forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
protocol.c
2478 lines (2017 loc) · 59.3 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
/* Multipath TCP
*
* Copyright (c) 2017 - 2019, Intel Corporation.
*/
#define pr_fmt(fmt) "MPTCP: " fmt
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/sched/signal.h>
#include <linux/atomic.h>
#include <net/sock.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
#include <net/protocol.h>
#include <net/tcp.h>
#include <net/tcp_states.h>
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
#include <net/transp_v6.h>
#endif
#include <net/mptcp.h>
#include "protocol.h"
#include "mib.h"
#define MPTCP_SAME_STATE TCP_MAX_STATES
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
struct mptcp6_sock {
struct mptcp_sock msk;
struct ipv6_pinfo np;
};
#endif
struct mptcp_skb_cb {
u32 offset;
};
#define MPTCP_SKB_CB(__skb) ((struct mptcp_skb_cb *)&((__skb)->cb[0]))
static struct percpu_counter mptcp_sockets_allocated;
/* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not
* completed yet or has failed, return the subflow socket.
* Otherwise return NULL.
*/
static struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk)
{
if (!msk->subflow || READ_ONCE(msk->can_ack))
return NULL;
return msk->subflow;
}
static bool mptcp_is_tcpsk(struct sock *sk)
{
struct socket *sock = sk->sk_socket;
if (unlikely(sk->sk_prot == &tcp_prot)) {
/* we are being invoked after mptcp_accept() has
* accepted a non-mp-capable flow: sk is a tcp_sk,
* not an mptcp one.
*
* Hand the socket over to tcp so all further socket ops
* bypass mptcp.
*/
sock->ops = &inet_stream_ops;
return true;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
} else if (unlikely(sk->sk_prot == &tcpv6_prot)) {
sock->ops = &inet6_stream_ops;
return true;
#endif
}
return false;
}
static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk)
{
sock_owned_by_me((const struct sock *)msk);
if (likely(!__mptcp_check_fallback(msk)))
return NULL;
return msk->first;
}
static int __mptcp_socket_create(struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow;
struct sock *sk = (struct sock *)msk;
struct socket *ssock;
int err;
err = mptcp_subflow_create_socket(sk, &ssock);
if (err)
return err;
msk->first = ssock->sk;
msk->subflow = ssock;
subflow = mptcp_subflow_ctx(ssock->sk);
list_add(&subflow->node, &msk->conn_list);
subflow->request_mptcp = 1;
/* accept() will wait on first subflow sk_wq, and we always wakes up
* via msk->sk_socket
*/
RCU_INIT_POINTER(msk->first->sk_wq, &sk->sk_socket->wq);
return 0;
}
static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
struct sk_buff *skb,
unsigned int offset, size_t copy_len)
{
struct sock *sk = (struct sock *)msk;
struct sk_buff *tail;
__skb_unlink(skb, &ssk->sk_receive_queue);
skb_ext_reset(skb);
skb_orphan(skb);
msk->ack_seq += copy_len;
tail = skb_peek_tail(&sk->sk_receive_queue);
if (offset == 0 && tail) {
bool fragstolen;
int delta;
if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) {
kfree_skb_partial(skb, fragstolen);
atomic_add(delta, &sk->sk_rmem_alloc);
sk_mem_charge(sk, delta);
return;
}
}
skb_set_owner_r(skb, sk);
__skb_queue_tail(&sk->sk_receive_queue, skb);
MPTCP_SKB_CB(skb)->offset = offset;
}
static void mptcp_stop_timer(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
mptcp_sk(sk)->timer_ival = 0;
}
/* both sockets must be locked */
static bool mptcp_subflow_dsn_valid(const struct mptcp_sock *msk,
struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
u64 dsn = mptcp_subflow_get_mapped_dsn(subflow);
/* revalidate data sequence number.
*
* mptcp_subflow_data_available() is usually called
* without msk lock. Its unlikely (but possible)
* that msk->ack_seq has been advanced since the last
* call found in-sequence data.
*/
if (likely(dsn == msk->ack_seq))
return true;
subflow->data_avail = 0;
return mptcp_subflow_data_available(ssk);
}
static void mptcp_check_data_fin_ack(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
if (__mptcp_check_fallback(msk))
return;
/* Look for an acknowledged DATA_FIN */
if (((1 << sk->sk_state) &
(TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) &&
msk->write_seq == atomic64_read(&msk->snd_una)) {
mptcp_stop_timer(sk);
WRITE_ONCE(msk->snd_data_fin_enable, 0);
switch (sk->sk_state) {
case TCP_FIN_WAIT1:
inet_sk_state_store(sk, TCP_FIN_WAIT2);
sk->sk_state_change(sk);
break;
case TCP_CLOSING:
fallthrough;
case TCP_LAST_ACK:
inet_sk_state_store(sk, TCP_CLOSE);
sk->sk_state_change(sk);
break;
}
if (sk->sk_shutdown == SHUTDOWN_MASK ||
sk->sk_state == TCP_CLOSE)
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
else
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
}
}
static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq)
{
struct mptcp_sock *msk = mptcp_sk(sk);
if (READ_ONCE(msk->rcv_data_fin) &&
((1 << sk->sk_state) &
(TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2))) {
u64 rcv_data_fin_seq = READ_ONCE(msk->rcv_data_fin_seq);
if (msk->ack_seq == rcv_data_fin_seq) {
if (seq)
*seq = rcv_data_fin_seq;
return true;
}
}
return false;
}
static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk)
{
long tout = ssk && inet_csk(ssk)->icsk_pending ?
inet_csk(ssk)->icsk_timeout - jiffies : 0;
if (tout <= 0)
tout = mptcp_sk(sk)->timer_ival;
mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN;
}
static void mptcp_check_data_fin(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
u64 rcv_data_fin_seq;
if (__mptcp_check_fallback(msk) || !msk->first)
return;
/* Need to ack a DATA_FIN received from a peer while this side
* of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2.
* msk->rcv_data_fin was set when parsing the incoming options
* at the subflow level and the msk lock was not held, so this
* is the first opportunity to act on the DATA_FIN and change
* the msk state.
*
* If we are caught up to the sequence number of the incoming
* DATA_FIN, send the DATA_ACK now and do state transition. If
* not caught up, do nothing and let the recv code send DATA_ACK
* when catching up.
*/
if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) {
struct mptcp_subflow_context *subflow;
msk->ack_seq++;
WRITE_ONCE(msk->rcv_data_fin, 0);
sk->sk_shutdown |= RCV_SHUTDOWN;
smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
set_bit(MPTCP_DATA_READY, &msk->flags);
switch (sk->sk_state) {
case TCP_ESTABLISHED:
inet_sk_state_store(sk, TCP_CLOSE_WAIT);
break;
case TCP_FIN_WAIT1:
inet_sk_state_store(sk, TCP_CLOSING);
break;
case TCP_FIN_WAIT2:
inet_sk_state_store(sk, TCP_CLOSE);
// @@ Close subflows now?
break;
default:
/* Other states not expected */
WARN_ON_ONCE(1);
break;
}
mptcp_set_timeout(sk, NULL);
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
lock_sock(ssk);
tcp_send_ack(ssk);
release_sock(ssk);
}
sk->sk_state_change(sk);
if (sk->sk_shutdown == SHUTDOWN_MASK ||
sk->sk_state == TCP_CLOSE)
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
else
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
}
}
static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
struct sock *ssk,
unsigned int *bytes)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct sock *sk = (struct sock *)msk;
unsigned int moved = 0;
bool more_data_avail;
struct tcp_sock *tp;
bool done = false;
if (!mptcp_subflow_dsn_valid(msk, ssk)) {
*bytes = 0;
return false;
}
tp = tcp_sk(ssk);
do {
u32 map_remaining, offset;
u32 seq = tp->copied_seq;
struct sk_buff *skb;
bool fin;
/* try to move as much data as available */
map_remaining = subflow->map_data_len -
mptcp_subflow_get_map_offset(subflow);
skb = skb_peek(&ssk->sk_receive_queue);
if (!skb)
break;
if (__mptcp_check_fallback(msk)) {
/* if we are running under the workqueue, TCP could have
* collapsed skbs between dummy map creation and now
* be sure to adjust the size
*/
map_remaining = skb->len;
subflow->map_data_len = skb->len;
}
offset = seq - TCP_SKB_CB(skb)->seq;
fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
if (fin) {
done = true;
seq++;
}
if (offset < skb->len) {
size_t len = skb->len - offset;
if (tp->urg_data)
done = true;
__mptcp_move_skb(msk, ssk, skb, offset, len);
seq += len;
moved += len;
if (WARN_ON_ONCE(map_remaining < len))
break;
} else {
WARN_ON_ONCE(!fin);
sk_eat_skb(ssk, skb);
done = true;
}
WRITE_ONCE(tp->copied_seq, seq);
more_data_avail = mptcp_subflow_data_available(ssk);
if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) {
done = true;
break;
}
} while (more_data_avail);
*bytes = moved;
/* If the moves have caught up with the DATA_FIN sequence number
* it's time to ack the DATA_FIN and change socket state, but
* this is not a good place to change state. Let the workqueue
* do it.
*/
if (mptcp_pending_data_fin(sk, NULL) &&
schedule_work(&msk->work))
sock_hold(sk);
return done;
}
/* In most cases we will be able to lock the mptcp socket. If its already
* owned, we need to defer to the work queue to avoid ABBA deadlock.
*/
static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
{
struct sock *sk = (struct sock *)msk;
unsigned int moved = 0;
if (READ_ONCE(sk->sk_lock.owned))
return false;
if (unlikely(!spin_trylock_bh(&sk->sk_lock.slock)))
return false;
/* must re-check after taking the lock */
if (!READ_ONCE(sk->sk_lock.owned))
__mptcp_move_skbs_from_subflow(msk, ssk, &moved);
spin_unlock_bh(&sk->sk_lock.slock);
return moved > 0;
}
void mptcp_data_ready(struct sock *sk, struct sock *ssk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
set_bit(MPTCP_DATA_READY, &msk->flags);
if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) &&
move_skbs_to_msk(msk, ssk))
goto wake;
/* don't schedule if mptcp sk is (still) over limit */
if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf))
goto wake;
/* mptcp socket is owned, release_cb should retry */
if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED,
&sk->sk_tsq_flags)) {
sock_hold(sk);
/* need to try again, its possible release_cb() has already
* been called after the test_and_set_bit() above.
*/
move_skbs_to_msk(msk, ssk);
}
wake:
sk->sk_data_ready(sk);
}
static void __mptcp_flush_join_list(struct mptcp_sock *msk)
{
if (likely(list_empty(&msk->join_list)))
return;
spin_lock_bh(&msk->join_list_lock);
list_splice_tail_init(&msk->join_list, &msk->conn_list);
spin_unlock_bh(&msk->join_list_lock);
}
static bool mptcp_timer_pending(struct sock *sk)
{
return timer_pending(&inet_csk(sk)->icsk_retransmit_timer);
}
static void mptcp_reset_timer(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
unsigned long tout;
/* should never be called with mptcp level timer cleared */
tout = READ_ONCE(mptcp_sk(sk)->timer_ival);
if (WARN_ON_ONCE(!tout))
tout = TCP_RTO_MIN;
sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + tout);
}
void mptcp_data_acked(struct sock *sk)
{
mptcp_reset_timer(sk);
if ((!sk_stream_is_writeable(sk) ||
(inet_sk_state_load(sk) != TCP_ESTABLISHED)) &&
schedule_work(&mptcp_sk(sk)->work))
sock_hold(sk);
}
void mptcp_subflow_eof(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
if (!test_and_set_bit(MPTCP_WORK_EOF, &msk->flags) &&
schedule_work(&msk->work))
sock_hold(sk);
}
static void mptcp_check_for_eof(struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow;
struct sock *sk = (struct sock *)msk;
int receivers = 0;
mptcp_for_each_subflow(msk, subflow)
receivers += !subflow->rx_eof;
if (!receivers && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
/* hopefully temporary hack: propagate shutdown status
* to msk, when all subflows agree on it
*/
sk->sk_shutdown |= RCV_SHUTDOWN;
smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
set_bit(MPTCP_DATA_READY, &msk->flags);
sk->sk_data_ready(sk);
}
}
static bool mptcp_ext_cache_refill(struct mptcp_sock *msk)
{
const struct sock *sk = (const struct sock *)msk;
if (!msk->cached_ext)
msk->cached_ext = __skb_ext_alloc(sk->sk_allocation);
return !!msk->cached_ext;
}
static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow;
struct sock *sk = (struct sock *)msk;
sock_owned_by_me(sk);
mptcp_for_each_subflow(msk, subflow) {
if (subflow->data_avail)
return mptcp_subflow_tcp_sock(subflow);
}
return NULL;
}
static bool mptcp_skb_can_collapse_to(u64 write_seq,
const struct sk_buff *skb,
const struct mptcp_ext *mpext)
{
if (!tcp_skb_can_collapse_to(skb))
return false;
/* can collapse only if MPTCP level sequence is in order */
return mpext && mpext->data_seq + mpext->data_len == write_seq;
}
static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
const struct page_frag *pfrag,
const struct mptcp_data_frag *df)
{
return df && pfrag->page == df->page &&
df->data_seq + df->data_len == msk->write_seq;
}
static void dfrag_uncharge(struct sock *sk, int len)
{
sk_mem_uncharge(sk, len);
sk_wmem_queued_add(sk, -len);
}
static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag)
{
int len = dfrag->data_len + dfrag->overhead;
list_del(&dfrag->list);
dfrag_uncharge(sk, len);
put_page(dfrag->page);
}
static void mptcp_clean_una(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
struct mptcp_data_frag *dtmp, *dfrag;
bool cleaned = false;
u64 snd_una;
/* on fallback we just need to ignore snd_una, as this is really
* plain TCP
*/
if (__mptcp_check_fallback(msk))
atomic64_set(&msk->snd_una, msk->write_seq);
snd_una = atomic64_read(&msk->snd_una);
list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) {
if (after64(dfrag->data_seq + dfrag->data_len, snd_una))
break;
dfrag_clear(sk, dfrag);
cleaned = true;
}
dfrag = mptcp_rtx_head(sk);
if (dfrag && after64(snd_una, dfrag->data_seq)) {
u64 delta = snd_una - dfrag->data_seq;
if (WARN_ON_ONCE(delta > dfrag->data_len))
goto out;
dfrag->data_seq += delta;
dfrag->offset += delta;
dfrag->data_len -= delta;
dfrag_uncharge(sk, delta);
cleaned = true;
}
out:
if (cleaned) {
sk_mem_reclaim_partial(sk);
/* Only wake up writers if a subflow is ready */
if (test_bit(MPTCP_SEND_SPACE, &msk->flags))
sk_stream_write_space(sk);
}
}
/* ensure we get enough memory for the frag hdr, beyond some minimal amount of
* data
*/
static bool mptcp_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
{
if (likely(skb_page_frag_refill(32U + sizeof(struct mptcp_data_frag),
pfrag, sk->sk_allocation)))
return true;
sk->sk_prot->enter_memory_pressure(sk);
sk_stream_moderate_sndbuf(sk);
return false;
}
static struct mptcp_data_frag *
mptcp_carve_data_frag(const struct mptcp_sock *msk, struct page_frag *pfrag,
int orig_offset)
{
int offset = ALIGN(orig_offset, sizeof(long));
struct mptcp_data_frag *dfrag;
dfrag = (struct mptcp_data_frag *)(page_to_virt(pfrag->page) + offset);
dfrag->data_len = 0;
dfrag->data_seq = msk->write_seq;
dfrag->overhead = offset - orig_offset + sizeof(struct mptcp_data_frag);
dfrag->offset = offset + sizeof(struct mptcp_data_frag);
dfrag->page = pfrag->page;
return dfrag;
}
static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
struct msghdr *msg, struct mptcp_data_frag *dfrag,
long *timeo, int *pmss_now,
int *ps_goal)
{
int mss_now, avail_size, size_goal, offset, ret, frag_truesize = 0;
bool dfrag_collapsed, can_collapse = false;
struct mptcp_sock *msk = mptcp_sk(sk);
struct mptcp_ext *mpext = NULL;
bool retransmission = !!dfrag;
struct sk_buff *skb, *tail;
struct page_frag *pfrag;
struct page *page;
u64 *write_seq;
size_t psize;
/* use the mptcp page cache so that we can easily move the data
* from one substream to another, but do per subflow memory accounting
* Note: pfrag is used only !retransmission, but the compiler if
* fooled into a warning if we don't init here
*/
pfrag = sk_page_frag(sk);
if (!retransmission) {
write_seq = &msk->write_seq;
page = pfrag->page;
} else {
write_seq = &dfrag->data_seq;
page = dfrag->page;
}
/* compute copy limit */
mss_now = tcp_send_mss(ssk, &size_goal, msg->msg_flags);
*pmss_now = mss_now;
*ps_goal = size_goal;
avail_size = size_goal;
skb = tcp_write_queue_tail(ssk);
if (skb) {
mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
/* Limit the write to the size available in the
* current skb, if any, so that we create at most a new skb.
* Explicitly tells TCP internals to avoid collapsing on later
* queue management operation, to avoid breaking the ext <->
* SSN association set here
*/
can_collapse = (size_goal - skb->len > 0) &&
mptcp_skb_can_collapse_to(*write_seq, skb, mpext);
if (!can_collapse)
TCP_SKB_CB(skb)->eor = 1;
else
avail_size = size_goal - skb->len;
}
if (!retransmission) {
/* reuse tail pfrag, if possible, or carve a new one from the
* page allocator
*/
dfrag = mptcp_rtx_tail(sk);
offset = pfrag->offset;
dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
if (!dfrag_collapsed) {
dfrag = mptcp_carve_data_frag(msk, pfrag, offset);
offset = dfrag->offset;
frag_truesize = dfrag->overhead;
}
psize = min_t(size_t, pfrag->size - offset, avail_size);
/* Copy to page */
pr_debug("left=%zu", msg_data_left(msg));
psize = copy_page_from_iter(pfrag->page, offset,
min_t(size_t, msg_data_left(msg),
psize),
&msg->msg_iter);
pr_debug("left=%zu", msg_data_left(msg));
if (!psize)
return -EINVAL;
if (!sk_wmem_schedule(sk, psize + dfrag->overhead)) {
iov_iter_revert(&msg->msg_iter, psize);
return -ENOMEM;
}
} else {
offset = dfrag->offset;
psize = min_t(size_t, dfrag->data_len, avail_size);
}
/* tell the TCP stack to delay the push so that we can safely
* access the skb after the sendpages call
*/
ret = do_tcp_sendpages(ssk, page, offset, psize,
msg->msg_flags | MSG_SENDPAGE_NOTLAST | MSG_DONTWAIT);
if (ret <= 0) {
if (!retransmission)
iov_iter_revert(&msg->msg_iter, psize);
return ret;
}
frag_truesize += ret;
if (!retransmission) {
if (unlikely(ret < psize))
iov_iter_revert(&msg->msg_iter, psize - ret);
/* send successful, keep track of sent data for mptcp-level
* retransmission
*/
dfrag->data_len += ret;
if (!dfrag_collapsed) {
get_page(dfrag->page);
list_add_tail(&dfrag->list, &msk->rtx_queue);
sk_wmem_queued_add(sk, frag_truesize);
} else {
sk_wmem_queued_add(sk, ret);
}
/* charge data on mptcp rtx queue to the master socket
* Note: we charge such data both to sk and ssk
*/
sk->sk_forward_alloc -= frag_truesize;
}
/* if the tail skb extension is still the cached one, collapsing
* really happened. Note: we can't check for 'same skb' as the sk_buff
* hdr on tail can be transmitted, freed and re-allocated by the
* do_tcp_sendpages() call
*/
tail = tcp_write_queue_tail(ssk);
if (mpext && tail && mpext == skb_ext_find(tail, SKB_EXT_MPTCP)) {
WARN_ON_ONCE(!can_collapse);
mpext->data_len += ret;
goto out;
}
skb = tcp_write_queue_tail(ssk);
mpext = __skb_ext_set(skb, SKB_EXT_MPTCP, msk->cached_ext);
msk->cached_ext = NULL;
memset(mpext, 0, sizeof(*mpext));
mpext->data_seq = *write_seq;
mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq;
mpext->data_len = ret;
mpext->use_map = 1;
mpext->dsn64 = 1;
pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d",
mpext->data_seq, mpext->subflow_seq, mpext->data_len,
mpext->dsn64);
out:
if (!retransmission)
pfrag->offset += frag_truesize;
WRITE_ONCE(*write_seq, *write_seq + ret);
mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
return ret;
}
static void mptcp_nospace(struct mptcp_sock *msk, struct socket *sock)
{
clear_bit(MPTCP_SEND_SPACE, &msk->flags);
smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */
/* enables sk->write_space() callbacks */
set_bit(SOCK_NOSPACE, &sock->flags);
}
static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow;
struct sock *backup = NULL;
sock_owned_by_me((const struct sock *)msk);
if (!mptcp_ext_cache_refill(msk))
return NULL;
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
if (!sk_stream_memory_free(ssk)) {
struct socket *sock = ssk->sk_socket;
if (sock)
mptcp_nospace(msk, sock);
return NULL;
}
if (subflow->backup) {
if (!backup)
backup = ssk;
continue;
}
return ssk;
}
return backup;
}
static void ssk_check_wmem(struct mptcp_sock *msk, struct sock *ssk)
{
struct socket *sock;
if (likely(sk_stream_is_writeable(ssk)))
return;
sock = READ_ONCE(ssk->sk_socket);
if (sock)
mptcp_nospace(msk, sock);
}
static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
int mss_now = 0, size_goal = 0, ret = 0;
struct mptcp_sock *msk = mptcp_sk(sk);
struct page_frag *pfrag;
size_t copied = 0;
struct sock *ssk;
bool tx_ok;
long timeo;
if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
return -EOPNOTSUPP;
lock_sock(sk);
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
ret = sk_stream_wait_connect(sk, &timeo);
if (ret)
goto out;
}
pfrag = sk_page_frag(sk);
restart:
mptcp_clean_una(sk);
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) {
ret = -EPIPE;
goto out;
}
__mptcp_flush_join_list(msk);
ssk = mptcp_subflow_get_send(msk);
while (!sk_stream_memory_free(sk) ||
!ssk ||
!mptcp_page_frag_refill(ssk, pfrag)) {
if (ssk) {
/* make sure retransmit timer is
* running before we wait for memory.
*
* The retransmit timer might be needed
* to make the peer send an up-to-date
* MPTCP Ack.
*/
mptcp_set_timeout(sk, ssk);
if (!mptcp_timer_pending(sk))
mptcp_reset_timer(sk);
}
ret = sk_stream_wait_memory(sk, &timeo);
if (ret)
goto out;
mptcp_clean_una(sk);
ssk = mptcp_subflow_get_send(msk);
if (list_empty(&msk->conn_list)) {
ret = -ENOTCONN;
goto out;
}
}
pr_debug("conn_list->subflow=%p", ssk);
lock_sock(ssk);
tx_ok = msg_data_left(msg);
while (tx_ok) {
ret = mptcp_sendmsg_frag(sk, ssk, msg, NULL, &timeo, &mss_now,
&size_goal);
if (ret < 0) {
if (ret == -EAGAIN && timeo > 0) {
mptcp_set_timeout(sk, ssk);
release_sock(ssk);
goto restart;
}
break;
}
copied += ret;
tx_ok = msg_data_left(msg);
if (!tx_ok)
break;
if (!sk_stream_memory_free(ssk) ||
!mptcp_page_frag_refill(ssk, pfrag) ||
!mptcp_ext_cache_refill(msk)) {
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
tcp_push(ssk, msg->msg_flags, mss_now,
tcp_sk(ssk)->nonagle, size_goal);
mptcp_set_timeout(sk, ssk);
release_sock(ssk);
goto restart;
}
/* memory is charged to mptcp level socket as well, i.e.
* if msg is very large, mptcp socket may run out of buffer
* space. mptcp_clean_una() will release data that has
* been acked at mptcp level in the mean time, so there is
* a good chance we can continue sending data right away.
*
* Normally, when the tcp subflow can accept more data, then
* so can the MPTCP socket. However, we need to cope with
* peers that might lag behind in their MPTCP-level
* acknowledgements, i.e. data might have been acked at
* tcp level only. So, we must also check the MPTCP socket
* limits before we send more data.
*/
if (unlikely(!sk_stream_memory_free(sk))) {
tcp_push(ssk, msg->msg_flags, mss_now,
tcp_sk(ssk)->nonagle, size_goal);
mptcp_clean_una(sk);
if (!sk_stream_memory_free(sk)) {
/* can't send more for now, need to wait for
* MPTCP-level ACKs from peer.
*
* Wakeup will happen via mptcp_clean_una().
*/
mptcp_set_timeout(sk, ssk);
release_sock(ssk);
goto restart;
}
}
}
mptcp_set_timeout(sk, ssk);
if (copied) {
tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle,
size_goal);
/* start the timer, if it's not pending */
if (!mptcp_timer_pending(sk))
mptcp_reset_timer(sk);
}
ssk_check_wmem(msk, ssk);
release_sock(ssk);