forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathinput.c
1502 lines (1302 loc) · 39.1 KB
/
input.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0-or-later
/* RxRPC packet reception
*
* Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved.
* Written by David Howells ([email protected])
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/errqueue.h>
#include <linux/udp.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/icmp.h>
#include <linux/gfp.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include <net/ip.h>
#include <net/udp.h>
#include <net/net_namespace.h>
#include "ar-internal.h"
static void rxrpc_proto_abort(const char *why,
struct rxrpc_call *call, rxrpc_seq_t seq)
{
if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG)) {
set_bit(RXRPC_CALL_EV_ABORT, &call->events);
rxrpc_queue_call(call);
}
}
/*
* Do TCP-style congestion management [RFC 5681].
*/
static void rxrpc_congestion_management(struct rxrpc_call *call,
struct sk_buff *skb,
struct rxrpc_ack_summary *summary,
rxrpc_serial_t acked_serial)
{
enum rxrpc_congest_change change = rxrpc_cong_no_change;
unsigned int cumulative_acks = call->cong_cumul_acks;
unsigned int cwnd = call->cong_cwnd;
bool resend = false;
summary->flight_size =
(call->tx_top - call->tx_hard_ack) - summary->nr_acks;
if (test_and_clear_bit(RXRPC_CALL_RETRANS_TIMEOUT, &call->flags)) {
summary->retrans_timeo = true;
call->cong_ssthresh = max_t(unsigned int,
summary->flight_size / 2, 2);
cwnd = 1;
if (cwnd >= call->cong_ssthresh &&
call->cong_mode == RXRPC_CALL_SLOW_START) {
call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
call->cong_tstamp = skb->tstamp;
cumulative_acks = 0;
}
}
cumulative_acks += summary->nr_new_acks;
cumulative_acks += summary->nr_rot_new_acks;
if (cumulative_acks > 255)
cumulative_acks = 255;
summary->mode = call->cong_mode;
summary->cwnd = call->cong_cwnd;
summary->ssthresh = call->cong_ssthresh;
summary->cumulative_acks = cumulative_acks;
summary->dup_acks = call->cong_dup_acks;
switch (call->cong_mode) {
case RXRPC_CALL_SLOW_START:
if (summary->nr_nacks > 0)
goto packet_loss_detected;
if (summary->cumulative_acks > 0)
cwnd += 1;
if (cwnd >= call->cong_ssthresh) {
call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
call->cong_tstamp = skb->tstamp;
}
goto out;
case RXRPC_CALL_CONGEST_AVOIDANCE:
if (summary->nr_nacks > 0)
goto packet_loss_detected;
/* We analyse the number of packets that get ACK'd per RTT
* period and increase the window if we managed to fill it.
*/
if (call->peer->rtt_count == 0)
goto out;
if (ktime_before(skb->tstamp,
ktime_add_us(call->cong_tstamp,
call->peer->srtt_us >> 3)))
goto out_no_clear_ca;
change = rxrpc_cong_rtt_window_end;
call->cong_tstamp = skb->tstamp;
if (cumulative_acks >= cwnd)
cwnd++;
goto out;
case RXRPC_CALL_PACKET_LOSS:
if (summary->nr_nacks == 0)
goto resume_normality;
if (summary->new_low_nack) {
change = rxrpc_cong_new_low_nack;
call->cong_dup_acks = 1;
if (call->cong_extra > 1)
call->cong_extra = 1;
goto send_extra_data;
}
call->cong_dup_acks++;
if (call->cong_dup_acks < 3)
goto send_extra_data;
change = rxrpc_cong_begin_retransmission;
call->cong_mode = RXRPC_CALL_FAST_RETRANSMIT;
call->cong_ssthresh = max_t(unsigned int,
summary->flight_size / 2, 2);
cwnd = call->cong_ssthresh + 3;
call->cong_extra = 0;
call->cong_dup_acks = 0;
resend = true;
goto out;
case RXRPC_CALL_FAST_RETRANSMIT:
if (!summary->new_low_nack) {
if (summary->nr_new_acks == 0)
cwnd += 1;
call->cong_dup_acks++;
if (call->cong_dup_acks == 2) {
change = rxrpc_cong_retransmit_again;
call->cong_dup_acks = 0;
resend = true;
}
} else {
change = rxrpc_cong_progress;
cwnd = call->cong_ssthresh;
if (summary->nr_nacks == 0)
goto resume_normality;
}
goto out;
default:
BUG();
goto out;
}
resume_normality:
change = rxrpc_cong_cleared_nacks;
call->cong_dup_acks = 0;
call->cong_extra = 0;
call->cong_tstamp = skb->tstamp;
if (cwnd < call->cong_ssthresh)
call->cong_mode = RXRPC_CALL_SLOW_START;
else
call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
out:
cumulative_acks = 0;
out_no_clear_ca:
if (cwnd >= RXRPC_RXTX_BUFF_SIZE - 1)
cwnd = RXRPC_RXTX_BUFF_SIZE - 1;
call->cong_cwnd = cwnd;
call->cong_cumul_acks = cumulative_acks;
trace_rxrpc_congest(call, summary, acked_serial, change);
if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events))
rxrpc_queue_call(call);
return;
packet_loss_detected:
change = rxrpc_cong_saw_nack;
call->cong_mode = RXRPC_CALL_PACKET_LOSS;
call->cong_dup_acks = 0;
goto send_extra_data;
send_extra_data:
/* Send some previously unsent DATA if we have some to advance the ACK
* state.
*/
if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] &
RXRPC_TX_ANNO_LAST ||
summary->nr_acks != call->tx_top - call->tx_hard_ack) {
call->cong_extra++;
wake_up(&call->waitq);
}
goto out_no_clear_ca;
}
/*
* Apply a hard ACK by advancing the Tx window.
*/
static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
struct rxrpc_ack_summary *summary)
{
struct sk_buff *skb, *list = NULL;
bool rot_last = false;
int ix;
u8 annotation;
if (call->acks_lowest_nak == call->tx_hard_ack) {
call->acks_lowest_nak = to;
} else if (before_eq(call->acks_lowest_nak, to)) {
summary->new_low_nack = true;
call->acks_lowest_nak = to;
}
spin_lock(&call->lock);
while (before(call->tx_hard_ack, to)) {
call->tx_hard_ack++;
ix = call->tx_hard_ack & RXRPC_RXTX_BUFF_MASK;
skb = call->rxtx_buffer[ix];
annotation = call->rxtx_annotations[ix];
rxrpc_see_skb(skb, rxrpc_skb_rotated);
call->rxtx_buffer[ix] = NULL;
call->rxtx_annotations[ix] = 0;
skb->next = list;
list = skb;
if (annotation & RXRPC_TX_ANNO_LAST) {
set_bit(RXRPC_CALL_TX_LAST, &call->flags);
rot_last = true;
}
if ((annotation & RXRPC_TX_ANNO_MASK) != RXRPC_TX_ANNO_ACK)
summary->nr_rot_new_acks++;
}
spin_unlock(&call->lock);
trace_rxrpc_transmit(call, (rot_last ?
rxrpc_transmit_rotate_last :
rxrpc_transmit_rotate));
wake_up(&call->waitq);
while (list) {
skb = list;
list = skb->next;
skb_mark_not_on_list(skb);
rxrpc_free_skb(skb, rxrpc_skb_freed);
}
return rot_last;
}
/*
* End the transmission phase of a call.
*
* This occurs when we get an ACKALL packet, the first DATA packet of a reply,
* or a final ACK packet.
*/
static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
const char *abort_why)
{
unsigned int state;
ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags));
write_lock(&call->state_lock);
state = call->state;
switch (state) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_CLIENT_AWAIT_REPLY:
if (reply_begun)
call->state = state = RXRPC_CALL_CLIENT_RECV_REPLY;
else
call->state = state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
break;
case RXRPC_CALL_SERVER_AWAIT_ACK:
__rxrpc_call_completed(call);
state = call->state;
break;
default:
goto bad_state;
}
write_unlock(&call->state_lock);
if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY)
trace_rxrpc_transmit(call, rxrpc_transmit_await_reply);
else
trace_rxrpc_transmit(call, rxrpc_transmit_end);
_leave(" = ok");
return true;
bad_state:
write_unlock(&call->state_lock);
kdebug("end_tx %s", rxrpc_call_states[call->state]);
rxrpc_proto_abort(abort_why, call, call->tx_top);
return false;
}
/*
* Begin the reply reception phase of a call.
*/
static bool rxrpc_receiving_reply(struct rxrpc_call *call)
{
struct rxrpc_ack_summary summary = { 0 };
unsigned long now, timo;
rxrpc_seq_t top = READ_ONCE(call->tx_top);
if (call->ackr_reason) {
spin_lock_bh(&call->lock);
call->ackr_reason = 0;
spin_unlock_bh(&call->lock);
now = jiffies;
timo = now + MAX_JIFFY_OFFSET;
WRITE_ONCE(call->resend_at, timo);
WRITE_ONCE(call->ack_at, timo);
trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now);
}
if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) {
if (!rxrpc_rotate_tx_window(call, top, &summary)) {
rxrpc_proto_abort("TXL", call, top);
return false;
}
}
if (!rxrpc_end_tx_phase(call, true, "ETD"))
return false;
call->tx_phase = false;
return true;
}
/*
* Scan a data packet to validate its structure and to work out how many
* subpackets it contains.
*
* A jumbo packet is a collection of consecutive packets glued together with
* little headers between that indicate how to change the initial header for
* each subpacket.
*
* RXRPC_JUMBO_PACKET must be set on all but the last subpacket - and all but
* the last are RXRPC_JUMBO_DATALEN in size. The last subpacket may be of any
* size.
*/
static bool rxrpc_validate_data(struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
unsigned int offset = sizeof(struct rxrpc_wire_header);
unsigned int len = skb->len;
u8 flags = sp->hdr.flags;
for (;;) {
if (flags & RXRPC_REQUEST_ACK)
__set_bit(sp->nr_subpackets, sp->rx_req_ack);
sp->nr_subpackets++;
if (!(flags & RXRPC_JUMBO_PACKET))
break;
if (len - offset < RXRPC_JUMBO_SUBPKTLEN)
goto protocol_error;
if (flags & RXRPC_LAST_PACKET)
goto protocol_error;
offset += RXRPC_JUMBO_DATALEN;
if (skb_copy_bits(skb, offset, &flags, 1) < 0)
goto protocol_error;
offset += sizeof(struct rxrpc_jumbo_header);
}
if (flags & RXRPC_LAST_PACKET)
sp->rx_flags |= RXRPC_SKB_INCL_LAST;
return true;
protocol_error:
return false;
}
/*
* Handle reception of a duplicate packet.
*
* We have to take care to avoid an attack here whereby we're given a series of
* jumbograms, each with a sequence number one before the preceding one and
* filled up to maximum UDP size. If they never send us the first packet in
* the sequence, they can cause us to have to hold on to around 2MiB of kernel
* space until the call times out.
*
* We limit the space usage by only accepting three duplicate jumbo packets per
* call. After that, we tell the other side we're no longer accepting jumbos
* (that information is encoded in the ACK packet).
*/
static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq,
bool is_jumbo, bool *_jumbo_bad)
{
/* Discard normal packets that are duplicates. */
if (is_jumbo)
return;
/* Skip jumbo subpackets that are duplicates. When we've had three or
* more partially duplicate jumbo packets, we refuse to take any more
* jumbos for this call.
*/
if (!*_jumbo_bad) {
call->nr_jumbo_bad++;
*_jumbo_bad = true;
}
}
/*
* Process a DATA packet, adding the packet to the Rx ring. The caller's
* packet ref must be passed on or discarded.
*/
static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
enum rxrpc_call_state state;
unsigned int j, nr_subpackets, nr_unacked = 0;
rxrpc_serial_t serial = sp->hdr.serial, ack_serial = serial;
rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack;
bool immediate_ack = false, jumbo_bad = false;
u8 ack = 0;
_enter("{%u,%u},{%u,%u}",
call->rx_hard_ack, call->rx_top, skb->len, seq0);
_proto("Rx DATA %%%u { #%u f=%02x n=%u }",
sp->hdr.serial, seq0, sp->hdr.flags, sp->nr_subpackets);
state = READ_ONCE(call->state);
if (state >= RXRPC_CALL_COMPLETE) {
rxrpc_free_skb(skb, rxrpc_skb_freed);
return;
}
if (state == RXRPC_CALL_SERVER_RECV_REQUEST) {
unsigned long timo = READ_ONCE(call->next_req_timo);
unsigned long now, expect_req_by;
if (timo) {
now = jiffies;
expect_req_by = now + timo;
WRITE_ONCE(call->expect_req_by, expect_req_by);
rxrpc_reduce_call_timer(call, expect_req_by, now,
rxrpc_timer_set_for_idle);
}
}
spin_lock(&call->input_lock);
/* Received data implicitly ACKs all of the request packets we sent
* when we're acting as a client.
*/
if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
!rxrpc_receiving_reply(call))
goto unlock;
hard_ack = READ_ONCE(call->rx_hard_ack);
nr_subpackets = sp->nr_subpackets;
if (nr_subpackets > 1) {
if (call->nr_jumbo_bad > 3) {
ack = RXRPC_ACK_NOSPACE;
ack_serial = serial;
goto ack;
}
}
for (j = 0; j < nr_subpackets; j++) {
rxrpc_serial_t serial = sp->hdr.serial + j;
rxrpc_seq_t seq = seq0 + j;
unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK;
bool terminal = (j == nr_subpackets - 1);
bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST);
u8 flags, annotation = j;
_proto("Rx DATA+%u %%%u { #%x t=%u l=%u }",
j, serial, seq, terminal, last);
if (last) {
if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
seq != call->rx_top) {
rxrpc_proto_abort("LSN", call, seq);
goto unlock;
}
} else {
if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
after_eq(seq, call->rx_top)) {
rxrpc_proto_abort("LSA", call, seq);
goto unlock;
}
}
flags = 0;
if (last)
flags |= RXRPC_LAST_PACKET;
if (!terminal)
flags |= RXRPC_JUMBO_PACKET;
if (test_bit(j, sp->rx_req_ack))
flags |= RXRPC_REQUEST_ACK;
trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation);
if (before_eq(seq, hard_ack)) {
ack = RXRPC_ACK_DUPLICATE;
ack_serial = serial;
continue;
}
if (call->rxtx_buffer[ix]) {
rxrpc_input_dup_data(call, seq, nr_subpackets > 1,
&jumbo_bad);
if (ack != RXRPC_ACK_DUPLICATE) {
ack = RXRPC_ACK_DUPLICATE;
ack_serial = serial;
}
immediate_ack = true;
continue;
}
if (after(seq, hard_ack + call->rx_winsize)) {
ack = RXRPC_ACK_EXCEEDS_WINDOW;
ack_serial = serial;
if (flags & RXRPC_JUMBO_PACKET) {
if (!jumbo_bad) {
call->nr_jumbo_bad++;
jumbo_bad = true;
}
}
goto ack;
}
if (flags & RXRPC_REQUEST_ACK && !ack) {
ack = RXRPC_ACK_REQUESTED;
ack_serial = serial;
}
if (after(seq0, call->ackr_highest_seq))
call->ackr_highest_seq = seq0;
/* Queue the packet. We use a couple of memory barriers here as need
* to make sure that rx_top is perceived to be set after the buffer
* pointer and that the buffer pointer is set after the annotation and
* the skb data.
*
* Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window()
* and also rxrpc_fill_out_ack().
*/
if (!terminal)
rxrpc_get_skb(skb, rxrpc_skb_got);
call->rxtx_annotations[ix] = annotation;
smp_wmb();
call->rxtx_buffer[ix] = skb;
if (after(seq, call->rx_top)) {
smp_store_release(&call->rx_top, seq);
} else if (before(seq, call->rx_top)) {
/* Send an immediate ACK if we fill in a hole */
if (!ack) {
ack = RXRPC_ACK_DELAY;
ack_serial = serial;
}
immediate_ack = true;
}
if (terminal) {
/* From this point on, we're not allowed to touch the
* packet any longer as its ref now belongs to the Rx
* ring.
*/
skb = NULL;
sp = NULL;
}
nr_unacked++;
if (last) {
set_bit(RXRPC_CALL_RX_LAST, &call->flags);
if (!ack) {
ack = RXRPC_ACK_DELAY;
ack_serial = serial;
}
trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq);
} else {
trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq);
}
if (after_eq(seq, call->rx_expect_next)) {
if (after(seq, call->rx_expect_next)) {
_net("OOS %u > %u", seq, call->rx_expect_next);
ack = RXRPC_ACK_OUT_OF_SEQUENCE;
ack_serial = serial;
}
call->rx_expect_next = seq + 1;
}
if (!ack)
ack_serial = serial;
}
ack:
if (atomic_add_return(nr_unacked, &call->ackr_nr_unacked) > 2 && !ack)
ack = RXRPC_ACK_IDLE;
if (ack)
rxrpc_propose_ACK(call, ack, ack_serial,
immediate_ack, true,
rxrpc_propose_ack_input_data);
else
rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial,
false, true,
rxrpc_propose_ack_input_data);
trace_rxrpc_notify_socket(call->debug_id, serial);
rxrpc_notify_socket(call);
unlock:
spin_unlock(&call->input_lock);
rxrpc_free_skb(skb, rxrpc_skb_freed);
_leave(" [queued]");
}
/*
* See if there's a cached RTT probe to complete.
*/
static void rxrpc_complete_rtt_probe(struct rxrpc_call *call,
ktime_t resp_time,
rxrpc_serial_t acked_serial,
rxrpc_serial_t ack_serial,
enum rxrpc_rtt_rx_trace type)
{
rxrpc_serial_t orig_serial;
unsigned long avail;
ktime_t sent_at;
bool matched = false;
int i;
avail = READ_ONCE(call->rtt_avail);
smp_rmb(); /* Read avail bits before accessing data. */
for (i = 0; i < ARRAY_SIZE(call->rtt_serial); i++) {
if (!test_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &avail))
continue;
sent_at = call->rtt_sent_at[i];
orig_serial = call->rtt_serial[i];
if (orig_serial == acked_serial) {
clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail);
smp_mb(); /* Read data before setting avail bit */
set_bit(i, &call->rtt_avail);
if (type != rxrpc_rtt_rx_cancel)
rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial,
sent_at, resp_time);
else
trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_cancel, i,
orig_serial, acked_serial, 0, 0);
matched = true;
}
/* If a later serial is being acked, then mark this slot as
* being available.
*/
if (after(acked_serial, orig_serial)) {
trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_obsolete, i,
orig_serial, acked_serial, 0, 0);
clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail);
smp_wmb();
set_bit(i, &call->rtt_avail);
}
}
if (!matched)
trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_lost, 9, 0, acked_serial, 0, 0);
}
/*
* Process the response to a ping that we sent to find out if we lost an ACK.
*
* If we got back a ping response that indicates a lower tx_top than what we
* had at the time of the ping transmission, we adjudge all the DATA packets
* sent between the response tx_top and the ping-time tx_top to have been lost.
*/
static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call)
{
rxrpc_seq_t top, bottom, seq;
bool resend = false;
spin_lock_bh(&call->lock);
bottom = call->tx_hard_ack + 1;
top = call->acks_lost_top;
if (before(bottom, top)) {
for (seq = bottom; before_eq(seq, top); seq++) {
int ix = seq & RXRPC_RXTX_BUFF_MASK;
u8 annotation = call->rxtx_annotations[ix];
u8 anno_type = annotation & RXRPC_TX_ANNO_MASK;
if (anno_type != RXRPC_TX_ANNO_UNACK)
continue;
annotation &= ~RXRPC_TX_ANNO_MASK;
annotation |= RXRPC_TX_ANNO_RETRANS;
call->rxtx_annotations[ix] = annotation;
resend = true;
}
}
spin_unlock_bh(&call->lock);
if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events))
rxrpc_queue_call(call);
}
/*
* Process a ping response.
*/
static void rxrpc_input_ping_response(struct rxrpc_call *call,
ktime_t resp_time,
rxrpc_serial_t acked_serial,
rxrpc_serial_t ack_serial)
{
if (acked_serial == call->acks_lost_ping)
rxrpc_input_check_for_lost_ack(call);
}
/*
* Process the extra information that may be appended to an ACK packet
*/
static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
struct rxrpc_ackinfo *ackinfo)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_peer *peer;
unsigned int mtu;
bool wake = false;
u32 rwind = ntohl(ackinfo->rwind);
_proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }",
sp->hdr.serial,
ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU),
rwind, ntohl(ackinfo->jumbo_max));
if (rwind > RXRPC_RXTX_BUFF_SIZE - 1)
rwind = RXRPC_RXTX_BUFF_SIZE - 1;
if (call->tx_winsize != rwind) {
if (rwind > call->tx_winsize)
wake = true;
trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, rwind, wake);
call->tx_winsize = rwind;
}
if (call->cong_ssthresh > rwind)
call->cong_ssthresh = rwind;
mtu = min(ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU));
peer = call->peer;
if (mtu < peer->maxdata) {
spin_lock_bh(&peer->lock);
peer->maxdata = mtu;
peer->mtu = mtu + peer->hdrsize;
spin_unlock_bh(&peer->lock);
_net("Net MTU %u (maxdata %u)", peer->mtu, peer->maxdata);
}
if (wake)
wake_up(&call->waitq);
}
/*
* Process individual soft ACKs.
*
* Each ACK in the array corresponds to one packet and can be either an ACK or
* a NAK. If we get find an explicitly NAK'd packet we resend immediately;
* packets that lie beyond the end of the ACK list are scheduled for resend by
* the timer on the basis that the peer might just not have processed them at
* the time the ACK was sent.
*/
static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks,
rxrpc_seq_t seq, int nr_acks,
struct rxrpc_ack_summary *summary)
{
int ix;
u8 annotation, anno_type;
for (; nr_acks > 0; nr_acks--, seq++) {
ix = seq & RXRPC_RXTX_BUFF_MASK;
annotation = call->rxtx_annotations[ix];
anno_type = annotation & RXRPC_TX_ANNO_MASK;
annotation &= ~RXRPC_TX_ANNO_MASK;
switch (*acks++) {
case RXRPC_ACK_TYPE_ACK:
summary->nr_acks++;
if (anno_type == RXRPC_TX_ANNO_ACK)
continue;
summary->nr_new_acks++;
call->rxtx_annotations[ix] =
RXRPC_TX_ANNO_ACK | annotation;
break;
case RXRPC_ACK_TYPE_NACK:
if (!summary->nr_nacks &&
call->acks_lowest_nak != seq) {
call->acks_lowest_nak = seq;
summary->new_low_nack = true;
}
summary->nr_nacks++;
if (anno_type == RXRPC_TX_ANNO_NAK)
continue;
summary->nr_new_nacks++;
if (anno_type == RXRPC_TX_ANNO_RETRANS)
continue;
call->rxtx_annotations[ix] =
RXRPC_TX_ANNO_NAK | annotation;
break;
default:
return rxrpc_proto_abort("SFT", call, 0);
}
}
}
/*
* Return true if the ACK is valid - ie. it doesn't appear to have regressed
* with respect to the ack state conveyed by preceding ACKs.
*/
static bool rxrpc_is_ack_valid(struct rxrpc_call *call,
rxrpc_seq_t first_pkt, rxrpc_seq_t prev_pkt)
{
rxrpc_seq_t base = READ_ONCE(call->acks_first_seq);
if (after(first_pkt, base))
return true; /* The window advanced */
if (before(first_pkt, base))
return false; /* firstPacket regressed */
if (after_eq(prev_pkt, call->acks_prev_seq))
return true; /* previousPacket hasn't regressed. */
/* Some rx implementations put a serial number in previousPacket. */
if (after_eq(prev_pkt, base + call->tx_winsize))
return false;
return true;
}
/*
* Process an ACK packet.
*
* ack.firstPacket is the sequence number of the first soft-ACK'd/NAK'd packet
* in the ACK array. Anything before that is hard-ACK'd and may be discarded.
*
* A hard-ACK means that a packet has been processed and may be discarded; a
* soft-ACK means that the packet may be discarded and retransmission
* requested. A phase is complete when all packets are hard-ACK'd.
*/
static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
{
struct rxrpc_ack_summary summary = { 0 };
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
union {
struct rxrpc_ackpacket ack;
struct rxrpc_ackinfo info;
u8 acks[RXRPC_MAXACKS];
} buf;
rxrpc_serial_t ack_serial, acked_serial;
rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt;
int nr_acks, offset, ioffset;
_enter("");
offset = sizeof(struct rxrpc_wire_header);
if (skb_copy_bits(skb, offset, &buf.ack, sizeof(buf.ack)) < 0) {
_debug("extraction failure");
return rxrpc_proto_abort("XAK", call, 0);
}
offset += sizeof(buf.ack);
ack_serial = sp->hdr.serial;
acked_serial = ntohl(buf.ack.serial);
first_soft_ack = ntohl(buf.ack.firstPacket);
prev_pkt = ntohl(buf.ack.previousPacket);
hard_ack = first_soft_ack - 1;
nr_acks = buf.ack.nAcks;
summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ?
buf.ack.reason : RXRPC_ACK__INVALID);
trace_rxrpc_rx_ack(call, ack_serial, acked_serial,
first_soft_ack, prev_pkt,
summary.ack_reason, nr_acks);
switch (buf.ack.reason) {
case RXRPC_ACK_PING_RESPONSE:
rxrpc_input_ping_response(call, skb->tstamp, acked_serial,
ack_serial);
rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
rxrpc_rtt_rx_ping_response);
break;
case RXRPC_ACK_REQUESTED:
rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
rxrpc_rtt_rx_requested_ack);
break;
default:
if (acked_serial != 0)
rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
rxrpc_rtt_rx_cancel);
break;
}
if (buf.ack.reason == RXRPC_ACK_PING) {
_proto("Rx ACK %%%u PING Request", ack_serial);
rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE,
ack_serial, true, true,
rxrpc_propose_ack_respond_to_ping);
} else if (sp->hdr.flags & RXRPC_REQUEST_ACK) {
rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED,
ack_serial, true, true,
rxrpc_propose_ack_respond_to_ack);
}
/* If we get an EXCEEDS_WINDOW ACK from the server, it probably
* indicates that the client address changed due to NAT. The server
* lost the call because it switched to a different peer.
*/
if (unlikely(buf.ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) &&
first_soft_ack == 1 &&
prev_pkt == 0 &&
rxrpc_is_client_call(call)) {
rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
0, -ENETRESET);
return;
}
/* If we get an OUT_OF_SEQUENCE ACK from the server, that can also
* indicate a change of address. However, we can retransmit the call
* if we still have it buffered to the beginning.
*/
if (unlikely(buf.ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) &&
first_soft_ack == 1 &&
prev_pkt == 0 &&
call->tx_hard_ack == 0 &&
rxrpc_is_client_call(call)) {
rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
0, -ENETRESET);
return;
}
/* Discard any out-of-order or duplicate ACKs (outside lock). */
if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) {
trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial,
first_soft_ack, call->acks_first_seq,
prev_pkt, call->acks_prev_seq);
return;
}
buf.info.rxMTU = 0;
ioffset = offset + nr_acks + 3;
if (skb->len >= ioffset + sizeof(buf.info) &&
skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0)
return rxrpc_proto_abort("XAI", call, 0);
spin_lock(&call->input_lock);
/* Discard any out-of-order or duplicate ACKs (inside lock). */
if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) {
trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial,
first_soft_ack, call->acks_first_seq,
prev_pkt, call->acks_prev_seq);
goto out;
}
call->acks_latest_ts = skb->tstamp;
call->acks_first_seq = first_soft_ack;
call->acks_prev_seq = prev_pkt;
/* Parse rwind and mtu sizes if provided. */
if (buf.info.rxMTU)
rxrpc_input_ackinfo(call, skb, &buf.info);
if (first_soft_ack == 0) {
rxrpc_proto_abort("AK0", call, 0);
goto out;
}
/* Ignore ACKs unless we are or have just been transmitting. */
switch (READ_ONCE(call->state)) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_CLIENT_AWAIT_REPLY:
case RXRPC_CALL_SERVER_SEND_REPLY:
case RXRPC_CALL_SERVER_AWAIT_ACK:
break;
default:
goto out;
}
if (before(hard_ack, call->tx_hard_ack) ||
after(hard_ack, call->tx_top)) {
rxrpc_proto_abort("AKW", call, 0);
goto out;
}
if (nr_acks > call->tx_top - hard_ack) {
rxrpc_proto_abort("AKN", call, 0);
goto out;
}
if (after(hard_ack, call->tx_hard_ack)) {