aboutsummaryrefslogtreecommitdiffstats
path: root/sys/netinet/tcp_timer.c
blob: 2b941cb22540b5b128d18b293b81c22f6f10b2dc (plain) (blame)
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
/*
 * 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.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 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
 * $FreeBSD$
 */

#include "opt_compat.h"
#include "opt_tcpdebug.h"

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

#include <machine/cpu.h>	/* before tcp_seq.h, for tcp_random18() */

#include <net/route.h>

#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_pcb.h>
#include <netinet/ip_var.h>
#include <netinet/tcp.h>
#include <netinet/tcp_fsm.h>
#include <netinet/tcp_seq.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 = TCPTV_KEEP_INIT;
SYSCTL_INT(_net_inet_tcp, TCPCTL_KEEPINIT, keepinit,
	CTLFLAG_RW, &tcp_keepinit , 0, "");

int	tcp_keepidle = TCPTV_KEEP_IDLE;
SYSCTL_INT(_net_inet_tcp, TCPCTL_KEEPIDLE, keepidle,
	CTLFLAG_RW, &tcp_keepidle , 0, "");

static int	tcp_keepintvl = TCPTV_KEEPINTVL;
SYSCTL_INT(_net_inet_tcp, TCPCTL_KEEPINTVL, keepintvl,
	CTLFLAG_RW, &tcp_keepintvl , 0, "");

static int	always_keepalive = 0;
SYSCTL_INT(_net_inet_tcp, OID_AUTO, always_keepalive,
	CTLFLAG_RW, &always_keepalive , 0, "");

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

/*
 * Fast timeout routine for processing delayed acks
 */
void
tcp_fasttimo()
{
	register struct inpcb *inp;
	register struct tcpcb *tp;
	int s;

	if (tcp_delack_enabled) {
		s = splnet();
		for (inp = tcb.lh_first; inp != NULL; inp = inp->inp_list.le_next) {
			if ((tp = (struct tcpcb *)inp->inp_ppcb) &&
			    (tp->t_flags & TF_DELACK)) {
				tp->t_flags &= ~TF_DELACK;
				tp->t_flags |= TF_ACKNOW;
				tcpstat.tcps_delack++;
				(void) tcp_output(tp);
			}
		}
		splx(s);
	}
}

/*
 * Tcp protocol timeout routine called every 500 ms.
 * Updates the timers in all active tcb's and
 * causes finite state machine actions if timers expire.
 */
void
tcp_slowtimo()
{
	register struct inpcb *ip, *ipnxt;
	register struct tcpcb *tp;
	register int i;
	int s;
#ifdef TCPDEBUG
	int ostate;
#endif

	s = splnet();

	tcp_maxidle = tcp_keepcnt * tcp_keepintvl;

	ip = tcb.lh_first;
	if (ip == NULL) {
		splx(s);
		return;
	}
	/*
	 * Search through tcb's and update active timers.
	 */
	for (; ip != NULL; ip = ipnxt) {
		ipnxt = ip->inp_list.le_next;
		tp = intotcpcb(ip);
		if (tp == 0 || tp->t_state == TCPS_LISTEN)
			continue;
		for (i = 0; i < TCPT_NTIMERS; i++) {
			if (tp->t_timer[i] && --tp->t_timer[i] == 0) {
#ifdef TCPDEBUG
				ostate = tp->t_state;
#endif
				tp = tcp_timers(tp, i);
				if (tp == NULL)
					goto tpgone;
#ifdef TCPDEBUG
				if (tp->t_inpcb->inp_socket->so_options
				    & SO_DEBUG)
					tcp_trace(TA_USER, ostate, tp,
						  (struct tcpiphdr *)0,
						  PRU_SLOWTIMO);
#endif
			}
		}
		tp->t_idle++;
		tp->t_duration++;
		if (tp->t_rtt)
			tp->t_rtt++;
tpgone:
		;
	}
#ifdef TCP_COMPAT_42
	tcp_iss += TCP_ISSINCR/PR_SLOWHZ;		/* increment iss */
	if ((int)tcp_iss < 0)
		tcp_iss = TCP_ISSINCR;			/* XXX */
#endif
	tcp_now++;					/* for timestamps */
	splx(s);
}

/*
 * Cancel all timers for TCP tp.
 */
void
tcp_canceltimers(tp)
	struct tcpcb *tp;
{
	register int i;

	for (i = 0; i < TCPT_NTIMERS; i++)
		tp->t_timer[i] = 0;
}

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

static int tcp_totbackoff = 511;	/* sum of tcp_backoff[] */

/*
 * TCP timer processing.
 */
struct tcpcb *
tcp_timers(tp, timer)
	register struct tcpcb *tp;
	int timer;
{
	register int rexmt;

	switch (timer) {

	/*
	 * 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.
	 */
	case TCPT_2MSL:
		if (tp->t_state != TCPS_TIME_WAIT &&
		    tp->t_idle <= tcp_maxidle)
			tp->t_timer[TCPT_2MSL] = tcp_keepintvl;
		else
			tp = tcp_close(tp);
		break;

	/*
	 * Retransmission timer went off.  Message has not
	 * been acked within retransmit interval.  Back off
	 * to a longer retransmit interval and retransmit one segment.
	 */
	case TCPT_REXMT:
		if (++tp->t_rxtshift > TCP_MAXRXTSHIFT) {
			tp->t_rxtshift = TCP_MAXRXTSHIFT;
			tcpstat.tcps_timeoutdrop++;
			tp = tcp_drop(tp, tp->t_softerror ?
			    tp->t_softerror : ETIMEDOUT);
			break;
		}
		tcpstat.tcps_rexmttimeo++;
		rexmt = TCP_REXMTVAL(tp) * tcp_backoff[tp->t_rxtshift];
		TCPT_RANGESET(tp->t_rxtcur, rexmt,
		    tp->t_rttmin, TCPTV_REXMTMAX);
		tp->t_timer[TCPT_REXMT] = tp->t_rxtcur;
		/*
		 * If losing, let the lower level know and try for
		 * a better route.  Also, 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) {
			in_losing(tp->t_inpcb);
			tp->t_rttvar += (tp->t_srtt >> TCP_RTT_SHIFT);
			tp->t_srtt = 0;
		}
		tp->snd_nxt = tp->snd_una;
		/*
		 * Force a segment to be sent.
		 */
		tp->t_flags |= TF_ACKNOW;
		/*
		 * If timing a segment in this window, stop the timer.
		 */
		tp->t_rtt = 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;
		}
		(void) tcp_output(tp);
		break;

	/*
	 * Persistance timer into zero window.
	 * Force a byte to be output, if possible.
	 */
	case TCPT_PERSIST:
		tcpstat.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 &&
		    (tp->t_idle >= tcp_maxpersistidle ||
		    tp->t_idle >= TCP_REXMTVAL(tp) * tcp_totbackoff)) {
			tcpstat.tcps_persistdrop++;
			tp = tcp_drop(tp, ETIMEDOUT);
			break;
		}
		tcp_setpersist(tp);
		tp->t_force = 1;
		(void) tcp_output(tp);
		tp->t_force = 0;
		break;

	/*
	 * Keep-alive timer went off; send something
	 * or drop connection if idle for too long.
	 */
	case TCPT_KEEP:
		tcpstat.tcps_keeptimeo++;
		if (tp->t_state < TCPS_ESTABLISHED)
			goto dropit;
		if ((always_keepalive ||
		    tp->t_inpcb->inp_socket->so_options & SO_KEEPALIVE) &&
		    tp->t_state <= TCPS_CLOSING) {
		    	if (tp->t_idle >= 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.tcps_keepprobe++;
#ifdef TCP_COMPAT_42
			/*
			 * The keepalive packet must have nonzero length
			 * to get a 4.2 host to respond.
			 */
			tcp_respond(tp, tp->t_template, (struct mbuf *)NULL,
			    tp->rcv_nxt - 1, tp->snd_una - 1, 0);
#else
			tcp_respond(tp, tp->t_template, (struct mbuf *)NULL,
			    tp->rcv_nxt, tp->snd_una - 1, 0);
#endif
			tp->t_timer[TCPT_KEEP] = tcp_keepintvl;
		} else
			tp->t_timer[TCPT_KEEP] = tcp_keepidle;
		break;
	dropit:
		tcpstat.tcps_keepdrops++;
		tp = tcp_drop(tp, ETIMEDOUT);
		break;
	}
	return (tp);
}