHABLE;
} else {
sctp_transport_dst_release(transport);
ulp_notify = false;
}
break;
case SCTP_TRANSPORT_PF:
transport->state = SCTP_PF;
if (asoc->pf_expose != SCTP_PF_EXPOSE_ENABLE)
ulp_notify = false;
else
spc_state = SCTP_ADDR_POTENTIALLY_FAILED;
break;
default:
return;
}
/* Generate and send a SCTP_PEER_ADDR_CHANGE notification
* to the user.
*/
if (ulp_notify)
sctp_ulpevent_notify_peer_addr_change(transport,
spc_state, error);
/* Select new active and retran paths. */
sctp_select_active_and_retran_path(asoc);
}
/* Hold a reference to an association. */
void sctp_association_hold(struct sctp_association *asoc)
{
refcount_inc(&asoc->base.refcnt);
}
/* Release a reference to an association and cleanup
* if there are no more references.
*/
void sctp_association_put(struct sctp_association *asoc)
{
if (refcount_dec_and_test(&asoc->base.refcnt))
sctp_association_destroy(asoc);
}
/* Allocate the next TSN, Transmission Sequence Number, for the given
* association.
*/
__u32 sctp_association_get_next_tsn(struct sctp_association *asoc)
{
/* From Section 1.6 Serial Number Arithmetic:
* Transmission Sequence Numbers wrap around when they reach
* 2**32 - 1. That is, the next TSN a DATA chunk MUST use
* after transmitting TSN = 2*32 - 1 is TSN = 0.
*/
__u32 retval = asoc->next_tsn;
asoc->next_tsn++;
asoc->unack_data++;
return retval;
}
/* Compare two addresses to see if they match. Wildcard addresses
* only match themselves.
*/
int sctp_cmp_addr_exact(const union sctp_addr *ss1,
const union sctp_addr *ss2)
{
struct sctp_af *af;
af = sctp_get_af_specific(ss1->sa.sa_family);
if (unlikely(!af))
return 0;
return af->cmp_addr(ss1, ss2);
}
/* Return an ecne chunk to get prepended to a packet.
* Note: We are sly and return a shared, prealloced chunk. FIXME:
* No we don't, but we could/should.
*/
struct sctp_chunk *sctp_get_ecne_prepend(struct sctp_association *asoc)
{
if (!asoc->need_ecne)
return NULL;
/* Send ECNE if needed.
* Not being able to allocate a chunk here is not deadly.
*/
return sctp_make_ecne(asoc, asoc->last_ecne_tsn);
}
/*
* Find which transport this TSN was sent on.
*/
struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *asoc,
__u32 tsn)
{
struct sctp_transport *active;
struct sctp_transport *match;
struct sctp_transport *transport;
struct sctp_chunk *chunk;
__be32 key = htonl(tsn);
match = NULL;
/*
* FIXME: In general, find a more efficient data structure for
* searching.
*/
/*
* The general strategy is to search each transport's transmitted
* list. Return which transport this TSN lives on.
*
* Let's be hopeful and check the active_path first.
* Another optimization would be to know if there is only one
* outbound path and not have to look for the TSN at all.
*
*/
active = asoc->peer.active_path;
list_for_each_entry(chunk, &active->transmitted,
transmitted_list) {
if (key == chunk->subh.data_hdr->tsn) {
match = active;
goto out;
}
}
/* If not found, go search all the other transports. */
list_for_each_entry(transport, &asoc->peer.transport_addr_list,
transports) {
if (transport == active)
continue;
list_for_each_entry(chunk, &transport->transmitted,
transmitted_list) {
if (key == chunk->subh.data_hdr->tsn) {
match = transport;
goto out;
}
}
}
out:
return match;
}
/* Do delayed input processing. This is scheduled by sctp_rcv(). */
static void sctp_assoc_bh_rcv(struct work_struct *work)
{
struct sctp_association *asoc =
container_of(work, struct sctp_association,
base.inqueue.immediate);
struct net *net = asoc->base.net;
union sctp_subtype subtype;
struct sctp_endpoint *ep;
struct sctp_chunk *chunk;
struct sctp_inq *inqueue;
int first_time = 1; /* is this the first time through the loop */
int error = 0;
int state;
/* The association should be held so we should be safe. */
ep = asoc->ep;
inqueue = &asoc->base.inqueue;
sctp_association_hold(asoc);
while (NULL != (chunk = sctp_inq_pop(inqueue))) {
state = asoc->state;
subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type);