summaryrefslogtreecommitdiffstats
path: root/sys/netinet/tcp_timer.c
blob: 8ead3dc36901c47f96af87551ef55c46e01c29d7 (plain)
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
/*-
 * Copyright (c) 1982, 1986, 1988, 1990, 1993, 1995
 *	The Regents of the University of California.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)tcp_timer.c	8.2 (Berkeley) 5/24/95
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include "opt_inet6.h"
#include "opt_tcpdebug.h"

#include <sys/param.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/mbuf.h>
#include <sys/mutex.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sysctl.h>
#include <sys/systm.h>

#include <net/if.h>
#include <net/route.h>
#include <net/vnet.h>

#include <netinet/in.h>
#include <netinet/in_pcb.h>
#include <netinet/in_systm.h>
#ifdef INET6
#include <netinet6/in6_pcb.h>
#endif
#include <netinet/ip_var.h>
#include <netinet/tcp.h>
#include <netinet/tcp_fsm.h>
#include <netinet/tcp_timer.h>
#include <netinet/tcp_var.h>
#include <netinet/tcpip.h>
#ifdef TCPDEBUG
#include <netinet/tcp_debug.h>
#endif

int	tcp_keepinit;
SYSCTL_PROC(_net_inet_tcp, TCPCTL_KEEPINIT, keepinit, CTLTYPE_INT|CTLFLAG_RW,
    &tcp_keepinit, 0, sysctl_msec_to_ticks, "I", "time to establish connection");

int	tcp_keepidle;
SYSCTL_PROC(_net_inet_tcp, TCPCTL_KEEPIDLE, keepidle, CTLTYPE_INT|CTLFLAG_RW,
    &tcp_keepidle, 0, sysctl_msec_to_ticks, "I", "time before keepalive probes begin");

int	tcp_keepintvl;
SYSCTL_PROC(_net_inet_tcp, TCPCTL_KEEPINTVL, keepintvl, CTLTYPE_INT|CTLFLAG_RW,
    &tcp_keepintvl, 0, sysctl_msec_to_ticks, "I", "time between keepalive probes");

int	tcp_delacktime;
SYSCTL_PROC(_net_inet_tcp, TCPCTL_DELACKTIME, delacktime, CTLTYPE_INT|CTLFLAG_RW,
    &tcp_delacktime, 0, sysctl_msec_to_ticks, "I",
    "Time before a delayed ACK is sent");

int	tcp_msl;
SYSCTL_PROC(_net_inet_tcp, OID_AUTO, msl, CTLTYPE_INT|CTLFLAG_RW,
    &tcp_msl, 0, sysctl_msec_to_ticks, "I", "Maximum segment lifetime");

int	tcp_rexmit_min;
SYSCTL_PROC(_net_inet_tcp, OID_AUTO, rexmit_min, CTLTYPE_INT|CTLFLAG_RW,
    &tcp_rexmit_min, 0, sysctl_msec_to_ticks, "I",
    "Minimum Retransmission Timeout");

int	tcp_rexmit_slop;
SYSCTL_PROC(_net_inet_tcp, OID_AUTO, rexmit_slop, CTLTYPE_INT|CTLFLAG_RW,
    &tcp_rexmit_slop, 0, sysctl_msec_to_ticks, "I",
    "Retransmission Timer Slop");

static int	always_keepalive = 1;
SYSCTL_INT(_net_inet_tcp, OID_AUTO, always_keepalive, CTLFLAG_RW,
    &always_keepalive , 0, "Assume SO_KEEPALIVE on all TCP connections");

int    tcp_fast_finwait2_recycle = 0;
SYSCTL_INT(_net_inet_tcp, OID_AUTO, fast_finwait2_recycle, CTLFLAG_RW, 
    &tcp_fast_finwait2_recycle, 0,
    "Recycle closed FIN_WAIT_2 connections faster");

int    tcp_finwait2_timeout;
SYSCTL_PROC(_net_inet_tcp, OID_AUTO, finwait2_timeout, CTLTYPE_INT|CTLFLAG_RW,
    &tcp_finwait2_timeout, 0, sysctl_msec_to_ticks, "I", "FIN-WAIT2 timeout");


static int	tcp_keepcnt = TCPTV_KEEPCNT;
	/* max idle probes */
int	tcp_maxpersistidle;
	/* max idle time in persist */
int	tcp_maxidle;

/*
 * Tcp protocol timeout routine called every 500 ms.
 * Updates timestamps used for TCP
 * causes finite state machine actions if timers expire.
 */
void
tcp_slowtimo(void)
{
	VNET_ITERATOR_DECL(vnet_iter);

	VNET_LIST_RLOCK_NOSLEEP();
	VNET_FOREACH(vnet_iter) {
		CURVNET_SET(vnet_iter);
		tcp_maxidle = tcp_keepcnt * tcp_keepintvl;
		INP_INFO_WLOCK(&V_tcbinfo);
		(void) tcp_tw_2msl_scan(0);
		INP_INFO_WUNLOCK(&V_tcbinfo);
		CURVNET_RESTORE();
	}
	VNET_LIST_RUNLOCK_NOSLEEP();
}

int	tcp_syn_backoff[TCP_MAXRXTSHIFT + 1] =
    { 1, 1, 1, 1, 1, 2, 4, 8, 16, 32, 64, 64, 64 };

int	tcp_backoff[TCP_MAXRXTSHIFT + 1] =
    { 1, 2, 4, 8, 16, 32, 64, 128, 256, 512, 512, 512, 512 };

static int tcp_totbackoff = 2559;	/* sum of tcp_backoff[] */

static int tcp_timer_race;
SYSCTL_INT(_net_inet_tcp, OID_AUTO, timer_race, CTLFLAG_RD, &tcp_timer_race,
    0, "Count of t_inpcb races on tcp_discardcb");

/*
 * TCP timer processing.
 */

void
tcp_timer_delack(void *xtp)
{
	struct tcpcb *tp = xtp;
	struct inpcb *inp;
	CURVNET_SET(tp->t_vnet);

	INP_INFO_RLOCK(&V_tcbinfo);
	inp = tp->t_inpcb;
	/*
	 * XXXRW: While this assert is in fact correct, bugs in the tcpcb
	 * tear-down mean we need it as a work-around for races between
	 * timers and tcp_discardcb().
	 *
	 * KASSERT(inp != NULL, ("tcp_timer_delack: inp == NULL"));
	 */
	if (inp == NULL) {
		tcp_timer_race++;
		INP_INFO_RUNLOCK(&V_tcbinfo);
		CURVNET_RESTORE();
		return;
	}
	INP_WLOCK(inp);
	INP_INFO_RUNLOCK(&V_tcbinfo);
	if ((inp->inp_flags & INP_DROPPED) || callout_pending(&tp->t_timers->tt_delack)
	    || !callout_active(&tp->t_timers->tt_delack)) {
		INP_WUNLOCK(inp);
		CURVNET_RESTORE();
		return;
	}
	callout_deactivate(&tp->t_timers->tt_delack);

	tp->t_flags |= TF_ACKNOW;
	TCPSTAT_INC(tcps_delack);
	(void) tcp_output(tp);
	INP_WUNLOCK(inp);
	CURVNET_RESTORE();
}

void
tcp_timer_2msl(void *xtp)
{
	struct tcpcb *tp = xtp;
	struct inpcb *inp;
	CURVNET_SET(tp->t_vnet);
#ifdef TCPDEBUG
	int ostate;

	ostate = tp->t_state;
#endif
	/*
	 * XXXRW: Does this actually happen?
	 */
	INP_INFO_WLOCK(&V_tcbinfo);
	inp = tp->t_inpcb;
	/*
	 * XXXRW: While this assert is in fact correct, bugs in the tcpcb
	 * tear-down mean we need it as a work-around for races between
	 * timers and tcp_discardcb().
	 *
	 * KASSERT(inp != NULL, ("tcp_timer_2msl: inp == NULL"));
	 */
	if (inp == NULL) {
		tcp_timer_race++;
		INP_INFO_WUNLOCK(&V_tcbinfo);
		CURVNET_RESTORE();
		return;
	}
	INP_WLOCK(inp);
	tcp_free_sackholes(tp);
	if ((inp->inp_flags & INP_DROPPED) || callout_pending(&tp->t_timers->tt_2msl) ||
	    !callout_active(&tp->t_timers->tt_2msl)) {
		INP_WUNLOCK(tp->t_inpcb);
		INP_INFO_WUNLOCK(&V_tcbinfo);
		CURVNET_RESTORE();
		return;
	}
	callout_deactivate(&tp->t_timers->tt_2msl);
	/*
	 * 2 MSL timeout in shutdown went off.  If we're closed but
	 * still waiting for peer to close and connection has been idle
	 * too long, or if 2MSL time is up from TIME_WAIT, delete connection
	 * control block.  Otherwise, check again in a bit.
	 *
	 * If fastrecycle of FIN_WAIT_2, in FIN_WAIT_2 and receiver has closed, 
	 * there's no point in hanging onto FIN_WAIT_2 socket. Just close it. 
	 * Ignore fact that there were recent incoming segments.
	 */
	if (tcp_fast_finwait2_recycle && tp->t_state == TCPS_FIN_WAIT_2 &&
	    tp->t_inpcb && tp->t_inpcb->inp_socket && 
	    (tp->t_inpcb->inp_socket->so_rcv.sb_state & SBS_CANTRCVMORE)) {
		TCPSTAT_INC(tcps_finwait2_drops);
		tp = tcp_close(tp);             
	} else {
		if (tp->t_state != TCPS_TIME_WAIT &&
		   ticks - tp->t_rcvtime <= tcp_maxidle)
		       callout_reset(&tp->t_timers->tt_2msl, tcp_keepintvl,
				     tcp_timer_2msl, tp);
	       else
		       tp = tcp_close(tp);
       }

#ifdef TCPDEBUG
	if (tp != NULL && (tp->t_inpcb->inp_socket->so_options & SO_DEBUG))
		tcp_trace(TA_USER, ostate, tp, (void *)0, (struct tcphdr *)0,
			  PRU_SLOWTIMO);
#endif
	if (tp != NULL)
		INP_WUNLOCK(inp);
	INP_INFO_WUNLOCK(&V_tcbinfo);
	CURVNET_RESTORE();
}

void
tcp_timer_keep(void *xtp)
{
	struct tcpcb *tp = xtp;
	struct tcptemp *t_template;
	struct inpcb *inp;
	CURVNET_SET(tp->t_vnet);
#ifdef TCPDEBUG
	int ostate;

	ostate = tp->t_state;
#endif
	INP_INFO_WLOCK(&V_tcbinfo);
	inp = tp->t_inpcb;
	/*
	 * XXXRW: While this assert is in fact correct, bugs in the tcpcb
	 * tear-down mean we need it as a work-around for races between
	 * timers and tcp_discardcb().
	 *
	 * KASSERT(inp != NULL, ("tcp_timer_keep: inp == NULL"));
	 */
	if (inp == NULL) {
		tcp_timer_race++;
		INP_INFO_WUNLOCK(&V_tcbinfo);
		CURVNET_RESTORE();
		return;
	}
	INP_WLOCK(inp);
	if ((inp->inp_flags & INP_DROPPED) || callout_pending(&tp->t_timers->tt_keep)
	    || !callout_active(&tp->t_timers->tt_keep)) {
		INP_WUNLOCK(inp);
		INP_INFO_WUNLOCK(&V_tcbinfo);
		CURVNET_RESTORE();
		return;
	}
	callout_deactivate(&tp->t_timers->tt_keep);
	/*
	 * Keep-alive timer went off; send something
	 * or drop connection if idle for too long.
	 */
	TCPSTAT_INC(tcps_keeptimeo);
	if (tp->t_state < TCPS_ESTABLISHED)
		goto dropit;
	if ((always_keepalive || inp->inp_socket->so_options & SO_KEEPALIVE) &&
	    tp->t_state <= TCPS_CLOSING) {
		if (ticks - tp->t_rcvtime >= tcp_keepidle + tcp_maxidle)
			goto dropit;
		/*
		 * Send a packet designed to force a response
		 * if the peer is up and reachable:
		 * either an ACK if the connection is still alive,
		 * or an RST if the peer has closed the connection
		 * due to timeout or reboot.
		 * Using sequence number tp->snd_una-1
		 * causes the transmitted zero-length segment
		 * to lie outside the receive window;
		 * by the protocol spec, this requires the
		 * correspondent TCP to respond.
		 */
		TCPSTAT_INC(tcps_keepprobe);
		t_template = tcpip_maketemplate(inp);
		if (t_template) {
			tcp_respond(tp, t_template->tt_ipgen,
				    &t_template->tt_t, (struct mbuf *)NULL,
				    tp->rcv_nxt, tp->snd_una - 1, 0);
			free(t_template, M_TEMP);
		}
		callout_reset(&tp->t_timers->tt_keep, tcp_keepintvl, tcp_timer_keep, tp);
	} else
		callout_reset(&tp->t_timers->tt_keep, tcp_keepidle, tcp_timer_keep, tp);

#ifdef TCPDEBUG
	if (inp->inp_socket->so_options & SO_DEBUG)
		tcp_trace(TA_USER, ostate, tp, (void *)0, (struct tcphdr *)0,
			  PRU_SLOWTIMO);
#endif
	INP_WUNLOCK(inp);
	INP_INFO_WUNLOCK(&V_tcbinfo);
	CURVNET_RESTORE();
	return;

dropit:
	TCPSTAT_INC(tcps_keepdrops);
	tp = tcp_drop(tp, ETIMEDOUT);

#ifdef TCPDEBUG
	if (tp != NULL && (tp->t_inpcb->inp_socket->so_options & SO_DEBUG))
		tcp_trace(TA_USER, ostate, tp, (void *)0, (struct tcphdr *)0,
			  PRU_SLOWTIMO);
#endif
	if (tp != NULL)
		INP_WUNLOCK(tp->t_inpcb);
	INP_INFO_WUNLOCK(&V_tcbinfo);
	CURVNET_RESTORE();
}

void
tcp_timer_persist(void *xtp)
{
	struct tcpcb *tp = xtp;
	struct inpcb *inp;
	CURVNET_SET(tp->t_vnet);
#ifdef TCPDEBUG
	int ostate;

	ostate = tp->t_state;
#endif
	INP_INFO_WLOCK(&V_tcbinfo);
	inp = tp->t_inpcb;
	/*
	 * XXXRW: While this assert is in fact correct, bugs in the tcpcb
	 * tear-down mean we need it as a work-around for races between
	 * timers and tcp_discardcb().
	 *
	 * KASSERT(inp != NULL, ("tcp_timer_persist: inp == NULL"));
	 */
	if (inp == NULL) {
		tcp_timer_race++;
		INP_INFO_WUNLOCK(&V_tcbinfo);
		CURVNET_RESTORE();
		return;
	}
	INP_WLOCK(inp);
	if ((inp->inp_flags & INP_DROPPED) || callout_pending(&tp->t_timers->tt_persist)
	    || !callout_active(&tp->t_timers->tt_persist)) {
		INP_WUNLOCK(inp);
		INP_INFO_WUNLOCK(&V_tcbinfo);
		CURVNET_RESTORE();
		return;
	}
	callout_deactivate(&tp->t_timers->tt_persist);
	/*
	 * Persistance timer into zero window.
	 * Force a byte to be output, if possible.
	 */
	TCPSTAT_INC(tcps_persisttimeo);
	/*
	 * Hack: if the peer is dead/unreachable, we do not
	 * time out if the window is closed.  After a full
	 * backoff, drop the connection if the idle time
	 * (no responses to probes) reaches the maximum
	 * backoff that we would use if retransmitting.
	 */
	if (tp->t_rxtshift == TCP_MAXRXTSHIFT &&
	    (ticks - tp->t_rcvtime >= tcp_maxpersistidle ||
	     ticks - tp->t_rcvtime >= TCP_REXMTVAL(tp) * tcp_totbackoff)) {
		TCPSTAT_INC(tcps_persistdrop);
		tp = tcp_drop(tp, ETIMEDOUT);
		goto out;
	}
	tcp_setpersist(tp);
	tp->t_flags |= TF_FORCEDATA;
	(void) tcp_output(tp);
	tp->t_flags &= ~TF_FORCEDATA;

out:
#ifdef TCPDEBUG
	if (tp != NULL && tp->t_inpcb->inp_socket->so_options & SO_DEBUG)
		tcp_trace(TA_USER, ostate, tp, NULL, NULL, PRU_SLOWTIMO);
#endif
	if (tp != NULL)
		INP_WUNLOCK(inp);
	INP_INFO_WUNLOCK(&V_tcbinfo);
	CURVNET_RESTORE();
}

void
tcp_timer_rexmt(void * xtp)
{
	struct tcpcb *tp = xtp;
	CURVNET_SET(tp->t_vnet);
	int rexmt;
	int headlocked;
	struct inpcb *inp;
#ifdef TCPDEBUG
	int ostate;

	ostate = tp->t_state;
#endif
	INP_INFO_WLOCK(&V_tcbinfo);
	headlocked = 1;
	inp = tp->t_inpcb;
	/*
	 * XXXRW: While this assert is in fact correct, bugs in the tcpcb
	 * tear-down mean we need it as a work-around for races between
	 * timers and tcp_discardcb().
	 *
	 * KASSERT(inp != NULL, ("tcp_timer_rexmt: inp == NULL"));
	 */
	if (inp == NULL) {
		tcp_timer_race++;
		INP_INFO_WUNLOCK(&V_tcbinfo);
		CURVNET_RESTORE();
		return;
	}
	INP_WLOCK(inp);
	if ((inp->inp_flags & INP_DROPPED) || callout_pending(&tp->t_timers->tt_rexmt)
	    || !callout_active(&tp->t_timers->tt_rexmt)) {
		INP_WUNLOCK(inp);
		INP_INFO_WUNLOCK(&V_tcbinfo);
		CURVNET_RESTORE();
		return;
	}
	callout_deactivate(&tp->t_timers->tt_rexmt);
	tcp_free_sackholes(tp);
	/*
	 * Retransmission timer went off.  Message has not
	 * been acked within retransmit interval.  Back off
	 * to a longer retransmit interval and retransmit one segment.
	 */
	if (++tp->t_rxtshift > TCP_MAXRXTSHIFT) {
		tp->t_rxtshift = TCP_MAXRXTSHIFT;
		TCPSTAT_INC(tcps_timeoutdrop);
		tp = tcp_drop(tp, tp->t_softerror ?
			      tp->t_softerror : ETIMEDOUT);
		goto out;
	}
	INP_INFO_WUNLOCK(&V_tcbinfo);
	headlocked = 0;
	if (tp->t_rxtshift == 1) {
		/*
		 * first retransmit; record ssthresh and cwnd so they can
		 * be recovered if this turns out to be a "bad" retransmit.
		 * A retransmit is considered "bad" if an ACK for this
		 * segment is received within RTT/2 interval; the assumption
		 * here is that the ACK was already in flight.  See
		 * "On Estimating End-to-End Network Path Properties" by
		 * Allman and Paxson for more details.
		 */
		tp->snd_cwnd_prev = tp->snd_cwnd;
		tp->snd_ssthresh_prev = tp->snd_ssthresh;
		tp->snd_recover_prev = tp->snd_recover;
		if (IN_FASTRECOVERY(tp))
		  tp->t_flags |= TF_WASFRECOVERY;
		else
		  tp->t_flags &= ~TF_WASFRECOVERY;
		tp->t_badrxtwin = ticks + (tp->t_srtt >> (TCP_RTT_SHIFT + 1));
	}
	TCPSTAT_INC(tcps_rexmttimeo);
	if (tp->t_state == TCPS_SYN_SENT)
		rexmt = TCP_REXMTVAL(tp) * tcp_syn_backoff[tp->t_rxtshift];
	else
		rexmt = TCP_REXMTVAL(tp) * tcp_backoff[tp->t_rxtshift];
	TCPT_RANGESET(tp->t_rxtcur, rexmt,
		      tp->t_rttmin, TCPTV_REXMTMAX);
	/*
	 * Disable rfc1323 if we havn't got any response to
	 * our third SYN to work-around some broken terminal servers
	 * (most of which have hopefully been retired) that have bad VJ
	 * header compression code which trashes TCP segments containing
	 * unknown-to-them TCP options.
	 */
	if ((tp->t_state == TCPS_SYN_SENT) && (tp->t_rxtshift == 3))
		tp->t_flags &= ~(TF_REQ_SCALE|TF_REQ_TSTMP);
	/*
	 * If we backed off this far, our srtt estimate is probably bogus.
	 * Clobber it so we'll take the next rtt measurement as our srtt;
	 * move the current srtt into rttvar to keep the current
	 * retransmit times until then.
	 */
	if (tp->t_rxtshift > TCP_MAXRXTSHIFT / 4) {
#ifdef INET6
		if ((tp->t_inpcb->inp_vflag & INP_IPV6) != 0)
			in6_losing(tp->t_inpcb);
		else
#endif
		tp->t_rttvar += (tp->t_srtt >> TCP_RTT_SHIFT);
		tp->t_srtt = 0;
	}
	tp->snd_nxt = tp->snd_una;
	tp->snd_recover = tp->snd_max;
	/*
	 * Force a segment to be sent.
	 */
	tp->t_flags |= TF_ACKNOW;
	/*
	 * If timing a segment in this window, stop the timer.
	 */
	tp->t_rtttime = 0;
	/*
	 * Close the congestion window down to one segment
	 * (we'll open it by one segment for each ack we get).
	 * Since we probably have a window's worth of unacked
	 * data accumulated, this "slow start" keeps us from
	 * dumping all that data as back-to-back packets (which
	 * might overwhelm an intermediate gateway).
	 *
	 * There are two phases to the opening: Initially we
	 * open by one mss on each ack.  This makes the window
	 * size increase exponentially with time.  If the
	 * window is larger than the path can handle, this
	 * exponential growth results in dropped packet(s)
	 * almost immediately.  To get more time between
	 * drops but still "push" the network to take advantage
	 * of improving conditions, we switch from exponential
	 * to linear window opening at some threshhold size.
	 * For a threshhold, we use half the current window
	 * size, truncated to a multiple of the mss.
	 *
	 * (the minimum cwnd that will give us exponential
	 * growth is 2 mss.  We don't allow the threshhold
	 * to go below this.)
	 */
	{
		u_int win = min(tp->snd_wnd, tp->snd_cwnd) / 2 / tp->t_maxseg;
		if (win < 2)
			win = 2;
		tp->snd_cwnd = tp->t_maxseg;
		tp->snd_ssthresh = win * tp->t_maxseg;
		tp->t_dupacks = 0;
	}
	EXIT_FASTRECOVERY(tp);
	tp->t_bytes_acked = 0;
	(void) tcp_output(tp);

out:
#ifdef TCPDEBUG
	if (tp != NULL && (tp->t_inpcb->inp_socket->so_options & SO_DEBUG))
		tcp_trace(TA_USER, ostate, tp, (void *)0, (struct tcphdr *)0,
			  PRU_SLOWTIMO);
#endif
	if (tp != NULL)
		INP_WUNLOCK(inp);
	if (headlocked)
		INP_INFO_WUNLOCK(&V_tcbinfo);
	CURVNET_RESTORE();
}

void
tcp_timer_activate(struct tcpcb *tp, int timer_type, u_int delta)
{
	struct callout *t_callout;
	void *f_callout;

	switch (timer_type) {
		case TT_DELACK:
			t_callout = &tp->t_timers->tt_delack;
			f_callout = tcp_timer_delack;
			break;
		case TT_REXMT:
			t_callout = &tp->t_timers->tt_rexmt;
			f_callout = tcp_timer_rexmt;
			break;
		case TT_PERSIST:
			t_callout = &tp->t_timers->tt_persist;
			f_callout = tcp_timer_persist;
			break;
		case TT_KEEP:
			t_callout = &tp->t_timers->tt_keep;
			f_callout = tcp_timer_keep;
			break;
		case TT_2MSL:
			t_callout = &tp->t_timers->tt_2msl;
			f_callout = tcp_timer_2msl;
			break;
		default:
			panic("bad timer_type");
		}
	if (delta == 0) {
		callout_stop(t_callout);
	} else {
		callout_reset(t_callout, delta, f_callout, tp);
	}
}

int
tcp_timer_active(struct tcpcb *tp, int timer_type)
{
	struct callout *t_callout;

	switch (timer_type) {
		case TT_DELACK:
			t_callout = &tp->t_timers->tt_delack;
			break;
		case TT_REXMT:
			t_callout = &tp->t_timers->tt_rexmt;
			break;
		case TT_PERSIST:
			t_callout = &tp->t_timers->tt_persist;
			break;
		case TT_KEEP:
			t_callout = &tp->t_timers->tt_keep;
			break;
		case TT_2MSL:
			t_callout = &tp->t_timers->tt_2msl;
			break;
		default:
			panic("bad timer_type");
		}
	return callout_active(t_callout);
}

#define	ticks_to_msecs(t)	(1000*(t) / hz)

void
tcp_timer_to_xtimer(struct tcpcb *tp, struct tcp_timer *timer, struct xtcp_timer *xtimer)
{
	bzero(xtimer, sizeof(struct xtcp_timer));
	if (timer == NULL)
		return;
	if (callout_active(&timer->tt_delack))
		xtimer->tt_delack = ticks_to_msecs(timer->tt_delack.c_time - ticks);
	if (callout_active(&timer->tt_rexmt))
		xtimer->tt_rexmt = ticks_to_msecs(timer->tt_rexmt.c_time - ticks);
	if (callout_active(&timer->tt_persist))
		xtimer->tt_persist = ticks_to_msecs(timer->tt_persist.c_time - ticks);
	if (callout_active(&timer->tt_keep))
		xtimer->tt_keep = ticks_to_msecs(timer->tt_keep.c_time - ticks);
	if (callout_active(&timer->tt_2msl))
		xtimer->tt_2msl = ticks_to_msecs(timer->tt_2msl.c_time - ticks);
	xtimer->t_rcvtime = ticks_to_msecs(ticks - tp->t_rcvtime);
}
OpenPOWER on IntegriCloud