summaryrefslogtreecommitdiff
path: root/sys/net/if_tun.c
blob: 724cae4b2a180f51facb0bb57eb6ea92d50357f9 (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
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
/*	$OpenBSD: if_tun.c,v 1.34 2001/05/16 12:53:34 ho Exp $	*/
/*	$NetBSD: if_tun.c,v 1.24 1996/05/07 02:40:48 thorpej Exp $	*/

/*
 * Copyright (c) 1988, Julian Onions <jpo@cs.nott.ac.uk>
 * Nottingham University 1987.
 *
 * This source may be freely distributed, however I would be interested
 * in any changes that are made.
 *
 * This driver takes packets off the IP i/f and hands them up to a
 * user process to have its wicked way with. This driver has its
 * roots in a similar driver written by Phil Cockcroft (formerly) at
 * UCL. This driver is based much more on read/write/select mode of
 * operation though.
 */

/* #define	TUN_DEBUG	9 */

#include <sys/param.h>
#include <sys/kernel.h>
#include <sys/proc.h>
#include <sys/systm.h>
#include <sys/mbuf.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/ioctl.h>
#include <sys/errno.h>
#include <sys/syslog.h>
#include <sys/select.h>
#include <sys/file.h>
#include <sys/time.h>
#include <sys/device.h>
#include <sys/vnode.h>
#include <sys/signalvar.h>
#include <sys/conf.h>

#include <machine/cpu.h>

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

#ifdef INET
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
/* #include <netinet/if_ether.h> */
#endif

#ifdef NS
#include <netns/ns.h>
#include <netns/ns_if.h>
#endif

#ifdef IPX
#include <netipx/ipx.h>
#include <netipx/ipx_if.h>
#endif

#ifdef NETATALK
#include <netatalk/at.h>
#include <netatalk/at_var.h>
#endif

#ifdef ISO
#include <netiso/iso.h>
#include <netiso/iso_var.h>
#endif

#include "bpfilter.h"
#if NBPFILTER > 0
#include <net/bpf.h>
#endif

#include <net/if_tun.h>

struct tun_softc {
	struct	ifnet tun_if;		/* the interface */
	u_short	tun_flags;		/* misc flags */
	pid_t	tun_pgid;		/* the process group - if any */
	uid_t	tun_siguid;		/* uid for process that set tun_pgid */
	uid_t	tun_sigeuid;		/* euid for process that set tun_pgid */
	struct	selinfo	tun_rsel;	/* read select */
	struct	selinfo	tun_wsel;	/* write select (not used) */
};

#ifdef	TUN_DEBUG
int	tundebug = TUN_DEBUG;
#define TUNDEBUG(a)	(tundebug? printf a : 0)
#else
#define TUNDEBUG(a)	/* (tundebug? printf a : 0) */
#endif

struct tun_softc *tunctl;
int ntun;

extern int ifqmaxlen;

void	tunattach __P((int));
int	tunopen	__P((dev_t, int, int, struct proc *));
int	tunclose __P((dev_t, int, int, struct proc *));
int	tun_ioctl __P((struct ifnet *, u_long, caddr_t));
int	tun_output __P((struct ifnet *, struct mbuf *, struct sockaddr *,
		        struct rtentry *rt));
int	tunioctl __P((dev_t, u_long, caddr_t, int, struct proc *));
int	tunread	__P((dev_t, struct uio *, int));
int	tunwrite __P((dev_t, struct uio *, int));
int	tunselect __P((dev_t, int, struct proc *));


static int tuninit __P((struct tun_softc *));

void
tunattach(n)
	int n;
{
	register int i;
	struct ifnet *ifp;

	ntun = n;
	tunctl = malloc(ntun * sizeof(*tunctl), M_DEVBUF, M_WAITOK);
	bzero(tunctl, ntun * sizeof(*tunctl));
	for (i = 0; i < ntun; i++) {
		tunctl[i].tun_flags = TUN_INITED;

		ifp = &tunctl[i].tun_if;
		sprintf(ifp->if_xname, "tun%d", i);
		ifp->if_softc = &tunctl[i];
		ifp->if_mtu = TUNMTU;
		ifp->if_ioctl = tun_ioctl;
		ifp->if_output = tun_output;
		ifp->if_flags = IFF_POINTOPOINT;
		ifp->if_type  = IFT_PROPVIRTUAL;
		ifp->if_snd.ifq_maxlen = ifqmaxlen;
		ifp->if_hdrlen = sizeof(u_int32_t);
		ifp->if_collisions = 0;
		ifp->if_ierrors = 0;
		ifp->if_oerrors = 0;
		ifp->if_ipackets = 0;
		ifp->if_opackets = 0;
		ifp->if_ibytes = 0;
		ifp->if_obytes = 0;
		if_attach(ifp);
#if NBPFILTER > 0
		bpfattach(&ifp->if_bpf, ifp, DLT_LOOP, sizeof(u_int32_t));
#endif
	}
}

/*
 * tunnel open - must be superuser & the device must be
 * configured in
 */
int
tunopen(dev, flag, mode, p)
	dev_t	dev;
	int	flag, mode;
	struct proc *p;
{
	struct tun_softc *tp;
	struct ifnet	*ifp;
	register int	unit, error;

	if ((error = suser(p->p_ucred, &p->p_acflag)) != 0)
		return (error);

	if ((unit = minor(dev)) >= ntun)
		return (ENXIO);

	tp = &tunctl[unit];
	if (tp->tun_flags & TUN_OPEN)
		return EBUSY;

	ifp = &tp->tun_if;
	tp->tun_flags |= TUN_OPEN;
	TUNDEBUG(("%s: open\n", ifp->if_xname));
	return (0);
}

/*
 * tunclose - close the device; if closing the real device, flush pending
 *  output and (unless set STAYUP) bring down the interface.
 */
int
tunclose(dev, flag, mode, p)
	dev_t	dev;
	int	flag;
	int	mode;
	struct proc *p;
{
	register int	unit, s;
	struct tun_softc *tp;
	struct ifnet	*ifp;
	struct mbuf	*m;

	if ((unit = minor(dev)) >= ntun)
		return (ENXIO);

	tp = &tunctl[unit];
	ifp = &tp->tun_if;
	tp->tun_flags &= ~TUN_OPEN;

	/*
	 * junk all pending output
	 */
	do {
		s = splimp();
		IF_DEQUEUE(&ifp->if_snd, m);
		splx(s);
		if (m)
			m_freem(m);
	} while (m);

	if ((ifp->if_flags & IFF_UP) && !(tp->tun_flags & TUN_STAYUP)) {
		s = splimp();
		if_down(ifp);
		if (ifp->if_flags & IFF_RUNNING) {
			/* find internet addresses and delete routes */
			register struct ifaddr *ifa;
			for (ifa = ifp->if_addrlist.tqh_first; ifa != 0;
			     ifa = ifa->ifa_list.tqe_next) {
#ifdef INET
				if (ifa->ifa_addr->sa_family == AF_INET) {
					rtinit(ifa, (int)RTM_DELETE,
					       (tp->tun_flags & TUN_DSTADDR)?
							RTF_HOST : 0);
				}
#endif
			}
		}
		splx(s);
	}
	tp->tun_pgid = 0;
	selwakeup(&tp->tun_rsel);
		
	TUNDEBUG(("%s: closed\n", ifp->if_xname));
	return (0);
}

static int
tuninit(tp)
	struct tun_softc *tp;
{
	struct ifnet	*ifp = &tp->tun_if;
	register struct ifaddr *ifa;

	TUNDEBUG(("%s: tuninit\n", ifp->if_xname));

	ifp->if_flags |= IFF_UP | IFF_RUNNING;

	tp->tun_flags &= ~(TUN_IASET|TUN_DSTADDR|TUN_BRDADDR);
	for (ifa = ifp->if_addrlist.tqh_first; ifa != 0;
	    ifa = ifa->ifa_list.tqe_next) {
#ifdef INET
		if (ifa->ifa_addr->sa_family == AF_INET) {
			struct sockaddr_in *sin;

			sin = satosin(ifa->ifa_addr);
			if (sin && sin->sin_addr.s_addr)
				tp->tun_flags |= TUN_IASET;

			if (ifp->if_flags & IFF_POINTOPOINT) {
				sin = satosin(ifa->ifa_dstaddr);
				if (sin && sin->sin_addr.s_addr)
					tp->tun_flags |= TUN_DSTADDR;
			} else
				tp->tun_flags &= ~TUN_DSTADDR;

			if (ifp->if_flags & IFF_BROADCAST) {
				sin = satosin(ifa->ifa_broadaddr);
				if (sin && sin->sin_addr.s_addr)
					tp->tun_flags |= TUN_BRDADDR;
			} else
				tp->tun_flags &= ~TUN_BRDADDR;
		}
#endif
	}

	return 0;
}

/*
 * Process an ioctl request.
 */
int
tun_ioctl(ifp, cmd, data)
	struct ifnet *ifp;
	u_long	cmd;
	caddr_t	data;
{
	int	error = 0, s;

	s = splimp();
	switch(cmd) {
	case SIOCSIFADDR:
		tuninit((struct tun_softc *)(ifp->if_softc));
		TUNDEBUG(("%s: address set\n", ifp->if_xname));
		break;
	case SIOCSIFDSTADDR:
		tuninit((struct tun_softc *)(ifp->if_softc));
		TUNDEBUG(("%s: destination address set\n", ifp->if_xname));
		break;
	case SIOCSIFBRDADDR:
		tuninit((struct tun_softc *)(ifp->if_softc));
		TUNDEBUG(("%s: broadcast address set\n", ifp->if_xname));
		break;
	case SIOCSIFMTU:
		ifp->if_mtu = ((struct ifreq *)data)->ifr_mtu;
		break;
	case SIOCSIFFLAGS:
		break;
	default:
		error = EINVAL;
	}
	splx(s);
	return (error);
}

/*
 * tun_output - queue packets from higher level ready to put out.
 */
int
tun_output(ifp, m0, dst, rt)
	struct ifnet   *ifp;
	struct mbuf    *m0;
	struct sockaddr *dst;
	struct rtentry *rt;
{
	struct tun_softc *tp = ifp->if_softc;
	int		s;
	u_int32_t	*af;

	TUNDEBUG(("%s: tun_output\n", ifp->if_xname));

	if ((tp->tun_flags & TUN_READY) != TUN_READY) {
		TUNDEBUG(("%s: not ready 0%o\n", ifp->if_xname,
			  tp->tun_flags));
		m_freem (m0);
		return EHOSTDOWN;
	}
	ifp->if_lastchange = time;


	M_PREPEND(m0, sizeof(*af), M_DONTWAIT);
	af = mtod(m0, u_int32_t *);
	*af = htonl(dst->sa_family);

#if NBPFILTER > 0
	if (ifp->if_bpf)
		bpf_mtap(ifp->if_bpf, m0);
#endif

	s = splimp();
	if (IF_QFULL(&ifp->if_snd)) {
		IF_DROP(&ifp->if_snd);
		m_freem(m0);
		splx(s);
		ifp->if_collisions++;
		return (ENOBUFS);
	}
	IF_ENQUEUE(&ifp->if_snd, m0);

	ifp->if_opackets++;
	ifp->if_obytes += m0->m_pkthdr.len + sizeof(*af);
	splx(s);

	if (tp->tun_flags & TUN_RWAIT) {
		tp->tun_flags &= ~TUN_RWAIT;
		wakeup((caddr_t)tp);
	}
	if (tp->tun_flags & TUN_ASYNC && tp->tun_pgid)
		csignal(tp->tun_pgid, SIGIO,
		    tp->tun_siguid, tp->tun_sigeuid);
	selwakeup(&tp->tun_rsel);
	return 0;
}

/*
 * the cdevsw interface is now pretty minimal.
 */
int
tunioctl(dev, cmd, data, flag, p)
	dev_t		dev;
	u_long		cmd;
	caddr_t		data;
	int		flag;
	struct proc	*p;
{
	int		unit, s;
	struct tun_softc *tp;
	struct tuninfo *tunp;

	if ((unit = minor(dev)) >= ntun)
		return (ENXIO);

	tp = &tunctl[unit];

	s = splimp();
	switch (cmd) {
	case TUNSIFINFO:
		tunp = (struct tuninfo *)data;
		tp->tun_if.if_mtu = tunp->mtu;
		tp->tun_if.if_type = tunp->type;
		tp->tun_if.if_flags = tunp->flags;
		tp->tun_if.if_baudrate = tunp->baudrate;
		break;
	case TUNGIFINFO:
		tunp = (struct tuninfo *)data;
		tunp->mtu = tp->tun_if.if_mtu;
		tunp->type = tp->tun_if.if_type;
		tunp->flags = tp->tun_if.if_flags;
		tunp->baudrate = tp->tun_if.if_baudrate;
		break;
#ifdef TUN_DEBUG
	case TUNSDEBUG:
		tundebug = *(int *)data;
		break;
	case TUNGDEBUG:
		*(int *)data = tundebug;
		break;
#endif
        case TUNSIFMODE:
	        switch (*(int *)data & (IFF_POINTOPOINT|IFF_BROADCAST)) {
                case IFF_POINTOPOINT:
                case IFF_BROADCAST:
                        if (tp->tun_if.if_flags & IFF_UP) {
                                splx(s);
                                return (EBUSY);
                        }
                        tp->tun_if.if_flags &=
                                ~(IFF_BROADCAST|IFF_POINTOPOINT|IFF_MULTICAST);
                        tp->tun_if.if_flags |= *(int *)data;
                        break;
                default:
		        splx(s);
                        return (EINVAL);
                }
                break;

       	case FIONBIO:
		if (*(int *)data)
			tp->tun_flags |= TUN_NBIO;
		else
			tp->tun_flags &= ~TUN_NBIO;
		break;
	case FIOASYNC:
		if (*(int *)data)
			tp->tun_flags |= TUN_ASYNC;
		else
			tp->tun_flags &= ~TUN_ASYNC;
		break;
	case FIONREAD:
		if (tp->tun_if.if_snd.ifq_head)
			*(int *)data = tp->tun_if.if_snd.ifq_head->m_pkthdr.len;
		else	
			*(int *)data = 0;
		break;
	case TIOCSPGRP:
		tp->tun_pgid = *(int *)data;
		tp->tun_siguid = p->p_cred->p_ruid;
		tp->tun_sigeuid = p->p_ucred->cr_uid;
		break;
	case TIOCGPGRP:
		*(int *)data = tp->tun_pgid;
		break;
	default:
		splx(s);
		return (ENOTTY);
	}
	splx(s);
	return (0);
}

/*
 * The cdevsw read interface - reads a packet at a time, or at
 * least as much of a packet as can be read.
 */
int
tunread(dev, uio, ioflag)
	dev_t		dev;
	struct uio	*uio;
	int		ioflag;
{
	int		unit;
	struct tun_softc *tp;
	struct ifnet	*ifp;
	struct mbuf	*m, *m0;
	int		error = 0, len, s;

	if ((unit = minor(dev)) >= ntun)
		return (ENXIO);

	tp = &tunctl[unit];
	ifp = &tp->tun_if;
	TUNDEBUG(("%s: read\n", ifp->if_xname));
	if ((tp->tun_flags & TUN_READY) != TUN_READY) {
		TUNDEBUG(("%s: not ready 0%o\n", ifp->if_xname,
			  tp->tun_flags));
		return EHOSTDOWN;
	}

	tp->tun_flags &= ~TUN_RWAIT;

	s = splimp();
	do {
		while ((tp->tun_flags & TUN_READY) != TUN_READY)
			if ((error = tsleep((caddr_t)tp,
			    (PZERO+1)|PCATCH, "tunread", 0)) != 0) {
				splx(s);
				return (error);
			}
		IF_DEQUEUE(&ifp->if_snd, m0);
		if (m0 == 0) {
			if (tp->tun_flags & TUN_NBIO && ioflag & IO_NDELAY) {
				splx(s);
				return EWOULDBLOCK;
			}
			tp->tun_flags |= TUN_RWAIT;
			if ((error = tsleep((caddr_t)tp,
			    (PZERO + 1)|PCATCH, "tunread", 0)) != 0) {
				splx(s);
				return (error);
			}
		}
	} while (m0 == 0);
	splx(s);

	while (m0 && uio->uio_resid > 0 && error == 0) {
		len = min(uio->uio_resid, m0->m_len);
		if (len == 0)
			break;
		error = uiomove(mtod(m0, caddr_t), len, uio);
		MFREE(m0, m);
		m0 = m;
	}

	if (m0) {
		TUNDEBUG(("Dropping mbuf\n"));
		m_freem(m0);
	}
	if (error)
		ifp->if_ierrors++;

	return error;
}

/*
 * the cdevsw write interface - an atomic write is a packet - or else!
 */
int
tunwrite(dev, uio, ioflag)
	dev_t		dev;
	struct uio	*uio;
	int		ioflag;
{
	int		unit;
	struct ifnet	*ifp;
	struct ifqueue	*ifq;
	u_int32_t	*th;
	struct mbuf	*top, **mp, *m;
	int		isr;
	int		error=0, s, tlen, mlen;

	if ((unit = minor(dev)) >= ntun)
		return (ENXIO);

	ifp = &tunctl[unit].tun_if;
	TUNDEBUG(("%s: tunwrite\n", ifp->if_xname));

	if (uio->uio_resid == 0 || uio->uio_resid > TUNMRU) {
		TUNDEBUG(("%s: len=%d!\n", ifp->if_xname, uio->uio_resid));
		return EMSGSIZE;
	}
	tlen = uio->uio_resid;

	/* get a header mbuf */
	MGETHDR(m, M_DONTWAIT, MT_DATA);
	if (m == NULL)
		return ENOBUFS;
	mlen = MHLEN;

	top = 0;
	mp = &top;
	while (error == 0 && uio->uio_resid > 0) {
		m->m_len = min(mlen, uio->uio_resid);
		error = uiomove(mtod (m, caddr_t), m->m_len, uio);
		*mp = m;
		mp = &m->m_next;
		if (uio->uio_resid > 0) {
			MGET (m, M_DONTWAIT, MT_DATA);
			if (m == 0) {
				error = ENOBUFS;
				break;
			}
			mlen = MLEN;
		}
	}
	if (error) {
		if (top)
			m_freem (top);
		ifp->if_ierrors++;
		return error;
	}

	top->m_pkthdr.len = tlen;
	top->m_pkthdr.rcvif = ifp;

#if NBPFILTER > 0
	if (ifp->if_bpf)
		bpf_mtap(ifp->if_bpf, top);
#endif

	th = mtod(top, u_int32_t *);
	/* strip the tunnel header */
	top->m_data += sizeof(*th);
	top->m_len  -= sizeof(*th);
	top->m_pkthdr.len -= sizeof(*th);

	switch (ntohl(*th)) {
#ifdef INET
	case AF_INET:
		ifq = &ipintrq;
		isr = NETISR_IP;
		break;
#endif
#ifdef INET6
	case AF_INET6:
		ifq = &ip6intrq;
		isr = NETISR_IPV6;
		break;
#endif
#ifdef NS
	case AF_NS:
		ifq = &nsintrq;
		isr = NETISR_NS;
		break;
#endif
#ifdef IPX
	case AF_IPX:
		ifq = &ipxintrq;
		isr = NETISR_IPX;
		break;
#endif
#ifdef NETATALK
	case AF_APPLETALK:
		ifq = &atintrq2;
		isr = NETISR_ATALK;
		break;
#endif
#ifdef ISO
	case AF_ISO:
		ifq = &clnlintrq;
		isr = NETISR_ISO;
		break;
#endif
	default:
		m_freem(top);
		return EAFNOSUPPORT;
	}

	s = splimp();
	if (IF_QFULL(ifq)) {
		IF_DROP(ifq);
		splx(s);
		ifp->if_collisions++;
		m_freem(top);
		return ENOBUFS;
	}
	IF_ENQUEUE(ifq, top);
	schednetisr(isr);
	ifp->if_ipackets++;
	ifp->if_ibytes += top->m_pkthdr.len;
	splx(s);
	return error;
}

/*
 * tunselect - the select interface, this is only useful on reads
 * really. The write detect always returns true, write never blocks
 * anyway, it either accepts the packet or drops it.
 */
int
tunselect(dev, rw, p)
	dev_t		dev;
	int		rw;
	struct proc	*p;
{
	int		unit, s;
	struct tun_softc *tp;
	struct ifnet	*ifp;

	if ((unit = minor(dev)) >= ntun)
		return (ENXIO);

	tp = &tunctl[unit];
	ifp = &tp->tun_if;
	s = splimp();
	TUNDEBUG(("%s: tunselect\n", ifp->if_xname));

	switch (rw) {
	case FREAD:
		if (ifp->if_snd.ifq_len > 0) {
			splx(s);
			TUNDEBUG(("%s: tunselect q=%d\n", ifp->if_xname,
				  ifp->if_snd.ifq_len));
			return 1;
		}
		selrecord(curproc, &tp->tun_rsel);
		break;
	case FWRITE:
		splx(s);
		return 1;
	}
	splx(s);
	TUNDEBUG(("%s: tunselect waiting\n", ifp->if_xname));
	return 0;
}