forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
protocol.c
3489 lines (2878 loc) · 86.1 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 <net/xfrm.h>
#include "protocol.h"
#include "mib.h"
#define CREATE_TRACE_POINTS
#include <trace/events/mptcp.h>
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
struct mptcp6_sock {
struct mptcp_sock msk;
struct ipv6_pinfo np;
};
#endif
struct mptcp_skb_cb {
u64 map_seq;
u64 end_seq;
u32 offset;
u8 has_rxtstamp:1;
};
#define MPTCP_SKB_CB(__skb) ((struct mptcp_skb_cb *)&((__skb)->cb[0]))
enum {
MPTCP_CMSG_TS = BIT(0),
};
static struct percpu_counter mptcp_sockets_allocated;
static void __mptcp_destroy_sock(struct sock *sk);
static void __mptcp_check_send_data_fin(struct sock *sk);
DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
static struct net_device mptcp_napi_dev;
/* 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.
*/
struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk)
{
if (!msk->subflow || READ_ONCE(msk->can_ack))
return NULL;
return msk->subflow;
}
/* Returns end sequence number of the receiver's advertised window */
static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
{
return READ_ONCE(msk->wnd_end);
}
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 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);
sock_hold(ssock->sk);
subflow->request_mptcp = 1;
mptcp_sock_graft(msk->first, sk->sk_socket);
return 0;
}
static void mptcp_drop(struct sock *sk, struct sk_buff *skb)
{
sk_drops_add(sk, skb);
__kfree_skb(skb);
}
static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
struct sk_buff *from)
{
bool fragstolen;
int delta;
if (MPTCP_SKB_CB(from)->offset ||
!skb_try_coalesce(to, from, &fragstolen, &delta))
return false;
pr_debug("colesced seq %llx into %llx new len %d new end seq %llx",
MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq,
to->len, MPTCP_SKB_CB(from)->end_seq);
MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq;
kfree_skb_partial(from, fragstolen);
atomic_add(delta, &sk->sk_rmem_alloc);
sk_mem_charge(sk, delta);
return true;
}
static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to,
struct sk_buff *from)
{
if (MPTCP_SKB_CB(from)->map_seq != MPTCP_SKB_CB(to)->end_seq)
return false;
return mptcp_try_coalesce((struct sock *)msk, to, from);
}
/* "inspired" by tcp_data_queue_ofo(), main differences:
* - use mptcp seqs
* - don't cope with sacks
*/
static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
{
struct sock *sk = (struct sock *)msk;
struct rb_node **p, *parent;
u64 seq, end_seq, max_seq;
struct sk_buff *skb1;
seq = MPTCP_SKB_CB(skb)->map_seq;
end_seq = MPTCP_SKB_CB(skb)->end_seq;
max_seq = READ_ONCE(msk->rcv_wnd_sent);
pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq,
RB_EMPTY_ROOT(&msk->out_of_order_queue));
if (after64(end_seq, max_seq)) {
/* out of window */
mptcp_drop(sk, skb);
pr_debug("oow by %lld, rcv_wnd_sent %llu\n",
(unsigned long long)end_seq - (unsigned long)max_seq,
(unsigned long long)msk->rcv_wnd_sent);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_NODSSWINDOW);
return;
}
p = &msk->out_of_order_queue.rb_node;
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUE);
if (RB_EMPTY_ROOT(&msk->out_of_order_queue)) {
rb_link_node(&skb->rbnode, NULL, p);
rb_insert_color(&skb->rbnode, &msk->out_of_order_queue);
msk->ooo_last_skb = skb;
goto end;
}
/* with 2 subflows, adding at end of ooo queue is quite likely
* Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
*/
if (mptcp_ooo_try_coalesce(msk, msk->ooo_last_skb, skb)) {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL);
return;
}
/* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */
if (!before64(seq, MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq)) {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL);
parent = &msk->ooo_last_skb->rbnode;
p = &parent->rb_right;
goto insert;
}
/* Find place to insert this segment. Handle overlaps on the way. */
parent = NULL;
while (*p) {
parent = *p;
skb1 = rb_to_skb(parent);
if (before64(seq, MPTCP_SKB_CB(skb1)->map_seq)) {
p = &parent->rb_left;
continue;
}
if (before64(seq, MPTCP_SKB_CB(skb1)->end_seq)) {
if (!after64(end_seq, MPTCP_SKB_CB(skb1)->end_seq)) {
/* All the bits are present. Drop. */
mptcp_drop(sk, skb);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
return;
}
if (after64(seq, MPTCP_SKB_CB(skb1)->map_seq)) {
/* partial overlap:
* | skb |
* | skb1 |
* continue traversing
*/
} else {
/* skb's seq == skb1's seq and skb covers skb1.
* Replace skb1 with skb.
*/
rb_replace_node(&skb1->rbnode, &skb->rbnode,
&msk->out_of_order_queue);
mptcp_drop(sk, skb1);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
goto merge_right;
}
} else if (mptcp_ooo_try_coalesce(msk, skb1, skb)) {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE);
return;
}
p = &parent->rb_right;
}
insert:
/* Insert segment into RB tree. */
rb_link_node(&skb->rbnode, parent, p);
rb_insert_color(&skb->rbnode, &msk->out_of_order_queue);
merge_right:
/* Remove other segments covered by skb. */
while ((skb1 = skb_rb_next(skb)) != NULL) {
if (before64(end_seq, MPTCP_SKB_CB(skb1)->end_seq))
break;
rb_erase(&skb1->rbnode, &msk->out_of_order_queue);
mptcp_drop(sk, skb1);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
}
/* If there is no skb after us, we are the last_skb ! */
if (!skb1)
msk->ooo_last_skb = skb;
end:
skb_condense(skb);
skb_set_owner_r(skb, sk);
}
static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
struct sk_buff *skb, unsigned int offset,
size_t copy_len)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct sock *sk = (struct sock *)msk;
struct sk_buff *tail;
bool has_rxtstamp;
__skb_unlink(skb, &ssk->sk_receive_queue);
skb_ext_reset(skb);
skb_orphan(skb);
/* try to fetch required memory from subflow */
if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
int amount = sk_mem_pages(skb->truesize) << SK_MEM_QUANTUM_SHIFT;
if (ssk->sk_forward_alloc < amount)
goto drop;
ssk->sk_forward_alloc -= amount;
sk->sk_forward_alloc += amount;
}
has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
/* the skb map_seq accounts for the skb offset:
* mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq
* value
*/
MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow);
MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len;
MPTCP_SKB_CB(skb)->offset = offset;
MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp;
if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) {
/* in sequence */
WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len);
tail = skb_peek_tail(&sk->sk_receive_queue);
if (tail && mptcp_try_coalesce(sk, tail, skb))
return true;
skb_set_owner_r(skb, sk);
__skb_queue_tail(&sk->sk_receive_queue, skb);
return true;
} else if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) {
mptcp_data_queue_ofo(msk, skb);
return false;
}
/* old data, keep it simple and drop the whole pkt, sender
* will retransmit as needed, if needed.
*/
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
drop:
mptcp_drop(sk, skb);
return false;
}
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;
}
static void mptcp_close_wake_up(struct sock *sk)
{
if (sock_flag(sk, SOCK_DEAD))
return;
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_pending_data_fin_ack(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
return !__mptcp_check_fallback(msk) &&
((1 << sk->sk_state) &
(TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) &&
msk->write_seq == READ_ONCE(msk->snd_una);
}
static void mptcp_check_data_fin_ack(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
/* Look for an acknowledged DATA_FIN */
if (mptcp_pending_data_fin_ack(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);
break;
case TCP_CLOSING:
case TCP_LAST_ACK:
inet_sk_state_store(sk, TCP_CLOSE);
break;
}
mptcp_close_wake_up(sk);
}
}
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_datafin_timeout(const struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
mptcp_sk(sk)->timer_ival = min(TCP_RTO_MAX,
TCP_RTO_MIN << icsk->icsk_retransmits);
}
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 bool tcp_can_send_ack(const struct sock *ssk)
{
return !((1 << inet_sk_state_load(ssk)) &
(TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN));
}
static void mptcp_send_ack(struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow;
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
bool slow;
slow = lock_sock_fast(ssk);
if (tcp_can_send_ack(ssk))
tcp_send_ack(ssk);
unlock_sock_fast(ssk, slow);
}
}
static void mptcp_subflow_cleanup_rbuf(struct sock *ssk)
{
bool slow;
slow = lock_sock_fast(ssk);
if (tcp_can_send_ack(ssk))
tcp_cleanup_rbuf(ssk, 1);
unlock_sock_fast(ssk, slow);
}
static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty)
{
const struct inet_connection_sock *icsk = inet_csk(ssk);
u8 ack_pending = READ_ONCE(icsk->icsk_ack.pending);
const struct tcp_sock *tp = tcp_sk(ssk);
return (ack_pending & ICSK_ACK_SCHED) &&
((READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->rcv_wup) >
READ_ONCE(icsk->icsk_ack.rcv_mss)) ||
(rx_empty && ack_pending &
(ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED)));
}
static void mptcp_cleanup_rbuf(struct mptcp_sock *msk)
{
int old_space = READ_ONCE(msk->old_wspace);
struct mptcp_subflow_context *subflow;
struct sock *sk = (struct sock *)msk;
int space = __mptcp_space(sk);
bool cleanup, rx_empty;
cleanup = (space > 0) && (space >= (old_space << 1));
rx_empty = !__mptcp_rmem(sk);
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty))
mptcp_subflow_cleanup_rbuf(ssk);
}
}
static bool mptcp_check_data_fin(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
u64 rcv_data_fin_seq;
bool ret = false;
if (__mptcp_check_fallback(msk))
return ret;
/* 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)) {
WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1);
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);
break;
default:
/* Other states not expected */
WARN_ON_ONCE(1);
break;
}
ret = true;
mptcp_set_timeout(sk, NULL);
mptcp_send_ack(msk);
mptcp_close_wake_up(sk);
}
return ret;
}
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;
int sk_rbuf;
sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
if (unlikely(ssk_rbuf > sk_rbuf)) {
WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf);
sk_rbuf = ssk_rbuf;
}
}
pr_debug("msk=%p ssk=%p", msk, ssk);
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) {
/* if no data is found, a racing workqueue/recvmsg
* already processed the new data, stop here or we
* can enter an infinite loop
*/
if (!moved)
done = true;
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;
if (__mptcp_move_skb(msk, ssk, skb, offset, len))
moved += len;
seq += 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) > sk_rbuf) {
done = true;
break;
}
} while (more_data_avail);
*bytes += moved;
return done;
}
static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
{
struct sock *sk = (struct sock *)msk;
struct sk_buff *skb, *tail;
bool moved = false;
struct rb_node *p;
u64 end_seq;
p = rb_first(&msk->out_of_order_queue);
pr_debug("msk=%p empty=%d", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue));
while (p) {
skb = rb_to_skb(p);
if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq))
break;
p = rb_next(p);
rb_erase(&skb->rbnode, &msk->out_of_order_queue);
if (unlikely(!after64(MPTCP_SKB_CB(skb)->end_seq,
msk->ack_seq))) {
mptcp_drop(sk, skb);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
continue;
}
end_seq = MPTCP_SKB_CB(skb)->end_seq;
tail = skb_peek_tail(&sk->sk_receive_queue);
if (!tail || !mptcp_ooo_try_coalesce(msk, tail, skb)) {
int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;
/* skip overlapping data, if any */
pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d",
MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq,
delta);
MPTCP_SKB_CB(skb)->offset += delta;
__skb_queue_tail(&sk->sk_receive_queue, skb);
}
msk->ack_seq = end_seq;
moved = true;
}
return moved;
}
/* 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;
__mptcp_move_skbs_from_subflow(msk, ssk, &moved);
__mptcp_ofo_queue(msk);
if (unlikely(ssk->sk_err)) {
if (!sock_owned_by_user(sk))
__mptcp_error_report(sk);
else
set_bit(MPTCP_ERROR_REPORT, &msk->flags);
}
/* 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))
mptcp_schedule_work(sk);
return moved > 0;
}
void mptcp_data_ready(struct sock *sk, struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct mptcp_sock *msk = mptcp_sk(sk);
int sk_rbuf, ssk_rbuf;
/* The peer can send data while we are shutting down this
* subflow at msk destruction time, but we must avoid enqueuing
* more data to the msk receive queue
*/
if (unlikely(subflow->disposable))
return;
ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
if (unlikely(ssk_rbuf > sk_rbuf))
sk_rbuf = ssk_rbuf;
/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
if (__mptcp_rmem(sk) > sk_rbuf) {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
return;
}
/* Wake-up the reader only for in-sequence data */
mptcp_data_lock(sk);
if (move_skbs_to_msk(msk, ssk)) {
set_bit(MPTCP_DATA_READY, &msk->flags);
sk->sk_data_ready(sk);
}
mptcp_data_unlock(sk);
}
static bool mptcp_do_flush_join_list(struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow;
bool ret = false;
if (likely(list_empty(&msk->join_list)))
return false;
spin_lock_bh(&msk->join_list_lock);
list_for_each_entry(subflow, &msk->join_list, node) {
u32 sseq = READ_ONCE(subflow->setsockopt_seq);
mptcp_propagate_sndbuf((struct sock *)msk, mptcp_subflow_tcp_sock(subflow));
if (READ_ONCE(msk->setsockopt_seq) != sseq)
ret = true;
}
list_splice_tail_init(&msk->join_list, &msk->conn_list);
spin_unlock_bh(&msk->join_list_lock);
return ret;
}
void __mptcp_flush_join_list(struct mptcp_sock *msk)
{
if (likely(!mptcp_do_flush_join_list(msk)))
return;
if (!test_and_set_bit(MPTCP_WORK_SYNC_SETSOCKOPT, &msk->flags))
mptcp_schedule_work((struct sock *)msk);
}
static void mptcp_flush_join_list(struct mptcp_sock *msk)
{
bool sync_needed = test_and_clear_bit(MPTCP_WORK_SYNC_SETSOCKOPT, &msk->flags);
might_sleep();
if (!mptcp_do_flush_join_list(msk) && !sync_needed)
return;
mptcp_sockopt_sync_all(msk);
}
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;
/* prevent rescheduling on close */
if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE))
return;
/* 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);
}
bool mptcp_schedule_work(struct sock *sk)
{
if (inet_sk_state_load(sk) != TCP_CLOSE &&
schedule_work(&mptcp_sk(sk)->work)) {
/* each subflow already holds a reference to the sk, and the
* workqueue is invoked by a subflow, so sk can't go away here.
*/
sock_hold(sk);
return true;
}
return false;
}
void mptcp_subflow_eof(struct sock *sk)
{
if (!test_and_set_bit(MPTCP_WORK_EOF, &mptcp_sk(sk)->flags))
mptcp_schedule_work(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)
return;
if (!(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);
}
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);
break;
default:
return;
}
mptcp_close_wake_up(sk);
}
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 (READ_ONCE(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 and this
* mapping has not been xmitted yet
*/
return mpext && mpext->data_seq + mpext->data_len == write_seq &&
!mpext->frozen;
}
/* we can append data to the given data frag if:
* - there is space available in the backing page_frag
* - the data frag tail matches the current page_frag free offset
* - the data frag end sequence number matches the current 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 &&
pfrag->size - pfrag->offset > 0 &&
pfrag->offset == (df->offset + df->data_len) &&
df->data_seq + df->data_len == msk->write_seq;
}
static int mptcp_wmem_with_overhead(int size)
{
return size + ((sizeof(struct mptcp_data_frag) * size) >> PAGE_SHIFT);
}
static void __mptcp_wmem_reserve(struct sock *sk, int size)
{
int amount = mptcp_wmem_with_overhead(size);
struct mptcp_sock *msk = mptcp_sk(sk);
WARN_ON_ONCE(msk->wmem_reserved);
if (WARN_ON_ONCE(amount < 0))
amount = 0;
if (amount <= sk->sk_forward_alloc)
goto reserve;
/* under memory pressure try to reserve at most a single page
* otherwise try to reserve the full estimate and fallback
* to a single page before entering the error path
*/
if ((tcp_under_memory_pressure(sk) && amount > PAGE_SIZE) ||
!sk_wmem_schedule(sk, amount)) {
if (amount <= PAGE_SIZE)
goto nomem;
amount = PAGE_SIZE;
if (!sk_wmem_schedule(sk, amount))
goto nomem;
}
reserve:
msk->wmem_reserved = amount;
sk->sk_forward_alloc -= amount;
return;
nomem:
/* we will wait for memory on next allocation */
msk->wmem_reserved = -1;
}
static void __mptcp_update_wmem(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
#ifdef CONFIG_LOCKDEP
WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock));
#endif
if (!msk->wmem_reserved)
return;
if (msk->wmem_reserved < 0)
msk->wmem_reserved = 0;
if (msk->wmem_reserved > 0) {
sk->sk_forward_alloc += msk->wmem_reserved;
msk->wmem_reserved = 0;
}
}
static bool mptcp_wmem_alloc(struct sock *sk, int size)
{
struct mptcp_sock *msk = mptcp_sk(sk);
/* check for pre-existing error condition */
if (msk->wmem_reserved < 0)
return false;
if (msk->wmem_reserved >= size)
goto account;
mptcp_data_lock(sk);
if (!sk_wmem_schedule(sk, size)) {
mptcp_data_unlock(sk);
return false;
}
sk->sk_forward_alloc -= size;
msk->wmem_reserved += size;
mptcp_data_unlock(sk);
account:
msk->wmem_reserved -= size;
return true;
}
static void mptcp_wmem_uncharge(struct sock *sk, int size)
{
struct mptcp_sock *msk = mptcp_sk(sk);
if (msk->wmem_reserved < 0)
msk->wmem_reserved = 0;
msk->wmem_reserved += size;
}
static void mptcp_mem_reclaim_partial(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);