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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Implementation of the Transmission Control Protocol(TCP).
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
* Corey Minyard <wf-rch!minyard@relay.EU.net>
* Florian La Roche, <flla@stud.uni-sb.de>
* Charles Hedrick, <hedrick@klinzhai.rutgers.edu>
* Linus Torvalds, <torvalds@cs.helsinki.fi>
* Alan Cox, <gw4pts@gw4pts.ampr.org>
* Matthew Dillon, <dillon@apollo.west.oic.com>
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
* Jorge Cwik, <jorge@laser.satlink.net>
*/
#include <linux/module.h>
#include <linux/gfp.h>
#include <net/tcp.h>
#include <net/rstreason.h>
static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
const struct tcp_sock *tp = tcp_sk(sk);
u32 elapsed, user_timeout;
s32 remaining;
user_timeout = READ_ONCE(icsk->icsk_user_timeout);
if (!user_timeout)
return icsk->icsk_rto;
elapsed = tcp_time_stamp_ts(tp) - tp->retrans_stamp;
if (tp->tcp_usec_ts)
elapsed /= USEC_PER_MSEC;
remaining = user_timeout - elapsed;
if (remaining <= 0)
return 1; /* user timeout has passed; fire ASAP */
return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining));
}
u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 remaining, user_timeout;
s32 elapsed;
user_timeout = READ_ONCE(icsk->icsk_user_timeout);
if (!user_timeout || !icsk->icsk_probes_tstamp)
return when;
elapsed = tcp_jiffies32 - icsk->icsk_probes_tstamp;
if (unlikely(elapsed < 0))
elapsed = 0;
remaining = msecs_to_jiffies(user_timeout) - elapsed;
remaining = max_t(u32, remaining, TCP_TIMEOUT_MIN);
return min_t(u32, remaining, when);
}
/**
* tcp_write_err() - close socket and save error info
* @sk: The socket the error has appeared on.
*
* Returns: Nothing (void)
*/
static void tcp_write_err(struct sock *sk)
{
tcp_done_with_error(sk, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);
}
/**
* tcp_out_of_resources() - Close socket if out of resources
* @sk: pointer to current socket
* @do_reset: send a last packet with reset flag
*
* Do not allow orphaned sockets to eat all our resources.
* This is direct violation of TCP specs, but it is required
* to prevent DoS attacks. It is called when a retransmission timeout
* or zero probe timeout occurs on orphaned socket.
*
* Also close if our net namespace is exiting; in that case there is no
* hope of ever communicating again since all netns interfaces are already
* down (or about to be down), and we need to release our dst references,
* which have been moved to the netns loopback interface, so the namespace
* can finish exiting. This condition is only possible if we are a kernel
* socket, as those do not hold references to the namespace.
*
* Criteria is still not confirmed experimentally and may change.
* We kill the socket, if:
* 1. If number of orphaned sockets exceeds an administratively configured
* limit.
* 2. If we have strong memory pressure.
* 3. If our net namespace is exiting.
*/
static int tcp_out_of_resources(struct sock *sk, bool do_reset)
{
struct tcp_sock *tp = tcp_sk(sk);
int shift = 0;
/* If peer does not open window for long time, or did not transmit
* anything for long time, penalize it. */
if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset)
shift++;
/* If some dubious ICMP arrived, penalize even more. */
if (READ_ONCE(sk->sk_err_soft))
shift++;
if (tcp_check_oom(sk, shift)) {
/* Catch exceptional cases, when connection requires reset.
* 1. Last segment was sent recently. */
if ((s32)(tcp_jiffies32 - tp->lsndtime) <= TCP_TIMEWAIT_LEN ||
/* 2. Window is closed. */
(!tp->snd_wnd && !tp->packets_out))
do_reset = true;
if (do_reset)
tcp_send_active_reset(sk, GFP_ATOMIC,
SK_RST_REASON_TCP_ABORT_ON_MEMORY);
tcp_done(sk);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY);
return 1;
}
if (!check_net(sock_net(sk))) {
/* Not possible to send reset; just close */
tcp_done(sk);
return 1;
}
return 0;
}
/**
* tcp_orphan_retries() - Returns maximal number of retries on an orphaned socket
* @sk: Pointer to the current socket.
* @alive: bool, socket alive state
*/
static int tcp_orphan_retries(struct sock *sk, bool alive)
{
int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */
/* We know from an ICMP that something is wrong. */
if (READ_ONCE(sk->sk_err_soft) && !alive)
retries = 0;
/* However, if socket sent something recently, select some safe
* number of retries. 8 corresponds to >100 seconds with minimal
* RTO of 200msec. */
if (retries == 0 && alive)
retries = 8;
return retries;
}
static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
{
const struct net *net = sock_net(sk);
int mss;
/* Black hole detection */
if (!READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing))
return;
if (!icsk->icsk_mtup.enabled) {
icsk->icsk_mtup.enabled = 1;
icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
} else {
mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
mss = min(READ_ONCE(net->ipv4.sysctl_tcp_base_mss), mss);
mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_mtu_probe_floor));
mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_min_snd_mss));
icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
}
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
}
static unsigned int tcp_model_timeout(struct sock *sk,
unsigned int boundary,
unsigned int rto_base)
{
unsigned int linear_backoff_thresh, timeout;
linear_backoff_thresh = ilog2(TCP_RTO_MAX / rto_base);
if (boundary <= linear_backoff_thresh)
timeout = ((2 << boundary) - 1) * rto_base;
else
timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +
(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
return jiffies_to_msecs(timeout);
}
/**
* retransmits_timed_out() - returns true if this connection has timed out
* @sk: The current socket
* @boundary: max number of retransmissions
* @timeout: A custom timeout value.
* If set to 0 the default timeout is calculated and used.
* Using TCP_RTO_MIN and the number of unsuccessful retransmits.
*
* The default "timeout" value this function can calculate and use
* is equivalent to the timeout of a TCP Connection
* after "boundary" unsuccessful, exponentially backed-off
* retransmissions with an initial RTO of TCP_RTO_MIN.
*/
static bool retransmits_timed_out(struct sock *sk,
unsigned int boundary,
unsigned int timeout)
{
struct tcp_sock *tp = tcp_sk(sk);
unsigned int start_ts, delta;
if (!inet_csk(sk)->icsk_retransmits)
return false;
start_ts = tp->retrans_stamp;
if (likely(timeout == 0)) {
unsigned int rto_base = TCP_RTO_MIN;
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
rto_base = tcp_timeout_init(sk);
timeout = tcp_model_timeout(sk, boundary, rto_base);
}
if (tp->tcp_usec_ts) {
/* delta maybe off up to a jiffy due to timer granularity. */
delta = tp->tcp_mstamp - start_ts + jiffies_to_usecs(1);
return (s32)(delta - timeout * USEC_PER_MSEC) >= 0;
}
return (s32)(tcp_time_stamp_ts(tp) - start_ts - timeout) >= 0;
}
/* A write timeout has occurred. Process the after effects. */
static int tcp_write_timeout(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
bool expired = false, do_reset;
int retry_until, max_retransmits;
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
if (icsk->icsk_retransmits)
__dst_negative_advice(sk);
/* Paired with WRITE_ONCE() in tcp_sock_set_syncnt() */
retry_until = READ_ONCE(icsk->icsk_syn_retries) ? :
READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
max_retransmits = retry_until;
if (sk->sk_state == TCP_SYN_SENT)
max_retransmits += READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts);
expired = icsk->icsk_retransmits >= max_retransmits;
} else {
if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) {
/* Black hole detection */
tcp_mtu_probing(icsk, sk);
__dst_negative_advice(sk);
}
retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2);
if (sock_flag(sk, SOCK_DEAD)) {
const bool alive = icsk->icsk_rto < TCP_RTO_MAX;
retry_until = tcp_orphan_retries(sk, alive);
do_reset = alive ||
!retransmits_timed_out(sk, retry_until, 0);
if (tcp_out_of_resources(sk, do_reset))
return 1;
}
}
if (!expired)
expired = retransmits_timed_out(sk, retry_until,
READ_ONCE(icsk->icsk_user_timeout));
tcp_fastopen_active_detect_blackhole(sk, expired);
mptcp_active_detect_blackhole(sk, expired);
if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG))
tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB,
icsk->icsk_retransmits,
icsk->icsk_rto, (int)expired);
if (expired) {
/* Has it gone just too far? */
tcp_write_err(sk);
return 1;
}
if (sk_rethink_txhash(sk)) {
tp->timeout_rehash++;
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTREHASH);
}
return 0;
}
/* Called with BH disabled */
void tcp_delack_timer_handler(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
return;
/* Handling the sack compression case */
if (tp->compressed_ack) {
tcp_mstamp_refresh(tp);
tcp_sack_compress_send_ack(sk);
return;
}
if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
return;
if (time_after(icsk->icsk_ack.timeout, jiffies)) {
sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
return;
}
icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER;
if (inet_csk_ack_scheduled(sk)) {
if (!inet_csk_in_pingpong_mode(sk)) {
/* Delayed ACK missed: inflate ATO. */
icsk->icsk_ack.ato = min_t(u32, icsk->icsk_ack.ato << 1, icsk->icsk_rto);
} else {
/* Delayed ACK missed: leave pingpong mode and
* deflate ATO.
*/
inet_csk_exit_pingpong_mode(sk);
icsk->icsk_ack.ato = TCP_ATO_MIN;
}
tcp_mstamp_refresh(tp);
tcp_send_ack(sk);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS);
}
}
/**
* tcp_delack_timer() - The TCP delayed ACK timeout handler
* @t: Pointer to the timer. (gets casted to struct sock *)
*
* This function gets (indirectly) called when the kernel timer for a TCP packet
* of this socket expires. Calls tcp_delack_timer_handler() to do the actual work.
*
* Returns: Nothing (void)
*/
static void tcp_delack_timer(struct timer_list *t)
{
struct inet_connection_sock *icsk =
from_timer(icsk, t, icsk_delack_timer);
struct sock *sk = &icsk->icsk_inet.sk;
/* Avoid taking socket spinlock if there is no ACK to send.
* The compressed_ack check is racy, but a separate hrtimer
* will take care of it eventually.
*/
if (!(smp_load_acquire(&icsk->icsk_ack.pending) & ICSK_ACK_TIMER) &&
!READ_ONCE(tcp_sk(sk)->compressed_ack))
goto out;
bh_lock_sock(sk);
if (!sock_owned_by_user(sk)) {
tcp_delack_timer_handler(sk);
} else {
__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
/* deleguate our work to tcp_release_cb() */
if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags))
sock_hold(sk);
}
bh_unlock_sock(sk);
out:
sock_put(sk);
}
static void tcp_probe_timer(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct sk_buff *skb = tcp_send_head(sk);
struct tcp_sock *tp = tcp_sk(sk);
int max_probes;
if (tp->packets_out || !skb) {
icsk->icsk_probes_out = 0;
icsk->icsk_probes_tstamp = 0;
return;
}
/* RFC 1122 4.2.2.17 requires the sender to stay open indefinitely as
* long as the receiver continues to respond probes. We support this by
* default and reset icsk_probes_out with incoming ACKs. But if the
* socket is orphaned or the user specifies TCP_USER_TIMEOUT, we
* kill the socket when the retry count and the time exceeds the
* corresponding system limit. We also implement similar policy when
* we use RTO to probe window in tcp_retransmit_timer().
*/
if (!icsk->icsk_probes_tstamp) {
icsk->icsk_probes_tstamp = tcp_jiffies32;
} else {
u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout);
if (user_timeout &&
(s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >=
msecs_to_jiffies(user_timeout))
goto abort;
}
max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2);
if (sock_flag(sk, SOCK_DEAD)) {
const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
max_probes = tcp_orphan_retries(sk, alive);
if (!alive && icsk->icsk_backoff >= max_probes)
goto abort;
if (tcp_out_of_resources(sk, true))
return;
}
if (icsk->icsk_probes_out >= max_probes) {
abort: tcp_write_err(sk);
} else {
/* Only send another probe if we didn't close things up. */
tcp_send_probe0(sk);
}
}
static void tcp_update_rto_stats(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
if (!icsk->icsk_retransmits) {
tp->total_rto_recoveries++;
tp->rto_stamp = tcp_time_stamp_ms(tp);
}
icsk->icsk_retransmits++;
tp->total_rto++;
}
/*
* Timer for Fast Open socket to retransmit SYNACK. Note that the
* sk here is the child socket, not the parent (listener) socket.
*/
static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int max_retries;
req->rsk_ops->syn_ack_timeout(req);
/* Add one more retry for fastopen.
* Paired with WRITE_ONCE() in tcp_sock_set_syncnt()
*/
max_retries = READ_ONCE(icsk->icsk_syn_retries) ? :
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1;
if (req->num_timeout >= max_retries) {
tcp_write_err(sk);
return;
}
/* Lower cwnd after certain SYNACK timeout like tcp_init_transfer() */
if (icsk->icsk_retransmits == 1)
tcp_enter_loss(sk);
/* XXX (TFO) - Unlike regular SYN-ACK retransmit, we ignore error
* returned from rtx_syn_ack() to make it more persistent like
* regular retransmit because if the child socket has been accepted
* it's not good to give up too easily.
*/
inet_rtx_syn_ack(sk, req);
req->num_timeout++;
tcp_update_rto_stats(sk);
if (!tp->retrans_stamp)
tp->retrans_stamp = tcp_time_stamp_ts(tp);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
req->timeout << req->num_timeout, TCP_RTO_MAX);
}
static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
const struct sk_buff *skb,
u32 rtx_delta)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout);
const struct tcp_sock *tp = tcp_sk(sk);
int timeout = TCP_RTO_MAX * 2;
s32 rcv_delta;
if (user_timeout) {
/* If user application specified a TCP_USER_TIMEOUT,
* it does not want win 0 packets to 'reset the timer'
* while retransmits are not making progress.
*/
if (rtx_delta > user_timeout)
return true;
timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout));
}
/* Note: timer interrupt might have been delayed by at least one jiffy,
* and tp->rcv_tstamp might very well have been written recently.
* rcv_delta can thus be negative.
*/
rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp;
if (rcv_delta <= timeout)
return false;
return msecs_to_jiffies(rtx_delta) > timeout;
}
/**
* tcp_retransmit_timer() - The TCP retransmit timeout handler
* @sk: Pointer to the current socket.
*
* This function gets called when the kernel timer for a TCP packet
* of this socket expires.
*
* It handles retransmission, timer adjustment and other necessary measures.
*
* Returns: Nothing (void)
*/
void tcp_retransmit_timer(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct request_sock *req;
struct sk_buff *skb;
req = rcu_dereference_protected(tp->fastopen_rsk,
lockdep_sock_is_held(sk));
if (req) {
WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
sk->sk_state != TCP_FIN_WAIT1);
tcp_fastopen_synack_timer(sk, req);
/* Before we receive ACK to our SYN-ACK don't retransmit
* anything else (e.g., data or FIN segments).
*/
return;
}
if (!tp->packets_out)
return;
skb = tcp_rtx_queue_head(sk);
if (WARN_ON_ONCE(!skb))
return;
if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) &&
!((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) {
/* Receiver dastardly shrinks window. Our retransmits
* become zero probes, but we should not timeout this
* connection. If the socket is an orphan, time it out,
* we cannot allow such beasts to hang infinitely.
*/
struct inet_sock *inet = inet_sk(sk);
u32 rtx_delta;
rtx_delta = tcp_time_stamp_ts(tp) - (tp->retrans_stamp ?:
tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb));
if (tp->tcp_usec_ts)
rtx_delta /= USEC_PER_MSEC;
if (sk->sk_family == AF_INET) {
net_dbg_ratelimited("Probing zero-window on %pI4:%u/%u, seq=%u:%u, recv %ums ago, lasting %ums\n",
&inet->inet_daddr, ntohs(inet->inet_dport),
inet->inet_num, tp->snd_una, tp->snd_nxt,
jiffies_to_msecs(jiffies - tp->rcv_tstamp),
rtx_delta);
}
#if IS_ENABLED(CONFIG_IPV6)
else if (sk->sk_family == AF_INET6) {
net_dbg_ratelimited("Probing zero-window on %pI6:%u/%u, seq=%u:%u, recv %ums ago, lasting %ums\n",
&sk->sk_v6_daddr, ntohs(inet->inet_dport),
inet->inet_num, tp->snd_una, tp->snd_nxt,
jiffies_to_msecs(jiffies - tp->rcv_tstamp),
rtx_delta);
}
#endif
if (tcp_rtx_probe0_timed_out(sk, skb, rtx_delta)) {
tcp_write_err(sk);
goto out;
}
tcp_enter_loss(sk);
tcp_retransmit_skb(sk, skb, 1);
__sk_dst_reset(sk);
goto out_reset_timer;
}
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTS);
if (tcp_write_timeout(sk))
goto out;
if (icsk->icsk_retransmits == 0) {
int mib_idx = 0;
if (icsk->icsk_ca_state == TCP_CA_Recovery) {
if (tcp_is_sack(tp))
mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL;
else
mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL;
} else if (icsk->icsk_ca_state == TCP_CA_Loss) {
mib_idx = LINUX_MIB_TCPLOSSFAILURES;
} else if ((icsk->icsk_ca_state == TCP_CA_Disorder) ||
tp->sacked_out) {
if (tcp_is_sack(tp))
mib_idx = LINUX_MIB_TCPSACKFAILURES;
else
mib_idx = LINUX_MIB_TCPRENOFAILURES;
}
if (mib_idx)
__NET_INC_STATS(sock_net(sk), mib_idx);
}
tcp_enter_loss(sk);
tcp_update_rto_stats(sk);
if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) {
/* Retransmission failed because of local congestion,
* Let senders fight for local resources conservatively.
*/
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
TCP_RESOURCE_PROBE_INTERVAL,
TCP_RTO_MAX);
goto out;
}
/* Increase the timeout each time we retransmit. Note that
* we do not increase the rtt estimate. rto is initialized
* from rtt, but increases here. Jacobson (SIGCOMM 88) suggests
* that doubling rto each time is the least we can get away with.
* In KA9Q, Karn uses this for the first few times, and then
* goes to quadratic. netBSD doubles, but only goes up to *64,
* and clamps at 1 to 64 sec afterwards. Note that 120 sec is
* defined in the protocol as the maximum possible RTT. I guess
* we'll have to use something other than TCP to talk to the
* University of Mars.
*
* PAWS allows us longer timeouts and large windows, so once
* implemented ftp to mars will work nicely. We will have to fix
* the 120 second clamps though!
*/
out_reset_timer:
/* If stream is thin, use linear timeouts. Since 'icsk_backoff' is
* used to reset timer, set to 0. Recalculate 'icsk_rto' as this
* might be increased if the stream oscillates between thin and thick,
* thus the old value might already be too high compared to the value
* set by 'tcp_set_rto' in tcp_input.c which resets the rto without
* backoff. Limit to TCP_THIN_LINEAR_RETRIES before initiating
* exponential backoff behaviour to avoid continue hammering
* linear-timeout retransmissions into a black hole
*/
if (sk->sk_state == TCP_ESTABLISHED &&
(tp->thin_lto || READ_ONCE(net->ipv4.sysctl_tcp_thin_linear_timeouts)) &&
tcp_stream_is_thin(tp) &&
icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
icsk->icsk_backoff = 0;
icsk->icsk_rto = clamp(__tcp_set_rto(tp),
tcp_rto_min(sk),
TCP_RTO_MAX);
} else if (sk->sk_state != TCP_SYN_SENT ||
tp->total_rto >
READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) {
/* Use normal (exponential) backoff unless linear timeouts are
* activated.
*/
icsk->icsk_backoff++;
icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
}
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX);
if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0))
__sk_dst_reset(sk);
out:;
}
/* Called with bottom-half processing disabled.
Called by tcp_write_timer() */
void tcp_write_timer_handler(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
int event;
if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
!icsk->icsk_pending)
return;
if (time_after(icsk->icsk_timeout, jiffies)) {
sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
return;
}
tcp_mstamp_refresh(tcp_sk(sk));
event = icsk->icsk_pending;
switch (event) {
case ICSK_TIME_REO_TIMEOUT:
tcp_rack_reo_timeout(sk);
break;
case ICSK_TIME_LOSS_PROBE:
tcp_send_loss_probe(sk);
break;
case ICSK_TIME_RETRANS:
smp_store_release(&icsk->icsk_pending, 0);
tcp_retransmit_timer(sk);
break;
case ICSK_TIME_PROBE0:
smp_store_release(&icsk->icsk_pending, 0);
tcp_probe_timer(sk);
break;
}
}
static void tcp_write_timer(struct timer_list *t)
{
struct inet_connection_sock *icsk =
from_timer(icsk, t, icsk_retransmit_timer);
struct sock *sk = &icsk->icsk_inet.sk;
/* Avoid locking the socket when there is no pending event. */
if (!smp_load_acquire(&icsk->icsk_pending))
goto out;
bh_lock_sock(sk);
if (!sock_owned_by_user(sk)) {
tcp_write_timer_handler(sk);
} else {
/* delegate our work to tcp_release_cb() */
if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &sk->sk_tsq_flags))
sock_hold(sk);
}
bh_unlock_sock(sk);
out:
sock_put(sk);
}
void tcp_syn_ack_timeout(const struct request_sock *req)
{
struct net *net = read_pnet(&inet_rsk(req)->ireq_net);
__NET_INC_STATS(net, LINUX_MIB_TCPTIMEOUTS);
}
EXPORT_SYMBOL(tcp_syn_ack_timeout);
void tcp_set_keepalive(struct sock *sk, int val)
{
if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
return;
if (val && !sock_flag(sk, SOCK_KEEPOPEN))
inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk)));
else if (!val)
inet_csk_delete_keepalive_timer(sk);
}
EXPORT_SYMBOL_GPL(tcp_set_keepalive);
static void tcp_keepalive_timer (struct timer_list *t)
{
struct sock *sk = from_timer(sk, t, sk_timer);
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
u32 elapsed;
/* Only process if socket is not in use. */
bh_lock_sock(sk);
if (sock_owned_by_user(sk)) {
/* Try again later. */
inet_csk_reset_keepalive_timer (sk, HZ/20);
goto out;
}
if (sk->sk_state == TCP_LISTEN) {
pr_err("Hmm... keepalive on a LISTEN ???\n");
goto out;
}
tcp_mstamp_refresh(tp);
if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) {
if (READ_ONCE(tp->linger2) >= 0) {
const int tmo = tcp_fin_time(sk) - TCP_TIMEWAIT_LEN;
if (tmo > 0) {
tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
goto out;
}
}
tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE);
goto death;
}
if (!sock_flag(sk, SOCK_KEEPOPEN) ||
((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)))
goto out;
elapsed = keepalive_time_when(tp);
/* It is alive without keepalive 8) */
if (tp->packets_out || !tcp_write_queue_empty(sk))
goto resched;
elapsed = keepalive_time_elapsed(tp);
if (elapsed >= keepalive_time_when(tp)) {
u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout);
/* If the TCP_USER_TIMEOUT option is enabled, use that
* to determine when to timeout instead.
*/
if ((user_timeout != 0 &&
elapsed >= msecs_to_jiffies(user_timeout) &&
icsk->icsk_probes_out > 0) ||
(user_timeout == 0 &&
icsk->icsk_probes_out >= keepalive_probes(tp))) {
tcp_send_active_reset(sk, GFP_ATOMIC,
SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT);
tcp_write_err(sk);
goto out;
}
if (tcp_write_wakeup(sk, LINUX_MIB_TCPKEEPALIVE) <= 0) {
icsk->icsk_probes_out++;
elapsed = keepalive_intvl_when(tp);
} else {
/* If keepalive was lost due to local congestion,
* try harder.
*/
elapsed = TCP_RESOURCE_PROBE_INTERVAL;
}
} else {
/* It is tp->rcv_tstamp + keepalive_time_when(tp) */
elapsed = keepalive_time_when(tp) - elapsed;
}
resched:
inet_csk_reset_keepalive_timer (sk, elapsed);
goto out;
death:
tcp_done(sk);
out:
bh_unlock_sock(sk);
sock_put(sk);
}
static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer)
{
struct tcp_sock *tp = container_of(timer, struct tcp_sock, compressed_ack_timer);
struct sock *sk = (struct sock *)tp;
bh_lock_sock(sk);
if (!sock_owned_by_user(sk)) {
if (tp->compressed_ack) {
/* Since we have to send one ack finally,
* subtract one from tp->compressed_ack to keep
* LINUX_MIB_TCPACKCOMPRESSED accurate.
*/
tp->compressed_ack--;
tcp_send_ack(sk);
}
} else {
if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED,
&sk->sk_tsq_flags))
sock_hold(sk);
}
bh_unlock_sock(sk);
sock_put(sk);
return HRTIMER_NORESTART;
}
void tcp_init_xmit_timers(struct sock *sk)
{
inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer,
&tcp_keepalive_timer);
hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC,
HRTIMER_MODE_ABS_PINNED_SOFT);
tcp_sk(sk)->pacing_timer.function = tcp_pace_kick;
hrtimer_init(&tcp_sk(sk)->compressed_ack_timer, CLOCK_MONOTONIC,
HRTIMER_MODE_REL_PINNED_SOFT);
tcp_sk(sk)->compressed_ack_timer.function = tcp_compressed_ack_kick;
}
|