forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
outqueue.c
1870 lines (1651 loc) · 54.4 KB
/
outqueue.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
/* SCTP kernel implementation
* (C) Copyright IBM Corp. 2001, 2004
* Copyright (c) 1999-2000 Cisco, Inc.
* Copyright (c) 1999-2001 Motorola, Inc.
* Copyright (c) 2001-2003 Intel Corp.
*
* This file is part of the SCTP kernel implementation
*
* These functions implement the sctp_outq class. The outqueue handles
* bundling and queueing of outgoing SCTP chunks.
*
* This SCTP implementation is free software;
* you can redistribute it and/or modify it under the terms of
* the GNU General Public License as published by
* the Free Software Foundation; either version 2, or (at your option)
* any later version.
*
* This SCTP implementation is distributed in the hope that it
* will be useful, but WITHOUT ANY WARRANTY; without even the implied
* ************************
* warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
* See the GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with GNU CC; see the file COPYING. If not, see
* <http://www.gnu.org/licenses/>.
*
* 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]>
* Perry Melange <[email protected]>
* Xingang Guo <[email protected]>
* Hui Huang <[email protected]>
* Sridhar Samudrala <[email protected]>
* Jon Grimm <[email protected]>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/types.h>
#include <linux/list.h> /* For struct list_head */
#include <linux/socket.h>
#include <linux/ip.h>
#include <linux/slab.h>
#include <net/sock.h> /* For skb_set_owner_w */
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
/* Declare internal functions here. */
static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn);
static void sctp_check_transmitted(struct sctp_outq *q,
struct list_head *transmitted_queue,
struct sctp_transport *transport,
union sctp_addr *saddr,
struct sctp_sackhdr *sack,
__u32 *highest_new_tsn);
static void sctp_mark_missing(struct sctp_outq *q,
struct list_head *transmitted_queue,
struct sctp_transport *transport,
__u32 highest_new_tsn,
int count_of_newacks);
static void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 sack_ctsn);
static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp);
/* Add data to the front of the queue. */
static inline void sctp_outq_head_data(struct sctp_outq *q,
struct sctp_chunk *ch)
{
list_add(&ch->list, &q->out_chunk_list);
q->out_qlen += ch->skb->len;
}
/* Take data from the front of the queue. */
static inline struct sctp_chunk *sctp_outq_dequeue_data(struct sctp_outq *q)
{
struct sctp_chunk *ch = NULL;
if (!list_empty(&q->out_chunk_list)) {
struct list_head *entry = q->out_chunk_list.next;
ch = list_entry(entry, struct sctp_chunk, list);
list_del_init(entry);
q->out_qlen -= ch->skb->len;
}
return ch;
}
/* Add data chunk to the end of the queue. */
static inline void sctp_outq_tail_data(struct sctp_outq *q,
struct sctp_chunk *ch)
{
list_add_tail(&ch->list, &q->out_chunk_list);
q->out_qlen += ch->skb->len;
}
/*
* SFR-CACC algorithm:
* D) If count_of_newacks is greater than or equal to 2
* and t was not sent to the current primary then the
* sender MUST NOT increment missing report count for t.
*/
static inline int sctp_cacc_skip_3_1_d(struct sctp_transport *primary,
struct sctp_transport *transport,
int count_of_newacks)
{
if (count_of_newacks >= 2 && transport != primary)
return 1;
return 0;
}
/*
* SFR-CACC algorithm:
* F) If count_of_newacks is less than 2, let d be the
* destination to which t was sent. If cacc_saw_newack
* is 0 for destination d, then the sender MUST NOT
* increment missing report count for t.
*/
static inline int sctp_cacc_skip_3_1_f(struct sctp_transport *transport,
int count_of_newacks)
{
if (count_of_newacks < 2 &&
(transport && !transport->cacc.cacc_saw_newack))
return 1;
return 0;
}
/*
* SFR-CACC algorithm:
* 3.1) If CYCLING_CHANGEOVER is 0, the sender SHOULD
* execute steps C, D, F.
*
* C has been implemented in sctp_outq_sack
*/
static inline int sctp_cacc_skip_3_1(struct sctp_transport *primary,
struct sctp_transport *transport,
int count_of_newacks)
{
if (!primary->cacc.cycling_changeover) {
if (sctp_cacc_skip_3_1_d(primary, transport, count_of_newacks))
return 1;
if (sctp_cacc_skip_3_1_f(transport, count_of_newacks))
return 1;
return 0;
}
return 0;
}
/*
* SFR-CACC algorithm:
* 3.2) Else if CYCLING_CHANGEOVER is 1, and t is less
* than next_tsn_at_change of the current primary, then
* the sender MUST NOT increment missing report count
* for t.
*/
static inline int sctp_cacc_skip_3_2(struct sctp_transport *primary, __u32 tsn)
{
if (primary->cacc.cycling_changeover &&
TSN_lt(tsn, primary->cacc.next_tsn_at_change))
return 1;
return 0;
}
/*
* SFR-CACC algorithm:
* 3) If the missing report count for TSN t is to be
* incremented according to [RFC2960] and
* [SCTP_STEWART-2002], and CHANGEOVER_ACTIVE is set,
* then the sender MUST further execute steps 3.1 and
* 3.2 to determine if the missing report count for
* TSN t SHOULD NOT be incremented.
*
* 3.3) If 3.1 and 3.2 do not dictate that the missing
* report count for t should not be incremented, then
* the sender SHOULD increment missing report count for
* t (according to [RFC2960] and [SCTP_STEWART_2002]).
*/
static inline int sctp_cacc_skip(struct sctp_transport *primary,
struct sctp_transport *transport,
int count_of_newacks,
__u32 tsn)
{
if (primary->cacc.changeover_active &&
(sctp_cacc_skip_3_1(primary, transport, count_of_newacks) ||
sctp_cacc_skip_3_2(primary, tsn)))
return 1;
return 0;
}
/* Initialize an existing sctp_outq. This does the boring stuff.
* You still need to define handlers if you really want to DO
* something with this structure...
*/
void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q)
{
memset(q, 0, sizeof(struct sctp_outq));
q->asoc = asoc;
INIT_LIST_HEAD(&q->out_chunk_list);
INIT_LIST_HEAD(&q->control_chunk_list);
INIT_LIST_HEAD(&q->retransmit);
INIT_LIST_HEAD(&q->sacked);
INIT_LIST_HEAD(&q->abandoned);
}
/* Free the outqueue structure and any related pending chunks.
*/
static void __sctp_outq_teardown(struct sctp_outq *q)
{
struct sctp_transport *transport;
struct list_head *lchunk, *temp;
struct sctp_chunk *chunk, *tmp;
/* Throw away unacknowledged chunks. */
list_for_each_entry(transport, &q->asoc->peer.transport_addr_list,
transports) {
while ((lchunk = sctp_list_dequeue(&transport->transmitted)) != NULL) {
chunk = list_entry(lchunk, struct sctp_chunk,
transmitted_list);
/* Mark as part of a failed message. */
sctp_chunk_fail(chunk, q->error);
sctp_chunk_free(chunk);
}
}
/* Throw away chunks that have been gap ACKed. */
list_for_each_safe(lchunk, temp, &q->sacked) {
list_del_init(lchunk);
chunk = list_entry(lchunk, struct sctp_chunk,
transmitted_list);
sctp_chunk_fail(chunk, q->error);
sctp_chunk_free(chunk);
}
/* Throw away any chunks in the retransmit queue. */
list_for_each_safe(lchunk, temp, &q->retransmit) {
list_del_init(lchunk);
chunk = list_entry(lchunk, struct sctp_chunk,
transmitted_list);
sctp_chunk_fail(chunk, q->error);
sctp_chunk_free(chunk);
}
/* Throw away any chunks that are in the abandoned queue. */
list_for_each_safe(lchunk, temp, &q->abandoned) {
list_del_init(lchunk);
chunk = list_entry(lchunk, struct sctp_chunk,
transmitted_list);
sctp_chunk_fail(chunk, q->error);
sctp_chunk_free(chunk);
}
/* Throw away any leftover data chunks. */
while ((chunk = sctp_outq_dequeue_data(q)) != NULL) {
/* Mark as send failure. */
sctp_chunk_fail(chunk, q->error);
sctp_chunk_free(chunk);
}
/* Throw away any leftover control chunks. */
list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) {
list_del_init(&chunk->list);
sctp_chunk_free(chunk);
}
}
void sctp_outq_teardown(struct sctp_outq *q)
{
__sctp_outq_teardown(q);
sctp_outq_init(q->asoc, q);
}
/* Free the outqueue structure and any related pending chunks. */
void sctp_outq_free(struct sctp_outq *q)
{
/* Throw away leftover chunks. */
__sctp_outq_teardown(q);
}
/* Put a new chunk in an sctp_outq. */
void sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk, gfp_t gfp)
{
struct net *net = sock_net(q->asoc->base.sk);
pr_debug("%s: outq:%p, chunk:%p[%s]\n", __func__, q, chunk,
chunk && chunk->chunk_hdr ?
sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) :
"illegal chunk");
/* If it is data, queue it up, otherwise, send it
* immediately.
*/
if (sctp_chunk_is_data(chunk)) {
pr_debug("%s: outqueueing: outq:%p, chunk:%p[%s])\n",
__func__, q, chunk, chunk && chunk->chunk_hdr ?
sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) :
"illegal chunk");
sctp_outq_tail_data(q, chunk);
if (chunk->asoc->peer.prsctp_capable &&
SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags))
chunk->asoc->sent_cnt_removable++;
if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS);
else
SCTP_INC_STATS(net, SCTP_MIB_OUTORDERCHUNKS);
} else {
list_add_tail(&chunk->list, &q->control_chunk_list);
SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS);
}
if (!q->cork)
sctp_outq_flush(q, 0, gfp);
}
/* Insert a chunk into the sorted list based on the TSNs. The retransmit list
* and the abandoned list are in ascending order.
*/
static void sctp_insert_list(struct list_head *head, struct list_head *new)
{
struct list_head *pos;
struct sctp_chunk *nchunk, *lchunk;
__u32 ntsn, ltsn;
int done = 0;
nchunk = list_entry(new, struct sctp_chunk, transmitted_list);
ntsn = ntohl(nchunk->subh.data_hdr->tsn);
list_for_each(pos, head) {
lchunk = list_entry(pos, struct sctp_chunk, transmitted_list);
ltsn = ntohl(lchunk->subh.data_hdr->tsn);
if (TSN_lt(ntsn, ltsn)) {
list_add(new, pos->prev);
done = 1;
break;
}
}
if (!done)
list_add_tail(new, head);
}
static int sctp_prsctp_prune_sent(struct sctp_association *asoc,
struct sctp_sndrcvinfo *sinfo,
struct list_head *queue, int msg_len)
{
struct sctp_chunk *chk, *temp;
list_for_each_entry_safe(chk, temp, queue, transmitted_list) {
if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) ||
chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)
continue;
list_del_init(&chk->transmitted_list);
sctp_insert_list(&asoc->outqueue.abandoned,
&chk->transmitted_list);
asoc->sent_cnt_removable--;
asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
if (!chk->tsn_gap_acked) {
if (chk->transport)
chk->transport->flight_size -=
sctp_data_size(chk);
asoc->outqueue.outstanding_bytes -= sctp_data_size(chk);
}
msg_len -= SCTP_DATA_SNDSIZE(chk) +
sizeof(struct sk_buff) +
sizeof(struct sctp_chunk);
if (msg_len <= 0)
break;
}
return msg_len;
}
static int sctp_prsctp_prune_unsent(struct sctp_association *asoc,
struct sctp_sndrcvinfo *sinfo,
struct list_head *queue, int msg_len)
{
struct sctp_chunk *chk, *temp;
list_for_each_entry_safe(chk, temp, queue, list) {
if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) ||
chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)
continue;
list_del_init(&chk->list);
asoc->sent_cnt_removable--;
asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
msg_len -= SCTP_DATA_SNDSIZE(chk) +
sizeof(struct sk_buff) +
sizeof(struct sctp_chunk);
sctp_chunk_free(chk);
if (msg_len <= 0)
break;
}
return msg_len;
}
/* Abandon the chunks according their priorities */
void sctp_prsctp_prune(struct sctp_association *asoc,
struct sctp_sndrcvinfo *sinfo, int msg_len)
{
struct sctp_transport *transport;
if (!asoc->peer.prsctp_capable || !asoc->sent_cnt_removable)
return;
msg_len = sctp_prsctp_prune_sent(asoc, sinfo,
&asoc->outqueue.retransmit,
msg_len);
if (msg_len <= 0)
return;
list_for_each_entry(transport, &asoc->peer.transport_addr_list,
transports) {
msg_len = sctp_prsctp_prune_sent(asoc, sinfo,
&transport->transmitted,
msg_len);
if (msg_len <= 0)
return;
}
sctp_prsctp_prune_unsent(asoc, sinfo,
&asoc->outqueue.out_chunk_list,
msg_len);
}
/* Mark all the eligible packets on a transport for retransmission. */
void sctp_retransmit_mark(struct sctp_outq *q,
struct sctp_transport *transport,
__u8 reason)
{
struct list_head *lchunk, *ltemp;
struct sctp_chunk *chunk;
/* Walk through the specified transmitted queue. */
list_for_each_safe(lchunk, ltemp, &transport->transmitted) {
chunk = list_entry(lchunk, struct sctp_chunk,
transmitted_list);
/* If the chunk is abandoned, move it to abandoned list. */
if (sctp_chunk_abandoned(chunk)) {
list_del_init(lchunk);
sctp_insert_list(&q->abandoned, lchunk);
/* If this chunk has not been previousely acked,
* stop considering it 'outstanding'. Our peer
* will most likely never see it since it will
* not be retransmitted
*/
if (!chunk->tsn_gap_acked) {
if (chunk->transport)
chunk->transport->flight_size -=
sctp_data_size(chunk);
q->outstanding_bytes -= sctp_data_size(chunk);
q->asoc->peer.rwnd += sctp_data_size(chunk);
}
continue;
}
/* If we are doing retransmission due to a timeout or pmtu
* discovery, only the chunks that are not yet acked should
* be added to the retransmit queue.
*/
if ((reason == SCTP_RTXR_FAST_RTX &&
(chunk->fast_retransmit == SCTP_NEED_FRTX)) ||
(reason != SCTP_RTXR_FAST_RTX && !chunk->tsn_gap_acked)) {
/* RFC 2960 6.2.1 Processing a Received SACK
*
* C) Any time a DATA chunk is marked for
* retransmission (via either T3-rtx timer expiration
* (Section 6.3.3) or via fast retransmit
* (Section 7.2.4)), add the data size of those
* chunks to the rwnd.
*/
q->asoc->peer.rwnd += sctp_data_size(chunk);
q->outstanding_bytes -= sctp_data_size(chunk);
if (chunk->transport)
transport->flight_size -= sctp_data_size(chunk);
/* sctpimpguide-05 Section 2.8.2
* M5) If a T3-rtx timer expires, the
* 'TSN.Missing.Report' of all affected TSNs is set
* to 0.
*/
chunk->tsn_missing_report = 0;
/* If a chunk that is being used for RTT measurement
* has to be retransmitted, we cannot use this chunk
* anymore for RTT measurements. Reset rto_pending so
* that a new RTT measurement is started when a new
* data chunk is sent.
*/
if (chunk->rtt_in_progress) {
chunk->rtt_in_progress = 0;
transport->rto_pending = 0;
}
chunk->resent = 1;
/* Move the chunk to the retransmit queue. The chunks
* on the retransmit queue are always kept in order.
*/
list_del_init(lchunk);
sctp_insert_list(&q->retransmit, lchunk);
}
}
pr_debug("%s: transport:%p, reason:%d, cwnd:%d, ssthresh:%d, "
"flight_size:%d, pba:%d\n", __func__, transport, reason,
transport->cwnd, transport->ssthresh, transport->flight_size,
transport->partial_bytes_acked);
}
/* Mark all the eligible packets on a transport for retransmission and force
* one packet out.
*/
void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport,
sctp_retransmit_reason_t reason)
{
struct net *net = sock_net(q->asoc->base.sk);
switch (reason) {
case SCTP_RTXR_T3_RTX:
SCTP_INC_STATS(net, SCTP_MIB_T3_RETRANSMITS);
sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_T3_RTX);
/* Update the retran path if the T3-rtx timer has expired for
* the current retran path.
*/
if (transport == transport->asoc->peer.retran_path)
sctp_assoc_update_retran_path(transport->asoc);
transport->asoc->rtx_data_chunks +=
transport->asoc->unack_data;
break;
case SCTP_RTXR_FAST_RTX:
SCTP_INC_STATS(net, SCTP_MIB_FAST_RETRANSMITS);
sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX);
q->fast_rtx = 1;
break;
case SCTP_RTXR_PMTUD:
SCTP_INC_STATS(net, SCTP_MIB_PMTUD_RETRANSMITS);
break;
case SCTP_RTXR_T1_RTX:
SCTP_INC_STATS(net, SCTP_MIB_T1_RETRANSMITS);
transport->asoc->init_retries++;
break;
default:
BUG();
}
sctp_retransmit_mark(q, transport, reason);
/* PR-SCTP A5) Any time the T3-rtx timer expires, on any destination,
* the sender SHOULD try to advance the "Advanced.Peer.Ack.Point" by
* following the procedures outlined in C1 - C5.
*/
if (reason == SCTP_RTXR_T3_RTX)
sctp_generate_fwdtsn(q, q->asoc->ctsn_ack_point);
/* Flush the queues only on timeout, since fast_rtx is only
* triggered during sack processing and the queue
* will be flushed at the end.
*/
if (reason != SCTP_RTXR_FAST_RTX)
sctp_outq_flush(q, /* rtx_timeout */ 1, GFP_ATOMIC);
}
/*
* Transmit DATA chunks on the retransmit queue. Upon return from
* sctp_outq_flush_rtx() the packet 'pkt' may contain chunks which
* need to be transmitted by the caller.
* We assume that pkt->transport has already been set.
*
* The return value is a normal kernel error return value.
*/
static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
int rtx_timeout, int *start_timer)
{
struct list_head *lqueue;
struct sctp_transport *transport = pkt->transport;
sctp_xmit_t status;
struct sctp_chunk *chunk, *chunk1;
int fast_rtx;
int error = 0;
int timer = 0;
int done = 0;
lqueue = &q->retransmit;
fast_rtx = q->fast_rtx;
/* This loop handles time-out retransmissions, fast retransmissions,
* and retransmissions due to opening of whindow.
*
* RFC 2960 6.3.3 Handle T3-rtx Expiration
*
* E3) Determine how many of the earliest (i.e., lowest TSN)
* outstanding DATA chunks for the address for which the
* T3-rtx has expired will fit into a single packet, subject
* to the MTU constraint for the path corresponding to the
* destination transport address to which the retransmission
* is being sent (this may be different from the address for
* which the timer expires [see Section 6.4]). Call this value
* K. Bundle and retransmit those K DATA chunks in a single
* packet to the destination endpoint.
*
* [Just to be painfully clear, if we are retransmitting
* because a timeout just happened, we should send only ONE
* packet of retransmitted data.]
*
* For fast retransmissions we also send only ONE packet. However,
* if we are just flushing the queue due to open window, we'll
* try to send as much as possible.
*/
list_for_each_entry_safe(chunk, chunk1, lqueue, transmitted_list) {
/* If the chunk is abandoned, move it to abandoned list. */
if (sctp_chunk_abandoned(chunk)) {
list_del_init(&chunk->transmitted_list);
sctp_insert_list(&q->abandoned,
&chunk->transmitted_list);
continue;
}
/* Make sure that Gap Acked TSNs are not retransmitted. A
* simple approach is just to move such TSNs out of the
* way and into a 'transmitted' queue and skip to the
* next chunk.
*/
if (chunk->tsn_gap_acked) {
list_move_tail(&chunk->transmitted_list,
&transport->transmitted);
continue;
}
/* If we are doing fast retransmit, ignore non-fast_rtransmit
* chunks
*/
if (fast_rtx && !chunk->fast_retransmit)
continue;
redo:
/* Attempt to append this chunk to the packet. */
status = sctp_packet_append_chunk(pkt, chunk);
switch (status) {
case SCTP_XMIT_PMTU_FULL:
if (!pkt->has_data && !pkt->has_cookie_echo) {
/* If this packet did not contain DATA then
* retransmission did not happen, so do it
* again. We'll ignore the error here since
* control chunks are already freed so there
* is nothing we can do.
*/
sctp_packet_transmit(pkt, GFP_ATOMIC);
goto redo;
}
/* Send this packet. */
error = sctp_packet_transmit(pkt, GFP_ATOMIC);
/* If we are retransmitting, we should only
* send a single packet.
* Otherwise, try appending this chunk again.
*/
if (rtx_timeout || fast_rtx)
done = 1;
else
goto redo;
/* Bundle next chunk in the next round. */
break;
case SCTP_XMIT_RWND_FULL:
/* Send this packet. */
error = sctp_packet_transmit(pkt, GFP_ATOMIC);
/* Stop sending DATA as there is no more room
* at the receiver.
*/
done = 1;
break;
case SCTP_XMIT_DELAY:
/* Send this packet. */
error = sctp_packet_transmit(pkt, GFP_ATOMIC);
/* Stop sending DATA because of nagle delay. */
done = 1;
break;
default:
/* The append was successful, so add this chunk to
* the transmitted list.
*/
list_move_tail(&chunk->transmitted_list,
&transport->transmitted);
/* Mark the chunk as ineligible for fast retransmit
* after it is retransmitted.
*/
if (chunk->fast_retransmit == SCTP_NEED_FRTX)
chunk->fast_retransmit = SCTP_DONT_FRTX;
q->asoc->stats.rtxchunks++;
break;
}
/* Set the timer if there were no errors */
if (!error && !timer)
timer = 1;
if (done)
break;
}
/* If we are here due to a retransmit timeout or a fast
* retransmit and if there are any chunks left in the retransmit
* queue that could not fit in the PMTU sized packet, they need
* to be marked as ineligible for a subsequent fast retransmit.
*/
if (rtx_timeout || fast_rtx) {
list_for_each_entry(chunk1, lqueue, transmitted_list) {
if (chunk1->fast_retransmit == SCTP_NEED_FRTX)
chunk1->fast_retransmit = SCTP_DONT_FRTX;
}
}
*start_timer = timer;
/* Clear fast retransmit hint */
if (fast_rtx)
q->fast_rtx = 0;
return error;
}
/* Cork the outqueue so queued chunks are really queued. */
void sctp_outq_uncork(struct sctp_outq *q, gfp_t gfp)
{
if (q->cork)
q->cork = 0;
sctp_outq_flush(q, 0, gfp);
}
/*
* Try to flush an outqueue.
*
* Description: Send everything in q which we legally can, subject to
* congestion limitations.
* * Note: This function can be called from multiple contexts so appropriate
* locking concerns must be made. Today we use the sock lock to protect
* this function.
*/
static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
{
struct sctp_packet *packet;
struct sctp_packet singleton;
struct sctp_association *asoc = q->asoc;
__u16 sport = asoc->base.bind_addr.port;
__u16 dport = asoc->peer.port;
__u32 vtag = asoc->peer.i.init_tag;
struct sctp_transport *transport = NULL;
struct sctp_transport *new_transport;
struct sctp_chunk *chunk, *tmp;
sctp_xmit_t status;
int error = 0;
int start_timer = 0;
int one_packet = 0;
/* These transports have chunks to send. */
struct list_head transport_list;
struct list_head *ltransport;
INIT_LIST_HEAD(&transport_list);
packet = NULL;
/*
* 6.10 Bundling
* ...
* When bundling control chunks with DATA chunks, an
* endpoint MUST place control chunks first in the outbound
* SCTP packet. The transmitter MUST transmit DATA chunks
* within a SCTP packet in increasing order of TSN.
* ...
*/
list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) {
/* RFC 5061, 5.3
* F1) This means that until such time as the ASCONF
* containing the add is acknowledged, the sender MUST
* NOT use the new IP address as a source for ANY SCTP
* packet except on carrying an ASCONF Chunk.
*/
if (asoc->src_out_of_asoc_ok &&
chunk->chunk_hdr->type != SCTP_CID_ASCONF)
continue;
list_del_init(&chunk->list);
/* Pick the right transport to use. */
new_transport = chunk->transport;
if (!new_transport) {
/*
* If we have a prior transport pointer, see if
* the destination address of the chunk
* matches the destination address of the
* current transport. If not a match, then
* try to look up the transport with a given
* destination address. We do this because
* after processing ASCONFs, we may have new
* transports created.
*/
if (transport &&
sctp_cmp_addr_exact(&chunk->dest,
&transport->ipaddr))
new_transport = transport;
else
new_transport = sctp_assoc_lookup_paddr(asoc,
&chunk->dest);
/* if we still don't have a new transport, then
* use the current active path.
*/
if (!new_transport)
new_transport = asoc->peer.active_path;
} else if ((new_transport->state == SCTP_INACTIVE) ||
(new_transport->state == SCTP_UNCONFIRMED) ||
(new_transport->state == SCTP_PF)) {
/* If the chunk is Heartbeat or Heartbeat Ack,
* send it to chunk->transport, even if it's
* inactive.
*
* 3.3.6 Heartbeat Acknowledgement:
* ...
* A HEARTBEAT ACK is always sent to the source IP
* address of the IP datagram containing the
* HEARTBEAT chunk to which this ack is responding.
* ...
*
* ASCONF_ACKs also must be sent to the source.
*/
if (chunk->chunk_hdr->type != SCTP_CID_HEARTBEAT &&
chunk->chunk_hdr->type != SCTP_CID_HEARTBEAT_ACK &&
chunk->chunk_hdr->type != SCTP_CID_ASCONF_ACK)
new_transport = asoc->peer.active_path;
}
/* Are we switching transports?
* Take care of transport locks.
*/
if (new_transport != transport) {
transport = new_transport;
if (list_empty(&transport->send_ready)) {
list_add_tail(&transport->send_ready,
&transport_list);
}
packet = &transport->packet;
sctp_packet_config(packet, vtag,
asoc->peer.ecn_capable);
}
switch (chunk->chunk_hdr->type) {
/*
* 6.10 Bundling
* ...
* An endpoint MUST NOT bundle INIT, INIT ACK or SHUTDOWN
* COMPLETE with any other chunks. [Send them immediately.]
*/
case SCTP_CID_INIT:
case SCTP_CID_INIT_ACK:
case SCTP_CID_SHUTDOWN_COMPLETE:
sctp_packet_init(&singleton, transport, sport, dport);
sctp_packet_config(&singleton, vtag, 0);
sctp_packet_append_chunk(&singleton, chunk);
error = sctp_packet_transmit(&singleton, gfp);
if (error < 0) {
asoc->base.sk->sk_err = -error;
return;
}
break;
case SCTP_CID_ABORT:
if (sctp_test_T_bit(chunk)) {
packet->vtag = asoc->c.my_vtag;
}
/* The following chunks are "response" chunks, i.e.
* they are generated in response to something we
* received. If we are sending these, then we can
* send only 1 packet containing these chunks.
*/
case SCTP_CID_HEARTBEAT_ACK:
case SCTP_CID_SHUTDOWN_ACK:
case SCTP_CID_COOKIE_ACK:
case SCTP_CID_COOKIE_ECHO:
case SCTP_CID_ERROR:
case SCTP_CID_ECN_CWR:
case SCTP_CID_ASCONF_ACK:
one_packet = 1;
/* Fall through */
case SCTP_CID_SACK:
case SCTP_CID_HEARTBEAT:
case SCTP_CID_SHUTDOWN:
case SCTP_CID_ECN_ECNE:
case SCTP_CID_ASCONF:
case SCTP_CID_FWD_TSN:
status = sctp_packet_transmit_chunk(packet, chunk,
one_packet, gfp);
if (status != SCTP_XMIT_OK) {
/* put the chunk back */
list_add(&chunk->list, &q->control_chunk_list);
} else {
asoc->stats.octrlchunks++;
/* PR-SCTP C5) If a FORWARD TSN is sent, the
* sender MUST assure that at least one T3-rtx
* timer is running.
*/
if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN) {
sctp_transport_reset_t3_rtx(transport);
transport->last_time_sent = jiffies;
}
}
break;
default:
/* We built a chunk with an illegal type! */
BUG();
}
}
if (q->asoc->src_out_of_asoc_ok)
goto sctp_flush_out;
/* Is it OK to send data chunks? */
switch (asoc->state) {
case SCTP_STATE_COOKIE_ECHOED:
/* Only allow bundling when this packet has a COOKIE-ECHO
* chunk.
*/
if (!packet || !packet->has_cookie_echo)
break;
/* fallthru */
case SCTP_STATE_ESTABLISHED:
case SCTP_STATE_SHUTDOWN_PENDING:
case SCTP_STATE_SHUTDOWN_RECEIVED:
/*
* RFC 2960 6.1 Transmission of DATA Chunks
*
* C) When the time comes for the sender to transmit,
* before sending new DATA chunks, the sender MUST
* first transmit any outstanding DATA chunks which
* are marked for retransmission (limited by the
* current cwnd).
*/
if (!list_empty(&q->retransmit)) {
if (asoc->peer.retran_path->state == SCTP_UNCONFIRMED)
goto sctp_flush_out;
if (transport == asoc->peer.retran_path)
goto retran;
/* Switch transports & prepare the packet. */
transport = asoc->peer.retran_path;
if (list_empty(&transport->send_ready)) {
list_add_tail(&transport->send_ready,
&transport_list);
}
packet = &transport->packet;
sctp_packet_config(packet, vtag,
asoc->peer.ecn_capable);
retran:
error = sctp_outq_flush_rtx(q, packet,
rtx_timeout, &start_timer);
if (error < 0)
asoc->base.sk->sk_err = -error;
if (start_timer) {
sctp_transport_reset_t3_rtx(transport);
transport->last_time_sent = jiffies;
}
/* This can happen on COOKIE-ECHO resend. Only
* one chunk can get bundled with a COOKIE-ECHO.
*/