summaryrefslogtreecommitdiff
path: root/sys/netinet/tcp_usrreq.c
blob: ea92e00c85801911f0e70dc9037c63b3c0651d4f (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
/*	$OpenBSD: tcp_usrreq.c,v 1.13 1998/01/03 22:32:53 deraadt Exp $	*/
/*	$NetBSD: tcp_usrreq.c,v 1.20 1996/02/13 23:44:16 christos Exp $	*/

/*
 * Copyright (c) 1982, 1986, 1988, 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. 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_usrreq.c	8.2 (Berkeley) 1/3/94
 */

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/protosw.h>
#include <sys/errno.h>
#include <sys/stat.h>
#include <sys/proc.h>
#include <sys/ucred.h>
#include <vm/vm.h>
#include <sys/sysctl.h>

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

#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.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>
#include <netinet/tcp_debug.h>
#include <dev/rndvar.h>

/*
 * TCP protocol interface to socket abstraction.
 */
extern	char *tcpstates[];
extern	int tcptv_keep_init;

/* from in_pcb.c */
extern	struct baddynamicports baddynamicports;

/*
 * Process a TCP user request for TCP tb.  If this is a send request
 * then m is the mbuf chain of send data.  If this is a timer expiration
 * (called from the software clock routine), then timertype tells which timer.
 */
/*ARGSUSED*/
int
tcp_usrreq(so, req, m, nam, control)
	struct socket *so;
	int req;
	struct mbuf *m, *nam, *control;
{
	register struct inpcb *inp;
	register struct tcpcb *tp = NULL;
	int s;
	int error = 0;
	int ostate;

	if (req == PRU_CONTROL)
		return (in_control(so, (u_long)m, (caddr_t)nam,
			(struct ifnet *)control));
	if (control && control->m_len) {
		m_freem(control);
		if (m)
			m_freem(m);
		return (EINVAL);
	}

	s = splsoftnet();
	inp = sotoinpcb(so);
	/*
	 * When a TCP is attached to a socket, then there will be
	 * a (struct inpcb) pointed at by the socket, and this
	 * structure will point at a subsidary (struct tcpcb).
	 */
	if (inp == 0 && req != PRU_ATTACH) {
		splx(s);
		/*
		 * The following corrects an mbuf leak under rare
		 * circumstances
		 */
		if (m && (req == PRU_SEND || req == PRU_SENDOOB))
			m_freem(m);
		return (EINVAL);		/* XXX */
	}
	if (inp) {
		tp = intotcpcb(inp);
		/* WHAT IF TP IS 0? */
#ifdef KPROF
		tcp_acounts[tp->t_state][req]++;
#endif
		ostate = tp->t_state;
	} else
		ostate = 0;
	switch (req) {

	/*
	 * TCP attaches to socket via PRU_ATTACH, reserving space,
	 * and an internet control block.
	 */
	case PRU_ATTACH:
		if (inp) {
			error = EISCONN;
			break;
		}
		error = tcp_attach(so);
		if (error)
			break;
		if ((so->so_options & SO_LINGER) && so->so_linger == 0)
			so->so_linger = TCP_LINGERTIME * hz;
		tp = sototcpcb(so);
		break;

	/*
	 * PRU_DETACH detaches the TCP protocol from the socket.
	 * If the protocol state is non-embryonic, then can't
	 * do this directly: have to initiate a PRU_DISCONNECT,
	 * which may finish later; embryonic TCB's can just
	 * be discarded here.
	 */
	case PRU_DETACH:
		tp = tcp_disconnect(tp);
		break;

	/*
	 * Give the socket an address.
	 */
	case PRU_BIND:
		error = in_pcbbind(inp, nam);
		if (error)
			break;
		break;

	/*
	 * Prepare to accept connections.
	 */
	case PRU_LISTEN:
		if (inp->inp_lport == 0)
			error = in_pcbbind(inp, (struct mbuf *)0);
		if (error == 0)
			tp->t_state = TCPS_LISTEN;
		break;

	/*
	 * Initiate connection to peer.
	 * Create a template for use in transmissions on this connection.
	 * Enter SYN_SENT state, and mark socket as connecting.
	 * Start keep-alive timer, and seed output sequence space.
	 * Send initial segment on connection.
	 */
	case PRU_CONNECT:
		if (inp->inp_lport == 0) {
			error = in_pcbbind(inp, (struct mbuf *)0);
			if (error)
				break;
		}
		error = in_pcbconnect(inp, nam);
		if (error)
			break;
		tp->t_template = tcp_template(tp);
		if (tp->t_template == 0) {
			in_pcbdisconnect(inp);
			error = ENOBUFS;
			break;
		}
		so->so_state |= SS_CONNECTOUT;
		/* Compute window scaling to request.  */
		while (tp->request_r_scale < TCP_MAX_WINSHIFT &&
		    (TCP_MAXWIN << tp->request_r_scale) < so->so_rcv.sb_hiwat)
			tp->request_r_scale++;
		soisconnecting(so);
		tcpstat.tcps_connattempt++;
		tp->t_state = TCPS_SYN_SENT;
		tp->t_timer[TCPT_KEEP] = tcptv_keep_init;
		tp->iss = tcp_iss;
#ifdef TCP_COMPAT_42
		tcp_iss += TCP_ISSINCR/2;
#else /* TCP_COMPAT_42 */
		tcp_iss += arc4random() % (TCP_ISSINCR / 2) + 1;
#endif /* !TCP_COMPAT_42 */
		tcp_sendseqinit(tp);
		error = tcp_output(tp);
		break;

	/*
	 * Create a TCP connection between two sockets.
	 */
	case PRU_CONNECT2:
		error = EOPNOTSUPP;
		break;

	/*
	 * Initiate disconnect from peer.
	 * If connection never passed embryonic stage, just drop;
	 * else if don't need to let data drain, then can just drop anyways,
	 * else have to begin TCP shutdown process: mark socket disconnecting,
	 * drain unread data, state switch to reflect user close, and
	 * send segment (e.g. FIN) to peer.  Socket will be really disconnected
	 * when peer sends FIN and acks ours.
	 *
	 * SHOULD IMPLEMENT LATER PRU_CONNECT VIA REALLOC TCPCB.
	 */
	case PRU_DISCONNECT:
		tp = tcp_disconnect(tp);
		break;

	/*
	 * Accept a connection.  Essentially all the work is
	 * done at higher levels; just return the address
	 * of the peer, storing through addr.
	 */
	case PRU_ACCEPT:
		in_setpeeraddr(inp, nam);
		break;

	/*
	 * Mark the connection as being incapable of further output.
	 */
	case PRU_SHUTDOWN:
		if (so->so_state & SS_CANTSENDMORE)
			break;
		socantsendmore(so);
		tp = tcp_usrclosed(tp);
		if (tp)
			error = tcp_output(tp);
		break;

	/*
	 * After a receive, possibly send window update to peer.
	 */
	case PRU_RCVD:
		(void) tcp_output(tp);
		break;

	/*
	 * Do a send by putting data in output queue and updating urgent
	 * marker if URG set.  Possibly send more data.
	 */
	case PRU_SEND:
		sbappend(&so->so_snd, m);
		error = tcp_output(tp);
		break;

	/*
	 * Abort the TCP.
	 */
	case PRU_ABORT:
		tp = tcp_drop(tp, ECONNABORTED);
		break;

	case PRU_SENSE:
		((struct stat *) m)->st_blksize = so->so_snd.sb_hiwat;
		(void) splx(s);
		return (0);

	case PRU_RCVOOB:
		if ((so->so_oobmark == 0 &&
		    (so->so_state & SS_RCVATMARK) == 0) ||
		    so->so_options & SO_OOBINLINE ||
		    tp->t_oobflags & TCPOOB_HADDATA) {
			error = EINVAL;
			break;
		}
		if ((tp->t_oobflags & TCPOOB_HAVEDATA) == 0) {
			error = EWOULDBLOCK;
			break;
		}
		m->m_len = 1;
		*mtod(m, caddr_t) = tp->t_iobc;
		if (((long)nam & MSG_PEEK) == 0)
			tp->t_oobflags ^= (TCPOOB_HAVEDATA | TCPOOB_HADDATA);
		break;

	case PRU_SENDOOB:
		if (sbspace(&so->so_snd) < -512) {
			m_freem(m);
			error = ENOBUFS;
			break;
		}
		/*
		 * According to RFC961 (Assigned Protocols),
		 * the urgent pointer points to the last octet
		 * of urgent data.  We continue, however,
		 * to consider it to indicate the first octet
		 * of data past the urgent section.
		 * Otherwise, snd_up should be one lower.
		 */
		sbappend(&so->so_snd, m);
		tp->snd_up = tp->snd_una + so->so_snd.sb_cc;
		tp->t_force = 1;
		error = tcp_output(tp);
		tp->t_force = 0;
		break;

	case PRU_SOCKADDR:
		in_setsockaddr(inp, nam);
		break;

	case PRU_PEERADDR:
		in_setpeeraddr(inp, nam);
		break;

	/*
	 * TCP slow timer went off; going through this
	 * routine for tracing's sake.
	 */
	case PRU_SLOWTIMO:
		tp = tcp_timers(tp, (long)nam);
		req |= (long)nam << 8;		/* for debug's sake */
		break;

	default:
		panic("tcp_usrreq");
	}
	if (tp && (so->so_options & SO_DEBUG))
		tcp_trace(TA_USER, ostate, tp, (struct tcpiphdr *)0, req);
	splx(s);
	return (error);
}

int
tcp_ctloutput(op, so, level, optname, mp)
	int op;
	struct socket *so;
	int level, optname;
	struct mbuf **mp;
{
	int error = 0, s;
	struct inpcb *inp;
	register struct tcpcb *tp;
	register struct mbuf *m;
	register int i;

	s = splsoftnet();
	inp = sotoinpcb(so);
	if (inp == NULL) {
		splx(s);
		if (op == PRCO_SETOPT && *mp)
			(void) m_free(*mp);
		return (ECONNRESET);
	}
	if (level != IPPROTO_TCP) {
		error = ip_ctloutput(op, so, level, optname, mp);
		splx(s);
		return (error);
	}
	tp = intotcpcb(inp);

	switch (op) {

	case PRCO_SETOPT:
		m = *mp;
		switch (optname) {

		case TCP_NODELAY:
			if (m == NULL || m->m_len < sizeof (int))
				error = EINVAL;
			else if (*mtod(m, int *))
				tp->t_flags |= TF_NODELAY;
			else
				tp->t_flags &= ~TF_NODELAY;
			break;

		case TCP_MAXSEG:
			if (m && (i = *mtod(m, int *)) > 0 && i <= tp->t_maxseg)
				tp->t_maxseg = i;
			else
				error = EINVAL;
			break;

		default:
			error = ENOPROTOOPT;
			break;
		}
		if (m)
			(void) m_free(m);
		break;

	case PRCO_GETOPT:
		*mp = m = m_get(M_WAIT, MT_SOOPTS);
		m->m_len = sizeof(int);

		switch (optname) {
		case TCP_NODELAY:
			*mtod(m, int *) = tp->t_flags & TF_NODELAY;
			break;
		case TCP_MAXSEG:
			*mtod(m, int *) = tp->t_maxseg;
			break;
		default:
			error = ENOPROTOOPT;
			break;
		}
		break;
	}
	splx(s);
	return (error);
}

#ifndef TCP_SENDSPACE
#define	TCP_SENDSPACE	1024*16;
#endif
u_long	tcp_sendspace = TCP_SENDSPACE;
#ifndef TCP_RECVSPACE
#define	TCP_RECVSPACE	1024*16;
#endif
u_long	tcp_recvspace = TCP_RECVSPACE;

/*
 * Attach TCP protocol to socket, allocating
 * internet protocol control block, tcp control block,
 * bufer space, and entering LISTEN state if to accept connections.
 */
int
tcp_attach(so)
	struct socket *so;
{
	register struct tcpcb *tp;
	struct inpcb *inp;
	int error;

	if (so->so_snd.sb_hiwat == 0 || so->so_rcv.sb_hiwat == 0) {
		error = soreserve(so, tcp_sendspace, tcp_recvspace);
		if (error)
			return (error);
	}
	error = in_pcballoc(so, &tcbtable);
	if (error)
		return (error);
	inp = sotoinpcb(so);
	tp = tcp_newtcpcb(inp);
	if (tp == 0) {
		int nofd = so->so_state & SS_NOFDREF;	/* XXX */

		so->so_state &= ~SS_NOFDREF;	/* don't free the socket yet */
		in_pcbdetach(inp);
		so->so_state |= nofd;
		return (ENOBUFS);
	}
	tp->t_state = TCPS_CLOSED;
	return (0);
}

/*
 * Initiate (or continue) disconnect.
 * If embryonic state, just send reset (once).
 * If in ``let data drain'' option and linger null, just drop.
 * Otherwise (hard), mark socket disconnecting and drop
 * current input data; switch states based on user close, and
 * send segment to peer (with FIN).
 */
struct tcpcb *
tcp_disconnect(tp)
	register struct tcpcb *tp;
{
	struct socket *so = tp->t_inpcb->inp_socket;

	if (TCPS_HAVEESTABLISHED(tp->t_state) == 0)
		tp = tcp_close(tp);
	else if ((so->so_options & SO_LINGER) && so->so_linger == 0)
		tp = tcp_drop(tp, 0);
	else {
		soisdisconnecting(so);
		sbflush(&so->so_rcv);
		tp = tcp_usrclosed(tp);
		if (tp)
			(void) tcp_output(tp);
	}
	return (tp);
}

/*
 * User issued close, and wish to trail through shutdown states:
 * if never received SYN, just forget it.  If got a SYN from peer,
 * but haven't sent FIN, then go to FIN_WAIT_1 state to send peer a FIN.
 * If already got a FIN from peer, then almost done; go to LAST_ACK
 * state.  In all other cases, have already sent FIN to peer (e.g.
 * after PRU_SHUTDOWN), and just have to play tedious game waiting
 * for peer to send FIN or not respond to keep-alives, etc.
 * We can let the user exit from the close as soon as the FIN is acked.
 */
struct tcpcb *
tcp_usrclosed(tp)
	register struct tcpcb *tp;
{

	switch (tp->t_state) {

	case TCPS_CLOSED:
	case TCPS_LISTEN:
	case TCPS_SYN_SENT:
		tp->t_state = TCPS_CLOSED;
		tp = tcp_close(tp);
		break;

	case TCPS_SYN_RECEIVED:
	case TCPS_ESTABLISHED:
		tp->t_state = TCPS_FIN_WAIT_1;
		break;

	case TCPS_CLOSE_WAIT:
		tp->t_state = TCPS_LAST_ACK;
		break;
	}
	if (tp && tp->t_state >= TCPS_FIN_WAIT_2) {
		soisdisconnected(tp->t_inpcb->inp_socket);
		/*
		 * If we are in FIN_WAIT_2, we arrived here because the
		 * application did a shutdown of the send side.  Like the
		 * case of a transition from FIN_WAIT_1 to FIN_WAIT_2 after
		 * a full close, we start a timer to make sure sockets are
		 * not left in FIN_WAIT_2 forever.
		 */
		if (tp->t_state == TCPS_FIN_WAIT_2)
			tp->t_timer[TCPT_2MSL] = tcp_maxidle;
	}
	return (tp);
}

/*
 * Sysctl for tcp variables.
 */
int
tcp_sysctl(name, namelen, oldp, oldlenp, newp, newlen)
	int *name;
	u_int namelen;
	void *oldp;
	size_t *oldlenp;
	void *newp;
	size_t newlen;
{

	/* All sysctl names at this level are terminal. */
	if (namelen != 1)
		return (ENOTDIR);

	switch (name[0]) {
	case TCPCTL_RFC1323:
		return (sysctl_int(oldp, oldlenp, newp, newlen,
		    &tcp_do_rfc1323));
	case TCPCTL_KEEPINITTIME:
		return (sysctl_int(oldp, oldlenp, newp, newlen,
		    &tcptv_keep_init));

	case TCPCTL_KEEPIDLE:
		return (sysctl_int(oldp, oldlenp, newp, newlen,
		    &tcp_keepidle));

	case TCPCTL_KEEPINTVL:
		return (sysctl_int(oldp, oldlenp, newp, newlen,
		    &tcp_keepintvl));

	case TCPCTL_SLOWHZ:
		return (sysctl_rdint(oldp, oldlenp, newp, PR_SLOWHZ));

	case TCPCTL_BADDYNAMIC:
		return (sysctl_struct(oldp, oldlenp, newp, newlen,
		    baddynamicports.tcp, sizeof(baddynamicports.tcp)));

	default:
		return (ENOPROTOOPT);
	}
	/* NOTREACHED */
}