summaryrefslogtreecommitdiff
path: root/slirp/tcp_output.c
blob: 819db27348b64fda5790fa08011b31f33121b67d (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
/*
 * Copyright (c) 1982, 1986, 1988, 1990, 1993
 *	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. 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_output.c	8.3 (Berkeley) 12/30/93
 * tcp_output.c,v 1.3 1994/09/15 10:36:55 davidg Exp
 */

/*
 * Changes and additions relating to SLiRP
 * Copyright (c) 1995 Danny Gasparovski.
 *
 * Please read the file COPYRIGHT for the
 * terms and conditions of the copyright.
 */

#include "qemu/osdep.h"
#include "slirp.h"

static const u_char  tcp_outflags[TCP_NSTATES] = {
	TH_RST|TH_ACK, 0,      TH_SYN,        TH_SYN|TH_ACK,
	TH_ACK,        TH_ACK, TH_FIN|TH_ACK, TH_FIN|TH_ACK,
	TH_FIN|TH_ACK, TH_ACK, TH_ACK,
};


#undef MAX_TCPOPTLEN
#define MAX_TCPOPTLEN	32	/* max # bytes that go in options */

/*
 * Tcp output routine: figure out what should be sent and send it.
 */
int
tcp_output(struct tcpcb *tp)
{
	register struct socket *so = tp->t_socket;
	register long len, win;
	int off, flags, error;
	register struct mbuf *m;
	register struct tcpiphdr *ti, tcpiph_save;
	struct ip *ip;
	struct ip6 *ip6;
	u_char opt[MAX_TCPOPTLEN];
	unsigned optlen, hdrlen;
	int idle, sendalot;

	DEBUG_CALL("tcp_output");
	DEBUG_ARG("tp = %p", tp);

	/*
	 * Determine length of data that should be transmitted,
	 * and flags that will be used.
	 * If there is some data or critical controls (SYN, RST)
	 * to send, then transmit; otherwise, investigate further.
	 */
	idle = (tp->snd_max == tp->snd_una);
	if (idle && tp->t_idle >= tp->t_rxtcur)
		/*
		 * We have been idle for "a while" and no acks are
		 * expected to clock out any data we send --
		 * slow start to get ack "clock" running again.
		 */
		tp->snd_cwnd = tp->t_maxseg;
again:
	sendalot = 0;
	off = tp->snd_nxt - tp->snd_una;
	win = min(tp->snd_wnd, tp->snd_cwnd);

	flags = tcp_outflags[tp->t_state];

	DEBUG_MISC((dfd, " --- tcp_output flags = 0x%x\n",flags));

	/*
	 * If in persist timeout with window of 0, send 1 byte.
	 * Otherwise, if window is small but nonzero
	 * and timer expired, we will send what we can
	 * and go to transmit state.
	 */
	if (tp->t_force) {
		if (win == 0) {
			/*
			 * If we still have some data to send, then
			 * clear the FIN bit.  Usually this would
			 * happen below when it realizes that we
			 * aren't sending all the data.  However,
			 * if we have exactly 1 byte of unset data,
			 * then it won't clear the FIN bit below,
			 * and if we are in persist state, we wind
			 * up sending the packet without recording
			 * that we sent the FIN bit.
			 *
			 * We can't just blindly clear the FIN bit,
			 * because if we don't have any more data
			 * to send then the probe will be the FIN
			 * itself.
			 */
			if (off < so->so_snd.sb_cc)
				flags &= ~TH_FIN;
			win = 1;
		} else {
			tp->t_timer[TCPT_PERSIST] = 0;
			tp->t_rxtshift = 0;
		}
	}

	len = min(so->so_snd.sb_cc, win) - off;

	if (len < 0) {
		/*
		 * If FIN has been sent but not acked,
		 * but we haven't been called to retransmit,
		 * len will be -1.  Otherwise, window shrank
		 * after we sent into it.  If window shrank to 0,
		 * cancel pending retransmit and pull snd_nxt
		 * back to (closed) window.  We will enter persist
		 * state below.  If the window didn't close completely,
		 * just wait for an ACK.
		 */
		len = 0;
		if (win == 0) {
			tp->t_timer[TCPT_REXMT] = 0;
			tp->snd_nxt = tp->snd_una;
		}
	}

	if (len > tp->t_maxseg) {
		len = tp->t_maxseg;
		sendalot = 1;
	}
	if (SEQ_LT(tp->snd_nxt + len, tp->snd_una + so->so_snd.sb_cc))
		flags &= ~TH_FIN;

	win = sbspace(&so->so_rcv);

	/*
	 * Sender silly window avoidance.  If connection is idle
	 * and can send all data, a maximum segment,
	 * at least a maximum default-size segment do it,
	 * or are forced, do it; otherwise don't bother.
	 * If peer's buffer is tiny, then send
	 * when window is at least half open.
	 * If retransmitting (possibly after persist timer forced us
	 * to send into a small window), then must resend.
	 */
	if (len) {
		if (len == tp->t_maxseg)
			goto send;
		if ((1 || idle || tp->t_flags & TF_NODELAY) &&
		    len + off >= so->so_snd.sb_cc)
			goto send;
		if (tp->t_force)
			goto send;
		if (len >= tp->max_sndwnd / 2 && tp->max_sndwnd > 0)
			goto send;
		if (SEQ_LT(tp->snd_nxt, tp->snd_max))
			goto send;
	}

	/*
	 * Compare available window to amount of window
	 * known to peer (as advertised window less
	 * next expected input).  If the difference is at least two
	 * max size segments, or at least 50% of the maximum possible
	 * window, then want to send a window update to peer.
	 */
	if (win > 0) {
		/*
		 * "adv" is the amount we can increase the window,
		 * taking into account that we are limited by
		 * TCP_MAXWIN << tp->rcv_scale.
		 */
		long adv = min(win, (long)TCP_MAXWIN << tp->rcv_scale) -
			(tp->rcv_adv - tp->rcv_nxt);

		if (adv >= (long) (2 * tp->t_maxseg))
			goto send;
		if (2 * adv >= (long) so->so_rcv.sb_datalen)
			goto send;
	}

	/*
	 * Send if we owe peer an ACK.
	 */
	if (tp->t_flags & TF_ACKNOW)
		goto send;
	if (flags & (TH_SYN|TH_RST))
		goto send;
	if (SEQ_GT(tp->snd_up, tp->snd_una))
		goto send;
	/*
	 * If our state indicates that FIN should be sent
	 * and we have not yet done so, or we're retransmitting the FIN,
	 * then we need to send.
	 */
	if (flags & TH_FIN &&
	    ((tp->t_flags & TF_SENTFIN) == 0 || tp->snd_nxt == tp->snd_una))
		goto send;

	/*
	 * TCP window updates are not reliable, rather a polling protocol
	 * using ``persist'' packets is used to insure receipt of window
	 * updates.  The three ``states'' for the output side are:
	 *	idle			not doing retransmits or persists
	 *	persisting		to move a small or zero window
	 *	(re)transmitting	and thereby not persisting
	 *
	 * tp->t_timer[TCPT_PERSIST]
	 *	is set when we are in persist state.
	 * tp->t_force
	 *	is set when we are called to send a persist packet.
	 * tp->t_timer[TCPT_REXMT]
	 *	is set when we are retransmitting
	 * The output side is idle when both timers are zero.
	 *
	 * If send window is too small, there is data to transmit, and no
	 * retransmit or persist is pending, then go to persist state.
	 * If nothing happens soon, send when timer expires:
	 * if window is nonzero, transmit what we can,
	 * otherwise force out a byte.
	 */
	if (so->so_snd.sb_cc && tp->t_timer[TCPT_REXMT] == 0 &&
	    tp->t_timer[TCPT_PERSIST] == 0) {
		tp->t_rxtshift = 0;
		tcp_setpersist(tp);
	}

	/*
	 * No reason to send a segment, just return.
	 */
	return (0);

send:
	/*
	 * Before ESTABLISHED, force sending of initial options
	 * unless TCP set not to do any options.
	 * NOTE: we assume that the IP/TCP header plus TCP options
	 * always fit in a single mbuf, leaving room for a maximum
	 * link header, i.e.
	 *	max_linkhdr + sizeof (struct tcpiphdr) + optlen <= MHLEN
	 */
	optlen = 0;
	hdrlen = sizeof (struct tcpiphdr);
	if (flags & TH_SYN) {
		tp->snd_nxt = tp->iss;
		if ((tp->t_flags & TF_NOOPT) == 0) {
			uint16_t mss;

			opt[0] = TCPOPT_MAXSEG;
			opt[1] = 4;
			mss = htons((uint16_t) tcp_mss(tp, 0));
			memcpy((caddr_t)(opt + 2), (caddr_t)&mss, sizeof(mss));
			optlen = 4;
		}
 	}

 	hdrlen += optlen;

	/*
	 * Adjust data length if insertion of options will
	 * bump the packet length beyond the t_maxseg length.
	 */
	 if (len > tp->t_maxseg - optlen) {
		len = tp->t_maxseg - optlen;
		sendalot = 1;
	 }

	/*
	 * Grab a header mbuf, attaching a copy of data to
	 * be transmitted, and initialize the header from
	 * the template for sends on this connection.
	 */
	if (len) {
		m = m_get(so->slirp);
		if (m == NULL) {
			error = 1;
			goto out;
		}
		m->m_data += IF_MAXLINKHDR;
		m->m_len = hdrlen;

		sbcopy(&so->so_snd, off, (int) len, mtod(m, caddr_t) + hdrlen);
		m->m_len += len;

		/*
		 * If we're sending everything we've got, set PUSH.
		 * (This will keep happy those implementations which only
		 * give data to the user when a buffer fills or
		 * a PUSH comes in.)
		 */
		if (off + len == so->so_snd.sb_cc)
			flags |= TH_PUSH;
	} else {
		m = m_get(so->slirp);
		if (m == NULL) {
			error = 1;
			goto out;
		}
		m->m_data += IF_MAXLINKHDR;
		m->m_len = hdrlen;
	}

	ti = mtod(m, struct tcpiphdr *);

	memcpy((caddr_t)ti, &tp->t_template, sizeof (struct tcpiphdr));

	/*
	 * Fill in fields, remembering maximum advertised
	 * window for use in delaying messages about window sizes.
	 * If resending a FIN, be sure not to use a new sequence number.
	 */
	if (flags & TH_FIN && tp->t_flags & TF_SENTFIN &&
	    tp->snd_nxt == tp->snd_max)
		tp->snd_nxt--;
	/*
	 * If we are doing retransmissions, then snd_nxt will
	 * not reflect the first unsent octet.  For ACK only
	 * packets, we do not want the sequence number of the
	 * retransmitted packet, we want the sequence number
	 * of the next unsent octet.  So, if there is no data
	 * (and no SYN or FIN), use snd_max instead of snd_nxt
	 * when filling in ti_seq.  But if we are in persist
	 * state, snd_max might reflect one byte beyond the
	 * right edge of the window, so use snd_nxt in that
	 * case, since we know we aren't doing a retransmission.
	 * (retransmit and persist are mutually exclusive...)
	 */
	if (len || (flags & (TH_SYN|TH_FIN)) || tp->t_timer[TCPT_PERSIST])
		ti->ti_seq = htonl(tp->snd_nxt);
	else
		ti->ti_seq = htonl(tp->snd_max);
	ti->ti_ack = htonl(tp->rcv_nxt);
	if (optlen) {
		memcpy((caddr_t)(ti + 1), (caddr_t)opt, optlen);
		ti->ti_off = (sizeof (struct tcphdr) + optlen) >> 2;
	}
	ti->ti_flags = flags;
	/*
	 * Calculate receive window.  Don't shrink window,
	 * but avoid silly window syndrome.
	 */
	if (win < (long)(so->so_rcv.sb_datalen / 4) && win < (long)tp->t_maxseg)
		win = 0;
	if (win > (long)TCP_MAXWIN << tp->rcv_scale)
		win = (long)TCP_MAXWIN << tp->rcv_scale;
	if (win < (long)(tp->rcv_adv - tp->rcv_nxt))
		win = (long)(tp->rcv_adv - tp->rcv_nxt);
	ti->ti_win = htons((uint16_t) (win>>tp->rcv_scale));

	if (SEQ_GT(tp->snd_up, tp->snd_una)) {
		ti->ti_urp = htons((uint16_t)(tp->snd_up - ntohl(ti->ti_seq)));
		ti->ti_flags |= TH_URG;
	} else
		/*
		 * If no urgent pointer to send, then we pull
		 * the urgent pointer to the left edge of the send window
		 * so that it doesn't drift into the send window on sequence
		 * number wraparound.
		 */
		tp->snd_up = tp->snd_una;		/* drag it along */

	/*
	 * Put TCP length in extended header, and then
	 * checksum extended header and data.
	 */
	if (len + optlen)
		ti->ti_len = htons((uint16_t)(sizeof (struct tcphdr) +
		    optlen + len));
	ti->ti_sum = cksum(m, (int)(hdrlen + len));

	/*
	 * In transmit state, time the transmission and arrange for
	 * the retransmit.  In persist state, just set snd_max.
	 */
	if (tp->t_force == 0 || tp->t_timer[TCPT_PERSIST] == 0) {
		tcp_seq startseq = tp->snd_nxt;

		/*
		 * Advance snd_nxt over sequence space of this segment.
		 */
		if (flags & (TH_SYN|TH_FIN)) {
			if (flags & TH_SYN)
				tp->snd_nxt++;
			if (flags & TH_FIN) {
				tp->snd_nxt++;
				tp->t_flags |= TF_SENTFIN;
			}
		}
		tp->snd_nxt += len;
		if (SEQ_GT(tp->snd_nxt, tp->snd_max)) {
			tp->snd_max = tp->snd_nxt;
			/*
			 * Time this transmission if not a retransmission and
			 * not currently timing anything.
			 */
			if (tp->t_rtt == 0) {
				tp->t_rtt = 1;
				tp->t_rtseq = startseq;
			}
		}

		/*
		 * Set retransmit timer if not currently set,
		 * and not doing an ack or a keep-alive probe.
		 * Initial value for retransmit timer is smoothed
		 * round-trip time + 2 * round-trip time variance.
		 * Initialize shift counter which is used for backoff
		 * of retransmit time.
		 */
		if (tp->t_timer[TCPT_REXMT] == 0 &&
		    tp->snd_nxt != tp->snd_una) {
			tp->t_timer[TCPT_REXMT] = tp->t_rxtcur;
			if (tp->t_timer[TCPT_PERSIST]) {
				tp->t_timer[TCPT_PERSIST] = 0;
				tp->t_rxtshift = 0;
			}
		}
	} else
		if (SEQ_GT(tp->snd_nxt + len, tp->snd_max))
			tp->snd_max = tp->snd_nxt + len;

	/*
	 * Fill in IP length and desired time to live and
	 * send to IP level.  There should be a better way
	 * to handle ttl and tos; we could keep them in
	 * the template, but need a way to checksum without them.
	 */
	m->m_len = hdrlen + len; /* XXX Needed? m_len should be correct */
	tcpiph_save = *mtod(m, struct tcpiphdr *);

	switch (so->so_ffamily) {
	case AF_INET:
	    m->m_data += sizeof(struct tcpiphdr) - sizeof(struct tcphdr)
	                                         - sizeof(struct ip);
	    m->m_len  -= sizeof(struct tcpiphdr) - sizeof(struct tcphdr)
	                                         - sizeof(struct ip);
	    ip = mtod(m, struct ip *);

	    ip->ip_len = m->m_len;
	    ip->ip_dst = tcpiph_save.ti_dst;
	    ip->ip_src = tcpiph_save.ti_src;
	    ip->ip_p = tcpiph_save.ti_pr;

	    ip->ip_ttl = IPDEFTTL;
	    ip->ip_tos = so->so_iptos;
	    error = ip_output(so, m);
	    break;

	case AF_INET6:
	    m->m_data += sizeof(struct tcpiphdr) - sizeof(struct tcphdr)
	                                         - sizeof(struct ip6);
	    m->m_len  -= sizeof(struct tcpiphdr) - sizeof(struct tcphdr)
	                                         - sizeof(struct ip6);
	    ip6 = mtod(m, struct ip6 *);

	    ip6->ip_pl = tcpiph_save.ti_len;
	    ip6->ip_dst = tcpiph_save.ti_dst6;
	    ip6->ip_src = tcpiph_save.ti_src6;
	    ip6->ip_nh = tcpiph_save.ti_nh6;

	    error = ip6_output(so, m, 0);
	    break;

	default:
	    g_assert_not_reached();
	}

	if (error) {
out:
		return (error);
	}

	/*
	 * Data sent (as far as we can tell).
	 * If this advertises a larger window than any other segment,
	 * then remember the size of the advertised window.
	 * Any pending ACK has now been sent.
	 */
	if (win > 0 && SEQ_GT(tp->rcv_nxt+win, tp->rcv_adv))
		tp->rcv_adv = tp->rcv_nxt + win;
	tp->last_ack_sent = tp->rcv_nxt;
	tp->t_flags &= ~(TF_ACKNOW|TF_DELACK);
	if (sendalot)
		goto again;

	return (0);
}

void
tcp_setpersist(struct tcpcb *tp)
{
    int t = ((tp->t_srtt >> 2) + tp->t_rttvar) >> 1;

	/*
	 * Start/restart persistence timer.
	 */
	TCPT_RANGESET(tp->t_timer[TCPT_PERSIST],
	    t * tcp_backoff[tp->t_rxtshift],
	    TCPTV_PERSMIN, TCPTV_PERSMAX);
	if (tp->t_rxtshift < TCP_MAXRXTSHIFT)
		tp->t_rxtshift++;
}